diff options
1516 files changed, 33785 insertions, 17060 deletions
diff --git a/.gitignore b/.gitignore index 7e9932e55475..42fa0d5626a9 100644 --- a/.gitignore +++ b/.gitignore @@ -92,3 +92,6 @@ extra_certificates signing_key.priv signing_key.x509 x509.genkey + +# Kconfig presets +all.config diff --git a/Documentation/00-INDEX b/Documentation/00-INDEX index 38f8444bdd0e..07de7e19b4ce 100644 --- a/Documentation/00-INDEX +++ b/Documentation/00-INDEX @@ -29,6 +29,8 @@ DMA-ISA-LPC.txt - How to do DMA with ISA (and LPC) devices. DMA-attributes.txt - listing of the various possible attributes a DMA region can have +dmatest.txt + - how to compile, configure and use the dmatest system. DocBook/ - directory with DocBook templates etc. for kernel documentation. EDID/ @@ -77,6 +79,8 @@ arm/ - directory with info about Linux on the ARM architecture. arm64/ - directory with info about Linux on the 64 bit ARM architecture. +assoc_array.txt + - generic associative array intro. atomic_ops.txt - semantics and behavior of atomic and bitmask operations. auxdisplay/ @@ -87,6 +91,8 @@ bad_memory.txt - how to use kernel parameters to exclude bad RAM regions. basic_profiling.txt - basic instructions for those who wants to profile Linux kernel. +bcache.txt + - Block-layer cache on fast SSDs to improve slow (raid) I/O performance. binfmt_misc.txt - info on the kernel support for extra binary formats. blackfin/ @@ -171,6 +177,8 @@ early-userspace/ - info about initramfs, klibc, and userspace early during boot. edac.txt - information on EDAC - Error Detection And Correction +efi-stub.txt + - How to use the EFI boot stub to bypass GRUB or elilo on EFI systems. eisa.txt - info on EISA bus support. email-clients.txt @@ -195,8 +203,8 @@ futex-requeue-pi.txt - info on requeueing of tasks from a non-PI futex to a PI futex gcov.txt - use of GCC's coverage testing tool "gcov" with the Linux kernel -gpio.txt - - overview of GPIO (General Purpose Input/Output) access conventions. +gpio/ + - gpio related documentation hid/ - directory with information on human interface devices highuid.txt @@ -255,6 +263,8 @@ kernel-docs.txt - listing of various WWW + books that document kernel internals. kernel-parameters.txt - summary listing of command line / boot prompt args for the kernel. +kernel-per-CPU-kthreads.txt + - List of all per-CPU kthreads and how they introduce jitter. kmemcheck.txt - info on dynamic checker that detects uses of uninitialized memory. kmemleak.txt @@ -299,8 +309,6 @@ memory-devices/ - directory with info on parts like the Texas Instruments EMIF driver memory-hotplug.txt - Hotpluggable memory support, how to use and current status. -memory.txt - - info on typical Linux memory problems. metag/ - directory with info about Linux on Meta architecture. mips/ @@ -311,6 +319,8 @@ mmc/ - directory with info about the MMC subsystem mn10300/ - directory with info about the mn10300 architecture port +module-signing.txt + - Kernel module signing for increased security when loading modules. mtd/ - directory with info about memory technology devices (flash) mono.txt @@ -343,6 +353,8 @@ pcmcia/ - info on the Linux PCMCIA driver. percpu-rw-semaphore.txt - RCU based read-write semaphore optimized for locking for reading +phy.txt + - Description of the generic PHY framework. pi-futex.txt - documentation on lightweight priority inheritance futexes. pinctrl.txt @@ -431,6 +443,8 @@ sysrq.txt - info on the magic SysRq key. target/ - directory with info on generating TCM v4 fabric .ko modules +this_cpu_ops.txt + - List rationale behind and the way to use this_cpu operations. thermal/ - directory with information on managing thermal issues (CPU/temp) trace/ @@ -469,6 +483,8 @@ wimax/ - directory with info about Intel Wireless Wimax Connections workqueue.txt - information on the Concurrency Managed Workqueue implementation +ww-mutex-design.txt + - Intro to Mutex wait/would deadlock handling.s x86/x86_64/ - directory with info on Linux support for AMD x86-64 (Hammer) machines. xtensa/ diff --git a/Documentation/ABI/testing/sysfs-bus-mdio b/Documentation/ABI/testing/sysfs-bus-mdio index 6349749ebc29..491baaf4285f 100644 --- a/Documentation/ABI/testing/sysfs-bus-mdio +++ b/Documentation/ABI/testing/sysfs-bus-mdio @@ -7,3 +7,23 @@ Description: by the device during bus enumeration, encoded in hexadecimal. This ID is used to match the device with the appropriate driver. + +What: /sys/bus/mdio_bus/devices/.../phy_interface +Date: February 2014 +KernelVersion: 3.15 +Contact: netdev@vger.kernel.org +Description: + This attribute contains the PHY interface as configured by the + Ethernet driver during bus enumeration, encoded in string. + This interface mode is used to configure the Ethernet MAC with the + appropriate mode for its data lines to the PHY hardware. + +What: /sys/bus/mdio_bus/devices/.../phy_has_fixups +Date: February 2014 +KernelVersion: 3.15 +Contact: netdev@vger.kernel.org +Description: + This attribute contains the boolean value whether a given PHY + device has had any "fixup" workaround running on it, encoded as + a boolean. This information is provided to help troubleshooting + PHY configurations. diff --git a/Documentation/PCI/MSI-HOWTO.txt b/Documentation/PCI/MSI-HOWTO.txt index a8d01005f480..10a93696e55a 100644 --- a/Documentation/PCI/MSI-HOWTO.txt +++ b/Documentation/PCI/MSI-HOWTO.txt @@ -82,7 +82,19 @@ Most of the hard work is done for the driver in the PCI layer. It simply has to request that the PCI layer set up the MSI capability for this device. -4.2.1 pci_enable_msi_range +4.2.1 pci_enable_msi + +int pci_enable_msi(struct pci_dev *dev) + +A successful call allocates ONE interrupt to the device, regardless +of how many MSIs the device supports. The device is switched from +pin-based interrupt mode to MSI mode. The dev->irq number is changed +to a new number which represents the message signaled interrupt; +consequently, this function should be called before the driver calls +request_irq(), because an MSI is delivered via a vector that is +different from the vector of a pin-based interrupt. + +4.2.2 pci_enable_msi_range int pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec) @@ -147,6 +159,11 @@ static int foo_driver_enable_msi(struct pci_dev *pdev, int nvec) return pci_enable_msi_range(pdev, nvec, nvec); } +Note, unlike pci_enable_msi_exact() function, which could be also used to +enable a particular number of MSI-X interrupts, pci_enable_msi_range() +returns either a negative errno or 'nvec' (not negative errno or 0 - as +pci_enable_msi_exact() does). + 4.2.1.3 Single MSI mode The most notorious example of the request type described above is @@ -158,7 +175,27 @@ static int foo_driver_enable_single_msi(struct pci_dev *pdev) return pci_enable_msi_range(pdev, 1, 1); } -4.2.2 pci_disable_msi +Note, unlike pci_enable_msi() function, which could be also used to +enable the single MSI mode, pci_enable_msi_range() returns either a +negative errno or 1 (not negative errno or 0 - as pci_enable_msi() +does). + +4.2.3 pci_enable_msi_exact + +int pci_enable_msi_exact(struct pci_dev *dev, int nvec) + +This variation on pci_enable_msi_range() call allows a device driver to +request exactly 'nvec' MSIs. + +If this function returns a negative number, it indicates an error and +the driver should not attempt to request any more MSI interrupts for +this device. + +By contrast with pci_enable_msi_range() function, pci_enable_msi_exact() +returns zero in case of success, which indicates MSI interrupts have been +successfully allocated. + +4.2.4 pci_disable_msi void pci_disable_msi(struct pci_dev *dev) @@ -172,7 +209,7 @@ on any interrupt for which it previously called request_irq(). Failure to do so results in a BUG_ON(), leaving the device with MSI enabled and thus leaking its vector. -4.2.3 pci_msi_vec_count +4.2.4 pci_msi_vec_count int pci_msi_vec_count(struct pci_dev *dev) @@ -257,8 +294,8 @@ possible, likely up to the limit returned by pci_msix_vec_count() function: static int foo_driver_enable_msix(struct foo_adapter *adapter, int nvec) { - return pci_enable_msi_range(adapter->pdev, adapter->msix_entries, - 1, nvec); + return pci_enable_msix_range(adapter->pdev, adapter->msix_entries, + 1, nvec); } Note the value of 'minvec' parameter is 1. As 'minvec' is inclusive, @@ -269,8 +306,8 @@ In this case the function could look like this: static int foo_driver_enable_msix(struct foo_adapter *adapter, int nvec) { - return pci_enable_msi_range(adapter->pdev, adapter->msix_entries, - FOO_DRIVER_MINIMUM_NVEC, nvec); + return pci_enable_msix_range(adapter->pdev, adapter->msix_entries, + FOO_DRIVER_MINIMUM_NVEC, nvec); } 4.3.1.2 Exact number of MSI-X interrupts @@ -282,10 +319,15 @@ parameters: static int foo_driver_enable_msix(struct foo_adapter *adapter, int nvec) { - return pci_enable_msi_range(adapter->pdev, adapter->msix_entries, - nvec, nvec); + return pci_enable_msix_range(adapter->pdev, adapter->msix_entries, + nvec, nvec); } +Note, unlike pci_enable_msix_exact() function, which could be also used to +enable a particular number of MSI-X interrupts, pci_enable_msix_range() +returns either a negative errno or 'nvec' (not negative errno or 0 - as +pci_enable_msix_exact() does). + 4.3.1.3 Specific requirements to the number of MSI-X interrupts As noted above, there could be devices that can not operate with just any @@ -332,7 +374,64 @@ Note how pci_enable_msix_range() return value is analized for a fallback - any error code other than -ENOSPC indicates a fatal error and should not be retried. -4.3.2 pci_disable_msix +4.3.2 pci_enable_msix_exact + +int pci_enable_msix_exact(struct pci_dev *dev, + struct msix_entry *entries, int nvec) + +This variation on pci_enable_msix_range() call allows a device driver to +request exactly 'nvec' MSI-Xs. + +If this function returns a negative number, it indicates an error and +the driver should not attempt to allocate any more MSI-X interrupts for +this device. + +By contrast with pci_enable_msix_range() function, pci_enable_msix_exact() +returns zero in case of success, which indicates MSI-X interrupts have been +successfully allocated. + +Another version of a routine that enables MSI-X mode for a device with +specific requirements described in chapter 4.3.1.3 might look like this: + +/* + * Assume 'minvec' and 'maxvec' are non-zero + */ +static int foo_driver_enable_msix(struct foo_adapter *adapter, + int minvec, int maxvec) +{ + int rc; + + minvec = roundup_pow_of_two(minvec); + maxvec = rounddown_pow_of_two(maxvec); + + if (minvec > maxvec) + return -ERANGE; + +retry: + rc = pci_enable_msix_exact(adapter->pdev, + adapter->msix_entries, maxvec); + + /* + * -ENOSPC is the only error code allowed to be analyzed + */ + if (rc == -ENOSPC) { + if (maxvec == 1) + return -ENOSPC; + + maxvec /= 2; + + if (minvec > maxvec) + return -ENOSPC; + + goto retry; + } else if (rc < 0) { + return rc; + } + + return maxvec; +} + +4.3.3 pci_disable_msix void pci_disable_msix(struct pci_dev *dev) diff --git a/Documentation/RCU/00-INDEX b/Documentation/RCU/00-INDEX index 1d7a885761f5..fa57139f50bf 100644 --- a/Documentation/RCU/00-INDEX +++ b/Documentation/RCU/00-INDEX @@ -8,6 +8,8 @@ listRCU.txt - Using RCU to Protect Read-Mostly Linked Lists lockdep.txt - RCU and lockdep checking +lockdep-splat.txt + - RCU Lockdep splats explained. NMI-RCU.txt - Using RCU to Protect Dynamic NMI Handlers rcubarrier.txt diff --git a/Documentation/arm/00-INDEX b/Documentation/arm/00-INDEX index 36420e116c90..a94090cc785d 100644 --- a/Documentation/arm/00-INDEX +++ b/Documentation/arm/00-INDEX @@ -4,6 +4,8 @@ Booting - requirements for booting Interrupts - ARM Interrupt subsystem documentation +IXP4xx + - Intel IXP4xx Network processor. msm - MSM specific documentation Netwinder @@ -24,8 +26,16 @@ SPEAr - ST SPEAr platform Linux Overview VFP/ - Release notes for Linux Kernel Vector Floating Point support code +cluster-pm-race-avoidance.txt + - Algorithm for CPU and Cluster setup/teardown empeg/ - Ltd's Empeg MP3 Car Audio Player +firmware.txt + - Secure firmware registration and calling. +kernel_mode_neon.txt + - How to use NEON instructions in kernel mode +kernel_user_helpers.txt + - Helper functions in kernel space made available for userspace. mem_alignment - alignment abort handler documentation memory.txt @@ -34,3 +44,7 @@ nwfpe/ - NWFPE floating point emulator documentation swp_emulation - SWP/SWPB emulation handler/logging description +tcm.txt + - ARM Tightly Coupled Memory +vlocks.txt + - Voting locks, low-level mechanism relying on memory system atomic writes. diff --git a/Documentation/blackfin/00-INDEX b/Documentation/blackfin/00-INDEX index 2df0365f2dff..c54fcdd4ae9f 100644 --- a/Documentation/blackfin/00-INDEX +++ b/Documentation/blackfin/00-INDEX @@ -1,8 +1,10 @@ 00-INDEX - This file - +Makefile + - Makefile for gptimers example file. bfin-gpio-notes.txt - Notes in developing/using bfin-gpio driver. - bfin-spi-notes.txt - Notes for using bfin spi bus driver. +gptimers-example.c + - gptimers example diff --git a/Documentation/block/00-INDEX b/Documentation/block/00-INDEX index 929d9904f74b..e840b47613f7 100644 --- a/Documentation/block/00-INDEX +++ b/Documentation/block/00-INDEX @@ -14,6 +14,8 @@ deadline-iosched.txt - Deadline IO scheduler tunables ioprio.txt - Block io priorities (in CFQ scheduler) +null_blk.txt + - Null block for block-layer benchmarking. queue-sysfs.txt - Queue's sysfs entries request.txt diff --git a/Documentation/devicetree/00-INDEX b/Documentation/devicetree/00-INDEX index b78f691fd847..8c4102c6a5e7 100644 --- a/Documentation/devicetree/00-INDEX +++ b/Documentation/devicetree/00-INDEX @@ -8,3 +8,5 @@ https://lists.ozlabs.org/listinfo/devicetree-discuss - this file booting-without-of.txt - Booting Linux without Open Firmware, describes history and format of device trees. +usage-model.txt + - How Linux uses DT and what DT aims to solve.
\ No newline at end of file diff --git a/Documentation/devicetree/bindings/arm/omap/omap.txt b/Documentation/devicetree/bindings/arm/omap/omap.txt index 34dc40cffdfd..af9b4a0d902b 100644 --- a/Documentation/devicetree/bindings/arm/omap/omap.txt +++ b/Documentation/devicetree/bindings/arm/omap/omap.txt @@ -91,7 +91,7 @@ Boards: compatible = "ti,omap3-beagle", "ti,omap3" - OMAP3 Tobi with Overo : Commercial expansion board with daughter board - compatible = "ti,omap3-tobi", "ti,omap3-overo", "ti,omap3" + compatible = "gumstix,omap3-overo-tobi", "gumstix,omap3-overo", "ti,omap3" - OMAP4 SDP : Software Development Board compatible = "ti,omap4-sdp", "ti,omap4430" diff --git a/Documentation/devicetree/bindings/clock/renesas,cpg-mstp-clocks.txt b/Documentation/devicetree/bindings/clock/renesas,cpg-mstp-clocks.txt index a6a352c2771e..5992dceec7af 100644 --- a/Documentation/devicetree/bindings/clock/renesas,cpg-mstp-clocks.txt +++ b/Documentation/devicetree/bindings/clock/renesas,cpg-mstp-clocks.txt @@ -21,9 +21,9 @@ Required Properties: must appear in the same order as the output clocks. - #clock-cells: Must be 1 - clock-output-names: The name of the clocks as free-form strings - - renesas,indices: Indices of the gate clocks into the group (0 to 31) + - renesas,clock-indices: Indices of the gate clocks into the group (0 to 31) -The clocks, clock-output-names and renesas,indices properties contain one +The clocks, clock-output-names and renesas,clock-indices properties contain one entry per gate clock. The MSTP groups are sparsely populated. Unimplemented gate clocks must not be declared. diff --git a/Documentation/devicetree/bindings/dma/fsl-imx-sdma.txt b/Documentation/devicetree/bindings/dma/fsl-imx-sdma.txt index 68b83ecc3850..ee9be9961524 100644 --- a/Documentation/devicetree/bindings/dma/fsl-imx-sdma.txt +++ b/Documentation/devicetree/bindings/dma/fsl-imx-sdma.txt @@ -1,12 +1,16 @@ * Freescale Smart Direct Memory Access (SDMA) Controller for i.MX Required properties: -- compatible : Should be "fsl,imx31-sdma", "fsl,imx31-to1-sdma", - "fsl,imx31-to2-sdma", "fsl,imx35-sdma", "fsl,imx35-to1-sdma", - "fsl,imx35-to2-sdma", "fsl,imx51-sdma", "fsl,imx53-sdma" or - "fsl,imx6q-sdma". The -to variants should be preferred since they - allow to determnine the correct ROM script addresses needed for - the driver to work without additional firmware. +- compatible : Should be one of + "fsl,imx25-sdma" + "fsl,imx31-sdma", "fsl,imx31-to1-sdma", "fsl,imx31-to2-sdma" + "fsl,imx35-sdma", "fsl,imx35-to1-sdma", "fsl,imx35-to2-sdma" + "fsl,imx51-sdma" + "fsl,imx53-sdma" + "fsl,imx6q-sdma" + The -to variants should be preferred since they allow to determnine the + correct ROM script addresses needed for the driver to work without additional + firmware. - reg : Should contain SDMA registers location and length - interrupts : Should contain SDMA interrupt - #dma-cells : Must be <3>. diff --git a/Documentation/devicetree/bindings/mmc/atmel-hsmci.txt b/Documentation/devicetree/bindings/mmc/atmel-hsmci.txt index 0a85c70cd30a..07ad02075a93 100644 --- a/Documentation/devicetree/bindings/mmc/atmel-hsmci.txt +++ b/Documentation/devicetree/bindings/mmc/atmel-hsmci.txt @@ -13,6 +13,9 @@ Required properties: - #address-cells: should be one. The cell is the slot id. - #size-cells: should be zero. - at least one slot node +- clock-names: tuple listing input clock names. + Required elements: "mci_clk" +- clocks: phandles to input clocks. The node contains child nodes for each slot that the platform uses @@ -24,6 +27,8 @@ mmc0: mmc@f0008000 { interrupts = <12 4>; #address-cells = <1>; #size-cells = <0>; + clock-names = "mci_clk"; + clocks = <&mci0_clk>; [ child node definitions...] }; diff --git a/Documentation/devicetree/bindings/net/allwinner,sun4i-emac.txt b/Documentation/devicetree/bindings/net/allwinner,sun4i-emac.txt index b90bfcd138ff..10640b17c866 100644 --- a/Documentation/devicetree/bindings/net/allwinner,sun4i-emac.txt +++ b/Documentation/devicetree/bindings/net/allwinner,sun4i-emac.txt @@ -1,20 +1,17 @@ * Allwinner EMAC ethernet controller Required properties: -- compatible: should be "allwinner,sun4i-emac". +- compatible: should be "allwinner,sun4i-a10-emac" (Deprecated: + "allwinner,sun4i-emac") - reg: address and length of the register set for the device. - interrupts: interrupt for the device -- phy: A phandle to a phy node defining the PHY address (as the reg - property, a single integer). +- phy: see ethernet.txt file in the same directory. - clocks: A phandle to the reference clock for this device -Optional properties: -- (local-)mac-address: mac address to be used by this driver - Example: emac: ethernet@01c0b000 { - compatible = "allwinner,sun4i-emac"; + compatible = "allwinner,sun4i-a10-emac"; reg = <0x01c0b000 0x1000>; interrupts = <55>; clocks = <&ahb_gates 17>; diff --git a/Documentation/devicetree/bindings/net/allwinner,sun4i-mdio.txt b/Documentation/devicetree/bindings/net/allwinner,sun4i-mdio.txt index 00b9f9a3ec1d..4ec56413779d 100644 --- a/Documentation/devicetree/bindings/net/allwinner,sun4i-mdio.txt +++ b/Documentation/devicetree/bindings/net/allwinner,sun4i-mdio.txt @@ -1,7 +1,8 @@ * Allwinner A10 MDIO Ethernet Controller interface Required properties: -- compatible: should be "allwinner,sun4i-mdio". +- compatible: should be "allwinner,sun4i-a10-mdio" + (Deprecated: "allwinner,sun4i-mdio"). - reg: address and length of the register set for the device. Optional properties: @@ -9,7 +10,7 @@ Optional properties: Example at the SoC level: mdio@01c0b080 { - compatible = "allwinner,sun4i-mdio"; + compatible = "allwinner,sun4i-a10-mdio"; reg = <0x01c0b080 0x14>; #address-cells = <1>; #size-cells = <0>; diff --git a/Documentation/devicetree/bindings/net/arc_emac.txt b/Documentation/devicetree/bindings/net/arc_emac.txt index bcbc3f009158..7fbb027218a1 100644 --- a/Documentation/devicetree/bindings/net/arc_emac.txt +++ b/Documentation/devicetree/bindings/net/arc_emac.txt @@ -6,19 +6,12 @@ Required properties: - interrupts: Should contain the EMAC interrupts - clock-frequency: CPU frequency. It is needed to calculate and set polling period of EMAC. -- max-speed: Maximum supported data-rate in Mbit/s. In some HW configurations -bandwidth of external memory controller might be a limiting factor. That's why -it's required to specify which data-rate is supported on current SoC or FPGA. -For example if only 10 Mbit/s is supported (10BASE-T) set "10". If 100 Mbit/s is -supported (100BASE-TX) set "100". -- phy: PHY device attached to the EMAC via MDIO bus +- max-speed: see ethernet.txt file in the same directory. +- phy: see ethernet.txt file in the same directory. Child nodes of the driver are the individual PHY devices connected to the MDIO bus. They must have a "reg" property given the PHY address on the MDIO bus. -Optional properties: -- mac-address: 6 bytes, mac address - Examples: ethernet@c0fc2000 { diff --git a/Documentation/devicetree/bindings/net/broadcom-bcmgenet.txt b/Documentation/devicetree/bindings/net/broadcom-bcmgenet.txt new file mode 100644 index 000000000000..f2febb94550e --- /dev/null +++ b/Documentation/devicetree/bindings/net/broadcom-bcmgenet.txt @@ -0,0 +1,121 @@ +* Broadcom BCM7xxx Ethernet Controller (GENET) + +Required properties: +- compatible: should contain one of "brcm,genet-v1", "brcm,genet-v2", + "brcm,genet-v3", "brcm,genet-v4". +- reg: address and length of the register set for the device +- interrupts: must be two cells, the first cell is the general purpose + interrupt line, while the second cell is the interrupt for the ring + RX and TX queues operating in ring mode +- phy-mode: see ethernet.txt file in the same directory +- #address-cells: should be 1 +- #size-cells: should be 1 + +Optional properties: +- clocks: When provided, must be two phandles to the functional clocks nodes + of the GENET block. The first phandle is the main GENET clock used during + normal operation, while the second phandle is the Wake-on-LAN clock. +- clock-names: When provided, names of the functional clock phandles, first + name should be "enet" and second should be "enet-wol". + +- phy-handle: See ethernet.txt file in the same directory; used to describe + configurations where a PHY (internal or external) is used. + +- fixed-link: When the GENET interface is connected to a MoCA hardware block or + when operating in a RGMII to RGMII type of connection, or when the MDIO bus is + voluntarily disabled, this property should be used to describe the "fixed link". + See Documentation/devicetree/bindings/net/fsl-tsec-phy.txt for information on + the property specifics + +Required child nodes: + +- mdio bus node: this node should always be present regarless of the PHY + configuration of the GENET instance + +MDIO bus node required properties: + +- compatible: should contain one of "brcm,genet-mdio-v1", "brcm,genet-mdio-v2" + "brcm,genet-mdio-v3", "brcm,genet-mdio-v4", the version has to match the + parent node compatible property (e.g: brcm,genet-v4 pairs with + brcm,genet-mdio-v4) +- reg: address and length relative to the parent node base register address +- #address-cells: address cell for MDIO bus addressing, should be 1 +- #size-cells: size of the cells for MDIO bus addressing, should be 0 + +Ethernet PHY node properties: + +See Documentation/devicetree/bindings/net/phy.txt for the list of required and +optional properties. + +Internal Gigabit PHY example: + +ethernet@f0b60000 { + phy-mode = "internal"; + phy-handle = <&phy1>; + mac-address = [ 00 10 18 36 23 1a ]; + compatible = "brcm,genet-v4"; + #address-cells = <0x1>; + #size-cells = <0x1>; + reg = <0xf0b60000 0xfc4c>; + interrupts = <0x0 0x14 0x0>, <0x0 0x15 0x0>; + + mdio@e14 { + compatible = "brcm,genet-mdio-v4"; + #address-cells = <0x1>; + #size-cells = <0x0>; + reg = <0xe14 0x8>; + + phy1: ethernet-phy@1 { + max-speed = <1000>; + reg = <0x1>; + compatible = "brcm,28nm-gphy", "ethernet-phy-ieee802.3-c22"; + }; + }; +}; + +MoCA interface / MAC to MAC example: + +ethernet@f0b80000 { + phy-mode = "moca"; + fixed-link = <1 0 1000 0 0>; + mac-address = [ 00 10 18 36 24 1a ]; + compatible = "brcm,genet-v4"; + #address-cells = <0x1>; + #size-cells = <0x1>; + reg = <0xf0b80000 0xfc4c>; + interrupts = <0x0 0x16 0x0>, <0x0 0x17 0x0>; + + mdio@e14 { + compatible = "brcm,genet-mdio-v4"; + #address-cells = <0x1>; + #size-cells = <0x0>; + reg = <0xe14 0x8>; + }; +}; + + +External MDIO-connected Gigabit PHY/switch: + +ethernet@f0ba0000 { + phy-mode = "rgmii"; + phy-handle = <&phy0>; + mac-address = [ 00 10 18 36 26 1a ]; + compatible = "brcm,genet-v4"; + #address-cells = <0x1>; + #size-cells = <0x1>; + reg = <0xf0ba0000 0xfc4c>; + interrupts = <0x0 0x18 0x0>, <0x0 0x19 0x0>; + + mdio@0e14 { + compatible = "brcm,genet-mdio-v4"; + #address-cells = <0x1>; + #size-cells = <0x0>; + reg = <0xe14 0x8>; + + phy0: ethernet-phy@0 { + max-speed = <1000>; + reg = <0x0>; + compatible = "brcm,bcm53125", "ethernet-phy-ieee802.3-c22"; + }; + }; +}; diff --git a/Documentation/devicetree/bindings/net/can/sja1000.txt b/Documentation/devicetree/bindings/net/can/sja1000.txt index f2105a47ec87..b4a6d53fb01a 100644 --- a/Documentation/devicetree/bindings/net/can/sja1000.txt +++ b/Documentation/devicetree/bindings/net/can/sja1000.txt @@ -12,6 +12,10 @@ Required properties: Optional properties: +- reg-io-width : Specify the size (in bytes) of the IO accesses that + should be performed on the device. Valid value is 1, 2 or 4. + Default to 1 (8 bits). + - nxp,external-clock-frequency : Frequency of the external oscillator clock in Hz. Note that the internal clock frequency used by the SJA1000 is half of that value. If not specified, a default value diff --git a/Documentation/devicetree/bindings/net/cavium-mix.txt b/Documentation/devicetree/bindings/net/cavium-mix.txt index 5da628db68bf..8d7c3096390f 100644 --- a/Documentation/devicetree/bindings/net/cavium-mix.txt +++ b/Documentation/devicetree/bindings/net/cavium-mix.txt @@ -18,12 +18,7 @@ Properties: - interrupts: Two interrupt specifiers. The first is the MIX interrupt routing and the second the routing for the AGL interrupts. -- mac-address: Optional, the MAC address to assign to the device. - -- local-mac-address: Optional, the MAC address to assign to the device - if mac-address is not specified. - -- phy-handle: Optional, a phandle for the PHY device connected to this device. +- phy-handle: Optional, see ethernet.txt file in the same directory. Example: ethernet@1070000100800 { diff --git a/Documentation/devicetree/bindings/net/cavium-pip.txt b/Documentation/devicetree/bindings/net/cavium-pip.txt index d4c53ba04b3b..7dbd158810d2 100644 --- a/Documentation/devicetree/bindings/net/cavium-pip.txt +++ b/Documentation/devicetree/bindings/net/cavium-pip.txt @@ -35,12 +35,7 @@ Properties for PIP port which is a child the PIP interface: - reg: The port number within the interface group. -- mac-address: Optional, the MAC address to assign to the device. - -- local-mac-address: Optional, the MAC address to assign to the device - if mac-address is not specified. - -- phy-handle: Optional, a phandle for the PHY device connected to this device. +- phy-handle: Optional, see ethernet.txt file in the same directory. Example: diff --git a/Documentation/devicetree/bindings/net/cdns-emac.txt b/Documentation/devicetree/bindings/net/cdns-emac.txt index 09055c2495f0..abd67c13d344 100644 --- a/Documentation/devicetree/bindings/net/cdns-emac.txt +++ b/Documentation/devicetree/bindings/net/cdns-emac.txt @@ -6,11 +6,7 @@ Required properties: or the generic form: "cdns,emac". - reg: Address and length of the register set for the device - interrupts: Should contain macb interrupt -- phy-mode: String, operation mode of the PHY interface. - Supported values are: "mii", "rmii". - -Optional properties: -- local-mac-address: 6 bytes, mac address +- phy-mode: see ethernet.txt file in the same directory. Examples: diff --git a/Documentation/devicetree/bindings/net/cpsw.txt b/Documentation/devicetree/bindings/net/cpsw.txt index 05d660e4ac64..ae2b8b7f9c38 100644 --- a/Documentation/devicetree/bindings/net/cpsw.txt +++ b/Documentation/devicetree/bindings/net/cpsw.txt @@ -28,9 +28,8 @@ Optional properties: Slave Properties: Required properties: - phy_id : Specifies slave phy id -- phy-mode : The interface between the SoC and the PHY (a string - that of_get_phy_mode() can understand) -- mac-address : Specifies slave MAC address +- phy-mode : See ethernet.txt file in the same directory +- mac-address : See ethernet.txt file in the same directory Optional properties: - dual_emac_res_vlan : Specifies VID to be used to segregate the ports diff --git a/Documentation/devicetree/bindings/net/davicom-dm9000.txt b/Documentation/devicetree/bindings/net/davicom-dm9000.txt index 2d39c990e641..28767ed7c1bd 100644 --- a/Documentation/devicetree/bindings/net/davicom-dm9000.txt +++ b/Documentation/devicetree/bindings/net/davicom-dm9000.txt @@ -9,8 +9,6 @@ Required properties: - interrupts : interrupt specifier specific to interrupt controller Optional properties: -- local-mac-address : A bytestring of 6 bytes specifying Ethernet MAC address - to use (from firmware or bootloader) - davicom,no-eeprom : Configuration EEPROM is not available - davicom,ext-phy : Use external PHY diff --git a/Documentation/devicetree/bindings/net/davinci_emac.txt b/Documentation/devicetree/bindings/net/davinci_emac.txt index 6e356d15154a..032808843f90 100644 --- a/Documentation/devicetree/bindings/net/davinci_emac.txt +++ b/Documentation/devicetree/bindings/net/davinci_emac.txt @@ -17,9 +17,8 @@ Required properties: Miscellaneous Interrupt> Optional properties: -- phy-handle: Contains a phandle to an Ethernet PHY. +- phy-handle: See ethernet.txt file in the same directory. If absent, davinci_emac driver defaults to 100/FULL. -- local-mac-address : 6 bytes, mac address - ti,davinci-rmii-en: 1 byte, 1 means use RMII - ti,davinci-no-bd-ram: boolean, does EMAC have BD RAM? diff --git a/Documentation/devicetree/bindings/net/ethernet.txt b/Documentation/devicetree/bindings/net/ethernet.txt new file mode 100644 index 000000000000..9ecd43d8792c --- /dev/null +++ b/Documentation/devicetree/bindings/net/ethernet.txt @@ -0,0 +1,25 @@ +The following properties are common to the Ethernet controllers: + +- local-mac-address: array of 6 bytes, specifies the MAC address that was + assigned to the network device; +- mac-address: array of 6 bytes, specifies the MAC address that was last used by + the boot program; should be used in cases where the MAC address assigned to + the device by the boot program is different from the "local-mac-address" + property; +- max-speed: number, specifies maximum speed in Mbit/s supported by the device; +- max-frame-size: number, maximum transfer unit (IEEE defined MTU), rather than + the maximum frame size (there's contradiction in ePAPR). +- phy-mode: string, operation mode of the PHY interface; supported values are + "mii", "gmii", "sgmii", "tbi", "rev-mii", "rmii", "rgmii", "rgmii-id", + "rgmii-rxid", "rgmii-txid", "rtbi", "smii", "xgmii"; this is now a de-facto + standard property; +- phy-connection-type: the same as "phy-mode" property but described in ePAPR; +- phy-handle: phandle, specifies a reference to a node representing a PHY + device; this property is described in ePAPR and so preferred; +- phy: the same as "phy-handle" property, not recommended for new bindings. +- phy-device: the same as "phy-handle" property, not recommended for new + bindings. + +Child nodes of the Ethernet controller are typically the individual PHY devices +connected via the MDIO bus (sometimes the MDIO bus controller is separate). +They are described in the phy.txt file in this same directory. diff --git a/Documentation/devicetree/bindings/net/fsl-fec.txt b/Documentation/devicetree/bindings/net/fsl-fec.txt index 845ff848d895..6bc84adb10c0 100644 --- a/Documentation/devicetree/bindings/net/fsl-fec.txt +++ b/Documentation/devicetree/bindings/net/fsl-fec.txt @@ -4,12 +4,9 @@ Required properties: - compatible : Should be "fsl,<soc>-fec" - reg : Address and length of the register set for the device - interrupts : Should contain fec interrupt -- phy-mode : String, operation mode of the PHY interface. - Supported values are: "mii", "gmii", "sgmii", "tbi", "rmii", - "rgmii", "rgmii-id", "rgmii-rxid", "rgmii-txid", "rtbi", "smii". +- phy-mode : See ethernet.txt file in the same directory Optional properties: -- local-mac-address : 6 bytes, mac address - phy-reset-gpios : Should specify the gpio for phy reset - phy-reset-duration : Reset duration in milliseconds. Should present only if property "phy-reset-gpios" is available. Missing the property diff --git a/Documentation/devicetree/bindings/net/fsl-tsec-phy.txt b/Documentation/devicetree/bindings/net/fsl-tsec-phy.txt index d2ea4605d078..737cdef4f903 100644 --- a/Documentation/devicetree/bindings/net/fsl-tsec-phy.txt +++ b/Documentation/devicetree/bindings/net/fsl-tsec-phy.txt @@ -38,22 +38,17 @@ Properties: - model : Model of the device. Can be "TSEC", "eTSEC", or "FEC" - compatible : Should be "gianfar" - reg : Offset and length of the register set for the device - - local-mac-address : List of bytes representing the ethernet address of - this controller - interrupts : For FEC devices, the first interrupt is the device's interrupt. For TSEC and eTSEC devices, the first interrupt is transmit, the second is receive, and the third is error. - - phy-handle : The phandle for the PHY connected to this ethernet - controller. + - phy-handle : See ethernet.txt file in the same directory. - fixed-link : <a b c d e> where a is emulated phy id - choose any, but unique to the all specified fixed-links, b is duplex - 0 half, 1 full, c is link speed - d#10/d#100/d#1000, d is pause - 0 no pause, 1 pause, e is asym_pause - 0 no asym_pause, 1 asym_pause. - - phy-connection-type : a string naming the controller/PHY interface type, - i.e., "mii" (default), "rmii", "gmii", "rgmii", "rgmii-id", "sgmii", - "tbi", or "rtbi". This property is only really needed if the connection - is of type "rgmii-id", as all other connection types are detected by - hardware. + - phy-connection-type : See ethernet.txt file in the same directory. + This property is only really needed if the connection is of type + "rgmii-id", as all other connection types are detected by hardware. - fsl,magic-packet : If present, indicates that the hardware supports waking up via magic packet. - bd-stash : If present, indicates that the hardware supports stashing diff --git a/Documentation/devicetree/bindings/net/lpc-eth.txt b/Documentation/devicetree/bindings/net/lpc-eth.txt index 585021acd178..b92e927808b6 100644 --- a/Documentation/devicetree/bindings/net/lpc-eth.txt +++ b/Documentation/devicetree/bindings/net/lpc-eth.txt @@ -6,10 +6,9 @@ Required properties: - interrupts: Should contain ethernet controller interrupt Optional properties: -- phy-mode: String, operation mode of the PHY interface. - Supported values are: "mii", "rmii" (default) +- phy-mode: See ethernet.txt file in the same directory. If the property is + absent, "rmii" is assumed. - use-iram: Use LPC32xx internal SRAM (IRAM) for DMA buffering -- local-mac-address : 6 bytes, mac address Example: diff --git a/Documentation/devicetree/bindings/net/macb.txt b/Documentation/devicetree/bindings/net/macb.txt index 70af2ec12b09..aaa696414f57 100644 --- a/Documentation/devicetree/bindings/net/macb.txt +++ b/Documentation/devicetree/bindings/net/macb.txt @@ -8,16 +8,12 @@ Required properties: the Cadence GEM, or the generic form: "cdns,gem". - reg: Address and length of the register set for the device - interrupts: Should contain macb interrupt -- phy-mode: String, operation mode of the PHY interface. - Supported values are: "mii", "rmii", "gmii", "rgmii". +- phy-mode: See ethernet.txt file in the same directory. - clock-names: Tuple listing input clock names. Required elements: 'pclk', 'hclk' Optional elements: 'tx_clk' - clocks: Phandles to input clocks. -Optional properties: -- local-mac-address: 6 bytes, mac address - Examples: macb0: ethernet@fffc4000 { diff --git a/Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt b/Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt index 859a6fa7569c..750d577e8083 100644 --- a/Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt +++ b/Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt @@ -4,10 +4,8 @@ Required properties: - compatible: should be "marvell,armada-370-neta". - reg: address and length of the register set for the device. - interrupts: interrupt for the device -- phy: A phandle to a phy node defining the PHY address (as the reg - property, a single integer). -- phy-mode: The interface between the SoC and the PHY (a string that - of_get_phy_mode() can understand) +- phy: See ethernet.txt file in the same directory. +- phy-mode: See ethernet.txt file in the same directory - clocks: a pointer to the reference clock for this device. Example: diff --git a/Documentation/devicetree/bindings/net/marvell-orion-net.txt b/Documentation/devicetree/bindings/net/marvell-orion-net.txt index c233b6114242..bce52b2ec55e 100644 --- a/Documentation/devicetree/bindings/net/marvell-orion-net.txt +++ b/Documentation/devicetree/bindings/net/marvell-orion-net.txt @@ -36,7 +36,7 @@ Required port properties: "marvell,kirkwood-eth-port". - reg: port number relative to ethernet controller, shall be 0, 1, or 2. - interrupts: port interrupt. - - local-mac-address: 6 bytes MAC address. + - local-mac-address: See ethernet.txt file in the same directory. Optional port properties: - marvell,tx-queue-size: size of the transmit ring buffer. @@ -48,7 +48,7 @@ Optional port properties: and - - phy-handle: phandle reference to ethernet PHY. + - phy-handle: See ethernet.txt file in the same directory. or diff --git a/Documentation/devicetree/bindings/net/micrel-ks8851.txt b/Documentation/devicetree/bindings/net/micrel-ks8851.txt index 11ace3c3d805..8e20c04a1da1 100644 --- a/Documentation/devicetree/bindings/net/micrel-ks8851.txt +++ b/Documentation/devicetree/bindings/net/micrel-ks8851.txt @@ -4,6 +4,3 @@ Required properties: - compatible = "micrel,ks8851-ml" of parallel interface - reg : 2 physical address and size of registers for data and command - interrupts : interrupt connection - -Optional properties: -- local-mac-address : Ethernet mac address to use diff --git a/Documentation/devicetree/bindings/net/micrel.txt b/Documentation/devicetree/bindings/net/micrel.txt new file mode 100644 index 000000000000..98a3e61f9ee8 --- /dev/null +++ b/Documentation/devicetree/bindings/net/micrel.txt @@ -0,0 +1,18 @@ +Micrel PHY properties. + +These properties cover the base properties Micrel PHYs. + +Optional properties: + + - micrel,led-mode : LED mode value to set for PHYs with configurable LEDs. + + Configure the LED mode with single value. The list of PHYs and + the bits that are currently supported: + + KSZ8001: register 0x1e, bits 15..14 + KSZ8041: register 0x1e, bits 15..14 + KSZ8021: register 0x1f, bits 5..4 + KSZ8031: register 0x1f, bits 5..4 + KSZ8051: register 0x1f, bits 5..4 + + See the respective PHY datasheet for the mode values. diff --git a/Documentation/devicetree/bindings/net/opencores-ethoc.txt b/Documentation/devicetree/bindings/net/opencores-ethoc.txt new file mode 100644 index 000000000000..2dc127c30d9b --- /dev/null +++ b/Documentation/devicetree/bindings/net/opencores-ethoc.txt @@ -0,0 +1,22 @@ +* OpenCores MAC 10/100 Mbps + +Required properties: +- compatible: Should be "opencores,ethoc". +- reg: two memory regions (address and length), + first region is for the device registers and descriptor rings, + second is for the device packet memory. +- interrupts: interrupt for the device. + +Optional properties: +- clocks: phandle to refer to the clk used as per + Documentation/devicetree/bindings/clock/clock-bindings.txt + +Examples: + + enet0: ethoc@fd030000 { + compatible = "opencores,ethoc"; + reg = <0xfd030000 0x4000 0xfd800000 0x4000>; + interrupts = <1>; + local-mac-address = [00 50 c2 13 6f 00]; + clocks = <&osc>; + }; diff --git a/Documentation/devicetree/bindings/net/sh_eth.txt b/Documentation/devicetree/bindings/net/sh_eth.txt new file mode 100644 index 000000000000..e7106b50dbdc --- /dev/null +++ b/Documentation/devicetree/bindings/net/sh_eth.txt @@ -0,0 +1,55 @@ +* Renesas Electronics SH EtherMAC + +This file provides information on what the device node for the SH EtherMAC +interface contains. + +Required properties: +- compatible: "renesas,gether-r8a7740" if the device is a part of R8A7740 SoC. + "renesas,ether-r8a7778" if the device is a part of R8A7778 SoC. + "renesas,ether-r8a7779" if the device is a part of R8A7779 SoC. + "renesas,ether-r8a7790" if the device is a part of R8A7790 SoC. + "renesas,ether-r8a7791" if the device is a part of R8A7791 SoC. + "renesas,ether-r7s72100" if the device is a part of R7S72100 SoC. +- reg: offset and length of (1) the E-DMAC/feLic register block (required), + (2) the TSU register block (optional). +- interrupts: interrupt specifier for the sole interrupt. +- phy-mode: see ethernet.txt file in the same directory. +- phy-handle: see ethernet.txt file in the same directory. +- #address-cells: number of address cells for the MDIO bus, must be equal to 1. +- #size-cells: number of size cells on the MDIO bus, must be equal to 0. +- clocks: clock phandle and specifier pair. +- pinctrl-0: phandle, referring to a default pin configuration node. + +Optional properties: +- interrupt-parent: the phandle for the interrupt controller that services + interrupts for this device. +- pinctrl-names: pin configuration state name ("default"). +- renesas,no-ether-link: boolean, specify when a board does not provide a proper + Ether LINK signal. +- renesas,ether-link-active-low: boolean, specify when the Ether LINK signal is + active-low instead of normal active-high. + +Example (Lager board): + + ethernet@ee700000 { + compatible = "renesas,ether-r8a7790"; + reg = <0 0xee700000 0 0x400>; + interrupt-parent = <&gic>; + interrupts = <0 162 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&mstp8_clks R8A7790_CLK_ETHER>; + phy-mode = "rmii"; + phy-handle = <&phy1>; + pinctrl-0 = <ðer_pins>; + pinctrl-names = "default"; + renesas,ether-link-active-low; + #address-cells = <1>; + #size-cells = <0>; + + phy1: ethernet-phy@1 { + reg = <1>; + interrupt-parent = <&irqc0>; + interrupts = <0 IRQ_TYPE_LEVEL_LOW>; + pinctrl-0 = <&phy1_pins>; + pinctrl-names = "default"; + }; + }; diff --git a/Documentation/devicetree/bindings/net/smsc-lan91c111.txt b/Documentation/devicetree/bindings/net/smsc-lan91c111.txt index 5a41a8658daa..0f8487b88822 100644 --- a/Documentation/devicetree/bindings/net/smsc-lan91c111.txt +++ b/Documentation/devicetree/bindings/net/smsc-lan91c111.txt @@ -6,8 +6,7 @@ Required properties: - interrupts : interrupt connection Optional properties: -- phy-device : phandle to Ethernet phy -- local-mac-address : Ethernet mac address to use +- phy-device : see ethernet.txt file in the same directory - reg-io-width : Mask of sizes (in bytes) of the IO accesses that are supported on the device. Valid value for SMSC LAN91c111 are 1, 2 or 4. If it's omitted or invalid, the size would be 2 meaning diff --git a/Documentation/devicetree/bindings/net/smsc911x.txt b/Documentation/devicetree/bindings/net/smsc911x.txt index adb5b5744ecd..3fed3c124411 100644 --- a/Documentation/devicetree/bindings/net/smsc911x.txt +++ b/Documentation/devicetree/bindings/net/smsc911x.txt @@ -6,9 +6,7 @@ Required properties: - interrupts : Should contain SMSC LAN interrupt line - interrupt-parent : Should be the phandle for the interrupt controller that services interrupts for this device -- phy-mode : String, operation mode of the PHY interface. - Supported values are: "mii", "gmii", "sgmii", "tbi", "rmii", - "rgmii", "rgmii-id", "rgmii-rxid", "rgmii-txid", "rtbi", "smii". +- phy-mode : See ethernet.txt file in the same directory Optional properties: - reg-shift : Specify the quantity to shift the register offsets by @@ -23,7 +21,6 @@ Optional properties: external PHY - smsc,save-mac-address : Indicates that mac address needs to be saved before resetting the controller -- local-mac-address : 6 bytes, mac address Examples: diff --git a/Documentation/devicetree/bindings/net/sti-dwmac.txt b/Documentation/devicetree/bindings/net/sti-dwmac.txt new file mode 100644 index 000000000000..3dd3d0bf112f --- /dev/null +++ b/Documentation/devicetree/bindings/net/sti-dwmac.txt @@ -0,0 +1,58 @@ +STMicroelectronics SoC DWMAC glue layer controller + +The device node has following properties. + +Required properties: + - compatible : Can be "st,stih415-dwmac", "st,stih416-dwmac" or + "st,stid127-dwmac". + - reg : Offset of the glue configuration register map in system + configuration regmap pointed by st,syscon property and size. + + - reg-names : Should be "sti-ethconf". + + - st,syscon : Should be phandle to system configuration node which + encompases this glue registers. + + - st,tx-retime-src: On STi Parts for Giga bit speeds, 125Mhz clocks can be + wired up in from different sources. One via TXCLK pin and other via CLK_125 + pin. This wiring is totally board dependent. However the retiming glue + logic should be configured accordingly. Possible values for this property + + "txclk" - if 125Mhz clock is wired up via txclk line. + "clk_125" - if 125Mhz clock is wired up via clk_125 line. + + This property is only valid for Giga bit setup( GMII, RGMII), and it is + un-used for non-giga bit (MII and RMII) setups. Also note that internal + clockgen can not generate stable 125Mhz clock. + + - st,ext-phyclk: This boolean property indicates who is generating the clock + for tx and rx. This property is only valid for RMII case where the clock can + be generated from the MAC or PHY. + + - clock-names: should be "sti-ethclk". + - clocks: Should point to ethernet clockgen which can generate phyclk. + + +Example: + +ethernet0: dwmac@fe810000 { + device_type = "network"; + compatible = "st,stih416-dwmac", "snps,dwmac", "snps,dwmac-3.710"; + reg = <0xfe810000 0x8000>, <0x8bc 0x4>; + reg-names = "stmmaceth", "sti-ethconf"; + interrupts = <0 133 0>, <0 134 0>, <0 135 0>; + interrupt-names = "macirq", "eth_wake_irq", "eth_lpi"; + phy-mode = "mii"; + + st,syscon = <&syscfg_rear>; + + snps,pbl = <32>; + snps,mixed-burst; + + resets = <&softreset STIH416_ETH0_SOFTRESET>; + reset-names = "stmmaceth"; + pinctrl-0 = <&pinctrl_mii0>; + pinctrl-names = "default"; + clocks = <&CLK_S_GMAC0_PHY>; + clock-names = "stmmaceth"; +}; diff --git a/Documentation/devicetree/bindings/net/stmmac.txt b/Documentation/devicetree/bindings/net/stmmac.txt index 9d92d42140f2..5748351fb9df 100644 --- a/Documentation/devicetree/bindings/net/stmmac.txt +++ b/Documentation/devicetree/bindings/net/stmmac.txt @@ -10,8 +10,7 @@ Required properties: - interrupt-names: Should contain the interrupt names "macirq" "eth_wake_irq" if this interrupt is supported in the "interrupts" property -- phy-mode: String, operation mode of the PHY interface. - Supported values are: "mii", "rmii", "gmii", "rgmii". +- phy-mode: See ethernet.txt file in the same directory. - snps,reset-gpio gpio number for phy reset. - snps,reset-active-low boolean flag to indicate if phy reset is active low. - snps,reset-delays-us is triplet of delays @@ -28,12 +27,10 @@ Required properties: ignored if force_thresh_dma_mode is set. Optional properties: -- mac-address: 6 bytes, mac address - resets: Should contain a phandle to the STMMAC reset signal, if any - reset-names: Should contain the reset signal name "stmmaceth", if a reset phandle is given -- max-frame-size: Maximum Transfer Unit (IEEE defined MTU), rather - than the maximum frame size. +- max-frame-size: See ethernet.txt file in the same directory Examples: diff --git a/Documentation/devicetree/bindings/power/bq2415x.txt b/Documentation/devicetree/bindings/power/bq2415x.txt new file mode 100644 index 000000000000..d0327f0b59ad --- /dev/null +++ b/Documentation/devicetree/bindings/power/bq2415x.txt @@ -0,0 +1,47 @@ +Binding for TI bq2415x Li-Ion Charger + +Required properties: +- compatible: Should contain one of the following: + * "ti,bq24150" + * "ti,bq24150" + * "ti,bq24150a" + * "ti,bq24151" + * "ti,bq24151a" + * "ti,bq24152" + * "ti,bq24153" + * "ti,bq24153a" + * "ti,bq24155" + * "ti,bq24156" + * "ti,bq24156a" + * "ti,bq24158" +- reg: integer, i2c address of the device. +- ti,current-limit: integer, initial maximum current charger can pull + from power supply in mA. +- ti,weak-battery-voltage: integer, weak battery voltage threshold in mV. + The chip will use slow precharge if battery voltage + is below this value. +- ti,battery-regulation-voltage: integer, maximum charging voltage in mV. +- ti,charge-current: integer, maximum charging current in mA. +- ti,termination-current: integer, charge will be terminated when current in + constant-voltage phase drops below this value (in mA). +- ti,resistor-sense: integer, value of sensing resistor in milliohm. + +Optional properties: +- ti,usb-charger-detection: phandle to usb charger detection device. + (required for auto mode) + +Example from Nokia N900: + +bq24150a { + compatible = "ti,bq24150a"; + reg = <0x6b>; + + ti,current-limit = <100>; + ti,weak-battery-voltage = <3400>; + ti,battery-regulation-voltage = <4200>; + ti,charge-current = <650>; + ti,termination-current = <100>; + ti,resistor-sense = <68>; + + ti,usb-charger-detection = <&isp1704>; +}; diff --git a/Documentation/devicetree/bindings/spi/spi_atmel.txt b/Documentation/devicetree/bindings/spi/spi_atmel.txt index 07e04cdc0c9e..4f8184d069cb 100644 --- a/Documentation/devicetree/bindings/spi/spi_atmel.txt +++ b/Documentation/devicetree/bindings/spi/spi_atmel.txt @@ -5,6 +5,9 @@ Required properties: - reg: Address and length of the register set for the device - interrupts: Should contain spi interrupt - cs-gpios: chipselects +- clock-names: tuple listing input clock names. + Required elements: "spi_clk" +- clocks: phandles to input clocks. Example: @@ -14,6 +17,8 @@ spi1: spi@fffcc000 { interrupts = <13 4 5>; #address-cells = <1>; #size-cells = <0>; + clocks = <&spi1_clk>; + clock-names = "spi_clk"; cs-gpios = <&pioB 3 0>; status = "okay"; diff --git a/Documentation/devicetree/bindings/vendor-prefixes.txt b/Documentation/devicetree/bindings/vendor-prefixes.txt index 3f900cd51bf0..40ce2df0e0e9 100644 --- a/Documentation/devicetree/bindings/vendor-prefixes.txt +++ b/Documentation/devicetree/bindings/vendor-prefixes.txt @@ -8,6 +8,7 @@ ad Avionic Design GmbH adi Analog Devices, Inc. aeroflexgaisler Aeroflex Gaisler AB ak Asahi Kasei Corp. +allwinner Allwinner Technology Co., Ltd. altr Altera Corp. amcc Applied Micro Circuits Corporation (APM, formally AMCC) amstaos AMS-Taos Inc. @@ -40,6 +41,7 @@ gmt Global Mixed-mode Technology, Inc. gumstix Gumstix, Inc. haoyu Haoyu Microelectronic Co. Ltd. hisilicon Hisilicon Limited. +honeywell Honeywell hp Hewlett Packard ibm International Business Machines (IBM) idt Integrated Device Technologies, Inc. @@ -55,6 +57,7 @@ maxim Maxim Integrated Products microchip Microchip Technology Inc. mosaixtech Mosaix Technologies, Inc. national National Semiconductor +neonode Neonode Inc. nintendo Nintendo nvidia NVIDIA nxp NXP Semiconductors @@ -64,7 +67,7 @@ phytec PHYTEC Messtechnik GmbH picochip Picochip Ltd powervr PowerVR (deprecated, use img) qca Qualcomm Atheros, Inc. -qcom Qualcomm, Inc. +qcom Qualcomm Technologies, Inc ralink Mediatek/Ralink Technology Corp. ramtron Ramtron International realtek Realtek Semiconductor Corp. @@ -78,6 +81,7 @@ silabs Silicon Laboratories simtek sirf SiRF Technology, Inc. snps Synopsys, Inc. +spansion Spansion Inc. st STMicroelectronics ste ST-Ericsson stericsson ST-Ericsson diff --git a/Documentation/fb/00-INDEX b/Documentation/fb/00-INDEX index 30a70542e823..fe85e7c5907a 100644 --- a/Documentation/fb/00-INDEX +++ b/Documentation/fb/00-INDEX @@ -5,6 +5,8 @@ please mail me. 00-INDEX - this file. +api.txt + - The frame buffer API between applications and buffer devices. arkfb.txt - info on the fbdev driver for ARK Logic chips. aty128fb.txt @@ -51,12 +53,16 @@ sh7760fb.txt - info on the SH7760/SH7763 integrated LCDC Framebuffer driver. sisfb.txt - info on the framebuffer device driver for various SiS chips. +sm501.txt + - info on the framebuffer device driver for sm501 videoframebuffer. sstfb.txt - info on the frame buffer driver for 3dfx' Voodoo Graphics boards. tgafb.txt - info on the TGA (DECChip 21030) frame buffer driver. tridentfb.txt info on the framebuffer driver for some Trident chip based cards. +udlfb.txt + - Driver for DisplayLink USB 2.0 chips. uvesafb.txt - info on the userspace VESA (VBE2+ compliant) frame buffer device. vesafb.txt diff --git a/Documentation/filesystems/00-INDEX b/Documentation/filesystems/00-INDEX index 632211cbdd56..ac28149aede4 100644 --- a/Documentation/filesystems/00-INDEX +++ b/Documentation/filesystems/00-INDEX @@ -2,6 +2,8 @@ - this file (info on some of the filesystems supported by linux). Locking - info on locking rules as they pertain to Linux VFS. +Makefile + - Makefile for building the filsystems-part of DocBook. 9p.txt - 9p (v9fs) is an implementation of the Plan 9 remote fs protocol. adfs.txt diff --git a/Documentation/filesystems/nfs/00-INDEX b/Documentation/filesystems/nfs/00-INDEX index 66eb6c8c5334..53f3b596ac0d 100644 --- a/Documentation/filesystems/nfs/00-INDEX +++ b/Documentation/filesystems/nfs/00-INDEX @@ -12,6 +12,8 @@ nfs41-server.txt - info on the Linux server implementation of NFSv4 minor version 1. nfs-rdma.txt - how to install and setup the Linux NFS/RDMA client and server software +nfsd-admin-interfaces.txt + - Administrative interfaces for nfsd. nfsroot.txt - short guide on setting up a diskless box with NFS root filesystem. pnfs.txt @@ -20,5 +22,5 @@ rpc-cache.txt - introduction to the caching mechanisms in the sunrpc layer. idmapper.txt - information for configuring request-keys to be used by idmapper -knfsd-rpcgss.txt +rpc-server-gss.txt - Information on GSS authentication support in the NFS Server diff --git a/Documentation/i2c/instantiating-devices b/Documentation/i2c/instantiating-devices index c70e7a7638d1..0d85ac1935b7 100644 --- a/Documentation/i2c/instantiating-devices +++ b/Documentation/i2c/instantiating-devices @@ -8,8 +8,8 @@ reason, the kernel code must instantiate I2C devices explicitly. There are several ways to achieve this, depending on the context and requirements. -Method 1: Declare the I2C devices by bus number ------------------------------------------------ +Method 1a: Declare the I2C devices by bus number +------------------------------------------------ This method is appropriate when the I2C bus is a system bus as is the case for many embedded systems. On such systems, each I2C bus has a number @@ -51,6 +51,43 @@ The devices will be automatically unbound and destroyed when the I2C bus they sit on goes away (if ever.) +Method 1b: Declare the I2C devices via devicetree +------------------------------------------------- + +This method has the same implications as method 1a. The declaration of I2C +devices is here done via devicetree as subnodes of the master controller. + +Example: + + i2c1: i2c@400a0000 { + /* ... master properties skipped ... */ + clock-frequency = <100000>; + + flash@50 { + compatible = "atmel,24c256"; + reg = <0x50>; + }; + + pca9532: gpio@60 { + compatible = "nxp,pca9532"; + gpio-controller; + #gpio-cells = <2>; + reg = <0x60>; + }; + }; + +Here, two devices are attached to the bus using a speed of 100kHz. For +additional properties which might be needed to set up the device, please refer +to its devicetree documentation in Documentation/devicetree/bindings/. + + +Method 1c: Declare the I2C devices via ACPI +------------------------------------------- + +ACPI can also describe I2C devices. There is special documentation for this +which is currently located at Documentation/acpi/enumeration.txt. + + Method 2: Instantiate the devices explicitly -------------------------------------------- diff --git a/Documentation/ide/00-INDEX b/Documentation/ide/00-INDEX index d6b778842b75..22f98ca79539 100644 --- a/Documentation/ide/00-INDEX +++ b/Documentation/ide/00-INDEX @@ -10,3 +10,5 @@ ide-tape.txt - info on the IDE ATAPI streaming tape driver ide.txt - important info for users of ATA devices (IDE/EIDE disks and CD-ROMS). +warm-plug-howto.txt + - using sysfs to remove and add IDE devices.
\ No newline at end of file diff --git a/Documentation/laptops/00-INDEX b/Documentation/laptops/00-INDEX index fa688538e757..d13b9a9a9e00 100644 --- a/Documentation/laptops/00-INDEX +++ b/Documentation/laptops/00-INDEX @@ -1,13 +1,15 @@ 00-INDEX - This file -acer-wmi.txt - - information on the Acer Laptop WMI Extras driver. +Makefile + - Makefile for building dslm example program. asus-laptop.txt - information on the Asus Laptop Extras driver. disk-shock-protection.txt - information on hard disk shock protection. dslm.c - Simple Disk Sleep Monitor program +hpfall.c + - (HP) laptop accelerometer program for disk protection. laptop-mode.txt - how to conserve battery power using laptop-mode. sony-laptop.txt diff --git a/Documentation/leds/00-INDEX b/Documentation/leds/00-INDEX index 1ecd1596633e..b4ef1f34e25f 100644 --- a/Documentation/leds/00-INDEX +++ b/Documentation/leds/00-INDEX @@ -1,3 +1,7 @@ +00-INDEX + - This file +leds-blinkm.txt + - Driver for BlinkM LED-devices. leds-class.txt - documents LED handling under Linux. leds-lp3944.txt @@ -12,3 +16,7 @@ leds-lp55xx.txt - description about lp55xx common driver. leds-lm3556.txt - notes on how to use the leds-lm3556 driver. +ledtrig-oneshot.txt + - One-shot LED trigger for both sporadic and dense events. +ledtrig-transient.txt + - LED Transient Trigger, one shot timer activation. diff --git a/Documentation/m68k/00-INDEX b/Documentation/m68k/00-INDEX index a014e9f00765..2be8c6b00e74 100644 --- a/Documentation/m68k/00-INDEX +++ b/Documentation/m68k/00-INDEX @@ -1,5 +1,7 @@ 00-INDEX - this file +README.buddha + - Amiga Buddha and Catweasel IDE Driver kernel-options.txt - command line options for Linux/m68k diff --git a/Documentation/networking/00-INDEX b/Documentation/networking/00-INDEX index f11580f8719a..557b6ef70c26 100644 --- a/Documentation/networking/00-INDEX +++ b/Documentation/networking/00-INDEX @@ -6,8 +6,14 @@ - information on the 3Com Etherlink III Series Ethernet cards. 6pack.txt - info on the 6pack protocol, an alternative to KISS for AX.25 -DLINK.txt - - info on the D-Link DE-600/DE-620 parallel port pocket adapters +LICENSE.qla3xxx + - GPLv2 for QLogic Linux Networking HBA Driver +LICENSE.qlge + - GPLv2 for QLogic Linux qlge NIC Driver +LICENSE.qlcnic + - GPLv2 for QLogic Linux qlcnic NIC Driver +Makefile + - Makefile for docsrc. PLIP.txt - PLIP: The Parallel Line Internet Protocol device driver README.ipw2100 @@ -17,7 +23,7 @@ README.ipw2200 README.sb1000 - info on General Instrument/NextLevel SURFboard1000 cable modem. alias.txt - - info on using alias network devices + - info on using alias network devices. arcnet-hardware.txt - tons of info on ARCnet, hubs, jumper settings for ARCnet cards, etc. arcnet.txt @@ -80,7 +86,7 @@ framerelay.txt - info on using Frame Relay/Data Link Connection Identifier (DLCI). gen_stats.txt - Generic networking statistics for netlink users. -generic_hdlc.txt +generic-hdlc.txt - The generic High Level Data Link Control (HDLC) layer. generic_netlink.txt - info on Generic Netlink @@ -88,6 +94,8 @@ gianfar.txt - Gianfar Ethernet Driver. i40e.txt - README for the Intel Ethernet Controller XL710 Driver (i40e). +i40evf.txt + - Short note on the Driver for the Intel(R) XL710 X710 Virtual Function ieee802154.txt - Linux IEEE 802.15.4 implementation, API and drivers igb.txt @@ -102,6 +110,8 @@ ipddp.txt - AppleTalk-IP Decapsulation and AppleTalk-IP Encapsulation iphase.txt - Interphase PCI ATM (i)Chip IA Linux driver info. +ipsec.txt + - Note on not compressing IPSec payload and resulting failed policy check. ipv6.txt - Options to the ipv6 kernel module. ipvs-sysctl.txt @@ -120,6 +130,8 @@ lapb-module.txt - programming information of the LAPB module. ltpc.txt - the Apple or Farallon LocalTalk PC card driver +mac80211-auth-assoc-deauth.txt + - authentication and association / deauth-disassoc with max80211 mac80211-injection.txt - HOWTO use packet injection with mac80211 multiqueue.txt @@ -134,6 +146,10 @@ netdevices.txt - info on network device driver functions exported to the kernel. netif-msg.txt - Design of the network interface message level setting (NETIF_MSG_*). +netlink_mmap.txt + - memory mapped I/O with netlink +nf_conntrack-sysctl.txt + - list of netfilter-sysctl knobs. nfc.txt - The Linux Near Field Communication (NFS) subsystem. openvswitch.txt @@ -176,7 +192,7 @@ skfp.txt - SysKonnect FDDI (SK-5xxx, Compaq Netelligent) driver info. smc9.txt - the driver for SMC's 9000 series of Ethernet cards -spider-net.txt +spider_net.txt - README for the Spidernet Driver (as found in PS3 / Cell BE). stmmac.txt - README for the STMicro Synopsys Ethernet driver. @@ -188,6 +204,8 @@ tcp.txt - short blurb on how TCP output takes place. tcp-thin.txt - kernel tuning options for low rate 'thin' TCP streams. +team.txt + - pointer to information for ethernet teaming devices. tlan.txt - ThunderLAN (Compaq Netelligent 10/100, Olicom OC-2xxx) driver info. tproxy.txt @@ -200,6 +218,8 @@ vortex.txt - info on using 3Com Vortex (3c590, 3c592, 3c595, 3c597) Ethernet cards. vxge.txt - README for the Neterion X3100 PCIe Server Adapter. +vxlan.txt + - Virtual extensible LAN overview x25.txt - general info on X.25 development. x25-iface.txt diff --git a/Documentation/networking/3c505.txt b/Documentation/networking/3c505.txt deleted file mode 100644 index 72f38b13101d..000000000000 --- a/Documentation/networking/3c505.txt +++ /dev/null @@ -1,45 +0,0 @@ -The 3Com Etherlink Plus (3c505) driver. - -This driver now uses DMA. There is currently no support for PIO operation. -The default DMA channel is 6; this is _not_ autoprobed, so you must -make sure you configure it correctly. If loading the driver as a -module, you can do this with "modprobe 3c505 dma=n". If the driver is -linked statically into the kernel, you must either use an "ether=" -statement on the command line, or change the definition of ELP_DMA in 3c505.h. - -The driver will warn you if it has to fall back on the compiled in -default DMA channel. - -If no base address is given at boot time, the driver will autoprobe -ports 0x300, 0x280 and 0x310 (in that order). If no IRQ is given, the driver -will try to probe for it. - -The driver can be used as a loadable module. - -Theoretically, one instance of the driver can now run multiple cards, -in the standard way (when loading a module, say "modprobe 3c505 -io=0x300,0x340 irq=10,11 dma=6,7" or whatever). I have not tested -this, though. - -The driver may now support revision 2 hardware; the dependency on -being able to read the host control register has been removed. This -is also untested, since I don't have a suitable card. - -Known problems: - I still see "DMA upload timed out" messages from time to time. These -seem to be fairly non-fatal though. - The card is old and slow. - -To do: - Improve probe/setup code - Test multicast and promiscuous operation - -Authors: - The driver is mainly written by Craig Southeren, email - <craigs@ineluki.apana.org.au>. - Parts of the driver (adapting the driver to 1.1.4+ kernels, - IRQ/address detection, some changes) and this README by - Juha Laiho <jlaiho@ichaos.nullnet.fi>. - DMA mode, more fixes, etc, by Philip Blundell <pjb27@cam.ac.uk> - Multicard support, Software configurable DMA, etc., by - Christopher Collins <ccollins@pcug.org.au> diff --git a/Documentation/networking/bonding.txt b/Documentation/networking/bonding.txt index 5cdb22971d19..a383c00392d0 100644 --- a/Documentation/networking/bonding.txt +++ b/Documentation/networking/bonding.txt @@ -270,16 +270,15 @@ arp_ip_target arp_validate Specifies whether or not ARP probes and replies should be - validated in the active-backup mode. This causes the ARP - monitor to examine the incoming ARP requests and replies, and - only consider a slave to be up if it is receiving the - appropriate ARP traffic. + validated in any mode that supports arp monitoring, or whether + non-ARP traffic should be filtered (disregarded) for link + monitoring purposes. Possible values are: none or 0 - No validation is performed. This is the default. + No validation or filtering is performed. active or 1 @@ -293,31 +292,68 @@ arp_validate Validation is performed for all slaves. - For the active slave, the validation checks ARP replies to - confirm that they were generated by an arp_ip_target. Since - backup slaves do not typically receive these replies, the - validation performed for backup slaves is on the ARP request - sent out via the active slave. It is possible that some - switch or network configurations may result in situations - wherein the backup slaves do not receive the ARP requests; in - such a situation, validation of backup slaves must be - disabled. - - The validation of ARP requests on backup slaves is mainly - helping bonding to decide which slaves are more likely to - work in case of the active slave failure, it doesn't really - guarantee that the backup slave will work if it's selected - as the next active slave. - - This option is useful in network configurations in which - multiple bonding hosts are concurrently issuing ARPs to one or - more targets beyond a common switch. Should the link between - the switch and target fail (but not the switch itself), the - probe traffic generated by the multiple bonding instances will - fool the standard ARP monitor into considering the links as - still up. Use of the arp_validate option can resolve this, as - the ARP monitor will only consider ARP requests and replies - associated with its own instance of bonding. + filter or 4 + + Filtering is applied to all slaves. No validation is + performed. + + filter_active or 5 + + Filtering is applied to all slaves, validation is performed + only for the active slave. + + filter_backup or 6 + + Filtering is applied to all slaves, validation is performed + only for backup slaves. + + Validation: + + Enabling validation causes the ARP monitor to examine the incoming + ARP requests and replies, and only consider a slave to be up if it + is receiving the appropriate ARP traffic. + + For an active slave, the validation checks ARP replies to confirm + that they were generated by an arp_ip_target. Since backup slaves + do not typically receive these replies, the validation performed + for backup slaves is on the broadcast ARP request sent out via the + active slave. It is possible that some switch or network + configurations may result in situations wherein the backup slaves + do not receive the ARP requests; in such a situation, validation + of backup slaves must be disabled. + + The validation of ARP requests on backup slaves is mainly helping + bonding to decide which slaves are more likely to work in case of + the active slave failure, it doesn't really guarantee that the + backup slave will work if it's selected as the next active slave. + + Validation is useful in network configurations in which multiple + bonding hosts are concurrently issuing ARPs to one or more targets + beyond a common switch. Should the link between the switch and + target fail (but not the switch itself), the probe traffic + generated by the multiple bonding instances will fool the standard + ARP monitor into considering the links as still up. Use of + validation can resolve this, as the ARP monitor will only consider + ARP requests and replies associated with its own instance of + bonding. + + Filtering: + + Enabling filtering causes the ARP monitor to only use incoming ARP + packets for link availability purposes. Arriving packets that are + not ARPs are delivered normally, but do not count when determining + if a slave is available. + + Filtering operates by only considering the reception of ARP + packets (any ARP packet, regardless of source or destination) when + determining if a slave has received traffic for link availability + purposes. + + Filtering is useful in network configurations in which significant + levels of third party broadcast traffic would fool the standard + ARP monitor into considering the links as still up. Use of + filtering can resolve this, as only ARP traffic is considered for + link availability purposes. This option was added in bonding version 3.1.0. diff --git a/Documentation/networking/can.txt b/Documentation/networking/can.txt index f3089d423515..0cbe6ec22d6f 100644 --- a/Documentation/networking/can.txt +++ b/Documentation/networking/can.txt @@ -554,12 +554,6 @@ solution for a couple of reasons: not specified in the struct can_frame and therefore it is only valid in CANFD_MTU sized CAN FD frames. - As long as the payload length is <=8 the received CAN frames from CAN FD - capable CAN devices can be received and read by legacy sockets too. When - user-generated CAN FD frames have a payload length <=8 these can be send - by legacy CAN network interfaces too. Sending CAN FD frames with payload - length > 8 to a legacy CAN network interface returns an -EMSGSIZE error. - Implementation hint for new CAN applications: To build a CAN FD aware application use struct canfd_frame as basic CAN diff --git a/Documentation/networking/gianfar.txt b/Documentation/networking/gianfar.txt index ad474ea07d07..ba1daea7f2e4 100644 --- a/Documentation/networking/gianfar.txt +++ b/Documentation/networking/gianfar.txt @@ -1,38 +1,8 @@ The Gianfar Ethernet Driver -Sysfs File description Author: Andy Fleming <afleming@freescale.com> Updated: 2005-07-28 -SYSFS - -Several of the features of the gianfar driver are controlled -through sysfs files. These are: - -bd_stash: -To stash RX Buffer Descriptors in the L2, echo 'on' or '1' to -bd_stash, echo 'off' or '0' to disable - -rx_stash_len: -To stash the first n bytes of the packet in L2, echo the number -of bytes to buf_stash_len. echo 0 to disable. - -WARNING: You could really screw these up if you set them too low or high! -fifo_threshold: -To change the number of bytes the controller needs in the -fifo before it starts transmission, echo the number of bytes to -fifo_thresh. Range should be 0-511. - -fifo_starve: -When the FIFO has less than this many bytes during a transmit, it -enters starve mode, and increases the priority of TX memory -transactions. To change, echo the number of bytes to -fifo_starve. Range should be 0-511. - -fifo_starve_off: -Once in starve mode, the FIFO remains there until it has this -many bytes. To change, echo the number of bytes to -fifo_starve_off. Range should be 0-511. CHECKSUM OFFLOADING diff --git a/Documentation/networking/phy.txt b/Documentation/networking/phy.txt index ebf270719402..e602c6f347df 100644 --- a/Documentation/networking/phy.txt +++ b/Documentation/networking/phy.txt @@ -253,16 +253,25 @@ Writing a PHY driver Each driver consists of a number of function pointers: + soft_reset: perform a PHY software reset config_init: configures PHY into a sane state after a reset. For instance, a Davicom PHY requires descrambling disabled. probe: Allocate phy->priv, optionally refuse to bind. PHY may not have been reset or had fixups run yet. suspend/resume: power management config_aneg: Changes the speed/duplex/negotiation settings + aneg_done: Determines the auto-negotiation result read_status: Reads the current speed/duplex/negotiation settings ack_interrupt: Clear a pending interrupt + did_interrupt: Checks if the PHY generated an interrupt config_intr: Enable or disable interrupts remove: Does any driver take-down + ts_info: Queries about the HW timestamping status + hwtstamp: Set the PHY HW timestamping configuration + rxtstamp: Requests a receive timestamp at the PHY level for a 'skb' + txtsamp: Requests a transmit timestamp at the PHY level for a 'skb' + set_wol: Enable Wake-on-LAN at the PHY level + get_wol: Get the Wake-on-LAN status at the PHY level Of these, only config_aneg and read_status are required to be assigned by the driver code. The rest are optional. Also, it is diff --git a/Documentation/networking/pktgen.txt b/Documentation/networking/pktgen.txt index 5a61a240a652..0e30c7845b2b 100644 --- a/Documentation/networking/pktgen.txt +++ b/Documentation/networking/pktgen.txt @@ -102,13 +102,18 @@ Examples: The 'minimum' MAC is what you set with dstmac. pgset "flag [name]" Set a flag to determine behaviour. Current flags - are: IPSRC_RND #IP Source is random (between min/max), - IPDST_RND, UDPSRC_RND, - UDPDST_RND, MACSRC_RND, MACDST_RND + are: IPSRC_RND # IP source is random (between min/max) + IPDST_RND # IP destination is random + UDPSRC_RND, UDPDST_RND, + MACSRC_RND, MACDST_RND + TXSIZE_RND, IPV6, MPLS_RND, VID_RND, SVID_RND + FLOW_SEQ, QUEUE_MAP_RND # queue map random QUEUE_MAP_CPU # queue map mirrors smp_processor_id() - IPSEC # Make IPsec encapsulation for packet + UDPCSUM, + IPSEC # IPsec encapsulation (needs CONFIG_XFRM) + NODE_ALLOC # node specific memory allocation pgset spi SPI_VALUE Set specific SA used to transform packet. @@ -233,13 +238,22 @@ udp_dst_max flag IPSRC_RND - TXSIZE_RND IPDST_RND UDPSRC_RND UDPDST_RND MACSRC_RND MACDST_RND + TXSIZE_RND + IPV6 + MPLS_RND + VID_RND + SVID_RND + FLOW_SEQ + QUEUE_MAP_RND + QUEUE_MAP_CPU + UDPCSUM IPSEC + NODE_ALLOC dst_min dst_max diff --git a/Documentation/networking/rxrpc.txt b/Documentation/networking/rxrpc.txt index b89bc82eed46..16a924c486bf 100644 --- a/Documentation/networking/rxrpc.txt +++ b/Documentation/networking/rxrpc.txt @@ -27,6 +27,8 @@ Contents of this document: (*) AF_RXRPC kernel interface. + (*) Configurable parameters. + ======== OVERVIEW @@ -864,3 +866,82 @@ The kernel interface functions are as follows: This is used to allocate a null RxRPC key that can be used to indicate anonymous security for a particular domain. + + +======================= +CONFIGURABLE PARAMETERS +======================= + +The RxRPC protocol driver has a number of configurable parameters that can be +adjusted through sysctls in /proc/net/rxrpc/: + + (*) req_ack_delay + + The amount of time in milliseconds after receiving a packet with the + request-ack flag set before we honour the flag and actually send the + requested ack. + + Usually the other side won't stop sending packets until the advertised + reception window is full (to a maximum of 255 packets), so delaying the + ACK permits several packets to be ACK'd in one go. + + (*) soft_ack_delay + + The amount of time in milliseconds after receiving a new packet before we + generate a soft-ACK to tell the sender that it doesn't need to resend. + + (*) idle_ack_delay + + The amount of time in milliseconds after all the packets currently in the + received queue have been consumed before we generate a hard-ACK to tell + the sender it can free its buffers, assuming no other reason occurs that + we would send an ACK. + + (*) resend_timeout + + The amount of time in milliseconds after transmitting a packet before we + transmit it again, assuming no ACK is received from the receiver telling + us they got it. + + (*) max_call_lifetime + + The maximum amount of time in seconds that a call may be in progress + before we preemptively kill it. + + (*) dead_call_expiry + + The amount of time in seconds before we remove a dead call from the call + list. Dead calls are kept around for a little while for the purpose of + repeating ACK and ABORT packets. + + (*) connection_expiry + + The amount of time in seconds after a connection was last used before we + remove it from the connection list. Whilst a connection is in existence, + it serves as a placeholder for negotiated security; when it is deleted, + the security must be renegotiated. + + (*) transport_expiry + + The amount of time in seconds after a transport was last used before we + remove it from the transport list. Whilst a transport is in existence, it + serves to anchor the peer data and keeps the connection ID counter. + + (*) rxrpc_rx_window_size + + The size of the receive window in packets. This is the maximum number of + unconsumed received packets we're willing to hold in memory for any + particular call. + + (*) rxrpc_rx_mtu + + The maximum packet MTU size that we're willing to receive in bytes. This + indicates to the peer whether we're willing to accept jumbo packets. + + (*) rxrpc_rx_jumbo_max + + The maximum number of packets that we're willing to accept in a jumbo + packet. Non-terminal packets in a jumbo packet must contain a four byte + header plus exactly 1412 bytes of data. The terminal packet must contain + a four byte header plus any amount of data. In any event, a jumbo packet + may not exceed rxrpc_rx_mtu in size. diff --git a/Documentation/networking/tcp.txt b/Documentation/networking/tcp.txt index 7d11bb5dc30a..bdc4c0db51e1 100644 --- a/Documentation/networking/tcp.txt +++ b/Documentation/networking/tcp.txt @@ -30,7 +30,7 @@ A congestion control mechanism can be registered through functions in tcp_cong.c. The functions used by the congestion control mechanism are registered via passing a tcp_congestion_ops struct to tcp_register_congestion_control. As a minimum name, ssthresh, -cong_avoid, min_cwnd must be valid. +cong_avoid must be valid. Private data for a congestion control mechanism is stored in tp->ca_priv. tcp_ca(tp) returns a pointer to this space. This is preallocated space - it diff --git a/Documentation/phy.txt b/Documentation/phy.txt index 0103e4b15b0e..ebff6ee52441 100644 --- a/Documentation/phy.txt +++ b/Documentation/phy.txt @@ -75,14 +75,26 @@ Before the controller can make use of the PHY, it has to get a reference to it. This framework provides the following APIs to get a reference to the PHY. struct phy *phy_get(struct device *dev, const char *string); +struct phy *phy_optional_get(struct device *dev, const char *string); struct phy *devm_phy_get(struct device *dev, const char *string); - -phy_get and devm_phy_get can be used to get the PHY. In the case of dt boot, -the string arguments should contain the phy name as given in the dt data and -in the case of non-dt boot, it should contain the label of the PHY. -The only difference between the two APIs is that devm_phy_get associates the -device with the PHY using devres on successful PHY get. On driver detach, -release function is invoked on the the devres data and devres data is freed. +struct phy *devm_phy_optional_get(struct device *dev, const char *string); + +phy_get, phy_optional_get, devm_phy_get and devm_phy_optional_get can +be used to get the PHY. In the case of dt boot, the string arguments +should contain the phy name as given in the dt data and in the case of +non-dt boot, it should contain the label of the PHY. The two +devm_phy_get associates the device with the PHY using devres on +successful PHY get. On driver detach, release function is invoked on +the the devres data and devres data is freed. phy_optional_get and +devm_phy_optional_get should be used when the phy is optional. These +two functions will never return -ENODEV, but instead returns NULL when +the phy cannot be found. + +It should be noted that NULL is a valid phy reference. All phy +consumer calls on the NULL phy become NOPs. That is the release calls, +the phy_init() and phy_exit() calls, and phy_power_on() and +phy_power_off() calls are all NOP when applied to a NULL phy. The NULL +phy is useful in devices for handling optional phy devices. 5. Releasing a reference to the PHY diff --git a/Documentation/power/00-INDEX b/Documentation/power/00-INDEX index a4d682f54231..ad04cc8097ed 100644 --- a/Documentation/power/00-INDEX +++ b/Documentation/power/00-INDEX @@ -4,6 +4,8 @@ apm-acpi.txt - basic info about the APM and ACPI support. basic-pm-debugging.txt - Debugging suspend and resume +charger-manager.txt + - Battery charger management. devices.txt - How drivers interact with system-wide power management drivers-testing.txt @@ -22,6 +24,8 @@ pm_qos_interface.txt - info on Linux PM Quality of Service interface power_supply_class.txt - Tells userspace about battery, UPS, AC or DC power supply properties +runtime_pm.txt + - Power management framework for I/O devices. s2ram.txt - How to get suspend to ram working (and debug it when it isn't) states.txt @@ -38,7 +42,5 @@ tricks.txt - How to trick software suspend (to disk) into working when it isn't userland-swsusp.txt - Experimental implementation of software suspend in userspace -video_extension.txt - - ACPI video extensions video.txt - Video issues during resume from suspend diff --git a/Documentation/ptp/testptp.c b/Documentation/ptp/testptp.c index a74d0a84d329..4aba0436da65 100644 --- a/Documentation/ptp/testptp.c +++ b/Documentation/ptp/testptp.c @@ -117,6 +117,7 @@ static void usage(char *progname) " -f val adjust the ptp clock frequency by 'val' ppb\n" " -g get the ptp clock time\n" " -h prints this message\n" + " -i val index for event/trigger\n" " -k val measure the time offset between system and phc clock\n" " for 'val' times (Maximum 25)\n" " -p val enable output with a period of 'val' nanoseconds\n" @@ -154,6 +155,7 @@ int main(int argc, char *argv[]) int capabilities = 0; int extts = 0; int gettime = 0; + int index = 0; int oneshot = 0; int pct_offset = 0; int n_samples = 0; @@ -167,7 +169,7 @@ int main(int argc, char *argv[]) progname = strrchr(argv[0], '/'); progname = progname ? 1+progname : argv[0]; - while (EOF != (c = getopt(argc, argv, "a:A:cd:e:f:ghk:p:P:sSt:v"))) { + while (EOF != (c = getopt(argc, argv, "a:A:cd:e:f:ghi:k:p:P:sSt:v"))) { switch (c) { case 'a': oneshot = atoi(optarg); @@ -190,6 +192,9 @@ int main(int argc, char *argv[]) case 'g': gettime = 1; break; + case 'i': + index = atoi(optarg); + break; case 'k': pct_offset = 1; n_samples = atoi(optarg); @@ -301,7 +306,7 @@ int main(int argc, char *argv[]) if (extts) { memset(&extts_request, 0, sizeof(extts_request)); - extts_request.index = 0; + extts_request.index = index; extts_request.flags = PTP_ENABLE_FEATURE; if (ioctl(fd, PTP_EXTTS_REQUEST, &extts_request)) { perror("PTP_EXTTS_REQUEST"); @@ -375,7 +380,7 @@ int main(int argc, char *argv[]) return -1; } memset(&perout_request, 0, sizeof(perout_request)); - perout_request.index = 0; + perout_request.index = index; perout_request.start.sec = ts.tv_sec + 2; perout_request.start.nsec = 0; perout_request.period.sec = 0; diff --git a/Documentation/s390/00-INDEX b/Documentation/s390/00-INDEX index 3a2b96302ecc..10c874ebdfe5 100644 --- a/Documentation/s390/00-INDEX +++ b/Documentation/s390/00-INDEX @@ -16,11 +16,13 @@ Debugging390.txt - hints for debugging on s390 systems. driver-model.txt - information on s390 devices and the driver model. +kvm.txt + - ioctl calls to /dev/kvm on s390. monreader.txt - information on accessing the z/VM monitor stream from Linux. +qeth.txt + - HiperSockets Bridge Port Support. s390dbf.txt - information on using the s390 debug feature. -TAPE - - information on the driver for channel-attached tapes. -zfcpdump +zfcpdump.txt - information on the s390 SCSI dump tool. diff --git a/Documentation/scheduler/00-INDEX b/Documentation/scheduler/00-INDEX index 46702e4f89c9..eccf7ad2e7f9 100644 --- a/Documentation/scheduler/00-INDEX +++ b/Documentation/scheduler/00-INDEX @@ -2,6 +2,8 @@ - this file. sched-arch.txt - CPU Scheduler implementation hints for architecture specific code. +sched-bwc.txt + - CFS bandwidth control overview. sched-design-CFS.txt - goals, design and implementation of the Completely Fair Scheduler. sched-domains.txt diff --git a/Documentation/scsi/00-INDEX b/Documentation/scsi/00-INDEX index 2044be565d93..c4b978a72f78 100644 --- a/Documentation/scsi/00-INDEX +++ b/Documentation/scsi/00-INDEX @@ -36,6 +36,8 @@ NinjaSCSI.txt - info on WorkBiT NinjaSCSI-32/32Bi driver aacraid.txt - Driver supporting Adaptec RAID controllers +advansys.txt + - List of Advansys Host Adapters aha152x.txt - info on driver for Adaptec AHA152x based adapters aic79xx.txt @@ -44,6 +46,12 @@ aic7xxx.txt - info on driver for Adaptec controllers arcmsr_spec.txt - ARECA FIRMWARE SPEC (for IOP331 adapter) +bfa.txt + - Brocade FC/FCOE adapter driver. +bnx2fc.txt + - FCoE hardware offload for Broadcom network interfaces. +cxgb3i.txt + - Chelsio iSCSI Linux Driver dc395x.txt - README file for the dc395x SCSI driver dpti.txt @@ -52,18 +60,24 @@ dtc3x80.txt - info on driver for DTC 2x80 based adapters g_NCR5380.txt - info on driver for NCR5380 and NCR53c400 based adapters +hpsa.txt + - HP Smart Array Controller SCSI driver. hptiop.txt - HIGHPOINT ROCKETRAID 3xxx RAID DRIVER in2000.txt - info on in2000 driver libsas.txt - Serial Attached SCSI management layer. +link_power_management_policy.txt + - Link power management options. lpfc.txt - LPFC driver release notes megaraid.txt - Common Management Module, shared code handling ioctls for LSI drivers ncr53c8xx.txt - info on driver for NCR53c8xx based adapters +osd.txt + Object-Based Storage Device, command set introduction. osst.txt - info on driver for OnStream SC-x0 SCSI tape ppa.txt @@ -74,6 +88,8 @@ scsi-changer.txt - README for the SCSI media changer driver scsi-generic.txt - info on the sg driver for generic (non-disk/CD/tape) SCSI devices. +scsi-parameters.txt + - List of SCSI-parameters to pass to the kernel at module load-time. scsi.txt - short blurb on using SCSI support as a module. scsi_mid_low_api.txt diff --git a/Documentation/serial/00-INDEX b/Documentation/serial/00-INDEX index 1f1b22fbd739..f9c6b5ed03e7 100644 --- a/Documentation/serial/00-INDEX +++ b/Documentation/serial/00-INDEX @@ -4,10 +4,12 @@ README.cycladesZ - info on Cyclades-Z firmware loading. digiepca.txt - info on Digi Intl. {PC,PCI,EISA}Xx and Xem series cards. -hayes-esp.txt - - info on using the Hayes ESP serial driver. +driver + - intro to the low level serial driver. moxa-smartio - file with info on installing/using Moxa multiport serial driver. +n_gsm.txt + - GSM 0710 tty multiplexer howto. riscom8.txt - notes on using the RISCom/8 multi-port serial driver. rocket.txt diff --git a/Documentation/spi/00-INDEX b/Documentation/spi/00-INDEX new file mode 100644 index 000000000000..a128fa835512 --- /dev/null +++ b/Documentation/spi/00-INDEX @@ -0,0 +1,22 @@ +00-INDEX + - this file. +Makefile + - Makefile for the example sourcefiles. +butterfly + - AVR Butterfly SPI driver overview and pin configuration. +ep93xx_spi + - Basic EP93xx SPI driver configuration. +pxa2xx + - PXA2xx SPI master controller build by spi_message fifo wq +spidev + - Intro to the userspace API for spi devices +spidev_fdx.c + - spidev example file +spi-lm70llp + - Connecting an LM70-LLP sensor to the kernel via the SPI subsys. +spi-sc18is602 + - NXP SC18IS602/603 I2C-bus to SPI bridge +spi-summary + - (Linux) SPI overview. If unsure about SPI or SPI in Linux, start here. +spidev_test.c + - SPI testing utility. diff --git a/Documentation/spi/spi-summary b/Documentation/spi/spi-summary index f72e0d1e0da8..7982bcc4d151 100644 --- a/Documentation/spi/spi-summary +++ b/Documentation/spi/spi-summary @@ -543,7 +543,22 @@ SPI MASTER METHODS queuing transfers that arrive in the meantime. When the driver is finished with this message, it must call spi_finalize_current_message() so the subsystem can issue the next - transfer. This may sleep. + message. This may sleep. + + master->transfer_one(struct spi_master *master, struct spi_device *spi, + struct spi_transfer *transfer) + The subsystem calls the driver to transfer a single transfer while + queuing transfers that arrive in the meantime. When the driver is + finished with this transfer, it must call + spi_finalize_current_transfer() so the subsystem can issue the next + transfer. This may sleep. Note: transfer_one and transfer_one_message + are mutually exclusive; when both are set, the generic subsystem does + not call your transfer_one callback. + + Return values: + negative errno: error + 0: transfer is finished + 1: transfer is still in progress DEPRECATED METHODS diff --git a/Documentation/timers/00-INDEX b/Documentation/timers/00-INDEX index ef2ccbf77fa2..6d042dc1cce0 100644 --- a/Documentation/timers/00-INDEX +++ b/Documentation/timers/00-INDEX @@ -8,6 +8,8 @@ hpet_example.c - sample hpet timer test program hrtimers.txt - subsystem for high-resolution kernel timers +Makefile + - Build and link hpet_example NO_HZ.txt - Summary of the different methods for the scheduler clock-interrupts management. timers-howto.txt diff --git a/Documentation/virtual/kvm/00-INDEX b/Documentation/virtual/kvm/00-INDEX index 641ec9220179..fee9f2bf9c64 100644 --- a/Documentation/virtual/kvm/00-INDEX +++ b/Documentation/virtual/kvm/00-INDEX @@ -20,5 +20,7 @@ ppc-pv.txt - the paravirtualization interface on PowerPC. review-checklist.txt - review checklist for KVM patches. +s390-diag.txt + - Diagnose hypercall description (for IBM S/390) timekeeping.txt - timekeeping virtualization for x86-based architectures. diff --git a/Documentation/vm/00-INDEX b/Documentation/vm/00-INDEX index a39d06680e1c..081c49777abb 100644 --- a/Documentation/vm/00-INDEX +++ b/Documentation/vm/00-INDEX @@ -16,8 +16,6 @@ hwpoison.txt - explains what hwpoison is ksm.txt - how to use the Kernel Samepage Merging feature. -locking - - info on how locking and synchronization is done in the Linux vm code. numa - information about NUMA specific code in the Linux vm. numa_memory_policy.txt @@ -32,6 +30,8 @@ slub.txt - a short users guide for SLUB. soft-dirty.txt - short explanation for soft-dirty PTEs +split_page_table_lock + - Separate per-table lock to improve scalability of the old page_table_lock. transhuge.txt - Transparent Hugepage Support, alternative way of using hugepages. unevictable-lru.txt diff --git a/Documentation/w1/masters/00-INDEX b/Documentation/w1/masters/00-INDEX index d63fa024ac05..8330cf9325f0 100644 --- a/Documentation/w1/masters/00-INDEX +++ b/Documentation/w1/masters/00-INDEX @@ -4,7 +4,9 @@ ds2482 - The Maxim/Dallas Semiconductor DS2482 provides 1-wire busses. ds2490 - The Maxim/Dallas Semiconductor DS2490 builds USB <-> W1 bridges. -mxc_w1 +mxc-w1 - W1 master controller driver found on Freescale MX2/MX3 SoCs +omap-hdq + - HDQ/1-wire module of TI OMAP 2430/3430. w1-gpio - GPIO 1-wire bus master driver. diff --git a/Documentation/w1/slaves/00-INDEX b/Documentation/w1/slaves/00-INDEX index 75613c9ac4db..6e18c70c3474 100644 --- a/Documentation/w1/slaves/00-INDEX +++ b/Documentation/w1/slaves/00-INDEX @@ -4,3 +4,5 @@ w1_therm - The Maxim/Dallas Semiconductor ds18*20 temperature sensor. w1_ds2423 - The Maxim/Dallas Semiconductor ds2423 counter device. +w1_ds28e04 + - The Maxim/Dallas Semiconductor ds28e04 eeprom. diff --git a/Documentation/x86/00-INDEX b/Documentation/x86/00-INDEX index f37b46d34861..692264456f0f 100644 --- a/Documentation/x86/00-INDEX +++ b/Documentation/x86/00-INDEX @@ -1,6 +1,20 @@ 00-INDEX - this file -mtrr.txt - - how to use x86 Memory Type Range Registers to increase performance +boot.txt + - List of boot protocol versions +early-microcode.txt + - How to load microcode from an initrd-CPIO archive early to fix CPU issues. +earlyprintk.txt + - Using earlyprintk with a USB2 debug port key. +entry_64.txt + - Describe (some of the) kernel entry points for x86. exception-tables.txt - why and how Linux kernel uses exception tables on x86 +mtrr.txt + - how to use x86 Memory Type Range Registers to increase performance +pat.txt + - Page Attribute Table intro and API +usb-legacy-support.txt + - how to fix/avoid quirks when using emulated PS/2 mouse/keyboard. +zero-page.txt + - layout of the first page of memory. diff --git a/Documentation/zh_CN/arm64/booting.txt b/Documentation/zh_CN/arm64/booting.txt index 28fa325b7461..6f6d956ac1c9 100644 --- a/Documentation/zh_CN/arm64/booting.txt +++ b/Documentation/zh_CN/arm64/booting.txt @@ -7,7 +7,7 @@ help. Contact the Chinese maintainer if this translation is outdated or if there is a problem with the translation. Maintainer: Will Deacon <will.deacon@arm.com> -Chinese maintainer: Fu Wei <tekkamanninja@gmail.com> +Chinese maintainer: Fu Wei <wefu@redhat.com> --------------------------------------------------------------------- Documentation/arm64/booting.txt çš„ä¸æ–‡ç¿»è¯‘ @@ -16,9 +16,9 @@ Documentation/arm64/booting.txt çš„ä¸æ–‡ç¿»è¯‘ 译å˜åœ¨é—®é¢˜ï¼Œè¯·è”ç³»ä¸æ–‡ç‰ˆç»´æŠ¤è€…。 英文版维护者： Will Deacon <will.deacon@arm.com> -ä¸æ–‡ç‰ˆç»´æŠ¤è€…： å‚…ç‚œ Fu Wei <tekkamanninja@gmail.com> -ä¸æ–‡ç‰ˆç¿»è¯‘者： å‚…ç‚œ Fu Wei <tekkamanninja@gmail.com> -ä¸æ–‡ç‰ˆæ ¡è¯‘者： å‚…ç‚œ Fu Wei <tekkamanninja@gmail.com> +ä¸æ–‡ç‰ˆç»´æŠ¤è€…： å‚…ç‚œ Fu Wei <wefu@redhat.com> +ä¸æ–‡ç‰ˆç¿»è¯‘者： å‚…ç‚œ Fu Wei <wefu@redhat.com> +ä¸æ–‡ç‰ˆæ ¡è¯‘者： å‚…ç‚œ Fu Wei <wefu@redhat.com> 以下为æ£æ–‡ --------------------------------------------------------------------- @@ -64,8 +64,8 @@ RAM，或å¯èƒ½ä½¿ç”¨å¯¹è¿™ä¸ªè®¾å¤‡å·²çŸ¥çš„ RAM ä¿¡æ¯ï¼Œè¿˜å¯èƒ½ä½¿ç”¨ä»»ä½• å¿…è¦æ€§: 强制 -è®¾å¤‡æ ‘æ•°æ®å—（dtb）大å°å¿…é¡»ä¸å¤§äºŽ 2 MB，且ä½äºŽä»Žå†…æ ¸æ˜ åƒèµ·å§‹ç®—起第一个 -512MB 内的 2MB è¾¹ç•Œä¸Šã€‚è¿™ä½¿å¾—å†…æ ¸å¯ä»¥é€šè¿‡åˆå§‹é¡µè¡¨ä¸çš„å•ä¸ªèŠ‚æè¿°ç¬¦æ¥ +è®¾å¤‡æ ‘æ•°æ®å—（dtb）必须 8 å—节对é½ï¼Œå¹¶ä½äºŽä»Žå†…æ ¸æ˜ åƒèµ·å§‹ç®—起第一个 512MB +内，且ä¸å¾—跨越 2MB 对é½è¾¹ç•Œã€‚è¿™ä½¿å¾—å†…æ ¸å¯ä»¥é€šè¿‡åˆå§‹é¡µè¡¨ä¸çš„å•ä¸ªèŠ‚æè¿°ç¬¦æ¥ æ˜ å°„æ¤æ•°æ®å—。 @@ -84,13 +84,23 @@ AArch64 å†…æ ¸å½“å‰æ²¡æœ‰æ供自解压代ç ï¼Œå› æ¤å¦‚果使用了压缩内 å¿…è¦æ€§: 强制 -å·²è§£åŽ‹çš„å†…æ ¸æ˜ åƒåŒ…å«ä¸€ä¸ª 32 å—节的头，内容如下： +å·²è§£åŽ‹çš„å†…æ ¸æ˜ åƒåŒ…å«ä¸€ä¸ª 64 å—节的头，内容如下： - u32 magic = 0x14000008; /* 跳转到 stext, å°ç«¯ */ - u32 res0 = 0; /* ä¿ç•™ */ + u32 code0; /* å¯æ‰§è¡Œä»£ç */ + u32 code1; /* å¯æ‰§è¡Œä»£ç */ u64 text_offset; /* æ˜ åƒè£…è½½å移 */ + u64 res0 = 0; /* ä¿ç•™ */ u64 res1 = 0; /* ä¿ç•™ */ u64 res2 = 0; /* ä¿ç•™ */ + u64 res3 = 0; /* ä¿ç•™ */ + u64 res4 = 0; /* ä¿ç•™ */ + u32 magic = 0x644d5241; /* é”æ•°, å°ç«¯, "ARM\x64" */ + u32 res5 = 0; /* ä¿ç•™ */ + + +æ˜ åƒå¤´æ³¨é‡Šï¼š + +- code0/code1 负责跳转到 stext. æ˜ åƒå¿…é¡»ä½äºŽç³»ç»Ÿ RAM 起始处的特定å移（当å‰æ˜¯ 0x80000）。系统 RAM 的起始地å€å¿…须是以 2MB 对é½çš„。 @@ -118,9 +128,9 @@ AArch64 å†…æ ¸å½“å‰æ²¡æœ‰æ供自解压代ç ï¼Œå› æ¤å¦‚果使用了压缩内 外部高速缓å˜ï¼ˆå¦‚æžœå˜åœ¨ï¼‰å¿…é¡»é…置并ç¦ç”¨ã€‚ - 架构计时器 - CNTFRQ 必须设定为计时器的频率。 - 如果在 EL1 模å¼ä¸‹è¿›å…¥å†…æ ¸ï¼Œåˆ™ CNTHCTL_EL2 ä¸çš„ EL1PCTEN (bit 0) - 必须置ä½ã€‚ + CNTFRQ 必须设定为计时器的频率，且 CNTVOFF 必须设定为对所有 CPU + 都一致的值。如果在 EL1 模å¼ä¸‹è¿›å…¥å†…æ ¸ï¼Œåˆ™ CNTHCTL_EL2 ä¸çš„ + EL1PCTEN (bit 0) 必须置ä½ã€‚ - 一致性 é€šè¿‡å†…æ ¸å¯åŠ¨çš„所有 CPU åœ¨å†…æ ¸å…¥å£åœ°å€ä¸Šå¿…须处于相åŒçš„一致性域ä¸ã€‚ @@ -131,23 +141,40 @@ AArch64 å†…æ ¸å½“å‰æ²¡æœ‰æ供自解压代ç ï¼Œå› æ¤å¦‚果使用了压缩内 åœ¨è¿›å…¥å†…æ ¸æ˜ åƒçš„异常级ä¸ï¼Œæ‰€æœ‰æž„架ä¸å¯å†™çš„系统寄å˜å™¨å¿…须通过软件 在一个更高的异常级别下åˆå§‹åŒ–，以防æ¢åœ¨ 未知 状æ€ä¸‹è¿è¡Œã€‚ +以上对于 CPU 模å¼ã€é«˜é€Ÿç¼“å˜ã€MMUã€æž¶æž„计时器ã€ä¸€è‡´æ€§ã€ç³»ç»Ÿå¯„å˜å™¨çš„ +å¿…è¦æ¡ä»¶æ述适用于所有 CPU。所有 CPU 必须在åŒä¸€å¼‚å¸¸çº§åˆ«è·³å…¥å†…æ ¸ã€‚ + 引导装载程åºå¿…须在æ¯ä¸ª CPU 处于以下状æ€æ—¶è·³å…¥å†…æ ¸å…¥å£ï¼š - 主 CPU å¿…é¡»ç›´æŽ¥è·³å…¥å†…æ ¸æ˜ åƒçš„第一æ¡æŒ‡ä»¤ã€‚é€šè¿‡æ¤ CPU ä¼ é€’çš„è®¾å¤‡æ ‘ - æ•°æ®å—必须在æ¯ä¸ª CPU 节点ä¸åŒ…å«ä»¥ä¸‹å†…容： - - 1ã€â€˜enable-method’属性。目å‰ï¼Œæ¤å—段支æŒçš„值仅为å—符串“spin-tableâ€ã€‚ - - 2ã€â€˜cpu-release-addrâ€™æ ‡è¯†ä¸€ä¸ª 64-bitã€åˆå§‹åŒ–为零的内å˜ä½ç½®ã€‚ + æ•°æ®å—必须在æ¯ä¸ª CPU 节点ä¸åŒ…å«ä¸€ä¸ª ‘enable-method’ 属性，所 + 支æŒçš„ enable-method 请è§ä¸‹æ–‡ã€‚ 引导装载程åºå¿…须生æˆè¿™äº›è®¾å¤‡æ ‘å±žæ€§ï¼Œå¹¶åœ¨è·³å…¥å†…æ ¸å…¥å£ä¹‹å‰å°†å…¶æ’å…¥ æ•°æ®å—。 -- 任何辅助 CPU 必须在内å˜ä¿ç•™åŒºï¼ˆé€šè¿‡è®¾å¤‡æ ‘ä¸çš„ /memreserve/ åŸŸä¼ é€’ +- enable-method 为 “spin-table†的 CPU 必须在它们的 CPU + 节点ä¸åŒ…å«ä¸€ä¸ª ‘cpu-release-addr’ å±žæ€§ã€‚è¿™ä¸ªå±žæ€§æ ‡è¯†äº†ä¸€ä¸ª + 64 ä½è‡ªç„¶å¯¹é½ä¸”åˆå§‹åŒ–为零的内å˜ä½ç½®ã€‚ + + 这些 CPU 必须在内å˜ä¿ç•™åŒºï¼ˆé€šè¿‡è®¾å¤‡æ ‘ä¸çš„ /memreserve/ åŸŸä¼ é€’ ç»™å†…æ ¸ï¼‰ä¸è‡ªæ—‹äºŽå†…æ ¸ä¹‹å¤–ï¼Œè½®è¯¢å®ƒä»¬çš„ cpu-release-addr ä½ç½®ï¼ˆå¿…é¡» 包å«åœ¨ä¿ç•™åŒºä¸ï¼‰ã€‚å¯é€šè¿‡æ’å…¥ wfe 指令æ¥é™ä½Žå¿™å¾ªçŽ¯å¼€é”€ï¼Œè€Œä¸» CPU å°† å‘出 sev 指令。当对 cpu-release-addr 所指ä½ç½®çš„读å–æ“作返回éžé›¶å€¼ - 时，CPU 必须直接跳入æ¤å€¼æ‰€æŒ‡å‘的地å€ã€‚ + 时，CPU 必须跳入æ¤å€¼æ‰€æŒ‡å‘的地å€ã€‚æ¤å€¼ä¸ºä¸€ä¸ªå•ç‹¬çš„ 64 ä½å°ç«¯å€¼ï¼Œ + å› æ¤ CPU 须在跳转å‰å°†æ‰€è¯»å–的值转æ¢ä¸ºå…¶æœ¬èº«çš„端模å¼ã€‚ + +- enable-method 为 “psci†的 CPU ä¿æŒåœ¨å†…æ ¸å¤–ï¼ˆæ¯”å¦‚ï¼Œåœ¨ + memory 节点ä¸æè¿°ä¸ºå†…æ ¸ç©ºé—´çš„å†…å˜åŒºå¤–ï¼Œæˆ–åœ¨é€šè¿‡è®¾å¤‡æ ‘ /memreserve/ + 域ä¸æè¿°ä¸ºå†…æ ¸ä¿ç•™åŒºçš„空间ä¸ï¼‰ã€‚å†…æ ¸å°†ä¼šå‘起在 ARM æ–‡æ¡£ï¼ˆç¼–å· + ARM DEN 0022A：用于 ARM 上的电æºçŠ¶æ€å调接å£ç³»ç»Ÿè½¯ä»¶ï¼‰ä¸æè¿°çš„ + CPU_ON 调用æ¥å°† CPU å¸¦å…¥å†…æ ¸ã€‚ + + *译者注:到文档翻译时，æ¤æ–‡æ¡£å·²æ›´æ–°ä¸º ARM DEN 0022B。 + + è®¾å¤‡æ ‘å¿…é¡»åŒ…å«ä¸€ä¸ª ‘psci’ 节点，请å‚考以下文档： + Documentation/devicetree/bindings/arm/psci.txt + - 辅助 CPU 通用寄å˜å™¨è®¾ç½® x0 = 0 (ä¿ç•™ï¼Œå°†æ¥å¯èƒ½ä½¿ç”¨) diff --git a/Documentation/zh_CN/arm64/memory.txt b/Documentation/zh_CN/arm64/memory.txt index a5f6283829f9..a782704c1cb5 100644 --- a/Documentation/zh_CN/arm64/memory.txt +++ b/Documentation/zh_CN/arm64/memory.txt @@ -7,7 +7,7 @@ help. Contact the Chinese maintainer if this translation is outdated or if there is a problem with the translation. Maintainer: Catalin Marinas <catalin.marinas@arm.com> -Chinese maintainer: Fu Wei <tekkamanninja@gmail.com> +Chinese maintainer: Fu Wei <wefu@redhat.com> --------------------------------------------------------------------- Documentation/arm64/memory.txt çš„ä¸æ–‡ç¿»è¯‘ @@ -16,9 +16,9 @@ Documentation/arm64/memory.txt çš„ä¸æ–‡ç¿»è¯‘ 译å˜åœ¨é—®é¢˜ï¼Œè¯·è”ç³»ä¸æ–‡ç‰ˆç»´æŠ¤è€…。 英文版维护者： Catalin Marinas <catalin.marinas@arm.com> -ä¸æ–‡ç‰ˆç»´æŠ¤è€…： å‚…ç‚œ Fu Wei <tekkamanninja@gmail.com> -ä¸æ–‡ç‰ˆç¿»è¯‘者： å‚…ç‚œ Fu Wei <tekkamanninja@gmail.com> -ä¸æ–‡ç‰ˆæ ¡è¯‘者： å‚…ç‚œ Fu Wei <tekkamanninja@gmail.com> +ä¸æ–‡ç‰ˆç»´æŠ¤è€…： å‚…ç‚œ Fu Wei <wefu@redhat.com> +ä¸æ–‡ç‰ˆç¿»è¯‘者： å‚…ç‚œ Fu Wei <wefu@redhat.com> +ä¸æ–‡ç‰ˆæ ¡è¯‘者： å‚…ç‚œ Fu Wei <wefu@redhat.com> 以下为æ£æ–‡ --------------------------------------------------------------------- @@ -41,7 +41,7 @@ AArch64 Linux 使用页大å°ä¸º 4KB çš„ 3 级转æ¢è¡¨é…置，对于用户和å TTBR1 ä¸ï¼Œä¸”从ä¸å†™å…¥ TTBR0。 -AArch64 Linux 内å˜å¸ƒå±€ï¼š +AArch64 Linux 在页大å°ä¸º 4KB 时的内å˜å¸ƒå±€ï¼š èµ·å§‹åœ°å€ ç»“æŸåœ°å€ å¤§å° ç”¨é€” ----------------------------------------------------------------------- @@ -55,15 +55,42 @@ ffffffbc00000000 ffffffbdffffffff 8GB vmemmap ffffffbe00000000 ffffffbffbbfffff ~8GB [防护页，未æ¥ç”¨äºŽ vmmemap] +ffffffbffbc00000 ffffffbffbdfffff 2MB earlyprintk 设备 + ffffffbffbe00000 ffffffbffbe0ffff 64KB PCI I/O 空间 -ffffffbbffff0000 ffffffbcffffffff ~2MB [防护页] +ffffffbffbe10000 ffffffbcffffffff ~2MB [防护页] ffffffbffc000000 ffffffbfffffffff 64MB æ¨¡å— ffffffc000000000 ffffffffffffffff 256GB å†…æ ¸é€»è¾‘å†…å˜æ˜ å°„ +AArch64 Linux 在页大å°ä¸º 64KB 时的内å˜å¸ƒå±€ï¼š + +èµ·å§‹åœ°å€ ç»“æŸåœ°å€ å¤§å° ç”¨é€” +----------------------------------------------------------------------- +0000000000000000 000003ffffffffff 4TB 用户空间 + +fffffc0000000000 fffffdfbfffeffff ~2TB vmalloc + +fffffdfbffff0000 fffffdfbffffffff 64KB [防护页] + +fffffdfc00000000 fffffdfdffffffff 8GB vmemmap + +fffffdfe00000000 fffffdfffbbfffff ~8GB [防护页，未æ¥ç”¨äºŽ vmmemap] + +fffffdfffbc00000 fffffdfffbdfffff 2MB earlyprintk 设备 + +fffffdfffbe00000 fffffdfffbe0ffff 64KB PCI I/O 空间 + +fffffdfffbe10000 fffffdfffbffffff ~2MB [防护页] + +fffffdfffc000000 fffffdffffffffff 64MB æ¨¡å— + +fffffe0000000000 ffffffffffffffff 2TB å†…æ ¸é€»è¾‘å†…å˜æ˜ å°„ + + 4KB 页大å°çš„转æ¢è¡¨æŸ¥æ‰¾ï¼š +--------+--------+--------+--------+--------+--------+--------+--------+ @@ -91,3 +118,10 @@ ffffffc000000000 ffffffffffffffff 256GB å†…æ ¸é€»è¾‘å†…å˜æ˜ å°„ | | +--------------------------> [41:29] L2 索引 (仅使用 38:29 ) | +-------------------------------> [47:42] L1 索引 (未使用) +-------------------------------------------------> [63] TTBR0/1 + +当使用 KVM æ—¶, 管ç†ç¨‹åºï¼ˆhypervisor）在 EL2 ä¸é€šè¿‡ç›¸å¯¹å†…æ ¸è™šæ‹Ÿåœ°å€çš„ +一个固定å移æ¥æ˜ å°„å†…æ ¸é¡µï¼ˆå†…æ ¸è™šæ‹Ÿåœ°å€çš„高 24 ä½è®¾ä¸ºé›¶ï¼‰: + +èµ·å§‹åœ°å€ ç»“æŸåœ°å€ å¤§å° ç”¨é€” +----------------------------------------------------------------------- +0000004000000000 0000007fffffffff 256GB 在 HYP ä¸æ˜ å°„çš„å†…æ ¸å¯¹è±¡ diff --git a/Documentation/zh_CN/arm64/tagged-pointers.txt b/Documentation/zh_CN/arm64/tagged-pointers.txt new file mode 100644 index 000000000000..2664d1bd5a1c --- /dev/null +++ b/Documentation/zh_CN/arm64/tagged-pointers.txt @@ -0,0 +1,52 @@ +Chinese translated version of Documentation/arm64/tagged-pointers.txt + +If you have any comment or update to the content, please contact the +original document maintainer directly. However, if you have a problem +communicating in English you can also ask the Chinese maintainer for +help. Contact the Chinese maintainer if this translation is outdated +or if there is a problem with the translation. + +Maintainer: Will Deacon <will.deacon@arm.com> +Chinese maintainer: Fu Wei <wefu@redhat.com> +--------------------------------------------------------------------- +Documentation/arm64/tagged-pointers.txt çš„ä¸æ–‡ç¿»è¯‘ + +如果想评论或更新本文的内容，请直接è”ç³»åŽŸæ–‡æ¡£çš„ç»´æŠ¤è€…ã€‚å¦‚æžœä½ ä½¿ç”¨è‹±æ–‡ +交æµæœ‰å›°éš¾çš„è¯ï¼Œä¹Ÿå¯ä»¥å‘ä¸æ–‡ç‰ˆç»´æŠ¤è€…求助。如果本翻译更新ä¸åŠæ—¶æˆ–者翻 +译å˜åœ¨é—®é¢˜ï¼Œè¯·è”ç³»ä¸æ–‡ç‰ˆç»´æŠ¤è€…。 + +英文版维护者： Will Deacon <will.deacon@arm.com> +ä¸æ–‡ç‰ˆç»´æŠ¤è€…： å‚…ç‚œ Fu Wei <wefu@redhat.com> +ä¸æ–‡ç‰ˆç¿»è¯‘者： å‚…ç‚œ Fu Wei <wefu@redhat.com> +ä¸æ–‡ç‰ˆæ ¡è¯‘者： å‚…ç‚œ Fu Wei <wefu@redhat.com> + +以下为æ£æ–‡ +--------------------------------------------------------------------- + Linux 在 AArch64 ä¸å¸¦æ ‡è®°çš„è™šæ‹Ÿåœ°å€ + ================================= + +作者: Will Deacon <will.deacon@arm.com> +日期: 2013 å¹´ 06 月 12 æ—¥ + +本文档简述了在 AArch64 地å€è½¬æ¢ç³»ç»Ÿä¸æä¾›çš„å¸¦æ ‡è®°çš„è™šæ‹Ÿåœ°å€åŠå…¶åœ¨ +AArch64 Linux ä¸çš„潜在用途。 + +å†…æ ¸æ供的地å€è½¬æ¢è¡¨é…置使通过 TTBR0 完æˆçš„虚拟地å€è½¬æ¢ï¼ˆå³ç”¨æˆ·ç©ºé—´ +æ˜ å°„ï¼‰ï¼Œå…¶è™šæ‹Ÿåœ°å€çš„最高 8 ä½ï¼ˆ63:56）会被转æ¢ç¡¬ä»¶æ‰€å¿½ç•¥ã€‚è¿™ç§æœºåˆ¶ +让这些ä½å¯ä¾›åº”用程åºè‡ªç”±ä½¿ç”¨ï¼Œå…¶æ³¨æ„事项如下： + + (1) å†…æ ¸è¦æ±‚æ‰€æœ‰ä¼ é€’åˆ° EL1 的用户空间地å€å¸¦æœ‰ 0x00 æ ‡è®°ã€‚ + è¿™æ„味ç€ä»»ä½•æºå¸¦ç”¨æˆ·ç©ºé—´è™šæ‹Ÿåœ°å€çš„系统调用（syscall） + å‚æ•° *å¿…é¡»* åœ¨é™·å…¥å†…æ ¸å‰ä½¿å®ƒä»¬çš„最高å—节被清零。 + + (2) éžé›¶æ ‡è®°åœ¨ä¼ 递信å·æ—¶ä¸è¢«ä¿å˜ã€‚è¿™æ„味ç€åœ¨åº”用程åºä¸åˆ©ç”¨äº† + æ ‡è®°çš„ä¿¡å·å¤„ç†å‡½æ•°æ— 法ä¾èµ– siginfo_t 的用户空间虚拟 + 地å€æ‰€æºå¸¦çš„包å«å…¶å†…部域信æ¯çš„æ ‡è®°ã€‚æ¤è§„则的一个例外是 + 当信å·æ˜¯åœ¨è°ƒè¯•è§‚察点的异常处ç†ç¨‹åºä¸äº§ç”Ÿçš„，æ¤æ—¶æ ‡è®°çš„ + ä¿¡æ¯å°†è¢«ä¿å˜ã€‚ + + (3) å½“ä½¿ç”¨å¸¦æ ‡è®°çš„æŒ‡é’ˆæ—¶éœ€ç‰¹åˆ«ç•™å¿ƒï¼Œå› ä¸ºä»…å¯¹ä¸¤ä¸ªè™šæ‹Ÿåœ°å€ + 的高å—节，C 编译器很å¯èƒ½æ— 法判æ–它们是ä¸åŒçš„。 + +æ¤æž„架会阻æ¢å¯¹å¸¦æ ‡è®°çš„ PC æŒ‡é’ˆçš„åˆ©ç”¨ï¼Œå› æ¤åœ¨å¼‚常返回时，其高å—节 +将被设置æˆä¸€ä¸ªä¸º “55†的扩展符。 diff --git a/MAINTAINERS b/MAINTAINERS index b2cf5cfb4d29..e4ee191f9ffa 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -73,7 +73,8 @@ Descriptions of section entries: L: Mailing list that is relevant to this area W: Web-page with status/info Q: Patchwork web based patch tracking system site - T: SCM tree type and location. Type is one of: git, hg, quilt, stgit, topgit. + T: SCM tree type and location. + Type is one of: git, hg, quilt, stgit, topgit S: Status, one of the following: Supported: Someone is actually paid to look after this. Maintained: Someone actually looks after it. @@ -538,7 +539,7 @@ F: arch/alpha/ ALTERA UART/JTAG UART SERIAL DRIVERS M: Tobias Klauser <tklauser@distanz.ch> L: linux-serial@vger.kernel.org -L: nios2-dev@sopc.et.ntust.edu.tw (moderated for non-subscribers) +L: nios2-dev@lists.rocketboards.org (moderated for non-subscribers) S: Maintained F: drivers/tty/serial/altera_uart.c F: drivers/tty/serial/altera_jtaguart.c @@ -1612,11 +1613,11 @@ S: Maintained F: drivers/net/wireless/atmel* ATTO EXPRESSSAS SAS/SATA RAID SCSI DRIVER -M: Bradley Grove <linuxdrivers@attotech.com> -L: linux-scsi@vger.kernel.org -W: http://www.attotech.com -S: Supported -F: drivers/scsi/esas2r +M: Bradley Grove <linuxdrivers@attotech.com> +L: linux-scsi@vger.kernel.org +W: http://www.attotech.com +S: Supported +F: drivers/scsi/esas2r AUDIT SUBSYSTEM M: Eric Paris <eparis@redhat.com> @@ -1845,6 +1846,12 @@ L: netdev@vger.kernel.org S: Supported F: drivers/net/ethernet/broadcom/b44.* +BROADCOM GENET ETHERNET DRIVER +M: Florian Fainelli <f.fainelli@gmail.com> +L: netdev@vger.kernel.org +S: Supported +F: drivers/net/ethernet/broadcom/genet/ + BROADCOM BNX2 GIGABIT ETHERNET DRIVER M: Michael Chan <mchan@broadcom.com> L: netdev@vger.kernel.org @@ -1860,6 +1867,7 @@ F: drivers/net/ethernet/broadcom/bnx2x/ BROADCOM BCM281XX/BCM11XXX ARM ARCHITECTURE M: Christian Daudt <bcm@fixthebug.org> +M: Matt Porter <mporter@linaro.org> L: bcm-kernel-feedback-list@broadcom.com T: git git://git.github.com/broadcom/bcm11351 S: Maintained @@ -2158,7 +2166,7 @@ F: Documentation/zh_CN/ CHIPIDEA USB HIGH SPEED DUAL ROLE CONTROLLER M: Peter Chen <Peter.Chen@freescale.com> -T: git://github.com/hzpeterchen/linux-usb.git +T: git git://github.com/hzpeterchen/linux-usb.git L: linux-usb@vger.kernel.org S: Maintained F: drivers/usb/chipidea/ @@ -2178,9 +2186,9 @@ S: Supported F: drivers/net/ethernet/cisco/enic/ CISCO VIC LOW LATENCY NIC DRIVER -M: Upinder Malhi <umalhi@cisco.com> -S: Supported -F: drivers/infiniband/hw/usnic +M: Upinder Malhi <umalhi@cisco.com> +S: Supported +F: drivers/infiniband/hw/usnic CIRRUS LOGIC EP93XX ETHERNET DRIVER M: Hartley Sweeten <hsweeten@visionengravers.com> @@ -2367,7 +2375,7 @@ F: include/linux/cpufreq.h CPU FREQUENCY DRIVERS - ARM BIG LITTLE M: Viresh Kumar <viresh.kumar@linaro.org> -M: Sudeep KarkadaNagesha <sudeep.karkadanagesha@arm.com> +M: Sudeep Holla <sudeep.holla@arm.com> L: cpufreq@vger.kernel.org L: linux-pm@vger.kernel.org W: http://www.arm.com/products/processors/technologies/biglittleprocessing.php @@ -2377,20 +2385,20 @@ F: drivers/cpufreq/arm_big_little.c F: drivers/cpufreq/arm_big_little_dt.c CPUIDLE DRIVER - ARM BIG LITTLE -M: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> -M: Daniel Lezcano <daniel.lezcano@linaro.org> -L: linux-pm@vger.kernel.org -L: linux-arm-kernel@lists.infradead.org -T: git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm.git -S: Maintained -F: drivers/cpuidle/cpuidle-big_little.c +M: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> +M: Daniel Lezcano <daniel.lezcano@linaro.org> +L: linux-pm@vger.kernel.org +L: linux-arm-kernel@lists.infradead.org +T: git git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm.git +S: Maintained +F: drivers/cpuidle/cpuidle-big_little.c CPUIDLE DRIVERS M: Rafael J. Wysocki <rjw@rjwysocki.net> M: Daniel Lezcano <daniel.lezcano@linaro.org> L: linux-pm@vger.kernel.org S: Maintained -T: git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm.git F: drivers/cpuidle/* F: include/linux/cpuidle.h @@ -2408,8 +2416,10 @@ F: tools/power/cpupower/ CPUSETS M: Li Zefan <lizefan@huawei.com> +L: cgroups@vger.kernel.org W: http://www.bullopensource.org/cpuset/ W: http://oss.sgi.com/projects/cpusets/ +T: git git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup.git S: Maintained F: Documentation/cgroups/cpusets.txt F: include/linux/cpuset.h @@ -2455,9 +2465,9 @@ S: Maintained F: sound/pci/cs5535audio/ CW1200 WLAN driver -M: Solomon Peachy <pizza@shaftnet.org> -S: Maintained -F: drivers/net/wireless/cw1200/ +M: Solomon Peachy <pizza@shaftnet.org> +S: Maintained +F: drivers/net/wireless/cw1200/ CX18 VIDEO4LINUX DRIVER M: Andy Walls <awalls@md.metrocast.net> @@ -2608,9 +2618,9 @@ DC395x SCSI driver M: Oliver Neukum <oliver@neukum.org> M: Ali Akcaagac <aliakc@web.de> M: Jamie Lenehan <lenehan@twibble.org> -W: http://twibble.org/dist/dc395x/ L: dc395x@twibble.org -L: http://lists.twibble.org/mailman/listinfo/dc395x/ +W: http://twibble.org/dist/dc395x/ +W: http://lists.twibble.org/mailman/listinfo/dc395x/ S: Maintained F: Documentation/scsi/dc395x.txt F: drivers/scsi/dc395x.* @@ -2845,19 +2855,29 @@ F: lib/kobj* DRM DRIVERS M: David Airlie <airlied@linux.ie> L: dri-devel@lists.freedesktop.org -T: git git://git.kernel.org/pub/scm/linux/kernel/git/airlied/drm-2.6.git +T: git git://people.freedesktop.org/~airlied/linux S: Maintained F: drivers/gpu/drm/ F: include/drm/ F: include/uapi/drm/ +RADEON DRM DRIVERS +M: Alex Deucher <alexander.deucher@amd.com> +M: Christian König <christian.koenig@amd.com> +L: dri-devel@lists.freedesktop.org +T: git git://people.freedesktop.org/~agd5f/linux +S: Supported +F: drivers/gpu/drm/radeon/ +F: include/drm/radeon* +F: include/uapi/drm/radeon* + INTEL DRM DRIVERS (excluding Poulsbo, Moorestown and derivative chipsets) M: Daniel Vetter <daniel.vetter@ffwll.ch> M: Jani Nikula <jani.nikula@linux.intel.com> L: intel-gfx@lists.freedesktop.org L: dri-devel@lists.freedesktop.org Q: http://patchwork.freedesktop.org/project/intel-gfx/ -T: git git://people.freedesktop.org/~danvet/drm-intel +T: git git://anongit.freedesktop.org/drm-intel S: Supported F: drivers/gpu/drm/i915/ F: include/drm/i915* @@ -3082,6 +3102,8 @@ F: fs/ecryptfs/ EDAC-CORE M: Doug Thompson <dougthompson@xmission.com> +M: Borislav Petkov <bp@alien8.de> +M: Mauro Carvalho Chehab <m.chehab@samsung.com> L: linux-edac@vger.kernel.org W: bluesmoke.sourceforge.net S: Supported @@ -3324,6 +3346,17 @@ S: Maintained F: include/linux/netfilter_bridge/ F: net/bridge/ +ETHERNET PHY LIBRARY +M: Florian Fainelli <f.fainelli@gmail.com> +L: netdev@vger.kernel.org +S: Maintained +F: include/linux/phy.h +F: include/linux/phy_fixed.h +F: drivers/net/phy/ +F: Documentation/networking/phy.txt +F: drivers/of/of_mdio.c +F: drivers/of/of_net.c + EXT2 FILE SYSTEM M: Jan Kara <jack@suse.cz> L: linux-ext4@vger.kernel.org @@ -4534,6 +4567,7 @@ F: Documentation/networking/ixgbevf.txt F: Documentation/networking/i40e.txt F: Documentation/networking/i40evf.txt F: drivers/net/ethernet/intel/ +F: drivers/net/ethernet/intel/*/ INTEL-MID GPIO DRIVER M: David Cohen <david.a.cohen@linux.intel.com> @@ -4890,7 +4924,7 @@ F: drivers/staging/ktap/ KCONFIG M: "Yann E. MORIN" <yann.morin.1998@free.fr> L: linux-kbuild@vger.kernel.org -T: git://gitorious.org/linux-kconfig/linux-kconfig +T: git git://gitorious.org/linux-kconfig/linux-kconfig S: Maintained F: Documentation/kbuild/kconfig-language.txt F: scripts/kconfig/ @@ -5447,11 +5481,11 @@ S: Maintained F: drivers/media/tuners/m88ts2022* MA901 MASTERKIT USB FM RADIO DRIVER -M: Alexey Klimov <klimov.linux@gmail.com> -L: linux-media@vger.kernel.org -T: git git://linuxtv.org/media_tree.git -S: Maintained -F: drivers/media/radio/radio-ma901.c +M: Alexey Klimov <klimov.linux@gmail.com> +L: linux-media@vger.kernel.org +T: git git://linuxtv.org/media_tree.git +S: Maintained +F: drivers/media/radio/radio-ma901.c MAC80211 M: Johannes Berg <johannes@sipsolutions.net> @@ -5487,6 +5521,11 @@ W: http://www.kernel.org/doc/man-pages L: linux-man@vger.kernel.org S: Maintained +MARVELL ARMADA DRM SUPPORT +M: Russell King <rmk+kernel@arm.linux.org.uk> +S: Maintained +F: drivers/gpu/drm/armada/ + MARVELL GIGABIT ETHERNET DRIVERS (skge/sky2) M: Mirko Lindner <mlindner@marvell.com> M: Stephen Hemminger <stephen@networkplumber.org> @@ -5607,7 +5646,7 @@ F: drivers/scsi/megaraid/ MELLANOX ETHERNET DRIVER (mlx4_en) M: Amir Vadai <amirv@mellanox.com> -L: netdev@vger.kernel.org +L: netdev@vger.kernel.org S: Supported W: http://www.mellanox.com Q: http://patchwork.ozlabs.org/project/netdev/list/ @@ -5648,7 +5687,7 @@ F: include/linux/mtd/ F: include/uapi/mtd/ MEN A21 WATCHDOG DRIVER -M: Johannes Thumshirn <johannes.thumshirn@men.de> +M: Johannes Thumshirn <johannes.thumshirn@men.de> L: linux-watchdog@vger.kernel.org S: Supported F: drivers/watchdog/mena21_wdt.c @@ -5704,20 +5743,20 @@ L: linux-rdma@vger.kernel.org W: http://www.mellanox.com Q: http://patchwork.ozlabs.org/project/netdev/list/ Q: http://patchwork.kernel.org/project/linux-rdma/list/ -T: git://openfabrics.org/~eli/connect-ib.git +T: git git://openfabrics.org/~eli/connect-ib.git S: Supported F: drivers/net/ethernet/mellanox/mlx5/core/ F: include/linux/mlx5/ Mellanox MLX5 IB driver -M: Eli Cohen <eli@mellanox.com> -L: linux-rdma@vger.kernel.org -W: http://www.mellanox.com -Q: http://patchwork.kernel.org/project/linux-rdma/list/ -T: git://openfabrics.org/~eli/connect-ib.git -S: Supported -F: include/linux/mlx5/ -F: drivers/infiniband/hw/mlx5/ +M: Eli Cohen <eli@mellanox.com> +L: linux-rdma@vger.kernel.org +W: http://www.mellanox.com +Q: http://patchwork.kernel.org/project/linux-rdma/list/ +T: git git://openfabrics.org/~eli/connect-ib.git +S: Supported +F: include/linux/mlx5/ +F: drivers/infiniband/hw/mlx5/ MODULE SUPPORT M: Rusty Russell <rusty@rustcorp.com.au> @@ -5992,6 +6031,7 @@ L: netdev@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec.git T: git git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec-next.git S: Maintained +F: net/core/flow.c F: net/xfrm/ F: net/key/ F: net/ipv4/xfrm* @@ -7020,13 +7060,8 @@ F: Documentation/networking/LICENSE.qla3xxx F: drivers/net/ethernet/qlogic/qla3xxx.* QLOGIC QLCNIC (1/10)Gb ETHERNET DRIVER -M: Himanshu Madhani <himanshu.madhani@qlogic.com> -M: Rajesh Borundia <rajesh.borundia@qlogic.com> M: Shahed Shaikh <shahed.shaikh@qlogic.com> -M: Jitendra Kalsaria <jitendra.kalsaria@qlogic.com> -M: Sony Chacko <sony.chacko@qlogic.com> -M: Sucheta Chakraborty <sucheta.chakraborty@qlogic.com> -M: linux-driver@qlogic.com +M: Dept-HSGLinuxNICDev@qlogic.com L: netdev@vger.kernel.org S: Supported F: drivers/net/ethernet/qlogic/qlcnic/ @@ -7196,7 +7231,7 @@ S: Maintained F: drivers/net/ethernet/rdc/r6040.c RDS - RELIABLE DATAGRAM SOCKETS -M: Venkat Venkatsubra <venkat.x.venkatsubra@oracle.com> +M: Chien Yen <chien.yen@oracle.com> L: rds-devel@oss.oracle.com (moderated for non-subscribers) S: Supported F: net/rds/ @@ -8429,8 +8464,8 @@ TARGET SUBSYSTEM M: Nicholas A. Bellinger <nab@linux-iscsi.org> L: linux-scsi@vger.kernel.org L: target-devel@vger.kernel.org -L: http://groups.google.com/group/linux-iscsi-target-dev W: http://www.linux-iscsi.org +W: http://groups.google.com/group/linux-iscsi-target-dev T: git git://git.kernel.org/pub/scm/linux/kernel/git/nab/target-pending.git master S: Supported F: drivers/target/ @@ -8671,17 +8706,17 @@ S: Maintained F: drivers/media/radio/radio-raremono.c THERMAL -M: Zhang Rui <rui.zhang@intel.com> -M: Eduardo Valentin <eduardo.valentin@ti.com> -L: linux-pm@vger.kernel.org -T: git git://git.kernel.org/pub/scm/linux/kernel/git/rzhang/linux.git -T: git git://git.kernel.org/pub/scm/linux/kernel/git/evalenti/linux-soc-thermal.git -Q: https://patchwork.kernel.org/project/linux-pm/list/ -S: Supported -F: drivers/thermal/ -F: include/linux/thermal.h -F: include/linux/cpu_cooling.h -F: Documentation/devicetree/bindings/thermal/ +M: Zhang Rui <rui.zhang@intel.com> +M: Eduardo Valentin <eduardo.valentin@ti.com> +L: linux-pm@vger.kernel.org +T: git git://git.kernel.org/pub/scm/linux/kernel/git/rzhang/linux.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/evalenti/linux-soc-thermal.git +Q: https://patchwork.kernel.org/project/linux-pm/list/ +S: Supported +F: drivers/thermal/ +F: include/linux/thermal.h +F: include/linux/cpu_cooling.h +F: Documentation/devicetree/bindings/thermal/ THINGM BLINK(1) USB RGB LED DRIVER M: Vivien Didelot <vivien.didelot@savoirfairelinux.com> @@ -9715,7 +9750,6 @@ F: drivers/xen/*swiotlb* XFS FILESYSTEM P: Silicon Graphics Inc M: Dave Chinner <david@fromorbit.com> -M: Ben Myers <bpm@sgi.com> M: xfs@oss.sgi.com L: xfs@oss.sgi.com W: http://oss.sgi.com/projects/xfs @@ -9784,7 +9818,7 @@ ZR36067 VIDEO FOR LINUX DRIVER L: mjpeg-users@lists.sourceforge.net L: linux-media@vger.kernel.org W: http://mjpeg.sourceforge.net/driver-zoran/ -T: Mercurial http://linuxtv.org/hg/v4l-dvb +T: hg http://linuxtv.org/hg/v4l-dvb S: Odd Fixes F: drivers/media/pci/zoran/ @@ -1,7 +1,7 @@ VERSION = 3 PATCHLEVEL = 14 SUBLEVEL = 0 -EXTRAVERSION = -rc2 +EXTRAVERSION = -rc5 NAME = Shuffling Zombie Juror # *DOCUMENTATION* @@ -605,10 +605,11 @@ endif ifdef CONFIG_CC_STACKPROTECTOR_REGULAR stackp-flag := -fstack-protector ifeq ($(call cc-option, $(stackp-flag)),) - $(warning Cannot use CONFIG_CC_STACKPROTECTOR: \ - -fstack-protector not supported by compiler)) + $(warning Cannot use CONFIG_CC_STACKPROTECTOR_REGULAR: \ + -fstack-protector not supported by compiler) endif -else ifdef CONFIG_CC_STACKPROTECTOR_STRONG +else +ifdef CONFIG_CC_STACKPROTECTOR_STRONG stackp-flag := -fstack-protector-strong ifeq ($(call cc-option, $(stackp-flag)),) $(warning Cannot use CONFIG_CC_STACKPROTECTOR_STRONG: \ @@ -618,6 +619,7 @@ else # Force off for distro compilers that enable stack protector by default. stackp-flag := $(call cc-option, -fno-stack-protector) endif +endif KBUILD_CFLAGS += $(stackp-flag) # This warning generated too much noise in a regular build. diff --git a/arch/arm/boot/dts/Makefile b/arch/arm/boot/dts/Makefile index b9d6a8b485e0..032030361bef 100644 --- a/arch/arm/boot/dts/Makefile +++ b/arch/arm/boot/dts/Makefile @@ -38,6 +38,7 @@ dtb-$(CONFIG_ARCH_AT91) += at91sam9g35ek.dtb dtb-$(CONFIG_ARCH_AT91) += at91sam9x25ek.dtb dtb-$(CONFIG_ARCH_AT91) += at91sam9x35ek.dtb # sama5d3 +dtb-$(CONFIG_ARCH_AT91) += at91-sama5d3_xplained.dtb dtb-$(CONFIG_ARCH_AT91) += sama5d31ek.dtb dtb-$(CONFIG_ARCH_AT91) += sama5d33ek.dtb dtb-$(CONFIG_ARCH_AT91) += sama5d34ek.dtb @@ -208,7 +209,8 @@ dtb-$(CONFIG_ARCH_OMAP2PLUS) += omap2420-h4.dtb \ omap3-n900.dtb \ omap3-n9.dtb \ omap3-n950.dtb \ - omap3-tobi.dtb \ + omap3-overo-tobi.dtb \ + omap3-overo-storm-tobi.dtb \ omap3-gta04.dtb \ omap3-igep0020.dtb \ omap3-igep0030.dtb \ diff --git a/arch/arm/boot/dts/am335x-evmsk.dts b/arch/arm/boot/dts/am335x-evmsk.dts index 4718ec4a4dbf..486880b74831 100644 --- a/arch/arm/boot/dts/am335x-evmsk.dts +++ b/arch/arm/boot/dts/am335x-evmsk.dts @@ -121,7 +121,7 @@ ti,model = "AM335x-EVMSK"; ti,audio-codec = <&tlv320aic3106>; ti,mcasp-controller = <&mcasp1>; - ti,codec-clock-rate = <24576000>; + ti,codec-clock-rate = <24000000>; ti,audio-routing = "Headphone Jack", "HPLOUT", "Headphone Jack", "HPROUT"; @@ -256,6 +256,12 @@ >; }; + mmc1_pins: pinmux_mmc1_pins { + pinctrl-single,pins = < + 0x160 (PIN_INPUT | MUX_MODE7) /* spi0_cs1.gpio0_6 */ + >; + }; + mcasp1_pins: mcasp1_pins { pinctrl-single,pins = < 0x10c (PIN_INPUT_PULLDOWN | MUX_MODE4) /* mii1_crs.mcasp1_aclkx */ @@ -456,6 +462,9 @@ status = "okay"; vmmc-supply = <&vmmc_reg>; bus-width = <4>; + pinctrl-names = "default"; + pinctrl-0 = <&mmc1_pins>; + cd-gpios = <&gpio0 6 GPIO_ACTIVE_HIGH>; }; &sham { diff --git a/arch/arm/boot/dts/armada-xp-mv78260.dtsi b/arch/arm/boot/dts/armada-xp-mv78260.dtsi index 66609684d41b..9480cf891f8c 100644 --- a/arch/arm/boot/dts/armada-xp-mv78260.dtsi +++ b/arch/arm/boot/dts/armada-xp-mv78260.dtsi @@ -23,6 +23,7 @@ gpio0 = &gpio0; gpio1 = &gpio1; gpio2 = &gpio2; + eth3 = ð3; }; cpus { @@ -291,7 +292,7 @@ interrupts = <91>; }; - ethernet@34000 { + eth3: ethernet@34000 { compatible = "marvell,armada-370-neta"; reg = <0x34000 0x4000>; interrupts = <14>; diff --git a/arch/arm/boot/dts/at91-sama5d3_xplained.dts b/arch/arm/boot/dts/at91-sama5d3_xplained.dts new file mode 100644 index 000000000000..ce1375595e5f --- /dev/null +++ b/arch/arm/boot/dts/at91-sama5d3_xplained.dts @@ -0,0 +1,229 @@ +/* + * at91-sama5d3_xplained.dts - Device Tree file for the SAMA5D3 Xplained board + * + * Copyright (C) 2014 Atmel, + * 2014 Nicolas Ferre <nicolas.ferre@atmel.com> + * + * Licensed under GPLv2 or later. + */ +/dts-v1/; +#include "sama5d36.dtsi" + +/ { + model = "SAMA5D3 Xplained"; + compatible = "atmel,sama5d3-xplained", "atmel,sama5d3", "atmel,sama5"; + + chosen { + bootargs = "console=ttyS0,115200"; + }; + + memory { + reg = <0x20000000 0x10000000>; + }; + + ahb { + apb { + mmc0: mmc@f0000000 { + pinctrl-0 = <&pinctrl_mmc0_clk_cmd_dat0 &pinctrl_mmc0_dat1_3 &pinctrl_mmc0_dat4_7 &pinctrl_mmc0_cd>; + status = "okay"; + slot@0 { + reg = <0>; + bus-width = <8>; + cd-gpios = <&pioE 0 GPIO_ACTIVE_LOW>; + }; + }; + + spi0: spi@f0004000 { + cs-gpios = <&pioD 13 0>; + status = "okay"; + }; + + can0: can@f000c000 { + status = "okay"; + }; + + i2c0: i2c@f0014000 { + status = "okay"; + }; + + i2c1: i2c@f0018000 { + status = "okay"; + }; + + macb0: ethernet@f0028000 { + phy-mode = "rgmii"; + status = "okay"; + }; + + usart0: serial@f001c000 { + status = "okay"; + }; + + usart1: serial@f0020000 { + pinctrl-0 = <&pinctrl_usart1 &pinctrl_usart1_rts_cts>; + status = "okay"; + }; + + uart0: serial@f0024000 { + status = "okay"; + }; + + mmc1: mmc@f8000000 { + pinctrl-0 = <&pinctrl_mmc1_clk_cmd_dat0 &pinctrl_mmc1_dat1_3 &pinctrl_mmc1_cd>; + status = "okay"; + slot@0 { + reg = <0>; + bus-width = <4>; + cd-gpios = <&pioE 1 GPIO_ACTIVE_HIGH>; + }; + }; + + spi1: spi@f8008000 { + cs-gpios = <&pioC 25 0>, <0>, <0>, <&pioD 16 0>; + status = "okay"; + }; + + adc0: adc@f8018000 { + pinctrl-0 = < + &pinctrl_adc0_adtrg + &pinctrl_adc0_ad0 + &pinctrl_adc0_ad1 + &pinctrl_adc0_ad2 + &pinctrl_adc0_ad3 + &pinctrl_adc0_ad4 + &pinctrl_adc0_ad5 + &pinctrl_adc0_ad6 + &pinctrl_adc0_ad7 + &pinctrl_adc0_ad8 + &pinctrl_adc0_ad9 + >; + status = "okay"; + }; + + i2c2: i2c@f801c000 { + dmas = <0>, <0>; /* Do not use DMA for i2c2 */ + status = "okay"; + }; + + macb1: ethernet@f802c000 { + phy-mode = "rmii"; + status = "okay"; + }; + + dbgu: serial@ffffee00 { + status = "okay"; + }; + + pinctrl@fffff200 { + board { + pinctrl_mmc0_cd: mmc0_cd { + atmel,pins = + <AT91_PIOE 0 AT91_PERIPH_GPIO AT91_PINCTRL_PULL_UP_DEGLITCH>; + }; + + pinctrl_mmc1_cd: mmc1_cd { + atmel,pins = + <AT91_PIOE 1 AT91_PERIPH_GPIO AT91_PINCTRL_PULL_UP_DEGLITCH>; + }; + + pinctrl_usba_vbus: usba_vbus { + atmel,pins = + <AT91_PIOE 9 AT91_PERIPH_GPIO AT91_PINCTRL_DEGLITCH>; /* PE9, conflicts with A9 */ + }; + }; + }; + + pmc: pmc@fffffc00 { + main: mainck { + clock-frequency = <12000000>; + }; + }; + }; + + nand0: nand@60000000 { + nand-bus-width = <8>; + nand-ecc-mode = "hw"; + atmel,has-pmecc; + atmel,pmecc-cap = <4>; + atmel,pmecc-sector-size = <512>; + nand-on-flash-bbt; + status = "okay"; + + at91bootstrap@0 { + label = "at91bootstrap"; + reg = <0x0 0x40000>; + }; + + bootloader@40000 { + label = "bootloader"; + reg = <0x40000 0x80000>; + }; + + bootloaderenv@c0000 { + label = "bootloader env"; + reg = <0xc0000 0xc0000>; + }; + + dtb@180000 { + label = "device tree"; + reg = <0x180000 0x80000>; + }; + + kernel@200000 { + label = "kernel"; + reg = <0x200000 0x600000>; + }; + + rootfs@800000 { + label = "rootfs"; + reg = <0x800000 0x0f800000>; + }; + }; + + usb0: gadget@00500000 { + atmel,vbus-gpio = <&pioE 9 GPIO_ACTIVE_HIGH>; /* PE9, conflicts with A9 */ + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_usba_vbus>; + status = "okay"; + }; + + usb1: ohci@00600000 { + num-ports = <3>; + atmel,vbus-gpio = <0 + &pioE 3 GPIO_ACTIVE_LOW + &pioE 4 GPIO_ACTIVE_LOW + >; + status = "okay"; + }; + + usb2: ehci@00700000 { + status = "okay"; + }; + }; + + gpio_keys { + compatible = "gpio-keys"; + + bp3 { + label = "PB_USER"; + gpios = <&pioE 29 GPIO_ACTIVE_LOW>; + linux,code = <0x104>; + gpio-key,wakeup; + }; + }; + + leds { + compatible = "gpio-leds"; + + d2 { + label = "d2"; + gpios = <&pioE 23 GPIO_ACTIVE_LOW>; /* PE23, conflicts with A23, CTS2 */ + linux,default-trigger = "heartbeat"; + }; + + d3 { + label = "d3"; + gpios = <&pioE 24 GPIO_ACTIVE_HIGH>; + }; + }; +}; diff --git a/arch/arm/boot/dts/at91sam9263.dtsi b/arch/arm/boot/dts/at91sam9263.dtsi index 0042f73068b0..fece8665fb63 100644 --- a/arch/arm/boot/dts/at91sam9263.dtsi +++ b/arch/arm/boot/dts/at91sam9263.dtsi @@ -523,7 +523,7 @@ }; i2c0: i2c@fff88000 { - compatible = "atmel,at91sam9263-i2c"; + compatible = "atmel,at91sam9260-i2c"; reg = <0xfff88000 0x100>; interrupts = <13 IRQ_TYPE_LEVEL_HIGH 6>; #address-cells = <1>; diff --git a/arch/arm/boot/dts/at91sam9n12ek.dts b/arch/arm/boot/dts/at91sam9n12ek.dts index e9487f6f0166..924a6a6ffd0f 100644 --- a/arch/arm/boot/dts/at91sam9n12ek.dts +++ b/arch/arm/boot/dts/at91sam9n12ek.dts @@ -124,6 +124,10 @@ nand-on-flash-bbt; status = "okay"; }; + + usb0: ohci@00500000 { + status = "okay"; + }; }; leds { diff --git a/arch/arm/boot/dts/dove.dtsi b/arch/arm/boot/dts/dove.dtsi index 2b76524f4aa7..187fd46b7b5e 100644 --- a/arch/arm/boot/dts/dove.dtsi +++ b/arch/arm/boot/dts/dove.dtsi @@ -379,15 +379,6 @@ #clock-cells = <1>; }; - pmu_intc: pmu-interrupt-ctrl@d0050 { - compatible = "marvell,dove-pmu-intc"; - interrupt-controller; - #interrupt-cells = <1>; - reg = <0xd0050 0x8>; - interrupts = <33>; - marvell,#interrupts = <7>; - }; - pinctrl: pin-ctrl@d0200 { compatible = "marvell,dove-pinctrl"; reg = <0xd0200 0x10>; @@ -610,8 +601,6 @@ rtc: real-time-clock@d8500 { compatible = "marvell,orion-rtc"; reg = <0xd8500 0x20>; - interrupt-parent = <&pmu_intc>; - interrupts = <5>; }; gpio2: gpio-ctrl@e8400 { diff --git a/arch/arm/boot/dts/imx6dl-hummingboard.dts b/arch/arm/boot/dts/imx6dl-hummingboard.dts index fd8fc7cd53f3..5bfae54fb780 100644 --- a/arch/arm/boot/dts/imx6dl-hummingboard.dts +++ b/arch/arm/boot/dts/imx6dl-hummingboard.dts @@ -52,12 +52,6 @@ }; }; - codec: spdif-transmitter { - compatible = "linux,spdif-dit"; - pinctrl-names = "default"; - pinctrl-0 = <&pinctrl_hummingboard_spdif>; - }; - sound-spdif { compatible = "fsl,imx-audio-spdif"; model = "imx-spdif"; @@ -111,7 +105,7 @@ }; pinctrl_hummingboard_spdif: hummingboard-spdif { - fsl,pins = <MX6QDL_PAD_GPIO_17__SPDIF_OUT 0x1b0b0>; + fsl,pins = <MX6QDL_PAD_GPIO_17__SPDIF_OUT 0x13091>; }; pinctrl_hummingboard_usbh1_vbus: hummingboard-usbh1-vbus { @@ -142,6 +136,8 @@ }; &spdif { + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_hummingboard_spdif>; status = "okay"; }; diff --git a/arch/arm/boot/dts/imx6qdl-cubox-i.dtsi b/arch/arm/boot/dts/imx6qdl-cubox-i.dtsi index 64daa3b311f6..c2a24888a276 100644 --- a/arch/arm/boot/dts/imx6qdl-cubox-i.dtsi +++ b/arch/arm/boot/dts/imx6qdl-cubox-i.dtsi @@ -46,12 +46,6 @@ }; }; - codec: spdif-transmitter { - compatible = "linux,spdif-dit"; - pinctrl-names = "default"; - pinctrl-0 = <&pinctrl_cubox_i_spdif>; - }; - sound-spdif { compatible = "fsl,imx-audio-spdif"; model = "imx-spdif"; @@ -89,7 +83,7 @@ }; pinctrl_cubox_i_spdif: cubox-i-spdif { - fsl,pins = <MX6QDL_PAD_GPIO_17__SPDIF_OUT 0x1b0b0>; + fsl,pins = <MX6QDL_PAD_GPIO_17__SPDIF_OUT 0x13091>; }; pinctrl_cubox_i_usbh1_vbus: cubox-i-usbh1-vbus { @@ -121,6 +115,8 @@ }; &spdif { + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_cubox_i_spdif>; status = "okay"; }; diff --git a/arch/arm/boot/dts/keystone-clocks.dtsi b/arch/arm/boot/dts/keystone-clocks.dtsi index 2363593e1050..ef58d1c24313 100644 --- a/arch/arm/boot/dts/keystone-clocks.dtsi +++ b/arch/arm/boot/dts/keystone-clocks.dtsi @@ -612,7 +612,7 @@ clocks { compatible = "ti,keystone,psc-clock"; clocks = <&chipclk13>; clock-output-names = "vcp-3"; - reg = <0x0235000a8 0xb00>, <0x02350060 0x400>; + reg = <0x023500a8 0xb00>, <0x02350060 0x400>; reg-names = "control", "domain"; domain-id = <24>; }; diff --git a/arch/arm/boot/dts/omap3-gta04.dts b/arch/arm/boot/dts/omap3-gta04.dts index b9b55c95a566..c551e4af4d83 100644 --- a/arch/arm/boot/dts/omap3-gta04.dts +++ b/arch/arm/boot/dts/omap3-gta04.dts @@ -32,7 +32,7 @@ aux-button { label = "aux"; linux,code = <169>; - gpios = <&gpio1 7 GPIO_ACTIVE_LOW>; + gpios = <&gpio1 7 GPIO_ACTIVE_HIGH>; gpio-key,wakeup; }; }; @@ -92,6 +92,8 @@ bmp085@77 { compatible = "bosch,bmp085"; reg = <0x77>; + interrupt-parent = <&gpio4>; + interrupts = <17 IRQ_TYPE_EDGE_RISING>; }; /* leds */ @@ -141,8 +143,8 @@ pinctrl-names = "default"; pinctrl-0 = <&mmc1_pins>; vmmc-supply = <&vmmc1>; - vmmc_aux-supply = <&vsim>; bus-width = <4>; + ti,non-removable; }; &mmc2 { diff --git a/arch/arm/boot/dts/omap3-n9.dts b/arch/arm/boot/dts/omap3-n9.dts index 39828ce464ee..9938b5dc1909 100644 --- a/arch/arm/boot/dts/omap3-n9.dts +++ b/arch/arm/boot/dts/omap3-n9.dts @@ -14,5 +14,5 @@ / { model = "Nokia N9"; - compatible = "nokia,omap3-n9", "ti,omap3"; + compatible = "nokia,omap3-n9", "ti,omap36xx", "ti,omap3"; }; diff --git a/arch/arm/boot/dts/omap3-n900.dts b/arch/arm/boot/dts/omap3-n900.dts index 6fc85f963530..0bf40c90faba 100644 --- a/arch/arm/boot/dts/omap3-n900.dts +++ b/arch/arm/boot/dts/omap3-n900.dts @@ -1,6 +1,6 @@ /* * Copyright (C) 2013 Pavel Machek <pavel@ucw.cz> - * Copyright 2013 Aaro Koskinen <aaro.koskinen@iki.fi> + * Copyright (C) 2013-2014 Aaro Koskinen <aaro.koskinen@iki.fi> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 (or later) as @@ -13,7 +13,7 @@ / { model = "Nokia N900"; - compatible = "nokia,omap3-n900", "ti,omap3"; + compatible = "nokia,omap3-n900", "ti,omap3430", "ti,omap3"; cpus { cpu@0 { diff --git a/arch/arm/boot/dts/omap3-n950.dts b/arch/arm/boot/dts/omap3-n950.dts index b076a526b999..261c5589bfa3 100644 --- a/arch/arm/boot/dts/omap3-n950.dts +++ b/arch/arm/boot/dts/omap3-n950.dts @@ -14,5 +14,5 @@ / { model = "Nokia N950"; - compatible = "nokia,omap3-n950", "ti,omap3"; + compatible = "nokia,omap3-n950", "ti,omap36xx", "ti,omap3"; }; diff --git a/arch/arm/boot/dts/omap3-overo-storm-tobi.dts b/arch/arm/boot/dts/omap3-overo-storm-tobi.dts new file mode 100644 index 000000000000..966b5c9cd96a --- /dev/null +++ b/arch/arm/boot/dts/omap3-overo-storm-tobi.dts @@ -0,0 +1,22 @@ +/* + * Copyright (C) 2012 Florian Vaussard, EPFL Mobots group + * + * 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. + */ + +/* + * Tobi expansion board is manufactured by Gumstix Inc. + */ + +/dts-v1/; + +#include "omap36xx.dtsi" +#include "omap3-overo-tobi-common.dtsi" + +/ { + model = "OMAP36xx/AM37xx/DM37xx Gumstix Overo on Tobi"; + compatible = "gumstix,omap3-overo-tobi", "gumstix,omap3-overo", "ti,omap36xx", "ti,omap3"; +}; + diff --git a/arch/arm/boot/dts/omap3-tobi.dts b/arch/arm/boot/dts/omap3-overo-tobi-common.dtsi index 7e4ad2aec37a..4edc013a91c1 100644 --- a/arch/arm/boot/dts/omap3-tobi.dts +++ b/arch/arm/boot/dts/omap3-overo-tobi-common.dtsi @@ -13,9 +13,6 @@ #include "omap3-overo.dtsi" / { - model = "TI OMAP3 Gumstix Overo on Tobi"; - compatible = "ti,omap3-tobi", "ti,omap3-overo", "ti,omap3"; - leds { compatible = "gpio-leds"; heartbeat { diff --git a/arch/arm/boot/dts/omap3-overo-tobi.dts b/arch/arm/boot/dts/omap3-overo-tobi.dts new file mode 100644 index 000000000000..de5653e1b5ca --- /dev/null +++ b/arch/arm/boot/dts/omap3-overo-tobi.dts @@ -0,0 +1,22 @@ +/* + * Copyright (C) 2012 Florian Vaussard, EPFL Mobots group + * + * 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. + */ + +/* + * Tobi expansion board is manufactured by Gumstix Inc. + */ + +/dts-v1/; + +#include "omap34xx.dtsi" +#include "omap3-overo-tobi-common.dtsi" + +/ { + model = "OMAP35xx Gumstix Overo on Tobi"; + compatible = "gumstix,omap3-overo-tobi", "gumstix,omap3-overo", "ti,omap3430", "ti,omap3"; +}; + diff --git a/arch/arm/boot/dts/omap3-overo.dtsi b/arch/arm/boot/dts/omap3-overo.dtsi index a461d2fd1fb0..597099907f8e 100644 --- a/arch/arm/boot/dts/omap3-overo.dtsi +++ b/arch/arm/boot/dts/omap3-overo.dtsi @@ -9,9 +9,6 @@ /* * The Gumstix Overo must be combined with an expansion board. */ -/dts-v1/; - -#include "omap34xx.dtsi" / { pwmleds { diff --git a/arch/arm/boot/dts/sama5d3.dtsi b/arch/arm/boot/dts/sama5d3.dtsi index 52447c17537a..3d5faf85f51b 100644 --- a/arch/arm/boot/dts/sama5d3.dtsi +++ b/arch/arm/boot/dts/sama5d3.dtsi @@ -1228,7 +1228,7 @@ compatible = "atmel,at91rm9200-ohci", "usb-ohci"; reg = <0x00600000 0x100000>; interrupts = <32 IRQ_TYPE_LEVEL_HIGH 2>; - clocks = <&usb>, <&uhphs_clk>, <&udphs_clk>, + clocks = <&usb>, <&uhphs_clk>, <&uhphs_clk>, <&uhpck>; clock-names = "usb_clk", "ohci_clk", "hclk", "uhpck"; status = "disabled"; diff --git a/arch/arm/boot/dts/ste-href.dtsi b/arch/arm/boot/dts/ste-href.dtsi index 0c1e8d871ed1..6cb9b68e2188 100644 --- a/arch/arm/boot/dts/ste-href.dtsi +++ b/arch/arm/boot/dts/ste-href.dtsi @@ -188,7 +188,6 @@ msp2: msp@80117000 { pinctrl-names = "default"; pinctrl-0 = <&msp2_default_mode>; - status = "okay"; }; msp3: msp@80125000 { diff --git a/arch/arm/boot/dts/sun4i-a10.dtsi b/arch/arm/boot/dts/sun4i-a10.dtsi index 040bb0eba152..10666ca8aee1 100644 --- a/arch/arm/boot/dts/sun4i-a10.dtsi +++ b/arch/arm/boot/dts/sun4i-a10.dtsi @@ -315,7 +315,7 @@ ranges; emac: ethernet@01c0b000 { - compatible = "allwinner,sun4i-emac"; + compatible = "allwinner,sun4i-a10-emac"; reg = <0x01c0b000 0x1000>; interrupts = <55>; clocks = <&ahb_gates 17>; @@ -323,7 +323,7 @@ }; mdio@01c0b080 { - compatible = "allwinner,sun4i-mdio"; + compatible = "allwinner,sun4i-a10-mdio"; reg = <0x01c0b080 0x14>; status = "disabled"; #address-cells = <1>; diff --git a/arch/arm/boot/dts/sun5i-a10s.dtsi b/arch/arm/boot/dts/sun5i-a10s.dtsi index ea16054857a4..64961595e8d6 100644 --- a/arch/arm/boot/dts/sun5i-a10s.dtsi +++ b/arch/arm/boot/dts/sun5i-a10s.dtsi @@ -278,7 +278,7 @@ ranges; emac: ethernet@01c0b000 { - compatible = "allwinner,sun4i-emac"; + compatible = "allwinner,sun4i-a10-emac"; reg = <0x01c0b000 0x1000>; interrupts = <55>; clocks = <&ahb_gates 17>; @@ -286,7 +286,7 @@ }; mdio@01c0b080 { - compatible = "allwinner,sun4i-mdio"; + compatible = "allwinner,sun4i-a10-mdio"; reg = <0x01c0b080 0x14>; status = "disabled"; #address-cells = <1>; diff --git a/arch/arm/boot/dts/sun7i-a20.dtsi b/arch/arm/boot/dts/sun7i-a20.dtsi index 119f066f0d98..9ff09484847b 100644 --- a/arch/arm/boot/dts/sun7i-a20.dtsi +++ b/arch/arm/boot/dts/sun7i-a20.dtsi @@ -340,7 +340,7 @@ ranges; emac: ethernet@01c0b000 { - compatible = "allwinner,sun4i-emac"; + compatible = "allwinner,sun4i-a10-emac"; reg = <0x01c0b000 0x1000>; interrupts = <0 55 4>; clocks = <&ahb_gates 17>; @@ -348,7 +348,7 @@ }; mdio@01c0b080 { - compatible = "allwinner,sun4i-mdio"; + compatible = "allwinner,sun4i-a10-mdio"; reg = <0x01c0b080 0x14>; status = "disabled"; #address-cells = <1>; diff --git a/arch/arm/boot/dts/tegra114.dtsi b/arch/arm/boot/dts/tegra114.dtsi index 389e987ec281..44ec401ec366 100644 --- a/arch/arm/boot/dts/tegra114.dtsi +++ b/arch/arm/boot/dts/tegra114.dtsi @@ -57,6 +57,8 @@ resets = <&tegra_car 27>; reset-names = "dc"; + nvidia,head = <0>; + rgb { status = "disabled"; }; @@ -72,6 +74,8 @@ resets = <&tegra_car 26>; reset-names = "dc"; + nvidia,head = <1>; + rgb { status = "disabled"; }; diff --git a/arch/arm/boot/dts/tegra20.dtsi b/arch/arm/boot/dts/tegra20.dtsi index 480ecda3416b..48d2a7f4d0c0 100644 --- a/arch/arm/boot/dts/tegra20.dtsi +++ b/arch/arm/boot/dts/tegra20.dtsi @@ -94,6 +94,8 @@ resets = <&tegra_car 27>; reset-names = "dc"; + nvidia,head = <0>; + rgb { status = "disabled"; }; @@ -109,6 +111,8 @@ resets = <&tegra_car 26>; reset-names = "dc"; + nvidia,head = <1>; + rgb { status = "disabled"; }; diff --git a/arch/arm/boot/dts/tegra30-cardhu.dtsi b/arch/arm/boot/dts/tegra30-cardhu.dtsi index 9104224124ee..1e156d9d0506 100644 --- a/arch/arm/boot/dts/tegra30-cardhu.dtsi +++ b/arch/arm/boot/dts/tegra30-cardhu.dtsi @@ -28,7 +28,7 @@ compatible = "nvidia,cardhu", "nvidia,tegra30"; aliases { - rtc0 = "/i2c@7000d000/tps6586x@34"; + rtc0 = "/i2c@7000d000/tps65911@2d"; rtc1 = "/rtc@7000e000"; }; diff --git a/arch/arm/boot/dts/tegra30.dtsi b/arch/arm/boot/dts/tegra30.dtsi index ed8e7700b46d..19a84e933f4e 100644 --- a/arch/arm/boot/dts/tegra30.dtsi +++ b/arch/arm/boot/dts/tegra30.dtsi @@ -170,6 +170,8 @@ resets = <&tegra_car 27>; reset-names = "dc"; + nvidia,head = <0>; + rgb { status = "disabled"; }; @@ -185,6 +187,8 @@ resets = <&tegra_car 26>; reset-names = "dc"; + nvidia,head = <1>; + rgb { status = "disabled"; }; diff --git a/arch/arm/boot/dts/testcases/tests.dtsi b/arch/arm/boot/dts/testcases/tests.dtsi deleted file mode 100644 index 3f123ecc9dd7..000000000000 --- a/arch/arm/boot/dts/testcases/tests.dtsi +++ /dev/null @@ -1,2 +0,0 @@ -/include/ "tests-phandle.dtsi" -/include/ "tests-interrupts.dtsi" diff --git a/arch/arm/boot/dts/versatile-pb.dts b/arch/arm/boot/dts/versatile-pb.dts index f43907c40c93..65f657711323 100644 --- a/arch/arm/boot/dts/versatile-pb.dts +++ b/arch/arm/boot/dts/versatile-pb.dts @@ -1,4 +1,4 @@ -/include/ "versatile-ab.dts" +#include <versatile-ab.dts> / { model = "ARM Versatile PB"; @@ -47,4 +47,4 @@ }; }; -/include/ "testcases/tests.dtsi" +#include <testcases.dtsi> diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig index 845bc745706b..ee6982976d66 100644 --- a/arch/arm/configs/multi_v7_defconfig +++ b/arch/arm/configs/multi_v7_defconfig @@ -29,6 +29,7 @@ CONFIG_ARCH_OMAP3=y CONFIG_ARCH_OMAP4=y CONFIG_SOC_OMAP5=y CONFIG_SOC_AM33XX=y +CONFIG_SOC_DRA7XX=y CONFIG_SOC_AM43XX=y CONFIG_ARCH_ROCKCHIP=y CONFIG_ARCH_SOCFPGA=y diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h index e9a49fe0284e..8b8b61685a34 100644 --- a/arch/arm/include/asm/cacheflush.h +++ b/arch/arm/include/asm/cacheflush.h @@ -212,6 +212,7 @@ extern void copy_to_user_page(struct vm_area_struct *, struct page *, static inline void __flush_icache_all(void) { __flush_icache_preferred(); + dsb(); } /* diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h index 03243f7eeddf..85c60adc8b60 100644 --- a/arch/arm/include/asm/pgtable-3level.h +++ b/arch/arm/include/asm/pgtable-3level.h @@ -120,13 +120,16 @@ /* * 2nd stage PTE definitions for LPAE. */ -#define L_PTE_S2_MT_UNCACHED (_AT(pteval_t, 0x5) << 2) /* MemAttr[3:0] */ -#define L_PTE_S2_MT_WRITETHROUGH (_AT(pteval_t, 0xa) << 2) /* MemAttr[3:0] */ -#define L_PTE_S2_MT_WRITEBACK (_AT(pteval_t, 0xf) << 2) /* MemAttr[3:0] */ -#define L_PTE_S2_RDONLY (_AT(pteval_t, 1) << 6) /* HAP[1] */ -#define L_PTE_S2_RDWR (_AT(pteval_t, 3) << 6) /* HAP[2:1] */ +#define L_PTE_S2_MT_UNCACHED (_AT(pteval_t, 0x0) << 2) /* strongly ordered */ +#define L_PTE_S2_MT_WRITETHROUGH (_AT(pteval_t, 0xa) << 2) /* normal inner write-through */ +#define L_PTE_S2_MT_WRITEBACK (_AT(pteval_t, 0xf) << 2) /* normal inner write-back */ +#define L_PTE_S2_MT_DEV_SHARED (_AT(pteval_t, 0x1) << 2) /* device */ +#define L_PTE_S2_MT_MASK (_AT(pteval_t, 0xf) << 2) -#define L_PMD_S2_RDWR (_AT(pmdval_t, 3) << 6) /* HAP[2:1] */ +#define L_PTE_S2_RDONLY (_AT(pteval_t, 1) << 6) /* HAP[1] */ +#define L_PTE_S2_RDWR (_AT(pteval_t, 3) << 6) /* HAP[2:1] */ + +#define L_PMD_S2_RDWR (_AT(pmdval_t, 3) << 6) /* HAP[2:1] */ /* * Hyp-mode PL2 PTE definitions for LPAE. diff --git a/arch/arm/include/asm/spinlock.h b/arch/arm/include/asm/spinlock.h index ef3c6072aa45..ac4bfae26702 100644 --- a/arch/arm/include/asm/spinlock.h +++ b/arch/arm/include/asm/spinlock.h @@ -37,18 +37,9 @@ static inline void dsb_sev(void) { -#if __LINUX_ARM_ARCH__ >= 7 - __asm__ __volatile__ ( - "dsb ishst\n" - SEV - ); -#else - __asm__ __volatile__ ( - "mcr p15, 0, %0, c7, c10, 4\n" - SEV - : : "r" (0) - ); -#endif + + dsb(ishst); + __asm__(SEV); } /* diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index b0df9761de6d..1e8b030dbefd 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -731,7 +731,7 @@ static void __init request_standard_resources(const struct machine_desc *mdesc) kernel_data.end = virt_to_phys(_end - 1); for_each_memblock(memory, region) { - res = memblock_virt_alloc_low(sizeof(*res), 0); + res = memblock_virt_alloc(sizeof(*res), 0); res->name = "System RAM"; res->start = __pfn_to_phys(memblock_region_memory_base_pfn(region)); res->end = __pfn_to_phys(memblock_region_memory_end_pfn(region)) - 1; diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c index 1d8248ea5669..bd18bb8b2770 100644 --- a/arch/arm/kvm/arm.c +++ b/arch/arm/kvm/arm.c @@ -878,7 +878,8 @@ static int hyp_init_cpu_pm_notifier(struct notifier_block *self, unsigned long cmd, void *v) { - if (cmd == CPU_PM_EXIT) { + if (cmd == CPU_PM_EXIT && + __hyp_get_vectors() == hyp_default_vectors) { cpu_init_hyp_mode(NULL); return NOTIFY_OK; } diff --git a/arch/arm/kvm/interrupts.S b/arch/arm/kvm/interrupts.S index ddc15539bad2..0d68d4073068 100644 --- a/arch/arm/kvm/interrupts.S +++ b/arch/arm/kvm/interrupts.S @@ -220,6 +220,10 @@ after_vfp_restore: * in Hyp mode (see init_hyp_mode in arch/arm/kvm/arm.c). Return values are * passed in r0 and r1. * + * A function pointer with a value of 0xffffffff has a special meaning, + * and is used to implement __hyp_get_vectors in the same way as in + * arch/arm/kernel/hyp_stub.S. + * * The calling convention follows the standard AAPCS: * r0 - r3: caller save * r12: caller save @@ -363,6 +367,11 @@ hyp_hvc: host_switch_to_hyp: pop {r0, r1, r2} + /* Check for __hyp_get_vectors */ + cmp r0, #-1 + mrceq p15, 4, r0, c12, c0, 0 @ get HVBAR + beq 1f + push {lr} mrs lr, SPSR push {lr} @@ -378,7 +387,7 @@ THUMB( orr lr, #1) pop {lr} msr SPSR_csxf, lr pop {lr} - eret +1: eret guest_trap: load_vcpu @ Load VCPU pointer to r0 diff --git a/arch/arm/mach-hisi/Kconfig b/arch/arm/mach-hisi/Kconfig index 8f4649b301b2..1abae5f6a418 100644 --- a/arch/arm/mach-hisi/Kconfig +++ b/arch/arm/mach-hisi/Kconfig @@ -8,7 +8,7 @@ config ARCH_HI3xxx select CLKSRC_OF select GENERIC_CLOCKEVENTS select HAVE_ARM_SCU - select HAVE_ARM_TWD + select HAVE_ARM_TWD if SMP select HAVE_SMP select PINCTRL select PINCTRL_SINGLE diff --git a/arch/arm/mach-imx/Makefile b/arch/arm/mach-imx/Makefile index befcaf5d0574..ec419649320f 100644 --- a/arch/arm/mach-imx/Makefile +++ b/arch/arm/mach-imx/Makefile @@ -101,11 +101,9 @@ obj-$(CONFIG_HOTPLUG_CPU) += hotplug.o obj-$(CONFIG_SOC_IMX6Q) += clk-imx6q.o mach-imx6q.o obj-$(CONFIG_SOC_IMX6SL) += clk-imx6sl.o mach-imx6sl.o -ifeq ($(CONFIG_PM),y) obj-$(CONFIG_SOC_IMX6Q) += pm-imx6q.o headsmp.o # i.MX6SL reuses i.MX6Q code obj-$(CONFIG_SOC_IMX6SL) += pm-imx6q.o headsmp.o -endif # i.MX5 based machines obj-$(CONFIG_MACH_MX51_BABBAGE) += mach-mx51_babbage.o diff --git a/arch/arm/mach-imx/clk-imx6q.c b/arch/arm/mach-imx/clk-imx6q.c index af2e582d2b74..4d677f442539 100644 --- a/arch/arm/mach-imx/clk-imx6q.c +++ b/arch/arm/mach-imx/clk-imx6q.c @@ -482,6 +482,9 @@ static void __init imx6q_clocks_init(struct device_node *ccm_node) if (IS_ENABLED(CONFIG_PCI_IMX6)) clk_set_parent(clk[lvds1_sel], clk[sata_ref]); + /* Set initial power mode */ + imx6q_set_lpm(WAIT_CLOCKED); + np = of_find_compatible_node(NULL, NULL, "fsl,imx6q-gpt"); base = of_iomap(np, 0); WARN_ON(!base); diff --git a/arch/arm/mach-imx/clk-imx6sl.c b/arch/arm/mach-imx/clk-imx6sl.c index 3781a1853998..4c86f3035205 100644 --- a/arch/arm/mach-imx/clk-imx6sl.c +++ b/arch/arm/mach-imx/clk-imx6sl.c @@ -266,6 +266,9 @@ static void __init imx6sl_clocks_init(struct device_node *ccm_node) /* Audio-related clocks configuration */ clk_set_parent(clks[IMX6SL_CLK_SPDIF0_SEL], clks[IMX6SL_CLK_PLL3_PFD3]); + /* Set initial power mode */ + imx6q_set_lpm(WAIT_CLOCKED); + np = of_find_compatible_node(NULL, NULL, "fsl,imx6sl-gpt"); base = of_iomap(np, 0); WARN_ON(!base); diff --git a/arch/arm/mach-imx/common.h b/arch/arm/mach-imx/common.h index 59c3b9b26bb4..baf439dc22d8 100644 --- a/arch/arm/mach-imx/common.h +++ b/arch/arm/mach-imx/common.h @@ -144,13 +144,11 @@ void imx6q_set_chicken_bit(void); void imx_cpu_die(unsigned int cpu); int imx_cpu_kill(unsigned int cpu); -#ifdef CONFIG_PM void imx6q_pm_init(void); void imx6q_pm_set_ccm_base(void __iomem *base); +#ifdef CONFIG_PM void imx5_pm_init(void); #else -static inline void imx6q_pm_init(void) {} -static inline void imx6q_pm_set_ccm_base(void __iomem *base) {} static inline void imx5_pm_init(void) {} #endif diff --git a/arch/arm/mach-imx/pm-imx6q.c b/arch/arm/mach-imx/pm-imx6q.c index 9d47adc078aa..7a9b98589db7 100644 --- a/arch/arm/mach-imx/pm-imx6q.c +++ b/arch/arm/mach-imx/pm-imx6q.c @@ -236,8 +236,6 @@ void __init imx6q_pm_init(void) regmap_update_bits(gpr, IOMUXC_GPR1, IMX6Q_GPR1_GINT, IMX6Q_GPR1_GINT); - /* Set initial power mode */ - imx6q_set_lpm(WAIT_CLOCKED); suspend_set_ops(&imx6q_pm_ops); } diff --git a/arch/arm/mach-moxart/Kconfig b/arch/arm/mach-moxart/Kconfig index ba470d64493b..3795ae28a613 100644 --- a/arch/arm/mach-moxart/Kconfig +++ b/arch/arm/mach-moxart/Kconfig @@ -2,7 +2,6 @@ config ARCH_MOXART bool "MOXA ART SoC" if ARCH_MULTI_V4T select CPU_FA526 select ARM_DMA_MEM_BUFFERABLE - select DMA_OF select USE_OF select CLKSRC_OF select CLKSRC_MMIO diff --git a/arch/arm/mach-omap1/board-nokia770.c b/arch/arm/mach-omap1/board-nokia770.c index 91449c5cb70f..85089d821982 100644 --- a/arch/arm/mach-omap1/board-nokia770.c +++ b/arch/arm/mach-omap1/board-nokia770.c @@ -156,6 +156,7 @@ static struct omap_usb_config nokia770_usb_config __initdata = { .register_dev = 1, .hmc_mode = 16, .pins[0] = 6, + .extcon = "tahvo-usb", }; #if defined(CONFIG_MMC_OMAP) || defined(CONFIG_MMC_OMAP_MODULE) diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig index 653b489479e0..0af7ca02314d 100644 --- a/arch/arm/mach-omap2/Kconfig +++ b/arch/arm/mach-omap2/Kconfig @@ -50,11 +50,12 @@ config SOC_OMAP5 bool "TI OMAP5" depends on ARCH_MULTI_V7 select ARCH_OMAP2PLUS + select ARCH_HAS_OPP select ARM_CPU_SUSPEND if PM select ARM_GIC select CPU_V7 select HAVE_ARM_SCU if SMP - select HAVE_ARM_TWD if LOCAL_TIMERS + select HAVE_ARM_TWD if SMP select HAVE_SMP select HAVE_ARM_ARCH_TIMER select ARM_ERRATA_798181 if SMP @@ -63,6 +64,7 @@ config SOC_AM33XX bool "TI AM33XX" depends on ARCH_MULTI_V7 select ARCH_OMAP2PLUS + select ARCH_HAS_OPP select ARM_CPU_SUSPEND if PM select CPU_V7 select MULTI_IRQ_HANDLER @@ -72,6 +74,7 @@ config SOC_AM43XX depends on ARCH_MULTI_V7 select CPU_V7 select ARCH_OMAP2PLUS + select ARCH_HAS_OPP select MULTI_IRQ_HANDLER select ARM_GIC select MACH_OMAP_GENERIC @@ -80,6 +83,7 @@ config SOC_DRA7XX bool "TI DRA7XX" depends on ARCH_MULTI_V7 select ARCH_OMAP2PLUS + select ARCH_HAS_OPP select ARM_CPU_SUSPEND if PM select ARM_GIC select CPU_V7 @@ -268,9 +272,6 @@ config MACH_OMAP_3430SDP default y select OMAP_PACKAGE_CBB -config MACH_NOKIA_N800 - bool - config MACH_NOKIA_N810 bool @@ -281,7 +282,6 @@ config MACH_NOKIA_N8X0 bool "Nokia N800/N810" depends on SOC_OMAP2420 default y - select MACH_NOKIA_N800 select MACH_NOKIA_N810 select MACH_NOKIA_N810_WIMAX select OMAP_PACKAGE_ZAC diff --git a/arch/arm/mach-omap2/gpmc.c b/arch/arm/mach-omap2/gpmc.c index d24926e6340f..ab43755364f5 100644 --- a/arch/arm/mach-omap2/gpmc.c +++ b/arch/arm/mach-omap2/gpmc.c @@ -1339,7 +1339,7 @@ static void __maybe_unused gpmc_read_timings_dt(struct device_node *np, of_property_read_bool(np, "gpmc,time-para-granularity"); } -#ifdef CONFIG_MTD_NAND +#if IS_ENABLED(CONFIG_MTD_NAND) static const char * const nand_xfer_types[] = { [NAND_OMAP_PREFETCH_POLLED] = "prefetch-polled", @@ -1429,7 +1429,7 @@ static int gpmc_probe_nand_child(struct platform_device *pdev, } #endif -#ifdef CONFIG_MTD_ONENAND +#if IS_ENABLED(CONFIG_MTD_ONENAND) static int gpmc_probe_onenand_child(struct platform_device *pdev, struct device_node *child) { diff --git a/arch/arm/mach-omap2/io.c b/arch/arm/mach-omap2/io.c index d408b15b4fbf..af432b191255 100644 --- a/arch/arm/mach-omap2/io.c +++ b/arch/arm/mach-omap2/io.c @@ -179,15 +179,6 @@ static struct map_desc omap34xx_io_desc[] __initdata = { .length = L4_EMU_34XX_SIZE, .type = MT_DEVICE }, -#if defined(CONFIG_DEBUG_LL) && \ - (defined(CONFIG_MACH_OMAP_ZOOM2) || defined(CONFIG_MACH_OMAP_ZOOM3)) - { - .virtual = ZOOM_UART_VIRT, - .pfn = __phys_to_pfn(ZOOM_UART_BASE), - .length = SZ_1M, - .type = MT_DEVICE - }, -#endif }; #endif diff --git a/arch/arm/mach-pxa/am300epd.c b/arch/arm/mach-pxa/am300epd.c index c9f309ae88c5..8b90c4f2d430 100644 --- a/arch/arm/mach-pxa/am300epd.c +++ b/arch/arm/mach-pxa/am300epd.c @@ -30,6 +30,7 @@ #include <mach/gumstix.h> #include <mach/mfp-pxa25x.h> +#include <mach/irqs.h> #include <linux/platform_data/video-pxafb.h> #include "generic.h" diff --git a/arch/arm/mach-pxa/include/mach/balloon3.h b/arch/arm/mach-pxa/include/mach/balloon3.h index 954641e6c8b1..1b0825911e62 100644 --- a/arch/arm/mach-pxa/include/mach/balloon3.h +++ b/arch/arm/mach-pxa/include/mach/balloon3.h @@ -14,6 +14,8 @@ #ifndef ASM_ARCH_BALLOON3_H #define ASM_ARCH_BALLOON3_H +#include "irqs.h" /* PXA_NR_BUILTIN_GPIO */ + enum balloon3_features { BALLOON3_FEATURE_OHCI, BALLOON3_FEATURE_MMC, diff --git a/arch/arm/mach-pxa/include/mach/corgi.h b/arch/arm/mach-pxa/include/mach/corgi.h index f3c3493b468d..c030d955bbd7 100644 --- a/arch/arm/mach-pxa/include/mach/corgi.h +++ b/arch/arm/mach-pxa/include/mach/corgi.h @@ -13,6 +13,7 @@ #ifndef __ASM_ARCH_CORGI_H #define __ASM_ARCH_CORGI_H 1 +#include "irqs.h" /* PXA_NR_BUILTIN_GPIO */ /* * Corgi (Non Standard) GPIO Definitions diff --git a/arch/arm/mach-pxa/include/mach/csb726.h b/arch/arm/mach-pxa/include/mach/csb726.h index 2628e7b72116..00cfbbbf73f7 100644 --- a/arch/arm/mach-pxa/include/mach/csb726.h +++ b/arch/arm/mach-pxa/include/mach/csb726.h @@ -11,6 +11,8 @@ #ifndef CSB726_H #define CSB726_H +#include "irqs.h" /* PXA_GPIO_TO_IRQ */ + #define CSB726_GPIO_IRQ_LAN 52 #define CSB726_GPIO_IRQ_SM501 53 #define CSB726_GPIO_MMC_DETECT 100 diff --git a/arch/arm/mach-pxa/include/mach/gumstix.h b/arch/arm/mach-pxa/include/mach/gumstix.h index dba14b6503ad..f7df27bbb42e 100644 --- a/arch/arm/mach-pxa/include/mach/gumstix.h +++ b/arch/arm/mach-pxa/include/mach/gumstix.h @@ -6,6 +6,7 @@ * published by the Free Software Foundation. */ +#include "irqs.h" /* PXA_GPIO_TO_IRQ */ /* BTRESET - Reset line to Bluetooth module, active low signal. */ #define GPIO_GUMSTIX_BTRESET 7 diff --git a/arch/arm/mach-pxa/include/mach/idp.h b/arch/arm/mach-pxa/include/mach/idp.h index 22a96f87232b..7e63f4680271 100644 --- a/arch/arm/mach-pxa/include/mach/idp.h +++ b/arch/arm/mach-pxa/include/mach/idp.h @@ -23,6 +23,7 @@ * IDP hardware. */ +#include "irqs.h" /* PXA_GPIO_TO_IRQ */ #define IDP_FLASH_PHYS (PXA_CS0_PHYS) #define IDP_ALT_FLASH_PHYS (PXA_CS1_PHYS) diff --git a/arch/arm/mach-pxa/include/mach/palmld.h b/arch/arm/mach-pxa/include/mach/palmld.h index 2c4471336570..b184f296023b 100644 --- a/arch/arm/mach-pxa/include/mach/palmld.h +++ b/arch/arm/mach-pxa/include/mach/palmld.h @@ -13,6 +13,8 @@ #ifndef _INCLUDE_PALMLD_H_ #define _INCLUDE_PALMLD_H_ +#include "irqs.h" /* PXA_GPIO_TO_IRQ */ + /** HERE ARE GPIOs **/ /* GPIOs */ diff --git a/arch/arm/mach-pxa/include/mach/palmt5.h b/arch/arm/mach-pxa/include/mach/palmt5.h index 0bd4f036c72f..e342c5921405 100644 --- a/arch/arm/mach-pxa/include/mach/palmt5.h +++ b/arch/arm/mach-pxa/include/mach/palmt5.h @@ -15,6 +15,8 @@ #ifndef _INCLUDE_PALMT5_H_ #define _INCLUDE_PALMT5_H_ +#include "irqs.h" /* PXA_GPIO_TO_IRQ */ + /** HERE ARE GPIOs **/ /* GPIOs */ diff --git a/arch/arm/mach-pxa/include/mach/palmtc.h b/arch/arm/mach-pxa/include/mach/palmtc.h index c383a21680b6..81c727b3cfd2 100644 --- a/arch/arm/mach-pxa/include/mach/palmtc.h +++ b/arch/arm/mach-pxa/include/mach/palmtc.h @@ -16,6 +16,8 @@ #ifndef _INCLUDE_PALMTC_H_ #define _INCLUDE_PALMTC_H_ +#include "irqs.h" /* PXA_GPIO_TO_IRQ */ + /** HERE ARE GPIOs **/ /* GPIOs */ diff --git a/arch/arm/mach-pxa/include/mach/palmtx.h b/arch/arm/mach-pxa/include/mach/palmtx.h index f2e530380253..92bc1f05300d 100644 --- a/arch/arm/mach-pxa/include/mach/palmtx.h +++ b/arch/arm/mach-pxa/include/mach/palmtx.h @@ -16,6 +16,8 @@ #ifndef _INCLUDE_PALMTX_H_ #define _INCLUDE_PALMTX_H_ +#include "irqs.h" /* PXA_GPIO_TO_IRQ */ + /** HERE ARE GPIOs **/ /* GPIOs */ diff --git a/arch/arm/mach-pxa/include/mach/pcm027.h b/arch/arm/mach-pxa/include/mach/pcm027.h index 6bf28de228bd..86ebd7b6c960 100644 --- a/arch/arm/mach-pxa/include/mach/pcm027.h +++ b/arch/arm/mach-pxa/include/mach/pcm027.h @@ -23,6 +23,8 @@ * Definitions of CPU card resources only */ +#include "irqs.h" /* PXA_GPIO_TO_IRQ */ + /* phyCORE-PXA270 (PCM027) Interrupts */ #define PCM027_IRQ(x) (IRQ_BOARD_START + (x)) #define PCM027_BTDET_IRQ PCM027_IRQ(0) diff --git a/arch/arm/mach-pxa/include/mach/pcm990_baseboard.h b/arch/arm/mach-pxa/include/mach/pcm990_baseboard.h index 0260aaa2fc17..7e544c14967e 100644 --- a/arch/arm/mach-pxa/include/mach/pcm990_baseboard.h +++ b/arch/arm/mach-pxa/include/mach/pcm990_baseboard.h @@ -20,6 +20,7 @@ */ #include <mach/pcm027.h> +#include "irqs.h" /* PXA_GPIO_TO_IRQ */ /* * definitions relevant only when the PCM-990 diff --git a/arch/arm/mach-pxa/include/mach/poodle.h b/arch/arm/mach-pxa/include/mach/poodle.h index f32ff75dcca8..b56b19351a03 100644 --- a/arch/arm/mach-pxa/include/mach/poodle.h +++ b/arch/arm/mach-pxa/include/mach/poodle.h @@ -15,6 +15,8 @@ #ifndef __ASM_ARCH_POODLE_H #define __ASM_ARCH_POODLE_H 1 +#include "irqs.h" /* PXA_GPIO_TO_IRQ */ + /* * GPIOs */ diff --git a/arch/arm/mach-pxa/include/mach/spitz.h b/arch/arm/mach-pxa/include/mach/spitz.h index 0bfe6507c95d..25c9f62e46aa 100644 --- a/arch/arm/mach-pxa/include/mach/spitz.h +++ b/arch/arm/mach-pxa/include/mach/spitz.h @@ -15,8 +15,8 @@ #define __ASM_ARCH_SPITZ_H 1 #endif +#include "irqs.h" /* PXA_NR_BUILTIN_GPIO, PXA_GPIO_TO_IRQ */ #include <linux/fb.h> -#include <linux/gpio.h> /* Spitz/Akita GPIOs */ diff --git a/arch/arm/mach-pxa/include/mach/tosa.h b/arch/arm/mach-pxa/include/mach/tosa.h index 2bb0e862598c..0497d95cef25 100644 --- a/arch/arm/mach-pxa/include/mach/tosa.h +++ b/arch/arm/mach-pxa/include/mach/tosa.h @@ -13,6 +13,8 @@ #ifndef _ASM_ARCH_TOSA_H_ #define _ASM_ARCH_TOSA_H_ 1 +#include "irqs.h" /* PXA_NR_BUILTIN_GPIO */ + /* TOSA Chip selects */ #define TOSA_LCDC_PHYS PXA_CS4_PHYS /* Internel Scoop */ diff --git a/arch/arm/mach-pxa/include/mach/trizeps4.h b/arch/arm/mach-pxa/include/mach/trizeps4.h index d2ca01053f69..ae3ca013afab 100644 --- a/arch/arm/mach-pxa/include/mach/trizeps4.h +++ b/arch/arm/mach-pxa/include/mach/trizeps4.h @@ -10,6 +10,8 @@ #ifndef _TRIPEPS4_H_ #define _TRIPEPS4_H_ +#include "irqs.h" /* PXA_GPIO_TO_IRQ */ + /* physical memory regions */ #define TRIZEPS4_FLASH_PHYS (PXA_CS0_PHYS) /* Flash region */ #define TRIZEPS4_DISK_PHYS (PXA_CS1_PHYS) /* Disk On Chip region */ diff --git a/arch/arm/mach-pxa/mioa701.c b/arch/arm/mach-pxa/mioa701.c index f70583fee59f..29997bde277d 100644 --- a/arch/arm/mach-pxa/mioa701.c +++ b/arch/arm/mach-pxa/mioa701.c @@ -38,6 +38,7 @@ #include <linux/mtd/physmap.h> #include <linux/usb/gpio_vbus.h> #include <linux/reboot.h> +#include <linux/regulator/fixed.h> #include <linux/regulator/max1586.h> #include <linux/slab.h> #include <linux/i2c/pxa-i2c.h> @@ -714,6 +715,10 @@ static struct gpio global_gpios[] = { { GPIO56_MT9M111_nOE, GPIOF_OUT_INIT_LOW, "Camera nOE" }, }; +static struct regulator_consumer_supply fixed_5v0_consumers[] = { + REGULATOR_SUPPLY("power", "pwm-backlight"), +}; + static void __init mioa701_machine_init(void) { int rc; @@ -753,6 +758,10 @@ static void __init mioa701_machine_init(void) pxa_set_i2c_info(&i2c_pdata); pxa27x_set_i2c_power_info(NULL); pxa_set_camera_info(&mioa701_pxacamera_platform_data); + + regulator_register_always_on(0, "fixed-5.0V", fixed_5v0_consumers, + ARRAY_SIZE(fixed_5v0_consumers), + 5000000); } static void mioa701_machine_exit(void) diff --git a/arch/arm/mach-shmobile/Kconfig b/arch/arm/mach-shmobile/Kconfig index 338640631e08..05fa505df585 100644 --- a/arch/arm/mach-shmobile/Kconfig +++ b/arch/arm/mach-shmobile/Kconfig @@ -8,7 +8,7 @@ config ARCH_SHMOBILE_MULTI select CPU_V7 select GENERIC_CLOCKEVENTS select HAVE_ARM_SCU if SMP - select HAVE_ARM_TWD if LOCAL_TIMERS + select HAVE_ARM_TWD if SMP select HAVE_SMP select ARM_GIC select MIGHT_HAVE_CACHE_L2X0 diff --git a/arch/arm/mach-tegra/pm.c b/arch/arm/mach-tegra/pm.c index 4ae0286b468d..f55b05a29b55 100644 --- a/arch/arm/mach-tegra/pm.c +++ b/arch/arm/mach-tegra/pm.c @@ -24,6 +24,7 @@ #include <linux/cpu_pm.h> #include <linux/suspend.h> #include <linux/err.h> +#include <linux/slab.h> #include <linux/clk/tegra.h> #include <asm/smp_plat.h> diff --git a/arch/arm/mach-tegra/tegra.c b/arch/arm/mach-tegra/tegra.c index 303a285d80fd..6191603379e1 100644 --- a/arch/arm/mach-tegra/tegra.c +++ b/arch/arm/mach-tegra/tegra.c @@ -73,10 +73,20 @@ u32 tegra_uart_config[3] = { static void __init tegra_init_cache(void) { #ifdef CONFIG_CACHE_L2X0 + static const struct of_device_id pl310_ids[] __initconst = { + { .compatible = "arm,pl310-cache", }, + {} + }; + + struct device_node *np; int ret; void __iomem *p = IO_ADDRESS(TEGRA_ARM_PERIF_BASE) + 0x3000; u32 aux_ctrl, cache_type; + np = of_find_matching_node(NULL, pl310_ids); + if (!np) + return; + cache_type = readl(p + L2X0_CACHE_TYPE); aux_ctrl = (cache_type & 0x700) << (17-8); aux_ctrl |= 0x7C400001; diff --git a/arch/arm/mach-zynq/common.c b/arch/arm/mach-zynq/common.c index 1db2a5ca9ab8..8c09a8393fb6 100644 --- a/arch/arm/mach-zynq/common.c +++ b/arch/arm/mach-zynq/common.c @@ -25,6 +25,7 @@ #include <linux/of_irq.h> #include <linux/of_platform.h> #include <linux/of.h> +#include <linux/memblock.h> #include <linux/irqchip.h> #include <linux/irqchip/arm-gic.h> @@ -41,6 +42,18 @@ void __iomem *zynq_scu_base; +/** + * zynq_memory_init - Initialize special memory + * + * We need to stop things allocating the low memory as DMA can't work in + * the 1st 512K of memory. + */ +static void __init zynq_memory_init(void) +{ + if (!__pa(PAGE_OFFSET)) + memblock_reserve(__pa(PAGE_OFFSET), __pa(swapper_pg_dir)); +} + static struct platform_device zynq_cpuidle_device = { .name = "cpuidle-zynq", }; @@ -117,5 +130,6 @@ DT_MACHINE_START(XILINX_EP107, "Xilinx Zynq Platform") .init_machine = zynq_init_machine, .init_time = zynq_timer_init, .dt_compat = zynq_dt_match, + .reserve = zynq_memory_init, .restart = zynq_system_reset, MACHINE_END diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index 1a77450e728a..11b3914660d2 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -1358,7 +1358,7 @@ static void *arm_iommu_alloc_attrs(struct device *dev, size_t size, *handle = DMA_ERROR_CODE; size = PAGE_ALIGN(size); - if (gfp & GFP_ATOMIC) + if (!(gfp & __GFP_WAIT)) return __iommu_alloc_atomic(dev, size, handle); /* diff --git a/arch/arm/mm/mm.h b/arch/arm/mm/mm.h index d5a982d15a88..7ea641b7aa7d 100644 --- a/arch/arm/mm/mm.h +++ b/arch/arm/mm/mm.h @@ -38,6 +38,7 @@ static inline pmd_t *pmd_off_k(unsigned long virt) struct mem_type { pteval_t prot_pte; + pteval_t prot_pte_s2; pmdval_t prot_l1; pmdval_t prot_sect; unsigned int domain; diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index 4f08c133cc25..a623cb3ad012 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -232,12 +232,16 @@ __setup("noalign", noalign_setup); #endif /* ifdef CONFIG_CPU_CP15 / else */ #define PROT_PTE_DEVICE L_PTE_PRESENT|L_PTE_YOUNG|L_PTE_DIRTY|L_PTE_XN +#define PROT_PTE_S2_DEVICE PROT_PTE_DEVICE #define PROT_SECT_DEVICE PMD_TYPE_SECT|PMD_SECT_AP_WRITE static struct mem_type mem_types[] = { [MT_DEVICE] = { /* Strongly ordered / ARMv6 shared device */ .prot_pte = PROT_PTE_DEVICE | L_PTE_MT_DEV_SHARED | L_PTE_SHARED, + .prot_pte_s2 = s2_policy(PROT_PTE_S2_DEVICE) | + s2_policy(L_PTE_S2_MT_DEV_SHARED) | + L_PTE_SHARED, .prot_l1 = PMD_TYPE_TABLE, .prot_sect = PROT_SECT_DEVICE | PMD_SECT_S, .domain = DOMAIN_IO, @@ -508,7 +512,8 @@ static void __init build_mem_type_table(void) cp = &cache_policies[cachepolicy]; vecs_pgprot = kern_pgprot = user_pgprot = cp->pte; s2_pgprot = cp->pte_s2; - hyp_device_pgprot = s2_device_pgprot = mem_types[MT_DEVICE].prot_pte; + hyp_device_pgprot = mem_types[MT_DEVICE].prot_pte; + s2_device_pgprot = mem_types[MT_DEVICE].prot_pte_s2; /* * ARMv6 and above have extended page tables. diff --git a/arch/arm/mm/proc-v6.S b/arch/arm/mm/proc-v6.S index 45dc29f85d56..32b3558321c4 100644 --- a/arch/arm/mm/proc-v6.S +++ b/arch/arm/mm/proc-v6.S @@ -208,7 +208,6 @@ __v6_setup: mcr p15, 0, r0, c7, c14, 0 @ clean+invalidate D cache mcr p15, 0, r0, c7, c5, 0 @ invalidate I cache mcr p15, 0, r0, c7, c15, 0 @ clean+invalidate cache - mcr p15, 0, r0, c7, c10, 4 @ drain write buffer #ifdef CONFIG_MMU mcr p15, 0, r0, c8, c7, 0 @ invalidate I + D TLBs mcr p15, 0, r0, c2, c0, 2 @ TTB control register @@ -218,6 +217,8 @@ __v6_setup: ALT_UP(orr r8, r8, #TTB_FLAGS_UP) mcr p15, 0, r8, c2, c0, 1 @ load TTB1 #endif /* CONFIG_MMU */ + mcr p15, 0, r0, c7, c10, 4 @ drain write buffer and + @ complete invalidations adr r5, v6_crval ldmia r5, {r5, r6} ARM_BE8(orr r6, r6, #1 << 25) @ big-endian page tables diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S index bd1781979a39..74f6033e76dd 100644 --- a/arch/arm/mm/proc-v7.S +++ b/arch/arm/mm/proc-v7.S @@ -351,7 +351,6 @@ __v7_setup: 4: mov r10, #0 mcr p15, 0, r10, c7, c5, 0 @ I+BTB cache invalidate - dsb #ifdef CONFIG_MMU mcr p15, 0, r10, c8, c7, 0 @ invalidate I + D TLBs v7_ttb_setup r10, r4, r8, r5 @ TTBCR, TTBRx setup @@ -360,6 +359,7 @@ __v7_setup: mcr p15, 0, r5, c10, c2, 0 @ write PRRR mcr p15, 0, r6, c10, c2, 1 @ write NMRR #endif + dsb @ Complete invalidations #ifndef CONFIG_ARM_THUMBEE mrc p15, 0, r0, c0, c1, 0 @ read ID_PFR0 for ThumbEE and r0, r0, #(0xf << 12) @ ThumbEE enabled field diff --git a/arch/arm64/include/asm/percpu.h b/arch/arm64/include/asm/percpu.h index 13fb0b3efc5f..453a179469a3 100644 --- a/arch/arm64/include/asm/percpu.h +++ b/arch/arm64/include/asm/percpu.h @@ -16,6 +16,8 @@ #ifndef __ASM_PERCPU_H #define __ASM_PERCPU_H +#ifdef CONFIG_SMP + static inline void set_my_cpu_offset(unsigned long off) { asm volatile("msr tpidr_el1, %0" :: "r" (off) : "memory"); @@ -36,6 +38,12 @@ static inline unsigned long __my_cpu_offset(void) } #define __my_cpu_offset __my_cpu_offset() +#else /* !CONFIG_SMP */ + +#define set_my_cpu_offset(x) do { } while (0) + +#endif /* CONFIG_SMP */ + #include <asm-generic/percpu.h> #endif /* __ASM_PERCPU_H */ diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index b524dcd17243..aa3917c8b623 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -136,11 +136,11 @@ extern struct page *empty_zero_page; /* * The following only work if pte_present(). Undefined behaviour otherwise. */ -#define pte_present(pte) (pte_val(pte) & (PTE_VALID | PTE_PROT_NONE)) -#define pte_dirty(pte) (pte_val(pte) & PTE_DIRTY) -#define pte_young(pte) (pte_val(pte) & PTE_AF) -#define pte_special(pte) (pte_val(pte) & PTE_SPECIAL) -#define pte_write(pte) (pte_val(pte) & PTE_WRITE) +#define pte_present(pte) (!!(pte_val(pte) & (PTE_VALID | PTE_PROT_NONE))) +#define pte_dirty(pte) (!!(pte_val(pte) & PTE_DIRTY)) +#define pte_young(pte) (!!(pte_val(pte) & PTE_AF)) +#define pte_special(pte) (!!(pte_val(pte) & PTE_SPECIAL)) +#define pte_write(pte) (!!(pte_val(pte) & PTE_WRITE)) #define pte_exec(pte) (!(pte_val(pte) & PTE_UXN)) #define pte_valid_user(pte) \ diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h index 495ab6f84a61..eaf54a30bedc 100644 --- a/arch/arm64/include/uapi/asm/kvm.h +++ b/arch/arm64/include/uapi/asm/kvm.h @@ -148,6 +148,15 @@ struct kvm_arch_memory_slot { #define KVM_REG_ARM_TIMER_CNT ARM64_SYS_REG(3, 3, 14, 3, 2) #define KVM_REG_ARM_TIMER_CVAL ARM64_SYS_REG(3, 3, 14, 0, 2) +/* Device Control API: ARM VGIC */ +#define KVM_DEV_ARM_VGIC_GRP_ADDR 0 +#define KVM_DEV_ARM_VGIC_GRP_DIST_REGS 1 +#define KVM_DEV_ARM_VGIC_GRP_CPU_REGS 2 +#define KVM_DEV_ARM_VGIC_CPUID_SHIFT 32 +#define KVM_DEV_ARM_VGIC_CPUID_MASK (0xffULL << KVM_DEV_ARM_VGIC_CPUID_SHIFT) +#define KVM_DEV_ARM_VGIC_OFFSET_SHIFT 0 +#define KVM_DEV_ARM_VGIC_OFFSET_MASK (0xffffffffULL << KVM_DEV_ARM_VGIC_OFFSET_SHIFT) + /* KVM_IRQ_LINE irq field index values */ #define KVM_ARM_IRQ_TYPE_SHIFT 24 #define KVM_ARM_IRQ_TYPE_MASK 0xff diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c index c3b6c63ea5fb..38f0558f0c0a 100644 --- a/arch/arm64/kernel/stacktrace.c +++ b/arch/arm64/kernel/stacktrace.c @@ -48,7 +48,11 @@ int unwind_frame(struct stackframe *frame) frame->sp = fp + 0x10; frame->fp = *(unsigned long *)(fp); - frame->pc = *(unsigned long *)(fp + 8); + /* + * -4 here because we care about the PC at time of bl, + * not where the return will go. + */ + frame->pc = *(unsigned long *)(fp + 8) - 4; return 0; } diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S index 3b47c36e10ff..2c56012cb2d2 100644 --- a/arch/arm64/kvm/hyp.S +++ b/arch/arm64/kvm/hyp.S @@ -694,6 +694,24 @@ __hyp_panic_str: .align 2 +/* + * u64 kvm_call_hyp(void *hypfn, ...); + * + * This is not really a variadic function in the classic C-way and care must + * be taken when calling this to ensure parameters are passed in registers + * only, since the stack will change between the caller and the callee. + * + * Call the function with the first argument containing a pointer to the + * function you wish to call in Hyp mode, and subsequent arguments will be + * passed as x0, x1, and x2 (a maximum of 3 arguments in addition to the + * function pointer can be passed). The function being called must be mapped + * in Hyp mode (see init_hyp_mode in arch/arm/kvm/arm.c). Return values are + * passed in r0 and r1. + * + * A function pointer with a value of 0 has a special meaning, and is + * used to implement __hyp_get_vectors in the same way as in + * arch/arm64/kernel/hyp_stub.S. + */ ENTRY(kvm_call_hyp) hvc #0 ret @@ -737,7 +755,12 @@ el1_sync: // Guest trapped into EL2 pop x2, x3 pop x0, x1 - push lr, xzr + /* Check for __hyp_get_vectors */ + cbnz x0, 1f + mrs x0, vbar_el2 + b 2f + +1: push lr, xzr /* * Compute the function address in EL2, and shuffle the parameters. @@ -750,7 +773,7 @@ el1_sync: // Guest trapped into EL2 blr lr pop lr, xzr - eret +2: eret el1_trap: /* diff --git a/arch/avr32/Makefile b/arch/avr32/Makefile index 22fb66590dcd..dba48a5d5bb9 100644 --- a/arch/avr32/Makefile +++ b/arch/avr32/Makefile @@ -11,7 +11,7 @@ all: uImage vmlinux.elf KBUILD_DEFCONFIG := atstk1002_defconfig -KBUILD_CFLAGS += -pipe -fno-builtin -mno-pic +KBUILD_CFLAGS += -pipe -fno-builtin -mno-pic -D__linux__ KBUILD_AFLAGS += -mrelax -mno-pic KBUILD_CFLAGS_MODULE += -mno-relax LDFLAGS_vmlinux += --relax diff --git a/arch/avr32/boards/mimc200/fram.c b/arch/avr32/boards/mimc200/fram.c index 9764a1a1073e..c1466a872b9c 100644 --- a/arch/avr32/boards/mimc200/fram.c +++ b/arch/avr32/boards/mimc200/fram.c @@ -11,6 +11,7 @@ #define FRAM_VERSION "1.0" #include <linux/miscdevice.h> +#include <linux/module.h> #include <linux/proc_fs.h> #include <linux/mm.h> #include <linux/io.h> diff --git a/arch/avr32/include/asm/Kbuild b/arch/avr32/include/asm/Kbuild index cfb9fe1b8df9..c7c64a63c29f 100644 --- a/arch/avr32/include/asm/Kbuild +++ b/arch/avr32/include/asm/Kbuild @@ -17,5 +17,6 @@ generic-y += scatterlist.h generic-y += sections.h generic-y += topology.h generic-y += trace_clock.h +generic-y += vga.h generic-y += xor.h generic-y += hash.h diff --git a/arch/avr32/include/asm/io.h b/arch/avr32/include/asm/io.h index fc6483f83ccc..4f5ec2bb7172 100644 --- a/arch/avr32/include/asm/io.h +++ b/arch/avr32/include/asm/io.h @@ -295,6 +295,8 @@ extern void __iounmap(void __iomem *addr); #define iounmap(addr) \ __iounmap(addr) +#define ioremap_wc ioremap_nocache + #define cached(addr) P1SEGADDR(addr) #define uncached(addr) P2SEGADDR(addr) diff --git a/arch/m68k/include/asm/Kbuild b/arch/m68k/include/asm/Kbuild index 7cc8c364924d..6fb9e813a910 100644 --- a/arch/m68k/include/asm/Kbuild +++ b/arch/m68k/include/asm/Kbuild @@ -1,4 +1,4 @@ - +generic-y += barrier.h generic-y += bitsperlong.h generic-y += clkdev.h generic-y += cputime.h @@ -6,6 +6,7 @@ generic-y += device.h generic-y += emergency-restart.h generic-y += errno.h generic-y += exec.h +generic-y += hash.h generic-y += hw_irq.h generic-y += ioctl.h generic-y += ipcbuf.h @@ -18,6 +19,7 @@ generic-y += local.h generic-y += mman.h generic-y += mutex.h generic-y += percpu.h +generic-y += preempt.h generic-y += resource.h generic-y += scatterlist.h generic-y += sections.h @@ -31,5 +33,3 @@ generic-y += trace_clock.h generic-y += types.h generic-y += word-at-a-time.h generic-y += xor.h -generic-y += preempt.h -generic-y += hash.h diff --git a/arch/m68k/include/asm/barrier.h b/arch/m68k/include/asm/barrier.h deleted file mode 100644 index 15c5f77c1614..000000000000 --- a/arch/m68k/include/asm/barrier.h +++ /dev/null @@ -1,8 +0,0 @@ -#ifndef _M68K_BARRIER_H -#define _M68K_BARRIER_H - -#define nop() do { asm volatile ("nop"); barrier(); } while (0) - -#include <asm-generic/barrier.h> - -#endif /* _M68K_BARRIER_H */ diff --git a/arch/m68k/include/asm/unistd.h b/arch/m68k/include/asm/unistd.h index 014f288fc813..9d38b73989eb 100644 --- a/arch/m68k/include/asm/unistd.h +++ b/arch/m68k/include/asm/unistd.h @@ -4,7 +4,7 @@ #include <uapi/asm/unistd.h> -#define NR_syscalls 349 +#define NR_syscalls 351 #define __ARCH_WANT_OLD_READDIR #define __ARCH_WANT_OLD_STAT diff --git a/arch/m68k/include/uapi/asm/unistd.h b/arch/m68k/include/uapi/asm/unistd.h index 625f321001dc..b932dd470041 100644 --- a/arch/m68k/include/uapi/asm/unistd.h +++ b/arch/m68k/include/uapi/asm/unistd.h @@ -354,5 +354,7 @@ #define __NR_process_vm_writev 346 #define __NR_kcmp 347 #define __NR_finit_module 348 +#define __NR_sched_setattr 349 +#define __NR_sched_getattr 350 #endif /* _UAPI_ASM_M68K_UNISTD_H_ */ diff --git a/arch/m68k/kernel/syscalltable.S b/arch/m68k/kernel/syscalltable.S index 3f04ea0ab802..b6223dc41d82 100644 --- a/arch/m68k/kernel/syscalltable.S +++ b/arch/m68k/kernel/syscalltable.S @@ -369,4 +369,6 @@ ENTRY(sys_call_table) .long sys_process_vm_writev .long sys_kcmp .long sys_finit_module + .long sys_sched_setattr + .long sys_sched_getattr /* 350 */ diff --git a/arch/microblaze/include/asm/delay.h b/arch/microblaze/include/asm/delay.h index 05b7d39e4391..66fc24c24238 100644 --- a/arch/microblaze/include/asm/delay.h +++ b/arch/microblaze/include/asm/delay.h @@ -13,6 +13,8 @@ #ifndef _ASM_MICROBLAZE_DELAY_H #define _ASM_MICROBLAZE_DELAY_H +#include <linux/param.h> + extern inline void __delay(unsigned long loops) { asm volatile ("# __delay \n\t" \ diff --git a/arch/microblaze/include/asm/io.h b/arch/microblaze/include/asm/io.h index a2cea7206077..3fbb7f1db3bc 100644 --- a/arch/microblaze/include/asm/io.h +++ b/arch/microblaze/include/asm/io.h @@ -89,6 +89,11 @@ static inline unsigned int readl(const volatile void __iomem *addr) { return le32_to_cpu(*(volatile unsigned int __force *)addr); } +#define readq readq +static inline u64 readq(const volatile void __iomem *addr) +{ + return le64_to_cpu(__raw_readq(addr)); +} static inline void writeb(unsigned char v, volatile void __iomem *addr) { *(volatile unsigned char __force *)addr = v; @@ -101,6 +106,7 @@ static inline void writel(unsigned int v, volatile void __iomem *addr) { *(volatile unsigned int __force *)addr = cpu_to_le32(v); } +#define writeq(b, addr) __raw_writeq(cpu_to_le64(b), addr) /* ioread and iowrite variants. thease are for now same as __raw_ * variants of accessors. we might check for endianess in the feature diff --git a/arch/microblaze/kernel/head.S b/arch/microblaze/kernel/head.S index b7fb0438458c..17645b2e2f07 100644 --- a/arch/microblaze/kernel/head.S +++ b/arch/microblaze/kernel/head.S @@ -66,7 +66,7 @@ real_start: mts rmsr, r0 /* Disable stack protection from bootloader */ mts rslr, r0 - addi r8, r0, 0xFFFFFFF + addi r8, r0, 0xFFFFFFFF mts rshr, r8 /* * According to Xilinx, msrclr instruction behaves like 'mfs rX,rpc' diff --git a/arch/powerpc/include/asm/compat.h b/arch/powerpc/include/asm/compat.h index 84fdf6857c31..a613d2c82fd9 100644 --- a/arch/powerpc/include/asm/compat.h +++ b/arch/powerpc/include/asm/compat.h @@ -200,10 +200,11 @@ static inline void __user *arch_compat_alloc_user_space(long len) /* * We can't access below the stack pointer in the 32bit ABI and - * can access 288 bytes in the 64bit ABI + * can access 288 bytes in the 64bit big-endian ABI, + * or 512 bytes with the new ELFv2 little-endian ABI. */ if (!is_32bit_task()) - usp -= 288; + usp -= USER_REDZONE_SIZE; return (void __user *) (usp - len); } diff --git a/arch/powerpc/include/asm/dma-mapping.h b/arch/powerpc/include/asm/dma-mapping.h index e27e9ad6818e..150866b2a3fe 100644 --- a/arch/powerpc/include/asm/dma-mapping.h +++ b/arch/powerpc/include/asm/dma-mapping.h @@ -134,6 +134,7 @@ static inline int dma_supported(struct device *dev, u64 mask) } extern int dma_set_mask(struct device *dev, u64 dma_mask); +extern int __dma_set_mask(struct device *dev, u64 dma_mask); #define dma_alloc_coherent(d,s,h,f) dma_alloc_attrs(d,s,h,f,NULL) diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h index 9e39ceb1d19f..d4dd41fb951b 100644 --- a/arch/powerpc/include/asm/eeh.h +++ b/arch/powerpc/include/asm/eeh.h @@ -172,10 +172,20 @@ struct eeh_ops { }; extern struct eeh_ops *eeh_ops; -extern int eeh_subsystem_enabled; +extern bool eeh_subsystem_enabled; extern raw_spinlock_t confirm_error_lock; extern int eeh_probe_mode; +static inline bool eeh_enabled(void) +{ + return eeh_subsystem_enabled; +} + +static inline void eeh_set_enable(bool mode) +{ + eeh_subsystem_enabled = mode; +} + #define EEH_PROBE_MODE_DEV (1<<0) /* From PCI device */ #define EEH_PROBE_MODE_DEVTREE (1<<1) /* From device tree */ @@ -246,7 +256,7 @@ void eeh_remove_device(struct pci_dev *); * If this macro yields TRUE, the caller relays to eeh_check_failure() * which does further tests out of line. */ -#define EEH_POSSIBLE_ERROR(val, type) ((val) == (type)~0 && eeh_subsystem_enabled) +#define EEH_POSSIBLE_ERROR(val, type) ((val) == (type)~0 && eeh_enabled()) /* * Reads from a device which has been isolated by EEH will return @@ -257,6 +267,13 @@ void eeh_remove_device(struct pci_dev *); #else /* !CONFIG_EEH */ +static inline bool eeh_enabled(void) +{ + return false; +} + +static inline void eeh_set_enable(bool mode) { } + static inline int eeh_init(void) { return 0; diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h index d750336b171d..623f2971ce0e 100644 --- a/arch/powerpc/include/asm/hugetlb.h +++ b/arch/powerpc/include/asm/hugetlb.h @@ -127,7 +127,7 @@ static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { #ifdef CONFIG_PPC64 - return __pte(pte_update(mm, addr, ptep, ~0UL, 1)); + return __pte(pte_update(mm, addr, ptep, ~0UL, 0, 1)); #else return __pte(pte_update(ptep, ~0UL, 0)); #endif diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h index f7a8036579b5..42632c7a2a4e 100644 --- a/arch/powerpc/include/asm/iommu.h +++ b/arch/powerpc/include/asm/iommu.h @@ -77,6 +77,7 @@ struct iommu_table { #ifdef CONFIG_IOMMU_API struct iommu_group *it_group; #endif + void (*set_bypass)(struct iommu_table *tbl, bool enable); }; /* Pure 2^n version of get_order */ diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h index 40157e2ca691..ed82142a3251 100644 --- a/arch/powerpc/include/asm/opal.h +++ b/arch/powerpc/include/asm/opal.h @@ -816,8 +816,8 @@ int64_t opal_pci_next_error(uint64_t phb_id, uint64_t *first_frozen_pe, int64_t opal_pci_poll(uint64_t phb_id); int64_t opal_return_cpu(void); -int64_t opal_xscom_read(uint32_t gcid, uint32_t pcb_addr, __be64 *val); -int64_t opal_xscom_write(uint32_t gcid, uint32_t pcb_addr, uint64_t val); +int64_t opal_xscom_read(uint32_t gcid, uint64_t pcb_addr, __be64 *val); +int64_t opal_xscom_write(uint32_t gcid, uint64_t pcb_addr, uint64_t val); int64_t opal_lpc_write(uint32_t chip_id, enum OpalLPCAddressType addr_type, uint32_t addr, uint32_t data, uint32_t sz); diff --git a/arch/powerpc/include/asm/pgtable-ppc64.h b/arch/powerpc/include/asm/pgtable-ppc64.h index bc141c950b1e..eb9261024f51 100644 --- a/arch/powerpc/include/asm/pgtable-ppc64.h +++ b/arch/powerpc/include/asm/pgtable-ppc64.h @@ -195,6 +195,7 @@ extern void hpte_need_flush(struct mm_struct *mm, unsigned long addr, static inline unsigned long pte_update(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned long clr, + unsigned long set, int huge) { #ifdef PTE_ATOMIC_UPDATES @@ -205,14 +206,15 @@ static inline unsigned long pte_update(struct mm_struct *mm, andi. %1,%0,%6\n\ bne- 1b \n\ andc %1,%0,%4 \n\ + or %1,%1,%7\n\ stdcx. %1,0,%3 \n\ bne- 1b" : "=&r" (old), "=&r" (tmp), "=m" (*ptep) - : "r" (ptep), "r" (clr), "m" (*ptep), "i" (_PAGE_BUSY) + : "r" (ptep), "r" (clr), "m" (*ptep), "i" (_PAGE_BUSY), "r" (set) : "cc" ); #else unsigned long old = pte_val(*ptep); - *ptep = __pte(old & ~clr); + *ptep = __pte((old & ~clr) | set); #endif /* huge pages use the old page table lock */ if (!huge) @@ -231,9 +233,9 @@ static inline int __ptep_test_and_clear_young(struct mm_struct *mm, { unsigned long old; - if ((pte_val(*ptep) & (_PAGE_ACCESSED | _PAGE_HASHPTE)) == 0) + if ((pte_val(*ptep) & (_PAGE_ACCESSED | _PAGE_HASHPTE)) == 0) return 0; - old = pte_update(mm, addr, ptep, _PAGE_ACCESSED, 0); + old = pte_update(mm, addr, ptep, _PAGE_ACCESSED, 0, 0); return (old & _PAGE_ACCESSED) != 0; } #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG @@ -252,7 +254,7 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, if ((pte_val(*ptep) & _PAGE_RW) == 0) return; - pte_update(mm, addr, ptep, _PAGE_RW, 0); + pte_update(mm, addr, ptep, _PAGE_RW, 0, 0); } static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, @@ -261,7 +263,7 @@ static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, if ((pte_val(*ptep) & _PAGE_RW) == 0) return; - pte_update(mm, addr, ptep, _PAGE_RW, 1); + pte_update(mm, addr, ptep, _PAGE_RW, 0, 1); } /* @@ -284,14 +286,14 @@ static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { - unsigned long old = pte_update(mm, addr, ptep, ~0UL, 0); + unsigned long old = pte_update(mm, addr, ptep, ~0UL, 0, 0); return __pte(old); } static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t * ptep) { - pte_update(mm, addr, ptep, ~0UL, 0); + pte_update(mm, addr, ptep, ~0UL, 0, 0); } @@ -506,7 +508,9 @@ extern int pmdp_set_access_flags(struct vm_area_struct *vma, extern unsigned long pmd_hugepage_update(struct mm_struct *mm, unsigned long addr, - pmd_t *pmdp, unsigned long clr); + pmd_t *pmdp, + unsigned long clr, + unsigned long set); static inline int __pmdp_test_and_clear_young(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp) @@ -515,7 +519,7 @@ static inline int __pmdp_test_and_clear_young(struct mm_struct *mm, if ((pmd_val(*pmdp) & (_PAGE_ACCESSED | _PAGE_HASHPTE)) == 0) return 0; - old = pmd_hugepage_update(mm, addr, pmdp, _PAGE_ACCESSED); + old = pmd_hugepage_update(mm, addr, pmdp, _PAGE_ACCESSED, 0); return ((old & _PAGE_ACCESSED) != 0); } @@ -542,7 +546,7 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long addr, if ((pmd_val(*pmdp) & _PAGE_RW) == 0) return; - pmd_hugepage_update(mm, addr, pmdp, _PAGE_RW); + pmd_hugepage_update(mm, addr, pmdp, _PAGE_RW, 0); } #define __HAVE_ARCH_PMDP_SPLITTING_FLUSH diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h index f83b6f3e1b39..3ebb188c3ff5 100644 --- a/arch/powerpc/include/asm/pgtable.h +++ b/arch/powerpc/include/asm/pgtable.h @@ -75,12 +75,34 @@ static inline pte_t pte_mknuma(pte_t pte) return pte; } +#define ptep_set_numa ptep_set_numa +static inline void ptep_set_numa(struct mm_struct *mm, unsigned long addr, + pte_t *ptep) +{ + if ((pte_val(*ptep) & _PAGE_PRESENT) == 0) + VM_BUG_ON(1); + + pte_update(mm, addr, ptep, _PAGE_PRESENT, _PAGE_NUMA, 0); + return; +} + #define pmd_numa pmd_numa static inline int pmd_numa(pmd_t pmd) { return pte_numa(pmd_pte(pmd)); } +#define pmdp_set_numa pmdp_set_numa +static inline void pmdp_set_numa(struct mm_struct *mm, unsigned long addr, + pmd_t *pmdp) +{ + if ((pmd_val(*pmdp) & _PAGE_PRESENT) == 0) + VM_BUG_ON(1); + + pmd_hugepage_update(mm, addr, pmdp, _PAGE_PRESENT, _PAGE_NUMA); + return; +} + #define pmd_mknonnuma pmd_mknonnuma static inline pmd_t pmd_mknonnuma(pmd_t pmd) { diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h index becc08e6a65c..279b80f3bb29 100644 --- a/arch/powerpc/include/asm/ptrace.h +++ b/arch/powerpc/include/asm/ptrace.h @@ -28,11 +28,23 @@ #ifdef __powerpc64__ +/* + * Size of redzone that userspace is allowed to use below the stack + * pointer. This is 288 in the 64-bit big-endian ELF ABI, and 512 in + * the new ELFv2 little-endian ABI, so we allow the larger amount. + * + * For kernel code we allow a 288-byte redzone, in order to conserve + * kernel stack space; gcc currently only uses 288 bytes, and will + * hopefully allow explicit control of the redzone size in future. + */ +#define USER_REDZONE_SIZE 512 +#define KERNEL_REDZONE_SIZE 288 + #define STACK_FRAME_OVERHEAD 112 /* size of minimum stack frame */ #define STACK_FRAME_LR_SAVE 2 /* Location of LR in stack frame */ #define STACK_FRAME_REGS_MARKER ASM_CONST(0x7265677368657265) #define STACK_INT_FRAME_SIZE (sizeof(struct pt_regs) + \ - STACK_FRAME_OVERHEAD + 288) + STACK_FRAME_OVERHEAD + KERNEL_REDZONE_SIZE) #define STACK_FRAME_MARKER 12 /* Size of dummy stack frame allocated when calling signal handler. */ @@ -41,6 +53,8 @@ #else /* __powerpc64__ */ +#define USER_REDZONE_SIZE 0 +#define KERNEL_REDZONE_SIZE 0 #define STACK_FRAME_OVERHEAD 16 /* size of minimum stack frame */ #define STACK_FRAME_LR_SAVE 1 /* Location of LR in stack frame */ #define STACK_FRAME_REGS_MARKER ASM_CONST(0x72656773) diff --git a/arch/powerpc/include/asm/sections.h b/arch/powerpc/include/asm/sections.h index 4ee06fe15de4..d0e784e0ff48 100644 --- a/arch/powerpc/include/asm/sections.h +++ b/arch/powerpc/include/asm/sections.h @@ -8,6 +8,7 @@ #ifdef __powerpc64__ +extern char __start_interrupts[]; extern char __end_interrupts[]; extern char __prom_init_toc_start[]; @@ -21,6 +22,17 @@ static inline int in_kernel_text(unsigned long addr) return 0; } +static inline int overlaps_interrupt_vector_text(unsigned long start, + unsigned long end) +{ + unsigned long real_start, real_end; + real_start = __start_interrupts - _stext; + real_end = __end_interrupts - _stext; + + return start < (unsigned long)__va(real_end) && + (unsigned long)__va(real_start) < end; +} + static inline int overlaps_kernel_text(unsigned long start, unsigned long end) { return start < (unsigned long)__init_end && diff --git a/arch/powerpc/include/asm/vdso.h b/arch/powerpc/include/asm/vdso.h index 0d9cecddf8a4..c53f5f6d1761 100644 --- a/arch/powerpc/include/asm/vdso.h +++ b/arch/powerpc/include/asm/vdso.h @@ -4,11 +4,11 @@ #ifdef __KERNEL__ /* Default link addresses for the vDSOs */ -#define VDSO32_LBASE 0x100000 -#define VDSO64_LBASE 0x100000 +#define VDSO32_LBASE 0x0 +#define VDSO64_LBASE 0x0 /* Default map addresses for 32bit vDSO */ -#define VDSO32_MBASE VDSO32_LBASE +#define VDSO32_MBASE 0x100000 #define VDSO_VERSION_STRING LINUX_2.6.15 diff --git a/arch/powerpc/kernel/crash_dump.c b/arch/powerpc/kernel/crash_dump.c index 11c1d069d920..7a13f378ca2c 100644 --- a/arch/powerpc/kernel/crash_dump.c +++ b/arch/powerpc/kernel/crash_dump.c @@ -98,17 +98,19 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf, size_t csize, unsigned long offset, int userbuf) { void *vaddr; + phys_addr_t paddr; if (!csize) return 0; csize = min_t(size_t, csize, PAGE_SIZE); + paddr = pfn << PAGE_SHIFT; - if ((min_low_pfn < pfn) && (pfn < max_pfn)) { - vaddr = __va(pfn << PAGE_SHIFT); + if (memblock_is_region_memory(paddr, csize)) { + vaddr = __va(paddr); csize = copy_oldmem_vaddr(vaddr, buf, csize, offset, userbuf); } else { - vaddr = __ioremap(pfn << PAGE_SHIFT, PAGE_SIZE, 0); + vaddr = __ioremap(paddr, PAGE_SIZE, 0); csize = copy_oldmem_vaddr(vaddr, buf, csize, offset, userbuf); iounmap(vaddr); } diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c index 8032b97ccdcb..ee78f6e49d64 100644 --- a/arch/powerpc/kernel/dma.c +++ b/arch/powerpc/kernel/dma.c @@ -191,12 +191,10 @@ EXPORT_SYMBOL(dma_direct_ops); #define PREALLOC_DMA_DEBUG_ENTRIES (1 << 16) -int dma_set_mask(struct device *dev, u64 dma_mask) +int __dma_set_mask(struct device *dev, u64 dma_mask) { struct dma_map_ops *dma_ops = get_dma_ops(dev); - if (ppc_md.dma_set_mask) - return ppc_md.dma_set_mask(dev, dma_mask); if ((dma_ops != NULL) && (dma_ops->set_dma_mask != NULL)) return dma_ops->set_dma_mask(dev, dma_mask); if (!dev->dma_mask || !dma_supported(dev, dma_mask)) @@ -204,6 +202,12 @@ int dma_set_mask(struct device *dev, u64 dma_mask) *dev->dma_mask = dma_mask; return 0; } +int dma_set_mask(struct device *dev, u64 dma_mask) +{ + if (ppc_md.dma_set_mask) + return ppc_md.dma_set_mask(dev, dma_mask); + return __dma_set_mask(dev, dma_mask); +} EXPORT_SYMBOL(dma_set_mask); u64 dma_get_required_mask(struct device *dev) diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index 148db72a8c43..e7b76a6bf150 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -28,6 +28,7 @@ #include <linux/pci.h> #include <linux/proc_fs.h> #include <linux/rbtree.h> +#include <linux/reboot.h> #include <linux/seq_file.h> #include <linux/spinlock.h> #include <linux/export.h> @@ -89,7 +90,7 @@ /* Platform dependent EEH operations */ struct eeh_ops *eeh_ops = NULL; -int eeh_subsystem_enabled; +bool eeh_subsystem_enabled = false; EXPORT_SYMBOL(eeh_subsystem_enabled); /* @@ -364,7 +365,7 @@ int eeh_dev_check_failure(struct eeh_dev *edev) eeh_stats.total_mmio_ffs++; - if (!eeh_subsystem_enabled) + if (!eeh_enabled()) return 0; if (!edev) { @@ -747,6 +748,17 @@ int __exit eeh_ops_unregister(const char *name) return -EEXIST; } +static int eeh_reboot_notifier(struct notifier_block *nb, + unsigned long action, void *unused) +{ + eeh_set_enable(false); + return NOTIFY_DONE; +} + +static struct notifier_block eeh_reboot_nb = { + .notifier_call = eeh_reboot_notifier, +}; + /** * eeh_init - EEH initialization * @@ -778,6 +790,14 @@ int eeh_init(void) if (machine_is(powernv) && cnt++ <= 0) return ret; + /* Register reboot notifier */ + ret = register_reboot_notifier(&eeh_reboot_nb); + if (ret) { + pr_warn("%s: Failed to register notifier (%d)\n", + __func__, ret); + return ret; + } + /* call platform initialization function */ if (!eeh_ops) { pr_warning("%s: Platform EEH operation not found\n", @@ -822,7 +842,7 @@ int eeh_init(void) return ret; } - if (eeh_subsystem_enabled) + if (eeh_enabled()) pr_info("EEH: PCI Enhanced I/O Error Handling Enabled\n"); else pr_warning("EEH: No capable adapters found\n"); @@ -897,7 +917,7 @@ void eeh_add_device_late(struct pci_dev *dev) struct device_node *dn; struct eeh_dev *edev; - if (!dev || !eeh_subsystem_enabled) + if (!dev || !eeh_enabled()) return; pr_debug("EEH: Adding device %s\n", pci_name(dev)); @@ -1005,7 +1025,7 @@ void eeh_remove_device(struct pci_dev *dev) { struct eeh_dev *edev; - if (!dev || !eeh_subsystem_enabled) + if (!dev || !eeh_enabled()) return; edev = pci_dev_to_eeh_dev(dev); @@ -1045,7 +1065,7 @@ void eeh_remove_device(struct pci_dev *dev) static int proc_eeh_show(struct seq_file *m, void *v) { - if (0 == eeh_subsystem_enabled) { + if (!eeh_enabled()) { seq_printf(m, "EEH Subsystem is globally disabled\n"); seq_printf(m, "eeh_total_mmio_ffs=%llu\n", eeh_stats.total_mmio_ffs); } else { diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index 7bb30dca4e19..fdc679d309ec 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -362,9 +362,13 @@ static void *eeh_rmv_device(void *data, void *userdata) */ if (!dev || (dev->hdr_type & PCI_HEADER_TYPE_BRIDGE)) return NULL; + driver = eeh_pcid_get(dev); - if (driver && driver->err_handler) - return NULL; + if (driver) { + eeh_pcid_put(dev); + if (driver->err_handler) + return NULL; + } /* Remove it from PCI subsystem */ pr_debug("EEH: Removing %s without EEH sensitive driver\n", diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c index 9b27b293a922..b0ded97ee4e1 100644 --- a/arch/powerpc/kernel/ftrace.c +++ b/arch/powerpc/kernel/ftrace.c @@ -74,6 +74,7 @@ ftrace_modify_code(unsigned long ip, unsigned int old, unsigned int new) */ static int test_24bit_addr(unsigned long ip, unsigned long addr) { + addr = ppc_function_entry((void *)addr); /* use the create_branch to verify that this offset can be branched */ return create_branch((unsigned int *)ip, addr, 0); diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index d773dd440a45..88e3ec6e1d96 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -1088,6 +1088,14 @@ int iommu_take_ownership(struct iommu_table *tbl) memset(tbl->it_map, 0xff, sz); iommu_clear_tces_and_put_pages(tbl, tbl->it_offset, tbl->it_size); + /* + * Disable iommu bypass, otherwise the user can DMA to all of + * our physical memory via the bypass window instead of just + * the pages that has been explicitly mapped into the iommu + */ + if (tbl->set_bypass) + tbl->set_bypass(tbl, false); + return 0; } EXPORT_SYMBOL_GPL(iommu_take_ownership); @@ -1102,6 +1110,10 @@ void iommu_release_ownership(struct iommu_table *tbl) /* Restore bit#0 set by iommu_init_table() */ if (tbl->it_offset == 0) set_bit(0, tbl->it_map); + + /* The kernel owns the device now, we can restore the iommu bypass */ + if (tbl->set_bypass) + tbl->set_bypass(tbl, true); } EXPORT_SYMBOL_GPL(iommu_release_ownership); diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 9729b23bfb0a..1d0848bba049 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -559,8 +559,13 @@ void exc_lvl_ctx_init(void) #ifdef CONFIG_PPC64 cpu_nr = i; #else +#ifdef CONFIG_SMP cpu_nr = get_hard_smp_processor_id(i); +#else + cpu_nr = 0; #endif +#endif + memset((void *)critirq_ctx[cpu_nr], 0, THREAD_SIZE); tp = critirq_ctx[cpu_nr]; tp->cpu = cpu_nr; diff --git a/arch/powerpc/kernel/machine_kexec.c b/arch/powerpc/kernel/machine_kexec.c index 75d4f7340da8..015ae55c1868 100644 --- a/arch/powerpc/kernel/machine_kexec.c +++ b/arch/powerpc/kernel/machine_kexec.c @@ -196,7 +196,9 @@ int overlaps_crashkernel(unsigned long start, unsigned long size) /* Values we need to export to the second kernel via the device tree. */ static phys_addr_t kernel_end; +static phys_addr_t crashk_base; static phys_addr_t crashk_size; +static unsigned long long mem_limit; static struct property kernel_end_prop = { .name = "linux,kernel-end", @@ -207,7 +209,7 @@ static struct property kernel_end_prop = { static struct property crashk_base_prop = { .name = "linux,crashkernel-base", .length = sizeof(phys_addr_t), - .value = &crashk_res.start, + .value = &crashk_base }; static struct property crashk_size_prop = { @@ -219,9 +221,11 @@ static struct property crashk_size_prop = { static struct property memory_limit_prop = { .name = "linux,memory-limit", .length = sizeof(unsigned long long), - .value = &memory_limit, + .value = &mem_limit, }; +#define cpu_to_be_ulong __PASTE(cpu_to_be, BITS_PER_LONG) + static void __init export_crashk_values(struct device_node *node) { struct property *prop; @@ -237,8 +241,9 @@ static void __init export_crashk_values(struct device_node *node) of_remove_property(node, prop); if (crashk_res.start != 0) { + crashk_base = cpu_to_be_ulong(crashk_res.start), of_add_property(node, &crashk_base_prop); - crashk_size = resource_size(&crashk_res); + crashk_size = cpu_to_be_ulong(resource_size(&crashk_res)); of_add_property(node, &crashk_size_prop); } @@ -246,6 +251,7 @@ static void __init export_crashk_values(struct device_node *node) * memory_limit is required by the kexec-tools to limit the * crash regions to the actual memory used. */ + mem_limit = cpu_to_be_ulong(memory_limit); of_update_property(node, &memory_limit_prop); } @@ -264,7 +270,7 @@ static int __init kexec_setup(void) of_remove_property(node, prop); /* information needed by userspace when using default_machine_kexec */ - kernel_end = __pa(_end); + kernel_end = cpu_to_be_ulong(__pa(_end)); of_add_property(node, &kernel_end_prop); export_crashk_values(node); diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c index be4e6d648f60..59d229a2a3e0 100644 --- a/arch/powerpc/kernel/machine_kexec_64.c +++ b/arch/powerpc/kernel/machine_kexec_64.c @@ -369,6 +369,7 @@ void default_machine_kexec(struct kimage *image) /* Values we need to export to the second kernel via the device tree. */ static unsigned long htab_base; +static unsigned long htab_size; static struct property htab_base_prop = { .name = "linux,htab-base", @@ -379,7 +380,7 @@ static struct property htab_base_prop = { static struct property htab_size_prop = { .name = "linux,htab-size", .length = sizeof(unsigned long), - .value = &htab_size_bytes, + .value = &htab_size, }; static int __init export_htab_values(void) @@ -403,8 +404,9 @@ static int __init export_htab_values(void) if (prop) of_remove_property(node, prop); - htab_base = __pa(htab_address); + htab_base = cpu_to_be64(__pa(htab_address)); of_add_property(node, &htab_base_prop); + htab_size = cpu_to_be64(htab_size_bytes); of_add_property(node, &htab_size_prop); of_node_put(node); diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S index 879f09620f83..7c6bb4b17b49 100644 --- a/arch/powerpc/kernel/misc_32.S +++ b/arch/powerpc/kernel/misc_32.S @@ -57,11 +57,14 @@ _GLOBAL(call_do_softirq) mtlr r0 blr +/* + * void call_do_irq(struct pt_regs *regs, struct thread_info *irqtp); + */ _GLOBAL(call_do_irq) mflr r0 stw r0,4(r1) lwz r10,THREAD+KSP_LIMIT(r2) - addi r11,r3,THREAD_INFO_GAP + addi r11,r4,THREAD_INFO_GAP stwu r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r4) mr r1,r4 stw r10,8(r1) diff --git a/arch/powerpc/kernel/reloc_64.S b/arch/powerpc/kernel/reloc_64.S index b47a0e1ab001..1482327cfeba 100644 --- a/arch/powerpc/kernel/reloc_64.S +++ b/arch/powerpc/kernel/reloc_64.S @@ -69,8 +69,8 @@ _GLOBAL(relocate) * R_PPC64_RELATIVE ones. */ mtctr r8 -5: lwz r0,12(9) /* ELF64_R_TYPE(reloc->r_info) */ - cmpwi r0,R_PPC64_RELATIVE +5: ld r0,8(9) /* ELF64_R_TYPE(reloc->r_info) */ + cmpdi r0,R_PPC64_RELATIVE bne 6f ld r6,0(r9) /* reloc->r_offset */ ld r0,16(r9) /* reloc->r_addend */ diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index 2b0da27eaee4..04cc4fcca78b 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -247,7 +247,12 @@ static void __init exc_lvl_early_init(void) /* interrupt stacks must be in lowmem, we get that for free on ppc32 * as the memblock is limited to lowmem by MEMBLOCK_REAL_LIMIT */ for_each_possible_cpu(i) { +#ifdef CONFIG_SMP hw_cpu = get_hard_smp_processor_id(i); +#else + hw_cpu = 0; +#endif + critirq_ctx[hw_cpu] = (struct thread_info *) __va(memblock_alloc(THREAD_SIZE, THREAD_SIZE)); #ifdef CONFIG_BOOKE diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index e35bf773df7a..8d253c29649b 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -65,8 +65,8 @@ struct rt_sigframe { struct siginfo __user *pinfo; void __user *puc; struct siginfo info; - /* 64 bit ABI allows for 288 bytes below sp before decrementing it. */ - char abigap[288]; + /* New 64 bit little-endian ABI allows redzone of 512 bytes below sp */ + char abigap[USER_REDZONE_SIZE]; } __attribute__ ((aligned (16))); static const char fmt32[] = KERN_INFO \ diff --git a/arch/powerpc/kernel/vdso32/vdso32_wrapper.S b/arch/powerpc/kernel/vdso32/vdso32_wrapper.S index 79683d0393f5..6ac107ac402a 100644 --- a/arch/powerpc/kernel/vdso32/vdso32_wrapper.S +++ b/arch/powerpc/kernel/vdso32/vdso32_wrapper.S @@ -6,7 +6,7 @@ .globl vdso32_start, vdso32_end .balign PAGE_SIZE vdso32_start: - .incbin "arch/powerpc/kernel/vdso32/vdso32.so" + .incbin "arch/powerpc/kernel/vdso32/vdso32.so.dbg" .balign PAGE_SIZE vdso32_end: diff --git a/arch/powerpc/kernel/vdso64/vdso64_wrapper.S b/arch/powerpc/kernel/vdso64/vdso64_wrapper.S index 8df9e2463007..df60fca6a13d 100644 --- a/arch/powerpc/kernel/vdso64/vdso64_wrapper.S +++ b/arch/powerpc/kernel/vdso64/vdso64_wrapper.S @@ -6,7 +6,7 @@ .globl vdso64_start, vdso64_end .balign PAGE_SIZE vdso64_start: - .incbin "arch/powerpc/kernel/vdso64/vdso64.so" + .incbin "arch/powerpc/kernel/vdso64/vdso64.so.dbg" .balign PAGE_SIZE vdso64_end: diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c index de6881259aef..d766d6ee33fe 100644 --- a/arch/powerpc/mm/hash_utils_64.c +++ b/arch/powerpc/mm/hash_utils_64.c @@ -207,6 +207,20 @@ int htab_bolt_mapping(unsigned long vstart, unsigned long vend, if (overlaps_kernel_text(vaddr, vaddr + step)) tprot &= ~HPTE_R_N; + /* + * If relocatable, check if it overlaps interrupt vectors that + * are copied down to real 0. For relocatable kernel + * (e.g. kdump case) we copy interrupt vectors down to real + * address 0. Mark that region as executable. This is + * because on p8 system with relocation on exception feature + * enabled, exceptions are raised with MMU (IR=DR=1) ON. Hence + * in order to execute the interrupt handlers in virtual + * mode the vector region need to be marked as executable. + */ + if ((PHYSICAL_START > MEMORY_START) && + overlaps_interrupt_vector_text(vaddr, vaddr + step)) + tprot &= ~HPTE_R_N; + hash = hpt_hash(vpn, shift, ssize); hpteg = ((hash & htab_hash_mask) * HPTES_PER_GROUP); diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c index 65b7b65e8708..62bf5e8e78da 100644 --- a/arch/powerpc/mm/pgtable_64.c +++ b/arch/powerpc/mm/pgtable_64.c @@ -510,7 +510,8 @@ int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address, } unsigned long pmd_hugepage_update(struct mm_struct *mm, unsigned long addr, - pmd_t *pmdp, unsigned long clr) + pmd_t *pmdp, unsigned long clr, + unsigned long set) { unsigned long old, tmp; @@ -526,14 +527,15 @@ unsigned long pmd_hugepage_update(struct mm_struct *mm, unsigned long addr, andi. %1,%0,%6\n\ bne- 1b \n\ andc %1,%0,%4 \n\ + or %1,%1,%7\n\ stdcx. %1,0,%3 \n\ bne- 1b" : "=&r" (old), "=&r" (tmp), "=m" (*pmdp) - : "r" (pmdp), "r" (clr), "m" (*pmdp), "i" (_PAGE_BUSY) + : "r" (pmdp), "r" (clr), "m" (*pmdp), "i" (_PAGE_BUSY), "r" (set) : "cc" ); #else old = pmd_val(*pmdp); - *pmdp = __pmd(old & ~clr); + *pmdp = __pmd((old & ~clr) | set); #endif if (old & _PAGE_HASHPTE) hpte_do_hugepage_flush(mm, addr, pmdp); @@ -708,7 +710,7 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr, void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { - pmd_hugepage_update(vma->vm_mm, address, pmdp, _PAGE_PRESENT); + pmd_hugepage_update(vma->vm_mm, address, pmdp, _PAGE_PRESENT, 0); } /* @@ -835,7 +837,7 @@ pmd_t pmdp_get_and_clear(struct mm_struct *mm, unsigned long old; pgtable_t *pgtable_slot; - old = pmd_hugepage_update(mm, addr, pmdp, ~0UL); + old = pmd_hugepage_update(mm, addr, pmdp, ~0UL, 0); old_pmd = __pmd(old); /* * We have pmd == none and we are holding page_table_lock. diff --git a/arch/powerpc/mm/subpage-prot.c b/arch/powerpc/mm/subpage-prot.c index a770df2dae70..6c0b1f5f8d2c 100644 --- a/arch/powerpc/mm/subpage-prot.c +++ b/arch/powerpc/mm/subpage-prot.c @@ -78,7 +78,7 @@ static void hpte_flush_range(struct mm_struct *mm, unsigned long addr, pte = pte_offset_map_lock(mm, pmd, addr, &ptl); arch_enter_lazy_mmu_mode(); for (; npages > 0; --npages) { - pte_update(mm, addr, pte, 0, 0); + pte_update(mm, addr, pte, 0, 0, 0); addr += PAGE_SIZE; ++pte; } diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index 29b89e863d7c..67cf22083f4c 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -1147,6 +1147,9 @@ static void power_pmu_enable(struct pmu *pmu) mmcr0 = ebb_switch_in(ebb, cpuhw->mmcr[0]); mb(); + if (cpuhw->bhrb_users) + ppmu->config_bhrb(cpuhw->bhrb_filter); + write_mmcr0(cpuhw, mmcr0); /* @@ -1158,8 +1161,6 @@ static void power_pmu_enable(struct pmu *pmu) } out: - if (cpuhw->bhrb_users) - ppmu->config_bhrb(cpuhw->bhrb_filter); local_irq_restore(flags); } diff --git a/arch/powerpc/perf/power8-pmu.c b/arch/powerpc/perf/power8-pmu.c index a3f7abd2f13f..96cee20dcd34 100644 --- a/arch/powerpc/perf/power8-pmu.c +++ b/arch/powerpc/perf/power8-pmu.c @@ -25,6 +25,37 @@ #define PM_BRU_FIN 0x10068 #define PM_BR_MPRED_CMPL 0x400f6 +/* All L1 D cache load references counted at finish, gated by reject */ +#define PM_LD_REF_L1 0x100ee +/* Load Missed L1 */ +#define PM_LD_MISS_L1 0x3e054 +/* Store Missed L1 */ +#define PM_ST_MISS_L1 0x300f0 +/* L1 cache data prefetches */ +#define PM_L1_PREF 0x0d8b8 +/* Instruction fetches from L1 */ +#define PM_INST_FROM_L1 0x04080 +/* Demand iCache Miss */ +#define PM_L1_ICACHE_MISS 0x200fd +/* Instruction Demand sectors wriittent into IL1 */ +#define PM_L1_DEMAND_WRITE 0x0408c +/* Instruction prefetch written into IL1 */ +#define PM_IC_PREF_WRITE 0x0408e +/* The data cache was reloaded from local core's L3 due to a demand load */ +#define PM_DATA_FROM_L3 0x4c042 +/* Demand LD - L3 Miss (not L2 hit and not L3 hit) */ +#define PM_DATA_FROM_L3MISS 0x300fe +/* All successful D-side store dispatches for this thread */ +#define PM_L2_ST 0x17080 +/* All successful D-side store dispatches for this thread that were L2 Miss */ +#define PM_L2_ST_MISS 0x17082 +/* Total HW L3 prefetches(Load+store) */ +#define PM_L3_PREF_ALL 0x4e052 +/* Data PTEG reload */ +#define PM_DTLB_MISS 0x300fc +/* ITLB Reloaded */ +#define PM_ITLB_MISS 0x400fc + /* * Raw event encoding for POWER8: @@ -557,6 +588,8 @@ static int power8_generic_events[] = { [PERF_COUNT_HW_INSTRUCTIONS] = PM_INST_CMPL, [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = PM_BRU_FIN, [PERF_COUNT_HW_BRANCH_MISSES] = PM_BR_MPRED_CMPL, + [PERF_COUNT_HW_CACHE_REFERENCES] = PM_LD_REF_L1, + [PERF_COUNT_HW_CACHE_MISSES] = PM_LD_MISS_L1, }; static u64 power8_bhrb_filter_map(u64 branch_sample_type) @@ -596,6 +629,116 @@ static void power8_config_bhrb(u64 pmu_bhrb_filter) mtspr(SPRN_MMCRA, (mfspr(SPRN_MMCRA) | pmu_bhrb_filter)); } +#define C(x) PERF_COUNT_HW_CACHE_##x + +/* + * Table of generalized cache-related events. + * 0 means not supported, -1 means nonsensical, other values + * are event codes. + */ +static int power8_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { + [ C(L1D) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = PM_LD_REF_L1, + [ C(RESULT_MISS) ] = PM_LD_MISS_L1, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0, + [ C(RESULT_MISS) ] = PM_ST_MISS_L1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = PM_L1_PREF, + [ C(RESULT_MISS) ] = 0, + }, + }, + [ C(L1I) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = PM_INST_FROM_L1, + [ C(RESULT_MISS) ] = PM_L1_ICACHE_MISS, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = PM_L1_DEMAND_WRITE, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = PM_IC_PREF_WRITE, + [ C(RESULT_MISS) ] = 0, + }, + }, + [ C(LL) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = PM_DATA_FROM_L3, + [ C(RESULT_MISS) ] = PM_DATA_FROM_L3MISS, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = PM_L2_ST, + [ C(RESULT_MISS) ] = PM_L2_ST_MISS, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = PM_L3_PREF_ALL, + [ C(RESULT_MISS) ] = 0, + }, + }, + [ C(DTLB) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0, + [ C(RESULT_MISS) ] = PM_DTLB_MISS, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, + [ C(ITLB) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0, + [ C(RESULT_MISS) ] = PM_ITLB_MISS, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, + [ C(BPU) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = PM_BRU_FIN, + [ C(RESULT_MISS) ] = PM_BR_MPRED_CMPL, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, + [ C(NODE) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, +}; + +#undef C + static struct power_pmu power8_pmu = { .name = "POWER8", .n_counter = 6, @@ -611,6 +754,7 @@ static struct power_pmu power8_pmu = { .flags = PPMU_HAS_SSLOT | PPMU_HAS_SIER | PPMU_BHRB | PPMU_EBB, .n_generic = ARRAY_SIZE(power8_generic_events), .generic_events = power8_generic_events, + .cache_events = &power8_cache_events, .attr_groups = power8_pmu_attr_groups, .bhrb_nr = 32, }; diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c index e1e71618b70c..253fefe3d1a0 100644 --- a/arch/powerpc/platforms/powernv/eeh-ioda.c +++ b/arch/powerpc/platforms/powernv/eeh-ioda.c @@ -44,7 +44,8 @@ static int ioda_eeh_event(struct notifier_block *nb, /* We simply send special EEH event */ if ((changed_evts & OPAL_EVENT_PCI_ERROR) && - (events & OPAL_EVENT_PCI_ERROR)) + (events & OPAL_EVENT_PCI_ERROR) && + eeh_enabled()) eeh_send_failure_event(NULL); return 0; @@ -113,6 +114,7 @@ DEFINE_SIMPLE_ATTRIBUTE(ioda_eeh_inbB_dbgfs_ops, ioda_eeh_inbB_dbgfs_get, ioda_eeh_inbB_dbgfs_set, "0x%llx\n"); #endif /* CONFIG_DEBUG_FS */ + /** * ioda_eeh_post_init - Chip dependent post initialization * @hose: PCI controller @@ -220,6 +222,22 @@ static int ioda_eeh_set_option(struct eeh_pe *pe, int option) return ret; } +static void ioda_eeh_phb_diag(struct pci_controller *hose) +{ + struct pnv_phb *phb = hose->private_data; + long rc; + + rc = opal_pci_get_phb_diag_data2(phb->opal_id, phb->diag.blob, + PNV_PCI_DIAG_BUF_SIZE); + if (rc != OPAL_SUCCESS) { + pr_warning("%s: Failed to get diag-data for PHB#%x (%ld)\n", + __func__, hose->global_number, rc); + return; + } + + pnv_pci_dump_phb_diag_data(hose, phb->diag.blob); +} + /** * ioda_eeh_get_state - Retrieve the state of PE * @pe: EEH PE @@ -271,6 +289,9 @@ static int ioda_eeh_get_state(struct eeh_pe *pe) result |= EEH_STATE_DMA_ACTIVE; result |= EEH_STATE_MMIO_ENABLED; result |= EEH_STATE_DMA_ENABLED; + } else if (!(pe->state & EEH_PE_ISOLATED)) { + eeh_pe_state_mark(pe, EEH_PE_ISOLATED); + ioda_eeh_phb_diag(hose); } return result; @@ -314,6 +335,15 @@ static int ioda_eeh_get_state(struct eeh_pe *pe) __func__, fstate, hose->global_number, pe_no); } + /* Dump PHB diag-data for frozen PE */ + if (result != EEH_STATE_NOT_SUPPORT && + (result & (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE)) != + (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE) && + !(pe->state & EEH_PE_ISOLATED)) { + eeh_pe_state_mark(pe, EEH_PE_ISOLATED); + ioda_eeh_phb_diag(hose); + } + return result; } @@ -489,8 +519,7 @@ static int ioda_eeh_bridge_reset(struct pci_controller *hose, static int ioda_eeh_reset(struct eeh_pe *pe, int option) { struct pci_controller *hose = pe->phb; - struct eeh_dev *edev; - struct pci_dev *dev; + struct pci_bus *bus; int ret; /* @@ -519,73 +548,17 @@ static int ioda_eeh_reset(struct eeh_pe *pe, int option) if (pe->type & EEH_PE_PHB) { ret = ioda_eeh_phb_reset(hose, option); } else { - if (pe->type & EEH_PE_DEVICE) { - /* - * If it's device PE, we didn't refer to the parent - * PCI bus yet. So we have to figure it out indirectly. - */ - edev = list_first_entry(&pe->edevs, - struct eeh_dev, list); - dev = eeh_dev_to_pci_dev(edev); - dev = dev->bus->self; - } else { - /* - * If it's bus PE, the parent PCI bus is already there - * and just pick it up. - */ - dev = pe->bus->self; - } - - /* - * Do reset based on the fact that the direct upstream bridge - * is root bridge (port) or not. - */ - if (dev->bus->number == 0) + bus = eeh_pe_bus_get(pe); + if (pci_is_root_bus(bus)) ret = ioda_eeh_root_reset(hose, option); else - ret = ioda_eeh_bridge_reset(hose, dev, option); + ret = ioda_eeh_bridge_reset(hose, bus->self, option); } return ret; } /** - * ioda_eeh_get_log - Retrieve error log - * @pe: EEH PE - * @severity: Severity level of the log - * @drv_log: buffer to store the log - * @len: space of the log buffer - * - * The function is used to retrieve error log from P7IOC. - */ -static int ioda_eeh_get_log(struct eeh_pe *pe, int severity, - char *drv_log, unsigned long len) -{ - s64 ret; - unsigned long flags; - struct pci_controller *hose = pe->phb; - struct pnv_phb *phb = hose->private_data; - - spin_lock_irqsave(&phb->lock, flags); - - ret = opal_pci_get_phb_diag_data2(phb->opal_id, - phb->diag.blob, PNV_PCI_DIAG_BUF_SIZE); - if (ret) { - spin_unlock_irqrestore(&phb->lock, flags); - pr_warning("%s: Can't get log for PHB#%x-PE#%x (%lld)\n", - __func__, hose->global_number, pe->addr, ret); - return -EIO; - } - - /* The PHB diag-data is always indicative */ - pnv_pci_dump_phb_diag_data(hose, phb->diag.blob); - - spin_unlock_irqrestore(&phb->lock, flags); - - return 0; -} - -/** * ioda_eeh_configure_bridge - Configure the PCI bridges for the indicated PE * @pe: EEH PE * @@ -666,22 +639,6 @@ static void ioda_eeh_hub_diag(struct pci_controller *hose) } } -static void ioda_eeh_phb_diag(struct pci_controller *hose) -{ - struct pnv_phb *phb = hose->private_data; - long rc; - - rc = opal_pci_get_phb_diag_data2(phb->opal_id, phb->diag.blob, - PNV_PCI_DIAG_BUF_SIZE); - if (rc != OPAL_SUCCESS) { - pr_warning("%s: Failed to get diag-data for PHB#%x (%ld)\n", - __func__, hose->global_number, rc); - return; - } - - pnv_pci_dump_phb_diag_data(hose, phb->diag.blob); -} - static int ioda_eeh_get_phb_pe(struct pci_controller *hose, struct eeh_pe **pe) { @@ -855,6 +812,20 @@ static int ioda_eeh_next_error(struct eeh_pe **pe) } /* + * EEH core will try recover from fenced PHB or + * frozen PE. In the time for frozen PE, EEH core + * enable IO path for that before collecting logs, + * but it ruins the site. So we have to dump the + * log in advance here. + */ + if ((ret == EEH_NEXT_ERR_FROZEN_PE || + ret == EEH_NEXT_ERR_FENCED_PHB) && + !((*pe)->state & EEH_PE_ISOLATED)) { + eeh_pe_state_mark(*pe, EEH_PE_ISOLATED); + ioda_eeh_phb_diag(hose); + } + + /* * If we have no errors on the specific PHB or only * informative error there, we continue poking it. * Otherwise, we need actions to be taken by upper @@ -872,7 +843,6 @@ struct pnv_eeh_ops ioda_eeh_ops = { .set_option = ioda_eeh_set_option, .get_state = ioda_eeh_get_state, .reset = ioda_eeh_reset, - .get_log = ioda_eeh_get_log, .configure_bridge = ioda_eeh_configure_bridge, .next_error = ioda_eeh_next_error }; diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c index a79fddc5e74e..a59788e83b8b 100644 --- a/arch/powerpc/platforms/powernv/eeh-powernv.c +++ b/arch/powerpc/platforms/powernv/eeh-powernv.c @@ -145,7 +145,7 @@ static int powernv_eeh_dev_probe(struct pci_dev *dev, void *flag) * Enable EEH explicitly so that we will do EEH check * while accessing I/O stuff */ - eeh_subsystem_enabled = 1; + eeh_set_enable(true); /* Save memory bars */ eeh_save_bars(edev); diff --git a/arch/powerpc/platforms/powernv/opal-xscom.c b/arch/powerpc/platforms/powernv/opal-xscom.c index 4fbf276ac99e..4cd2ea6c0dbe 100644 --- a/arch/powerpc/platforms/powernv/opal-xscom.c +++ b/arch/powerpc/platforms/powernv/opal-xscom.c @@ -71,11 +71,11 @@ static int opal_xscom_err_xlate(int64_t rc) } } -static u64 opal_scom_unmangle(u64 reg) +static u64 opal_scom_unmangle(u64 addr) { /* * XSCOM indirect addresses have the top bit set. Additionally - * the reset of the top 3 nibbles is always 0. + * the rest of the top 3 nibbles is always 0. * * Because the debugfs interface uses signed offsets and shifts * the address left by 3, we basically cannot use the top 4 bits @@ -86,10 +86,13 @@ static u64 opal_scom_unmangle(u64 reg) * conversion here. To leave room for further xscom address * expansion, we only clear out the top byte * + * For in-kernel use, we also support the real indirect bit, so + * we test for any of the top 5 bits + * */ - if (reg & (1ull << 59)) - reg = (reg & ~(0xffull << 56)) | (1ull << 63); - return reg; + if (addr & (0x1full << 59)) + addr = (addr & ~(0xffull << 56)) | (1ull << 63); + return addr; } static int opal_scom_read(scom_map_t map, u64 reg, u64 *value) @@ -98,8 +101,8 @@ static int opal_scom_read(scom_map_t map, u64 reg, u64 *value) int64_t rc; __be64 v; - reg = opal_scom_unmangle(reg); - rc = opal_xscom_read(m->chip, m->addr + reg, (__be64 *)__pa(&v)); + reg = opal_scom_unmangle(m->addr + reg); + rc = opal_xscom_read(m->chip, reg, (__be64 *)__pa(&v)); *value = be64_to_cpu(v); return opal_xscom_err_xlate(rc); } @@ -109,8 +112,8 @@ static int opal_scom_write(scom_map_t map, u64 reg, u64 value) struct opal_scom_map *m = map; int64_t rc; - reg = opal_scom_unmangle(reg); - rc = opal_xscom_write(m->chip, m->addr + reg, value); + reg = opal_scom_unmangle(m->addr + reg); + rc = opal_xscom_write(m->chip, reg, value); return opal_xscom_err_xlate(rc); } diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 7d6dcc6d5fa9..3b2b4fb3585b 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -21,6 +21,7 @@ #include <linux/irq.h> #include <linux/io.h> #include <linux/msi.h> +#include <linux/memblock.h> #include <asm/sections.h> #include <asm/io.h> @@ -460,9 +461,39 @@ static void pnv_pci_ioda_dma_dev_setup(struct pnv_phb *phb, struct pci_dev *pdev return; pe = &phb->ioda.pe_array[pdn->pe_number]; + WARN_ON(get_dma_ops(&pdev->dev) != &dma_iommu_ops); set_iommu_table_base_and_group(&pdev->dev, &pe->tce32_table); } +static int pnv_pci_ioda_dma_set_mask(struct pnv_phb *phb, + struct pci_dev *pdev, u64 dma_mask) +{ + struct pci_dn *pdn = pci_get_pdn(pdev); + struct pnv_ioda_pe *pe; + uint64_t top; + bool bypass = false; + + if (WARN_ON(!pdn || pdn->pe_number == IODA_INVALID_PE)) + return -ENODEV;; + + pe = &phb->ioda.pe_array[pdn->pe_number]; + if (pe->tce_bypass_enabled) { + top = pe->tce_bypass_base + memblock_end_of_DRAM() - 1; + bypass = (dma_mask >= top); + } + + if (bypass) { + dev_info(&pdev->dev, "Using 64-bit DMA iommu bypass\n"); + set_dma_ops(&pdev->dev, &dma_direct_ops); + set_dma_offset(&pdev->dev, pe->tce_bypass_base); + } else { + dev_info(&pdev->dev, "Using 32-bit DMA via iommu\n"); + set_dma_ops(&pdev->dev, &dma_iommu_ops); + set_iommu_table_base(&pdev->dev, &pe->tce32_table); + } + return 0; +} + static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe, struct pci_bus *bus) { struct pci_dev *dev; @@ -657,6 +688,56 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb, __free_pages(tce_mem, get_order(TCE32_TABLE_SIZE * segs)); } +static void pnv_pci_ioda2_set_bypass(struct iommu_table *tbl, bool enable) +{ + struct pnv_ioda_pe *pe = container_of(tbl, struct pnv_ioda_pe, + tce32_table); + uint16_t window_id = (pe->pe_number << 1 ) + 1; + int64_t rc; + + pe_info(pe, "%sabling 64-bit DMA bypass\n", enable ? "En" : "Dis"); + if (enable) { + phys_addr_t top = memblock_end_of_DRAM(); + + top = roundup_pow_of_two(top); + rc = opal_pci_map_pe_dma_window_real(pe->phb->opal_id, + pe->pe_number, + window_id, + pe->tce_bypass_base, + top); + } else { + rc = opal_pci_map_pe_dma_window_real(pe->phb->opal_id, + pe->pe_number, + window_id, + pe->tce_bypass_base, + 0); + + /* + * We might want to reset the DMA ops of all devices on + * this PE. However in theory, that shouldn't be necessary + * as this is used for VFIO/KVM pass-through and the device + * hasn't yet been returned to its kernel driver + */ + } + if (rc) + pe_err(pe, "OPAL error %lld configuring bypass window\n", rc); + else + pe->tce_bypass_enabled = enable; +} + +static void pnv_pci_ioda2_setup_bypass_pe(struct pnv_phb *phb, + struct pnv_ioda_pe *pe) +{ + /* TVE #1 is selected by PCI address bit 59 */ + pe->tce_bypass_base = 1ull << 59; + + /* Install set_bypass callback for VFIO */ + pe->tce32_table.set_bypass = pnv_pci_ioda2_set_bypass; + + /* Enable bypass by default */ + pnv_pci_ioda2_set_bypass(&pe->tce32_table, true); +} + static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe) { @@ -727,6 +808,8 @@ static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb, else pnv_ioda_setup_bus_dma(pe, pe->pbus); + /* Also create a bypass window */ + pnv_pci_ioda2_setup_bypass_pe(phb, pe); return; fail: if (pe->tce32_seg >= 0) @@ -1286,6 +1369,7 @@ void __init pnv_pci_init_ioda_phb(struct device_node *np, /* Setup TCEs */ phb->dma_dev_setup = pnv_pci_ioda_dma_dev_setup; + phb->dma_set_mask = pnv_pci_ioda_dma_set_mask; /* Setup shutdown function for kexec */ phb->shutdown = pnv_pci_ioda_shutdown; diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index b555ebc57ef5..8518817dcdfd 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -134,57 +134,72 @@ static void pnv_pci_dump_p7ioc_diag_data(struct pci_controller *hose, pr_info("P7IOC PHB#%d Diag-data (Version: %d)\n\n", hose->global_number, common->version); - pr_info(" brdgCtl: %08x\n", data->brdgCtl); - - pr_info(" portStatusReg: %08x\n", data->portStatusReg); - pr_info(" rootCmplxStatus: %08x\n", data->rootCmplxStatus); - pr_info(" busAgentStatus: %08x\n", data->busAgentStatus); - - pr_info(" deviceStatus: %08x\n", data->deviceStatus); - pr_info(" slotStatus: %08x\n", data->slotStatus); - pr_info(" linkStatus: %08x\n", data->linkStatus); - pr_info(" devCmdStatus: %08x\n", data->devCmdStatus); - pr_info(" devSecStatus: %08x\n", data->devSecStatus); - - pr_info(" rootErrorStatus: %08x\n", data->rootErrorStatus); - pr_info(" uncorrErrorStatus: %08x\n", data->uncorrErrorStatus); - pr_info(" corrErrorStatus: %08x\n", data->corrErrorStatus); - pr_info(" tlpHdr1: %08x\n", data->tlpHdr1); - pr_info(" tlpHdr2: %08x\n", data->tlpHdr2); - pr_info(" tlpHdr3: %08x\n", data->tlpHdr3); - pr_info(" tlpHdr4: %08x\n", data->tlpHdr4); - pr_info(" sourceId: %08x\n", data->sourceId); - pr_info(" errorClass: %016llx\n", data->errorClass); - pr_info(" correlator: %016llx\n", data->correlator); - pr_info(" p7iocPlssr: %016llx\n", data->p7iocPlssr); - pr_info(" p7iocCsr: %016llx\n", data->p7iocCsr); - pr_info(" lemFir: %016llx\n", data->lemFir); - pr_info(" lemErrorMask: %016llx\n", data->lemErrorMask); - pr_info(" lemWOF: %016llx\n", data->lemWOF); - pr_info(" phbErrorStatus: %016llx\n", data->phbErrorStatus); - pr_info(" phbFirstErrorStatus: %016llx\n", data->phbFirstErrorStatus); - pr_info(" phbErrorLog0: %016llx\n", data->phbErrorLog0); - pr_info(" phbErrorLog1: %016llx\n", data->phbErrorLog1); - pr_info(" mmioErrorStatus: %016llx\n", data->mmioErrorStatus); - pr_info(" mmioFirstErrorStatus: %016llx\n", data->mmioFirstErrorStatus); - pr_info(" mmioErrorLog0: %016llx\n", data->mmioErrorLog0); - pr_info(" mmioErrorLog1: %016llx\n", data->mmioErrorLog1); - pr_info(" dma0ErrorStatus: %016llx\n", data->dma0ErrorStatus); - pr_info(" dma0FirstErrorStatus: %016llx\n", data->dma0FirstErrorStatus); - pr_info(" dma0ErrorLog0: %016llx\n", data->dma0ErrorLog0); - pr_info(" dma0ErrorLog1: %016llx\n", data->dma0ErrorLog1); - pr_info(" dma1ErrorStatus: %016llx\n", data->dma1ErrorStatus); - pr_info(" dma1FirstErrorStatus: %016llx\n", data->dma1FirstErrorStatus); - pr_info(" dma1ErrorLog0: %016llx\n", data->dma1ErrorLog0); - pr_info(" dma1ErrorLog1: %016llx\n", data->dma1ErrorLog1); + if (data->brdgCtl) + pr_info(" brdgCtl: %08x\n", + data->brdgCtl); + if (data->portStatusReg || data->rootCmplxStatus || + data->busAgentStatus) + pr_info(" UtlSts: %08x %08x %08x\n", + data->portStatusReg, data->rootCmplxStatus, + data->busAgentStatus); + if (data->deviceStatus || data->slotStatus || + data->linkStatus || data->devCmdStatus || + data->devSecStatus) + pr_info(" RootSts: %08x %08x %08x %08x %08x\n", + data->deviceStatus, data->slotStatus, + data->linkStatus, data->devCmdStatus, + data->devSecStatus); + if (data->rootErrorStatus || data->uncorrErrorStatus || + data->corrErrorStatus) + pr_info(" RootErrSts: %08x %08x %08x\n", + data->rootErrorStatus, data->uncorrErrorStatus, + data->corrErrorStatus); + if (data->tlpHdr1 || data->tlpHdr2 || + data->tlpHdr3 || data->tlpHdr4) + pr_info(" RootErrLog: %08x %08x %08x %08x\n", + data->tlpHdr1, data->tlpHdr2, + data->tlpHdr3, data->tlpHdr4); + if (data->sourceId || data->errorClass || + data->correlator) + pr_info(" RootErrLog1: %08x %016llx %016llx\n", + data->sourceId, data->errorClass, + data->correlator); + if (data->p7iocPlssr || data->p7iocCsr) + pr_info(" PhbSts: %016llx %016llx\n", + data->p7iocPlssr, data->p7iocCsr); + if (data->lemFir || data->lemErrorMask || + data->lemWOF) + pr_info(" Lem: %016llx %016llx %016llx\n", + data->lemFir, data->lemErrorMask, + data->lemWOF); + if (data->phbErrorStatus || data->phbFirstErrorStatus || + data->phbErrorLog0 || data->phbErrorLog1) + pr_info(" PhbErr: %016llx %016llx %016llx %016llx\n", + data->phbErrorStatus, data->phbFirstErrorStatus, + data->phbErrorLog0, data->phbErrorLog1); + if (data->mmioErrorStatus || data->mmioFirstErrorStatus || + data->mmioErrorLog0 || data->mmioErrorLog1) + pr_info(" OutErr: %016llx %016llx %016llx %016llx\n", + data->mmioErrorStatus, data->mmioFirstErrorStatus, + data->mmioErrorLog0, data->mmioErrorLog1); + if (data->dma0ErrorStatus || data->dma0FirstErrorStatus || + data->dma0ErrorLog0 || data->dma0ErrorLog1) + pr_info(" InAErr: %016llx %016llx %016llx %016llx\n", + data->dma0ErrorStatus, data->dma0FirstErrorStatus, + data->dma0ErrorLog0, data->dma0ErrorLog1); + if (data->dma1ErrorStatus || data->dma1FirstErrorStatus || + data->dma1ErrorLog0 || data->dma1ErrorLog1) + pr_info(" InBErr: %016llx %016llx %016llx %016llx\n", + data->dma1ErrorStatus, data->dma1FirstErrorStatus, + data->dma1ErrorLog0, data->dma1ErrorLog1); for (i = 0; i < OPAL_P7IOC_NUM_PEST_REGS; i++) { if ((data->pestA[i] >> 63) == 0 && (data->pestB[i] >> 63) == 0) continue; - pr_info(" PE[%3d] PESTA: %016llx\n", i, data->pestA[i]); - pr_info(" PESTB: %016llx\n", data->pestB[i]); + pr_info(" PE[%3d] A/B: %016llx %016llx\n", + i, data->pestA[i], data->pestB[i]); } } @@ -197,62 +212,77 @@ static void pnv_pci_dump_phb3_diag_data(struct pci_controller *hose, data = (struct OpalIoPhb3ErrorData*)common; pr_info("PHB3 PHB#%d Diag-data (Version: %d)\n\n", hose->global_number, common->version); - - pr_info(" brdgCtl: %08x\n", data->brdgCtl); - - pr_info(" portStatusReg: %08x\n", data->portStatusReg); - pr_info(" rootCmplxStatus: %08x\n", data->rootCmplxStatus); - pr_info(" busAgentStatus: %08x\n", data->busAgentStatus); - - pr_info(" deviceStatus: %08x\n", data->deviceStatus); - pr_info(" slotStatus: %08x\n", data->slotStatus); - pr_info(" linkStatus: %08x\n", data->linkStatus); - pr_info(" devCmdStatus: %08x\n", data->devCmdStatus); - pr_info(" devSecStatus: %08x\n", data->devSecStatus); - - pr_info(" rootErrorStatus: %08x\n", data->rootErrorStatus); - pr_info(" uncorrErrorStatus: %08x\n", data->uncorrErrorStatus); - pr_info(" corrErrorStatus: %08x\n", data->corrErrorStatus); - pr_info(" tlpHdr1: %08x\n", data->tlpHdr1); - pr_info(" tlpHdr2: %08x\n", data->tlpHdr2); - pr_info(" tlpHdr3: %08x\n", data->tlpHdr3); - pr_info(" tlpHdr4: %08x\n", data->tlpHdr4); - pr_info(" sourceId: %08x\n", data->sourceId); - pr_info(" errorClass: %016llx\n", data->errorClass); - pr_info(" correlator: %016llx\n", data->correlator); - - pr_info(" nFir: %016llx\n", data->nFir); - pr_info(" nFirMask: %016llx\n", data->nFirMask); - pr_info(" nFirWOF: %016llx\n", data->nFirWOF); - pr_info(" PhbPlssr: %016llx\n", data->phbPlssr); - pr_info(" PhbCsr: %016llx\n", data->phbCsr); - pr_info(" lemFir: %016llx\n", data->lemFir); - pr_info(" lemErrorMask: %016llx\n", data->lemErrorMask); - pr_info(" lemWOF: %016llx\n", data->lemWOF); - pr_info(" phbErrorStatus: %016llx\n", data->phbErrorStatus); - pr_info(" phbFirstErrorStatus: %016llx\n", data->phbFirstErrorStatus); - pr_info(" phbErrorLog0: %016llx\n", data->phbErrorLog0); - pr_info(" phbErrorLog1: %016llx\n", data->phbErrorLog1); - pr_info(" mmioErrorStatus: %016llx\n", data->mmioErrorStatus); - pr_info(" mmioFirstErrorStatus: %016llx\n", data->mmioFirstErrorStatus); - pr_info(" mmioErrorLog0: %016llx\n", data->mmioErrorLog0); - pr_info(" mmioErrorLog1: %016llx\n", data->mmioErrorLog1); - pr_info(" dma0ErrorStatus: %016llx\n", data->dma0ErrorStatus); - pr_info(" dma0FirstErrorStatus: %016llx\n", data->dma0FirstErrorStatus); - pr_info(" dma0ErrorLog0: %016llx\n", data->dma0ErrorLog0); - pr_info(" dma0ErrorLog1: %016llx\n", data->dma0ErrorLog1); - pr_info(" dma1ErrorStatus: %016llx\n", data->dma1ErrorStatus); - pr_info(" dma1FirstErrorStatus: %016llx\n", data->dma1FirstErrorStatus); - pr_info(" dma1ErrorLog0: %016llx\n", data->dma1ErrorLog0); - pr_info(" dma1ErrorLog1: %016llx\n", data->dma1ErrorLog1); + if (data->brdgCtl) + pr_info(" brdgCtl: %08x\n", + data->brdgCtl); + if (data->portStatusReg || data->rootCmplxStatus || + data->busAgentStatus) + pr_info(" UtlSts: %08x %08x %08x\n", + data->portStatusReg, data->rootCmplxStatus, + data->busAgentStatus); + if (data->deviceStatus || data->slotStatus || + data->linkStatus || data->devCmdStatus || + data->devSecStatus) + pr_info(" RootSts: %08x %08x %08x %08x %08x\n", + data->deviceStatus, data->slotStatus, + data->linkStatus, data->devCmdStatus, + data->devSecStatus); + if (data->rootErrorStatus || data->uncorrErrorStatus || + data->corrErrorStatus) + pr_info(" RootErrSts: %08x %08x %08x\n", + data->rootErrorStatus, data->uncorrErrorStatus, + data->corrErrorStatus); + if (data->tlpHdr1 || data->tlpHdr2 || + data->tlpHdr3 || data->tlpHdr4) + pr_info(" RootErrLog: %08x %08x %08x %08x\n", + data->tlpHdr1, data->tlpHdr2, + data->tlpHdr3, data->tlpHdr4); + if (data->sourceId || data->errorClass || + data->correlator) + pr_info(" RootErrLog1: %08x %016llx %016llx\n", + data->sourceId, data->errorClass, + data->correlator); + if (data->nFir || data->nFirMask || + data->nFirWOF) + pr_info(" nFir: %016llx %016llx %016llx\n", + data->nFir, data->nFirMask, + data->nFirWOF); + if (data->phbPlssr || data->phbCsr) + pr_info(" PhbSts: %016llx %016llx\n", + data->phbPlssr, data->phbCsr); + if (data->lemFir || data->lemErrorMask || + data->lemWOF) + pr_info(" Lem: %016llx %016llx %016llx\n", + data->lemFir, data->lemErrorMask, + data->lemWOF); + if (data->phbErrorStatus || data->phbFirstErrorStatus || + data->phbErrorLog0 || data->phbErrorLog1) + pr_info(" PhbErr: %016llx %016llx %016llx %016llx\n", + data->phbErrorStatus, data->phbFirstErrorStatus, + data->phbErrorLog0, data->phbErrorLog1); + if (data->mmioErrorStatus || data->mmioFirstErrorStatus || + data->mmioErrorLog0 || data->mmioErrorLog1) + pr_info(" OutErr: %016llx %016llx %016llx %016llx\n", + data->mmioErrorStatus, data->mmioFirstErrorStatus, + data->mmioErrorLog0, data->mmioErrorLog1); + if (data->dma0ErrorStatus || data->dma0FirstErrorStatus || + data->dma0ErrorLog0 || data->dma0ErrorLog1) + pr_info(" InAErr: %016llx %016llx %016llx %016llx\n", + data->dma0ErrorStatus, data->dma0FirstErrorStatus, + data->dma0ErrorLog0, data->dma0ErrorLog1); + if (data->dma1ErrorStatus || data->dma1FirstErrorStatus || + data->dma1ErrorLog0 || data->dma1ErrorLog1) + pr_info(" InBErr: %016llx %016llx %016llx %016llx\n", + data->dma1ErrorStatus, data->dma1FirstErrorStatus, + data->dma1ErrorLog0, data->dma1ErrorLog1); for (i = 0; i < OPAL_PHB3_NUM_PEST_REGS; i++) { if ((data->pestA[i] >> 63) == 0 && (data->pestB[i] >> 63) == 0) continue; - pr_info(" PE[%3d] PESTA: %016llx\n", i, data->pestA[i]); - pr_info(" PESTB: %016llx\n", data->pestB[i]); + pr_info(" PE[%3d] A/B: %016llx %016llx\n", + i, data->pestA[i], data->pestB[i]); } } @@ -634,6 +664,16 @@ static void pnv_pci_dma_dev_setup(struct pci_dev *pdev) pnv_pci_dma_fallback_setup(hose, pdev); } +int pnv_pci_dma_set_mask(struct pci_dev *pdev, u64 dma_mask) +{ + struct pci_controller *hose = pci_bus_to_host(pdev->bus); + struct pnv_phb *phb = hose->private_data; + + if (phb && phb->dma_set_mask) + return phb->dma_set_mask(phb, pdev, dma_mask); + return __dma_set_mask(&pdev->dev, dma_mask); +} + void pnv_pci_shutdown(void) { struct pci_controller *hose; diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h index 13f1942a9a5f..cde169442775 100644 --- a/arch/powerpc/platforms/powernv/pci.h +++ b/arch/powerpc/platforms/powernv/pci.h @@ -54,7 +54,9 @@ struct pnv_ioda_pe { struct iommu_table tce32_table; phys_addr_t tce_inval_reg_phys; - /* XXX TODO: Add support for additional 64-bit iommus */ + /* 64-bit TCE bypass region */ + bool tce_bypass_enabled; + uint64_t tce_bypass_base; /* MSIs. MVE index is identical for for 32 and 64 bit MSI * and -1 if not supported. (It's actually identical to the @@ -113,6 +115,8 @@ struct pnv_phb { unsigned int hwirq, unsigned int virq, unsigned int is_64, struct msi_msg *msg); void (*dma_dev_setup)(struct pnv_phb *phb, struct pci_dev *pdev); + int (*dma_set_mask)(struct pnv_phb *phb, struct pci_dev *pdev, + u64 dma_mask); void (*fixup_phb)(struct pci_controller *hose); u32 (*bdfn_to_pe)(struct pnv_phb *phb, struct pci_bus *bus, u32 devfn); void (*shutdown)(struct pnv_phb *phb); diff --git a/arch/powerpc/platforms/powernv/powernv.h b/arch/powerpc/platforms/powernv/powernv.h index de6819be1f95..0051e108ef0f 100644 --- a/arch/powerpc/platforms/powernv/powernv.h +++ b/arch/powerpc/platforms/powernv/powernv.h @@ -7,12 +7,20 @@ extern void pnv_smp_init(void); static inline void pnv_smp_init(void) { } #endif +struct pci_dev; + #ifdef CONFIG_PCI extern void pnv_pci_init(void); extern void pnv_pci_shutdown(void); +extern int pnv_pci_dma_set_mask(struct pci_dev *pdev, u64 dma_mask); #else static inline void pnv_pci_init(void) { } static inline void pnv_pci_shutdown(void) { } + +static inline int pnv_pci_dma_set_mask(struct pci_dev *pdev, u64 dma_mask) +{ + return -ENODEV; +} #endif extern void pnv_lpc_init(void); diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c index 21166f65c97c..110f4fbd319f 100644 --- a/arch/powerpc/platforms/powernv/setup.c +++ b/arch/powerpc/platforms/powernv/setup.c @@ -27,6 +27,7 @@ #include <linux/interrupt.h> #include <linux/bug.h> #include <linux/cpuidle.h> +#include <linux/pci.h> #include <asm/machdep.h> #include <asm/firmware.h> @@ -141,6 +142,13 @@ static void pnv_progress(char *s, unsigned short hex) { } +static int pnv_dma_set_mask(struct device *dev, u64 dma_mask) +{ + if (dev_is_pci(dev)) + return pnv_pci_dma_set_mask(to_pci_dev(dev), dma_mask); + return __dma_set_mask(dev, dma_mask); +} + static void pnv_shutdown(void) { /* Let the PCI code clear up IODA tables */ @@ -238,6 +246,7 @@ define_machine(powernv) { .machine_shutdown = pnv_shutdown, .power_save = powernv_idle, .calibrate_decr = generic_calibrate_decr, + .dma_set_mask = pnv_dma_set_mask, #ifdef CONFIG_KEXEC .kexec_cpu_down = pnv_kexec_cpu_down, #endif diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig index 37300f6ee244..80b1d57c306a 100644 --- a/arch/powerpc/platforms/pseries/Kconfig +++ b/arch/powerpc/platforms/pseries/Kconfig @@ -20,6 +20,7 @@ config PPC_PSERIES select PPC_DOORBELL select HAVE_CONTEXT_TRACKING select HOTPLUG_CPU if SMP + select ARCH_RANDOM default y config PPC_SPLPAR diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c index 9ef3cc8ebc11..8a8f0472d98f 100644 --- a/arch/powerpc/platforms/pseries/eeh_pseries.c +++ b/arch/powerpc/platforms/pseries/eeh_pseries.c @@ -265,7 +265,7 @@ static void *pseries_eeh_of_probe(struct device_node *dn, void *flag) enable = 1; if (enable) { - eeh_subsystem_enabled = 1; + eeh_set_enable(true); eeh_add_to_parent_pe(edev); pr_debug("%s: EEH enabled on %s PHB#%d-PE#%x, config addr#%x\n", diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c index 82789e79e539..0ea99e3d4815 100644 --- a/arch/powerpc/platforms/pseries/hotplug-cpu.c +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c @@ -35,12 +35,7 @@ #include "offline_states.h" /* This version can't take the spinlock, because it never returns */ -static struct rtas_args rtas_stop_self_args = { - .token = RTAS_UNKNOWN_SERVICE, - .nargs = 0, - .nret = 1, - .rets = &rtas_stop_self_args.args[0], -}; +static int rtas_stop_self_token = RTAS_UNKNOWN_SERVICE; static DEFINE_PER_CPU(enum cpu_state_vals, preferred_offline_state) = CPU_STATE_OFFLINE; @@ -93,15 +88,20 @@ void set_default_offline_state(int cpu) static void rtas_stop_self(void) { - struct rtas_args *args = &rtas_stop_self_args; + struct rtas_args args = { + .token = cpu_to_be32(rtas_stop_self_token), + .nargs = 0, + .nret = 1, + .rets = &args.args[0], + }; local_irq_disable(); - BUG_ON(args->token == RTAS_UNKNOWN_SERVICE); + BUG_ON(rtas_stop_self_token == RTAS_UNKNOWN_SERVICE); printk("cpu %u (hwid %u) Ready to die...\n", smp_processor_id(), hard_smp_processor_id()); - enter_rtas(__pa(args)); + enter_rtas(__pa(&args)); panic("Alas, I survived.\n"); } @@ -392,10 +392,10 @@ static int __init pseries_cpu_hotplug_init(void) } } - rtas_stop_self_args.token = rtas_token("stop-self"); + rtas_stop_self_token = rtas_token("stop-self"); qcss_tok = rtas_token("query-cpu-stopped-state"); - if (rtas_stop_self_args.token == RTAS_UNKNOWN_SERVICE || + if (rtas_stop_self_token == RTAS_UNKNOWN_SERVICE || qcss_tok == RTAS_UNKNOWN_SERVICE) { printk(KERN_INFO "CPU Hotplug not supported by firmware " "- disabling.\n"); diff --git a/arch/powerpc/platforms/pseries/pci.c b/arch/powerpc/platforms/pseries/pci.c index 70670a2d9cf2..c413ec158ff5 100644 --- a/arch/powerpc/platforms/pseries/pci.c +++ b/arch/powerpc/platforms/pseries/pci.c @@ -113,7 +113,8 @@ int pseries_root_bridge_prepare(struct pci_host_bridge *bridge) { struct device_node *dn, *pdn; struct pci_bus *bus; - const __be32 *pcie_link_speed_stats; + u32 pcie_link_speed_stats[2]; + int rc; bus = bridge->bus; @@ -122,38 +123,45 @@ int pseries_root_bridge_prepare(struct pci_host_bridge *bridge) return 0; for (pdn = dn; pdn != NULL; pdn = of_get_next_parent(pdn)) { - pcie_link_speed_stats = of_get_property(pdn, - "ibm,pcie-link-speed-stats", NULL); - if (pcie_link_speed_stats) + rc = of_property_read_u32_array(pdn, + "ibm,pcie-link-speed-stats", + &pcie_link_speed_stats[0], 2); + if (!rc) break; } of_node_put(pdn); - if (!pcie_link_speed_stats) { + if (rc) { pr_err("no ibm,pcie-link-speed-stats property\n"); return 0; } - switch (be32_to_cpup(pcie_link_speed_stats)) { + switch (pcie_link_speed_stats[0]) { case 0x01: bus->max_bus_speed = PCIE_SPEED_2_5GT; break; case 0x02: bus->max_bus_speed = PCIE_SPEED_5_0GT; break; + case 0x04: + bus->max_bus_speed = PCIE_SPEED_8_0GT; + break; default: bus->max_bus_speed = PCI_SPEED_UNKNOWN; break; } - switch (be32_to_cpup(pcie_link_speed_stats)) { + switch (pcie_link_speed_stats[1]) { case 0x01: bus->cur_bus_speed = PCIE_SPEED_2_5GT; break; case 0x02: bus->cur_bus_speed = PCIE_SPEED_5_0GT; break; + case 0x04: + bus->cur_bus_speed = PCIE_SPEED_8_0GT; + break; default: bus->cur_bus_speed = PCI_SPEED_UNKNOWN; break; diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 8e639d7cbda7..972df0ffd4dc 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -430,8 +430,7 @@ static void pSeries_machine_kexec(struct kimage *image) { long rc; - if (firmware_has_feature(FW_FEATURE_SET_MODE) && - (image->type != KEXEC_TYPE_CRASH)) { + if (firmware_has_feature(FW_FEATURE_SET_MODE)) { rc = pSeries_disable_reloc_on_exc(); if (rc != H_SUCCESS) pr_warning("Warning: Failed to disable relocation on " diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c index 0e166ed4cd16..8209744b2829 100644 --- a/arch/powerpc/sysdev/mpic.c +++ b/arch/powerpc/sysdev/mpic.c @@ -886,25 +886,25 @@ int mpic_set_irq_type(struct irq_data *d, unsigned int flow_type) /* Default: read HW settings */ if (flow_type == IRQ_TYPE_DEFAULT) { - switch(vold & (MPIC_INFO(VECPRI_POLARITY_MASK) | - MPIC_INFO(VECPRI_SENSE_MASK))) { - case MPIC_INFO(VECPRI_SENSE_EDGE) | - MPIC_INFO(VECPRI_POLARITY_POSITIVE): - flow_type = IRQ_TYPE_EDGE_RISING; - break; - case MPIC_INFO(VECPRI_SENSE_EDGE) | - MPIC_INFO(VECPRI_POLARITY_NEGATIVE): - flow_type = IRQ_TYPE_EDGE_FALLING; - break; - case MPIC_INFO(VECPRI_SENSE_LEVEL) | - MPIC_INFO(VECPRI_POLARITY_POSITIVE): - flow_type = IRQ_TYPE_LEVEL_HIGH; - break; - case MPIC_INFO(VECPRI_SENSE_LEVEL) | - MPIC_INFO(VECPRI_POLARITY_NEGATIVE): - flow_type = IRQ_TYPE_LEVEL_LOW; - break; - } + int vold_ps; + + vold_ps = vold & (MPIC_INFO(VECPRI_POLARITY_MASK) | + MPIC_INFO(VECPRI_SENSE_MASK)); + + if (vold_ps == (MPIC_INFO(VECPRI_SENSE_EDGE) | + MPIC_INFO(VECPRI_POLARITY_POSITIVE))) + flow_type = IRQ_TYPE_EDGE_RISING; + else if (vold_ps == (MPIC_INFO(VECPRI_SENSE_EDGE) | + MPIC_INFO(VECPRI_POLARITY_NEGATIVE))) + flow_type = IRQ_TYPE_EDGE_FALLING; + else if (vold_ps == (MPIC_INFO(VECPRI_SENSE_LEVEL) | + MPIC_INFO(VECPRI_POLARITY_POSITIVE))) + flow_type = IRQ_TYPE_LEVEL_HIGH; + else if (vold_ps == (MPIC_INFO(VECPRI_SENSE_LEVEL) | + MPIC_INFO(VECPRI_POLARITY_NEGATIVE))) + flow_type = IRQ_TYPE_LEVEL_LOW; + else + WARN_ONCE(1, "mpic: unknown IRQ type %d\n", vold); } /* Apply to irq desc */ diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index a90731b3d44a..b07909850f77 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -309,16 +309,23 @@ static void get_output_lock(void) if (xmon_speaker == me) return; + for (;;) { - if (xmon_speaker == 0) { - last_speaker = cmpxchg(&xmon_speaker, 0, me); - if (last_speaker == 0) - return; - } - timeout = 10000000; + last_speaker = cmpxchg(&xmon_speaker, 0, me); + if (last_speaker == 0) + return; + + /* + * Wait a full second for the lock, we might be on a slow + * console, but check every 100us. + */ + timeout = 10000; while (xmon_speaker == last_speaker) { - if (--timeout > 0) + if (--timeout > 0) { + udelay(100); continue; + } + /* hostile takeover */ prev = cmpxchg(&xmon_speaker, last_speaker, me); if (prev == last_speaker) @@ -397,7 +404,6 @@ static int xmon_core(struct pt_regs *regs, int fromipi) } xmon_fault_jmp[cpu] = recurse_jmp; - cpumask_set_cpu(cpu, &cpus_in_xmon); bp = NULL; if ((regs->msr & (MSR_IR|MSR_PR|MSR_64BIT)) == (MSR_IR|MSR_64BIT)) @@ -419,6 +425,8 @@ static int xmon_core(struct pt_regs *regs, int fromipi) release_output_lock(); } + cpumask_set_cpu(cpu, &cpus_in_xmon); + waiting: secondary = 1; while (secondary && !xmon_gate) { diff --git a/arch/s390/appldata/appldata_base.c b/arch/s390/appldata/appldata_base.c index 4c4a1cef5208..47c8630c93cd 100644 --- a/arch/s390/appldata/appldata_base.c +++ b/arch/s390/appldata/appldata_base.c @@ -529,6 +529,7 @@ static int __init appldata_init(void) { int rc; + init_virt_timer(&appldata_timer); appldata_timer.function = appldata_timer_function; appldata_timer.data = (unsigned long) &appldata_work; diff --git a/arch/s390/kernel/compat_wrapper.S b/arch/s390/kernel/compat_wrapper.S index 59c8efce1b99..0248949a756d 100644 --- a/arch/s390/kernel/compat_wrapper.S +++ b/arch/s390/kernel/compat_wrapper.S @@ -1421,5 +1421,5 @@ ENTRY(sys_sched_setattr_wrapper) ENTRY(sys_sched_getattr_wrapper) lgfr %r2,%r2 # pid_t llgtr %r3,%r3 # const char __user * - llgfr %r3,%r3 # unsigned int + llgfr %r4,%r4 # unsigned int jg sys_sched_getattr diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S index b9e25ae2579c..d7c00507568a 100644 --- a/arch/s390/kernel/head64.S +++ b/arch/s390/kernel/head64.S @@ -59,7 +59,7 @@ ENTRY(startup_continue) .quad 0 # cr12: tracing off .quad 0 # cr13: home space segment table .quad 0xc0000000 # cr14: machine check handling off - .quad 0 # cr15: linkage stack operations + .quad .Llinkage_stack # cr15: linkage stack operations .Lpcmsk:.quad 0x0000000180000000 .L4malign:.quad 0xffffffffffc00000 .Lscan2g:.quad 0x80000000 + 0x20000 - 8 # 2GB + 128K - 8 @@ -67,12 +67,15 @@ ENTRY(startup_continue) .Lparmaddr: .quad PARMAREA .align 64 -.Lduct: .long 0,0,0,0,.Lduald,0,0,0 +.Lduct: .long 0,.Laste,.Laste,0,.Lduald,0,0,0 .long 0,0,0,0,0,0,0,0 +.Laste: .quad 0,0xffffffffffffffff,0,0,0,0,0,0 .align 128 .Lduald:.rept 8 .long 0x80000000,0,0,0 # invalid access-list entries .endr +.Llinkage_stack: + .long 0,0,0x89000000,0,0,0,0x8a000000,0 ENTRY(_ehead) diff --git a/arch/s390/mm/page-states.c b/arch/s390/mm/page-states.c index a90d45e9dfb0..27c50f4d90cb 100644 --- a/arch/s390/mm/page-states.c +++ b/arch/s390/mm/page-states.c @@ -12,6 +12,8 @@ #include <linux/mm.h> #include <linux/gfp.h> #include <linux/init.h> +#include <asm/setup.h> +#include <asm/ipl.h> #define ESSA_SET_STABLE 1 #define ESSA_SET_UNUSED 2 @@ -41,6 +43,14 @@ void __init cmma_init(void) if (!cmma_flag) return; + /* + * Disable CMM for dump, otherwise the tprot based memory + * detection can fail because of unstable pages. + */ + if (OLDMEM_BASE || ipl_info.type == IPL_TYPE_FCP_DUMP) { + cmma_flag = 0; + return; + } asm volatile( " .insn rrf,0xb9ab0000,%1,%1,0,0\n" "0: la %0,0\n" diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c index 60c11a629d96..f91c03119804 100644 --- a/arch/s390/pci/pci_dma.c +++ b/arch/s390/pci/pci_dma.c @@ -206,11 +206,13 @@ static void dma_cleanup_tables(struct zpci_dev *zdev) zdev->dma_table = NULL; } -static unsigned long __dma_alloc_iommu(struct zpci_dev *zdev, unsigned long start, - int size) +static unsigned long __dma_alloc_iommu(struct zpci_dev *zdev, + unsigned long start, int size) { - unsigned long boundary_size = 0x1000000; + unsigned long boundary_size; + boundary_size = ALIGN(dma_get_seg_boundary(&zdev->pdev->dev) + 1, + PAGE_SIZE) >> PAGE_SHIFT; return iommu_area_alloc(zdev->iommu_bitmap, zdev->iommu_pages, start, size, 0, boundary_size, 0); } diff --git a/arch/sh/include/cpu-sh2/cpu/cache.h b/arch/sh/include/cpu-sh2/cpu/cache.h index 673515bc4135..aa1b2b9088a7 100644 --- a/arch/sh/include/cpu-sh2/cpu/cache.h +++ b/arch/sh/include/cpu-sh2/cpu/cache.h @@ -18,7 +18,7 @@ #define SH_CACHE_ASSOC 8 #if defined(CONFIG_CPU_SUBTYPE_SH7619) -#define CCR 0xffffffec +#define SH_CCR 0xffffffec #define CCR_CACHE_CE 0x01 /* Cache enable */ #define CCR_CACHE_WT 0x02 /* CCR[bit1=1,bit2=1] */ diff --git a/arch/sh/include/cpu-sh2a/cpu/cache.h b/arch/sh/include/cpu-sh2a/cpu/cache.h index defb0baa5a06..b27ce92cb600 100644 --- a/arch/sh/include/cpu-sh2a/cpu/cache.h +++ b/arch/sh/include/cpu-sh2a/cpu/cache.h @@ -17,8 +17,8 @@ #define SH_CACHE_COMBINED 4 #define SH_CACHE_ASSOC 8 -#define CCR 0xfffc1000 /* CCR1 */ -#define CCR2 0xfffc1004 +#define SH_CCR 0xfffc1000 /* CCR1 */ +#define SH_CCR2 0xfffc1004 /* * Most of the SH-2A CCR1 definitions resemble the SH-4 ones. All others not diff --git a/arch/sh/include/cpu-sh3/cpu/cache.h b/arch/sh/include/cpu-sh3/cpu/cache.h index bee2d81c56bf..29700fd88c75 100644 --- a/arch/sh/include/cpu-sh3/cpu/cache.h +++ b/arch/sh/include/cpu-sh3/cpu/cache.h @@ -17,7 +17,7 @@ #define SH_CACHE_COMBINED 4 #define SH_CACHE_ASSOC 8 -#define CCR 0xffffffec /* Address of Cache Control Register */ +#define SH_CCR 0xffffffec /* Address of Cache Control Register */ #define CCR_CACHE_CE 0x01 /* Cache Enable */ #define CCR_CACHE_WT 0x02 /* Write-Through (for P0,U0,P3) (else writeback) */ diff --git a/arch/sh/include/cpu-sh4/cpu/cache.h b/arch/sh/include/cpu-sh4/cpu/cache.h index 7bfb9e8b069c..92c4cd119b66 100644 --- a/arch/sh/include/cpu-sh4/cpu/cache.h +++ b/arch/sh/include/cpu-sh4/cpu/cache.h @@ -17,7 +17,7 @@ #define SH_CACHE_COMBINED 4 #define SH_CACHE_ASSOC 8 -#define CCR 0xff00001c /* Address of Cache Control Register */ +#define SH_CCR 0xff00001c /* Address of Cache Control Register */ #define CCR_CACHE_OCE 0x0001 /* Operand Cache Enable */ #define CCR_CACHE_WT 0x0002 /* Write-Through (for P0,U0,P3) (else writeback)*/ #define CCR_CACHE_CB 0x0004 /* Copy-Back (for P1) (else writethrough) */ diff --git a/arch/sh/kernel/cpu/init.c b/arch/sh/kernel/cpu/init.c index ecf83cd158dc..0d7360d549c1 100644 --- a/arch/sh/kernel/cpu/init.c +++ b/arch/sh/kernel/cpu/init.c @@ -112,7 +112,7 @@ static void cache_init(void) unsigned long ccr, flags; jump_to_uncached(); - ccr = __raw_readl(CCR); + ccr = __raw_readl(SH_CCR); /* * At this point we don't know whether the cache is enabled or not - a @@ -189,7 +189,7 @@ static void cache_init(void) l2_cache_init(); - __raw_writel(flags, CCR); + __raw_writel(flags, SH_CCR); back_to_cached(); } #else diff --git a/arch/sh/mm/cache-debugfs.c b/arch/sh/mm/cache-debugfs.c index 115725198038..777e50f33c00 100644 --- a/arch/sh/mm/cache-debugfs.c +++ b/arch/sh/mm/cache-debugfs.c @@ -36,7 +36,7 @@ static int cache_seq_show(struct seq_file *file, void *iter) */ jump_to_uncached(); - ccr = __raw_readl(CCR); + ccr = __raw_readl(SH_CCR); if ((ccr & CCR_CACHE_ENABLE) == 0) { back_to_cached(); diff --git a/arch/sh/mm/cache-sh2.c b/arch/sh/mm/cache-sh2.c index defcf719f2e8..a74259f2f981 100644 --- a/arch/sh/mm/cache-sh2.c +++ b/arch/sh/mm/cache-sh2.c @@ -63,9 +63,9 @@ static void sh2__flush_invalidate_region(void *start, int size) local_irq_save(flags); jump_to_uncached(); - ccr = __raw_readl(CCR); + ccr = __raw_readl(SH_CCR); ccr |= CCR_CACHE_INVALIDATE; - __raw_writel(ccr, CCR); + __raw_writel(ccr, SH_CCR); back_to_cached(); local_irq_restore(flags); diff --git a/arch/sh/mm/cache-sh2a.c b/arch/sh/mm/cache-sh2a.c index 949e2d3138a0..ee87d081259b 100644 --- a/arch/sh/mm/cache-sh2a.c +++ b/arch/sh/mm/cache-sh2a.c @@ -134,7 +134,8 @@ static void sh2a__flush_invalidate_region(void *start, int size) /* If there are too many pages then just blow the cache */ if (((end - begin) >> PAGE_SHIFT) >= MAX_OCACHE_PAGES) { - __raw_writel(__raw_readl(CCR) | CCR_OCACHE_INVALIDATE, CCR); + __raw_writel(__raw_readl(SH_CCR) | CCR_OCACHE_INVALIDATE, + SH_CCR); } else { for (v = begin; v < end; v += L1_CACHE_BYTES) sh2a_invalidate_line(CACHE_OC_ADDRESS_ARRAY, v); @@ -167,7 +168,8 @@ static void sh2a_flush_icache_range(void *args) /* I-Cache invalidate */ /* If there are too many pages then just blow the cache */ if (((end - start) >> PAGE_SHIFT) >= MAX_ICACHE_PAGES) { - __raw_writel(__raw_readl(CCR) | CCR_ICACHE_INVALIDATE, CCR); + __raw_writel(__raw_readl(SH_CCR) | CCR_ICACHE_INVALIDATE, + SH_CCR); } else { for (v = start; v < end; v += L1_CACHE_BYTES) sh2a_invalidate_line(CACHE_IC_ADDRESS_ARRAY, v); diff --git a/arch/sh/mm/cache-sh4.c b/arch/sh/mm/cache-sh4.c index 0e529285b28d..51d8f7f31d1d 100644 --- a/arch/sh/mm/cache-sh4.c +++ b/arch/sh/mm/cache-sh4.c @@ -133,9 +133,9 @@ static void flush_icache_all(void) jump_to_uncached(); /* Flush I-cache */ - ccr = __raw_readl(CCR); + ccr = __raw_readl(SH_CCR); ccr |= CCR_CACHE_ICI; - __raw_writel(ccr, CCR); + __raw_writel(ccr, SH_CCR); /* * back_to_cached() will take care of the barrier for us, don't add diff --git a/arch/sh/mm/cache-shx3.c b/arch/sh/mm/cache-shx3.c index c0adbee97b5f..24c58b7dc022 100644 --- a/arch/sh/mm/cache-shx3.c +++ b/arch/sh/mm/cache-shx3.c @@ -19,7 +19,7 @@ void __init shx3_cache_init(void) { unsigned int ccr; - ccr = __raw_readl(CCR); + ccr = __raw_readl(SH_CCR); /* * If we've got cache aliases, resolve them in hardware. @@ -40,5 +40,5 @@ void __init shx3_cache_init(void) ccr |= CCR_CACHE_IBE; #endif - writel_uncached(ccr, CCR); + writel_uncached(ccr, SH_CCR); } diff --git a/arch/sh/mm/cache.c b/arch/sh/mm/cache.c index 616966a96cba..097c2cdd117f 100644 --- a/arch/sh/mm/cache.c +++ b/arch/sh/mm/cache.c @@ -285,8 +285,8 @@ void __init cpu_cache_init(void) { unsigned int cache_disabled = 0; -#ifdef CCR - cache_disabled = !(__raw_readl(CCR) & CCR_CACHE_ENABLE); +#ifdef SH_CCR + cache_disabled = !(__raw_readl(SH_CCR) & CCR_CACHE_ENABLE); #endif compute_alias(&boot_cpu_data.icache); diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index c51efdcd07a2..7d8b7e94b93b 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -27,7 +27,7 @@ config SPARC select RTC_DRV_M48T59 select HAVE_DMA_ATTRS select HAVE_DMA_API_DEBUG - select HAVE_ARCH_JUMP_LABEL + select HAVE_ARCH_JUMP_LABEL if SPARC64 select GENERIC_IRQ_SHOW select ARCH_WANT_IPC_PARSE_VERSION select GENERIC_PCI_IOMAP diff --git a/arch/sparc/mm/srmmu.c b/arch/sparc/mm/srmmu.c index 869023abe5a4..cfbe53c17b0d 100644 --- a/arch/sparc/mm/srmmu.c +++ b/arch/sparc/mm/srmmu.c @@ -14,6 +14,7 @@ #include <linux/pagemap.h> #include <linux/vmalloc.h> #include <linux/kdebug.h> +#include <linux/export.h> #include <linux/kernel.h> #include <linux/init.h> #include <linux/log2.h> @@ -62,6 +63,7 @@ extern unsigned long last_valid_pfn; static pgd_t *srmmu_swapper_pg_dir; const struct sparc32_cachetlb_ops *sparc32_cachetlb_ops; +EXPORT_SYMBOL(sparc32_cachetlb_ops); #ifdef CONFIG_SMP const struct sparc32_cachetlb_ops *local_ops; diff --git a/arch/x86/boot/compressed/aslr.c b/arch/x86/boot/compressed/aslr.c index 90a21f430117..4dbf967da50d 100644 --- a/arch/x86/boot/compressed/aslr.c +++ b/arch/x86/boot/compressed/aslr.c @@ -111,7 +111,7 @@ struct mem_vector { }; #define MEM_AVOID_MAX 5 -struct mem_vector mem_avoid[MEM_AVOID_MAX]; +static struct mem_vector mem_avoid[MEM_AVOID_MAX]; static bool mem_contains(struct mem_vector *region, struct mem_vector *item) { @@ -180,7 +180,7 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size, } /* Does this memory vector overlap a known avoided area? */ -bool mem_avoid_overlap(struct mem_vector *img) +static bool mem_avoid_overlap(struct mem_vector *img) { int i; @@ -192,8 +192,9 @@ bool mem_avoid_overlap(struct mem_vector *img) return false; } -unsigned long slots[CONFIG_RANDOMIZE_BASE_MAX_OFFSET / CONFIG_PHYSICAL_ALIGN]; -unsigned long slot_max = 0; +static unsigned long slots[CONFIG_RANDOMIZE_BASE_MAX_OFFSET / + CONFIG_PHYSICAL_ALIGN]; +static unsigned long slot_max; static void slots_append(unsigned long addr) { diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 3b978c472d08..3d6b9f81cc68 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -132,6 +132,8 @@ extern void __init efi_map_region_fixed(efi_memory_desc_t *md); extern void efi_sync_low_kernel_mappings(void); extern void efi_setup_page_tables(void); extern void __init old_map_region(efi_memory_desc_t *md); +extern void __init runtime_code_page_mkexec(void); +extern void __init efi_runtime_mkexec(void); struct efi_setup_data { u64 fw_vendor; diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index bbc8b12fa443..5ad38ad07890 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -445,10 +445,20 @@ static inline int pte_same(pte_t a, pte_t b) return a.pte == b.pte; } +static inline int pteval_present(pteval_t pteval) +{ + /* + * Yes Linus, _PAGE_PROTNONE == _PAGE_NUMA. Expressing it this + * way clearly states that the intent is that protnone and numa + * hinting ptes are considered present for the purposes of + * pagetable operations like zapping, protection changes, gup etc. + */ + return pteval & (_PAGE_PRESENT | _PAGE_PROTNONE | _PAGE_NUMA); +} + static inline int pte_present(pte_t a) { - return pte_flags(a) & (_PAGE_PRESENT | _PAGE_PROTNONE | - _PAGE_NUMA); + return pteval_present(pte_flags(a)); } #define pte_accessible pte_accessible diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h index 57ae63cd6ee2..94605c0e9cee 100644 --- a/arch/x86/include/asm/tsc.h +++ b/arch/x86/include/asm/tsc.h @@ -66,6 +66,6 @@ extern void tsc_save_sched_clock_state(void); extern void tsc_restore_sched_clock_state(void); /* MSR based TSC calibration for Intel Atom SoC platforms */ -int try_msr_calibrate_tsc(unsigned long *fast_calibrate); +unsigned long try_msr_calibrate_tsc(void); #endif /* _ASM_X86_TSC_H */ diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 24b6fd10625a..8e28bf2fc3ef 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -284,8 +284,13 @@ static __always_inline void setup_smap(struct cpuinfo_x86 *c) raw_local_save_flags(eflags); BUG_ON(eflags & X86_EFLAGS_AC); - if (cpu_has(c, X86_FEATURE_SMAP)) + if (cpu_has(c, X86_FEATURE_SMAP)) { +#ifdef CONFIG_X86_SMAP set_in_cr4(X86_CR4_SMAP); +#else + clear_in_cr4(X86_CR4_SMAP); +#endif + } } /* diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index b88645191fe5..79f9f848bee4 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -1192,6 +1192,9 @@ static void x86_pmu_del(struct perf_event *event, int flags) for (i = 0; i < cpuc->n_events; i++) { if (event == cpuc->event_list[i]) { + if (i >= cpuc->n_events - cpuc->n_added) + --cpuc->n_added; + if (x86_pmu.put_event_constraints) x86_pmu.put_event_constraints(cpuc, event); @@ -1521,6 +1524,8 @@ static int __init init_hw_perf_events(void) pr_cont("%s PMU driver.\n", x86_pmu.name); + x86_pmu.attr_rdpmc = 1; /* enable userspace RDPMC usage by default */ + for (quirk = x86_pmu.quirks; quirk; quirk = quirk->next) quirk->func(); @@ -1534,7 +1539,6 @@ static int __init init_hw_perf_events(void) __EVENT_CONSTRAINT(0, (1ULL << x86_pmu.num_counters) - 1, 0, x86_pmu.num_counters, 0, 0); - x86_pmu.attr_rdpmc = 1; /* enable userspace RDPMC usage by default */ x86_pmu_format_group.attrs = x86_pmu.format_attrs; if (x86_pmu.event_attrs) @@ -1820,9 +1824,12 @@ static ssize_t set_attr_rdpmc(struct device *cdev, if (ret) return ret; + if (x86_pmu.attr_rdpmc_broken) + return -ENOTSUPP; + if (!!val != !!x86_pmu.attr_rdpmc) { x86_pmu.attr_rdpmc = !!val; - smp_call_function(change_rdpmc, (void *)val, 1); + on_each_cpu(change_rdpmc, (void *)val, 1); } return count; diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index c1a861829d81..4972c244d0bc 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -409,6 +409,7 @@ struct x86_pmu { /* * sysfs attrs */ + int attr_rdpmc_broken; int attr_rdpmc; struct attribute **format_attrs; struct attribute **event_attrs; diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 0fa4f242f050..aa333d966886 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -1361,10 +1361,8 @@ static int intel_pmu_handle_irq(struct pt_regs *regs) intel_pmu_disable_all(); handled = intel_pmu_drain_bts_buffer(); status = intel_pmu_get_status(); - if (!status) { - intel_pmu_enable_all(0); - return handled; - } + if (!status) + goto done; loops = 0; again: @@ -2310,10 +2308,7 @@ __init int intel_pmu_init(void) if (version > 1) x86_pmu.num_counters_fixed = max((int)edx.split.num_counters_fixed, 3); - /* - * v2 and above have a perf capabilities MSR - */ - if (version > 1) { + if (boot_cpu_has(X86_FEATURE_PDCM)) { u64 capabilities; rdmsrl(MSR_IA32_PERF_CAPABILITIES, capabilities); diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c index 29c248799ced..c88f7f4b03ee 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c @@ -501,8 +501,11 @@ static struct extra_reg snbep_uncore_cbox_extra_regs[] = { SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN, SNBEP_CBO_PMON_CTL_TID_EN, 0x1), SNBEP_CBO_EVENT_EXTRA_REG(0x0334, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x4334, 0xffff, 0x6), SNBEP_CBO_EVENT_EXTRA_REG(0x0534, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x4534, 0xffff, 0x6), SNBEP_CBO_EVENT_EXTRA_REG(0x0934, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x4934, 0xffff, 0x6), SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0x6), SNBEP_CBO_EVENT_EXTRA_REG(0x0135, 0xffff, 0x8), SNBEP_CBO_EVENT_EXTRA_REG(0x0335, 0xffff, 0x8), @@ -1178,10 +1181,15 @@ static struct extra_reg ivt_uncore_cbox_extra_regs[] = { SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN, SNBEP_CBO_PMON_CTL_TID_EN, 0x1), SNBEP_CBO_EVENT_EXTRA_REG(0x1031, 0x10ff, 0x2), + SNBEP_CBO_EVENT_EXTRA_REG(0x1134, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0xc), + SNBEP_CBO_EVENT_EXTRA_REG(0x5134, 0xffff, 0xc), SNBEP_CBO_EVENT_EXTRA_REG(0x0334, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x4334, 0xffff, 0xc), SNBEP_CBO_EVENT_EXTRA_REG(0x0534, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x4534, 0xffff, 0xc), SNBEP_CBO_EVENT_EXTRA_REG(0x0934, 0xffff, 0x4), - SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0xc), + SNBEP_CBO_EVENT_EXTRA_REG(0x4934, 0xffff, 0xc), SNBEP_CBO_EVENT_EXTRA_REG(0x0135, 0xffff, 0x10), SNBEP_CBO_EVENT_EXTRA_REG(0x0335, 0xffff, 0x10), SNBEP_CBO_EVENT_EXTRA_REG(0x2135, 0xffff, 0x10), diff --git a/arch/x86/kernel/cpu/perf_event_p6.c b/arch/x86/kernel/cpu/perf_event_p6.c index b1e2fe115323..7c1a0c07b607 100644 --- a/arch/x86/kernel/cpu/perf_event_p6.c +++ b/arch/x86/kernel/cpu/perf_event_p6.c @@ -231,31 +231,49 @@ static __initconst const struct x86_pmu p6_pmu = { }; +static __init void p6_pmu_rdpmc_quirk(void) +{ + if (boot_cpu_data.x86_mask < 9) { + /* + * PPro erratum 26; fixed in stepping 9 and above. + */ + pr_warn("Userspace RDPMC support disabled due to a CPU erratum\n"); + x86_pmu.attr_rdpmc_broken = 1; + x86_pmu.attr_rdpmc = 0; + } +} + __init int p6_pmu_init(void) { + x86_pmu = p6_pmu; + switch (boot_cpu_data.x86_model) { - case 1: - case 3: /* Pentium Pro */ - case 5: - case 6: /* Pentium II */ - case 7: - case 8: - case 11: /* Pentium III */ - case 9: - case 13: - /* Pentium M */ + case 1: /* Pentium Pro */ + x86_add_quirk(p6_pmu_rdpmc_quirk); + break; + + case 3: /* Pentium II - Klamath */ + case 5: /* Pentium II - Deschutes */ + case 6: /* Pentium II - Mendocino */ break; + + case 7: /* Pentium III - Katmai */ + case 8: /* Pentium III - Coppermine */ + case 10: /* Pentium III Xeon */ + case 11: /* Pentium III - Tualatin */ + break; + + case 9: /* Pentium M - Banias */ + case 13: /* Pentium M - Dothan */ + break; + default: - pr_cont("unsupported p6 CPU model %d ", - boot_cpu_data.x86_model); + pr_cont("unsupported p6 CPU model %d ", boot_cpu_data.x86_model); return -ENODEV; } - x86_pmu = p6_pmu; - memcpy(hw_cache_event_ids, p6_hw_cache_event_ids, sizeof(hw_cache_event_ids)); - return 0; } diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index d4bdd253fea7..e6253195a301 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -77,8 +77,7 @@ within(unsigned long addr, unsigned long start, unsigned long end) return addr >= start && addr < end; } -static int -do_ftrace_mod_code(unsigned long ip, const void *new_code) +static unsigned long text_ip_addr(unsigned long ip) { /* * On x86_64, kernel text mappings are mapped read-only with @@ -91,7 +90,7 @@ do_ftrace_mod_code(unsigned long ip, const void *new_code) if (within(ip, (unsigned long)_text, (unsigned long)_etext)) ip = (unsigned long)__va(__pa_symbol(ip)); - return probe_kernel_write((void *)ip, new_code, MCOUNT_INSN_SIZE); + return ip; } static const unsigned char *ftrace_nop_replace(void) @@ -123,8 +122,10 @@ ftrace_modify_code_direct(unsigned long ip, unsigned const char *old_code, if (memcmp(replaced, old_code, MCOUNT_INSN_SIZE) != 0) return -EINVAL; + ip = text_ip_addr(ip); + /* replace the text with the new text */ - if (do_ftrace_mod_code(ip, new_code)) + if (probe_kernel_write((void *)ip, new_code, MCOUNT_INSN_SIZE)) return -EPERM; sync_core(); @@ -221,37 +222,51 @@ int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, return -EINVAL; } -int ftrace_update_ftrace_func(ftrace_func_t func) +static unsigned long ftrace_update_func; + +static int update_ftrace_func(unsigned long ip, void *new) { - unsigned long ip = (unsigned long)(&ftrace_call); - unsigned char old[MCOUNT_INSN_SIZE], *new; + unsigned char old[MCOUNT_INSN_SIZE]; int ret; - memcpy(old, &ftrace_call, MCOUNT_INSN_SIZE); - new = ftrace_call_replace(ip, (unsigned long)func); + memcpy(old, (void *)ip, MCOUNT_INSN_SIZE); + + ftrace_update_func = ip; + /* Make sure the breakpoints see the ftrace_update_func update */ + smp_wmb(); /* See comment above by declaration of modifying_ftrace_code */ atomic_inc(&modifying_ftrace_code); ret = ftrace_modify_code(ip, old, new); + atomic_dec(&modifying_ftrace_code); + + return ret; +} + +int ftrace_update_ftrace_func(ftrace_func_t func) +{ + unsigned long ip = (unsigned long)(&ftrace_call); + unsigned char *new; + int ret; + + new = ftrace_call_replace(ip, (unsigned long)func); + ret = update_ftrace_func(ip, new); + /* Also update the regs callback function */ if (!ret) { ip = (unsigned long)(&ftrace_regs_call); - memcpy(old, &ftrace_regs_call, MCOUNT_INSN_SIZE); new = ftrace_call_replace(ip, (unsigned long)func); - ret = ftrace_modify_code(ip, old, new); + ret = update_ftrace_func(ip, new); } - atomic_dec(&modifying_ftrace_code); - return ret; } static int is_ftrace_caller(unsigned long ip) { - if (ip == (unsigned long)(&ftrace_call) || - ip == (unsigned long)(&ftrace_regs_call)) + if (ip == ftrace_update_func) return 1; return 0; @@ -677,45 +692,41 @@ int __init ftrace_dyn_arch_init(void *data) #ifdef CONFIG_DYNAMIC_FTRACE extern void ftrace_graph_call(void); -static int ftrace_mod_jmp(unsigned long ip, - int old_offset, int new_offset) +static unsigned char *ftrace_jmp_replace(unsigned long ip, unsigned long addr) { - unsigned char code[MCOUNT_INSN_SIZE]; + static union ftrace_code_union calc; - if (probe_kernel_read(code, (void *)ip, MCOUNT_INSN_SIZE)) - return -EFAULT; + /* Jmp not a call (ignore the .e8) */ + calc.e8 = 0xe9; + calc.offset = ftrace_calc_offset(ip + MCOUNT_INSN_SIZE, addr); - if (code[0] != 0xe9 || old_offset != *(int *)(&code[1])) - return -EINVAL; + /* + * ftrace external locks synchronize the access to the static variable. + */ + return calc.code; +} - *(int *)(&code[1]) = new_offset; +static int ftrace_mod_jmp(unsigned long ip, void *func) +{ + unsigned char *new; - if (do_ftrace_mod_code(ip, &code)) - return -EPERM; + new = ftrace_jmp_replace(ip, (unsigned long)func); - return 0; + return update_ftrace_func(ip, new); } int ftrace_enable_ftrace_graph_caller(void) { unsigned long ip = (unsigned long)(&ftrace_graph_call); - int old_offset, new_offset; - old_offset = (unsigned long)(&ftrace_stub) - (ip + MCOUNT_INSN_SIZE); - new_offset = (unsigned long)(&ftrace_graph_caller) - (ip + MCOUNT_INSN_SIZE); - - return ftrace_mod_jmp(ip, old_offset, new_offset); + return ftrace_mod_jmp(ip, &ftrace_graph_caller); } int ftrace_disable_ftrace_graph_caller(void) { unsigned long ip = (unsigned long)(&ftrace_graph_call); - int old_offset, new_offset; - - old_offset = (unsigned long)(&ftrace_graph_caller) - (ip + MCOUNT_INSN_SIZE); - new_offset = (unsigned long)(&ftrace_stub) - (ip + MCOUNT_INSN_SIZE); - return ftrace_mod_jmp(ip, old_offset, new_offset); + return ftrace_mod_jmp(ip, &ftrace_stub); } #endif /* !CONFIG_DYNAMIC_FTRACE */ diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 4eabc160696f..679cef0791cd 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -279,5 +279,7 @@ void arch_crash_save_vmcoreinfo(void) VMCOREINFO_SYMBOL(node_data); VMCOREINFO_LENGTH(node_data, MAX_NUMNODES); #endif + vmcoreinfo_append_str("KERNELOFFSET=%lx\n", + (unsigned long)&_text - __START_KERNEL); } diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index 872079a67e4d..f7d0672481fd 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -100,8 +100,10 @@ void *dma_generic_alloc_coherent(struct device *dev, size_t size, flag |= __GFP_ZERO; again: page = NULL; - if (!(flag & GFP_ATOMIC)) + /* CMA can be used only in the context which permits sleeping */ + if (flag & __GFP_WAIT) page = dma_alloc_from_contiguous(dev, count, get_order(size)); + /* fallback */ if (!page) page = alloc_pages_node(dev_to_node(dev), flag, get_order(size)); if (!page) diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 19e5adb49a27..cfbe99f88830 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -209,7 +209,7 @@ static inline unsigned long long cycles_2_ns(unsigned long long cyc) * dance when its actually needed. */ - preempt_disable(); + preempt_disable_notrace(); data = this_cpu_read(cyc2ns.head); tail = this_cpu_read(cyc2ns.tail); @@ -229,7 +229,7 @@ static inline unsigned long long cycles_2_ns(unsigned long long cyc) if (!--data->__count) this_cpu_write(cyc2ns.tail, data); } - preempt_enable(); + preempt_enable_notrace(); return ns; } @@ -653,13 +653,10 @@ unsigned long native_calibrate_tsc(void) /* Calibrate TSC using MSR for Intel Atom SoCs */ local_irq_save(flags); - i = try_msr_calibrate_tsc(&fast_calibrate); + fast_calibrate = try_msr_calibrate_tsc(); local_irq_restore(flags); - if (i >= 0) { - if (i == 0) - pr_warn("Fast TSC calibration using MSR failed\n"); + if (fast_calibrate) return fast_calibrate; - } local_irq_save(flags); fast_calibrate = quick_pit_calibrate(); diff --git a/arch/x86/kernel/tsc_msr.c b/arch/x86/kernel/tsc_msr.c index 8b5434f4389f..92ae6acac8a7 100644 --- a/arch/x86/kernel/tsc_msr.c +++ b/arch/x86/kernel/tsc_msr.c @@ -53,7 +53,7 @@ static struct freq_desc freq_desc_tables[] = { /* TNG */ { 6, 0x4a, 1, { 0, FREQ_100, FREQ_133, 0, 0, 0, 0, 0 } }, /* VLV2 */ - { 6, 0x37, 1, { 0, FREQ_100, FREQ_133, FREQ_166, 0, 0, 0, 0 } }, + { 6, 0x37, 1, { FREQ_83, FREQ_100, FREQ_133, FREQ_166, 0, 0, 0, 0 } }, /* ANN */ { 6, 0x5a, 1, { FREQ_83, FREQ_100, FREQ_133, FREQ_100, 0, 0, 0, 0 } }, }; @@ -77,21 +77,18 @@ static int match_cpu(u8 family, u8 model) /* * Do MSR calibration only for known/supported CPUs. - * Return values: - * -1: CPU is unknown/unsupported for MSR based calibration - * 0: CPU is known/supported, but calibration failed - * 1: CPU is known/supported, and calibration succeeded + * + * Returns the calibration value or 0 if MSR calibration failed. */ -int try_msr_calibrate_tsc(unsigned long *fast_calibrate) +unsigned long try_msr_calibrate_tsc(void) { - int cpu_index; u32 lo, hi, ratio, freq_id, freq; + unsigned long res; + int cpu_index; cpu_index = match_cpu(boot_cpu_data.x86, boot_cpu_data.x86_model); if (cpu_index < 0) - return -1; - - *fast_calibrate = 0; + return 0; if (freq_desc_tables[cpu_index].msr_plat) { rdmsr(MSR_PLATFORM_INFO, lo, hi); @@ -103,7 +100,7 @@ int try_msr_calibrate_tsc(unsigned long *fast_calibrate) pr_info("Maximum core-clock to bus-clock ratio: 0x%x\n", ratio); if (!ratio) - return 0; + goto fail; /* Get FSB FREQ ID */ rdmsr(MSR_FSB_FREQ, lo, hi); @@ -112,16 +109,19 @@ int try_msr_calibrate_tsc(unsigned long *fast_calibrate) pr_info("Resolved frequency ID: %u, frequency: %u KHz\n", freq_id, freq); if (!freq) - return 0; + goto fail; /* TSC frequency = maximum resolved freq * maximum resolved bus ratio */ - *fast_calibrate = freq * ratio; - pr_info("TSC runs at %lu KHz\n", *fast_calibrate); + res = freq * ratio; + pr_info("TSC runs at %lu KHz\n", res); #ifdef CONFIG_X86_LOCAL_APIC lapic_timer_frequency = (freq * 1000) / HZ; pr_info("lapic_timer_frequency = %d\n", lapic_timer_frequency); #endif + return res; - return 1; +fail: + pr_warn("Fast TSC calibration using MSR failed\n"); + return 0; } diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index e50425d0f5f7..9b531351a587 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -2672,6 +2672,7 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write, break; } + drop_large_spte(vcpu, iterator.sptep); if (!is_shadow_present_pte(*iterator.sptep)) { u64 base_addr = iterator.addr; diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index a06f101ef64b..392752834751 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -6688,7 +6688,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) else if (is_page_fault(intr_info)) return enable_ept; else if (is_no_device(intr_info) && - !(nested_read_cr0(vmcs12) & X86_CR0_TS)) + !(vmcs12->guest_cr0 & X86_CR0_TS)) return 0; return vmcs12->exception_bitmap & (1u << (intr_info & INTR_INFO_VECTOR_MASK)); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 39c28f09dfd5..2b8578432d5b 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -6186,7 +6186,7 @@ static int complete_emulated_mmio(struct kvm_vcpu *vcpu) frag->len -= len; } - if (vcpu->mmio_cur_fragment == vcpu->mmio_nr_fragments) { + if (vcpu->mmio_cur_fragment >= vcpu->mmio_nr_fragments) { vcpu->mmio_needed = 0; /* FIXME: return into emulator if single-stepping. */ diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 9d591c895803..6dea040cc3a1 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -1001,6 +1001,12 @@ static int fault_in_kernel_space(unsigned long address) static inline bool smap_violation(int error_code, struct pt_regs *regs) { + if (!IS_ENABLED(CONFIG_X86_SMAP)) + return false; + + if (!static_cpu_has(X86_FEATURE_SMAP)) + return false; + if (error_code & PF_USER) return false; @@ -1087,11 +1093,9 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code) if (unlikely(error_code & PF_RSVD)) pgtable_bad(regs, error_code, address); - if (static_cpu_has(X86_FEATURE_SMAP)) { - if (unlikely(smap_violation(error_code, regs))) { - bad_area_nosemaphore(regs, error_code, address); - return; - } + if (unlikely(smap_violation(error_code, regs))) { + bad_area_nosemaphore(regs, error_code, address); + return; } /* diff --git a/arch/x86/platform/efi/efi-bgrt.c b/arch/x86/platform/efi/efi-bgrt.c index 4df9591eadad..f15103dff4b4 100644 --- a/arch/x86/platform/efi/efi-bgrt.c +++ b/arch/x86/platform/efi/efi-bgrt.c @@ -42,7 +42,7 @@ void __init efi_bgrt_init(void) if (bgrt_tab->header.length < sizeof(*bgrt_tab)) return; - if (bgrt_tab->version != 1) + if (bgrt_tab->version != 1 || bgrt_tab->status != 1) return; if (bgrt_tab->image_type != 0 || !bgrt_tab->image_address) return; diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index d62ec87a2b26..1a201ac7cef8 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -792,7 +792,7 @@ void __init efi_set_executable(efi_memory_desc_t *md, bool executable) set_memory_nx(addr, npages); } -static void __init runtime_code_page_mkexec(void) +void __init runtime_code_page_mkexec(void) { efi_memory_desc_t *md; void *p; @@ -1069,8 +1069,7 @@ void __init efi_enter_virtual_mode(void) efi.update_capsule = virt_efi_update_capsule; efi.query_capsule_caps = virt_efi_query_capsule_caps; - if (efi_enabled(EFI_OLD_MEMMAP) && (__supported_pte_mask & _PAGE_NX)) - runtime_code_page_mkexec(); + efi_runtime_mkexec(); kfree(new_memmap); diff --git a/arch/x86/platform/efi/efi_32.c b/arch/x86/platform/efi/efi_32.c index 249b183cf417..0b74cdf7f816 100644 --- a/arch/x86/platform/efi/efi_32.c +++ b/arch/x86/platform/efi/efi_32.c @@ -77,3 +77,9 @@ void efi_call_phys_epilog(void) local_irq_restore(efi_rt_eflags); } + +void __init efi_runtime_mkexec(void) +{ + if (__supported_pte_mask & _PAGE_NX) + runtime_code_page_mkexec(); +} diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 6284f158a47d..0c2a234fef1e 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -233,3 +233,12 @@ void __init parse_efi_setup(u64 phys_addr, u32 data_len) { efi_setup = phys_addr + sizeof(struct setup_data); } + +void __init efi_runtime_mkexec(void) +{ + if (!efi_enabled(EFI_OLD_MEMMAP)) + return; + + if (__supported_pte_mask & _PAGE_NX) + runtime_code_page_mkexec(); +} diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 2423ef04ffea..256282e7888b 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -365,7 +365,7 @@ void xen_ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr, /* Assume pteval_t is equivalent to all the other *val_t types. */ static pteval_t pte_mfn_to_pfn(pteval_t val) { - if (val & _PAGE_PRESENT) { + if (pteval_present(val)) { unsigned long mfn = (val & PTE_PFN_MASK) >> PAGE_SHIFT; unsigned long pfn = mfn_to_pfn(mfn); @@ -381,7 +381,7 @@ static pteval_t pte_mfn_to_pfn(pteval_t val) static pteval_t pte_pfn_to_mfn(pteval_t val) { - if (val & _PAGE_PRESENT) { + if (pteval_present(val)) { unsigned long pfn = (val & PTE_PFN_MASK) >> PAGE_SHIFT; pteval_t flags = val & PTE_FLAGS_MASK; unsigned long mfn; diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig index ba56e11cbf77..c87ae7c6e5f9 100644 --- a/arch/xtensa/Kconfig +++ b/arch/xtensa/Kconfig @@ -20,6 +20,7 @@ config XTENSA select HAVE_FUNCTION_TRACER select HAVE_IRQ_TIME_ACCOUNTING select HAVE_PERF_EVENTS + select COMMON_CLK help Xtensa processors are 32-bit RISC machines designed by Tensilica primarily for embedded systems. These processors are both @@ -80,7 +81,6 @@ choice config XTENSA_VARIANT_FSF bool "fsf - default (not generic) configuration" select MMU - select HAVE_XTENSA_GPIO32 config XTENSA_VARIANT_DC232B bool "dc232b - Diamond 232L Standard Core Rev.B (LE)" @@ -135,7 +135,6 @@ config HAVE_SMP config SMP bool "Enable Symmetric multi-processing support" depends on HAVE_SMP - select USE_GENERIC_SMP_HELPERS select GENERIC_SMP_IDLE_THREAD help Enabled SMP Software; allows more than one CPU/CORE diff --git a/arch/xtensa/boot/dts/xtfpga.dtsi b/arch/xtensa/boot/dts/xtfpga.dtsi index 46b4f5eab421..e7370b11348e 100644 --- a/arch/xtensa/boot/dts/xtfpga.dtsi +++ b/arch/xtensa/boot/dts/xtfpga.dtsi @@ -35,6 +35,13 @@ interrupt-controller; }; + clocks { + osc: main-oscillator { + #clock-cells = <0>; + compatible = "fixed-clock"; + }; + }; + serial0: serial@fd050020 { device_type = "serial"; compatible = "ns16550a"; @@ -42,9 +49,7 @@ reg = <0xfd050020 0x20>; reg-shift = <2>; interrupts = <0 1>; /* external irq 0 */ - /* Filled in by platform_setup from FPGA register - * clock-frequency = <100000000>; - */ + clocks = <&osc>; }; enet0: ethoc@fd030000 { @@ -52,5 +57,6 @@ reg = <0xfd030000 0x4000 0xfd800000 0x4000>; interrupts = <1 1>; /* external irq 1 */ local-mac-address = [00 50 c2 13 6f 00]; + clocks = <&osc>; }; }; diff --git a/arch/xtensa/include/asm/io.h b/arch/xtensa/include/asm/io.h index 2a042d430c25..74944207167e 100644 --- a/arch/xtensa/include/asm/io.h +++ b/arch/xtensa/include/asm/io.h @@ -25,7 +25,7 @@ #ifdef CONFIG_MMU -#if XCHAL_HAVE_PTP_MMU && XCHAL_HAVE_SPANNING_WAY && CONFIG_OF +#if XCHAL_HAVE_PTP_MMU && XCHAL_HAVE_SPANNING_WAY && defined(CONFIG_OF) extern unsigned long xtensa_kio_paddr; static inline unsigned long xtensa_get_kio_paddr(void) diff --git a/arch/xtensa/include/asm/traps.h b/arch/xtensa/include/asm/traps.h index 8c194f6af45e..677bfcf4ee5d 100644 --- a/arch/xtensa/include/asm/traps.h +++ b/arch/xtensa/include/asm/traps.h @@ -23,25 +23,37 @@ void secondary_trap_init(void); static inline void spill_registers(void) { - +#if XCHAL_NUM_AREGS > 16 __asm__ __volatile__ ( - "movi a14, "__stringify((1 << PS_EXCM_BIT) | LOCKLEVEL)"\n\t" - "mov a12, a0\n\t" - "rsr a13, sar\n\t" - "xsr a14, ps\n\t" - "movi a0, _spill_registers\n\t" - "rsync\n\t" - "callx0 a0\n\t" - "mov a0, a12\n\t" - "wsr a13, sar\n\t" - "wsr a14, ps\n\t" - : : -#if defined(CONFIG_FRAME_POINTER) - : "a2", "a3", "a4", "a11", "a12", "a13", "a14", "a15", + " call12 1f\n" + " _j 2f\n" + " retw\n" + " .align 4\n" + "1:\n" + " _entry a1, 48\n" + " addi a12, a0, 3\n" +#if XCHAL_NUM_AREGS > 32 + " .rept (" __stringify(XCHAL_NUM_AREGS) " - 32) / 12\n" + " _entry a1, 48\n" + " mov a12, a0\n" + " .endr\n" +#endif + " _entry a1, 48\n" +#if XCHAL_NUM_AREGS % 12 == 0 + " mov a8, a8\n" +#elif XCHAL_NUM_AREGS % 12 == 4 + " mov a12, a12\n" +#elif XCHAL_NUM_AREGS % 12 == 8 + " mov a4, a4\n" +#endif + " retw\n" + "2:\n" + : : : "a12", "a13", "memory"); #else - : "a2", "a3", "a4", "a7", "a11", "a12", "a13", "a14", "a15", + __asm__ __volatile__ ( + " mov a12, a12\n" + : : : "memory"); #endif - "memory"); } #endif /* _XTENSA_TRAPS_H */ diff --git a/arch/xtensa/include/asm/vectors.h b/arch/xtensa/include/asm/vectors.h index 5791b45d5a5d..f74ddfbb92ef 100644 --- a/arch/xtensa/include/asm/vectors.h +++ b/arch/xtensa/include/asm/vectors.h @@ -25,7 +25,7 @@ #define XCHAL_KIO_DEFAULT_PADDR 0xf0000000 #define XCHAL_KIO_SIZE 0x10000000 -#if XCHAL_HAVE_PTP_MMU && XCHAL_HAVE_SPANNING_WAY && CONFIG_OF +#if XCHAL_HAVE_PTP_MMU && XCHAL_HAVE_SPANNING_WAY && defined(CONFIG_OF) #define XCHAL_KIO_PADDR xtensa_get_kio_paddr() #else #define XCHAL_KIO_PADDR XCHAL_KIO_DEFAULT_PADDR diff --git a/arch/xtensa/include/uapi/asm/unistd.h b/arch/xtensa/include/uapi/asm/unistd.h index 51940fec6990..b9395529f02d 100644 --- a/arch/xtensa/include/uapi/asm/unistd.h +++ b/arch/xtensa/include/uapi/asm/unistd.h @@ -734,7 +734,12 @@ __SYSCALL(332, sys_finit_module, 3) #define __NR_accept4 333 __SYSCALL(333, sys_accept4, 4) -#define __NR_syscall_count 334 +#define __NR_sched_setattr 334 +__SYSCALL(334, sys_sched_setattr, 2) +#define __NR_sched_getattr 335 +__SYSCALL(335, sys_sched_getattr, 3) + +#define __NR_syscall_count 336 /* * sysxtensa syscall handler diff --git a/arch/xtensa/kernel/entry.S b/arch/xtensa/kernel/entry.S index 21dbe6bdb8ed..ef7f4990722b 100644 --- a/arch/xtensa/kernel/entry.S +++ b/arch/xtensa/kernel/entry.S @@ -1081,196 +1081,53 @@ ENTRY(fast_syscall_spill_registers) rsr a0, sar s32i a3, a2, PT_AREG3 - s32i a4, a2, PT_AREG4 - s32i a0, a2, PT_AREG5 # store SAR to PT_AREG5 + s32i a0, a2, PT_SAR - /* The spill routine might clobber a7, a11, and a15. */ + /* The spill routine might clobber a4, a7, a8, a11, a12, and a15. */ + s32i a4, a2, PT_AREG4 s32i a7, a2, PT_AREG7 + s32i a8, a2, PT_AREG8 s32i a11, a2, PT_AREG11 + s32i a12, a2, PT_AREG12 s32i a15, a2, PT_AREG15 - call0 _spill_registers # destroys a3, a4, and SAR - - /* Advance PC, restore registers and SAR, and return from exception. */ - - l32i a3, a2, PT_AREG5 - l32i a4, a2, PT_AREG4 - l32i a0, a2, PT_AREG0 - wsr a3, sar - l32i a3, a2, PT_AREG3 - - /* Restore clobbered registers. */ - - l32i a7, a2, PT_AREG7 - l32i a11, a2, PT_AREG11 - l32i a15, a2, PT_AREG15 - - movi a2, 0 - rfe - -ENDPROC(fast_syscall_spill_registers) - -/* Fixup handler. - * - * We get here if the spill routine causes an exception, e.g. tlb miss. - * We basically restore WINDOWBASE and WINDOWSTART to the condition when - * we entered the spill routine and jump to the user exception handler. - * - * a0: value of depc, original value in depc - * a2: trashed, original value in EXC_TABLE_DOUBLE_SAVE - * a3: exctable, original value in excsave1 - */ - -ENTRY(fast_syscall_spill_registers_fixup) - - rsr a2, windowbase # get current windowbase (a2 is saved) - xsr a0, depc # restore depc and a0 - ssl a2 # set shift (32 - WB) - - /* We need to make sure the current registers (a0-a3) are preserved. - * To do this, we simply set the bit for the current window frame - * in WS, so that the exception handlers save them to the task stack. - */ - - xsr a3, excsave1 # get spill-mask - slli a3, a3, 1 # shift left by one - - slli a2, a3, 32-WSBITS - src a2, a3, a2 # a2 = xxwww1yyxxxwww1yy...... - wsr a2, windowstart # set corrected windowstart - - srli a3, a3, 1 - rsr a2, excsave1 - l32i a2, a2, EXC_TABLE_DOUBLE_SAVE # restore a2 - xsr a2, excsave1 - s32i a3, a2, EXC_TABLE_DOUBLE_SAVE # save a3 - l32i a3, a2, EXC_TABLE_PARAM # original WB (in user task) - xsr a2, excsave1 - - /* Return to the original (user task) WINDOWBASE. - * We leave the following frame behind: - * a0, a1, a2 same - * a3: trashed (saved in EXC_TABLE_DOUBLE_SAVE) - * depc: depc (we have to return to that address) - * excsave_1: exctable - */ - - wsr a3, windowbase - rsync - - /* We are now in the original frame when we entered _spill_registers: - * a0: return address - * a1: used, stack pointer - * a2: kernel stack pointer - * a3: available - * depc: exception address - * excsave: exctable - * Note: This frame might be the same as above. - */ - - /* Setup stack pointer. */ - - addi a2, a2, -PT_USER_SIZE - s32i a0, a2, PT_AREG0 - - /* Make sure we return to this fixup handler. */ - - movi a3, fast_syscall_spill_registers_fixup_return - s32i a3, a2, PT_DEPC # setup depc - - /* Jump to the exception handler. */ - - rsr a3, excsave1 - rsr a0, exccause - addx4 a0, a0, a3 # find entry in table - l32i a0, a0, EXC_TABLE_FAST_USER # load handler - l32i a3, a3, EXC_TABLE_DOUBLE_SAVE - jx a0 - -ENDPROC(fast_syscall_spill_registers_fixup) - -ENTRY(fast_syscall_spill_registers_fixup_return) - - /* When we return here, all registers have been restored (a2: DEPC) */ - - wsr a2, depc # exception address - - /* Restore fixup handler. */ - - rsr a2, excsave1 - s32i a3, a2, EXC_TABLE_DOUBLE_SAVE - movi a3, fast_syscall_spill_registers_fixup - s32i a3, a2, EXC_TABLE_FIXUP - rsr a3, windowbase - s32i a3, a2, EXC_TABLE_PARAM - l32i a2, a2, EXC_TABLE_KSTK - - /* Load WB at the time the exception occurred. */ - - rsr a3, sar # WB is still in SAR - neg a3, a3 - wsr a3, windowbase - rsync - - rsr a3, excsave1 - l32i a3, a3, EXC_TABLE_DOUBLE_SAVE - - rfde - -ENDPROC(fast_syscall_spill_registers_fixup_return) - -/* - * spill all registers. - * - * This is not a real function. The following conditions must be met: - * - * - must be called with call0. - * - uses a3, a4 and SAR. - * - the last 'valid' register of each frame are clobbered. - * - the caller must have registered a fixup handler - * (or be inside a critical section) - * - PS_EXCM must be set (PS_WOE cleared?) - */ - -ENTRY(_spill_registers) - /* * Rotate ws so that the current windowbase is at bit 0. * Assume ws = xxxwww1yy (www1 current window frame). * Rotate ws right so that a4 = yyxxxwww1. */ - rsr a4, windowbase + rsr a0, windowbase rsr a3, windowstart # a3 = xxxwww1yy - ssr a4 # holds WB - slli a4, a3, WSBITS - or a3, a3, a4 # a3 = xxxwww1yyxxxwww1yy + ssr a0 # holds WB + slli a0, a3, WSBITS + or a3, a3, a0 # a3 = xxxwww1yyxxxwww1yy srl a3, a3 # a3 = 00xxxwww1yyxxxwww1 /* We are done if there are no more than the current register frame. */ extui a3, a3, 1, WSBITS-1 # a3 = 0yyxxxwww - movi a4, (1 << (WSBITS-1)) + movi a0, (1 << (WSBITS-1)) _beqz a3, .Lnospill # only one active frame? jump /* We want 1 at the top, so that we return to the current windowbase */ - or a3, a3, a4 # 1yyxxxwww + or a3, a3, a0 # 1yyxxxwww /* Skip empty frames - get 'oldest' WINDOWSTART-bit. */ wsr a3, windowstart # save shifted windowstart - neg a4, a3 - and a3, a4, a3 # first bit set from right: 000010000 + neg a0, a3 + and a3, a0, a3 # first bit set from right: 000010000 - ffs_ws a4, a3 # a4: shifts to skip empty frames + ffs_ws a0, a3 # a0: shifts to skip empty frames movi a3, WSBITS - sub a4, a3, a4 # WSBITS-a4:number of 0-bits from right - ssr a4 # save in SAR for later. + sub a0, a3, a0 # WSBITS-a0:number of 0-bits from right + ssr a0 # save in SAR for later. rsr a3, windowbase - add a3, a3, a4 + add a3, a3, a0 wsr a3, windowbase rsync @@ -1285,22 +1142,6 @@ ENTRY(_spill_registers) * we have to save 4,8. or 12 registers. */ - _bbsi.l a3, 1, .Lc4 - _bbsi.l a3, 2, .Lc8 - - /* Special case: we have a call12-frame starting at a4. */ - - _bbci.l a3, 3, .Lc12 # bit 3 shouldn't be zero! (Jump to Lc12 first) - - s32e a4, a1, -16 # a1 is valid with an empty spill area - l32e a4, a5, -12 - s32e a8, a4, -48 - mov a8, a4 - l32e a4, a1, -16 - j .Lc12c - -.Lnospill: - ret .Lloop: _bbsi.l a3, 1, .Lc4 _bbci.l a3, 2, .Lc12 @@ -1314,20 +1155,10 @@ ENTRY(_spill_registers) s32e a9, a4, -28 s32e a10, a4, -24 s32e a11, a4, -20 - srli a11, a3, 2 # shift windowbase by 2 rotw 2 _bnei a3, 1, .Lloop - -.Lexit: /* Done. Do the final rotation, set WS, and return. */ - - rotw 1 - rsr a3, windowbase - ssl a3 - movi a3, 1 - sll a3, a3 - wsr a3, windowstart - ret + j .Lexit .Lc4: s32e a4, a9, -16 s32e a5, a9, -12 @@ -1343,11 +1174,11 @@ ENTRY(_spill_registers) /* 12-register frame (call12) */ - l32e a2, a5, -12 - s32e a8, a2, -48 - mov a8, a2 + l32e a0, a5, -12 + s32e a8, a0, -48 + mov a8, a0 -.Lc12c: s32e a9, a8, -44 + s32e a9, a8, -44 s32e a10, a8, -40 s32e a11, a8, -36 s32e a12, a8, -32 @@ -1367,30 +1198,54 @@ ENTRY(_spill_registers) */ rotw 1 - mov a5, a13 + mov a4, a13 rotw -1 - s32e a4, a9, -16 - s32e a5, a9, -12 - s32e a6, a9, -8 - s32e a7, a9, -4 + s32e a4, a8, -16 + s32e a5, a8, -12 + s32e a6, a8, -8 + s32e a7, a8, -4 rotw 3 _beqi a3, 1, .Lexit j .Lloop -.Linvalid_mask: +.Lexit: - /* We get here because of an unrecoverable error in the window - * registers. If we are in user space, we kill the application, - * however, this condition is unrecoverable in kernel space. - */ + /* Done. Do the final rotation and set WS */ + + rotw 1 + rsr a3, windowbase + ssl a3 + movi a3, 1 + sll a3, a3 + wsr a3, windowstart +.Lnospill: + + /* Advance PC, restore registers and SAR, and return from exception. */ + + l32i a3, a2, PT_SAR + l32i a0, a2, PT_AREG0 + wsr a3, sar + l32i a3, a2, PT_AREG3 - rsr a0, ps - _bbci.l a0, PS_UM_BIT, 1f + /* Restore clobbered registers. */ - /* User space: Setup a dummy frame and kill application. + l32i a4, a2, PT_AREG4 + l32i a7, a2, PT_AREG7 + l32i a8, a2, PT_AREG8 + l32i a11, a2, PT_AREG11 + l32i a12, a2, PT_AREG12 + l32i a15, a2, PT_AREG15 + + movi a2, 0 + rfe + +.Linvalid_mask: + + /* We get here because of an unrecoverable error in the window + * registers, so set up a dummy frame and kill the user application. * Note: We assume EXC_TABLE_KSTK contains a valid stack pointer. */ @@ -1414,14 +1269,136 @@ ENTRY(_spill_registers) movi a4, do_exit callx4 a4 -1: /* Kernel space: PANIC! */ + /* shouldn't return, so panic */ wsr a0, excsave1 movi a0, unrecoverable_exception callx0 a0 # should not return 1: j 1b -ENDPROC(_spill_registers) + +ENDPROC(fast_syscall_spill_registers) + +/* Fixup handler. + * + * We get here if the spill routine causes an exception, e.g. tlb miss. + * We basically restore WINDOWBASE and WINDOWSTART to the condition when + * we entered the spill routine and jump to the user exception handler. + * + * Note that we only need to restore the bits in windowstart that have not + * been spilled yet by the _spill_register routine. Luckily, a3 contains a + * rotated windowstart with only those bits set for frames that haven't been + * spilled yet. Because a3 is rotated such that bit 0 represents the register + * frame for the current windowbase - 1, we need to rotate a3 left by the + * value of the current windowbase + 1 and move it to windowstart. + * + * a0: value of depc, original value in depc + * a2: trashed, original value in EXC_TABLE_DOUBLE_SAVE + * a3: exctable, original value in excsave1 + */ + +ENTRY(fast_syscall_spill_registers_fixup) + + rsr a2, windowbase # get current windowbase (a2 is saved) + xsr a0, depc # restore depc and a0 + ssl a2 # set shift (32 - WB) + + /* We need to make sure the current registers (a0-a3) are preserved. + * To do this, we simply set the bit for the current window frame + * in WS, so that the exception handlers save them to the task stack. + * + * Note: we use a3 to set the windowbase, so we take a special care + * of it, saving it in the original _spill_registers frame across + * the exception handler call. + */ + + xsr a3, excsave1 # get spill-mask + slli a3, a3, 1 # shift left by one + addi a3, a3, 1 # set the bit for the current window frame + + slli a2, a3, 32-WSBITS + src a2, a3, a2 # a2 = xxwww1yyxxxwww1yy...... + wsr a2, windowstart # set corrected windowstart + + srli a3, a3, 1 + rsr a2, excsave1 + l32i a2, a2, EXC_TABLE_DOUBLE_SAVE # restore a2 + xsr a2, excsave1 + s32i a3, a2, EXC_TABLE_DOUBLE_SAVE # save a3 + l32i a3, a2, EXC_TABLE_PARAM # original WB (in user task) + xsr a2, excsave1 + + /* Return to the original (user task) WINDOWBASE. + * We leave the following frame behind: + * a0, a1, a2 same + * a3: trashed (saved in EXC_TABLE_DOUBLE_SAVE) + * depc: depc (we have to return to that address) + * excsave_1: exctable + */ + + wsr a3, windowbase + rsync + + /* We are now in the original frame when we entered _spill_registers: + * a0: return address + * a1: used, stack pointer + * a2: kernel stack pointer + * a3: available + * depc: exception address + * excsave: exctable + * Note: This frame might be the same as above. + */ + + /* Setup stack pointer. */ + + addi a2, a2, -PT_USER_SIZE + s32i a0, a2, PT_AREG0 + + /* Make sure we return to this fixup handler. */ + + movi a3, fast_syscall_spill_registers_fixup_return + s32i a3, a2, PT_DEPC # setup depc + + /* Jump to the exception handler. */ + + rsr a3, excsave1 + rsr a0, exccause + addx4 a0, a0, a3 # find entry in table + l32i a0, a0, EXC_TABLE_FAST_USER # load handler + l32i a3, a3, EXC_TABLE_DOUBLE_SAVE + jx a0 + +ENDPROC(fast_syscall_spill_registers_fixup) + +ENTRY(fast_syscall_spill_registers_fixup_return) + + /* When we return here, all registers have been restored (a2: DEPC) */ + + wsr a2, depc # exception address + + /* Restore fixup handler. */ + + rsr a2, excsave1 + s32i a3, a2, EXC_TABLE_DOUBLE_SAVE + movi a3, fast_syscall_spill_registers_fixup + s32i a3, a2, EXC_TABLE_FIXUP + rsr a3, windowbase + s32i a3, a2, EXC_TABLE_PARAM + l32i a2, a2, EXC_TABLE_KSTK + + /* Load WB at the time the exception occurred. */ + + rsr a3, sar # WB is still in SAR + neg a3, a3 + wsr a3, windowbase + rsync + + rsr a3, excsave1 + l32i a3, a3, EXC_TABLE_DOUBLE_SAVE + + rfde + +ENDPROC(fast_syscall_spill_registers_fixup_return) #ifdef CONFIG_MMU /* @@ -1794,6 +1771,43 @@ ENTRY(system_call) ENDPROC(system_call) +/* + * Spill live registers on the kernel stack macro. + * + * Entry condition: ps.woe is set, ps.excm is cleared + * Exit condition: windowstart has single bit set + * May clobber: a12, a13 + */ + .macro spill_registers_kernel + +#if XCHAL_NUM_AREGS > 16 + call12 1f + _j 2f + retw + .align 4 +1: + _entry a1, 48 + addi a12, a0, 3 +#if XCHAL_NUM_AREGS > 32 + .rept (XCHAL_NUM_AREGS - 32) / 12 + _entry a1, 48 + mov a12, a0 + .endr +#endif + _entry a1, 48 +#if XCHAL_NUM_AREGS % 12 == 0 + mov a8, a8 +#elif XCHAL_NUM_AREGS % 12 == 4 + mov a12, a12 +#elif XCHAL_NUM_AREGS % 12 == 8 + mov a4, a4 +#endif + retw +2: +#else + mov a12, a12 +#endif + .endm /* * Task switch. @@ -1806,21 +1820,20 @@ ENTRY(_switch_to) entry a1, 16 - mov a12, a2 # preserve 'prev' (a2) - mov a13, a3 # and 'next' (a3) + mov a10, a2 # preserve 'prev' (a2) + mov a11, a3 # and 'next' (a3) l32i a4, a2, TASK_THREAD_INFO l32i a5, a3, TASK_THREAD_INFO - save_xtregs_user a4 a6 a8 a9 a10 a11 THREAD_XTREGS_USER + save_xtregs_user a4 a6 a8 a9 a12 a13 THREAD_XTREGS_USER - s32i a0, a12, THREAD_RA # save return address - s32i a1, a12, THREAD_SP # save stack pointer + s32i a0, a10, THREAD_RA # save return address + s32i a1, a10, THREAD_SP # save stack pointer /* Disable ints while we manipulate the stack pointer. */ - movi a14, (1 << PS_EXCM_BIT) | LOCKLEVEL - xsr a14, ps + rsil a14, LOCKLEVEL rsr a3, excsave1 rsync s32i a3, a3, EXC_TABLE_FIXUP /* enter critical section */ @@ -1835,7 +1848,7 @@ ENTRY(_switch_to) /* Flush register file. */ - call0 _spill_registers # destroys a3, a4, and SAR + spill_registers_kernel /* Set kernel stack (and leave critical section) * Note: It's save to set it here. The stack will not be overwritten @@ -1851,13 +1864,13 @@ ENTRY(_switch_to) /* restore context of the task 'next' */ - l32i a0, a13, THREAD_RA # restore return address - l32i a1, a13, THREAD_SP # restore stack pointer + l32i a0, a11, THREAD_RA # restore return address + l32i a1, a11, THREAD_SP # restore stack pointer - load_xtregs_user a5 a6 a8 a9 a10 a11 THREAD_XTREGS_USER + load_xtregs_user a5 a6 a8 a9 a12 a13 THREAD_XTREGS_USER wsr a14, ps - mov a2, a12 # return 'prev' + mov a2, a10 # return 'prev' rsync retw diff --git a/arch/xtensa/kernel/setup.c b/arch/xtensa/kernel/setup.c index 7d12af1317f1..84fe931bb60e 100644 --- a/arch/xtensa/kernel/setup.c +++ b/arch/xtensa/kernel/setup.c @@ -22,6 +22,7 @@ #include <linux/bootmem.h> #include <linux/kernel.h> #include <linux/percpu.h> +#include <linux/clk-provider.h> #include <linux/cpu.h> #include <linux/of_fdt.h> #include <linux/of_platform.h> @@ -276,6 +277,7 @@ void __init early_init_devtree(void *params) static int __init xtensa_device_probe(void) { + of_clk_init(NULL); of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL); return 0; } diff --git a/arch/xtensa/kernel/time.c b/arch/xtensa/kernel/time.c index 08b769d3b3a1..2a1823de69cc 100644 --- a/arch/xtensa/kernel/time.c +++ b/arch/xtensa/kernel/time.c @@ -30,6 +30,7 @@ #include <asm/platform.h> unsigned long ccount_freq; /* ccount Hz */ +EXPORT_SYMBOL(ccount_freq); static cycle_t ccount_read(struct clocksource *cs) { diff --git a/arch/xtensa/kernel/vectors.S b/arch/xtensa/kernel/vectors.S index cb8fd44caabc..f9e1ec346e35 100644 --- a/arch/xtensa/kernel/vectors.S +++ b/arch/xtensa/kernel/vectors.S @@ -235,7 +235,7 @@ ENTRY(_DoubleExceptionVector) /* Check for overflow/underflow exception, jump if overflow. */ - _bbci.l a0, 6, _DoubleExceptionVector_WindowOverflow + bbci.l a0, 6, _DoubleExceptionVector_WindowOverflow /* * Restart window underflow exception. diff --git a/arch/xtensa/kernel/xtensa_ksyms.c b/arch/xtensa/kernel/xtensa_ksyms.c index 74a60c7e085e..80b33ed51f31 100644 --- a/arch/xtensa/kernel/xtensa_ksyms.c +++ b/arch/xtensa/kernel/xtensa_ksyms.c @@ -122,9 +122,7 @@ EXPORT_SYMBOL(insw); EXPORT_SYMBOL(insl); extern long common_exception_return; -extern long _spill_registers; EXPORT_SYMBOL(common_exception_return); -EXPORT_SYMBOL(_spill_registers); #ifdef CONFIG_FUNCTION_TRACER EXPORT_SYMBOL(_mcount); diff --git a/arch/xtensa/mm/init.c b/arch/xtensa/mm/init.c index 479d7537a32a..aff108df92d3 100644 --- a/arch/xtensa/mm/init.c +++ b/arch/xtensa/mm/init.c @@ -90,7 +90,7 @@ int __init mem_reserve(unsigned long start, unsigned long end, int must_exist) /* - * Initialize the bootmem system and give it all the memory we have available. + * Initialize the bootmem system and give it all low memory we have available. */ void __init bootmem_init(void) @@ -142,9 +142,14 @@ void __init bootmem_init(void) /* Add all remaining memory pieces into the bootmem map */ - for (i=0; i<sysmem.nr_banks; i++) - free_bootmem(sysmem.bank[i].start, - sysmem.bank[i].end - sysmem.bank[i].start); + for (i = 0; i < sysmem.nr_banks; i++) { + if (sysmem.bank[i].start >> PAGE_SHIFT < max_low_pfn) { + unsigned long end = min(max_low_pfn << PAGE_SHIFT, + sysmem.bank[i].end); + free_bootmem(sysmem.bank[i].start, + end - sysmem.bank[i].start); + } + } } diff --git a/arch/xtensa/mm/mmu.c b/arch/xtensa/mm/mmu.c index 36ec171698b8..861203e958da 100644 --- a/arch/xtensa/mm/mmu.c +++ b/arch/xtensa/mm/mmu.c @@ -39,7 +39,7 @@ void init_mmu(void) set_itlbcfg_register(0); set_dtlbcfg_register(0); #endif -#if XCHAL_HAVE_PTP_MMU && XCHAL_HAVE_SPANNING_WAY && CONFIG_OF +#if XCHAL_HAVE_PTP_MMU && XCHAL_HAVE_SPANNING_WAY && defined(CONFIG_OF) /* * Update the IO area mapping in case xtensa_kio_paddr has changed */ diff --git a/arch/xtensa/platforms/xtfpga/setup.c b/arch/xtensa/platforms/xtfpga/setup.c index 800227862fe8..57fd08b36f51 100644 --- a/arch/xtensa/platforms/xtfpga/setup.c +++ b/arch/xtensa/platforms/xtfpga/setup.c @@ -135,11 +135,11 @@ static void __init update_local_mac(struct device_node *node) static int __init machine_setup(void) { - struct device_node *serial; + struct device_node *clock; struct device_node *eth = NULL; - for_each_compatible_node(serial, NULL, "ns16550a") - update_clock_frequency(serial); + for_each_node_by_name(clock, "main-oscillator") + update_clock_frequency(clock); if ((eth = of_find_compatible_node(eth, NULL, "opencores,ethoc"))) update_local_mac(eth); @@ -290,6 +290,7 @@ static int __init xtavnet_init(void) * knows whether they set it correctly on the DIP switches. */ pr_info("XTFPGA: Ethernet MAC %pM\n", ethoc_pdata.hwaddr); + ethoc_pdata.eth_clkfreq = *(long *)XTFPGA_CLKFRQ_VADDR; return 0; } diff --git a/arch/xtensa/variants/fsf/include/variant/tie.h b/arch/xtensa/variants/fsf/include/variant/tie.h index bf4020116df5..244cdea4dee5 100644 --- a/arch/xtensa/variants/fsf/include/variant/tie.h +++ b/arch/xtensa/variants/fsf/include/variant/tie.h @@ -18,13 +18,6 @@ #define XCHAL_CP_MASK 0x00 /* bitmask of all CPs by ID */ #define XCHAL_CP_PORT_MASK 0x00 /* bitmask of only port CPs */ -/* Basic parameters of each coprocessor: */ -#define XCHAL_CP7_NAME "XTIOP" -#define XCHAL_CP7_IDENT XTIOP -#define XCHAL_CP7_SA_SIZE 0 /* size of state save area */ -#define XCHAL_CP7_SA_ALIGN 1 /* min alignment of save area */ -#define XCHAL_CP_ID_XTIOP 7 /* coprocessor ID (0..7) */ - /* Filler info for unassigned coprocessors, to simplify arrays etc: */ #define XCHAL_NCP_SA_SIZE 0 #define XCHAL_NCP_SA_ALIGN 1 @@ -42,6 +35,8 @@ #define XCHAL_CP5_SA_ALIGN 1 #define XCHAL_CP6_SA_SIZE 0 #define XCHAL_CP6_SA_ALIGN 1 +#define XCHAL_CP7_SA_SIZE 0 +#define XCHAL_CP7_SA_ALIGN 1 /* Save area for non-coprocessor optional and custom (TIE) state: */ #define XCHAL_NCP_SA_SIZE 0 diff --git a/block/blk-core.c b/block/blk-core.c index c00e0bdeab4a..853f92749202 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -693,11 +693,20 @@ blk_init_queue_node(request_fn_proc *rfn, spinlock_t *lock, int node_id) if (!uninit_q) return NULL; + uninit_q->flush_rq = kzalloc(sizeof(struct request), GFP_KERNEL); + if (!uninit_q->flush_rq) + goto out_cleanup_queue; + q = blk_init_allocated_queue(uninit_q, rfn, lock); if (!q) - blk_cleanup_queue(uninit_q); - + goto out_free_flush_rq; return q; + +out_free_flush_rq: + kfree(uninit_q->flush_rq); +out_cleanup_queue: + blk_cleanup_queue(uninit_q); + return NULL; } EXPORT_SYMBOL(blk_init_queue_node); @@ -1127,7 +1136,7 @@ static struct request *blk_old_get_request(struct request_queue *q, int rw, struct request *blk_get_request(struct request_queue *q, int rw, gfp_t gfp_mask) { if (q->mq_ops) - return blk_mq_alloc_request(q, rw, gfp_mask, false); + return blk_mq_alloc_request(q, rw, gfp_mask); else return blk_old_get_request(q, rw, gfp_mask); } @@ -1278,6 +1287,11 @@ void __blk_put_request(struct request_queue *q, struct request *req) if (unlikely(!q)) return; + if (q->mq_ops) { + blk_mq_free_request(req); + return; + } + blk_pm_put_request(req); elv_completed_request(q, req); diff --git a/block/blk-exec.c b/block/blk-exec.c index bbfc072a79c2..c68613bb4c79 100644 --- a/block/blk-exec.c +++ b/block/blk-exec.c @@ -65,7 +65,7 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk, * be resued after dying flag is set */ if (q->mq_ops) { - blk_mq_insert_request(q, rq, true); + blk_mq_insert_request(q, rq, at_head, true); return; } diff --git a/block/blk-flush.c b/block/blk-flush.c index 9288aaf35c21..66e2b697f5db 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -130,20 +130,26 @@ static void blk_flush_restore_request(struct request *rq) blk_clear_rq_complete(rq); } -static void mq_flush_data_run(struct work_struct *work) +static void mq_flush_run(struct work_struct *work) { struct request *rq; - rq = container_of(work, struct request, mq_flush_data); + rq = container_of(work, struct request, mq_flush_work); memset(&rq->csd, 0, sizeof(rq->csd)); blk_mq_run_request(rq, true, false); } -static void blk_mq_flush_data_insert(struct request *rq) +static bool blk_flush_queue_rq(struct request *rq) { - INIT_WORK(&rq->mq_flush_data, mq_flush_data_run); - kblockd_schedule_work(rq->q, &rq->mq_flush_data); + if (rq->q->mq_ops) { + INIT_WORK(&rq->mq_flush_work, mq_flush_run); + kblockd_schedule_work(rq->q, &rq->mq_flush_work); + return false; + } else { + list_add_tail(&rq->queuelist, &rq->q->queue_head); + return true; + } } /** @@ -187,12 +193,7 @@ static bool blk_flush_complete_seq(struct request *rq, unsigned int seq, case REQ_FSEQ_DATA: list_move_tail(&rq->flush.list, &q->flush_data_in_flight); - if (q->mq_ops) - blk_mq_flush_data_insert(rq); - else { - list_add(&rq->queuelist, &q->queue_head); - queued = true; - } + queued = blk_flush_queue_rq(rq); break; case REQ_FSEQ_DONE: @@ -216,9 +217,6 @@ static bool blk_flush_complete_seq(struct request *rq, unsigned int seq, } kicked = blk_kick_flush(q); - /* blk_mq_run_flush will run queue */ - if (q->mq_ops) - return queued; return kicked | queued; } @@ -230,10 +228,9 @@ static void flush_end_io(struct request *flush_rq, int error) struct request *rq, *n; unsigned long flags = 0; - if (q->mq_ops) { - blk_mq_free_request(flush_rq); + if (q->mq_ops) spin_lock_irqsave(&q->mq_flush_lock, flags); - } + running = &q->flush_queue[q->flush_running_idx]; BUG_ON(q->flush_pending_idx == q->flush_running_idx); @@ -263,49 +260,14 @@ static void flush_end_io(struct request *flush_rq, int error) * kblockd. */ if (queued || q->flush_queue_delayed) { - if (!q->mq_ops) - blk_run_queue_async(q); - else - /* - * This can be optimized to only run queues with requests - * queued if necessary. - */ - blk_mq_run_queues(q, true); + WARN_ON(q->mq_ops); + blk_run_queue_async(q); } q->flush_queue_delayed = 0; if (q->mq_ops) spin_unlock_irqrestore(&q->mq_flush_lock, flags); } -static void mq_flush_work(struct work_struct *work) -{ - struct request_queue *q; - struct request *rq; - - q = container_of(work, struct request_queue, mq_flush_work); - - /* We don't need set REQ_FLUSH_SEQ, it's for consistency */ - rq = blk_mq_alloc_request(q, WRITE_FLUSH|REQ_FLUSH_SEQ, - __GFP_WAIT|GFP_ATOMIC, true); - rq->cmd_type = REQ_TYPE_FS; - rq->end_io = flush_end_io; - - blk_mq_run_request(rq, true, false); -} - -/* - * We can't directly use q->flush_rq, because it doesn't have tag and is not in - * hctx->rqs[]. so we must allocate a new request, since we can't sleep here, - * so offload the work to workqueue. - * - * Note: we assume a flush request finished in any hardware queue will flush - * the whole disk cache. - */ -static void mq_run_flush(struct request_queue *q) -{ - kblockd_schedule_work(q, &q->mq_flush_work); -} - /** * blk_kick_flush - consider issuing flush request * @q: request_queue being kicked @@ -340,19 +302,31 @@ static bool blk_kick_flush(struct request_queue *q) * different from running_idx, which means flush is in flight. */ q->flush_pending_idx ^= 1; + if (q->mq_ops) { - mq_run_flush(q); - return true; + struct blk_mq_ctx *ctx = first_rq->mq_ctx; + struct blk_mq_hw_ctx *hctx = q->mq_ops->map_queue(q, ctx->cpu); + + blk_mq_rq_init(hctx, q->flush_rq); + q->flush_rq->mq_ctx = ctx; + + /* + * Reuse the tag value from the fist waiting request, + * with blk-mq the tag is generated during request + * allocation and drivers can rely on it being inside + * the range they asked for. + */ + q->flush_rq->tag = first_rq->tag; + } else { + blk_rq_init(q, q->flush_rq); } - blk_rq_init(q, &q->flush_rq); - q->flush_rq.cmd_type = REQ_TYPE_FS; - q->flush_rq.cmd_flags = WRITE_FLUSH | REQ_FLUSH_SEQ; - q->flush_rq.rq_disk = first_rq->rq_disk; - q->flush_rq.end_io = flush_end_io; + q->flush_rq->cmd_type = REQ_TYPE_FS; + q->flush_rq->cmd_flags = WRITE_FLUSH | REQ_FLUSH_SEQ; + q->flush_rq->rq_disk = first_rq->rq_disk; + q->flush_rq->end_io = flush_end_io; - list_add_tail(&q->flush_rq.queuelist, &q->queue_head); - return true; + return blk_flush_queue_rq(q->flush_rq); } static void flush_data_end_io(struct request *rq, int error) @@ -558,5 +532,4 @@ EXPORT_SYMBOL(blkdev_issue_flush); void blk_mq_init_flush(struct request_queue *q) { spin_lock_init(&q->mq_flush_lock); - INIT_WORK(&q->mq_flush_work, mq_flush_work); } diff --git a/block/blk-lib.c b/block/blk-lib.c index 2da76c999ef3..97a733cf3d5f 100644 --- a/block/blk-lib.c +++ b/block/blk-lib.c @@ -119,6 +119,14 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector, atomic_inc(&bb.done); submit_bio(type, bio); + + /* + * We can loop for a long time in here, if someone does + * full device discards (like mkfs). Be nice and allow + * us to schedule out to avoid softlocking if preempt + * is disabled. + */ + cond_resched(); } blk_finish_plug(&plug); diff --git a/block/blk-merge.c b/block/blk-merge.c index 8f8adaa95466..6c583f9c5b65 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -21,6 +21,16 @@ static unsigned int __blk_recalc_rq_segments(struct request_queue *q, if (!bio) return 0; + /* + * This should probably be returning 0, but blk_add_request_payload() + * (Christoph!!!!) + */ + if (bio->bi_rw & REQ_DISCARD) + return 1; + + if (bio->bi_rw & REQ_WRITE_SAME) + return 1; + fbio = bio; cluster = blk_queue_cluster(q); seg_size = 0; @@ -161,30 +171,60 @@ new_segment: *bvprv = *bvec; } -/* - * map a request to scatterlist, return number of sg entries setup. Caller - * must make sure sg can hold rq->nr_phys_segments entries - */ -int blk_rq_map_sg(struct request_queue *q, struct request *rq, - struct scatterlist *sglist) +static int __blk_bios_map_sg(struct request_queue *q, struct bio *bio, + struct scatterlist *sglist, + struct scatterlist **sg) { struct bio_vec bvec, bvprv = { NULL }; - struct req_iterator iter; - struct scatterlist *sg; + struct bvec_iter iter; int nsegs, cluster; nsegs = 0; cluster = blk_queue_cluster(q); - /* - * for each bio in rq - */ - sg = NULL; - rq_for_each_segment(bvec, rq, iter) { - __blk_segment_map_sg(q, &bvec, sglist, &bvprv, &sg, - &nsegs, &cluster); - } /* segments in rq */ + if (bio->bi_rw & REQ_DISCARD) { + /* + * This is a hack - drivers should be neither modifying the + * biovec, nor relying on bi_vcnt - but because of + * blk_add_request_payload(), a discard bio may or may not have + * a payload we need to set up here (thank you Christoph) and + * bi_vcnt is really the only way of telling if we need to. + */ + + if (bio->bi_vcnt) + goto single_segment; + + return 0; + } + + if (bio->bi_rw & REQ_WRITE_SAME) { +single_segment: + *sg = sglist; + bvec = bio_iovec(bio); + sg_set_page(*sg, bvec.bv_page, bvec.bv_len, bvec.bv_offset); + return 1; + } + + for_each_bio(bio) + bio_for_each_segment(bvec, bio, iter) + __blk_segment_map_sg(q, &bvec, sglist, &bvprv, sg, + &nsegs, &cluster); + return nsegs; +} + +/* + * map a request to scatterlist, return number of sg entries setup. Caller + * must make sure sg can hold rq->nr_phys_segments entries + */ +int blk_rq_map_sg(struct request_queue *q, struct request *rq, + struct scatterlist *sglist) +{ + struct scatterlist *sg = NULL; + int nsegs = 0; + + if (rq->bio) + nsegs = __blk_bios_map_sg(q, rq->bio, sglist, &sg); if (unlikely(rq->cmd_flags & REQ_COPY_USER) && (blk_rq_bytes(rq) & q->dma_pad_mask)) { @@ -230,20 +270,13 @@ EXPORT_SYMBOL(blk_rq_map_sg); int blk_bio_map_sg(struct request_queue *q, struct bio *bio, struct scatterlist *sglist) { - struct bio_vec bvec, bvprv = { NULL }; - struct scatterlist *sg; - int nsegs, cluster; - struct bvec_iter iter; - - nsegs = 0; - cluster = blk_queue_cluster(q); - - sg = NULL; - bio_for_each_segment(bvec, bio, iter) { - __blk_segment_map_sg(q, &bvec, sglist, &bvprv, &sg, - &nsegs, &cluster); - } /* segments in bio */ + struct scatterlist *sg = NULL; + int nsegs; + struct bio *next = bio->bi_next; + bio->bi_next = NULL; + nsegs = __blk_bios_map_sg(q, bio, sglist, &sg); + bio->bi_next = next; if (sg) sg_mark_end(sg); diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index 5d70edc9855f..83ae96c51a27 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -184,7 +184,7 @@ void blk_mq_free_tags(struct blk_mq_tags *tags) ssize_t blk_mq_tag_sysfs_show(struct blk_mq_tags *tags, char *page) { char *orig_page = page; - int cpu; + unsigned int cpu; if (!tags) return 0; diff --git a/block/blk-mq.c b/block/blk-mq.c index 57039fcd9c93..1fa9dd153fde 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -226,15 +226,14 @@ static struct request *blk_mq_alloc_request_pinned(struct request_queue *q, return rq; } -struct request *blk_mq_alloc_request(struct request_queue *q, int rw, - gfp_t gfp, bool reserved) +struct request *blk_mq_alloc_request(struct request_queue *q, int rw, gfp_t gfp) { struct request *rq; if (blk_mq_queue_enter(q)) return NULL; - rq = blk_mq_alloc_request_pinned(q, rw, gfp, reserved); + rq = blk_mq_alloc_request_pinned(q, rw, gfp, false); if (rq) blk_mq_put_ctx(rq->mq_ctx); return rq; @@ -258,7 +257,7 @@ EXPORT_SYMBOL(blk_mq_alloc_reserved_request); /* * Re-init and set pdu, if we have it */ -static void blk_mq_rq_init(struct blk_mq_hw_ctx *hctx, struct request *rq) +void blk_mq_rq_init(struct blk_mq_hw_ctx *hctx, struct request *rq) { blk_rq_init(hctx->queue, rq); @@ -305,7 +304,7 @@ static void blk_mq_bio_endio(struct request *rq, struct bio *bio, int error) bio_endio(bio, error); } -void blk_mq_complete_request(struct request *rq, int error) +void blk_mq_end_io(struct request *rq, int error) { struct bio *bio = rq->bio; unsigned int bytes = 0; @@ -330,48 +329,55 @@ void blk_mq_complete_request(struct request *rq, int error) else blk_mq_free_request(rq); } +EXPORT_SYMBOL(blk_mq_end_io); -void __blk_mq_end_io(struct request *rq, int error) -{ - if (!blk_mark_rq_complete(rq)) - blk_mq_complete_request(rq, error); -} - -static void blk_mq_end_io_remote(void *data) +static void __blk_mq_complete_request_remote(void *data) { struct request *rq = data; - __blk_mq_end_io(rq, rq->errors); + rq->q->softirq_done_fn(rq); } -/* - * End IO on this request on a multiqueue enabled driver. We'll either do - * it directly inline, or punt to a local IPI handler on the matching - * remote CPU. - */ -void blk_mq_end_io(struct request *rq, int error) +void __blk_mq_complete_request(struct request *rq) { struct blk_mq_ctx *ctx = rq->mq_ctx; int cpu; - if (!ctx->ipi_redirect) - return __blk_mq_end_io(rq, error); + if (!ctx->ipi_redirect) { + rq->q->softirq_done_fn(rq); + return; + } cpu = get_cpu(); if (cpu != ctx->cpu && cpu_online(ctx->cpu)) { - rq->errors = error; - rq->csd.func = blk_mq_end_io_remote; + rq->csd.func = __blk_mq_complete_request_remote; rq->csd.info = rq; rq->csd.flags = 0; __smp_call_function_single(ctx->cpu, &rq->csd, 0); } else { - __blk_mq_end_io(rq, error); + rq->q->softirq_done_fn(rq); } put_cpu(); } -EXPORT_SYMBOL(blk_mq_end_io); -static void blk_mq_start_request(struct request *rq) +/** + * blk_mq_complete_request - end I/O on a request + * @rq: the request being processed + * + * Description: + * Ends all I/O on a request. It does not handle partial completions. + * The actual completion happens out-of-order, through a IPI handler. + **/ +void blk_mq_complete_request(struct request *rq) +{ + if (unlikely(blk_should_fake_timeout(rq->q))) + return; + if (!blk_mark_rq_complete(rq)) + __blk_mq_complete_request(rq); +} +EXPORT_SYMBOL(blk_mq_complete_request); + +static void blk_mq_start_request(struct request *rq, bool last) { struct request_queue *q = rq->q; @@ -384,6 +390,25 @@ static void blk_mq_start_request(struct request *rq) */ rq->deadline = jiffies + q->rq_timeout; set_bit(REQ_ATOM_STARTED, &rq->atomic_flags); + + if (q->dma_drain_size && blk_rq_bytes(rq)) { + /* + * Make sure space for the drain appears. We know we can do + * this because max_hw_segments has been adjusted to be one + * fewer than the device can handle. + */ + rq->nr_phys_segments++; + } + + /* + * Flag the last request in the series so that drivers know when IO + * should be kicked off, if they don't do it on a per-request basis. + * + * Note: the flag isn't the only condition drivers should do kick off. + * If drive is busy, the last request might not have the bit set. + */ + if (last) + rq->cmd_flags |= REQ_END; } static void blk_mq_requeue_request(struct request *rq) @@ -392,6 +417,11 @@ static void blk_mq_requeue_request(struct request *rq) trace_block_rq_requeue(q, rq); clear_bit(REQ_ATOM_STARTED, &rq->atomic_flags); + + rq->cmd_flags &= ~REQ_END; + + if (q->dma_drain_size && blk_rq_bytes(rq)) + rq->nr_phys_segments--; } struct blk_mq_timeout_data { @@ -559,19 +589,8 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx) rq = list_first_entry(&rq_list, struct request, queuelist); list_del_init(&rq->queuelist); - blk_mq_start_request(rq); - /* - * Last request in the series. Flag it as such, this - * enables drivers to know when IO should be kicked off, - * if they don't do it on a per-request basis. - * - * Note: the flag isn't the only condition drivers - * should do kick off. If drive is busy, the last - * request might not have the bit set. - */ - if (list_empty(&rq_list)) - rq->cmd_flags |= REQ_END; + blk_mq_start_request(rq, list_empty(&rq_list)); ret = q->mq_ops->queue_rq(hctx, rq); switch (ret) { @@ -589,8 +608,8 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx) break; default: pr_err("blk-mq: bad return on queue: %d\n", ret); - rq->errors = -EIO; case BLK_MQ_RQ_QUEUE_ERROR: + rq->errors = -EIO; blk_mq_end_io(rq, rq->errors); break; } @@ -693,13 +712,16 @@ static void blk_mq_work_fn(struct work_struct *work) } static void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, - struct request *rq) + struct request *rq, bool at_head) { struct blk_mq_ctx *ctx = rq->mq_ctx; trace_block_rq_insert(hctx->queue, rq); - list_add_tail(&rq->queuelist, &ctx->rq_list); + if (at_head) + list_add(&rq->queuelist, &ctx->rq_list); + else + list_add_tail(&rq->queuelist, &ctx->rq_list); blk_mq_hctx_mark_pending(hctx, ctx); /* @@ -709,7 +731,7 @@ static void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, } void blk_mq_insert_request(struct request_queue *q, struct request *rq, - bool run_queue) + bool at_head, bool run_queue) { struct blk_mq_hw_ctx *hctx; struct blk_mq_ctx *ctx, *current_ctx; @@ -728,7 +750,7 @@ void blk_mq_insert_request(struct request_queue *q, struct request *rq, rq->mq_ctx = ctx; } spin_lock(&ctx->lock); - __blk_mq_insert_request(hctx, rq); + __blk_mq_insert_request(hctx, rq, at_head); spin_unlock(&ctx->lock); blk_mq_put_ctx(current_ctx); @@ -760,7 +782,7 @@ void blk_mq_run_request(struct request *rq, bool run_queue, bool async) /* ctx->cpu might be offline */ spin_lock(&ctx->lock); - __blk_mq_insert_request(hctx, rq); + __blk_mq_insert_request(hctx, rq, false); spin_unlock(&ctx->lock); blk_mq_put_ctx(current_ctx); @@ -798,7 +820,7 @@ static void blk_mq_insert_requests(struct request_queue *q, rq = list_first_entry(list, struct request, queuelist); list_del_init(&rq->queuelist); rq->mq_ctx = ctx; - __blk_mq_insert_request(hctx, rq); + __blk_mq_insert_request(hctx, rq, false); } spin_unlock(&ctx->lock); @@ -888,6 +910,11 @@ static void blk_mq_make_request(struct request_queue *q, struct bio *bio) blk_queue_bounce(q, &bio); + if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) { + bio_endio(bio, -EIO); + return; + } + if (use_plug && blk_attempt_plug_merge(q, bio, &request_count)) return; @@ -950,7 +977,7 @@ static void blk_mq_make_request(struct request_queue *q, struct bio *bio) __blk_mq_free_request(hctx, ctx, rq); else { blk_mq_bio_to_request(rq, bio); - __blk_mq_insert_request(hctx, rq); + __blk_mq_insert_request(hctx, rq, false); } spin_unlock(&ctx->lock); @@ -1309,15 +1336,6 @@ struct request_queue *blk_mq_init_queue(struct blk_mq_reg *reg, reg->queue_depth = BLK_MQ_MAX_DEPTH; } - /* - * Set aside a tag for flush requests. It will only be used while - * another flush request is in progress but outside the driver. - * - * TODO: only allocate if flushes are supported - */ - reg->queue_depth++; - reg->reserved_tags++; - if (reg->queue_depth < (reg->reserved_tags + BLK_MQ_TAG_MIN)) return ERR_PTR(-EINVAL); @@ -1360,17 +1378,27 @@ struct request_queue *blk_mq_init_queue(struct blk_mq_reg *reg, q->mq_ops = reg->ops; q->queue_flags |= QUEUE_FLAG_MQ_DEFAULT; + q->sg_reserved_size = INT_MAX; + blk_queue_make_request(q, blk_mq_make_request); blk_queue_rq_timed_out(q, reg->ops->timeout); if (reg->timeout) blk_queue_rq_timeout(q, reg->timeout); + if (reg->ops->complete) + blk_queue_softirq_done(q, reg->ops->complete); + blk_mq_init_flush(q); blk_mq_init_cpu_queues(q, reg->nr_hw_queues); - if (blk_mq_init_hw_queues(q, reg, driver_data)) + q->flush_rq = kzalloc(round_up(sizeof(struct request) + reg->cmd_size, + cache_line_size()), GFP_KERNEL); + if (!q->flush_rq) goto err_hw; + if (blk_mq_init_hw_queues(q, reg, driver_data)) + goto err_flush_rq; + blk_mq_map_swqueue(q); mutex_lock(&all_q_mutex); @@ -1378,6 +1406,9 @@ struct request_queue *blk_mq_init_queue(struct blk_mq_reg *reg, mutex_unlock(&all_q_mutex); return q; + +err_flush_rq: + kfree(q->flush_rq); err_hw: kfree(q->mq_map); err_map: diff --git a/block/blk-mq.h b/block/blk-mq.h index 5c3917984b00..ed0035cd458e 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -22,13 +22,13 @@ struct blk_mq_ctx { struct kobject kobj; }; -void __blk_mq_end_io(struct request *rq, int error); -void blk_mq_complete_request(struct request *rq, int error); +void __blk_mq_complete_request(struct request *rq); void blk_mq_run_request(struct request *rq, bool run_queue, bool async); void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async); void blk_mq_init_flush(struct request_queue *q); void blk_mq_drain_queue(struct request_queue *q); void blk_mq_free_queue(struct request_queue *q); +void blk_mq_rq_init(struct blk_mq_hw_ctx *hctx, struct request *rq); /* * CPU hotplug helpers diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 8095c4a21fc0..7500f876dae4 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -549,6 +549,8 @@ static void blk_release_queue(struct kobject *kobj) if (q->mq_ops) blk_mq_free_queue(q); + kfree(q->flush_rq); + blk_trace_shutdown(q); bdi_destroy(&q->backing_dev_info); diff --git a/block/blk-timeout.c b/block/blk-timeout.c index bba81c9348e1..d96f7061c6fd 100644 --- a/block/blk-timeout.c +++ b/block/blk-timeout.c @@ -91,7 +91,7 @@ static void blk_rq_timed_out(struct request *req) case BLK_EH_HANDLED: /* Can we use req->errors here? */ if (q->mq_ops) - blk_mq_complete_request(req, req->errors); + __blk_mq_complete_request(req); else __blk_complete_request(req); break; diff --git a/block/blk.h b/block/blk.h index c90e1d8f7a2b..d23b415b8a28 100644 --- a/block/blk.h +++ b/block/blk.h @@ -113,7 +113,7 @@ static inline struct request *__elv_next_request(struct request_queue *q) q->flush_queue_delayed = 1; return NULL; } - if (unlikely(blk_queue_dying(q)) || + if (unlikely(blk_queue_bypass(q)) || !q->elevator->type->ops.elevator_dispatch_fn(q, 0)) return NULL; } diff --git a/drivers/acpi/ac.c b/drivers/acpi/ac.c index e7515aa43d6b..6f190bc2b8b7 100644 --- a/drivers/acpi/ac.c +++ b/drivers/acpi/ac.c @@ -243,6 +243,8 @@ static int acpi_ac_resume(struct device *dev) kobject_uevent(&ac->charger.dev->kobj, KOBJ_CHANGE); return 0; } +#else +#define acpi_ac_resume NULL #endif static SIMPLE_DEV_PM_OPS(acpi_ac_pm_ops, NULL, acpi_ac_resume); diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c index 018a42883706..797a6938d051 100644 --- a/drivers/acpi/battery.c +++ b/drivers/acpi/battery.c @@ -841,6 +841,8 @@ static int acpi_battery_resume(struct device *dev) acpi_battery_update(battery); return 0; } +#else +#define acpi_battery_resume NULL #endif static SIMPLE_DEV_PM_OPS(acpi_battery_pm, NULL, acpi_battery_resume); diff --git a/drivers/acpi/blacklist.c b/drivers/acpi/blacklist.c index 10e4964d051a..afec4526c48a 100644 --- a/drivers/acpi/blacklist.c +++ b/drivers/acpi/blacklist.c @@ -260,14 +260,6 @@ static struct dmi_system_id acpi_osi_dmi_table[] __initdata = { }, { .callback = dmi_disable_osi_win8, - .ident = "Dell Inspiron 15R SE", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), - DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 7520"), - }, - }, - { - .callback = dmi_disable_osi_win8, .ident = "ThinkPad Edge E530", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), @@ -322,56 +314,6 @@ static struct dmi_system_id acpi_osi_dmi_table[] __initdata = { DMI_MATCH(DMI_PRODUCT_VERSION, "2349D15"), }, }, - { - .callback = dmi_disable_osi_win8, - .ident = "HP ProBook 2013 models", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), - DMI_MATCH(DMI_PRODUCT_NAME, "HP ProBook "), - DMI_MATCH(DMI_PRODUCT_NAME, " G1"), - }, - }, - { - .callback = dmi_disable_osi_win8, - .ident = "HP EliteBook 2013 models", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), - DMI_MATCH(DMI_PRODUCT_NAME, "HP EliteBook "), - DMI_MATCH(DMI_PRODUCT_NAME, " G1"), - }, - }, - { - .callback = dmi_disable_osi_win8, - .ident = "HP ZBook 14", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), - DMI_MATCH(DMI_PRODUCT_NAME, "HP ZBook 14"), - }, - }, - { - .callback = dmi_disable_osi_win8, - .ident = "HP ZBook 15", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), - DMI_MATCH(DMI_PRODUCT_NAME, "HP ZBook 15"), - }, - }, - { - .callback = dmi_disable_osi_win8, - .ident = "HP ZBook 17", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), - DMI_MATCH(DMI_PRODUCT_NAME, "HP ZBook 17"), - }, - }, - { - .callback = dmi_disable_osi_win8, - .ident = "HP EliteBook 8780w", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), - DMI_MATCH(DMI_PRODUCT_NAME, "HP EliteBook 8780w"), - }, - }, /* * BIOS invocation of _OSI(Linux) is almost always a BIOS bug. diff --git a/drivers/acpi/button.c b/drivers/acpi/button.c index 11c11f6b8fa1..714e957a871a 100644 --- a/drivers/acpi/button.c +++ b/drivers/acpi/button.c @@ -80,6 +80,8 @@ static void acpi_button_notify(struct acpi_device *device, u32 event); #ifdef CONFIG_PM_SLEEP static int acpi_button_resume(struct device *dev); +#else +#define acpi_button_resume NULL #endif static SIMPLE_DEV_PM_OPS(acpi_button_pm, NULL, acpi_button_resume); diff --git a/drivers/acpi/container.c b/drivers/acpi/container.c index 0b6ae6eb5c4a..368f9ddb8480 100644 --- a/drivers/acpi/container.c +++ b/drivers/acpi/container.c @@ -79,9 +79,10 @@ static int container_device_attach(struct acpi_device *adev, ACPI_COMPANION_SET(dev, adev); dev->release = acpi_container_release; ret = device_register(dev); - if (ret) + if (ret) { + put_device(dev); return ret; - + } adev->driver_data = dev; return 1; } diff --git a/drivers/acpi/dock.c b/drivers/acpi/dock.c index c431c88faaff..5bfd769fc91f 100644 --- a/drivers/acpi/dock.c +++ b/drivers/acpi/dock.c @@ -609,7 +609,7 @@ static int handle_eject_request(struct dock_station *ds, u32 event) static void dock_notify(struct dock_station *ds, u32 event) { acpi_handle handle = ds->handle; - struct acpi_device *ad; + struct acpi_device *adev = NULL; int surprise_removal = 0; /* @@ -632,7 +632,8 @@ static void dock_notify(struct dock_station *ds, u32 event) switch (event) { case ACPI_NOTIFY_BUS_CHECK: case ACPI_NOTIFY_DEVICE_CHECK: - if (!dock_in_progress(ds) && acpi_bus_get_device(handle, &ad)) { + acpi_bus_get_device(handle, &adev); + if (!dock_in_progress(ds) && !acpi_device_enumerated(adev)) { begin_dock(ds); dock(ds); if (!dock_present(ds)) { @@ -712,13 +713,11 @@ static acpi_status __init find_dock_devices(acpi_handle handle, u32 lvl, static ssize_t show_docked(struct device *dev, struct device_attribute *attr, char *buf) { - struct acpi_device *tmp; - struct dock_station *dock_station = dev->platform_data; + struct acpi_device *adev = NULL; - if (!acpi_bus_get_device(dock_station->handle, &tmp)) - return snprintf(buf, PAGE_SIZE, "1\n"); - return snprintf(buf, PAGE_SIZE, "0\n"); + acpi_bus_get_device(dock_station->handle, &adev); + return snprintf(buf, PAGE_SIZE, "%u\n", acpi_device_enumerated(adev)); } static DEVICE_ATTR(docked, S_IRUGO, show_docked, NULL); diff --git a/drivers/acpi/fan.c b/drivers/acpi/fan.c index 1fb62900f32a..09e423f3d8ad 100644 --- a/drivers/acpi/fan.c +++ b/drivers/acpi/fan.c @@ -55,6 +55,9 @@ MODULE_DEVICE_TABLE(acpi, fan_device_ids); #ifdef CONFIG_PM_SLEEP static int acpi_fan_suspend(struct device *dev); static int acpi_fan_resume(struct device *dev); +#else +#define acpi_fan_suspend NULL +#define acpi_fan_resume NULL #endif static SIMPLE_DEV_PM_OPS(acpi_fan_pm, acpi_fan_suspend, acpi_fan_resume); diff --git a/drivers/acpi/pci_irq.c b/drivers/acpi/pci_irq.c index 52d45ea2bc4f..361b40c10c3f 100644 --- a/drivers/acpi/pci_irq.c +++ b/drivers/acpi/pci_irq.c @@ -430,6 +430,7 @@ int acpi_pci_irq_enable(struct pci_dev *dev) pin_name(pin)); } + kfree(entry); return 0; } diff --git a/drivers/acpi/processor_throttling.c b/drivers/acpi/processor_throttling.c index 28baa05b8018..84243c32e29c 100644 --- a/drivers/acpi/processor_throttling.c +++ b/drivers/acpi/processor_throttling.c @@ -56,6 +56,12 @@ struct throttling_tstate { int target_state; /* target T-state */ }; +struct acpi_processor_throttling_arg { + struct acpi_processor *pr; + int target_state; + bool force; +}; + #define THROTTLING_PRECHANGE (1) #define THROTTLING_POSTCHANGE (2) @@ -1060,16 +1066,24 @@ static int acpi_processor_set_throttling_ptc(struct acpi_processor *pr, return 0; } +static long acpi_processor_throttling_fn(void *data) +{ + struct acpi_processor_throttling_arg *arg = data; + struct acpi_processor *pr = arg->pr; + + return pr->throttling.acpi_processor_set_throttling(pr, + arg->target_state, arg->force); +} + int acpi_processor_set_throttling(struct acpi_processor *pr, int state, bool force) { - cpumask_var_t saved_mask; int ret = 0; unsigned int i; struct acpi_processor *match_pr; struct acpi_processor_throttling *p_throttling; + struct acpi_processor_throttling_arg arg; struct throttling_tstate t_state; - cpumask_var_t online_throttling_cpus; if (!pr) return -EINVAL; @@ -1080,14 +1094,6 @@ int acpi_processor_set_throttling(struct acpi_processor *pr, if ((state < 0) || (state > (pr->throttling.state_count - 1))) return -EINVAL; - if (!alloc_cpumask_var(&saved_mask, GFP_KERNEL)) - return -ENOMEM; - - if (!alloc_cpumask_var(&online_throttling_cpus, GFP_KERNEL)) { - free_cpumask_var(saved_mask); - return -ENOMEM; - } - if (cpu_is_offline(pr->id)) { /* * the cpu pointed by pr->id is offline. Unnecessary to change @@ -1096,17 +1102,15 @@ int acpi_processor_set_throttling(struct acpi_processor *pr, return -ENODEV; } - cpumask_copy(saved_mask, ¤t->cpus_allowed); t_state.target_state = state; p_throttling = &(pr->throttling); - cpumask_and(online_throttling_cpus, cpu_online_mask, - p_throttling->shared_cpu_map); + /* * The throttling notifier will be called for every * affected cpu in order to get one proper T-state. * The notifier event is THROTTLING_PRECHANGE. */ - for_each_cpu(i, online_throttling_cpus) { + for_each_cpu_and(i, cpu_online_mask, p_throttling->shared_cpu_map) { t_state.cpu = i; acpi_processor_throttling_notifier(THROTTLING_PRECHANGE, &t_state); @@ -1118,21 +1122,18 @@ int acpi_processor_set_throttling(struct acpi_processor *pr, * it can be called only for the cpu pointed by pr. */ if (p_throttling->shared_type == DOMAIN_COORD_TYPE_SW_ANY) { - /* FIXME: use work_on_cpu() */ - if (set_cpus_allowed_ptr(current, cpumask_of(pr->id))) { - /* Can't migrate to the pr->id CPU. Exit */ - ret = -ENODEV; - goto exit; - } - ret = p_throttling->acpi_processor_set_throttling(pr, - t_state.target_state, force); + arg.pr = pr; + arg.target_state = state; + arg.force = force; + ret = work_on_cpu(pr->id, acpi_processor_throttling_fn, &arg); } else { /* * When the T-state coordination is SW_ALL or HW_ALL, * it is necessary to set T-state for every affected * cpus. */ - for_each_cpu(i, online_throttling_cpus) { + for_each_cpu_and(i, cpu_online_mask, + p_throttling->shared_cpu_map) { match_pr = per_cpu(processors, i); /* * If the pointer is invalid, we will report the @@ -1153,13 +1154,12 @@ int acpi_processor_set_throttling(struct acpi_processor *pr, "on CPU %d\n", i)); continue; } - t_state.cpu = i; - /* FIXME: use work_on_cpu() */ - if (set_cpus_allowed_ptr(current, cpumask_of(i))) - continue; - ret = match_pr->throttling. - acpi_processor_set_throttling( - match_pr, t_state.target_state, force); + + arg.pr = match_pr; + arg.target_state = state; + arg.force = force; + ret = work_on_cpu(pr->id, acpi_processor_throttling_fn, + &arg); } } /* @@ -1168,17 +1168,12 @@ int acpi_processor_set_throttling(struct acpi_processor *pr, * affected cpu to update the T-states. * The notifier event is THROTTLING_POSTCHANGE */ - for_each_cpu(i, online_throttling_cpus) { + for_each_cpu_and(i, cpu_online_mask, p_throttling->shared_cpu_map) { t_state.cpu = i; acpi_processor_throttling_notifier(THROTTLING_POSTCHANGE, &t_state); } - /* restore the previous state */ - /* FIXME: use work_on_cpu() */ - set_cpus_allowed_ptr(current, saved_mask); -exit: - free_cpumask_var(online_throttling_cpus); - free_cpumask_var(saved_mask); + return ret; } diff --git a/drivers/acpi/sbs.c b/drivers/acpi/sbs.c index d465ae6cdd00..dbd48498b938 100644 --- a/drivers/acpi/sbs.c +++ b/drivers/acpi/sbs.c @@ -450,7 +450,7 @@ static ssize_t acpi_battery_alarm_store(struct device *dev, { unsigned long x; struct acpi_battery *battery = to_acpi_battery(dev_get_drvdata(dev)); - if (sscanf(buf, "%ld\n", &x) == 1) + if (sscanf(buf, "%lu\n", &x) == 1) battery->alarm_capacity = x / (1000 * acpi_battery_scale(battery)); if (battery->present) @@ -668,6 +668,8 @@ static int acpi_sbs_resume(struct device *dev) acpi_sbs_callback(sbs); return 0; } +#else +#define acpi_sbs_resume NULL #endif static SIMPLE_DEV_PM_OPS(acpi_sbs_pm, NULL, acpi_sbs_resume); diff --git a/drivers/acpi/thermal.c b/drivers/acpi/thermal.c index 8349a555b92b..08626c851be7 100644 --- a/drivers/acpi/thermal.c +++ b/drivers/acpi/thermal.c @@ -102,6 +102,8 @@ MODULE_DEVICE_TABLE(acpi, thermal_device_ids); #ifdef CONFIG_PM_SLEEP static int acpi_thermal_resume(struct device *dev); +#else +#define acpi_thermal_resume NULL #endif static SIMPLE_DEV_PM_OPS(acpi_thermal_pm, NULL, acpi_thermal_resume); diff --git a/drivers/acpi/video.c b/drivers/acpi/video.c index b727d105046d..b6ba88ed31ae 100644 --- a/drivers/acpi/video.c +++ b/drivers/acpi/video.c @@ -81,11 +81,12 @@ static bool allow_duplicates; module_param(allow_duplicates, bool, 0644); /* - * For Windows 8 systems: if set ture and the GPU driver has - * registered a backlight interface, skip registering ACPI video's. + * For Windows 8 systems: used to decide if video module + * should skip registering backlight interface of its own. */ -static bool use_native_backlight = false; -module_param(use_native_backlight, bool, 0644); +static int use_native_backlight_param = -1; +module_param_named(use_native_backlight, use_native_backlight_param, int, 0444); +static bool use_native_backlight_dmi = false; static int register_count; static struct mutex video_list_lock; @@ -231,9 +232,17 @@ static int acpi_video_get_next_level(struct acpi_video_device *device, static int acpi_video_switch_brightness(struct acpi_video_device *device, int event); +static bool acpi_video_use_native_backlight(void) +{ + if (use_native_backlight_param != -1) + return use_native_backlight_param; + else + return use_native_backlight_dmi; +} + static bool acpi_video_verify_backlight_support(void) { - if (acpi_osi_is_win8() && use_native_backlight && + if (acpi_osi_is_win8() && acpi_video_use_native_backlight() && backlight_device_registered(BACKLIGHT_RAW)) return false; return acpi_video_backlight_support(); @@ -398,6 +407,12 @@ static int __init video_set_bqc_offset(const struct dmi_system_id *d) return 0; } +static int __init video_set_use_native_backlight(const struct dmi_system_id *d) +{ + use_native_backlight_dmi = true; + return 0; +} + static struct dmi_system_id video_dmi_table[] __initdata = { /* * Broken _BQC workaround http://bugzilla.kernel.org/show_bug.cgi?id=13121 @@ -442,6 +457,120 @@ static struct dmi_system_id video_dmi_table[] __initdata = { DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 7720"), }, }, + { + .callback = video_set_use_native_backlight, + .ident = "ThinkPad T430s", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T430s"), + }, + }, + { + .callback = video_set_use_native_backlight, + .ident = "ThinkPad X230", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad X230"), + }, + }, + { + .callback = video_set_use_native_backlight, + .ident = "ThinkPad X1 Carbon", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad X1 Carbon"), + }, + }, + { + .callback = video_set_use_native_backlight, + .ident = "Lenovo Yoga 13", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo IdeaPad Yoga 13"), + }, + }, + { + .callback = video_set_use_native_backlight, + .ident = "Dell Inspiron 7520", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_VERSION, "Inspiron 7520"), + }, + }, + { + .callback = video_set_use_native_backlight, + .ident = "Acer Aspire 5733Z", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5733Z"), + }, + }, + { + .callback = video_set_use_native_backlight, + .ident = "Acer Aspire V5-431", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Aspire V5-431"), + }, + }, + { + .callback = video_set_use_native_backlight, + .ident = "HP ProBook 4340s", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), + DMI_MATCH(DMI_PRODUCT_VERSION, "HP ProBook 4340s"), + }, + }, + { + .callback = video_set_use_native_backlight, + .ident = "HP ProBook 2013 models", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), + DMI_MATCH(DMI_PRODUCT_NAME, "HP ProBook "), + DMI_MATCH(DMI_PRODUCT_NAME, " G1"), + }, + }, + { + .callback = video_set_use_native_backlight, + .ident = "HP EliteBook 2013 models", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), + DMI_MATCH(DMI_PRODUCT_NAME, "HP EliteBook "), + DMI_MATCH(DMI_PRODUCT_NAME, " G1"), + }, + }, + { + .callback = video_set_use_native_backlight, + .ident = "HP ZBook 14", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), + DMI_MATCH(DMI_PRODUCT_NAME, "HP ZBook 14"), + }, + }, + { + .callback = video_set_use_native_backlight, + .ident = "HP ZBook 15", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), + DMI_MATCH(DMI_PRODUCT_NAME, "HP ZBook 15"), + }, + }, + { + .callback = video_set_use_native_backlight, + .ident = "HP ZBook 17", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), + DMI_MATCH(DMI_PRODUCT_NAME, "HP ZBook 17"), + }, + }, + { + .callback = video_set_use_native_backlight, + .ident = "HP EliteBook 8780w", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), + DMI_MATCH(DMI_PRODUCT_NAME, "HP EliteBook 8780w"), + }, + }, {} }; @@ -685,6 +814,7 @@ acpi_video_init_brightness(struct acpi_video_device *device) union acpi_object *o; struct acpi_video_device_brightness *br = NULL; int result = -EINVAL; + u32 value; if (!ACPI_SUCCESS(acpi_video_device_lcd_query_levels(device, &obj))) { ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Could not query available " @@ -715,7 +845,12 @@ acpi_video_init_brightness(struct acpi_video_device *device) printk(KERN_ERR PREFIX "Invalid data\n"); continue; } - br->levels[count] = (u32) o->integer.value; + value = (u32) o->integer.value; + /* Skip duplicate entries */ + if (count > 2 && br->levels[count - 1] == value) + continue; + + br->levels[count] = value; if (br->levels[count] > max_level) max_level = br->levels[count]; diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c index a697b77b8865..19080c8e2f2a 100644 --- a/drivers/acpi/video_detect.c +++ b/drivers/acpi/video_detect.c @@ -168,22 +168,6 @@ static struct dmi_system_id video_detect_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "UL30A"), }, }, - { - .callback = video_detect_force_vendor, - .ident = "HP EliteBook Revolve 810", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), - DMI_MATCH(DMI_PRODUCT_NAME, "HP EliteBook Revolve 810 G1"), - }, - }, - { - .callback = video_detect_force_vendor, - .ident = "Lenovo Yoga 13", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), - DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo IdeaPad Yoga 13"), - }, - }, { }, }; diff --git a/drivers/ata/Kconfig b/drivers/ata/Kconfig index 4e737728aee2..868429a47be4 100644 --- a/drivers/ata/Kconfig +++ b/drivers/ata/Kconfig @@ -247,6 +247,7 @@ config SATA_HIGHBANK config SATA_MV tristate "Marvell SATA support" + select GENERIC_PHY help This option enables support for the Marvell Serial ATA family. Currently supports 88SX[56]0[48][01] PCI(-X) chips, diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index dc2756fb6f33..c81d809c111b 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -61,6 +61,7 @@ enum board_ids { /* board IDs by feature in alphabetical order */ board_ahci, board_ahci_ign_iferr, + board_ahci_noncq, board_ahci_nosntf, board_ahci_yes_fbs, @@ -121,6 +122,13 @@ static const struct ata_port_info ahci_port_info[] = { .udma_mask = ATA_UDMA6, .port_ops = &ahci_ops, }, + [board_ahci_noncq] = { + AHCI_HFLAGS (AHCI_HFLAG_NO_NCQ), + .flags = AHCI_FLAG_COMMON, + .pio_mask = ATA_PIO4, + .udma_mask = ATA_UDMA6, + .port_ops = &ahci_ops, + }, [board_ahci_nosntf] = { AHCI_HFLAGS (AHCI_HFLAG_NO_SNTF), .flags = AHCI_FLAG_COMMON, @@ -452,6 +460,12 @@ static const struct pci_device_id ahci_pci_tbl[] = { { PCI_VDEVICE(ASMEDIA, 0x0611), board_ahci }, /* ASM1061 */ { PCI_VDEVICE(ASMEDIA, 0x0612), board_ahci }, /* ASM1062 */ + /* + * Samsung SSDs found on some macbooks. NCQ times out. + * https://bugzilla.kernel.org/show_bug.cgi?id=60731 + */ + { PCI_VDEVICE(SAMSUNG, 0x1600), board_ahci_noncq }, + /* Enmotus */ { PCI_DEVICE(0x1c44, 0x8000), board_ahci }, @@ -1170,8 +1184,10 @@ static int ahci_init_interrupts(struct pci_dev *pdev, unsigned int n_ports, nvec = rc; rc = pci_enable_msi_block(pdev, nvec); - if (rc) + if (rc < 0) goto intx; + else if (rc > 0) + goto single_msi; return nvec; diff --git a/drivers/ata/libata-pmp.c b/drivers/ata/libata-pmp.c index 20fd337a5731..7ccc084bf1df 100644 --- a/drivers/ata/libata-pmp.c +++ b/drivers/ata/libata-pmp.c @@ -447,8 +447,11 @@ static void sata_pmp_quirks(struct ata_port *ap) * otherwise. Don't try hard to recover it. */ ap->pmp_link[ap->nr_pmp_links - 1].flags |= ATA_LFLAG_NO_RETRY; - } else if (vendor == 0x197b && devid == 0x2352) { - /* chip found in Thermaltake BlackX Duet, jmicron JMB350? */ + } else if (vendor == 0x197b && (devid == 0x2352 || devid == 0x0325)) { + /* + * 0x2352: found in Thermaltake BlackX Duet, jmicron JMB350? + * 0x0325: jmicron JMB394. + */ ata_for_each_link(link, ap, EDGE) { /* SRST breaks detection and disks get misclassified * LPM disabled to avoid potential problems diff --git a/drivers/ata/pata_imx.c b/drivers/ata/pata_imx.c index 26386f0b89a8..b0b18ec5465f 100644 --- a/drivers/ata/pata_imx.c +++ b/drivers/ata/pata_imx.c @@ -119,7 +119,9 @@ static int pata_imx_probe(struct platform_device *pdev) return PTR_ERR(priv->clk); } - clk_prepare_enable(priv->clk); + ret = clk_prepare_enable(priv->clk); + if (ret) + return ret; host = ata_host_alloc(&pdev->dev, 1); if (!host) { @@ -212,7 +214,9 @@ static int pata_imx_resume(struct device *dev) struct ata_host *host = dev_get_drvdata(dev); struct pata_imx_priv *priv = host->private_data; - clk_prepare_enable(priv->clk); + int ret = clk_prepare_enable(priv->clk); + if (ret) + return ret; __raw_writel(priv->ata_ctl, priv->host_regs + PATA_IMX_ATA_CONTROL); diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c index 20a7517bd339..05c8a44adf8e 100644 --- a/drivers/ata/sata_mv.c +++ b/drivers/ata/sata_mv.c @@ -4104,7 +4104,6 @@ static int mv_platform_probe(struct platform_device *pdev) if (!hpriv->port_phys) return -ENOMEM; host->private_data = hpriv; - hpriv->n_ports = n_ports; hpriv->board_idx = chip_soc; host->iomap = NULL; @@ -4126,17 +4125,24 @@ static int mv_platform_probe(struct platform_device *pdev) clk_prepare_enable(hpriv->port_clks[port]); sprintf(port_number, "port%d", port); - hpriv->port_phys[port] = devm_phy_get(&pdev->dev, port_number); + hpriv->port_phys[port] = devm_phy_optional_get(&pdev->dev, + port_number); if (IS_ERR(hpriv->port_phys[port])) { rc = PTR_ERR(hpriv->port_phys[port]); hpriv->port_phys[port] = NULL; - if ((rc != -EPROBE_DEFER) && (rc != -ENODEV)) - dev_warn(&pdev->dev, "error getting phy"); + if (rc != -EPROBE_DEFER) + dev_warn(&pdev->dev, "error getting phy %d", rc); + + /* Cleanup only the initialized ports */ + hpriv->n_ports = port; goto err; } else phy_power_on(hpriv->port_phys[port]); } + /* All the ports have been initialized */ + hpriv->n_ports = n_ports; + /* * (Re-)program MBUS remapping windows if we are asked to. */ @@ -4174,7 +4180,7 @@ err: clk_disable_unprepare(hpriv->clk); clk_put(hpriv->clk); } - for (port = 0; port < n_ports; port++) { + for (port = 0; port < hpriv->n_ports; port++) { if (!IS_ERR(hpriv->port_clks[port])) { clk_disable_unprepare(hpriv->port_clks[port]); clk_put(hpriv->port_clks[port]); diff --git a/drivers/ata/sata_sil.c b/drivers/ata/sata_sil.c index d67fc351343c..b7695e804635 100644 --- a/drivers/ata/sata_sil.c +++ b/drivers/ata/sata_sil.c @@ -157,6 +157,7 @@ static const struct sil_drivelist { { "ST380011ASL", SIL_QUIRK_MOD15WRITE }, { "ST3120022ASL", SIL_QUIRK_MOD15WRITE }, { "ST3160021ASL", SIL_QUIRK_MOD15WRITE }, + { "TOSHIBA MK2561GSYN", SIL_QUIRK_MOD15WRITE }, { "Maxtor 4D060H3", SIL_QUIRK_UDMA5MAX }, { } }; diff --git a/drivers/atm/ambassador.c b/drivers/atm/ambassador.c index 62a76076b548..f1a9198dfe5a 100644 --- a/drivers/atm/ambassador.c +++ b/drivers/atm/ambassador.c @@ -1925,7 +1925,7 @@ static int ucode_init(loader_block *lb, amb_dev *dev) const struct firmware *fw; unsigned long start_address; const struct ihex_binrec *rec; - const char *errmsg = 0; + const char *errmsg = NULL; int res; res = request_ihex_firmware(&fw, "atmsar11.fw", &dev->pci_dev->dev); diff --git a/drivers/atm/firestream.c b/drivers/atm/firestream.c index b41c9481b67b..f43e1c13b300 100644 --- a/drivers/atm/firestream.c +++ b/drivers/atm/firestream.c @@ -736,8 +736,8 @@ static void process_txdone_queue (struct fs_dev *dev, struct queue *q) skb = td->skb; if (skb == FS_VCC (ATM_SKB(skb)->vcc)->last_skb) { - wake_up_interruptible (& FS_VCC (ATM_SKB(skb)->vcc)->close_wait); FS_VCC (ATM_SKB(skb)->vcc)->last_skb = NULL; + wake_up_interruptible (& FS_VCC (ATM_SKB(skb)->vcc)->close_wait); } td->dev->ntxpckts--; @@ -1123,7 +1123,7 @@ static void fs_close(struct atm_vcc *atm_vcc) this sleep_on, we'll lose any reference to these packets. Memory leak! On the other hand, it's awfully convenient that we can abort a "close" that is taking too long. Maybe just use non-interruptible sleep on? -- REW */ - interruptible_sleep_on (& vcc->close_wait); + wait_event_interruptible(vcc->close_wait, !vcc->last_skb); } txtp = &atm_vcc->qos.txtp; diff --git a/drivers/atm/nicstar.c b/drivers/atm/nicstar.c index 9587e959ce1a..9988ac98b6d8 100644 --- a/drivers/atm/nicstar.c +++ b/drivers/atm/nicstar.c @@ -639,9 +639,9 @@ static int ns_init_card(int i, struct pci_dev *pcidev) card->hbnr.init = NUM_HB; card->hbnr.max = MAX_HB; - card->sm_handle = 0x00000000; + card->sm_handle = NULL; card->sm_addr = 0x00000000; - card->lg_handle = 0x00000000; + card->lg_handle = NULL; card->lg_addr = 0x00000000; card->efbie = 1; /* To prevent push_rxbufs from enabling the interrupt */ @@ -979,7 +979,7 @@ static void push_rxbufs(ns_dev * card, struct sk_buff *skb) addr2 = card->sm_addr; handle2 = card->sm_handle; card->sm_addr = 0x00000000; - card->sm_handle = 0x00000000; + card->sm_handle = NULL; } else { /* (!sm_addr) */ card->sm_addr = addr1; @@ -993,7 +993,7 @@ static void push_rxbufs(ns_dev * card, struct sk_buff *skb) addr2 = card->lg_addr; handle2 = card->lg_handle; card->lg_addr = 0x00000000; - card->lg_handle = 0x00000000; + card->lg_handle = NULL; } else { /* (!lg_addr) */ card->lg_addr = addr1; @@ -1739,10 +1739,10 @@ static int push_scqe(ns_dev * card, vc_map * vc, scq_info * scq, ns_scqe * tbd, } scq->full = 1; - spin_unlock_irqrestore(&scq->lock, flags); - interruptible_sleep_on_timeout(&scq->scqfull_waitq, - SCQFULL_TIMEOUT); - spin_lock_irqsave(&scq->lock, flags); + wait_event_interruptible_lock_irq_timeout(scq->scqfull_waitq, + scq->tail != scq->next, + scq->lock, + SCQFULL_TIMEOUT); if (scq->full) { spin_unlock_irqrestore(&scq->lock, flags); @@ -1789,10 +1789,10 @@ static int push_scqe(ns_dev * card, vc_map * vc, scq_info * scq, ns_scqe * tbd, scq->full = 1; if (has_run++) break; - spin_unlock_irqrestore(&scq->lock, flags); - interruptible_sleep_on_timeout(&scq->scqfull_waitq, - SCQFULL_TIMEOUT); - spin_lock_irqsave(&scq->lock, flags); + wait_event_interruptible_lock_irq_timeout(scq->scqfull_waitq, + scq->tail != scq->next, + scq->lock, + SCQFULL_TIMEOUT); } if (!scq->full) { diff --git a/drivers/atm/solos-pci.c b/drivers/atm/solos-pci.c index e3fb496c7163..943cf0d6abaf 100644 --- a/drivers/atm/solos-pci.c +++ b/drivers/atm/solos-pci.c @@ -760,7 +760,7 @@ static irqreturn_t solos_irq(int irq, void *dev_id) return IRQ_RETVAL(handled); } -void solos_bh(unsigned long card_arg) +static void solos_bh(unsigned long card_arg) { struct solos_card *card = (void *)card_arg; uint32_t card_flags; diff --git a/drivers/base/component.c b/drivers/base/component.c index c53efe6c6d8e..c4778995cd72 100644 --- a/drivers/base/component.c +++ b/drivers/base/component.c @@ -133,9 +133,16 @@ static int try_to_bring_up_master(struct master *master, goto out; } + if (!devres_open_group(master->dev, NULL, GFP_KERNEL)) { + ret = -ENOMEM; + goto out; + } + /* Found all components */ ret = master->ops->bind(master->dev); if (ret < 0) { + devres_release_group(master->dev, NULL); + dev_info(master->dev, "master bind failed: %d\n", ret); master_remove_components(master); goto out; } @@ -166,6 +173,7 @@ static void take_down_master(struct master *master) { if (master->bound) { master->ops->unbind(master->dev); + devres_release_group(master->dev, NULL); master->bound = false; } diff --git a/drivers/base/dma-buf.c b/drivers/base/dma-buf.c index 1e16cbd61da2..61d6d62cc0d3 100644 --- a/drivers/base/dma-buf.c +++ b/drivers/base/dma-buf.c @@ -616,36 +616,35 @@ static int dma_buf_describe(struct seq_file *s) if (ret) return ret; - seq_printf(s, "\nDma-buf Objects:\n"); - seq_printf(s, "\texp_name\tsize\tflags\tmode\tcount\n"); + seq_puts(s, "\nDma-buf Objects:\n"); + seq_puts(s, "size\tflags\tmode\tcount\texp_name\n"); list_for_each_entry(buf_obj, &db_list.head, list_node) { ret = mutex_lock_interruptible(&buf_obj->lock); if (ret) { - seq_printf(s, - "\tERROR locking buffer object: skipping\n"); + seq_puts(s, + "\tERROR locking buffer object: skipping\n"); continue; } - seq_printf(s, "\t"); - - seq_printf(s, "\t%s\t%08zu\t%08x\t%08x\t%08ld\n", - buf_obj->exp_name, buf_obj->size, + seq_printf(s, "%08zu\t%08x\t%08x\t%08ld\t%s\n", + buf_obj->size, buf_obj->file->f_flags, buf_obj->file->f_mode, - (long)(buf_obj->file->f_count.counter)); + (long)(buf_obj->file->f_count.counter), + buf_obj->exp_name); - seq_printf(s, "\t\tAttached Devices:\n"); + seq_puts(s, "\tAttached Devices:\n"); attach_count = 0; list_for_each_entry(attach_obj, &buf_obj->attachments, node) { - seq_printf(s, "\t\t"); + seq_puts(s, "\t"); - seq_printf(s, "%s\n", attach_obj->dev->init_name); + seq_printf(s, "%s\n", dev_name(attach_obj->dev)); attach_count++; } - seq_printf(s, "\n\t\tTotal %d devices attached\n", + seq_printf(s, "Total %d devices attached\n\n", attach_count); count++; diff --git a/drivers/base/firmware_class.c b/drivers/base/firmware_class.c index 8a97ddfa6122..c30df50e4440 100644 --- a/drivers/base/firmware_class.c +++ b/drivers/base/firmware_class.c @@ -1580,6 +1580,7 @@ static int fw_pm_notify(struct notifier_block *notify_block, switch (mode) { case PM_HIBERNATION_PREPARE: case PM_SUSPEND_PREPARE: + case PM_RESTORE_PREPARE: kill_requests_without_uevent(); device_cache_fw_images(); break; diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c index 8184451b57c0..422b7d84f686 100644 --- a/drivers/block/aoe/aoecmd.c +++ b/drivers/block/aoe/aoecmd.c @@ -874,7 +874,7 @@ bio_pageinc(struct bio *bio) /* Non-zero page count for non-head members of * compound pages is no longer allowed by the kernel. */ - page = compound_trans_head(bv.bv_page); + page = compound_head(bv.bv_page); atomic_inc(&page->_count); } } @@ -887,7 +887,7 @@ bio_pagedec(struct bio *bio) struct bvec_iter iter; bio_for_each_segment(bv, bio, iter) { - page = compound_trans_head(bv.bv_page); + page = compound_head(bv.bv_page); atomic_dec(&page->_count); } } diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c index 3107282a9741..091b9ea14feb 100644 --- a/drivers/block/null_blk.c +++ b/drivers/block/null_blk.c @@ -60,7 +60,9 @@ enum { NULL_IRQ_NONE = 0, NULL_IRQ_SOFTIRQ = 1, NULL_IRQ_TIMER = 2, +}; +enum { NULL_Q_BIO = 0, NULL_Q_RQ = 1, NULL_Q_MQ = 2, @@ -172,18 +174,20 @@ static struct nullb_cmd *alloc_cmd(struct nullb_queue *nq, int can_wait) static void end_cmd(struct nullb_cmd *cmd) { - if (cmd->rq) { - if (queue_mode == NULL_Q_MQ) - blk_mq_end_io(cmd->rq, 0); - else { - INIT_LIST_HEAD(&cmd->rq->queuelist); - blk_end_request_all(cmd->rq, 0); - } - } else if (cmd->bio) + switch (queue_mode) { + case NULL_Q_MQ: + blk_mq_end_io(cmd->rq, 0); + return; + case NULL_Q_RQ: + INIT_LIST_HEAD(&cmd->rq->queuelist); + blk_end_request_all(cmd->rq, 0); + break; + case NULL_Q_BIO: bio_endio(cmd->bio, 0); + break; + } - if (queue_mode != NULL_Q_MQ) - free_cmd(cmd); + free_cmd(cmd); } static enum hrtimer_restart null_cmd_timer_expired(struct hrtimer *timer) @@ -195,6 +199,7 @@ static enum hrtimer_restart null_cmd_timer_expired(struct hrtimer *timer) cq = &per_cpu(completion_queues, smp_processor_id()); while ((entry = llist_del_all(&cq->list)) != NULL) { + entry = llist_reverse_order(entry); do { cmd = container_of(entry, struct nullb_cmd, ll_list); end_cmd(cmd); @@ -221,61 +226,31 @@ static void null_cmd_end_timer(struct nullb_cmd *cmd) static void null_softirq_done_fn(struct request *rq) { - blk_end_request_all(rq, 0); -} - -#ifdef CONFIG_SMP - -static void null_ipi_cmd_end_io(void *data) -{ - struct completion_queue *cq; - struct llist_node *entry, *next; - struct nullb_cmd *cmd; - - cq = &per_cpu(completion_queues, smp_processor_id()); - - entry = llist_del_all(&cq->list); - - while (entry) { - next = entry->next; - cmd = llist_entry(entry, struct nullb_cmd, ll_list); - end_cmd(cmd); - entry = next; - } -} - -static void null_cmd_end_ipi(struct nullb_cmd *cmd) -{ - struct call_single_data *data = &cmd->csd; - int cpu = get_cpu(); - struct completion_queue *cq = &per_cpu(completion_queues, cpu); - - cmd->ll_list.next = NULL; - - if (llist_add(&cmd->ll_list, &cq->list)) { - data->func = null_ipi_cmd_end_io; - data->flags = 0; - __smp_call_function_single(cpu, data, 0); - } - - put_cpu(); + end_cmd(rq->special); } -#endif /* CONFIG_SMP */ - static inline void null_handle_cmd(struct nullb_cmd *cmd) { /* Complete IO by inline, softirq or timer */ switch (irqmode) { - case NULL_IRQ_NONE: - end_cmd(cmd); - break; case NULL_IRQ_SOFTIRQ: -#ifdef CONFIG_SMP - null_cmd_end_ipi(cmd); -#else + switch (queue_mode) { + case NULL_Q_MQ: + blk_mq_complete_request(cmd->rq); + break; + case NULL_Q_RQ: + blk_complete_request(cmd->rq); + break; + case NULL_Q_BIO: + /* + * XXX: no proper submitting cpu information available. + */ + end_cmd(cmd); + break; + } + break; + case NULL_IRQ_NONE: end_cmd(cmd); -#endif break; case NULL_IRQ_TIMER: null_cmd_end_timer(cmd); @@ -411,6 +386,7 @@ static struct blk_mq_ops null_mq_ops = { .queue_rq = null_queue_rq, .map_queue = blk_mq_map_queue, .init_hctx = null_init_hctx, + .complete = null_softirq_done_fn, }; static struct blk_mq_reg null_mq_reg = { @@ -609,13 +585,6 @@ static int __init null_init(void) { unsigned int i; -#if !defined(CONFIG_SMP) - if (irqmode == NULL_IRQ_SOFTIRQ) { - pr_warn("null_blk: softirq completions not available.\n"); - pr_warn("null_blk: using direct completions.\n"); - irqmode = NULL_IRQ_NONE; - } -#endif if (bs > PAGE_SIZE) { pr_warn("null_blk: invalid block size\n"); pr_warn("null_blk: defaults block size to %lu\n", PAGE_SIZE); diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 6a680d4de7f1..b1cb3f4c4db4 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -110,9 +110,9 @@ static int __virtblk_add_req(struct virtqueue *vq, return virtqueue_add_sgs(vq, sgs, num_out, num_in, vbr, GFP_ATOMIC); } -static inline void virtblk_request_done(struct virtblk_req *vbr) +static inline void virtblk_request_done(struct request *req) { - struct request *req = vbr->req; + struct virtblk_req *vbr = req->special; int error = virtblk_result(vbr); if (req->cmd_type == REQ_TYPE_BLOCK_PC) { @@ -138,7 +138,7 @@ static void virtblk_done(struct virtqueue *vq) do { virtqueue_disable_cb(vq); while ((vbr = virtqueue_get_buf(vblk->vq, &len)) != NULL) { - virtblk_request_done(vbr); + blk_mq_complete_request(vbr->req); req_done = true; } if (unlikely(virtqueue_is_broken(vq))) @@ -479,6 +479,7 @@ static struct blk_mq_ops virtio_mq_ops = { .map_queue = blk_mq_map_queue, .alloc_hctx = blk_mq_alloc_single_hw_queue, .free_hctx = blk_mq_free_single_hw_queue, + .complete = virtblk_request_done, }; static struct blk_mq_reg virtio_mq_reg = { diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c index 4b97b86da926..64c60edcdfbc 100644 --- a/drivers/block/xen-blkback/blkback.c +++ b/drivers/block/xen-blkback/blkback.c @@ -299,7 +299,7 @@ static void free_persistent_gnts(struct xen_blkif *blkif, struct rb_root *root, BUG_ON(num != 0); } -static void unmap_purged_grants(struct work_struct *work) +void xen_blkbk_unmap_purged_grants(struct work_struct *work) { struct gnttab_unmap_grant_ref unmap[BLKIF_MAX_SEGMENTS_PER_REQUEST]; struct page *pages[BLKIF_MAX_SEGMENTS_PER_REQUEST]; @@ -375,7 +375,7 @@ static void purge_persistent_gnt(struct xen_blkif *blkif) pr_debug(DRV_PFX "Going to purge %u persistent grants\n", num_clean); - INIT_LIST_HEAD(&blkif->persistent_purge_list); + BUG_ON(!list_empty(&blkif->persistent_purge_list)); root = &blkif->persistent_gnts; purge_list: foreach_grant_safe(persistent_gnt, n, root, node) { @@ -420,7 +420,6 @@ finished: blkif->vbd.overflow_max_grants = 0; /* We can defer this work */ - INIT_WORK(&blkif->persistent_purge_work, unmap_purged_grants); schedule_work(&blkif->persistent_purge_work); pr_debug(DRV_PFX "Purged %u/%u\n", (total - num_clean), total); return; @@ -625,9 +624,23 @@ purge_gnt_list: print_stats(blkif); } - /* Since we are shutting down remove all pages from the buffer */ - shrink_free_pagepool(blkif, 0 /* All */); + /* Drain pending purge work */ + flush_work(&blkif->persistent_purge_work); + if (log_stats) + print_stats(blkif); + + blkif->xenblkd = NULL; + xen_blkif_put(blkif); + + return 0; +} + +/* + * Remove persistent grants and empty the pool of free pages + */ +void xen_blkbk_free_caches(struct xen_blkif *blkif) +{ /* Free all persistent grant pages */ if (!RB_EMPTY_ROOT(&blkif->persistent_gnts)) free_persistent_gnts(blkif, &blkif->persistent_gnts, @@ -636,13 +649,8 @@ purge_gnt_list: BUG_ON(!RB_EMPTY_ROOT(&blkif->persistent_gnts)); blkif->persistent_gnt_c = 0; - if (log_stats) - print_stats(blkif); - - blkif->xenblkd = NULL; - xen_blkif_put(blkif); - - return 0; + /* Since we are shutting down remove all pages from the buffer */ + shrink_free_pagepool(blkif, 0 /* All */); } /* @@ -838,7 +846,7 @@ static int xen_blkbk_parse_indirect(struct blkif_request *req, struct grant_page **pages = pending_req->indirect_pages; struct xen_blkif *blkif = pending_req->blkif; int indirect_grefs, rc, n, nseg, i; - struct blkif_request_segment_aligned *segments = NULL; + struct blkif_request_segment *segments = NULL; nseg = pending_req->nr_pages; indirect_grefs = INDIRECT_PAGES(nseg); @@ -934,9 +942,7 @@ static void xen_blk_drain_io(struct xen_blkif *blkif) { atomic_set(&blkif->drain, 1); do { - /* The initial value is one, and one refcnt taken at the - * start of the xen_blkif_schedule thread. */ - if (atomic_read(&blkif->refcnt) <= 2) + if (atomic_read(&blkif->inflight) == 0) break; wait_for_completion_interruptible_timeout( &blkif->drain_complete, HZ); @@ -976,17 +982,30 @@ static void __end_block_io_op(struct pending_req *pending_req, int error) * the proper response on the ring. */ if (atomic_dec_and_test(&pending_req->pendcnt)) { - xen_blkbk_unmap(pending_req->blkif, + struct xen_blkif *blkif = pending_req->blkif; + + xen_blkbk_unmap(blkif, pending_req->segments, pending_req->nr_pages); - make_response(pending_req->blkif, pending_req->id, + make_response(blkif, pending_req->id, pending_req->operation, pending_req->status); - xen_blkif_put(pending_req->blkif); - if (atomic_read(&pending_req->blkif->refcnt) <= 2) { - if (atomic_read(&pending_req->blkif->drain)) - complete(&pending_req->blkif->drain_complete); + free_req(blkif, pending_req); + /* + * Make sure the request is freed before releasing blkif, + * or there could be a race between free_req and the + * cleanup done in xen_blkif_free during shutdown. + * + * NB: The fact that we might try to wake up pending_free_wq + * before drain_complete (in case there's a drain going on) + * it's not a problem with our current implementation + * because we can assure there's no thread waiting on + * pending_free_wq if there's a drain going on, but it has + * to be taken into account if the current model is changed. + */ + if (atomic_dec_and_test(&blkif->inflight) && atomic_read(&blkif->drain)) { + complete(&blkif->drain_complete); } - free_req(pending_req->blkif, pending_req); + xen_blkif_put(blkif); } } @@ -1240,6 +1259,7 @@ static int dispatch_rw_block_io(struct xen_blkif *blkif, * below (in "!bio") if we are handling a BLKIF_OP_DISCARD. */ xen_blkif_get(blkif); + atomic_inc(&blkif->inflight); for (i = 0; i < nseg; i++) { while ((bio == NULL) || diff --git a/drivers/block/xen-blkback/common.h b/drivers/block/xen-blkback/common.h index 8d8807563d99..be052773ad03 100644 --- a/drivers/block/xen-blkback/common.h +++ b/drivers/block/xen-blkback/common.h @@ -57,7 +57,7 @@ #define MAX_INDIRECT_SEGMENTS 256 #define SEGS_PER_INDIRECT_FRAME \ - (PAGE_SIZE/sizeof(struct blkif_request_segment_aligned)) + (PAGE_SIZE/sizeof(struct blkif_request_segment)) #define MAX_INDIRECT_PAGES \ ((MAX_INDIRECT_SEGMENTS + SEGS_PER_INDIRECT_FRAME - 1)/SEGS_PER_INDIRECT_FRAME) #define INDIRECT_PAGES(_segs) \ @@ -278,6 +278,7 @@ struct xen_blkif { /* for barrier (drain) requests */ struct completion drain_complete; atomic_t drain; + atomic_t inflight; /* One thread per one blkif. */ struct task_struct *xenblkd; unsigned int waiting_reqs; @@ -376,6 +377,7 @@ int xen_blkif_xenbus_init(void); irqreturn_t xen_blkif_be_int(int irq, void *dev_id); int xen_blkif_schedule(void *arg); int xen_blkif_purge_persistent(void *arg); +void xen_blkbk_free_caches(struct xen_blkif *blkif); int xen_blkbk_flush_diskcache(struct xenbus_transaction xbt, struct backend_info *be, int state); @@ -383,6 +385,7 @@ int xen_blkbk_flush_diskcache(struct xenbus_transaction xbt, int xen_blkbk_barrier(struct xenbus_transaction xbt, struct backend_info *be, int state); struct xenbus_device *xen_blkbk_xenbus(struct backend_info *be); +void xen_blkbk_unmap_purged_grants(struct work_struct *work); static inline void blkif_get_x86_32_req(struct blkif_request *dst, struct blkif_x86_32_request *src) diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c index c2014a0aa206..9a547e6b6ebf 100644 --- a/drivers/block/xen-blkback/xenbus.c +++ b/drivers/block/xen-blkback/xenbus.c @@ -125,8 +125,11 @@ static struct xen_blkif *xen_blkif_alloc(domid_t domid) blkif->persistent_gnts.rb_node = NULL; spin_lock_init(&blkif->free_pages_lock); INIT_LIST_HEAD(&blkif->free_pages); + INIT_LIST_HEAD(&blkif->persistent_purge_list); blkif->free_pages_num = 0; atomic_set(&blkif->persistent_gnt_in_use, 0); + atomic_set(&blkif->inflight, 0); + INIT_WORK(&blkif->persistent_purge_work, xen_blkbk_unmap_purged_grants); INIT_LIST_HEAD(&blkif->pending_free); @@ -259,6 +262,17 @@ static void xen_blkif_free(struct xen_blkif *blkif) if (!atomic_dec_and_test(&blkif->refcnt)) BUG(); + /* Remove all persistent grants and the cache of ballooned pages. */ + xen_blkbk_free_caches(blkif); + + /* Make sure everything is drained before shutting down */ + BUG_ON(blkif->persistent_gnt_c != 0); + BUG_ON(atomic_read(&blkif->persistent_gnt_in_use) != 0); + BUG_ON(blkif->free_pages_num != 0); + BUG_ON(!list_empty(&blkif->persistent_purge_list)); + BUG_ON(!list_empty(&blkif->free_pages)); + BUG_ON(!RB_EMPTY_ROOT(&blkif->persistent_gnts)); + /* Check that there is no request in use */ list_for_each_entry_safe(req, n, &blkif->pending_free, free_list) { list_del(&req->free_list); diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 8dcfb54f1603..efe1b4761735 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -162,7 +162,7 @@ static DEFINE_SPINLOCK(minor_lock); #define DEV_NAME "xvd" /* name in /dev */ #define SEGS_PER_INDIRECT_FRAME \ - (PAGE_SIZE/sizeof(struct blkif_request_segment_aligned)) + (PAGE_SIZE/sizeof(struct blkif_request_segment)) #define INDIRECT_GREFS(_segs) \ ((_segs + SEGS_PER_INDIRECT_FRAME - 1)/SEGS_PER_INDIRECT_FRAME) @@ -393,7 +393,7 @@ static int blkif_queue_request(struct request *req) unsigned long id; unsigned int fsect, lsect; int i, ref, n; - struct blkif_request_segment_aligned *segments = NULL; + struct blkif_request_segment *segments = NULL; /* * Used to store if we are able to queue the request by just using @@ -550,7 +550,7 @@ static int blkif_queue_request(struct request *req) } else { n = i % SEGS_PER_INDIRECT_FRAME; segments[n] = - (struct blkif_request_segment_aligned) { + (struct blkif_request_segment) { .gref = ref, .first_sect = fsect, .last_sect = lsect }; @@ -1904,13 +1904,16 @@ static void blkback_changed(struct xenbus_device *dev, case XenbusStateReconfiguring: case XenbusStateReconfigured: case XenbusStateUnknown: - case XenbusStateClosed: break; case XenbusStateConnected: blkfront_connect(info); break; + case XenbusStateClosed: + if (dev->state == XenbusStateClosed) + break; + /* Missed the backend's Closing state -- fallthrough */ case XenbusStateClosing: blkfront_closing(info); break; diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 011e55d820b1..51c557cfd92b 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -612,6 +612,8 @@ static ssize_t disksize_store(struct device *dev, disksize = PAGE_ALIGN(disksize); meta = zram_meta_alloc(disksize); + if (!meta) + return -ENOMEM; down_write(&zram->init_lock); if (zram->init_done) { up_write(&zram->init_lock); diff --git a/drivers/char/Kconfig b/drivers/char/Kconfig index fa3243d71c76..1386749b48ff 100644 --- a/drivers/char/Kconfig +++ b/drivers/char/Kconfig @@ -499,6 +499,7 @@ config RAW_DRIVER config MAX_RAW_DEVS int "Maximum number of RAW devices to support (1-65536)" depends on RAW_DRIVER + range 1 65536 default "256" help The maximum number of RAW devices that are supported. diff --git a/drivers/char/raw.c b/drivers/char/raw.c index f3223aac4df1..6e8d65e9b1d3 100644 --- a/drivers/char/raw.c +++ b/drivers/char/raw.c @@ -190,7 +190,7 @@ static int bind_get(int number, dev_t *dev) struct raw_device_data *rawdev; struct block_device *bdev; - if (number <= 0 || number >= MAX_RAW_MINORS) + if (number <= 0 || number >= max_raw_minors) return -EINVAL; rawdev = &raw_devices[number]; diff --git a/drivers/clk/at91/clk-master.c b/drivers/clk/at91/clk-master.c index bd313f7816a8..c1af80bcdf20 100644 --- a/drivers/clk/at91/clk-master.c +++ b/drivers/clk/at91/clk-master.c @@ -242,7 +242,7 @@ of_at91_clk_master_setup(struct device_node *np, struct at91_pmc *pmc, irq = irq_of_parse_and_map(np, 0); if (!irq) - return; + goto out_free_characteristics; clk = at91_clk_register_master(pmc, irq, name, num_parents, parent_names, layout, diff --git a/drivers/clk/clk-nomadik.c b/drivers/clk/clk-nomadik.c index 6a934a5296bd..05e04ce0f148 100644 --- a/drivers/clk/clk-nomadik.c +++ b/drivers/clk/clk-nomadik.c @@ -494,6 +494,9 @@ static const struct file_operations nomadik_src_clk_debugfs_ops = { static int __init nomadik_src_clk_init_debugfs(void) { + /* Vital for multiplatform */ + if (!src_base) + return -ENODEV; src_pcksr0_boot = readl(src_base + SRC_PCKSR0); src_pcksr1_boot = readl(src_base + SRC_PCKSR1); debugfs_create_file("nomadik-src-clk", S_IFREG | S_IRUGO, diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index 5517944495d8..c42e608af6bb 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -2226,24 +2226,25 @@ EXPORT_SYMBOL_GPL(devm_clk_unregister); */ int __clk_get(struct clk *clk) { - if (clk && !try_module_get(clk->owner)) - return 0; + if (clk) { + if (!try_module_get(clk->owner)) + return 0; - kref_get(&clk->ref); + kref_get(&clk->ref); + } return 1; } void __clk_put(struct clk *clk) { - if (WARN_ON_ONCE(IS_ERR(clk))) + if (!clk || WARN_ON_ONCE(IS_ERR(clk))) return; clk_prepare_lock(); kref_put(&clk->ref, __clk_release); clk_prepare_unlock(); - if (clk) - module_put(clk->owner); + module_put(clk->owner); } /*** clk rate change notifiers ***/ diff --git a/drivers/clk/keystone/gate.c b/drivers/clk/keystone/gate.c index 17a598398a53..86f1e362eafb 100644 --- a/drivers/clk/keystone/gate.c +++ b/drivers/clk/keystone/gate.c @@ -179,6 +179,7 @@ static struct clk *clk_register_psc(struct device *dev, init.name = name; init.ops = &clk_psc_ops; + init.flags = 0; init.parent_names = (parent_name ? &parent_name : NULL); init.num_parents = (parent_name ? 1 : 0); diff --git a/drivers/clk/mvebu/armada-370.c b/drivers/clk/mvebu/armada-370.c index 81a202d12a7a..bef198a83863 100644 --- a/drivers/clk/mvebu/armada-370.c +++ b/drivers/clk/mvebu/armada-370.c @@ -141,13 +141,6 @@ static const struct coreclk_soc_desc a370_coreclks = { .num_ratios = ARRAY_SIZE(a370_coreclk_ratios), }; -static void __init a370_coreclk_init(struct device_node *np) -{ - mvebu_coreclk_setup(np, &a370_coreclks); -} -CLK_OF_DECLARE(a370_core_clk, "marvell,armada-370-core-clock", - a370_coreclk_init); - /* * Clock Gating Control */ @@ -168,9 +161,15 @@ static const struct clk_gating_soc_desc a370_gating_desc[] __initconst = { { } }; -static void __init a370_clk_gating_init(struct device_node *np) +static void __init a370_clk_init(struct device_node *np) { - mvebu_clk_gating_setup(np, a370_gating_desc); + struct device_node *cgnp = + of_find_compatible_node(NULL, NULL, "marvell,armada-370-gating-clock"); + + mvebu_coreclk_setup(np, &a370_coreclks); + + if (cgnp) + mvebu_clk_gating_setup(cgnp, a370_gating_desc); } -CLK_OF_DECLARE(a370_clk_gating, "marvell,armada-370-gating-clock", - a370_clk_gating_init); +CLK_OF_DECLARE(a370_clk, "marvell,armada-370-core-clock", a370_clk_init); + diff --git a/drivers/clk/mvebu/armada-xp.c b/drivers/clk/mvebu/armada-xp.c index 9922c4475aa8..b3094315a3c0 100644 --- a/drivers/clk/mvebu/armada-xp.c +++ b/drivers/clk/mvebu/armada-xp.c @@ -158,13 +158,6 @@ static const struct coreclk_soc_desc axp_coreclks = { .num_ratios = ARRAY_SIZE(axp_coreclk_ratios), }; -static void __init axp_coreclk_init(struct device_node *np) -{ - mvebu_coreclk_setup(np, &axp_coreclks); -} -CLK_OF_DECLARE(axp_core_clk, "marvell,armada-xp-core-clock", - axp_coreclk_init); - /* * Clock Gating Control */ @@ -202,9 +195,14 @@ static const struct clk_gating_soc_desc axp_gating_desc[] __initconst = { { } }; -static void __init axp_clk_gating_init(struct device_node *np) +static void __init axp_clk_init(struct device_node *np) { - mvebu_clk_gating_setup(np, axp_gating_desc); + struct device_node *cgnp = + of_find_compatible_node(NULL, NULL, "marvell,armada-xp-gating-clock"); + + mvebu_coreclk_setup(np, &axp_coreclks); + + if (cgnp) + mvebu_clk_gating_setup(cgnp, axp_gating_desc); } -CLK_OF_DECLARE(axp_clk_gating, "marvell,armada-xp-gating-clock", - axp_clk_gating_init); +CLK_OF_DECLARE(axp_clk, "marvell,armada-xp-core-clock", axp_clk_init); diff --git a/drivers/clk/mvebu/dove.c b/drivers/clk/mvebu/dove.c index 38aee1e3f242..b8c2424ac926 100644 --- a/drivers/clk/mvebu/dove.c +++ b/drivers/clk/mvebu/dove.c @@ -154,12 +154,6 @@ static const struct coreclk_soc_desc dove_coreclks = { .num_ratios = ARRAY_SIZE(dove_coreclk_ratios), }; -static void __init dove_coreclk_init(struct device_node *np) -{ - mvebu_coreclk_setup(np, &dove_coreclks); -} -CLK_OF_DECLARE(dove_core_clk, "marvell,dove-core-clock", dove_coreclk_init); - /* * Clock Gating Control */ @@ -186,9 +180,14 @@ static const struct clk_gating_soc_desc dove_gating_desc[] __initconst = { { } }; -static void __init dove_clk_gating_init(struct device_node *np) +static void __init dove_clk_init(struct device_node *np) { - mvebu_clk_gating_setup(np, dove_gating_desc); + struct device_node *cgnp = + of_find_compatible_node(NULL, NULL, "marvell,dove-gating-clock"); + + mvebu_coreclk_setup(np, &dove_coreclks); + + if (cgnp) + mvebu_clk_gating_setup(cgnp, dove_gating_desc); } -CLK_OF_DECLARE(dove_clk_gating, "marvell,dove-gating-clock", - dove_clk_gating_init); +CLK_OF_DECLARE(dove_clk, "marvell,dove-core-clock", dove_clk_init); diff --git a/drivers/clk/mvebu/kirkwood.c b/drivers/clk/mvebu/kirkwood.c index 2636a55f29f9..ddb666a86500 100644 --- a/drivers/clk/mvebu/kirkwood.c +++ b/drivers/clk/mvebu/kirkwood.c @@ -193,13 +193,6 @@ static const struct coreclk_soc_desc kirkwood_coreclks = { .num_ratios = ARRAY_SIZE(kirkwood_coreclk_ratios), }; -static void __init kirkwood_coreclk_init(struct device_node *np) -{ - mvebu_coreclk_setup(np, &kirkwood_coreclks); -} -CLK_OF_DECLARE(kirkwood_core_clk, "marvell,kirkwood-core-clock", - kirkwood_coreclk_init); - static const struct coreclk_soc_desc mv88f6180_coreclks = { .get_tclk_freq = kirkwood_get_tclk_freq, .get_cpu_freq = mv88f6180_get_cpu_freq, @@ -208,13 +201,6 @@ static const struct coreclk_soc_desc mv88f6180_coreclks = { .num_ratios = ARRAY_SIZE(kirkwood_coreclk_ratios), }; -static void __init mv88f6180_coreclk_init(struct device_node *np) -{ - mvebu_coreclk_setup(np, &mv88f6180_coreclks); -} -CLK_OF_DECLARE(mv88f6180_core_clk, "marvell,mv88f6180-core-clock", - mv88f6180_coreclk_init); - /* * Clock Gating Control */ @@ -239,9 +225,21 @@ static const struct clk_gating_soc_desc kirkwood_gating_desc[] __initconst = { { } }; -static void __init kirkwood_clk_gating_init(struct device_node *np) +static void __init kirkwood_clk_init(struct device_node *np) { - mvebu_clk_gating_setup(np, kirkwood_gating_desc); + struct device_node *cgnp = + of_find_compatible_node(NULL, NULL, "marvell,kirkwood-gating-clock"); + + + if (of_device_is_compatible(np, "marvell,mv88f6180-core-clock")) + mvebu_coreclk_setup(np, &mv88f6180_coreclks); + else + mvebu_coreclk_setup(np, &kirkwood_coreclks); + + if (cgnp) + mvebu_clk_gating_setup(cgnp, kirkwood_gating_desc); } -CLK_OF_DECLARE(kirkwood_clk_gating, "marvell,kirkwood-gating-clock", - kirkwood_clk_gating_init); +CLK_OF_DECLARE(kirkwood_clk, "marvell,kirkwood-core-clock", + kirkwood_clk_init); +CLK_OF_DECLARE(mv88f6180_clk, "marvell,mv88f6180-core-clock", + kirkwood_clk_init); diff --git a/drivers/clk/shmobile/clk-rcar-gen2.c b/drivers/clk/shmobile/clk-rcar-gen2.c index a59ec217a124..dd272a0d1446 100644 --- a/drivers/clk/shmobile/clk-rcar-gen2.c +++ b/drivers/clk/shmobile/clk-rcar-gen2.c @@ -186,7 +186,7 @@ rcar_gen2_cpg_register_clock(struct device_node *np, struct rcar_gen2_cpg *cpg, const char *name) { const struct clk_div_table *table = NULL; - const char *parent_name = "main"; + const char *parent_name; unsigned int shift; unsigned int mult = 1; unsigned int div = 1; @@ -201,23 +201,31 @@ rcar_gen2_cpg_register_clock(struct device_node *np, struct rcar_gen2_cpg *cpg, * the multiplier value. */ u32 value = clk_readl(cpg->reg + CPG_PLL0CR); + parent_name = "main"; mult = ((value >> 24) & ((1 << 7) - 1)) + 1; } else if (!strcmp(name, "pll1")) { + parent_name = "main"; mult = config->pll1_mult / 2; } else if (!strcmp(name, "pll3")) { + parent_name = "main"; mult = config->pll3_mult; } else if (!strcmp(name, "lb")) { + parent_name = "pll1_div2"; div = cpg_mode & BIT(18) ? 36 : 24; } else if (!strcmp(name, "qspi")) { + parent_name = "pll1_div2"; div = (cpg_mode & (BIT(3) | BIT(2) | BIT(1))) == BIT(2) - ? 16 : 20; + ? 8 : 10; } else if (!strcmp(name, "sdh")) { + parent_name = "pll1_div2"; table = cpg_sdh_div_table; shift = 8; } else if (!strcmp(name, "sd0")) { + parent_name = "pll1_div2"; table = cpg_sd01_div_table; shift = 4; } else if (!strcmp(name, "sd1")) { + parent_name = "pll1_div2"; table = cpg_sd01_div_table; shift = 0; } else if (!strcmp(name, "z")) { diff --git a/drivers/clk/tegra/clk-divider.c b/drivers/clk/tegra/clk-divider.c index 4d75b1f37e3a..290f9c1a3749 100644 --- a/drivers/clk/tegra/clk-divider.c +++ b/drivers/clk/tegra/clk-divider.c @@ -59,7 +59,7 @@ static int get_div(struct tegra_clk_frac_div *divider, unsigned long rate, return 0; if (divider_ux1 > get_max_div(divider)) - return -EINVAL; + return get_max_div(divider); return divider_ux1; } diff --git a/drivers/clk/tegra/clk-id.h b/drivers/clk/tegra/clk-id.h index cf0c323f2c36..c39613c519af 100644 --- a/drivers/clk/tegra/clk-id.h +++ b/drivers/clk/tegra/clk-id.h @@ -180,9 +180,13 @@ enum clk_id { tegra_clk_sbc6_8, tegra_clk_sclk, tegra_clk_sdmmc1, + tegra_clk_sdmmc1_8, tegra_clk_sdmmc2, + tegra_clk_sdmmc2_8, tegra_clk_sdmmc3, + tegra_clk_sdmmc3_8, tegra_clk_sdmmc4, + tegra_clk_sdmmc4_8, tegra_clk_se, tegra_clk_soc_therm, tegra_clk_sor0, diff --git a/drivers/clk/tegra/clk-tegra-periph.c b/drivers/clk/tegra/clk-tegra-periph.c index 5c35885f4a7c..1fa5c3f33b20 100644 --- a/drivers/clk/tegra/clk-tegra-periph.c +++ b/drivers/clk/tegra/clk-tegra-periph.c @@ -371,9 +371,7 @@ static const char *mux_pllp3_pllc_clkm[] = { static const char *mux_pllm_pllc_pllp_plla_pllc2_c3_clkm[] = { "pll_m", "pll_c", "pll_p", "pll_a", "pll_c2", "pll_c3", "clk_m" }; -static u32 mux_pllm_pllc_pllp_plla_pllc2_c3_clkm_idx[] = { - [0] = 0, [1] = 1, [2] = 2, [3] = 3, [4] = 4, [5] = 6, -}; +#define mux_pllm_pllc_pllp_plla_pllc2_c3_clkm_idx NULL static const char *mux_pllm_pllc2_c_c3_pllp_plla_pllc4[] = { "pll_m", "pll_c2", "pll_c", "pll_c3", "pll_p", "pll_a_out0", "pll_c4", @@ -465,6 +463,10 @@ static struct tegra_periph_init_data periph_clks[] = { MUX("adx1", mux_plla_pllc_pllp_clkm, CLK_SOURCE_ADX1, 180, TEGRA_PERIPH_ON_APB, tegra_clk_adx1), MUX("amx1", mux_plla_pllc_pllp_clkm, CLK_SOURCE_AMX1, 185, TEGRA_PERIPH_ON_APB, tegra_clk_amx1), MUX("vi_sensor2", mux_pllm_pllc2_c_c3_pllp_plla, CLK_SOURCE_VI_SENSOR2, 20, TEGRA_PERIPH_NO_RESET, tegra_clk_vi_sensor2), + MUX8("sdmmc1", mux_pllp_pllc2_c_c3_pllm_clkm, CLK_SOURCE_SDMMC1, 14, 0, tegra_clk_sdmmc1_8), + MUX8("sdmmc2", mux_pllp_pllc2_c_c3_pllm_clkm, CLK_SOURCE_SDMMC2, 9, 0, tegra_clk_sdmmc2_8), + MUX8("sdmmc3", mux_pllp_pllc2_c_c3_pllm_clkm, CLK_SOURCE_SDMMC3, 69, 0, tegra_clk_sdmmc3_8), + MUX8("sdmmc4", mux_pllp_pllc2_c_c3_pllm_clkm, CLK_SOURCE_SDMMC4, 15, 0, tegra_clk_sdmmc4_8), MUX8("sbc1", mux_pllp_pllc2_c_c3_pllm_clkm, CLK_SOURCE_SBC1, 41, TEGRA_PERIPH_ON_APB, tegra_clk_sbc1_8), MUX8("sbc2", mux_pllp_pllc2_c_c3_pllm_clkm, CLK_SOURCE_SBC2, 44, TEGRA_PERIPH_ON_APB, tegra_clk_sbc2_8), MUX8("sbc3", mux_pllp_pllc2_c_c3_pllm_clkm, CLK_SOURCE_SBC3, 46, TEGRA_PERIPH_ON_APB, tegra_clk_sbc3_8), @@ -492,7 +494,7 @@ static struct tegra_periph_init_data periph_clks[] = { UART("uartb", mux_pllp_pllc_pllm_clkm, CLK_SOURCE_UARTB, 7, tegra_clk_uartb), UART("uartc", mux_pllp_pllc_pllm_clkm, CLK_SOURCE_UARTC, 55, tegra_clk_uartc), UART("uartd", mux_pllp_pllc_pllm_clkm, CLK_SOURCE_UARTD, 65, tegra_clk_uartd), - UART("uarte", mux_pllp_pllc_pllm_clkm, CLK_SOURCE_UARTE, 65, tegra_clk_uarte), + UART("uarte", mux_pllp_pllc_pllm_clkm, CLK_SOURCE_UARTE, 66, tegra_clk_uarte), XUSB("xusb_host_src", mux_clkm_pllp_pllc_pllre, CLK_SOURCE_XUSB_HOST_SRC, 143, TEGRA_PERIPH_ON_APB | TEGRA_PERIPH_NO_RESET, tegra_clk_xusb_host_src), XUSB("xusb_falcon_src", mux_clkm_pllp_pllc_pllre, CLK_SOURCE_XUSB_FALCON_SRC, 143, TEGRA_PERIPH_NO_RESET, tegra_clk_xusb_falcon_src), XUSB("xusb_fs_src", mux_clkm_48M_pllp_480M, CLK_SOURCE_XUSB_FS_SRC, 143, TEGRA_PERIPH_NO_RESET, tegra_clk_xusb_fs_src), diff --git a/drivers/clk/tegra/clk-tegra-super-gen4.c b/drivers/clk/tegra/clk-tegra-super-gen4.c index 05dce4aa2c11..feb3201c85ce 100644 --- a/drivers/clk/tegra/clk-tegra-super-gen4.c +++ b/drivers/clk/tegra/clk-tegra-super-gen4.c @@ -120,7 +120,7 @@ void __init tegra_super_clk_gen4_init(void __iomem *clk_base, ARRAY_SIZE(cclk_lp_parents), CLK_SET_RATE_PARENT, clk_base + CCLKLP_BURST_POLICY, - 0, 4, 8, 9, NULL); + TEGRA_DIVIDER_2, 4, 8, 9, NULL); *dt_clk = clk; } diff --git a/drivers/clk/tegra/clk-tegra114.c b/drivers/clk/tegra/clk-tegra114.c index 90d9d25f2228..80431f0fb268 100644 --- a/drivers/clk/tegra/clk-tegra114.c +++ b/drivers/clk/tegra/clk-tegra114.c @@ -682,12 +682,12 @@ static struct tegra_clk tegra114_clks[tegra_clk_max] __initdata = { [tegra_clk_timer] = { .dt_id = TEGRA114_CLK_TIMER, .present = true }, [tegra_clk_uarta] = { .dt_id = TEGRA114_CLK_UARTA, .present = true }, [tegra_clk_uartd] = { .dt_id = TEGRA114_CLK_UARTD, .present = true }, - [tegra_clk_sdmmc2] = { .dt_id = TEGRA114_CLK_SDMMC2, .present = true }, + [tegra_clk_sdmmc2_8] = { .dt_id = TEGRA114_CLK_SDMMC2, .present = true }, [tegra_clk_i2s1] = { .dt_id = TEGRA114_CLK_I2S1, .present = true }, [tegra_clk_i2c1] = { .dt_id = TEGRA114_CLK_I2C1, .present = true }, [tegra_clk_ndflash] = { .dt_id = TEGRA114_CLK_NDFLASH, .present = true }, - [tegra_clk_sdmmc1] = { .dt_id = TEGRA114_CLK_SDMMC1, .present = true }, - [tegra_clk_sdmmc4] = { .dt_id = TEGRA114_CLK_SDMMC4, .present = true }, + [tegra_clk_sdmmc1_8] = { .dt_id = TEGRA114_CLK_SDMMC1, .present = true }, + [tegra_clk_sdmmc4_8] = { .dt_id = TEGRA114_CLK_SDMMC4, .present = true }, [tegra_clk_pwm] = { .dt_id = TEGRA114_CLK_PWM, .present = true }, [tegra_clk_i2s0] = { .dt_id = TEGRA114_CLK_I2S0, .present = true }, [tegra_clk_i2s2] = { .dt_id = TEGRA114_CLK_I2S2, .present = true }, @@ -723,7 +723,7 @@ static struct tegra_clk tegra114_clks[tegra_clk_max] __initdata = { [tegra_clk_bsev] = { .dt_id = TEGRA114_CLK_BSEV, .present = true }, [tegra_clk_i2c3] = { .dt_id = TEGRA114_CLK_I2C3, .present = true }, [tegra_clk_sbc4_8] = { .dt_id = TEGRA114_CLK_SBC4, .present = true }, - [tegra_clk_sdmmc3] = { .dt_id = TEGRA114_CLK_SDMMC3, .present = true }, + [tegra_clk_sdmmc3_8] = { .dt_id = TEGRA114_CLK_SDMMC3, .present = true }, [tegra_clk_owr] = { .dt_id = TEGRA114_CLK_OWR, .present = true }, [tegra_clk_csite] = { .dt_id = TEGRA114_CLK_CSITE, .present = true }, [tegra_clk_la] = { .dt_id = TEGRA114_CLK_LA, .present = true }, diff --git a/drivers/clk/tegra/clk-tegra124.c b/drivers/clk/tegra/clk-tegra124.c index aff86b5bc745..166e02f16c8a 100644 --- a/drivers/clk/tegra/clk-tegra124.c +++ b/drivers/clk/tegra/clk-tegra124.c @@ -516,11 +516,11 @@ static struct div_nmp pllp_nmp = { }; static struct tegra_clk_pll_freq_table pll_p_freq_table[] = { - {12000000, 216000000, 432, 12, 1, 8}, - {13000000, 216000000, 432, 13, 1, 8}, - {16800000, 216000000, 360, 14, 1, 8}, - {19200000, 216000000, 360, 16, 1, 8}, - {26000000, 216000000, 432, 26, 1, 8}, + {12000000, 408000000, 408, 12, 0, 8}, + {13000000, 408000000, 408, 13, 0, 8}, + {16800000, 408000000, 340, 14, 0, 8}, + {19200000, 408000000, 340, 16, 0, 8}, + {26000000, 408000000, 408, 26, 0, 8}, {0, 0, 0, 0, 0, 0}, }; @@ -570,6 +570,15 @@ static struct tegra_clk_pll_params pll_a_params = { .flags = TEGRA_PLL_HAS_CPCON | TEGRA_PLL_USE_LOCK, }; +static struct div_nmp plld_nmp = { + .divm_shift = 0, + .divm_width = 5, + .divn_shift = 8, + .divn_width = 11, + .divp_shift = 20, + .divp_width = 3, +}; + static struct tegra_clk_pll_freq_table pll_d_freq_table[] = { {12000000, 216000000, 864, 12, 4, 12}, {13000000, 216000000, 864, 13, 4, 12}, @@ -603,19 +612,18 @@ static struct tegra_clk_pll_params pll_d_params = { .lock_mask = PLL_BASE_LOCK, .lock_enable_bit_idx = PLLDU_MISC_LOCK_ENABLE, .lock_delay = 1000, - .div_nmp = &pllp_nmp, + .div_nmp = &plld_nmp, .freq_table = pll_d_freq_table, .flags = TEGRA_PLL_HAS_CPCON | TEGRA_PLL_SET_LFCON | TEGRA_PLL_USE_LOCK, }; static struct tegra_clk_pll_freq_table tegra124_pll_d2_freq_table[] = { - { 12000000, 148500000, 99, 1, 8}, - { 12000000, 594000000, 99, 1, 1}, - { 13000000, 594000000, 91, 1, 1}, /* actual: 591.5 MHz */ - { 16800000, 594000000, 71, 1, 1}, /* actual: 596.4 MHz */ - { 19200000, 594000000, 62, 1, 1}, /* actual: 595.2 MHz */ - { 26000000, 594000000, 91, 2, 1}, /* actual: 591.5 MHz */ + { 12000000, 594000000, 99, 1, 2}, + { 13000000, 594000000, 91, 1, 2}, /* actual: 591.5 MHz */ + { 16800000, 594000000, 71, 1, 2}, /* actual: 596.4 MHz */ + { 19200000, 594000000, 62, 1, 2}, /* actual: 595.2 MHz */ + { 26000000, 594000000, 91, 2, 2}, /* actual: 591.5 MHz */ { 0, 0, 0, 0, 0, 0 }, }; @@ -753,21 +761,19 @@ static struct tegra_clk tegra124_clks[tegra_clk_max] __initdata = { [tegra_clk_rtc] = { .dt_id = TEGRA124_CLK_RTC, .present = true }, [tegra_clk_timer] = { .dt_id = TEGRA124_CLK_TIMER, .present = true }, [tegra_clk_uarta] = { .dt_id = TEGRA124_CLK_UARTA, .present = true }, - [tegra_clk_sdmmc2] = { .dt_id = TEGRA124_CLK_SDMMC2, .present = true }, + [tegra_clk_sdmmc2_8] = { .dt_id = TEGRA124_CLK_SDMMC2, .present = true }, [tegra_clk_i2s1] = { .dt_id = TEGRA124_CLK_I2S1, .present = true }, [tegra_clk_i2c1] = { .dt_id = TEGRA124_CLK_I2C1, .present = true }, [tegra_clk_ndflash] = { .dt_id = TEGRA124_CLK_NDFLASH, .present = true }, - [tegra_clk_sdmmc1] = { .dt_id = TEGRA124_CLK_SDMMC1, .present = true }, - [tegra_clk_sdmmc4] = { .dt_id = TEGRA124_CLK_SDMMC4, .present = true }, + [tegra_clk_sdmmc1_8] = { .dt_id = TEGRA124_CLK_SDMMC1, .present = true }, + [tegra_clk_sdmmc4_8] = { .dt_id = TEGRA124_CLK_SDMMC4, .present = true }, [tegra_clk_pwm] = { .dt_id = TEGRA124_CLK_PWM, .present = true }, [tegra_clk_i2s2] = { .dt_id = TEGRA124_CLK_I2S2, .present = true }, - [tegra_clk_gr2d] = { .dt_id = TEGRA124_CLK_GR_2D, .present = true }, [tegra_clk_usbd] = { .dt_id = TEGRA124_CLK_USBD, .present = true }, [tegra_clk_isp_8] = { .dt_id = TEGRA124_CLK_ISP, .present = true }, - [tegra_clk_gr3d] = { .dt_id = TEGRA124_CLK_GR_3D, .present = true }, [tegra_clk_disp2] = { .dt_id = TEGRA124_CLK_DISP2, .present = true }, [tegra_clk_disp1] = { .dt_id = TEGRA124_CLK_DISP1, .present = true }, - [tegra_clk_host1x] = { .dt_id = TEGRA124_CLK_HOST1X, .present = true }, + [tegra_clk_host1x_8] = { .dt_id = TEGRA124_CLK_HOST1X, .present = true }, [tegra_clk_vcp] = { .dt_id = TEGRA124_CLK_VCP, .present = true }, [tegra_clk_i2s0] = { .dt_id = TEGRA124_CLK_I2S0, .present = true }, [tegra_clk_apbdma] = { .dt_id = TEGRA124_CLK_APBDMA, .present = true }, @@ -794,7 +800,7 @@ static struct tegra_clk tegra124_clks[tegra_clk_max] __initdata = { [tegra_clk_uartd] = { .dt_id = TEGRA124_CLK_UARTD, .present = true }, [tegra_clk_i2c3] = { .dt_id = TEGRA124_CLK_I2C3, .present = true }, [tegra_clk_sbc4] = { .dt_id = TEGRA124_CLK_SBC4, .present = true }, - [tegra_clk_sdmmc3] = { .dt_id = TEGRA124_CLK_SDMMC3, .present = true }, + [tegra_clk_sdmmc3_8] = { .dt_id = TEGRA124_CLK_SDMMC3, .present = true }, [tegra_clk_pcie] = { .dt_id = TEGRA124_CLK_PCIE, .present = true }, [tegra_clk_owr] = { .dt_id = TEGRA124_CLK_OWR, .present = true }, [tegra_clk_afi] = { .dt_id = TEGRA124_CLK_AFI, .present = true }, @@ -1286,9 +1292,9 @@ static void __init tegra124_pll_init(void __iomem *clk_base, clk_register_clkdev(clk, "pll_d2", NULL); clks[TEGRA124_CLK_PLL_D2] = clk; - /* PLLD2_OUT0 ?? */ + /* PLLD2_OUT0 */ clk = clk_register_fixed_factor(NULL, "pll_d2_out0", "pll_d2", - CLK_SET_RATE_PARENT, 1, 2); + CLK_SET_RATE_PARENT, 1, 1); clk_register_clkdev(clk, "pll_d2_out0", NULL); clks[TEGRA124_CLK_PLL_D2_OUT0] = clk; diff --git a/drivers/clk/tegra/clk-tegra20.c b/drivers/clk/tegra/clk-tegra20.c index dbace152b2fa..dace2b1b5ae6 100644 --- a/drivers/clk/tegra/clk-tegra20.c +++ b/drivers/clk/tegra/clk-tegra20.c @@ -574,6 +574,8 @@ static struct tegra_clk tegra20_clks[tegra_clk_max] __initdata = { [tegra_clk_tvdac] = { .dt_id = TEGRA20_CLK_TVDAC, .present = true }, [tegra_clk_vi_sensor] = { .dt_id = TEGRA20_CLK_VI_SENSOR, .present = true }, [tegra_clk_afi] = { .dt_id = TEGRA20_CLK_AFI, .present = true }, + [tegra_clk_fuse] = { .dt_id = TEGRA20_CLK_FUSE, .present = true }, + [tegra_clk_kfuse] = { .dt_id = TEGRA20_CLK_KFUSE, .present = true }, }; static unsigned long tegra20_clk_measure_input_freq(void) diff --git a/drivers/clocksource/bcm_kona_timer.c b/drivers/clocksource/bcm_kona_timer.c index 974b2db2fe10..0595dc6c453e 100644 --- a/drivers/clocksource/bcm_kona_timer.c +++ b/drivers/clocksource/bcm_kona_timer.c @@ -99,31 +99,6 @@ kona_timer_get_counter(void *timer_base, uint32_t *msw, uint32_t *lsw) return; } -static void __init kona_timers_init(struct device_node *node) -{ - u32 freq; - struct clk *external_clk; - - external_clk = of_clk_get_by_name(node, NULL); - - if (!IS_ERR(external_clk)) { - arch_timer_rate = clk_get_rate(external_clk); - clk_prepare_enable(external_clk); - } else if (!of_property_read_u32(node, "clock-frequency", &freq)) { - arch_timer_rate = freq; - } else { - panic("unable to determine clock-frequency"); - } - - /* Setup IRQ numbers */ - timers.tmr_irq = irq_of_parse_and_map(node, 0); - - /* Setup IO addresses */ - timers.tmr_regs = of_iomap(node, 0); - - kona_timer_disable_and_clear(timers.tmr_regs); -} - static int kona_timer_set_next_event(unsigned long clc, struct clock_event_device *unused) { @@ -198,7 +173,34 @@ static struct irqaction kona_timer_irq = { static void __init kona_timer_init(struct device_node *node) { - kona_timers_init(node); + u32 freq; + struct clk *external_clk; + + if (!of_device_is_available(node)) { + pr_info("Kona Timer v1 marked as disabled in device tree\n"); + return; + } + + external_clk = of_clk_get_by_name(node, NULL); + + if (!IS_ERR(external_clk)) { + arch_timer_rate = clk_get_rate(external_clk); + clk_prepare_enable(external_clk); + } else if (!of_property_read_u32(node, "clock-frequency", &freq)) { + arch_timer_rate = freq; + } else { + pr_err("Kona Timer v1 unable to determine clock-frequency"); + return; + } + + /* Setup IRQ numbers */ + timers.tmr_irq = irq_of_parse_and_map(node, 0); + + /* Setup IO addresses */ + timers.tmr_regs = of_iomap(node, 0); + + kona_timer_disable_and_clear(timers.tmr_regs); + kona_timer_clockevents_init(); setup_irq(timers.tmr_irq, &kona_timer_irq); kona_timer_set_next_event((arch_timer_rate / HZ), NULL); diff --git a/drivers/connector/connector.c b/drivers/connector/connector.c index a36749f1e44a..9b0ea0a6e26e 100644 --- a/drivers/connector/connector.c +++ b/drivers/connector/connector.c @@ -139,7 +139,6 @@ static int cn_call_callback(struct sk_buff *skb) spin_unlock_bh(&dev->cbdev->queue_lock); if (cbq != NULL) { - err = 0; cbq->callback(msg, nsp); kfree_skb(skb); cn_queue_release_callback(cbq); diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 08ca8c9f41cd..cb003a6b72c8 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -1323,8 +1323,7 @@ static int __cpufreq_remove_dev_prepare(struct device *dev, up_read(&policy->rwsem); if (cpu != policy->cpu) { - if (!frozen) - sysfs_remove_link(&dev->kobj, "cpufreq"); + sysfs_remove_link(&dev->kobj, "cpufreq"); } else if (cpus > 1) { new_cpu = cpufreq_nominate_new_policy_cpu(policy, cpu); if (new_cpu >= 0) { diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 79606f473f48..2cd36b9297f3 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -34,12 +34,15 @@ #define SAMPLE_COUNT 3 -#define BYT_RATIOS 0x66a -#define BYT_VIDS 0x66b +#define BYT_RATIOS 0x66a +#define BYT_VIDS 0x66b +#define BYT_TURBO_RATIOS 0x66c -#define FRAC_BITS 8 + +#define FRAC_BITS 6 #define int_tofp(X) ((int64_t)(X) << FRAC_BITS) #define fp_toint(X) ((X) >> FRAC_BITS) +#define FP_ROUNDUP(X) ((X) += 1 << FRAC_BITS) static inline int32_t mul_fp(int32_t x, int32_t y) { @@ -51,8 +54,6 @@ static inline int32_t div_fp(int32_t x, int32_t y) return div_s64((int64_t)x << FRAC_BITS, (int64_t)y); } -static u64 energy_divisor; - struct sample { int32_t core_pct_busy; u64 aperf; @@ -359,7 +360,7 @@ static int byt_get_min_pstate(void) { u64 value; rdmsrl(BYT_RATIOS, value); - return value & 0xFF; + return (value >> 8) & 0xFF; } static int byt_get_max_pstate(void) @@ -369,6 +370,13 @@ static int byt_get_max_pstate(void) return (value >> 16) & 0xFF; } +static int byt_get_turbo_pstate(void) +{ + u64 value; + rdmsrl(BYT_TURBO_RATIOS, value); + return value & 0x3F; +} + static void byt_set_pstate(struct cpudata *cpudata, int pstate) { u64 val; @@ -471,7 +479,7 @@ static struct cpu_defaults byt_params = { .funcs = { .get_max = byt_get_max_pstate, .get_min = byt_get_min_pstate, - .get_turbo = byt_get_max_pstate, + .get_turbo = byt_get_turbo_pstate, .set = byt_set_pstate, .get_vid = byt_get_vid, }, @@ -549,18 +557,20 @@ static void intel_pstate_get_cpu_pstates(struct cpudata *cpu) static inline void intel_pstate_calc_busy(struct cpudata *cpu, struct sample *sample) { - u64 core_pct; - u64 c0_pct; + int32_t core_pct; + int32_t c0_pct; + + core_pct = div_fp(int_tofp((sample->aperf)), + int_tofp((sample->mperf))); + core_pct = mul_fp(core_pct, int_tofp(100)); + FP_ROUNDUP(core_pct); - core_pct = div64_u64(sample->aperf * 100, sample->mperf); + c0_pct = div_fp(int_tofp(sample->mperf), int_tofp(sample->tsc)); - c0_pct = div64_u64(sample->mperf * 100, sample->tsc); sample->freq = fp_toint( - mul_fp(int_tofp(cpu->pstate.max_pstate), - int_tofp(core_pct * 1000))); + mul_fp(int_tofp(cpu->pstate.max_pstate * 1000), core_pct)); - sample->core_pct_busy = mul_fp(int_tofp(core_pct), - div_fp(int_tofp(c0_pct + 1), int_tofp(100))); + sample->core_pct_busy = mul_fp(core_pct, c0_pct); } static inline void intel_pstate_sample(struct cpudata *cpu) @@ -572,6 +582,10 @@ static inline void intel_pstate_sample(struct cpudata *cpu) rdmsrl(MSR_IA32_MPERF, mperf); tsc = native_read_tsc(); + aperf = aperf >> FRAC_BITS; + mperf = mperf >> FRAC_BITS; + tsc = tsc >> FRAC_BITS; + cpu->sample_ptr = (cpu->sample_ptr + 1) % SAMPLE_COUNT; cpu->samples[cpu->sample_ptr].aperf = aperf; cpu->samples[cpu->sample_ptr].mperf = mperf; @@ -603,7 +617,8 @@ static inline int32_t intel_pstate_get_scaled_busy(struct cpudata *cpu) core_busy = cpu->samples[cpu->sample_ptr].core_pct_busy; max_pstate = int_tofp(cpu->pstate.max_pstate); current_pstate = int_tofp(cpu->pstate.current_pstate); - return mul_fp(core_busy, div_fp(max_pstate, current_pstate)); + core_busy = mul_fp(core_busy, div_fp(max_pstate, current_pstate)); + return FP_ROUNDUP(core_busy); } static inline void intel_pstate_adjust_busy_pstate(struct cpudata *cpu) @@ -630,12 +645,10 @@ static void intel_pstate_timer_func(unsigned long __data) { struct cpudata *cpu = (struct cpudata *) __data; struct sample *sample; - u64 energy; intel_pstate_sample(cpu); sample = &cpu->samples[cpu->sample_ptr]; - rdmsrl(MSR_PKG_ENERGY_STATUS, energy); intel_pstate_adjust_busy_pstate(cpu); @@ -644,7 +657,6 @@ static void intel_pstate_timer_func(unsigned long __data) cpu->pstate.current_pstate, sample->mperf, sample->aperf, - div64_u64(energy, energy_divisor), sample->freq); intel_pstate_set_sample_time(cpu); @@ -926,7 +938,6 @@ static int __init intel_pstate_init(void) int cpu, rc = 0; const struct x86_cpu_id *id; struct cpu_defaults *cpu_info; - u64 units; if (no_load) return -ENODEV; @@ -960,9 +971,6 @@ static int __init intel_pstate_init(void) if (rc) goto out; - rdmsrl(MSR_RAPL_POWER_UNIT, units); - energy_divisor = 1 << ((units >> 8) & 0x1f); /* bits{12:8} */ - intel_pstate_debug_expose_params(); intel_pstate_sysfs_expose_params(); diff --git a/drivers/cpufreq/powernow-k8.c b/drivers/cpufreq/powernow-k8.c index e10b646634d7..6684e0342792 100644 --- a/drivers/cpufreq/powernow-k8.c +++ b/drivers/cpufreq/powernow-k8.c @@ -1076,7 +1076,7 @@ static int powernowk8_cpu_init(struct cpufreq_policy *pol) { struct powernow_k8_data *data; struct init_on_cpu init_on_cpu; - int rc; + int rc, cpu; smp_call_function_single(pol->cpu, check_supported_cpu, &rc, 1); if (rc) @@ -1140,7 +1140,9 @@ static int powernowk8_cpu_init(struct cpufreq_policy *pol) pr_debug("cpu_init done, current fid 0x%x, vid 0x%x\n", data->currfid, data->currvid); - per_cpu(powernow_data, pol->cpu) = data; + /* Point all the CPUs in this policy to the same data */ + for_each_cpu(cpu, pol->cpus) + per_cpu(powernow_data, cpu) = data; return 0; @@ -1155,6 +1157,7 @@ err_out: static int powernowk8_cpu_exit(struct cpufreq_policy *pol) { struct powernow_k8_data *data = per_cpu(powernow_data, pol->cpu); + int cpu; if (!data) return -EINVAL; @@ -1165,7 +1168,8 @@ static int powernowk8_cpu_exit(struct cpufreq_policy *pol) kfree(data->powernow_table); kfree(data); - per_cpu(powernow_data, pol->cpu) = NULL; + for_each_cpu(cpu, pol->cpus) + per_cpu(powernow_data, cpu) = NULL; return 0; } diff --git a/drivers/crypto/nx/nx-842.c b/drivers/crypto/nx/nx-842.c index 6c4c000671c5..1e5481d88a26 100644 --- a/drivers/crypto/nx/nx-842.c +++ b/drivers/crypto/nx/nx-842.c @@ -158,6 +158,15 @@ static inline unsigned long nx842_get_scatterlist_size( return sl->entry_nr * sizeof(struct nx842_slentry); } +static inline unsigned long nx842_get_pa(void *addr) +{ + if (is_vmalloc_addr(addr)) + return page_to_phys(vmalloc_to_page(addr)) + + offset_in_page(addr); + else + return __pa(addr); +} + static int nx842_build_scatterlist(unsigned long buf, int len, struct nx842_scatterlist *sl) { @@ -168,7 +177,7 @@ static int nx842_build_scatterlist(unsigned long buf, int len, entry = sl->entries; while (len) { - entry->ptr = __pa(buf); + entry->ptr = nx842_get_pa((void *)buf); nextpage = ALIGN(buf + 1, NX842_HW_PAGE_SIZE); if (nextpage < buf + len) { /* we aren't at the end yet */ @@ -370,8 +379,8 @@ int nx842_compress(const unsigned char *in, unsigned int inlen, op.flags = NX842_OP_COMPRESS; csbcpb = &workmem->csbcpb; memset(csbcpb, 0, sizeof(*csbcpb)); - op.csbcpb = __pa(csbcpb); - op.out = __pa(slout.entries); + op.csbcpb = nx842_get_pa(csbcpb); + op.out = nx842_get_pa(slout.entries); for (i = 0; i < hdr->blocks_nr; i++) { /* @@ -401,13 +410,13 @@ int nx842_compress(const unsigned char *in, unsigned int inlen, */ if (likely(max_sync_size == NX842_HW_PAGE_SIZE)) { /* Create direct DDE */ - op.in = __pa(inbuf); + op.in = nx842_get_pa((void *)inbuf); op.inlen = max_sync_size; } else { /* Create indirect DDE (scatterlist) */ nx842_build_scatterlist(inbuf, max_sync_size, &slin); - op.in = __pa(slin.entries); + op.in = nx842_get_pa(slin.entries); op.inlen = -nx842_get_scatterlist_size(&slin); } @@ -565,7 +574,7 @@ int nx842_decompress(const unsigned char *in, unsigned int inlen, op.flags = NX842_OP_DECOMPRESS; csbcpb = &workmem->csbcpb; memset(csbcpb, 0, sizeof(*csbcpb)); - op.csbcpb = __pa(csbcpb); + op.csbcpb = nx842_get_pa(csbcpb); /* * max_sync_size may have changed since compression, @@ -597,12 +606,12 @@ int nx842_decompress(const unsigned char *in, unsigned int inlen, if (likely((inbuf & NX842_HW_PAGE_MASK) == ((inbuf + hdr->sizes[i] - 1) & NX842_HW_PAGE_MASK))) { /* Create direct DDE */ - op.in = __pa(inbuf); + op.in = nx842_get_pa((void *)inbuf); op.inlen = hdr->sizes[i]; } else { /* Create indirect DDE (scatterlist) */ nx842_build_scatterlist(inbuf, hdr->sizes[i] , &slin); - op.in = __pa(slin.entries); + op.in = nx842_get_pa(slin.entries); op.inlen = -nx842_get_scatterlist_size(&slin); } @@ -613,12 +622,12 @@ int nx842_decompress(const unsigned char *in, unsigned int inlen, */ if (likely(max_sync_size == NX842_HW_PAGE_SIZE)) { /* Create direct DDE */ - op.out = __pa(outbuf); + op.out = nx842_get_pa((void *)outbuf); op.outlen = max_sync_size; } else { /* Create indirect DDE (scatterlist) */ nx842_build_scatterlist(outbuf, max_sync_size, &slout); - op.out = __pa(slout.entries); + op.out = nx842_get_pa(slout.entries); op.outlen = -nx842_get_scatterlist_size(&slout); } diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig index 9bed1a2a67a1..605b016bcea4 100644 --- a/drivers/dma/Kconfig +++ b/drivers/dma/Kconfig @@ -346,6 +346,7 @@ config MOXART_DMA tristate "MOXART DMA support" depends on ARCH_MOXART select DMA_ENGINE + select DMA_OF select DMA_VIRTUAL_CHANNELS help Enable support for the MOXA ART SoC DMA controller. diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c index 4e7918339b12..19041cefabb1 100644 --- a/drivers/dma/imx-sdma.c +++ b/drivers/dma/imx-sdma.c @@ -449,6 +449,7 @@ static const struct of_device_id sdma_dt_ids[] = { { .compatible = "fsl,imx51-sdma", .data = &sdma_imx51, }, { .compatible = "fsl,imx35-sdma", .data = &sdma_imx35, }, { .compatible = "fsl,imx31-sdma", .data = &sdma_imx31, }, + { .compatible = "fsl,imx25-sdma", .data = &sdma_imx25, }, { /* sentinel */ } }; MODULE_DEVICE_TABLE(of, sdma_dt_ids); diff --git a/drivers/dma/ioat/dma.c b/drivers/dma/ioat/dma.c index 87529181efcc..4e3549a16132 100644 --- a/drivers/dma/ioat/dma.c +++ b/drivers/dma/ioat/dma.c @@ -77,7 +77,8 @@ static irqreturn_t ioat_dma_do_interrupt(int irq, void *data) attnstatus = readl(instance->reg_base + IOAT_ATTNSTATUS_OFFSET); for_each_set_bit(bit, &attnstatus, BITS_PER_LONG) { chan = ioat_chan_by_index(instance, bit); - tasklet_schedule(&chan->cleanup_task); + if (test_bit(IOAT_RUN, &chan->state)) + tasklet_schedule(&chan->cleanup_task); } writeb(intrctrl, instance->reg_base + IOAT_INTRCTRL_OFFSET); @@ -93,7 +94,8 @@ static irqreturn_t ioat_dma_do_interrupt_msix(int irq, void *data) { struct ioat_chan_common *chan = data; - tasklet_schedule(&chan->cleanup_task); + if (test_bit(IOAT_RUN, &chan->state)) + tasklet_schedule(&chan->cleanup_task); return IRQ_HANDLED; } @@ -116,7 +118,6 @@ void ioat_init_channel(struct ioatdma_device *device, struct ioat_chan_common *c chan->timer.function = device->timer_fn; chan->timer.data = data; tasklet_init(&chan->cleanup_task, device->cleanup_fn, data); - tasklet_disable(&chan->cleanup_task); } /** @@ -354,13 +355,49 @@ static int ioat1_dma_alloc_chan_resources(struct dma_chan *c) writel(((u64) chan->completion_dma) >> 32, chan->reg_base + IOAT_CHANCMP_OFFSET_HIGH); - tasklet_enable(&chan->cleanup_task); + set_bit(IOAT_RUN, &chan->state); ioat1_dma_start_null_desc(ioat); /* give chain to dma device */ dev_dbg(to_dev(chan), "%s: allocated %d descriptors\n", __func__, ioat->desccount); return ioat->desccount; } +void ioat_stop(struct ioat_chan_common *chan) +{ + struct ioatdma_device *device = chan->device; + struct pci_dev *pdev = device->pdev; + int chan_id = chan_num(chan); + struct msix_entry *msix; + + /* 1/ stop irq from firing tasklets + * 2/ stop the tasklet from re-arming irqs + */ + clear_bit(IOAT_RUN, &chan->state); + + /* flush inflight interrupts */ + switch (device->irq_mode) { + case IOAT_MSIX: + msix = &device->msix_entries[chan_id]; + synchronize_irq(msix->vector); + break; + case IOAT_MSI: + case IOAT_INTX: + synchronize_irq(pdev->irq); + break; + default: + break; + } + + /* flush inflight timers */ + del_timer_sync(&chan->timer); + + /* flush inflight tasklet runs */ + tasklet_kill(&chan->cleanup_task); + + /* final cleanup now that everything is quiesced and can't re-arm */ + device->cleanup_fn((unsigned long) &chan->common); +} + /** * ioat1_dma_free_chan_resources - release all the descriptors * @chan: the channel to be cleaned @@ -379,9 +416,7 @@ static void ioat1_dma_free_chan_resources(struct dma_chan *c) if (ioat->desccount == 0) return; - tasklet_disable(&chan->cleanup_task); - del_timer_sync(&chan->timer); - ioat1_cleanup(ioat); + ioat_stop(chan); /* Delay 100ms after reset to allow internal DMA logic to quiesce * before removing DMA descriptor resources. @@ -526,8 +561,11 @@ ioat1_dma_prep_memcpy(struct dma_chan *c, dma_addr_t dma_dest, static void ioat1_cleanup_event(unsigned long data) { struct ioat_dma_chan *ioat = to_ioat_chan((void *) data); + struct ioat_chan_common *chan = &ioat->base; ioat1_cleanup(ioat); + if (!test_bit(IOAT_RUN, &chan->state)) + return; writew(IOAT_CHANCTRL_RUN, ioat->base.reg_base + IOAT_CHANCTRL_OFFSET); } diff --git a/drivers/dma/ioat/dma.h b/drivers/dma/ioat/dma.h index 11fb877ddca9..e982f00a9843 100644 --- a/drivers/dma/ioat/dma.h +++ b/drivers/dma/ioat/dma.h @@ -356,6 +356,7 @@ bool ioat_cleanup_preamble(struct ioat_chan_common *chan, void ioat_kobject_add(struct ioatdma_device *device, struct kobj_type *type); void ioat_kobject_del(struct ioatdma_device *device); int ioat_dma_setup_interrupts(struct ioatdma_device *device); +void ioat_stop(struct ioat_chan_common *chan); extern const struct sysfs_ops ioat_sysfs_ops; extern struct ioat_sysfs_entry ioat_version_attr; extern struct ioat_sysfs_entry ioat_cap_attr; diff --git a/drivers/dma/ioat/dma_v2.c b/drivers/dma/ioat/dma_v2.c index 5d3affe7e976..8d1058085eeb 100644 --- a/drivers/dma/ioat/dma_v2.c +++ b/drivers/dma/ioat/dma_v2.c @@ -190,8 +190,11 @@ static void ioat2_cleanup(struct ioat2_dma_chan *ioat) void ioat2_cleanup_event(unsigned long data) { struct ioat2_dma_chan *ioat = to_ioat2_chan((void *) data); + struct ioat_chan_common *chan = &ioat->base; ioat2_cleanup(ioat); + if (!test_bit(IOAT_RUN, &chan->state)) + return; writew(IOAT_CHANCTRL_RUN, ioat->base.reg_base + IOAT_CHANCTRL_OFFSET); } @@ -553,10 +556,10 @@ int ioat2_alloc_chan_resources(struct dma_chan *c) ioat->issued = 0; ioat->tail = 0; ioat->alloc_order = order; + set_bit(IOAT_RUN, &chan->state); spin_unlock_bh(&ioat->prep_lock); spin_unlock_bh(&chan->cleanup_lock); - tasklet_enable(&chan->cleanup_task); ioat2_start_null_desc(ioat); /* check that we got off the ground */ @@ -566,7 +569,6 @@ int ioat2_alloc_chan_resources(struct dma_chan *c) } while (i++ < 20 && !is_ioat_active(status) && !is_ioat_idle(status)); if (is_ioat_active(status) || is_ioat_idle(status)) { - set_bit(IOAT_RUN, &chan->state); return 1 << ioat->alloc_order; } else { u32 chanerr = readl(chan->reg_base + IOAT_CHANERR_OFFSET); @@ -809,11 +811,8 @@ void ioat2_free_chan_resources(struct dma_chan *c) if (!ioat->ring) return; - tasklet_disable(&chan->cleanup_task); - del_timer_sync(&chan->timer); - device->cleanup_fn((unsigned long) c); + ioat_stop(chan); device->reset_hw(chan); - clear_bit(IOAT_RUN, &chan->state); spin_lock_bh(&chan->cleanup_lock); spin_lock_bh(&ioat->prep_lock); diff --git a/drivers/dma/ioat/dma_v3.c b/drivers/dma/ioat/dma_v3.c index 820817e97e62..b9b38a1cf92f 100644 --- a/drivers/dma/ioat/dma_v3.c +++ b/drivers/dma/ioat/dma_v3.c @@ -464,8 +464,11 @@ static void ioat3_cleanup(struct ioat2_dma_chan *ioat) static void ioat3_cleanup_event(unsigned long data) { struct ioat2_dma_chan *ioat = to_ioat2_chan((void *) data); + struct ioat_chan_common *chan = &ioat->base; ioat3_cleanup(ioat); + if (!test_bit(IOAT_RUN, &chan->state)) + return; writew(IOAT_CHANCTRL_RUN, ioat->base.reg_base + IOAT_CHANCTRL_OFFSET); } diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c index 53fb0c8365b0..766b68ed505c 100644 --- a/drivers/dma/mv_xor.c +++ b/drivers/dma/mv_xor.c @@ -497,8 +497,8 @@ mv_xor_tx_submit(struct dma_async_tx_descriptor *tx) if (!mv_can_chain(grp_start)) goto submit_done; - dev_dbg(mv_chan_to_devp(mv_chan), "Append to last desc %x\n", - old_chain_tail->async_tx.phys); + dev_dbg(mv_chan_to_devp(mv_chan), "Append to last desc %pa\n", + &old_chain_tail->async_tx.phys); /* fix up the hardware chain */ mv_desc_set_next_desc(old_chain_tail, grp_start->async_tx.phys); @@ -527,7 +527,8 @@ submit_done: /* returns the number of allocated descriptors */ static int mv_xor_alloc_chan_resources(struct dma_chan *chan) { - char *hw_desc; + void *virt_desc; + dma_addr_t dma_desc; int idx; struct mv_xor_chan *mv_chan = to_mv_xor_chan(chan); struct mv_xor_desc_slot *slot = NULL; @@ -542,17 +543,16 @@ static int mv_xor_alloc_chan_resources(struct dma_chan *chan) " %d descriptor slots", idx); break; } - hw_desc = (char *) mv_chan->dma_desc_pool_virt; - slot->hw_desc = (void *) &hw_desc[idx * MV_XOR_SLOT_SIZE]; + virt_desc = mv_chan->dma_desc_pool_virt; + slot->hw_desc = virt_desc + idx * MV_XOR_SLOT_SIZE; dma_async_tx_descriptor_init(&slot->async_tx, chan); slot->async_tx.tx_submit = mv_xor_tx_submit; INIT_LIST_HEAD(&slot->chain_node); INIT_LIST_HEAD(&slot->slot_node); INIT_LIST_HEAD(&slot->tx_list); - hw_desc = (char *) mv_chan->dma_desc_pool; - slot->async_tx.phys = - (dma_addr_t) &hw_desc[idx * MV_XOR_SLOT_SIZE]; + dma_desc = mv_chan->dma_desc_pool; + slot->async_tx.phys = dma_desc + idx * MV_XOR_SLOT_SIZE; slot->idx = idx++; spin_lock_bh(&mv_chan->lock); @@ -582,8 +582,8 @@ mv_xor_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src, int slot_cnt; dev_dbg(mv_chan_to_devp(mv_chan), - "%s dest: %x src %x len: %u flags: %ld\n", - __func__, dest, src, len, flags); + "%s dest: %pad src %pad len: %u flags: %ld\n", + __func__, &dest, &src, len, flags); if (unlikely(len < MV_XOR_MIN_BYTE_COUNT)) return NULL; @@ -626,8 +626,8 @@ mv_xor_prep_dma_xor(struct dma_chan *chan, dma_addr_t dest, dma_addr_t *src, BUG_ON(len > MV_XOR_MAX_BYTE_COUNT); dev_dbg(mv_chan_to_devp(mv_chan), - "%s src_cnt: %d len: dest %x %u flags: %ld\n", - __func__, src_cnt, len, dest, flags); + "%s src_cnt: %d len: %u dest %pad flags: %ld\n", + __func__, src_cnt, len, &dest, flags); spin_lock_bh(&mv_chan->lock); slot_cnt = mv_chan_xor_slot_count(len, src_cnt); diff --git a/drivers/dma/ste_dma40.c b/drivers/dma/ste_dma40.c index 00a2de957b23..bf18c786ed40 100644 --- a/drivers/dma/ste_dma40.c +++ b/drivers/dma/ste_dma40.c @@ -1641,6 +1641,7 @@ static void dma_tasklet(unsigned long data) struct d40_chan *d40c = (struct d40_chan *) data; struct d40_desc *d40d; unsigned long flags; + bool callback_active; dma_async_tx_callback callback; void *callback_param; @@ -1668,6 +1669,7 @@ static void dma_tasklet(unsigned long data) } /* Callback to client */ + callback_active = !!(d40d->txd.flags & DMA_PREP_INTERRUPT); callback = d40d->txd.callback; callback_param = d40d->txd.callback_param; @@ -1690,7 +1692,7 @@ static void dma_tasklet(unsigned long data) spin_unlock_irqrestore(&d40c->lock, flags); - if (callback && (d40d->txd.flags & DMA_PREP_INTERRUPT)) + if (callback_active && callback) callback(callback_param); return; diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c index e8c9ef03495b..33edd6766344 100644 --- a/drivers/edac/edac_mc.c +++ b/drivers/edac/edac_mc.c @@ -559,7 +559,8 @@ static void edac_mc_workq_function(struct work_struct *work_req) * * called with the mem_ctls_mutex held */ -static void edac_mc_workq_setup(struct mem_ctl_info *mci, unsigned msec) +static void edac_mc_workq_setup(struct mem_ctl_info *mci, unsigned msec, + bool init) { edac_dbg(0, "\n"); @@ -567,7 +568,9 @@ static void edac_mc_workq_setup(struct mem_ctl_info *mci, unsigned msec) if (mci->op_state != OP_RUNNING_POLL) return; - INIT_DELAYED_WORK(&mci->work, edac_mc_workq_function); + if (init) + INIT_DELAYED_WORK(&mci->work, edac_mc_workq_function); + mod_delayed_work(edac_workqueue, &mci->work, msecs_to_jiffies(msec)); } @@ -601,7 +604,7 @@ static void edac_mc_workq_teardown(struct mem_ctl_info *mci) * user space has updated our poll period value, need to * reset our workq delays */ -void edac_mc_reset_delay_period(int value) +void edac_mc_reset_delay_period(unsigned long value) { struct mem_ctl_info *mci; struct list_head *item; @@ -611,7 +614,7 @@ void edac_mc_reset_delay_period(int value) list_for_each(item, &mc_devices) { mci = list_entry(item, struct mem_ctl_info, link); - edac_mc_workq_setup(mci, (unsigned long) value); + edac_mc_workq_setup(mci, value, false); } mutex_unlock(&mem_ctls_mutex); @@ -782,7 +785,7 @@ int edac_mc_add_mc(struct mem_ctl_info *mci) /* This instance is NOW RUNNING */ mci->op_state = OP_RUNNING_POLL; - edac_mc_workq_setup(mci, edac_mc_get_poll_msec()); + edac_mc_workq_setup(mci, edac_mc_get_poll_msec(), true); } else { mci->op_state = OP_RUNNING_INTERRUPT; } diff --git a/drivers/edac/edac_mc_sysfs.c b/drivers/edac/edac_mc_sysfs.c index 51c0362acf5c..b335c6ab5efe 100644 --- a/drivers/edac/edac_mc_sysfs.c +++ b/drivers/edac/edac_mc_sysfs.c @@ -52,18 +52,20 @@ int edac_mc_get_poll_msec(void) static int edac_set_poll_msec(const char *val, struct kernel_param *kp) { - long l; + unsigned long l; int ret; if (!val) return -EINVAL; - ret = kstrtol(val, 0, &l); + ret = kstrtoul(val, 0, &l); if (ret) return ret; - if ((int)l != l) + + if (l < 1000) return -EINVAL; - *((int *)kp->arg) = l; + + *((unsigned long *)kp->arg) = l; /* notify edac_mc engine to reset the poll period */ edac_mc_reset_delay_period(l); diff --git a/drivers/edac/edac_module.h b/drivers/edac/edac_module.h index 3d139c6e7fe3..f2118bfcf8df 100644 --- a/drivers/edac/edac_module.h +++ b/drivers/edac/edac_module.h @@ -52,7 +52,7 @@ extern void edac_device_workq_setup(struct edac_device_ctl_info *edac_dev, extern void edac_device_workq_teardown(struct edac_device_ctl_info *edac_dev); extern void edac_device_reset_delay_period(struct edac_device_ctl_info *edac_dev, unsigned long value); -extern void edac_mc_reset_delay_period(int value); +extern void edac_mc_reset_delay_period(unsigned long value); extern void *edac_align_ptr(void **p, unsigned size, int n_elems); diff --git a/drivers/edac/i7300_edac.c b/drivers/edac/i7300_edac.c index d63f4798f7d0..57e96a3350f0 100644 --- a/drivers/edac/i7300_edac.c +++ b/drivers/edac/i7300_edac.c @@ -943,33 +943,35 @@ static int i7300_get_devices(struct mem_ctl_info *mci) /* Attempt to 'get' the MCH register we want */ pdev = NULL; - while (!pvt->pci_dev_16_1_fsb_addr_map || - !pvt->pci_dev_16_2_fsb_err_regs) { - pdev = pci_get_device(PCI_VENDOR_ID_INTEL, - PCI_DEVICE_ID_INTEL_I7300_MCH_ERR, pdev); - if (!pdev) { - /* End of list, leave */ - i7300_printk(KERN_ERR, - "'system address,Process Bus' " - "device not found:" - "vendor 0x%x device 0x%x ERR funcs " - "(broken BIOS?)\n", - PCI_VENDOR_ID_INTEL, - PCI_DEVICE_ID_INTEL_I7300_MCH_ERR); - goto error; - } - + while ((pdev = pci_get_device(PCI_VENDOR_ID_INTEL, + PCI_DEVICE_ID_INTEL_I7300_MCH_ERR, + pdev))) { /* Store device 16 funcs 1 and 2 */ switch (PCI_FUNC(pdev->devfn)) { case 1: - pvt->pci_dev_16_1_fsb_addr_map = pdev; + if (!pvt->pci_dev_16_1_fsb_addr_map) + pvt->pci_dev_16_1_fsb_addr_map = + pci_dev_get(pdev); break; case 2: - pvt->pci_dev_16_2_fsb_err_regs = pdev; + if (!pvt->pci_dev_16_2_fsb_err_regs) + pvt->pci_dev_16_2_fsb_err_regs = + pci_dev_get(pdev); break; } } + if (!pvt->pci_dev_16_1_fsb_addr_map || + !pvt->pci_dev_16_2_fsb_err_regs) { + /* At least one device was not found */ + i7300_printk(KERN_ERR, + "'system address,Process Bus' device not found:" + "vendor 0x%x device 0x%x ERR funcs (broken BIOS?)\n", + PCI_VENDOR_ID_INTEL, + PCI_DEVICE_ID_INTEL_I7300_MCH_ERR); + goto error; + } + edac_dbg(1, "System Address, processor bus- PCI Bus ID: %s %x:%x\n", pci_name(pvt->pci_dev_16_0_fsb_ctlr), pvt->pci_dev_16_0_fsb_ctlr->vendor, diff --git a/drivers/edac/i7core_edac.c b/drivers/edac/i7core_edac.c index 87533ca7752e..d871275196f6 100644 --- a/drivers/edac/i7core_edac.c +++ b/drivers/edac/i7core_edac.c @@ -1334,14 +1334,19 @@ static int i7core_get_onedevice(struct pci_dev **prev, * is at addr 8086:2c40, instead of 8086:2c41. So, we need * to probe for the alternate address in case of failure */ - if (dev_descr->dev_id == PCI_DEVICE_ID_INTEL_I7_NONCORE && !pdev) + if (dev_descr->dev_id == PCI_DEVICE_ID_INTEL_I7_NONCORE && !pdev) { + pci_dev_get(*prev); /* pci_get_device will put it */ pdev = pci_get_device(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_I7_NONCORE_ALT, *prev); + } - if (dev_descr->dev_id == PCI_DEVICE_ID_INTEL_LYNNFIELD_NONCORE && !pdev) + if (dev_descr->dev_id == PCI_DEVICE_ID_INTEL_LYNNFIELD_NONCORE && + !pdev) { + pci_dev_get(*prev); /* pci_get_device will put it */ pdev = pci_get_device(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_LYNNFIELD_NONCORE_ALT, *prev); + } if (!pdev) { if (*prev) { diff --git a/drivers/extcon/extcon-arizona.c b/drivers/extcon/extcon-arizona.c index c20602f601ee..98a14f6143a7 100644 --- a/drivers/extcon/extcon-arizona.c +++ b/drivers/extcon/extcon-arizona.c @@ -222,27 +222,19 @@ static void arizona_extcon_pulse_micbias(struct arizona_extcon_info *info) struct snd_soc_dapm_context *dapm = arizona->dapm; int ret; - mutex_lock(&dapm->card->dapm_mutex); - ret = snd_soc_dapm_force_enable_pin(dapm, widget); if (ret != 0) dev_warn(arizona->dev, "Failed to enable %s: %d\n", widget, ret); - mutex_unlock(&dapm->card->dapm_mutex); - snd_soc_dapm_sync(dapm); if (!arizona->pdata.micd_force_micbias) { - mutex_lock(&dapm->card->dapm_mutex); - ret = snd_soc_dapm_disable_pin(arizona->dapm, widget); if (ret != 0) dev_warn(arizona->dev, "Failed to disable %s: %d\n", widget, ret); - mutex_unlock(&dapm->card->dapm_mutex); - snd_soc_dapm_sync(dapm); } } @@ -304,16 +296,12 @@ static void arizona_stop_mic(struct arizona_extcon_info *info) ARIZONA_MICD_ENA, 0, &change); - mutex_lock(&dapm->card->dapm_mutex); - ret = snd_soc_dapm_disable_pin(dapm, widget); if (ret != 0) dev_warn(arizona->dev, "Failed to disable %s: %d\n", widget, ret); - mutex_unlock(&dapm->card->dapm_mutex); - snd_soc_dapm_sync(dapm); if (info->micd_reva) { diff --git a/drivers/fmc/fmc-write-eeprom.c b/drivers/fmc/fmc-write-eeprom.c index ee5b47904130..9bb2cbd5c9f2 100644 --- a/drivers/fmc/fmc-write-eeprom.c +++ b/drivers/fmc/fmc-write-eeprom.c @@ -27,7 +27,7 @@ FMC_PARAM_BUSID(fwe_drv); /* The "file=" is like the generic "gateware=" used elsewhere */ static char *fwe_file[FMC_MAX_CARDS]; static int fwe_file_n; -module_param_array_named(file, fwe_file, charp, &fwe_file_n, 444); +module_param_array_named(file, fwe_file, charp, &fwe_file_n, 0444); static int fwe_run_tlv(struct fmc_device *fmc, const struct firmware *fw, int write) diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig index 697338772b64..903f24d28ba0 100644 --- a/drivers/gpio/Kconfig +++ b/drivers/gpio/Kconfig @@ -403,6 +403,7 @@ config GPIO_GRGPIO config GPIO_TB10X bool + select GENERIC_IRQ_CHIP select OF_GPIO comment "I2C GPIO expanders:" diff --git a/drivers/gpio/gpio-bcm-kona.c b/drivers/gpio/gpio-bcm-kona.c index 233d088ac59f..f32357e2d78d 100644 --- a/drivers/gpio/gpio-bcm-kona.c +++ b/drivers/gpio/gpio-bcm-kona.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2012-2013 Broadcom Corporation + * Copyright (C) 2012-2014 Broadcom Corporation * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License as @@ -657,6 +657,6 @@ static struct platform_driver bcm_kona_gpio_driver = { module_platform_driver(bcm_kona_gpio_driver); -MODULE_AUTHOR("Broadcom"); +MODULE_AUTHOR("Broadcom Corporation <bcm-kernel-feedback-list@broadcom.com>"); MODULE_DESCRIPTION("Broadcom Kona GPIO Driver"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/gpio/gpio-clps711x.c b/drivers/gpio/gpio-clps711x.c index d3550274b8f7..3c2ba2ad0ada 100644 --- a/drivers/gpio/gpio-clps711x.c +++ b/drivers/gpio/gpio-clps711x.c @@ -97,3 +97,4 @@ module_platform_driver(clps711x_gpio_driver); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Alexander Shiyan <shc_work@mail.ru>"); MODULE_DESCRIPTION("CLPS711X GPIO driver"); +MODULE_ALIAS("platform:clps711x-gpio"); diff --git a/drivers/gpio/gpio-intel-mid.c b/drivers/gpio/gpio-intel-mid.c index d1b50ef5fab8..e585163f1ad5 100644 --- a/drivers/gpio/gpio-intel-mid.c +++ b/drivers/gpio/gpio-intel-mid.c @@ -394,8 +394,8 @@ static const struct irq_domain_ops intel_gpio_irq_ops = { static int intel_gpio_runtime_idle(struct device *dev) { - pm_schedule_suspend(dev, 500); - return -EBUSY; + int err = pm_schedule_suspend(dev, 500); + return err ?: -EBUSY; } static const struct dev_pm_ops intel_gpio_pm_ops = { diff --git a/drivers/gpio/gpio-xtensa.c b/drivers/gpio/gpio-xtensa.c index 1d136eceda62..7081304d6797 100644 --- a/drivers/gpio/gpio-xtensa.c +++ b/drivers/gpio/gpio-xtensa.c @@ -40,6 +40,8 @@ #error GPIO32 option is not enabled for your xtensa core variant #endif +#if XCHAL_HAVE_CP + static inline unsigned long enable_cp(unsigned long *cpenable) { unsigned long flags; @@ -57,6 +59,20 @@ static inline void disable_cp(unsigned long flags, unsigned long cpenable) local_irq_restore(flags); } +#else + +static inline unsigned long enable_cp(unsigned long *cpenable) +{ + *cpenable = 0; /* avoid uninitialized value warning */ + return 0; +} + +static inline void disable_cp(unsigned long flags, unsigned long cpenable) +{ +} + +#endif /* XCHAL_HAVE_CP */ + static int xtensa_impwire_get_direction(struct gpio_chip *gc, unsigned offset) { return 1; /* input only */ diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c index dffc836144cc..f4dc9b7a3831 100644 --- a/drivers/gpu/drm/drm_ioctl.c +++ b/drivers/gpu/drm/drm_ioctl.c @@ -296,6 +296,18 @@ int drm_getcap(struct drm_device *dev, void *data, struct drm_file *file_priv) case DRM_CAP_ASYNC_PAGE_FLIP: req->value = dev->mode_config.async_page_flip; break; + case DRM_CAP_CURSOR_WIDTH: + if (dev->mode_config.cursor_width) + req->value = dev->mode_config.cursor_width; + else + req->value = 64; + break; + case DRM_CAP_CURSOR_HEIGHT: + if (dev->mode_config.cursor_height) + req->value = dev->mode_config.cursor_height; + else + req->value = 64; + break; default: return -EINVAL; } diff --git a/drivers/gpu/drm/exynos/Kconfig b/drivers/gpu/drm/exynos/Kconfig index f227f544aa36..6e1a1a20cf6b 100644 --- a/drivers/gpu/drm/exynos/Kconfig +++ b/drivers/gpu/drm/exynos/Kconfig @@ -51,7 +51,7 @@ config DRM_EXYNOS_G2D config DRM_EXYNOS_IPP bool "Exynos DRM IPP" - depends on DRM_EXYNOS && !ARCH_MULTIPLATFORM + depends on DRM_EXYNOS help Choose this option if you want to use IPP feature for DRM. @@ -69,6 +69,6 @@ config DRM_EXYNOS_ROTATOR config DRM_EXYNOS_GSC bool "Exynos DRM GSC" - depends on DRM_EXYNOS_IPP && ARCH_EXYNOS5 + depends on DRM_EXYNOS_IPP && ARCH_EXYNOS5 && !ARCH_MULTIPLATFORM help Choose this option if you want to use Exynos GSC for DRM. diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.c b/drivers/gpu/drm/exynos/exynos_drm_drv.c index 9d096a0c5f8d..215131ab1dd2 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_drv.c +++ b/drivers/gpu/drm/exynos/exynos_drm_drv.c @@ -171,22 +171,24 @@ static int exynos_drm_open(struct drm_device *dev, struct drm_file *file) file->driver_priv = file_priv; ret = exynos_drm_subdrv_open(dev, file); - if (ret) { - kfree(file_priv); - file->driver_priv = NULL; - } + if (ret) + goto out; anon_filp = anon_inode_getfile("exynos_gem", &exynos_drm_gem_fops, NULL, 0); if (IS_ERR(anon_filp)) { - kfree(file_priv); - return PTR_ERR(anon_filp); + ret = PTR_ERR(anon_filp); + goto out; } anon_filp->f_mode = FMODE_READ | FMODE_WRITE; file_priv->anon_filp = anon_filp; return ret; +out: + kfree(file_priv); + file->driver_priv = NULL; + return ret; } static void exynos_drm_preclose(struct drm_device *dev, diff --git a/drivers/gpu/drm/exynos/exynos_drm_g2d.c b/drivers/gpu/drm/exynos/exynos_drm_g2d.c index 380aec28840b..6c1885eedfdf 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_g2d.c +++ b/drivers/gpu/drm/exynos/exynos_drm_g2d.c @@ -607,7 +607,7 @@ static enum g2d_reg_type g2d_get_reg_type(int reg_offset) reg_type = REG_TYPE_NONE; DRM_ERROR("Unknown register offset![%d]\n", reg_offset); break; - }; + } return reg_type; } diff --git a/drivers/gpu/drm/exynos/exynos_drm_ipp.c b/drivers/gpu/drm/exynos/exynos_drm_ipp.c index d519a4e5fe40..09312b877470 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_ipp.c +++ b/drivers/gpu/drm/exynos/exynos_drm_ipp.c @@ -16,7 +16,6 @@ #include <linux/types.h> #include <linux/clk.h> #include <linux/pm_runtime.h> -#include <plat/map-base.h> #include <drm/drmP.h> #include <drm/exynos_drm.h> @@ -826,7 +825,7 @@ static void ipp_put_event(struct drm_exynos_ipp_cmd_node *c_node, DRM_DEBUG_KMS("count[%d]e[0x%x]\n", count++, (int)e); /* - * quf == NULL condition means all event deletion. + * qbuf == NULL condition means all event deletion. * stop operations want to delete all event list. * another case delete only same buf id. */ diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.c b/drivers/gpu/drm/exynos/exynos_hdmi.c index a0e10aeb0e67..c021ddc1ffb4 100644 --- a/drivers/gpu/drm/exynos/exynos_hdmi.c +++ b/drivers/gpu/drm/exynos/exynos_hdmi.c @@ -34,6 +34,7 @@ #include <linux/io.h> #include <linux/of.h> #include <linux/of_gpio.h> +#include <linux/hdmi.h> #include <drm/exynos_drm.h> @@ -59,19 +60,6 @@ #define HDMI_AUI_VERSION 0x01 #define HDMI_AUI_LENGTH 0x0A -/* HDMI infoframe to configure HDMI out packet header, AUI and AVI */ -enum HDMI_PACKET_TYPE { - /* refer to Table 5-8 Packet Type in HDMI specification v1.4a */ - /* InfoFrame packet type */ - HDMI_PACKET_TYPE_INFOFRAME = 0x80, - /* Vendor-Specific InfoFrame */ - HDMI_PACKET_TYPE_VSI = HDMI_PACKET_TYPE_INFOFRAME + 1, - /* Auxiliary Video information InfoFrame */ - HDMI_PACKET_TYPE_AVI = HDMI_PACKET_TYPE_INFOFRAME + 2, - /* Audio information InfoFrame */ - HDMI_PACKET_TYPE_AUI = HDMI_PACKET_TYPE_INFOFRAME + 4 -}; - enum hdmi_type { HDMI_TYPE13, HDMI_TYPE14, @@ -379,12 +367,6 @@ static const struct hdmiphy_config hdmiphy_v14_configs[] = { }, }; -struct hdmi_infoframe { - enum HDMI_PACKET_TYPE type; - u8 ver; - u8 len; -}; - static inline u32 hdmi_reg_read(struct hdmi_context *hdata, u32 reg_id) { return readl(hdata->regs + reg_id); @@ -682,7 +664,7 @@ static u8 hdmi_chksum(struct hdmi_context *hdata, } static void hdmi_reg_infoframe(struct hdmi_context *hdata, - struct hdmi_infoframe *infoframe) + union hdmi_infoframe *infoframe) { u32 hdr_sum; u8 chksum; @@ -700,13 +682,15 @@ static void hdmi_reg_infoframe(struct hdmi_context *hdata, return; } - switch (infoframe->type) { - case HDMI_PACKET_TYPE_AVI: + switch (infoframe->any.type) { + case HDMI_INFOFRAME_TYPE_AVI: hdmi_reg_writeb(hdata, HDMI_AVI_CON, HDMI_AVI_CON_EVERY_VSYNC); - hdmi_reg_writeb(hdata, HDMI_AVI_HEADER0, infoframe->type); - hdmi_reg_writeb(hdata, HDMI_AVI_HEADER1, infoframe->ver); - hdmi_reg_writeb(hdata, HDMI_AVI_HEADER2, infoframe->len); - hdr_sum = infoframe->type + infoframe->ver + infoframe->len; + hdmi_reg_writeb(hdata, HDMI_AVI_HEADER0, infoframe->any.type); + hdmi_reg_writeb(hdata, HDMI_AVI_HEADER1, + infoframe->any.version); + hdmi_reg_writeb(hdata, HDMI_AVI_HEADER2, infoframe->any.length); + hdr_sum = infoframe->any.type + infoframe->any.version + + infoframe->any.length; /* Output format zero hardcoded ,RGB YBCR selection */ hdmi_reg_writeb(hdata, HDMI_AVI_BYTE(1), 0 << 5 | @@ -722,18 +706,20 @@ static void hdmi_reg_infoframe(struct hdmi_context *hdata, hdmi_reg_writeb(hdata, HDMI_AVI_BYTE(4), vic); chksum = hdmi_chksum(hdata, HDMI_AVI_BYTE(1), - infoframe->len, hdr_sum); + infoframe->any.length, hdr_sum); DRM_DEBUG_KMS("AVI checksum = 0x%x\n", chksum); hdmi_reg_writeb(hdata, HDMI_AVI_CHECK_SUM, chksum); break; - case HDMI_PACKET_TYPE_AUI: + case HDMI_INFOFRAME_TYPE_AUDIO: hdmi_reg_writeb(hdata, HDMI_AUI_CON, 0x02); - hdmi_reg_writeb(hdata, HDMI_AUI_HEADER0, infoframe->type); - hdmi_reg_writeb(hdata, HDMI_AUI_HEADER1, infoframe->ver); - hdmi_reg_writeb(hdata, HDMI_AUI_HEADER2, infoframe->len); - hdr_sum = infoframe->type + infoframe->ver + infoframe->len; + hdmi_reg_writeb(hdata, HDMI_AUI_HEADER0, infoframe->any.type); + hdmi_reg_writeb(hdata, HDMI_AUI_HEADER1, + infoframe->any.version); + hdmi_reg_writeb(hdata, HDMI_AUI_HEADER2, infoframe->any.length); + hdr_sum = infoframe->any.type + infoframe->any.version + + infoframe->any.length; chksum = hdmi_chksum(hdata, HDMI_AUI_BYTE(1), - infoframe->len, hdr_sum); + infoframe->any.length, hdr_sum); DRM_DEBUG_KMS("AUI checksum = 0x%x\n", chksum); hdmi_reg_writeb(hdata, HDMI_AUI_CHECK_SUM, chksum); break; @@ -985,7 +971,7 @@ static void hdmi_conf_reset(struct hdmi_context *hdata) static void hdmi_conf_init(struct hdmi_context *hdata) { - struct hdmi_infoframe infoframe; + union hdmi_infoframe infoframe; /* disable HPD interrupts from HDMI IP block, use GPIO instead */ hdmi_reg_writemask(hdata, HDMI_INTC_CON, 0, HDMI_INTC_EN_GLOBAL | @@ -1021,14 +1007,14 @@ static void hdmi_conf_init(struct hdmi_context *hdata) hdmi_reg_writeb(hdata, HDMI_V13_AUI_CON, 0x02); hdmi_reg_writeb(hdata, HDMI_V13_ACR_CON, 0x04); } else { - infoframe.type = HDMI_PACKET_TYPE_AVI; - infoframe.ver = HDMI_AVI_VERSION; - infoframe.len = HDMI_AVI_LENGTH; + infoframe.any.type = HDMI_INFOFRAME_TYPE_AVI; + infoframe.any.version = HDMI_AVI_VERSION; + infoframe.any.length = HDMI_AVI_LENGTH; hdmi_reg_infoframe(hdata, &infoframe); - infoframe.type = HDMI_PACKET_TYPE_AUI; - infoframe.ver = HDMI_AUI_VERSION; - infoframe.len = HDMI_AUI_LENGTH; + infoframe.any.type = HDMI_INFOFRAME_TYPE_AUDIO; + infoframe.any.version = HDMI_AUI_VERSION; + infoframe.any.length = HDMI_AUI_LENGTH; hdmi_reg_infoframe(hdata, &infoframe); /* enable AVI packet every vsync, fixes purple line problem */ diff --git a/drivers/gpu/drm/i2c/tda998x_drv.c b/drivers/gpu/drm/i2c/tda998x_drv.c index 400b0c4a10fb..faa77f543a07 100644 --- a/drivers/gpu/drm/i2c/tda998x_drv.c +++ b/drivers/gpu/drm/i2c/tda998x_drv.c @@ -208,7 +208,7 @@ struct tda998x_priv { # define PLL_SERIAL_1_SRL_IZ(x) (((x) & 3) << 1) # define PLL_SERIAL_1_SRL_MAN_IZ (1 << 6) #define REG_PLL_SERIAL_2 REG(0x02, 0x01) /* read/write */ -# define PLL_SERIAL_2_SRL_NOSC(x) (((x) & 3) << 0) +# define PLL_SERIAL_2_SRL_NOSC(x) ((x) << 0) # define PLL_SERIAL_2_SRL_PR(x) (((x) & 0xf) << 4) #define REG_PLL_SERIAL_3 REG(0x02, 0x02) /* read/write */ # define PLL_SERIAL_3_SRL_CCIR (1 << 0) @@ -528,10 +528,10 @@ tda998x_write_aif(struct drm_encoder *encoder, struct tda998x_encoder_params *p) { uint8_t buf[PB(5) + 1]; + memset(buf, 0, sizeof(buf)); buf[HB(0)] = 0x84; buf[HB(1)] = 0x01; buf[HB(2)] = 10; - buf[PB(0)] = 0; buf[PB(1)] = p->audio_frame[1] & 0x07; /* CC */ buf[PB(2)] = p->audio_frame[2] & 0x1c; /* SF */ buf[PB(4)] = p->audio_frame[4]; @@ -824,6 +824,11 @@ tda998x_encoder_mode_set(struct drm_encoder *encoder, } div = 148500 / mode->clock; + if (div != 0) { + div--; + if (div > 3) + div = 3; + } /* mute the audio FIFO: */ reg_set(encoder, REG_AIP_CNTRL_0, AIP_CNTRL_0_RST_FIFO); @@ -913,7 +918,7 @@ tda998x_encoder_mode_set(struct drm_encoder *encoder, if (priv->rev == TDA19988) { /* let incoming pixels fill the active space (if any) */ - reg_write(encoder, REG_ENABLE_SPACE, 0x01); + reg_write(encoder, REG_ENABLE_SPACE, 0x00); } /* must be last register set: */ @@ -1094,6 +1099,8 @@ tda998x_encoder_destroy(struct drm_encoder *encoder) { struct tda998x_priv *priv = to_tda998x_priv(encoder); drm_i2c_encoder_destroy(encoder); + if (priv->cec) + i2c_unregister_device(priv->cec); kfree(priv); } @@ -1142,8 +1149,12 @@ tda998x_encoder_init(struct i2c_client *client, priv->vip_cntrl_1 = VIP_CNTRL_1_SWAP_C(0) | VIP_CNTRL_1_SWAP_D(1); priv->vip_cntrl_2 = VIP_CNTRL_2_SWAP_E(4) | VIP_CNTRL_2_SWAP_F(5); - priv->current_page = 0; + priv->current_page = 0xff; priv->cec = i2c_new_dummy(client->adapter, 0x34); + if (!priv->cec) { + kfree(priv); + return -ENODEV; + } priv->dpms = DRM_MODE_DPMS_OFF; encoder_slave->slave_priv = priv; diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 4a2bf8e3f739..df77e20e3c3d 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -1831,6 +1831,14 @@ struct drm_i915_file_private { /* Early gen2 have a totally busted CS tlb and require pinned batches. */ #define HAS_BROKEN_CS_TLB(dev) (IS_I830(dev) || IS_845G(dev)) +/* + * dp aux and gmbus irq on gen4 seems to be able to generate legacy interrupts + * even when in MSI mode. This results in spurious interrupt warnings if the + * legacy irq no. is shared with another device. The kernel then disables that + * interrupt source and so prevents the other device from working properly. + */ +#define HAS_AUX_IRQ(dev) (INTEL_INFO(dev)->gen >= 5) +#define HAS_GMBUS_IRQ(dev) (INTEL_INFO(dev)->gen >= 5) /* With the 945 and later, Y tiling got adjusted so that it was 32 128-byte * rows, which changed the alignment requirements and fence programming. diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c index d7fd2fd2f0a5..990cf8f43efd 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.c +++ b/drivers/gpu/drm/i915/i915_gpu_error.c @@ -146,7 +146,10 @@ static void i915_error_vprintf(struct drm_i915_error_state_buf *e, va_list tmp; va_copy(tmp, args); - if (!__i915_error_seek(e, vsnprintf(NULL, 0, f, tmp))) + len = vsnprintf(NULL, 0, f, tmp); + va_end(tmp); + + if (!__i915_error_seek(e, len)) return; } diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index 17d8fcb1b6f7..9fec71175571 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -567,8 +567,7 @@ static u32 i915_get_vblank_counter(struct drm_device *dev, int pipe) vbl_start = mode->crtc_vblank_start * mode->crtc_htotal; } else { - enum transcoder cpu_transcoder = - intel_pipe_to_cpu_transcoder(dev_priv, pipe); + enum transcoder cpu_transcoder = (enum transcoder) pipe; u32 htotal; htotal = ((I915_READ(HTOTAL(cpu_transcoder)) >> 16) & 0x1fff) + 1; diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 9fa24347963a..4c1672809493 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -8586,6 +8586,20 @@ static int intel_gen7_queue_flip(struct drm_device *dev, if (ring->id == RCS) len += 6; + /* + * BSpec MI_DISPLAY_FLIP for IVB: + * "The full packet must be contained within the same cache line." + * + * Currently the LRI+SRM+MI_DISPLAY_FLIP all fit within the same + * cacheline, if we ever start emitting more commands before + * the MI_DISPLAY_FLIP we may need to first emit everything else, + * then do the cacheline alignment, and finally emit the + * MI_DISPLAY_FLIP. + */ + ret = intel_ring_cacheline_align(ring); + if (ret) + goto err_unpin; + ret = intel_ring_begin(ring, len); if (ret) goto err_unpin; diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index 5ede4e8e290d..57552eb386b0 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -404,7 +404,7 @@ intel_dp_aux_ch(struct intel_dp *intel_dp, int i, ret, recv_bytes; uint32_t status; int try, precharge, clock = 0; - bool has_aux_irq = true; + bool has_aux_irq = HAS_AUX_IRQ(dev); uint32_t timeout; /* dp aux is extremely sensitive to irq latency, hence request the @@ -537,6 +537,7 @@ intel_dp_aux_native_write(struct intel_dp *intel_dp, uint8_t msg[20]; int msg_bytes; uint8_t ack; + int retry; if (WARN_ON(send_bytes > 16)) return -E2BIG; @@ -548,19 +549,21 @@ intel_dp_aux_native_write(struct intel_dp *intel_dp, msg[3] = send_bytes - 1; memcpy(&msg[4], send, send_bytes); msg_bytes = send_bytes + 4; - for (;;) { + for (retry = 0; retry < 7; retry++) { ret = intel_dp_aux_ch(intel_dp, msg, msg_bytes, &ack, 1); if (ret < 0) return ret; ack >>= 4; if ((ack & DP_AUX_NATIVE_REPLY_MASK) == DP_AUX_NATIVE_REPLY_ACK) - break; + return send_bytes; else if ((ack & DP_AUX_NATIVE_REPLY_MASK) == DP_AUX_NATIVE_REPLY_DEFER) - udelay(100); + usleep_range(400, 500); else return -EIO; } - return send_bytes; + + DRM_ERROR("too many retries, giving up\n"); + return -EIO; } /* Write a single byte to the aux channel in native mode */ @@ -582,6 +585,7 @@ intel_dp_aux_native_read(struct intel_dp *intel_dp, int reply_bytes; uint8_t ack; int ret; + int retry; if (WARN_ON(recv_bytes > 19)) return -E2BIG; @@ -595,7 +599,7 @@ intel_dp_aux_native_read(struct intel_dp *intel_dp, msg_bytes = 4; reply_bytes = recv_bytes + 1; - for (;;) { + for (retry = 0; retry < 7; retry++) { ret = intel_dp_aux_ch(intel_dp, msg, msg_bytes, reply, reply_bytes); if (ret == 0) @@ -608,10 +612,13 @@ intel_dp_aux_native_read(struct intel_dp *intel_dp, return ret - 1; } else if ((ack & DP_AUX_NATIVE_REPLY_MASK) == DP_AUX_NATIVE_REPLY_DEFER) - udelay(100); + usleep_range(400, 500); else return -EIO; } + + DRM_ERROR("too many retries, giving up\n"); + return -EIO; } static int @@ -1869,10 +1876,12 @@ static void vlv_pre_enable_dp(struct intel_encoder *encoder) mutex_unlock(&dev_priv->dpio_lock); - /* init power sequencer on this pipe and port */ - intel_dp_init_panel_power_sequencer(dev, intel_dp, &power_seq); - intel_dp_init_panel_power_sequencer_registers(dev, intel_dp, - &power_seq); + if (is_edp(intel_dp)) { + /* init power sequencer on this pipe and port */ + intel_dp_init_panel_power_sequencer(dev, intel_dp, &power_seq); + intel_dp_init_panel_power_sequencer_registers(dev, intel_dp, + &power_seq); + } intel_enable_dp(encoder); diff --git a/drivers/gpu/drm/i915/intel_i2c.c b/drivers/gpu/drm/i915/intel_i2c.c index b1dc33f47899..d33b61d0dd33 100644 --- a/drivers/gpu/drm/i915/intel_i2c.c +++ b/drivers/gpu/drm/i915/intel_i2c.c @@ -258,13 +258,6 @@ intel_gpio_setup(struct intel_gmbus *bus, u32 pin) algo->data = bus; } -/* - * gmbus on gen4 seems to be able to generate legacy interrupts even when in MSI - * mode. This results in spurious interrupt warnings if the legacy irq no. is - * shared with another device. The kernel then disables that interrupt source - * and so prevents the other device from working properly. - */ -#define HAS_GMBUS_IRQ(dev) (INTEL_INFO(dev)->gen >= 5) static int gmbus_wait_hw_status(struct drm_i915_private *dev_priv, u32 gmbus2_status, diff --git a/drivers/gpu/drm/i915/intel_opregion.c b/drivers/gpu/drm/i915/intel_opregion.c index 4e960ec7419f..acde2945eb8a 100644 --- a/drivers/gpu/drm/i915/intel_opregion.c +++ b/drivers/gpu/drm/i915/intel_opregion.c @@ -226,6 +226,8 @@ struct opregion_asle { #define ACPI_DIGITAL_OUTPUT (3<<8) #define ACPI_LVDS_OUTPUT (4<<8) +#define MAX_DSLP 1500 + #ifdef CONFIG_ACPI static int swsci(struct drm_device *dev, u32 function, u32 parm, u32 *parm_out) { @@ -260,10 +262,11 @@ static int swsci(struct drm_device *dev, u32 function, u32 parm, u32 *parm_out) /* The spec says 2ms should be the default, but it's too small * for some machines. */ dslp = 50; - } else if (dslp > 500) { + } else if (dslp > MAX_DSLP) { /* Hey bios, trust must be earned. */ - WARN_ONCE(1, "excessive driver sleep timeout (DSPL) %u\n", dslp); - dslp = 500; + DRM_INFO_ONCE("ACPI BIOS requests an excessive sleep of %u ms, " + "using %u ms instead\n", dslp, MAX_DSLP); + dslp = MAX_DSLP; } /* The spec tells us to do this, but we are the only user... */ diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index b7f1742caf87..31b36c5ac894 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -1653,6 +1653,27 @@ int intel_ring_begin(struct intel_ring_buffer *ring, return 0; } +/* Align the ring tail to a cacheline boundary */ +int intel_ring_cacheline_align(struct intel_ring_buffer *ring) +{ + int num_dwords = (64 - (ring->tail & 63)) / sizeof(uint32_t); + int ret; + + if (num_dwords == 0) + return 0; + + ret = intel_ring_begin(ring, num_dwords); + if (ret) + return ret; + + while (num_dwords--) + intel_ring_emit(ring, MI_NOOP); + + intel_ring_advance(ring); + + return 0; +} + void intel_ring_init_seqno(struct intel_ring_buffer *ring, u32 seqno) { struct drm_i915_private *dev_priv = ring->dev->dev_private; diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h index 71a73f4fe252..0b243ce33714 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.h +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h @@ -233,6 +233,7 @@ intel_write_status_page(struct intel_ring_buffer *ring, void intel_cleanup_ring_buffer(struct intel_ring_buffer *ring); int __must_check intel_ring_begin(struct intel_ring_buffer *ring, int n); +int __must_check intel_ring_cacheline_align(struct intel_ring_buffer *ring); static inline void intel_ring_emit(struct intel_ring_buffer *ring, u32 data) { diff --git a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_crtc.c b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_crtc.c index 1964f4f0d452..84c5b13b33c9 100644 --- a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_crtc.c +++ b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_crtc.c @@ -39,6 +39,7 @@ struct mdp4_crtc { spinlock_t lock; bool stale; uint32_t width, height; + uint32_t x, y; /* next cursor to scan-out: */ uint32_t next_iova; @@ -57,9 +58,16 @@ struct mdp4_crtc { #define PENDING_FLIP 0x2 atomic_t pending; - /* the fb that we currently hold a scanout ref to: */ + /* the fb that we logically (from PoV of KMS API) hold a ref + * to. Which we may not yet be scanning out (we may still + * be scanning out previous in case of page_flip while waiting + * for gpu rendering to complete: + */ struct drm_framebuffer *fb; + /* the fb that we currently hold a scanout ref to: */ + struct drm_framebuffer *scanout_fb; + /* for unref'ing framebuffers after scanout completes: */ struct drm_flip_work unref_fb_work; @@ -77,24 +85,73 @@ static struct mdp4_kms *get_kms(struct drm_crtc *crtc) return to_mdp4_kms(to_mdp_kms(priv->kms)); } -static void update_fb(struct drm_crtc *crtc, bool async, - struct drm_framebuffer *new_fb) +static void request_pending(struct drm_crtc *crtc, uint32_t pending) { struct mdp4_crtc *mdp4_crtc = to_mdp4_crtc(crtc); - struct drm_framebuffer *old_fb = mdp4_crtc->fb; - if (old_fb) - drm_flip_work_queue(&mdp4_crtc->unref_fb_work, old_fb); + atomic_or(pending, &mdp4_crtc->pending); + mdp_irq_register(&get_kms(crtc)->base, &mdp4_crtc->vblank); +} + +static void crtc_flush(struct drm_crtc *crtc) +{ + struct mdp4_crtc *mdp4_crtc = to_mdp4_crtc(crtc); + struct mdp4_kms *mdp4_kms = get_kms(crtc); + uint32_t i, flush = 0; + + for (i = 0; i < ARRAY_SIZE(mdp4_crtc->planes); i++) { + struct drm_plane *plane = mdp4_crtc->planes[i]; + if (plane) { + enum mdp4_pipe pipe_id = mdp4_plane_pipe(plane); + flush |= pipe2flush(pipe_id); + } + } + flush |= ovlp2flush(mdp4_crtc->ovlp); + + DBG("%s: flush=%08x", mdp4_crtc->name, flush); + + mdp4_write(mdp4_kms, REG_MDP4_OVERLAY_FLUSH, flush); +} + +static void update_fb(struct drm_crtc *crtc, struct drm_framebuffer *new_fb) +{ + struct mdp4_crtc *mdp4_crtc = to_mdp4_crtc(crtc); + struct drm_framebuffer *old_fb = mdp4_crtc->fb; /* grab reference to incoming scanout fb: */ drm_framebuffer_reference(new_fb); mdp4_crtc->base.fb = new_fb; mdp4_crtc->fb = new_fb; - if (!async) { - /* enable vblank to pick up the old_fb */ - mdp_irq_register(&get_kms(crtc)->base, &mdp4_crtc->vblank); - } + if (old_fb) + drm_flip_work_queue(&mdp4_crtc->unref_fb_work, old_fb); +} + +/* unlike update_fb(), take a ref to the new scanout fb *before* updating + * plane, then call this. Needed to ensure we don't unref the buffer that + * is actually still being scanned out. + * + * Note that this whole thing goes away with atomic.. since we can defer + * calling into driver until rendering is done. + */ +static void update_scanout(struct drm_crtc *crtc, struct drm_framebuffer *fb) +{ + struct mdp4_crtc *mdp4_crtc = to_mdp4_crtc(crtc); + + /* flush updates, to make sure hw is updated to new scanout fb, + * so that we can safely queue unref to current fb (ie. next + * vblank we know hw is done w/ previous scanout_fb). + */ + crtc_flush(crtc); + + if (mdp4_crtc->scanout_fb) + drm_flip_work_queue(&mdp4_crtc->unref_fb_work, + mdp4_crtc->scanout_fb); + + mdp4_crtc->scanout_fb = fb; + + /* enable vblank to complete flip: */ + request_pending(crtc, PENDING_FLIP); } /* if file!=NULL, this is preclose potential cancel-flip path */ @@ -120,34 +177,6 @@ static void complete_flip(struct drm_crtc *crtc, struct drm_file *file) spin_unlock_irqrestore(&dev->event_lock, flags); } -static void crtc_flush(struct drm_crtc *crtc) -{ - struct mdp4_crtc *mdp4_crtc = to_mdp4_crtc(crtc); - struct mdp4_kms *mdp4_kms = get_kms(crtc); - uint32_t i, flush = 0; - - for (i = 0; i < ARRAY_SIZE(mdp4_crtc->planes); i++) { - struct drm_plane *plane = mdp4_crtc->planes[i]; - if (plane) { - enum mdp4_pipe pipe_id = mdp4_plane_pipe(plane); - flush |= pipe2flush(pipe_id); - } - } - flush |= ovlp2flush(mdp4_crtc->ovlp); - - DBG("%s: flush=%08x", mdp4_crtc->name, flush); - - mdp4_write(mdp4_kms, REG_MDP4_OVERLAY_FLUSH, flush); -} - -static void request_pending(struct drm_crtc *crtc, uint32_t pending) -{ - struct mdp4_crtc *mdp4_crtc = to_mdp4_crtc(crtc); - - atomic_or(pending, &mdp4_crtc->pending); - mdp_irq_register(&get_kms(crtc)->base, &mdp4_crtc->vblank); -} - static void pageflip_cb(struct msm_fence_cb *cb) { struct mdp4_crtc *mdp4_crtc = @@ -158,11 +187,9 @@ static void pageflip_cb(struct msm_fence_cb *cb) if (!fb) return; + drm_framebuffer_reference(fb); mdp4_plane_set_scanout(mdp4_crtc->plane, fb); - crtc_flush(crtc); - - /* enable vblank to complete flip: */ - request_pending(crtc, PENDING_FLIP); + update_scanout(crtc, fb); } static void unref_fb_worker(struct drm_flip_work *work, void *val) @@ -320,6 +347,20 @@ static int mdp4_crtc_mode_set(struct drm_crtc *crtc, mode->vsync_end, mode->vtotal, mode->type, mode->flags); + /* grab extra ref for update_scanout() */ + drm_framebuffer_reference(crtc->fb); + + ret = mdp4_plane_mode_set(mdp4_crtc->plane, crtc, crtc->fb, + 0, 0, mode->hdisplay, mode->vdisplay, + x << 16, y << 16, + mode->hdisplay << 16, mode->vdisplay << 16); + if (ret) { + drm_framebuffer_unreference(crtc->fb); + dev_err(crtc->dev->dev, "%s: failed to set mode on plane: %d\n", + mdp4_crtc->name, ret); + return ret; + } + mdp4_write(mdp4_kms, REG_MDP4_DMA_SRC_SIZE(dma), MDP4_DMA_SRC_SIZE_WIDTH(mode->hdisplay) | MDP4_DMA_SRC_SIZE_HEIGHT(mode->vdisplay)); @@ -341,24 +382,15 @@ static int mdp4_crtc_mode_set(struct drm_crtc *crtc, mdp4_write(mdp4_kms, REG_MDP4_OVLP_CFG(ovlp), 1); - update_fb(crtc, false, crtc->fb); - - ret = mdp4_plane_mode_set(mdp4_crtc->plane, crtc, crtc->fb, - 0, 0, mode->hdisplay, mode->vdisplay, - x << 16, y << 16, - mode->hdisplay << 16, mode->vdisplay << 16); - if (ret) { - dev_err(crtc->dev->dev, "%s: failed to set mode on plane: %d\n", - mdp4_crtc->name, ret); - return ret; - } - if (dma == DMA_E) { mdp4_write(mdp4_kms, REG_MDP4_DMA_E_QUANT(0), 0x00ff0000); mdp4_write(mdp4_kms, REG_MDP4_DMA_E_QUANT(1), 0x00ff0000); mdp4_write(mdp4_kms, REG_MDP4_DMA_E_QUANT(2), 0x00ff0000); } + update_fb(crtc, crtc->fb); + update_scanout(crtc, crtc->fb); + return 0; } @@ -385,13 +417,24 @@ static int mdp4_crtc_mode_set_base(struct drm_crtc *crtc, int x, int y, struct mdp4_crtc *mdp4_crtc = to_mdp4_crtc(crtc); struct drm_plane *plane = mdp4_crtc->plane; struct drm_display_mode *mode = &crtc->mode; + int ret; - update_fb(crtc, false, crtc->fb); + /* grab extra ref for update_scanout() */ + drm_framebuffer_reference(crtc->fb); - return mdp4_plane_mode_set(plane, crtc, crtc->fb, + ret = mdp4_plane_mode_set(plane, crtc, crtc->fb, 0, 0, mode->hdisplay, mode->vdisplay, x << 16, y << 16, mode->hdisplay << 16, mode->vdisplay << 16); + if (ret) { + drm_framebuffer_unreference(crtc->fb); + return ret; + } + + update_fb(crtc, crtc->fb); + update_scanout(crtc, crtc->fb); + + return 0; } static void mdp4_crtc_load_lut(struct drm_crtc *crtc) @@ -419,7 +462,7 @@ static int mdp4_crtc_page_flip(struct drm_crtc *crtc, mdp4_crtc->event = event; spin_unlock_irqrestore(&dev->event_lock, flags); - update_fb(crtc, true, new_fb); + update_fb(crtc, new_fb); return msm_gem_queue_inactive_cb(obj, &mdp4_crtc->pageflip_cb); } @@ -442,12 +485,12 @@ static int mdp4_crtc_set_property(struct drm_crtc *crtc, static void update_cursor(struct drm_crtc *crtc) { struct mdp4_crtc *mdp4_crtc = to_mdp4_crtc(crtc); + struct mdp4_kms *mdp4_kms = get_kms(crtc); enum mdp4_dma dma = mdp4_crtc->dma; unsigned long flags; spin_lock_irqsave(&mdp4_crtc->cursor.lock, flags); if (mdp4_crtc->cursor.stale) { - struct mdp4_kms *mdp4_kms = get_kms(crtc); struct drm_gem_object *next_bo = mdp4_crtc->cursor.next_bo; struct drm_gem_object *prev_bo = mdp4_crtc->cursor.scanout_bo; uint32_t iova = mdp4_crtc->cursor.next_iova; @@ -479,6 +522,11 @@ static void update_cursor(struct drm_crtc *crtc) mdp4_crtc->cursor.scanout_bo = next_bo; mdp4_crtc->cursor.stale = false; } + + mdp4_write(mdp4_kms, REG_MDP4_DMA_CURSOR_POS(dma), + MDP4_DMA_CURSOR_POS_X(mdp4_crtc->cursor.x) | + MDP4_DMA_CURSOR_POS_Y(mdp4_crtc->cursor.y)); + spin_unlock_irqrestore(&mdp4_crtc->cursor.lock, flags); } @@ -530,6 +578,7 @@ static int mdp4_crtc_cursor_set(struct drm_crtc *crtc, drm_gem_object_unreference_unlocked(old_bo); } + crtc_flush(crtc); request_pending(crtc, PENDING_CURSOR); return 0; @@ -542,12 +591,15 @@ fail: static int mdp4_crtc_cursor_move(struct drm_crtc *crtc, int x, int y) { struct mdp4_crtc *mdp4_crtc = to_mdp4_crtc(crtc); - struct mdp4_kms *mdp4_kms = get_kms(crtc); - enum mdp4_dma dma = mdp4_crtc->dma; + unsigned long flags; - mdp4_write(mdp4_kms, REG_MDP4_DMA_CURSOR_POS(dma), - MDP4_DMA_CURSOR_POS_X(x) | - MDP4_DMA_CURSOR_POS_Y(y)); + spin_lock_irqsave(&mdp4_crtc->cursor.lock, flags); + mdp4_crtc->cursor.x = x; + mdp4_crtc->cursor.y = y; + spin_unlock_irqrestore(&mdp4_crtc->cursor.lock, flags); + + crtc_flush(crtc); + request_pending(crtc, PENDING_CURSOR); return 0; } @@ -713,6 +765,7 @@ struct drm_crtc *mdp4_crtc_init(struct drm_device *dev, crtc = &mdp4_crtc->base; mdp4_crtc->plane = plane; + mdp4_crtc->id = id; mdp4_crtc->ovlp = ovlp_id; mdp4_crtc->dma = dma_id; diff --git a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_plane.c b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_plane.c index 2406027200ec..1e893dd13859 100644 --- a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_plane.c +++ b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_plane.c @@ -170,8 +170,8 @@ int mdp4_plane_mode_set(struct drm_plane *plane, MDP4_PIPE_DST_SIZE_HEIGHT(crtc_h)); mdp4_write(mdp4_kms, REG_MDP4_PIPE_DST_XY(pipe), - MDP4_PIPE_SRC_XY_X(crtc_x) | - MDP4_PIPE_SRC_XY_Y(crtc_y)); + MDP4_PIPE_DST_XY_X(crtc_x) | + MDP4_PIPE_DST_XY_Y(crtc_y)); mdp4_plane_set_scanout(plane, fb); diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_crtc.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_crtc.c index 71a3b2345eb3..f2794021f086 100644 --- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_crtc.c +++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_crtc.c @@ -296,6 +296,7 @@ static int mdp5_crtc_mode_set(struct drm_crtc *crtc, x << 16, y << 16, mode->hdisplay << 16, mode->vdisplay << 16); if (ret) { + drm_framebuffer_unreference(crtc->fb); dev_err(crtc->dev->dev, "%s: failed to set mode on plane: %d\n", mdp5_crtc->name, ret); return ret; @@ -343,11 +344,15 @@ static int mdp5_crtc_mode_set_base(struct drm_crtc *crtc, int x, int y, 0, 0, mode->hdisplay, mode->vdisplay, x << 16, y << 16, mode->hdisplay << 16, mode->vdisplay << 16); + if (ret) { + drm_framebuffer_unreference(crtc->fb); + return ret; + } update_fb(crtc, crtc->fb); update_scanout(crtc, crtc->fb); - return ret; + return 0; } static void mdp5_crtc_load_lut(struct drm_crtc *crtc) diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c index d8d60c969ac7..3da8264d3039 100644 --- a/drivers/gpu/drm/msm/msm_gem.c +++ b/drivers/gpu/drm/msm/msm_gem.c @@ -644,7 +644,7 @@ struct drm_gem_object *msm_gem_new(struct drm_device *dev, fail: if (obj) - drm_gem_object_unreference_unlocked(obj); + drm_gem_object_unreference(obj); return ERR_PTR(ret); } diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c index 5281d4bc37f7..5423e914e491 100644 --- a/drivers/gpu/drm/msm/msm_gem_submit.c +++ b/drivers/gpu/drm/msm/msm_gem_submit.c @@ -163,7 +163,7 @@ retry: /* if locking succeeded, pin bo: */ - ret = msm_gem_get_iova(&msm_obj->base, + ret = msm_gem_get_iova_locked(&msm_obj->base, submit->gpu->id, &iova); /* this would break the logic in the fail path.. there is no @@ -247,7 +247,7 @@ static int submit_reloc(struct msm_gem_submit *submit, struct msm_gem_object *ob /* For now, just map the entire thing. Eventually we probably * to do it page-by-page, w/ kmap() if not vmap()d.. */ - ptr = msm_gem_vaddr(&obj->base); + ptr = msm_gem_vaddr_locked(&obj->base); if (IS_ERR(ptr)) { ret = PTR_ERR(ptr); @@ -307,14 +307,12 @@ static void submit_cleanup(struct msm_gem_submit *submit, bool fail) { unsigned i; - mutex_lock(&submit->dev->struct_mutex); for (i = 0; i < submit->nr_bos; i++) { struct msm_gem_object *msm_obj = submit->bos[i].obj; submit_unlock_unpin_bo(submit, i); list_del_init(&msm_obj->submit_entry); drm_gem_object_unreference(&msm_obj->base); } - mutex_unlock(&submit->dev->struct_mutex); ww_acquire_fini(&submit->ticket); kfree(submit); @@ -342,6 +340,8 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, if (args->nr_cmds > MAX_CMDS) return -EINVAL; + mutex_lock(&dev->struct_mutex); + submit = submit_create(dev, gpu, args->nr_bos); if (!submit) { ret = -ENOMEM; @@ -410,5 +410,6 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, out: if (submit) submit_cleanup(submit, !!ret); + mutex_unlock(&dev->struct_mutex); return ret; } diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c index 4ebce8be489d..0cfe3f426ee4 100644 --- a/drivers/gpu/drm/msm/msm_gpu.c +++ b/drivers/gpu/drm/msm/msm_gpu.c @@ -298,8 +298,6 @@ int msm_gpu_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit, struct msm_drm_private *priv = dev->dev_private; int i, ret; - mutex_lock(&dev->struct_mutex); - submit->fence = ++priv->next_fence; gpu->submitted_fence = submit->fence; @@ -331,7 +329,6 @@ int msm_gpu_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit, msm_gem_move_to_active(&msm_obj->base, gpu, true, submit->fence); } hangcheck_timer_reset(gpu); - mutex_unlock(&dev->struct_mutex); return ret; } diff --git a/drivers/gpu/drm/nouveau/Makefile b/drivers/gpu/drm/nouveau/Makefile index e88145ba1bf5..d310c195bdfe 100644 --- a/drivers/gpu/drm/nouveau/Makefile +++ b/drivers/gpu/drm/nouveau/Makefile @@ -141,6 +141,7 @@ nouveau-y += core/subdev/mc/base.o nouveau-y += core/subdev/mc/nv04.o nouveau-y += core/subdev/mc/nv40.o nouveau-y += core/subdev/mc/nv44.o +nouveau-y += core/subdev/mc/nv4c.o nouveau-y += core/subdev/mc/nv50.o nouveau-y += core/subdev/mc/nv94.o nouveau-y += core/subdev/mc/nv98.o diff --git a/drivers/gpu/drm/nouveau/core/engine/device/nv40.c b/drivers/gpu/drm/nouveau/core/engine/device/nv40.c index 1b653dd74a70..08b88591ed60 100644 --- a/drivers/gpu/drm/nouveau/core/engine/device/nv40.c +++ b/drivers/gpu/drm/nouveau/core/engine/device/nv40.c @@ -311,7 +311,7 @@ nv40_identify(struct nouveau_device *device) device->oclass[NVDEV_SUBDEV_CLOCK ] = &nv40_clock_oclass; device->oclass[NVDEV_SUBDEV_THERM ] = &nv40_therm_oclass; device->oclass[NVDEV_SUBDEV_DEVINIT] = nv1a_devinit_oclass; - device->oclass[NVDEV_SUBDEV_MC ] = nv44_mc_oclass; + device->oclass[NVDEV_SUBDEV_MC ] = nv4c_mc_oclass; device->oclass[NVDEV_SUBDEV_BUS ] = nv31_bus_oclass; device->oclass[NVDEV_SUBDEV_TIMER ] = &nv04_timer_oclass; device->oclass[NVDEV_SUBDEV_FB ] = nv46_fb_oclass; @@ -334,7 +334,7 @@ nv40_identify(struct nouveau_device *device) device->oclass[NVDEV_SUBDEV_CLOCK ] = &nv40_clock_oclass; device->oclass[NVDEV_SUBDEV_THERM ] = &nv40_therm_oclass; device->oclass[NVDEV_SUBDEV_DEVINIT] = nv1a_devinit_oclass; - device->oclass[NVDEV_SUBDEV_MC ] = nv44_mc_oclass; + device->oclass[NVDEV_SUBDEV_MC ] = nv4c_mc_oclass; device->oclass[NVDEV_SUBDEV_BUS ] = nv31_bus_oclass; device->oclass[NVDEV_SUBDEV_TIMER ] = &nv04_timer_oclass; device->oclass[NVDEV_SUBDEV_FB ] = nv4e_fb_oclass; @@ -357,7 +357,7 @@ nv40_identify(struct nouveau_device *device) device->oclass[NVDEV_SUBDEV_CLOCK ] = &nv40_clock_oclass; device->oclass[NVDEV_SUBDEV_THERM ] = &nv40_therm_oclass; device->oclass[NVDEV_SUBDEV_DEVINIT] = nv1a_devinit_oclass; - device->oclass[NVDEV_SUBDEV_MC ] = nv44_mc_oclass; + device->oclass[NVDEV_SUBDEV_MC ] = nv4c_mc_oclass; device->oclass[NVDEV_SUBDEV_BUS ] = nv31_bus_oclass; device->oclass[NVDEV_SUBDEV_TIMER ] = &nv04_timer_oclass; device->oclass[NVDEV_SUBDEV_FB ] = nv46_fb_oclass; @@ -380,7 +380,7 @@ nv40_identify(struct nouveau_device *device) device->oclass[NVDEV_SUBDEV_CLOCK ] = &nv40_clock_oclass; device->oclass[NVDEV_SUBDEV_THERM ] = &nv40_therm_oclass; device->oclass[NVDEV_SUBDEV_DEVINIT] = nv1a_devinit_oclass; - device->oclass[NVDEV_SUBDEV_MC ] = nv44_mc_oclass; + device->oclass[NVDEV_SUBDEV_MC ] = nv4c_mc_oclass; device->oclass[NVDEV_SUBDEV_BUS ] = nv31_bus_oclass; device->oclass[NVDEV_SUBDEV_TIMER ] = &nv04_timer_oclass; device->oclass[NVDEV_SUBDEV_FB ] = nv46_fb_oclass; @@ -403,7 +403,7 @@ nv40_identify(struct nouveau_device *device) device->oclass[NVDEV_SUBDEV_CLOCK ] = &nv40_clock_oclass; device->oclass[NVDEV_SUBDEV_THERM ] = &nv40_therm_oclass; device->oclass[NVDEV_SUBDEV_DEVINIT] = nv1a_devinit_oclass; - device->oclass[NVDEV_SUBDEV_MC ] = nv44_mc_oclass; + device->oclass[NVDEV_SUBDEV_MC ] = nv4c_mc_oclass; device->oclass[NVDEV_SUBDEV_BUS ] = nv31_bus_oclass; device->oclass[NVDEV_SUBDEV_TIMER ] = &nv04_timer_oclass; device->oclass[NVDEV_SUBDEV_FB ] = nv46_fb_oclass; diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/nv50.c b/drivers/gpu/drm/nouveau/core/engine/disp/nv50.c index 940eaa5d8b9a..9ad722e4e087 100644 --- a/drivers/gpu/drm/nouveau/core/engine/disp/nv50.c +++ b/drivers/gpu/drm/nouveau/core/engine/disp/nv50.c @@ -1142,7 +1142,7 @@ nv50_disp_intr_unk20_2(struct nv50_disp_priv *priv, int head) if (conf != ~0) { if (outp.location == 0 && outp.type == DCB_OUTPUT_DP) { u32 soff = (ffs(outp.or) - 1) * 0x08; - u32 ctrl = nv_rd32(priv, 0x610798 + soff); + u32 ctrl = nv_rd32(priv, 0x610794 + soff); u32 datarate; switch ((ctrl & 0x000f0000) >> 16) { diff --git a/drivers/gpu/drm/nouveau/core/engine/fifo/nve0.c b/drivers/gpu/drm/nouveau/core/engine/fifo/nve0.c index 9a850fe19515..54c1b5b471cd 100644 --- a/drivers/gpu/drm/nouveau/core/engine/fifo/nve0.c +++ b/drivers/gpu/drm/nouveau/core/engine/fifo/nve0.c @@ -112,7 +112,7 @@ nve0_fifo_runlist_update(struct nve0_fifo_priv *priv, u32 engine) nv_wr32(priv, 0x002270, cur->addr >> 12); nv_wr32(priv, 0x002274, (engine << 20) | (p >> 3)); - if (!nv_wait(priv, 0x002284 + (engine * 4), 0x00100000, 0x00000000)) + if (!nv_wait(priv, 0x002284 + (engine * 8), 0x00100000, 0x00000000)) nv_error(priv, "runlist %d update timeout\n", engine); mutex_unlock(&nv_subdev(priv)->mutex); } diff --git a/drivers/gpu/drm/nouveau/core/engine/graph/nv50.c b/drivers/gpu/drm/nouveau/core/engine/graph/nv50.c index 30ed19c52e05..7a367c402978 100644 --- a/drivers/gpu/drm/nouveau/core/engine/graph/nv50.c +++ b/drivers/gpu/drm/nouveau/core/engine/graph/nv50.c @@ -539,7 +539,7 @@ nv50_priv_tp_trap(struct nv50_graph_priv *priv, int type, u32 ustatus_old, ustatus &= ~0x04030000; } if (ustatus && display) { - nv_error("%s - TP%d:", name, i); + nv_error(priv, "%s - TP%d:", name, i); nouveau_bitfield_print(nv50_mpc_traps, ustatus); pr_cont("\n"); ustatus = 0; diff --git a/drivers/gpu/drm/nouveau/core/include/subdev/mc.h b/drivers/gpu/drm/nouveau/core/include/subdev/mc.h index adc88b73d911..3c6738edd127 100644 --- a/drivers/gpu/drm/nouveau/core/include/subdev/mc.h +++ b/drivers/gpu/drm/nouveau/core/include/subdev/mc.h @@ -47,6 +47,7 @@ struct nouveau_mc_oclass { extern struct nouveau_oclass *nv04_mc_oclass; extern struct nouveau_oclass *nv40_mc_oclass; extern struct nouveau_oclass *nv44_mc_oclass; +extern struct nouveau_oclass *nv4c_mc_oclass; extern struct nouveau_oclass *nv50_mc_oclass; extern struct nouveau_oclass *nv94_mc_oclass; extern struct nouveau_oclass *nv98_mc_oclass; diff --git a/drivers/gpu/drm/nouveau/core/subdev/bios/base.c b/drivers/gpu/drm/nouveau/core/subdev/bios/base.c index aa0fbbec7f08..ef0c9c4a8cc3 100644 --- a/drivers/gpu/drm/nouveau/core/subdev/bios/base.c +++ b/drivers/gpu/drm/nouveau/core/subdev/bios/base.c @@ -130,6 +130,10 @@ nouveau_bios_shadow_prom(struct nouveau_bios *bios) u16 pcir; int i; + /* there is no prom on nv4x IGP's */ + if (device->card_type == NV_40 && device->chipset >= 0x4c) + return; + /* enable access to rom */ if (device->card_type >= NV_50) pcireg = 0x088050; diff --git a/drivers/gpu/drm/nouveau/core/subdev/fb/nv1a.c b/drivers/gpu/drm/nouveau/core/subdev/fb/nv1a.c index 9159a5ccee93..265d1253624a 100644 --- a/drivers/gpu/drm/nouveau/core/subdev/fb/nv1a.c +++ b/drivers/gpu/drm/nouveau/core/subdev/fb/nv1a.c @@ -36,7 +36,7 @@ nv1a_fb_oclass = &(struct nv04_fb_impl) { .fini = _nouveau_fb_fini, }, .base.memtype = nv04_fb_memtype_valid, - .base.ram = &nv10_ram_oclass, + .base.ram = &nv1a_ram_oclass, .tile.regions = 8, .tile.init = nv10_fb_tile_init, .tile.fini = nv10_fb_tile_fini, diff --git a/drivers/gpu/drm/nouveau/core/subdev/mc/nv04.h b/drivers/gpu/drm/nouveau/core/subdev/mc/nv04.h index b0d5c31606c1..81a408e7d034 100644 --- a/drivers/gpu/drm/nouveau/core/subdev/mc/nv04.h +++ b/drivers/gpu/drm/nouveau/core/subdev/mc/nv04.h @@ -14,6 +14,7 @@ int nv04_mc_ctor(struct nouveau_object *, struct nouveau_object *, extern const struct nouveau_mc_intr nv04_mc_intr[]; int nv04_mc_init(struct nouveau_object *); void nv40_mc_msi_rearm(struct nouveau_mc *); +int nv44_mc_init(struct nouveau_object *object); int nv50_mc_init(struct nouveau_object *); extern const struct nouveau_mc_intr nv50_mc_intr[]; extern const struct nouveau_mc_intr nvc0_mc_intr[]; diff --git a/drivers/gpu/drm/nouveau/core/subdev/mc/nv44.c b/drivers/gpu/drm/nouveau/core/subdev/mc/nv44.c index 3bfee5c6c4f2..cc4d0d2d886e 100644 --- a/drivers/gpu/drm/nouveau/core/subdev/mc/nv44.c +++ b/drivers/gpu/drm/nouveau/core/subdev/mc/nv44.c @@ -24,7 +24,7 @@ #include "nv04.h" -static int +int nv44_mc_init(struct nouveau_object *object) { struct nv04_mc_priv *priv = (void *)object; diff --git a/drivers/gpu/drm/nouveau/core/subdev/mc/nv4c.c b/drivers/gpu/drm/nouveau/core/subdev/mc/nv4c.c new file mode 100644 index 000000000000..a75c35ccf25c --- /dev/null +++ b/drivers/gpu/drm/nouveau/core/subdev/mc/nv4c.c @@ -0,0 +1,45 @@ +/* + * Copyright 2014 Ilia Mirkin + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * 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 COPYRIGHT HOLDER(S) OR AUTHOR(S) 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. + * + * Authors: Ilia Mirkin + */ + +#include "nv04.h" + +static void +nv4c_mc_msi_rearm(struct nouveau_mc *pmc) +{ + struct nv04_mc_priv *priv = (void *)pmc; + nv_wr08(priv, 0x088050, 0xff); +} + +struct nouveau_oclass * +nv4c_mc_oclass = &(struct nouveau_mc_oclass) { + .base.handle = NV_SUBDEV(MC, 0x4c), + .base.ofuncs = &(struct nouveau_ofuncs) { + .ctor = nv04_mc_ctor, + .dtor = _nouveau_mc_dtor, + .init = nv44_mc_init, + .fini = _nouveau_mc_fini, + }, + .intr = nv04_mc_intr, + .msi_rearm = nv4c_mc_msi_rearm, +}.base; diff --git a/drivers/gpu/drm/nouveau/nouveau_acpi.c b/drivers/gpu/drm/nouveau/nouveau_acpi.c index 4ef83df2b246..83face3f608f 100644 --- a/drivers/gpu/drm/nouveau/nouveau_acpi.c +++ b/drivers/gpu/drm/nouveau/nouveau_acpi.c @@ -106,6 +106,29 @@ static int nouveau_optimus_dsm(acpi_handle handle, int func, int arg, uint32_t * return 0; } +/* + * On some platforms, _DSM(nouveau_op_dsm_muid, func0) has special + * requirements on the fourth parameter, so a private implementation + * instead of using acpi_check_dsm(). + */ +static int nouveau_check_optimus_dsm(acpi_handle handle) +{ + int result; + + /* + * Function 0 returns a Buffer containing available functions. + * The args parameter is ignored for function 0, so just put 0 in it + */ + if (nouveau_optimus_dsm(handle, 0, 0, &result)) + return 0; + + /* + * ACPI Spec v4 9.14.1: if bit 0 is zero, no function is supported. + * If the n-th bit is enabled, function n is supported + */ + return result & 1 && result & (1 << NOUVEAU_DSM_OPTIMUS_CAPS); +} + static int nouveau_dsm(acpi_handle handle, int func, int arg) { int ret = 0; @@ -207,8 +230,7 @@ static int nouveau_dsm_pci_probe(struct pci_dev *pdev) 1 << NOUVEAU_DSM_POWER)) retval |= NOUVEAU_DSM_HAS_MUX; - if (acpi_check_dsm(dhandle, nouveau_op_dsm_muid, 0x00000100, - 1 << NOUVEAU_DSM_OPTIMUS_CAPS)) + if (nouveau_check_optimus_dsm(dhandle)) retval |= NOUVEAU_DSM_HAS_OPT; if (retval & NOUVEAU_DSM_HAS_OPT) { diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c index 488686d490c0..4aed1714b9ab 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.c +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c @@ -1249,7 +1249,7 @@ nouveau_ttm_io_mem_reserve(struct ttm_bo_device *bdev, struct ttm_mem_reg *mem) mem->bus.is_iomem = !dev->agp->cant_use_aperture; } #endif - if (!node->memtype) + if (nv_device(drm->device)->card_type < NV_50 || !node->memtype) /* untiled */ break; /* fallthrough, tiled memory */ diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c index 78c8e7146d56..89c484d8ac26 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drm.c +++ b/drivers/gpu/drm/nouveau/nouveau_drm.c @@ -376,6 +376,8 @@ nouveau_drm_load(struct drm_device *dev, unsigned long flags) if (ret) goto fail_device; + dev->irq_enabled = true; + /* workaround an odd issue on nvc1 by disabling the device's * nosnoop capability. hopefully won't cause issues until a * better fix is found - assuming there is one... @@ -475,6 +477,7 @@ nouveau_drm_remove(struct pci_dev *pdev) struct nouveau_drm *drm = nouveau_drm(dev); struct nouveau_object *device; + dev->irq_enabled = false; device = drm->client.base.device; drm_put_dev(dev); diff --git a/drivers/gpu/drm/nouveau/nouveau_vga.c b/drivers/gpu/drm/nouveau/nouveau_vga.c index 81638d7f2eff..471347edc27e 100644 --- a/drivers/gpu/drm/nouveau/nouveau_vga.c +++ b/drivers/gpu/drm/nouveau/nouveau_vga.c @@ -14,7 +14,9 @@ nouveau_vga_set_decode(void *priv, bool state) { struct nouveau_device *device = nouveau_dev(priv); - if (device->chipset >= 0x40) + if (device->card_type == NV_40 && device->chipset >= 0x4c) + nv_wr32(device, 0x088060, state); + else if (device->chipset >= 0x40) nv_wr32(device, 0x088054, state); else nv_wr32(device, 0x001854, state); diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c index a9338c85630f..daa4dd375ab1 100644 --- a/drivers/gpu/drm/radeon/atombios_crtc.c +++ b/drivers/gpu/drm/radeon/atombios_crtc.c @@ -559,7 +559,7 @@ static u32 atombios_adjust_pll(struct drm_crtc *crtc, u32 adjusted_clock = mode->clock; int encoder_mode = atombios_get_encoder_mode(encoder); u32 dp_clock = mode->clock; - int bpc = radeon_get_monitor_bpc(connector); + int bpc = radeon_crtc->bpc; bool is_duallink = radeon_dig_monitor_is_duallink(encoder, mode->clock); /* reset the pll flags */ @@ -1176,7 +1176,7 @@ static int dce4_crtc_do_set_base(struct drm_crtc *crtc, evergreen_tiling_fields(tiling_flags, &bankw, &bankh, &mtaspect, &tile_split); /* Set NUM_BANKS. */ - if (rdev->family >= CHIP_BONAIRE) { + if (rdev->family >= CHIP_TAHITI) { unsigned tileb, index, num_banks, tile_split_bytes; /* Calculate the macrotile mode index. */ @@ -1194,13 +1194,14 @@ static int dce4_crtc_do_set_base(struct drm_crtc *crtc, return -EINVAL; } - num_banks = (rdev->config.cik.macrotile_mode_array[index] >> 6) & 0x3; + if (rdev->family >= CHIP_BONAIRE) + num_banks = (rdev->config.cik.macrotile_mode_array[index] >> 6) & 0x3; + else + num_banks = (rdev->config.si.tile_mode_array[index] >> 20) & 0x3; fb_format |= EVERGREEN_GRPH_NUM_BANKS(num_banks); } else { - /* SI and older. */ - if (rdev->family >= CHIP_TAHITI) - tmp = rdev->config.si.tile_config; - else if (rdev->family >= CHIP_CAYMAN) + /* NI and older. */ + if (rdev->family >= CHIP_CAYMAN) tmp = rdev->config.cayman.tile_config; else tmp = rdev->config.evergreen.tile_config; @@ -1773,6 +1774,20 @@ static int radeon_atom_pick_pll(struct drm_crtc *crtc) return ATOM_PPLL1; DRM_ERROR("unable to allocate a PPLL\n"); return ATOM_PPLL_INVALID; + } else if (ASIC_IS_DCE41(rdev)) { + /* Don't share PLLs on DCE4.1 chips */ + if (ENCODER_MODE_IS_DP(atombios_get_encoder_mode(radeon_crtc->encoder))) { + if (rdev->clock.dp_extclk) + /* skip PPLL programming if using ext clock */ + return ATOM_PPLL_INVALID; + } + pll_in_use = radeon_get_pll_use_mask(crtc); + if (!(pll_in_use & (1 << ATOM_PPLL1))) + return ATOM_PPLL1; + if (!(pll_in_use & (1 << ATOM_PPLL2))) + return ATOM_PPLL2; + DRM_ERROR("unable to allocate a PPLL\n"); + return ATOM_PPLL_INVALID; } else if (ASIC_IS_DCE4(rdev)) { /* in DP mode, the DP ref clock can come from PPLL, DCPLL, or ext clock, * depending on the asic: @@ -1800,7 +1815,7 @@ static int radeon_atom_pick_pll(struct drm_crtc *crtc) if (pll != ATOM_PPLL_INVALID) return pll; } - } else if (!ASIC_IS_DCE41(rdev)) { /* Don't share PLLs on DCE4.1 chips */ + } else { /* use the same PPLL for all monitors with the same clock */ pll = radeon_get_shared_nondp_ppll(crtc); if (pll != ATOM_PPLL_INVALID) diff --git a/drivers/gpu/drm/radeon/atombios_encoders.c b/drivers/gpu/drm/radeon/atombios_encoders.c index a42d61571f49..2cec2ab02f80 100644 --- a/drivers/gpu/drm/radeon/atombios_encoders.c +++ b/drivers/gpu/drm/radeon/atombios_encoders.c @@ -464,11 +464,12 @@ atombios_tv_setup(struct drm_encoder *encoder, int action) static u8 radeon_atom_get_bpc(struct drm_encoder *encoder) { - struct drm_connector *connector = radeon_get_connector_for_encoder(encoder); int bpc = 8; - if (connector) - bpc = radeon_get_monitor_bpc(connector); + if (encoder->crtc) { + struct radeon_crtc *radeon_crtc = to_radeon_crtc(encoder->crtc); + bpc = radeon_crtc->bpc; + } switch (bpc) { case 0: diff --git a/drivers/gpu/drm/radeon/btc_dpm.c b/drivers/gpu/drm/radeon/btc_dpm.c index 0fbd36f3d4e9..ea103ccdf4bd 100644 --- a/drivers/gpu/drm/radeon/btc_dpm.c +++ b/drivers/gpu/drm/radeon/btc_dpm.c @@ -29,6 +29,7 @@ #include "cypress_dpm.h" #include "btc_dpm.h" #include "atom.h" +#include <linux/seq_file.h> #define MC_CG_ARB_FREQ_F0 0x0a #define MC_CG_ARB_FREQ_F1 0x0b @@ -2756,6 +2757,37 @@ void btc_dpm_fini(struct radeon_device *rdev) r600_free_extended_power_table(rdev); } +void btc_dpm_debugfs_print_current_performance_level(struct radeon_device *rdev, + struct seq_file *m) +{ + struct evergreen_power_info *eg_pi = evergreen_get_pi(rdev); + struct radeon_ps *rps = &eg_pi->current_rps; + struct rv7xx_ps *ps = rv770_get_ps(rps); + struct rv7xx_pl *pl; + u32 current_index = + (RREG32(TARGET_AND_CURRENT_PROFILE_INDEX) & CURRENT_PROFILE_INDEX_MASK) >> + CURRENT_PROFILE_INDEX_SHIFT; + + if (current_index > 2) { + seq_printf(m, "invalid dpm profile %d\n", current_index); + } else { + if (current_index == 0) + pl = &ps->low; + else if (current_index == 1) + pl = &ps->medium; + else /* current_index == 2 */ + pl = &ps->high; + seq_printf(m, "uvd vclk: %d dclk: %d\n", rps->vclk, rps->dclk); + if (rdev->family >= CHIP_CEDAR) { + seq_printf(m, "power level %d sclk: %u mclk: %u vddc: %u vddci: %u\n", + current_index, pl->sclk, pl->mclk, pl->vddc, pl->vddci); + } else { + seq_printf(m, "power level %d sclk: %u mclk: %u vddc: %u\n", + current_index, pl->sclk, pl->mclk, pl->vddc); + } + } +} + u32 btc_dpm_get_sclk(struct radeon_device *rdev, bool low) { struct evergreen_power_info *eg_pi = evergreen_get_pi(rdev); diff --git a/drivers/gpu/drm/radeon/btcd.h b/drivers/gpu/drm/radeon/btcd.h index 29e32de7e025..9c65be2d55a9 100644 --- a/drivers/gpu/drm/radeon/btcd.h +++ b/drivers/gpu/drm/radeon/btcd.h @@ -44,6 +44,10 @@ # define DYN_SPREAD_SPECTRUM_EN (1 << 23) # define AC_DC_SW (1 << 24) +#define TARGET_AND_CURRENT_PROFILE_INDEX 0x66c +# define CURRENT_PROFILE_INDEX_MASK (0xf << 4) +# define CURRENT_PROFILE_INDEX_SHIFT 4 + #define CG_BIF_REQ_AND_RSP 0x7f4 #define CG_CLIENT_REQ(x) ((x) << 0) #define CG_CLIENT_REQ_MASK (0xff << 0) diff --git a/drivers/gpu/drm/radeon/dce6_afmt.c b/drivers/gpu/drm/radeon/dce6_afmt.c index 713a5d359901..94e858751994 100644 --- a/drivers/gpu/drm/radeon/dce6_afmt.c +++ b/drivers/gpu/drm/radeon/dce6_afmt.c @@ -278,13 +278,15 @@ static int dce6_audio_chipset_supported(struct radeon_device *rdev) return !ASIC_IS_NODCE(rdev); } -static void dce6_audio_enable(struct radeon_device *rdev, - struct r600_audio_pin *pin, - bool enable) +void dce6_audio_enable(struct radeon_device *rdev, + struct r600_audio_pin *pin, + bool enable) { + if (!pin) + return; + WREG32_ENDPOINT(pin->offset, AZ_F0_CODEC_PIN_CONTROL_HOTPLUG_CONTROL, - AUDIO_ENABLED); - DRM_INFO("%s audio %d support\n", enable ? "Enabling" : "Disabling", pin->id); + enable ? AUDIO_ENABLED : 0); } static const u32 pin_offsets[7] = @@ -323,7 +325,8 @@ int dce6_audio_init(struct radeon_device *rdev) rdev->audio.pin[i].connected = false; rdev->audio.pin[i].offset = pin_offsets[i]; rdev->audio.pin[i].id = i; - dce6_audio_enable(rdev, &rdev->audio.pin[i], true); + /* disable audio. it will be set up later */ + dce6_audio_enable(rdev, &rdev->audio.pin[i], false); } return 0; diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c index f2b9e21ce4da..8a2c010b7dc5 100644 --- a/drivers/gpu/drm/radeon/evergreen.c +++ b/drivers/gpu/drm/radeon/evergreen.c @@ -1680,7 +1680,7 @@ bool evergreen_hpd_sense(struct radeon_device *rdev, enum radeon_hpd_id hpd) case RADEON_HPD_6: if (RREG32(DC_HPD6_INT_STATUS) & DC_HPDx_SENSE) connected = true; - break; + break; default: break; } @@ -5475,9 +5475,9 @@ void evergreen_fini(struct radeon_device *rdev) radeon_wb_fini(rdev); radeon_ib_pool_fini(rdev); radeon_irq_kms_fini(rdev); - evergreen_pcie_gart_fini(rdev); uvd_v1_0_fini(rdev); radeon_uvd_fini(rdev); + evergreen_pcie_gart_fini(rdev); r600_vram_scratch_fini(rdev); radeon_gem_fini(rdev); radeon_fence_driver_fini(rdev); diff --git a/drivers/gpu/drm/radeon/evergreen_hdmi.c b/drivers/gpu/drm/radeon/evergreen_hdmi.c index 0c6d5cef4cf1..05b0c95813fd 100644 --- a/drivers/gpu/drm/radeon/evergreen_hdmi.c +++ b/drivers/gpu/drm/radeon/evergreen_hdmi.c @@ -306,6 +306,15 @@ void evergreen_hdmi_setmode(struct drm_encoder *encoder, struct drm_display_mode return; offset = dig->afmt->offset; + /* disable audio prior to setting up hw */ + if (ASIC_IS_DCE6(rdev)) { + dig->afmt->pin = dce6_audio_get_pin(rdev); + dce6_audio_enable(rdev, dig->afmt->pin, false); + } else { + dig->afmt->pin = r600_audio_get_pin(rdev); + r600_audio_enable(rdev, dig->afmt->pin, false); + } + evergreen_audio_set_dto(encoder, mode->clock); WREG32(HDMI_VBI_PACKET_CONTROL + offset, @@ -409,12 +418,16 @@ void evergreen_hdmi_setmode(struct drm_encoder *encoder, struct drm_display_mode WREG32(AFMT_RAMP_CONTROL1 + offset, 0x007FFFFF); WREG32(AFMT_RAMP_CONTROL2 + offset, 0x00000001); WREG32(AFMT_RAMP_CONTROL3 + offset, 0x00000001); + + /* enable audio after to setting up hw */ + if (ASIC_IS_DCE6(rdev)) + dce6_audio_enable(rdev, dig->afmt->pin, true); + else + r600_audio_enable(rdev, dig->afmt->pin, true); } void evergreen_hdmi_enable(struct drm_encoder *encoder, bool enable) { - struct drm_device *dev = encoder->dev; - struct radeon_device *rdev = dev->dev_private; struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder); struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv; @@ -427,15 +440,6 @@ void evergreen_hdmi_enable(struct drm_encoder *encoder, bool enable) if (!enable && !dig->afmt->enabled) return; - if (enable) { - if (ASIC_IS_DCE6(rdev)) - dig->afmt->pin = dce6_audio_get_pin(rdev); - else - dig->afmt->pin = r600_audio_get_pin(rdev); - } else { - dig->afmt->pin = NULL; - } - dig->afmt->enabled = enable; DRM_DEBUG("%sabling HDMI interface @ 0x%04X for encoder 0x%x\n", diff --git a/drivers/gpu/drm/radeon/kv_dpm.c b/drivers/gpu/drm/radeon/kv_dpm.c index b6e01d5d2cce..351db361239d 100644 --- a/drivers/gpu/drm/radeon/kv_dpm.c +++ b/drivers/gpu/drm/radeon/kv_dpm.c @@ -1223,7 +1223,7 @@ int kv_dpm_enable(struct radeon_device *rdev) int kv_dpm_late_enable(struct radeon_device *rdev) { - int ret; + int ret = 0; if (rdev->irq.installed && r600_is_internal_thermal_sensor(rdev->pm.int_thermal_type)) { diff --git a/drivers/gpu/drm/radeon/ni_dpm.c b/drivers/gpu/drm/radeon/ni_dpm.c index c351226ecb31..ca814276b075 100644 --- a/drivers/gpu/drm/radeon/ni_dpm.c +++ b/drivers/gpu/drm/radeon/ni_dpm.c @@ -2588,7 +2588,7 @@ static int ni_populate_sq_ramping_values(struct radeon_device *rdev, if (NISLANDS_DPM2_SQ_RAMP_STI_SIZE > (STI_SIZE_MASK >> STI_SIZE_SHIFT)) enable_sq_ramping = false; - if (NISLANDS_DPM2_SQ_RAMP_LTI_RATIO <= (LTI_RATIO_MASK >> LTI_RATIO_SHIFT)) + if (NISLANDS_DPM2_SQ_RAMP_LTI_RATIO > (LTI_RATIO_MASK >> LTI_RATIO_SHIFT)) enable_sq_ramping = false; for (i = 0; i < state->performance_level_count; i++) { @@ -3945,7 +3945,6 @@ static void ni_parse_pplib_clock_info(struct radeon_device *rdev, struct rv7xx_power_info *pi = rv770_get_pi(rdev); struct evergreen_power_info *eg_pi = evergreen_get_pi(rdev); struct ni_ps *ps = ni_get_ps(rps); - u16 vddc; struct rv7xx_pl *pl = &ps->performance_levels[index]; ps->performance_level_count = index + 1; @@ -3961,8 +3960,8 @@ static void ni_parse_pplib_clock_info(struct radeon_device *rdev, /* patch up vddc if necessary */ if (pl->vddc == 0xff01) { - if (radeon_atom_get_max_vddc(rdev, 0, 0, &vddc) == 0) - pl->vddc = vddc; + if (pi->max_vddc) + pl->vddc = pi->max_vddc; } if (rps->class & ATOM_PPLIB_CLASSIFICATION_ACPI) { @@ -4322,7 +4321,8 @@ void ni_dpm_print_power_state(struct radeon_device *rdev, void ni_dpm_debugfs_print_current_performance_level(struct radeon_device *rdev, struct seq_file *m) { - struct radeon_ps *rps = rdev->pm.dpm.current_ps; + struct evergreen_power_info *eg_pi = evergreen_get_pi(rdev); + struct radeon_ps *rps = &eg_pi->current_rps; struct ni_ps *ps = ni_get_ps(rps); struct rv7xx_pl *pl; u32 current_index = diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c index 56140b4e5bb2..cdbc4171fe73 100644 --- a/drivers/gpu/drm/radeon/r600.c +++ b/drivers/gpu/drm/radeon/r600.c @@ -3991,6 +3991,10 @@ restart_ih: break; } break; + case 124: /* UVD */ + DRM_DEBUG("IH: UVD int: 0x%08x\n", src_data); + radeon_fence_process(rdev, R600_RING_TYPE_UVD_INDEX); + break; case 176: /* CP_INT in ring buffer */ case 177: /* CP_INT in IB1 */ case 178: /* CP_INT in IB2 */ diff --git a/drivers/gpu/drm/radeon/r600_audio.c b/drivers/gpu/drm/radeon/r600_audio.c index 47fc2b886979..bffac10c4296 100644 --- a/drivers/gpu/drm/radeon/r600_audio.c +++ b/drivers/gpu/drm/radeon/r600_audio.c @@ -142,12 +142,15 @@ void r600_audio_update_hdmi(struct work_struct *work) } /* enable the audio stream */ -static void r600_audio_enable(struct radeon_device *rdev, - struct r600_audio_pin *pin, - bool enable) +void r600_audio_enable(struct radeon_device *rdev, + struct r600_audio_pin *pin, + bool enable) { u32 value = 0; + if (!pin) + return; + if (ASIC_IS_DCE4(rdev)) { if (enable) { value |= 0x81000000; /* Required to enable audio */ @@ -158,7 +161,6 @@ static void r600_audio_enable(struct radeon_device *rdev, WREG32_P(R600_AUDIO_ENABLE, enable ? 0x81000000 : 0x0, ~0x81000000); } - DRM_INFO("%s audio %d support\n", enable ? "Enabling" : "Disabling", pin->id); } /* @@ -178,8 +180,8 @@ int r600_audio_init(struct radeon_device *rdev) rdev->audio.pin[0].status_bits = 0; rdev->audio.pin[0].category_code = 0; rdev->audio.pin[0].id = 0; - - r600_audio_enable(rdev, &rdev->audio.pin[0], true); + /* disable audio. it will be set up later */ + r600_audio_enable(rdev, &rdev->audio.pin[0], false); return 0; } diff --git a/drivers/gpu/drm/radeon/r600_hdmi.c b/drivers/gpu/drm/radeon/r600_hdmi.c index 3016fc14f502..85a2bb28aed2 100644 --- a/drivers/gpu/drm/radeon/r600_hdmi.c +++ b/drivers/gpu/drm/radeon/r600_hdmi.c @@ -329,9 +329,6 @@ static void dce3_2_afmt_write_speaker_allocation(struct drm_encoder *encoder) u8 *sadb; int sad_count; - /* XXX: setting this register causes hangs on some asics */ - return; - list_for_each_entry(connector, &encoder->dev->mode_config.connector_list, head) { if (connector->encoder == encoder) { radeon_connector = to_radeon_connector(connector); @@ -460,6 +457,10 @@ void r600_hdmi_setmode(struct drm_encoder *encoder, struct drm_display_mode *mod return; offset = dig->afmt->offset; + /* disable audio prior to setting up hw */ + dig->afmt->pin = r600_audio_get_pin(rdev); + r600_audio_enable(rdev, dig->afmt->pin, false); + r600_audio_set_dto(encoder, mode->clock); WREG32(HDMI0_VBI_PACKET_CONTROL + offset, @@ -531,6 +532,9 @@ void r600_hdmi_setmode(struct drm_encoder *encoder, struct drm_display_mode *mod WREG32(HDMI0_RAMP_CONTROL3 + offset, 0x00000001); r600_hdmi_audio_workaround(encoder); + + /* enable audio after to setting up hw */ + r600_audio_enable(rdev, dig->afmt->pin, true); } /* @@ -651,11 +655,6 @@ void r600_hdmi_enable(struct drm_encoder *encoder, bool enable) if (!enable && !dig->afmt->enabled) return; - if (enable) - dig->afmt->pin = r600_audio_get_pin(rdev); - else - dig->afmt->pin = NULL; - /* Older chipsets require setting HDMI and routing manually */ if (!ASIC_IS_DCE3(rdev)) { if (enable) diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h index 4a8ac1cd6b4c..e887d027b6d0 100644 --- a/drivers/gpu/drm/radeon/radeon.h +++ b/drivers/gpu/drm/radeon/radeon.h @@ -135,6 +135,9 @@ extern int radeon_hard_reset; /* R600+ */ #define R600_RING_TYPE_UVD_INDEX 5 +/* number of hw syncs before falling back on blocking */ +#define RADEON_NUM_SYNCS 4 + /* hardcode those limit for now */ #define RADEON_VA_IB_OFFSET (1 << 20) #define RADEON_VA_RESERVED_SIZE (8 << 20) @@ -554,7 +557,6 @@ int radeon_mode_dumb_mmap(struct drm_file *filp, /* * Semaphores. */ -/* everything here is constant */ struct radeon_semaphore { struct radeon_sa_bo *sa_bo; signed waiters; @@ -2745,6 +2747,12 @@ int radeon_vm_bo_rmv(struct radeon_device *rdev, void r600_audio_update_hdmi(struct work_struct *work); struct r600_audio_pin *r600_audio_get_pin(struct radeon_device *rdev); struct r600_audio_pin *dce6_audio_get_pin(struct radeon_device *rdev); +void r600_audio_enable(struct radeon_device *rdev, + struct r600_audio_pin *pin, + bool enable); +void dce6_audio_enable(struct radeon_device *rdev, + struct r600_audio_pin *pin, + bool enable); /* * R600 vram scratch functions diff --git a/drivers/gpu/drm/radeon/radeon_asic.c b/drivers/gpu/drm/radeon/radeon_asic.c index f74db43346fd..dda02bfc10a4 100644 --- a/drivers/gpu/drm/radeon/radeon_asic.c +++ b/drivers/gpu/drm/radeon/radeon_asic.c @@ -1555,7 +1555,7 @@ static struct radeon_asic btc_asic = { .get_sclk = &btc_dpm_get_sclk, .get_mclk = &btc_dpm_get_mclk, .print_power_state = &rv770_dpm_print_power_state, - .debugfs_print_current_performance_level = &rv770_dpm_debugfs_print_current_performance_level, + .debugfs_print_current_performance_level = &btc_dpm_debugfs_print_current_performance_level, .force_performance_level = &rv770_dpm_force_performance_level, .vblank_too_short = &btc_dpm_vblank_too_short, }, diff --git a/drivers/gpu/drm/radeon/radeon_asic.h b/drivers/gpu/drm/radeon/radeon_asic.h index b3bc433eed4c..ae637cfda783 100644 --- a/drivers/gpu/drm/radeon/radeon_asic.h +++ b/drivers/gpu/drm/radeon/radeon_asic.h @@ -551,6 +551,8 @@ void btc_dpm_fini(struct radeon_device *rdev); u32 btc_dpm_get_sclk(struct radeon_device *rdev, bool low); u32 btc_dpm_get_mclk(struct radeon_device *rdev, bool low); bool btc_dpm_vblank_too_short(struct radeon_device *rdev); +void btc_dpm_debugfs_print_current_performance_level(struct radeon_device *rdev, + struct seq_file *m); int sumo_dpm_init(struct radeon_device *rdev); int sumo_dpm_enable(struct radeon_device *rdev); int sumo_dpm_late_enable(struct radeon_device *rdev); diff --git a/drivers/gpu/drm/radeon/radeon_atpx_handler.c b/drivers/gpu/drm/radeon/radeon_atpx_handler.c index 485848f889f5..fa9a9c02751e 100644 --- a/drivers/gpu/drm/radeon/radeon_atpx_handler.c +++ b/drivers/gpu/drm/radeon/radeon_atpx_handler.c @@ -219,7 +219,8 @@ static int radeon_atpx_verify_interface(struct radeon_atpx *atpx) memcpy(&output, info->buffer.pointer, size); /* TODO: check version? */ - printk("ATPX version %u\n", output.version); + printk("ATPX version %u, functions 0x%08x\n", + output.version, output.function_bits); radeon_atpx_parse_functions(&atpx->functions, output.function_bits); diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c index d680608f6f5b..fbd8b930f2be 100644 --- a/drivers/gpu/drm/radeon/radeon_display.c +++ b/drivers/gpu/drm/radeon/radeon_display.c @@ -571,6 +571,8 @@ static void radeon_crtc_init(struct drm_device *dev, int index) radeon_crtc->max_cursor_width = CURSOR_WIDTH; radeon_crtc->max_cursor_height = CURSOR_HEIGHT; } + dev->mode_config.cursor_width = radeon_crtc->max_cursor_width; + dev->mode_config.cursor_height = radeon_crtc->max_cursor_height; #if 0 radeon_crtc->mode_set.crtc = &radeon_crtc->base; diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c index 114d1672d616..2aecd6dc2610 100644 --- a/drivers/gpu/drm/radeon/radeon_kms.c +++ b/drivers/gpu/drm/radeon/radeon_kms.c @@ -537,6 +537,10 @@ int radeon_driver_open_kms(struct drm_device *dev, struct drm_file *file_priv) radeon_vm_init(rdev, &fpriv->vm); + r = radeon_bo_reserve(rdev->ring_tmp_bo.bo, false); + if (r) + return r; + /* map the ib pool buffer read only into * virtual address space */ bo_va = radeon_vm_bo_add(rdev, &fpriv->vm, @@ -544,6 +548,8 @@ int radeon_driver_open_kms(struct drm_device *dev, struct drm_file *file_priv) r = radeon_vm_bo_set_addr(rdev, bo_va, RADEON_VA_IB_OFFSET, RADEON_VM_PAGE_READABLE | RADEON_VM_PAGE_SNOOPED); + + radeon_bo_unreserve(rdev->ring_tmp_bo.bo); if (r) { radeon_vm_fini(rdev, &fpriv->vm); kfree(fpriv); diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c index 1b783f0e6d3a..15e44a7281ab 100644 --- a/drivers/gpu/drm/radeon/radeon_ring.c +++ b/drivers/gpu/drm/radeon/radeon_ring.c @@ -139,7 +139,7 @@ int radeon_ib_schedule(struct radeon_device *rdev, struct radeon_ib *ib, } /* 64 dwords should be enough for fence too */ - r = radeon_ring_lock(rdev, ring, 64 + RADEON_NUM_RINGS * 8); + r = radeon_ring_lock(rdev, ring, 64 + RADEON_NUM_SYNCS * 8); if (r) { dev_err(rdev->dev, "scheduling IB failed (%d).\n", r); return r; diff --git a/drivers/gpu/drm/radeon/radeon_semaphore.c b/drivers/gpu/drm/radeon/radeon_semaphore.c index 2b42aa1914f2..9006b32d5eed 100644 --- a/drivers/gpu/drm/radeon/radeon_semaphore.c +++ b/drivers/gpu/drm/radeon/radeon_semaphore.c @@ -34,14 +34,15 @@ int radeon_semaphore_create(struct radeon_device *rdev, struct radeon_semaphore **semaphore) { + uint32_t *cpu_addr; int i, r; *semaphore = kmalloc(sizeof(struct radeon_semaphore), GFP_KERNEL); if (*semaphore == NULL) { return -ENOMEM; } - r = radeon_sa_bo_new(rdev, &rdev->ring_tmp_bo, - &(*semaphore)->sa_bo, 8, 8, true); + r = radeon_sa_bo_new(rdev, &rdev->ring_tmp_bo, &(*semaphore)->sa_bo, + 8 * RADEON_NUM_SYNCS, 8, true); if (r) { kfree(*semaphore); *semaphore = NULL; @@ -49,7 +50,10 @@ int radeon_semaphore_create(struct radeon_device *rdev, } (*semaphore)->waiters = 0; (*semaphore)->gpu_addr = radeon_sa_bo_gpu_addr((*semaphore)->sa_bo); - *((uint64_t*)radeon_sa_bo_cpu_addr((*semaphore)->sa_bo)) = 0; + + cpu_addr = radeon_sa_bo_cpu_addr((*semaphore)->sa_bo); + for (i = 0; i < RADEON_NUM_SYNCS; ++i) + cpu_addr[i] = 0; for (i = 0; i < RADEON_NUM_RINGS; ++i) (*semaphore)->sync_to[i] = NULL; @@ -125,6 +129,7 @@ int radeon_semaphore_sync_rings(struct radeon_device *rdev, struct radeon_semaphore *semaphore, int ring) { + unsigned count = 0; int i, r; for (i = 0; i < RADEON_NUM_RINGS; ++i) { @@ -140,6 +145,12 @@ int radeon_semaphore_sync_rings(struct radeon_device *rdev, return -EINVAL; } + if (++count > RADEON_NUM_SYNCS) { + /* not enough room, wait manually */ + radeon_fence_wait_locked(fence); + continue; + } + /* allocate enough space for sync command */ r = radeon_ring_alloc(rdev, &rdev->ring[i], 16); if (r) { @@ -164,6 +175,8 @@ int radeon_semaphore_sync_rings(struct radeon_device *rdev, radeon_ring_commit(rdev, &rdev->ring[i]); radeon_fence_note_sync(fence, ring); + + semaphore->gpu_addr += 8; } return 0; diff --git a/drivers/gpu/drm/radeon/radeon_uvd.c b/drivers/gpu/drm/radeon/radeon_uvd.c index 6781fee1eaad..3e6804b2b2ef 100644 --- a/drivers/gpu/drm/radeon/radeon_uvd.c +++ b/drivers/gpu/drm/radeon/radeon_uvd.c @@ -171,6 +171,8 @@ void radeon_uvd_fini(struct radeon_device *rdev) radeon_bo_unref(&rdev->uvd.vcpu_bo); + radeon_ring_fini(rdev, &rdev->ring[R600_RING_TYPE_UVD_INDEX]); + release_firmware(rdev->uvd_fw); } diff --git a/drivers/gpu/drm/radeon/rv770.c b/drivers/gpu/drm/radeon/rv770.c index 6c772e58c784..4e37a42305d8 100644 --- a/drivers/gpu/drm/radeon/rv770.c +++ b/drivers/gpu/drm/radeon/rv770.c @@ -1955,9 +1955,9 @@ void rv770_fini(struct radeon_device *rdev) radeon_wb_fini(rdev); radeon_ib_pool_fini(rdev); radeon_irq_kms_fini(rdev); - rv770_pcie_gart_fini(rdev); uvd_v1_0_fini(rdev); radeon_uvd_fini(rdev); + rv770_pcie_gart_fini(rdev); r600_vram_scratch_fini(rdev); radeon_gem_fini(rdev); radeon_fence_driver_fini(rdev); diff --git a/drivers/gpu/drm/radeon/rv770_dpm.c b/drivers/gpu/drm/radeon/rv770_dpm.c index 80c595aba359..b5f63f5e22a3 100644 --- a/drivers/gpu/drm/radeon/rv770_dpm.c +++ b/drivers/gpu/drm/radeon/rv770_dpm.c @@ -2174,7 +2174,6 @@ static void rv7xx_parse_pplib_clock_info(struct radeon_device *rdev, struct evergreen_power_info *eg_pi = evergreen_get_pi(rdev); struct rv7xx_ps *ps = rv770_get_ps(rps); u32 sclk, mclk; - u16 vddc; struct rv7xx_pl *pl; switch (index) { @@ -2214,8 +2213,8 @@ static void rv7xx_parse_pplib_clock_info(struct radeon_device *rdev, /* patch up vddc if necessary */ if (pl->vddc == 0xff01) { - if (radeon_atom_get_max_vddc(rdev, 0, 0, &vddc) == 0) - pl->vddc = vddc; + if (pi->max_vddc) + pl->vddc = pi->max_vddc; } if (rps->class & ATOM_PPLIB_CLASSIFICATION_ACPI) { @@ -2527,14 +2526,7 @@ u32 rv770_dpm_get_mclk(struct radeon_device *rdev, bool low) bool rv770_dpm_vblank_too_short(struct radeon_device *rdev) { u32 vblank_time = r600_dpm_get_vblank_time(rdev); - u32 switch_limit = 300; - - /* quirks */ - /* ASUS K70AF */ - if ((rdev->pdev->device == 0x9553) && - (rdev->pdev->subsystem_vendor == 0x1043) && - (rdev->pdev->subsystem_device == 0x1c42)) - switch_limit = 200; + u32 switch_limit = 200; /* 300 */ /* RV770 */ /* mclk switching doesn't seem to work reliably on desktop RV770s */ diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c index 09ec4f6c53bb..83578324e5d1 100644 --- a/drivers/gpu/drm/radeon/si.c +++ b/drivers/gpu/drm/radeon/si.c @@ -6338,6 +6338,10 @@ restart_ih: break; } break; + case 124: /* UVD */ + DRM_DEBUG("IH: UVD int: 0x%08x\n", src_data); + radeon_fence_process(rdev, R600_RING_TYPE_UVD_INDEX); + break; case 146: case 147: addr = RREG32(VM_CONTEXT1_PROTECTION_FAULT_ADDR); diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c index 0471501338fb..0a2f5b4bca43 100644 --- a/drivers/gpu/drm/radeon/si_dpm.c +++ b/drivers/gpu/drm/radeon/si_dpm.c @@ -2395,7 +2395,7 @@ static int si_populate_sq_ramping_values(struct radeon_device *rdev, if (SISLANDS_DPM2_SQ_RAMP_STI_SIZE > (STI_SIZE_MASK >> STI_SIZE_SHIFT)) enable_sq_ramping = false; - if (SISLANDS_DPM2_SQ_RAMP_LTI_RATIO <= (LTI_RATIO_MASK >> LTI_RATIO_SHIFT)) + if (SISLANDS_DPM2_SQ_RAMP_LTI_RATIO > (LTI_RATIO_MASK >> LTI_RATIO_SHIFT)) enable_sq_ramping = false; for (i = 0; i < state->performance_level_count; i++) { @@ -6472,7 +6472,8 @@ void si_dpm_fini(struct radeon_device *rdev) void si_dpm_debugfs_print_current_performance_level(struct radeon_device *rdev, struct seq_file *m) { - struct radeon_ps *rps = rdev->pm.dpm.current_ps; + struct evergreen_power_info *eg_pi = evergreen_get_pi(rdev); + struct radeon_ps *rps = &eg_pi->current_rps; struct ni_ps *ps = ni_get_ps(rps); struct rv7xx_pl *pl; u32 current_index = diff --git a/drivers/gpu/drm/radeon/sumo_dpm.c b/drivers/gpu/drm/radeon/sumo_dpm.c index f121efe12dc5..8b47b3cd0357 100644 --- a/drivers/gpu/drm/radeon/sumo_dpm.c +++ b/drivers/gpu/drm/radeon/sumo_dpm.c @@ -1807,7 +1807,7 @@ void sumo_dpm_debugfs_print_current_performance_level(struct radeon_device *rdev struct seq_file *m) { struct sumo_power_info *pi = sumo_get_pi(rdev); - struct radeon_ps *rps = rdev->pm.dpm.current_ps; + struct radeon_ps *rps = &pi->current_rps; struct sumo_ps *ps = sumo_get_ps(rps); struct sumo_pl *pl; u32 current_index = diff --git a/drivers/gpu/drm/radeon/trinity_dpm.c b/drivers/gpu/drm/radeon/trinity_dpm.c index 2d447192d6f7..2da0e17eb960 100644 --- a/drivers/gpu/drm/radeon/trinity_dpm.c +++ b/drivers/gpu/drm/radeon/trinity_dpm.c @@ -1926,7 +1926,8 @@ void trinity_dpm_print_power_state(struct radeon_device *rdev, void trinity_dpm_debugfs_print_current_performance_level(struct radeon_device *rdev, struct seq_file *m) { - struct radeon_ps *rps = rdev->pm.dpm.current_ps; + struct trinity_power_info *pi = trinity_get_pi(rdev); + struct radeon_ps *rps = &pi->current_rps; struct trinity_ps *ps = trinity_get_ps(rps); struct trinity_pl *pl; u32 current_index = diff --git a/drivers/gpu/drm/radeon/uvd_v2_2.c b/drivers/gpu/drm/radeon/uvd_v2_2.c index 824550db3fed..d1771004cb52 100644 --- a/drivers/gpu/drm/radeon/uvd_v2_2.c +++ b/drivers/gpu/drm/radeon/uvd_v2_2.c @@ -57,7 +57,6 @@ void uvd_v2_2_fence_emit(struct radeon_device *rdev, radeon_ring_write(ring, 0); radeon_ring_write(ring, PACKET0(UVD_GPCOM_VCPU_CMD, 0)); radeon_ring_write(ring, 2); - return; } /** diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c index 88a529008ce0..c71594754f46 100644 --- a/drivers/gpu/drm/tegra/drm.c +++ b/drivers/gpu/drm/tegra/drm.c @@ -104,7 +104,7 @@ static void tegra_drm_context_free(struct tegra_drm_context *context) static void tegra_drm_lastclose(struct drm_device *drm) { -#ifdef CONFIG_TEGRA_DRM_FBDEV +#ifdef CONFIG_DRM_TEGRA_FBDEV struct tegra_drm *tegra = drm->dev_private; tegra_fbdev_restore_mode(tegra->fbdev); diff --git a/drivers/gpu/drm/tegra/rgb.c b/drivers/gpu/drm/tegra/rgb.c index 338f7f6561d7..0266fb40479e 100644 --- a/drivers/gpu/drm/tegra/rgb.c +++ b/drivers/gpu/drm/tegra/rgb.c @@ -15,6 +15,7 @@ struct tegra_rgb { struct tegra_output output; struct tegra_dc *dc; + bool enabled; struct clk *clk_parent; struct clk *clk; @@ -89,6 +90,9 @@ static int tegra_output_rgb_enable(struct tegra_output *output) struct tegra_rgb *rgb = to_rgb(output); unsigned long value; + if (rgb->enabled) + return 0; + tegra_dc_write_regs(rgb->dc, rgb_enable, ARRAY_SIZE(rgb_enable)); value = DE_SELECT_ACTIVE | DE_CONTROL_NORMAL; @@ -122,6 +126,8 @@ static int tegra_output_rgb_enable(struct tegra_output *output) tegra_dc_writel(rgb->dc, GENERAL_ACT_REQ << 8, DC_CMD_STATE_CONTROL); tegra_dc_writel(rgb->dc, GENERAL_ACT_REQ, DC_CMD_STATE_CONTROL); + rgb->enabled = true; + return 0; } @@ -130,6 +136,9 @@ static int tegra_output_rgb_disable(struct tegra_output *output) struct tegra_rgb *rgb = to_rgb(output); unsigned long value; + if (!rgb->enabled) + return 0; + value = tegra_dc_readl(rgb->dc, DC_CMD_DISPLAY_POWER_CONTROL); value &= ~(PW0_ENABLE | PW1_ENABLE | PW2_ENABLE | PW3_ENABLE | PW4_ENABLE | PM0_ENABLE | PM1_ENABLE); @@ -144,6 +153,8 @@ static int tegra_output_rgb_disable(struct tegra_output *output) tegra_dc_write_regs(rgb->dc, rgb_disable, ARRAY_SIZE(rgb_disable)); + rgb->enabled = false; + return 0; } diff --git a/drivers/gpu/drm/ttm/ttm_agp_backend.c b/drivers/gpu/drm/ttm/ttm_agp_backend.c index 3302f99e7497..764be36397fd 100644 --- a/drivers/gpu/drm/ttm/ttm_agp_backend.c +++ b/drivers/gpu/drm/ttm/ttm_agp_backend.c @@ -126,6 +126,7 @@ struct ttm_tt *ttm_agp_tt_create(struct ttm_bo_device *bdev, agp_be->ttm.func = &ttm_agp_func; if (ttm_tt_init(&agp_be->ttm, bdev, size, page_flags, dummy_read_page)) { + kfree(agp_be); return NULL; } diff --git a/drivers/gpu/drm/vmwgfx/svga3d_reg.h b/drivers/gpu/drm/vmwgfx/svga3d_reg.h index b645647b7776..f58dc7dd15c5 100644 --- a/drivers/gpu/drm/vmwgfx/svga3d_reg.h +++ b/drivers/gpu/drm/vmwgfx/svga3d_reg.h @@ -261,12 +261,7 @@ typedef enum SVGA3dSurfaceFormat { /* Planar video formats. */ SVGA3D_YV12 = 121, - /* Shader constant formats. */ - SVGA3D_SURFACE_SHADERCONST_FLOAT = 122, - SVGA3D_SURFACE_SHADERCONST_INT = 123, - SVGA3D_SURFACE_SHADERCONST_BOOL = 124, - - SVGA3D_FORMAT_MAX = 125, + SVGA3D_FORMAT_MAX = 122, } SVGA3dSurfaceFormat; typedef uint32 SVGA3dColor; /* a, r, g, b */ @@ -1223,9 +1218,19 @@ typedef enum { #define SVGA_3D_CMD_INVALIDATE_GB_IMAGE_PARTIAL 1129 #define SVGA_3D_CMD_SET_GB_SHADERCONSTS_INLINE 1130 - +#define SVGA_3D_CMD_GB_SCREEN_DMA 1131 +#define SVGA_3D_CMD_BIND_GB_SURFACE_WITH_PITCH 1132 +#define SVGA_3D_CMD_GB_MOB_FENCE 1133 +#define SVGA_3D_CMD_DEFINE_GB_SURFACE_V2 1134 #define SVGA_3D_CMD_DEFINE_GB_MOB64 1135 #define SVGA_3D_CMD_REDEFINE_GB_MOB64 1136 +#define SVGA_3D_CMD_NOP_ERROR 1137 + +#define SVGA_3D_CMD_RESERVED1 1138 +#define SVGA_3D_CMD_RESERVED2 1139 +#define SVGA_3D_CMD_RESERVED3 1140 +#define SVGA_3D_CMD_RESERVED4 1141 +#define SVGA_3D_CMD_RESERVED5 1142 #define SVGA_3D_CMD_MAX 1142 #define SVGA_3D_CMD_FUTURE_MAX 3000 @@ -1973,8 +1978,7 @@ struct { uint32 sizeInBytes; uint32 validSizeInBytes; SVGAMobFormat ptDepth; -} -__attribute__((__packed__)) +} __packed SVGA3dCmdSetOTableBase; /* SVGA_3D_CMD_SET_OTABLE_BASE */ typedef @@ -1984,15 +1988,13 @@ struct { uint32 sizeInBytes; uint32 validSizeInBytes; SVGAMobFormat ptDepth; -} -__attribute__((__packed__)) +} __packed SVGA3dCmdSetOTableBase64; /* SVGA_3D_CMD_SET_OTABLE_BASE64 */ typedef struct { SVGAOTableType type; -} -__attribute__((__packed__)) +} __packed SVGA3dCmdReadbackOTable; /* SVGA_3D_CMD_READBACK_OTABLE */ /* @@ -2005,8 +2007,7 @@ struct SVGA3dCmdDefineGBMob { SVGAMobFormat ptDepth; PPN base; uint32 sizeInBytes; -} -__attribute__((__packed__)) +} __packed SVGA3dCmdDefineGBMob; /* SVGA_3D_CMD_DEFINE_GB_MOB */ @@ -2017,8 +2018,7 @@ SVGA3dCmdDefineGBMob; /* SVGA_3D_CMD_DEFINE_GB_MOB */ typedef struct SVGA3dCmdDestroyGBMob { SVGAMobId mobid; -} -__attribute__((__packed__)) +} __packed SVGA3dCmdDestroyGBMob; /* SVGA_3D_CMD_DESTROY_GB_MOB */ /* @@ -2031,8 +2031,7 @@ struct SVGA3dCmdRedefineGBMob { SVGAMobFormat ptDepth; PPN base; uint32 sizeInBytes; -} -__attribute__((__packed__)) +} __packed SVGA3dCmdRedefineGBMob; /* SVGA_3D_CMD_REDEFINE_GB_MOB */ /* @@ -2045,8 +2044,7 @@ struct SVGA3dCmdDefineGBMob64 { SVGAMobFormat ptDepth; PPN64 base; uint32 sizeInBytes; -} -__attribute__((__packed__)) +} __packed SVGA3dCmdDefineGBMob64; /* SVGA_3D_CMD_DEFINE_GB_MOB64 */ /* @@ -2059,8 +2057,7 @@ struct SVGA3dCmdRedefineGBMob64 { SVGAMobFormat ptDepth; PPN64 base; uint32 sizeInBytes; -} -__attribute__((__packed__)) +} __packed SVGA3dCmdRedefineGBMob64; /* SVGA_3D_CMD_REDEFINE_GB_MOB64 */ /* @@ -2070,8 +2067,7 @@ SVGA3dCmdRedefineGBMob64; /* SVGA_3D_CMD_REDEFINE_GB_MOB64 */ typedef struct SVGA3dCmdUpdateGBMobMapping { SVGAMobId mobid; -} -__attribute__((__packed__)) +} __packed SVGA3dCmdUpdateGBMobMapping; /* SVGA_3D_CMD_UPDATE_GB_MOB_MAPPING */ /* @@ -2087,7 +2083,8 @@ struct SVGA3dCmdDefineGBSurface { uint32 multisampleCount; SVGA3dTextureFilter autogenFilter; SVGA3dSize size; -} SVGA3dCmdDefineGBSurface; /* SVGA_3D_CMD_DEFINE_GB_SURFACE */ +} __packed +SVGA3dCmdDefineGBSurface; /* SVGA_3D_CMD_DEFINE_GB_SURFACE */ /* * Destroy a guest-backed surface. @@ -2096,7 +2093,8 @@ struct SVGA3dCmdDefineGBSurface { typedef struct SVGA3dCmdDestroyGBSurface { uint32 sid; -} SVGA3dCmdDestroyGBSurface; /* SVGA_3D_CMD_DESTROY_GB_SURFACE */ +} __packed +SVGA3dCmdDestroyGBSurface; /* SVGA_3D_CMD_DESTROY_GB_SURFACE */ /* * Bind a guest-backed surface to an object. @@ -2106,7 +2104,8 @@ typedef struct SVGA3dCmdBindGBSurface { uint32 sid; SVGAMobId mobid; -} SVGA3dCmdBindGBSurface; /* SVGA_3D_CMD_BIND_GB_SURFACE */ +} __packed +SVGA3dCmdBindGBSurface; /* SVGA_3D_CMD_BIND_GB_SURFACE */ /* * Conditionally bind a mob to a guest backed surface if testMobid @@ -2123,7 +2122,7 @@ struct{ SVGAMobId testMobid; SVGAMobId mobid; uint32 flags; -} +} __packed SVGA3dCmdCondBindGBSurface; /* SVGA_3D_CMD_COND_BIND_GB_SURFACE */ /* @@ -2135,7 +2134,8 @@ typedef struct SVGA3dCmdUpdateGBImage { SVGA3dSurfaceImageId image; SVGA3dBox box; -} SVGA3dCmdUpdateGBImage; /* SVGA_3D_CMD_UPDATE_GB_IMAGE */ +} __packed +SVGA3dCmdUpdateGBImage; /* SVGA_3D_CMD_UPDATE_GB_IMAGE */ /* * Update an entire guest-backed surface. @@ -2145,7 +2145,8 @@ struct SVGA3dCmdUpdateGBImage { typedef struct SVGA3dCmdUpdateGBSurface { uint32 sid; -} SVGA3dCmdUpdateGBSurface; /* SVGA_3D_CMD_UPDATE_GB_SURFACE */ +} __packed +SVGA3dCmdUpdateGBSurface; /* SVGA_3D_CMD_UPDATE_GB_SURFACE */ /* * Readback an image in a guest-backed surface. @@ -2155,7 +2156,8 @@ struct SVGA3dCmdUpdateGBSurface { typedef struct SVGA3dCmdReadbackGBImage { SVGA3dSurfaceImageId image; -} SVGA3dCmdReadbackGBImage; /* SVGA_3D_CMD_READBACK_GB_IMAGE*/ +} __packed +SVGA3dCmdReadbackGBImage; /* SVGA_3D_CMD_READBACK_GB_IMAGE*/ /* * Readback an entire guest-backed surface. @@ -2165,7 +2167,8 @@ struct SVGA3dCmdReadbackGBImage { typedef struct SVGA3dCmdReadbackGBSurface { uint32 sid; -} SVGA3dCmdReadbackGBSurface; /* SVGA_3D_CMD_READBACK_GB_SURFACE */ +} __packed +SVGA3dCmdReadbackGBSurface; /* SVGA_3D_CMD_READBACK_GB_SURFACE */ /* * Readback a sub rect of an image in a guest-backed surface. After @@ -2179,7 +2182,7 @@ struct SVGA3dCmdReadbackGBImagePartial { SVGA3dSurfaceImageId image; SVGA3dBox box; uint32 invertBox; -} +} __packed SVGA3dCmdReadbackGBImagePartial; /* SVGA_3D_CMD_READBACK_GB_IMAGE_PARTIAL */ /* @@ -2190,7 +2193,8 @@ SVGA3dCmdReadbackGBImagePartial; /* SVGA_3D_CMD_READBACK_GB_IMAGE_PARTIAL */ typedef struct SVGA3dCmdInvalidateGBImage { SVGA3dSurfaceImageId image; -} SVGA3dCmdInvalidateGBImage; /* SVGA_3D_CMD_INVALIDATE_GB_IMAGE */ +} __packed +SVGA3dCmdInvalidateGBImage; /* SVGA_3D_CMD_INVALIDATE_GB_IMAGE */ /* * Invalidate an entire guest-backed surface. @@ -2200,7 +2204,8 @@ struct SVGA3dCmdInvalidateGBImage { typedef struct SVGA3dCmdInvalidateGBSurface { uint32 sid; -} SVGA3dCmdInvalidateGBSurface; /* SVGA_3D_CMD_INVALIDATE_GB_SURFACE */ +} __packed +SVGA3dCmdInvalidateGBSurface; /* SVGA_3D_CMD_INVALIDATE_GB_SURFACE */ /* * Invalidate a sub rect of an image in a guest-backed surface. After @@ -2214,7 +2219,7 @@ struct SVGA3dCmdInvalidateGBImagePartial { SVGA3dSurfaceImageId image; SVGA3dBox box; uint32 invertBox; -} +} __packed SVGA3dCmdInvalidateGBImagePartial; /* SVGA_3D_CMD_INVALIDATE_GB_IMAGE_PARTIAL */ /* @@ -2224,7 +2229,8 @@ SVGA3dCmdInvalidateGBImagePartial; /* SVGA_3D_CMD_INVALIDATE_GB_IMAGE_PARTIAL */ typedef struct SVGA3dCmdDefineGBContext { uint32 cid; -} SVGA3dCmdDefineGBContext; /* SVGA_3D_CMD_DEFINE_GB_CONTEXT */ +} __packed +SVGA3dCmdDefineGBContext; /* SVGA_3D_CMD_DEFINE_GB_CONTEXT */ /* * Destroy a guest-backed context. @@ -2233,7 +2239,8 @@ struct SVGA3dCmdDefineGBContext { typedef struct SVGA3dCmdDestroyGBContext { uint32 cid; -} SVGA3dCmdDestroyGBContext; /* SVGA_3D_CMD_DESTROY_GB_CONTEXT */ +} __packed +SVGA3dCmdDestroyGBContext; /* SVGA_3D_CMD_DESTROY_GB_CONTEXT */ /* * Bind a guest-backed context. @@ -2252,7 +2259,8 @@ struct SVGA3dCmdBindGBContext { uint32 cid; SVGAMobId mobid; uint32 validContents; -} SVGA3dCmdBindGBContext; /* SVGA_3D_CMD_BIND_GB_CONTEXT */ +} __packed +SVGA3dCmdBindGBContext; /* SVGA_3D_CMD_BIND_GB_CONTEXT */ /* * Readback a guest-backed context. @@ -2262,7 +2270,8 @@ struct SVGA3dCmdBindGBContext { typedef struct SVGA3dCmdReadbackGBContext { uint32 cid; -} SVGA3dCmdReadbackGBContext; /* SVGA_3D_CMD_READBACK_GB_CONTEXT */ +} __packed +SVGA3dCmdReadbackGBContext; /* SVGA_3D_CMD_READBACK_GB_CONTEXT */ /* * Invalidate a guest-backed context. @@ -2270,7 +2279,8 @@ struct SVGA3dCmdReadbackGBContext { typedef struct SVGA3dCmdInvalidateGBContext { uint32 cid; -} SVGA3dCmdInvalidateGBContext; /* SVGA_3D_CMD_INVALIDATE_GB_CONTEXT */ +} __packed +SVGA3dCmdInvalidateGBContext; /* SVGA_3D_CMD_INVALIDATE_GB_CONTEXT */ /* * Define a guest-backed shader. @@ -2281,7 +2291,8 @@ struct SVGA3dCmdDefineGBShader { uint32 shid; SVGA3dShaderType type; uint32 sizeInBytes; -} SVGA3dCmdDefineGBShader; /* SVGA_3D_CMD_DEFINE_GB_SHADER */ +} __packed +SVGA3dCmdDefineGBShader; /* SVGA_3D_CMD_DEFINE_GB_SHADER */ /* * Bind a guest-backed shader. @@ -2291,7 +2302,8 @@ typedef struct SVGA3dCmdBindGBShader { uint32 shid; SVGAMobId mobid; uint32 offsetInBytes; -} SVGA3dCmdBindGBShader; /* SVGA_3D_CMD_BIND_GB_SHADER */ +} __packed +SVGA3dCmdBindGBShader; /* SVGA_3D_CMD_BIND_GB_SHADER */ /* * Destroy a guest-backed shader. @@ -2299,7 +2311,8 @@ typedef struct SVGA3dCmdBindGBShader { typedef struct SVGA3dCmdDestroyGBShader { uint32 shid; -} SVGA3dCmdDestroyGBShader; /* SVGA_3D_CMD_DESTROY_GB_SHADER */ +} __packed +SVGA3dCmdDestroyGBShader; /* SVGA_3D_CMD_DESTROY_GB_SHADER */ typedef struct { @@ -2314,14 +2327,16 @@ struct { * Note that FLOAT and INT constants are 4-dwords in length, while * BOOL constants are 1-dword in length. */ -} SVGA3dCmdSetGBShaderConstInline; +} __packed +SVGA3dCmdSetGBShaderConstInline; /* SVGA_3D_CMD_SET_GB_SHADERCONSTS_INLINE */ typedef struct { uint32 cid; SVGA3dQueryType type; -} SVGA3dCmdBeginGBQuery; /* SVGA_3D_CMD_BEGIN_GB_QUERY */ +} __packed +SVGA3dCmdBeginGBQuery; /* SVGA_3D_CMD_BEGIN_GB_QUERY */ typedef struct { @@ -2329,7 +2344,8 @@ struct { SVGA3dQueryType type; SVGAMobId mobid; uint32 offset; -} SVGA3dCmdEndGBQuery; /* SVGA_3D_CMD_END_GB_QUERY */ +} __packed +SVGA3dCmdEndGBQuery; /* SVGA_3D_CMD_END_GB_QUERY */ /* @@ -2346,21 +2362,22 @@ struct { SVGA3dQueryType type; SVGAMobId mobid; uint32 offset; -} SVGA3dCmdWaitForGBQuery; /* SVGA_3D_CMD_WAIT_FOR_GB_QUERY */ +} __packed +SVGA3dCmdWaitForGBQuery; /* SVGA_3D_CMD_WAIT_FOR_GB_QUERY */ typedef struct { SVGAMobId mobid; uint32 fbOffset; uint32 initalized; -} +} __packed SVGA3dCmdEnableGart; /* SVGA_3D_CMD_ENABLE_GART */ typedef struct { SVGAMobId mobid; uint32 gartOffset; -} +} __packed SVGA3dCmdMapMobIntoGart; /* SVGA_3D_CMD_MAP_MOB_INTO_GART */ @@ -2368,7 +2385,7 @@ typedef struct { uint32 gartOffset; uint32 numPages; -} +} __packed SVGA3dCmdUnmapGartRange; /* SVGA_3D_CMD_UNMAP_GART_RANGE */ @@ -2385,27 +2402,27 @@ struct { int32 xRoot; int32 yRoot; uint32 flags; -} +} __packed SVGA3dCmdDefineGBScreenTarget; /* SVGA_3D_CMD_DEFINE_GB_SCREENTARGET */ typedef struct { uint32 stid; -} +} __packed SVGA3dCmdDestroyGBScreenTarget; /* SVGA_3D_CMD_DESTROY_GB_SCREENTARGET */ typedef struct { uint32 stid; SVGA3dSurfaceImageId image; -} +} __packed SVGA3dCmdBindGBScreenTarget; /* SVGA_3D_CMD_BIND_GB_SCREENTARGET */ typedef struct { uint32 stid; SVGA3dBox box; -} +} __packed SVGA3dCmdUpdateGBScreenTarget; /* SVGA_3D_CMD_UPDATE_GB_SCREENTARGET */ /* diff --git a/drivers/gpu/drm/vmwgfx/svga3d_surfacedefs.h b/drivers/gpu/drm/vmwgfx/svga3d_surfacedefs.h index 8369c3ba10fe..ef3385096145 100644 --- a/drivers/gpu/drm/vmwgfx/svga3d_surfacedefs.h +++ b/drivers/gpu/drm/vmwgfx/svga3d_surfacedefs.h @@ -38,8 +38,11 @@ #define DIV_ROUND_UP(x, y) (((x) + (y) - 1) / (y)) #define max_t(type, x, y) ((x) > (y) ? (x) : (y)) +#define min_t(type, x, y) ((x) < (y) ? (x) : (y)) #define surf_size_struct SVGA3dSize #define u32 uint32 +#define u64 uint64_t +#define U32_MAX ((u32)~0U) #endif /* __KERNEL__ */ @@ -704,8 +707,8 @@ static const struct svga3d_surface_desc svga3d_surface_descs[] = { static inline u32 clamped_umul32(u32 a, u32 b) { - uint64_t tmp = (uint64_t) a*b; - return (tmp > (uint64_t) ((u32) -1)) ? (u32) -1 : tmp; + u64 tmp = (u64) a*b; + return (tmp > (u64) U32_MAX) ? U32_MAX : tmp; } static inline const struct svga3d_surface_desc * @@ -834,7 +837,7 @@ svga3dsurface_get_serialized_size(SVGA3dSurfaceFormat format, bool cubemap) { const struct svga3d_surface_desc *desc = svga3dsurface_get_desc(format); - u32 total_size = 0; + u64 total_size = 0; u32 mip; for (mip = 0; mip < num_mip_levels; mip++) { @@ -847,7 +850,7 @@ svga3dsurface_get_serialized_size(SVGA3dSurfaceFormat format, if (cubemap) total_size *= SVGA3D_MAX_SURFACE_FACES; - return total_size; + return (u32) min_t(u64, total_size, (u64) U32_MAX); } diff --git a/drivers/gpu/drm/vmwgfx/svga_reg.h b/drivers/gpu/drm/vmwgfx/svga_reg.h index 71defa4d2d75..11323dd5196f 100644 --- a/drivers/gpu/drm/vmwgfx/svga_reg.h +++ b/drivers/gpu/drm/vmwgfx/svga_reg.h @@ -169,10 +169,17 @@ enum { SVGA_REG_TRACES = 45, /* Enable trace-based updates even when FIFO is on */ SVGA_REG_GMRS_MAX_PAGES = 46, /* Maximum number of 4KB pages for all GMRs */ SVGA_REG_MEMORY_SIZE = 47, /* Total dedicated device memory excluding FIFO */ + SVGA_REG_COMMAND_LOW = 48, /* Lower 32 bits and submits commands */ + SVGA_REG_COMMAND_HIGH = 49, /* Upper 32 bits of command buffer PA */ SVGA_REG_MAX_PRIMARY_BOUNDING_BOX_MEM = 50, /* Max primary memory */ SVGA_REG_SUGGESTED_GBOBJECT_MEM_SIZE_KB = 51, /* Suggested limit on mob mem */ SVGA_REG_DEV_CAP = 52, /* Write dev cap index, read value */ - SVGA_REG_TOP = 53, /* Must be 1 more than the last register */ + SVGA_REG_CMD_PREPEND_LOW = 53, + SVGA_REG_CMD_PREPEND_HIGH = 54, + SVGA_REG_SCREENTARGET_MAX_WIDTH = 55, + SVGA_REG_SCREENTARGET_MAX_HEIGHT = 56, + SVGA_REG_MOB_MAX_SIZE = 57, + SVGA_REG_TOP = 58, /* Must be 1 more than the last register */ SVGA_PALETTE_BASE = 1024, /* Base of SVGA color map */ /* Next 768 (== 256*3) registers exist for colormap */ diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_context.c b/drivers/gpu/drm/vmwgfx/vmwgfx_context.c index 9426c53fb483..1e80152674b5 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_context.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_context.c @@ -551,8 +551,7 @@ static int vmw_context_scrub_shader(struct vmw_ctx_bindinfo *bi, bool rebind) cmd->header.size = sizeof(cmd->body); cmd->body.cid = bi->ctx->id; cmd->body.type = bi->i1.shader_type; - cmd->body.shid = - cpu_to_le32((rebind) ? bi->res->id : SVGA3D_INVALID_ID); + cmd->body.shid = ((rebind) ? bi->res->id : SVGA3D_INVALID_ID); vmw_fifo_commit(dev_priv, sizeof(*cmd)); return 0; @@ -585,8 +584,7 @@ static int vmw_context_scrub_render_target(struct vmw_ctx_bindinfo *bi, cmd->header.size = sizeof(cmd->body); cmd->body.cid = bi->ctx->id; cmd->body.type = bi->i1.rt_type; - cmd->body.target.sid = - cpu_to_le32((rebind) ? bi->res->id : SVGA3D_INVALID_ID); + cmd->body.target.sid = ((rebind) ? bi->res->id : SVGA3D_INVALID_ID); cmd->body.target.face = 0; cmd->body.target.mipmap = 0; vmw_fifo_commit(dev_priv, sizeof(*cmd)); @@ -628,8 +626,7 @@ static int vmw_context_scrub_texture(struct vmw_ctx_bindinfo *bi, cmd->body.c.cid = bi->ctx->id; cmd->body.s1.stage = bi->i1.texture_stage; cmd->body.s1.name = SVGA3D_TS_BIND_TEXTURE; - cmd->body.s1.value = - cpu_to_le32((rebind) ? bi->res->id : SVGA3D_INVALID_ID); + cmd->body.s1.value = ((rebind) ? bi->res->id : SVGA3D_INVALID_ID); vmw_fifo_commit(dev_priv, sizeof(*cmd)); return 0; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index 3bdc0adc656d..0083cbf99edf 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -667,6 +667,7 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset) dev_priv->memory_size = 512*1024*1024; } dev_priv->max_mob_pages = 0; + dev_priv->max_mob_size = 0; if (dev_priv->capabilities & SVGA_CAP_GBOBJECTS) { uint64_t mem_size = vmw_read(dev_priv, @@ -676,6 +677,8 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset) dev_priv->prim_bb_mem = vmw_read(dev_priv, SVGA_REG_MAX_PRIMARY_BOUNDING_BOX_MEM); + dev_priv->max_mob_size = + vmw_read(dev_priv, SVGA_REG_MOB_MAX_SIZE); } else dev_priv->prim_bb_mem = dev_priv->vram_size; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h index ecaa302a6154..07831554dad7 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h @@ -40,7 +40,7 @@ #include <drm/ttm/ttm_module.h> #include "vmwgfx_fence.h" -#define VMWGFX_DRIVER_DATE "20121114" +#define VMWGFX_DRIVER_DATE "20140228" #define VMWGFX_DRIVER_MAJOR 2 #define VMWGFX_DRIVER_MINOR 5 #define VMWGFX_DRIVER_PATCHLEVEL 0 @@ -386,6 +386,7 @@ struct vmw_private { uint32_t max_gmr_ids; uint32_t max_gmr_pages; uint32_t max_mob_pages; + uint32_t max_mob_size; uint32_t memory_size; bool has_gmr; bool has_mob; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c index 269b85cc875a..efb575a7996c 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c @@ -602,7 +602,7 @@ static int vmw_cmd_cid_check(struct vmw_private *dev_priv, { struct vmw_cid_cmd { SVGA3dCmdHeader header; - __le32 cid; + uint32_t cid; } *cmd; cmd = container_of(header, struct vmw_cid_cmd, header); @@ -1835,7 +1835,7 @@ static int vmw_cmd_check_not_3d(struct vmw_private *dev_priv, return 0; } -static const struct vmw_cmd_entry const vmw_cmd_entries[SVGA_3D_CMD_MAX] = { +static const struct vmw_cmd_entry vmw_cmd_entries[SVGA_3D_CMD_MAX] = { VMW_CMD_DEF(SVGA_3D_CMD_SURFACE_DEFINE, &vmw_cmd_invalid, false, false, false), VMW_CMD_DEF(SVGA_3D_CMD_SURFACE_DESTROY, &vmw_cmd_invalid, @@ -2032,6 +2032,9 @@ static int vmw_cmd_check(struct vmw_private *dev_priv, goto out_invalid; entry = &vmw_cmd_entries[cmd_id]; + if (unlikely(!entry->func)) + goto out_invalid; + if (unlikely(!entry->user_allow && !sw_context->kernel)) goto out_privileged; @@ -2469,7 +2472,7 @@ int vmw_execbuf_process(struct drm_file *file_priv, if (dev_priv->has_mob) { ret = vmw_rebind_contexts(sw_context); if (unlikely(ret != 0)) - goto out_err; + goto out_unlock_binding; } cmd = vmw_fifo_reserve(dev_priv, command_size); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c index f9881f9e62bd..47b70949bf3a 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c @@ -102,6 +102,9 @@ int vmw_getparam_ioctl(struct drm_device *dev, void *data, vmw_fp->gb_aware = true; param->value = dev_priv->max_mob_pages * PAGE_SIZE; break; + case DRM_VMW_PARAM_MAX_MOB_SIZE: + param->value = dev_priv->max_mob_size; + break; default: DRM_ERROR("Illegal vmwgfx get param request: %d\n", param->param); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c b/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c index d4a5a19cb8c3..04a64b8cd3cd 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c @@ -188,18 +188,20 @@ static void vmw_takedown_otable_base(struct vmw_private *dev_priv, bo = otable->page_table->pt_bo; cmd = vmw_fifo_reserve(dev_priv, sizeof(*cmd)); - if (unlikely(cmd == NULL)) - DRM_ERROR("Failed reserving FIFO space for OTable setup.\n"); - - memset(cmd, 0, sizeof(*cmd)); - cmd->header.id = SVGA_3D_CMD_SET_OTABLE_BASE; - cmd->header.size = sizeof(cmd->body); - cmd->body.type = type; - cmd->body.baseAddress = 0; - cmd->body.sizeInBytes = 0; - cmd->body.validSizeInBytes = 0; - cmd->body.ptDepth = SVGA3D_MOBFMT_INVALID; - vmw_fifo_commit(dev_priv, sizeof(*cmd)); + if (unlikely(cmd == NULL)) { + DRM_ERROR("Failed reserving FIFO space for OTable " + "takedown.\n"); + } else { + memset(cmd, 0, sizeof(*cmd)); + cmd->header.id = SVGA_3D_CMD_SET_OTABLE_BASE; + cmd->header.size = sizeof(cmd->body); + cmd->body.type = type; + cmd->body.baseAddress = 0; + cmd->body.sizeInBytes = 0; + cmd->body.validSizeInBytes = 0; + cmd->body.ptDepth = SVGA3D_MOBFMT_INVALID; + vmw_fifo_commit(dev_priv, sizeof(*cmd)); + } if (bo) { int ret; @@ -562,11 +564,12 @@ void vmw_mob_unbind(struct vmw_private *dev_priv, if (unlikely(cmd == NULL)) { DRM_ERROR("Failed reserving FIFO space for Memory " "Object unbinding.\n"); + } else { + cmd->header.id = SVGA_3D_CMD_DESTROY_GB_MOB; + cmd->header.size = sizeof(cmd->body); + cmd->body.mobid = mob->id; + vmw_fifo_commit(dev_priv, sizeof(*cmd)); } - cmd->header.id = SVGA_3D_CMD_DESTROY_GB_MOB; - cmd->header.size = sizeof(cmd->body); - cmd->body.mobid = mob->id; - vmw_fifo_commit(dev_priv, sizeof(*cmd)); if (bo) { vmw_fence_single_bo(bo, NULL); ttm_bo_unreserve(bo); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c index 2aa4bc6a4d60..9757b57f8388 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c @@ -427,8 +427,7 @@ int vmw_dmabuf_init(struct vmw_private *dev_priv, INIT_LIST_HEAD(&vmw_bo->res_list); ret = ttm_bo_init(bdev, &vmw_bo->base, size, - (user) ? ttm_bo_type_device : - ttm_bo_type_kernel, placement, + ttm_bo_type_device, placement, 0, interruptible, NULL, acc_size, NULL, bo_free); return ret; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c b/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c index 217d941b8176..ee3856578a12 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c @@ -371,13 +371,13 @@ int vmw_shader_destroy_ioctl(struct drm_device *dev, void *data, TTM_REF_USAGE); } -int vmw_shader_alloc(struct vmw_private *dev_priv, - struct vmw_dma_buffer *buffer, - size_t shader_size, - size_t offset, - SVGA3dShaderType shader_type, - struct ttm_object_file *tfile, - u32 *handle) +static int vmw_shader_alloc(struct vmw_private *dev_priv, + struct vmw_dma_buffer *buffer, + size_t shader_size, + size_t offset, + SVGA3dShaderType shader_type, + struct ttm_object_file *tfile, + u32 *handle) { struct vmw_user_shader *ushader; struct vmw_resource *res, *tmp; @@ -779,6 +779,8 @@ vmw_compat_shader_man_create(struct vmw_private *dev_priv) int ret; man = kzalloc(sizeof(*man), GFP_KERNEL); + if (man == NULL) + return ERR_PTR(-ENOMEM); man->dev_priv = dev_priv; INIT_LIST_HEAD(&man->list); diff --git a/drivers/gpu/host1x/job.c b/drivers/gpu/host1x/job.c index 1146e3bba6e1..112f27e51bc7 100644 --- a/drivers/gpu/host1x/job.c +++ b/drivers/gpu/host1x/job.c @@ -538,7 +538,7 @@ int host1x_job_pin(struct host1x_job *job, struct device *dev) g->base = job->gather_addr_phys[i]; - for (j = 0; j < job->num_gathers; j++) + for (j = i + 1; j < job->num_gathers; j++) if (job->gathers[j].bo == g->bo) job->gathers[j].handled = true; diff --git a/drivers/hid/hid-apple.c b/drivers/hid/hid-apple.c index 497558127bb3..f822fd2a1ada 100644 --- a/drivers/hid/hid-apple.c +++ b/drivers/hid/hid-apple.c @@ -469,6 +469,9 @@ static const struct hid_device_id apple_devices[] = { { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_ANSI), .driver_data = APPLE_NUMLOCK_EMULATION | APPLE_HAS_FN }, + { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, + USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_JIS), + .driver_data = APPLE_NUMLOCK_EMULATION | APPLE_HAS_FN }, { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_JIS), .driver_data = APPLE_NUMLOCK_EMULATION | APPLE_HAS_FN }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING_ANSI), diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index 3bfac3accd22..cc32a6f96c64 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -1679,6 +1679,7 @@ static const struct hid_device_id hid_have_special_driver[] = { { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_JIS) }, { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_ANSI) }, { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_ISO) }, + { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_JIS) }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_FOUNTAIN_TP_ONLY) }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_GEYSER1_TP_ONLY) }, { HID_USB_DEVICE(USB_VENDOR_ID_AUREAL, USB_DEVICE_ID_AUREAL_W01RN) }, @@ -1779,6 +1780,8 @@ static const struct hid_device_id hid_have_special_driver[] = { { HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_PRESENTER_8K_USB) }, { HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_DIGITAL_MEDIA_3K) }, { HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_WIRELESS_OPTICAL_DESKTOP_3_0) }, + { HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TYPE_COVER_2) }, + { HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TOUCH_COVER_2) }, { HID_USB_DEVICE(USB_VENDOR_ID_MONTEREY, USB_DEVICE_ID_GENIUS_KB29E) }, { HID_USB_DEVICE(USB_VENDOR_ID_NTRIG, USB_DEVICE_ID_NTRIG_TOUCH_SCREEN) }, { HID_USB_DEVICE(USB_VENDOR_ID_NTRIG, USB_DEVICE_ID_NTRIG_TOUCH_SCREEN_1) }, diff --git a/drivers/hid/hid-hyperv.c b/drivers/hid/hid-hyperv.c index 8fae6d1414cc..c24908f14934 100644 --- a/drivers/hid/hid-hyperv.c +++ b/drivers/hid/hid-hyperv.c @@ -157,6 +157,7 @@ struct mousevsc_dev { u32 report_desc_size; struct hv_input_dev_info hid_dev_info; struct hid_device *hid_device; + u8 input_buf[HID_MAX_BUFFER_SIZE]; }; @@ -256,6 +257,7 @@ static void mousevsc_on_receive(struct hv_device *device, struct synthhid_msg *hid_msg; struct mousevsc_dev *input_dev = hv_get_drvdata(device); struct synthhid_input_report *input_report; + size_t len; pipe_msg = (struct pipe_prt_msg *)((unsigned long)packet + (packet->offset8 << 3)); @@ -300,9 +302,12 @@ static void mousevsc_on_receive(struct hv_device *device, (struct synthhid_input_report *)pipe_msg->data; if (!input_dev->init_complete) break; - hid_input_report(input_dev->hid_device, - HID_INPUT_REPORT, input_report->buffer, - input_report->header.size, 1); + + len = min(input_report->header.size, + (u32)sizeof(input_dev->input_buf)); + memcpy(input_dev->input_buf, input_report->buffer, len); + hid_input_report(input_dev->hid_device, HID_INPUT_REPORT, + input_dev->input_buf, len, 1); break; default: pr_err("unsupported hid msg type - type %d len %d", diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 5a5248f2cc07..22f28d6b33a8 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -135,6 +135,7 @@ #define USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_JIS 0x023b #define USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_ANSI 0x0255 #define USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_ISO 0x0256 +#define USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_JIS 0x0257 #define USB_DEVICE_ID_APPLE_WELLSPRING8_ANSI 0x0290 #define USB_DEVICE_ID_APPLE_WELLSPRING8_ISO 0x0291 #define USB_DEVICE_ID_APPLE_WELLSPRING8_JIS 0x0292 @@ -240,6 +241,7 @@ #define USB_VENDOR_ID_CYGNAL 0x10c4 #define USB_DEVICE_ID_CYGNAL_RADIO_SI470X 0x818a +#define USB_DEVICE_ID_FOCALTECH_FTXXXX_MULTITOUCH 0x81b9 #define USB_DEVICE_ID_CYGNAL_RADIO_SI4713 0x8244 @@ -451,6 +453,9 @@ #define USB_VENDOR_ID_INTEL_1 0x8087 #define USB_DEVICE_ID_INTEL_HID_SENSOR 0x09fa +#define USB_VENDOR_ID_STM_0 0x0483 +#define USB_DEVICE_ID_STM_HID_SENSOR 0x91d1 + #define USB_VENDOR_ID_ION 0x15e4 #define USB_DEVICE_ID_ICADE 0x0132 @@ -619,6 +624,8 @@ #define USB_DEVICE_ID_MS_PRESENTER_8K_USB 0x0713 #define USB_DEVICE_ID_MS_DIGITAL_MEDIA_3K 0x0730 #define USB_DEVICE_ID_MS_COMFORT_MOUSE_4500 0x076c +#define USB_DEVICE_ID_MS_TOUCH_COVER_2 0x07a7 +#define USB_DEVICE_ID_MS_TYPE_COVER_2 0x07a9 #define USB_VENDOR_ID_MOJO 0x8282 #define USB_DEVICE_ID_RETRO_ADAPTER 0x3201 @@ -644,6 +651,7 @@ #define USB_VENDOR_ID_NEXIO 0x1870 #define USB_DEVICE_ID_NEXIO_MULTITOUCH_420 0x010d +#define USB_DEVICE_ID_NEXIO_MULTITOUCH_PTI0750 0x0110 #define USB_VENDOR_ID_NEXTWINDOW 0x1926 #define USB_DEVICE_ID_NEXTWINDOW_TOUCHSCREEN 0x0003 diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c index d50e7313b171..a713e6211419 100644 --- a/drivers/hid/hid-input.c +++ b/drivers/hid/hid-input.c @@ -1178,7 +1178,7 @@ static void hidinput_led_worker(struct work_struct *work) /* fall back to generic raw-output-report */ len = ((report->size - 1) >> 3) + 1 + (report->id > 0); - buf = kmalloc(len, GFP_KERNEL); + buf = hid_alloc_report_buf(report, GFP_KERNEL); if (!buf) return; diff --git a/drivers/hid/hid-microsoft.c b/drivers/hid/hid-microsoft.c index c6ef6eed3091..404a3a8a82f1 100644 --- a/drivers/hid/hid-microsoft.c +++ b/drivers/hid/hid-microsoft.c @@ -208,6 +208,10 @@ static const struct hid_device_id ms_devices[] = { .driver_data = MS_NOGET }, { HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_COMFORT_MOUSE_4500), .driver_data = MS_DUPLICATE_USAGES }, + { HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TYPE_COVER_2), + .driver_data = 0 }, + { HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TOUCH_COVER_2), + .driver_data = 0 }, { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_PRESENTER_8K_BT), .driver_data = MS_PRESENTER }, diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c index f134d73beca1..221d503f1c24 100644 --- a/drivers/hid/hid-multitouch.c +++ b/drivers/hid/hid-multitouch.c @@ -1166,6 +1166,11 @@ static const struct hid_device_id mt_devices[] = { MT_USB_DEVICE(USB_VENDOR_ID_FLATFROG, USB_DEVICE_ID_MULTITOUCH_3200) }, + /* FocalTech Panels */ + { .driver_data = MT_CLS_SERIAL, + MT_USB_DEVICE(USB_VENDOR_ID_CYGNAL, + USB_DEVICE_ID_FOCALTECH_FTXXXX_MULTITOUCH) }, + /* GeneralTouch panel */ { .driver_data = MT_CLS_GENERALTOUCH_TWOFINGERS, MT_USB_DEVICE(USB_VENDOR_ID_GENERAL_TOUCH, diff --git a/drivers/hid/hid-sensor-hub.c b/drivers/hid/hid-sensor-hub.c index 46f4480035bc..9c22e14c57f0 100644 --- a/drivers/hid/hid-sensor-hub.c +++ b/drivers/hid/hid-sensor-hub.c @@ -665,6 +665,9 @@ static const struct hid_device_id sensor_hub_devices[] = { { HID_DEVICE(HID_BUS_ANY, HID_GROUP_SENSOR_HUB, USB_VENDOR_ID_INTEL_1, USB_DEVICE_ID_INTEL_HID_SENSOR), .driver_data = HID_SENSOR_HUB_ENUM_QUIRK}, + { HID_DEVICE(HID_BUS_ANY, HID_GROUP_SENSOR_HUB, USB_VENDOR_ID_STM_0, + USB_DEVICE_ID_STM_HID_SENSOR), + .driver_data = HID_SENSOR_HUB_ENUM_QUIRK}, { HID_DEVICE(HID_BUS_ANY, HID_GROUP_SENSOR_HUB, HID_ANY_ID, HID_ANY_ID) }, { } diff --git a/drivers/hid/i2c-hid/i2c-hid.c b/drivers/hid/i2c-hid/i2c-hid.c index d1f81f52481a..42eebd14de1f 100644 --- a/drivers/hid/i2c-hid/i2c-hid.c +++ b/drivers/hid/i2c-hid/i2c-hid.c @@ -582,7 +582,7 @@ static void i2c_hid_request(struct hid_device *hid, struct hid_report *rep, int ret; int len = i2c_hid_get_report_length(rep) - 2; - buf = kzalloc(len, GFP_KERNEL); + buf = hid_alloc_report_buf(rep, GFP_KERNEL); if (!buf) return; diff --git a/drivers/hid/usbhid/hid-quirks.c b/drivers/hid/usbhid/hid-quirks.c index 175ec0afb70c..dbd83878ff99 100644 --- a/drivers/hid/usbhid/hid-quirks.c +++ b/drivers/hid/usbhid/hid-quirks.c @@ -74,6 +74,7 @@ static const struct hid_blacklist { { USB_VENDOR_ID_FREESCALE, USB_DEVICE_ID_FREESCALE_MX28, HID_QUIRK_NOGET }, { USB_VENDOR_ID_MGE, USB_DEVICE_ID_MGE_UPS, HID_QUIRK_NOGET }, { USB_VENDOR_ID_MSI, USB_DEVICE_ID_MSI_GX680R_LED_PANEL, HID_QUIRK_NO_INIT_REPORTS }, + { USB_VENDOR_ID_NEXIO, USB_DEVICE_ID_NEXIO_MULTITOUCH_PTI0750, HID_QUIRK_NO_INIT_REPORTS }, { USB_VENDOR_ID_NOVATEK, USB_DEVICE_ID_NOVATEK_MOUSE, HID_QUIRK_NO_INIT_REPORTS }, { USB_VENDOR_ID_PIXART, USB_DEVICE_ID_PIXART_OPTICAL_TOUCH_SCREEN, HID_QUIRK_NO_INIT_REPORTS }, { USB_VENDOR_ID_PIXART, USB_DEVICE_ID_PIXART_OPTICAL_TOUCH_SCREEN1, HID_QUIRK_NO_INIT_REPORTS }, diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c index af6edf9b1936..f2d7bf90c9fe 100644 --- a/drivers/hv/connection.c +++ b/drivers/hv/connection.c @@ -67,7 +67,6 @@ static int vmbus_negotiate_version(struct vmbus_channel_msginfo *msginfo, int ret = 0; struct vmbus_channel_initiate_contact *msg; unsigned long flags; - int t; init_completion(&msginfo->waitevent); @@ -78,6 +77,8 @@ static int vmbus_negotiate_version(struct vmbus_channel_msginfo *msginfo, msg->interrupt_page = virt_to_phys(vmbus_connection.int_page); msg->monitor_page1 = virt_to_phys(vmbus_connection.monitor_pages[0]); msg->monitor_page2 = virt_to_phys(vmbus_connection.monitor_pages[1]); + if (version == VERSION_WIN8) + msg->target_vcpu = hv_context.vp_index[smp_processor_id()]; /* * Add to list before we send the request since we may @@ -100,15 +101,7 @@ static int vmbus_negotiate_version(struct vmbus_channel_msginfo *msginfo, } /* Wait for the connection response */ - t = wait_for_completion_timeout(&msginfo->waitevent, 5*HZ); - if (t == 0) { - spin_lock_irqsave(&vmbus_connection.channelmsg_lock, - flags); - list_del(&msginfo->msglistentry); - spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, - flags); - return -ETIMEDOUT; - } + wait_for_completion(&msginfo->waitevent); spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags); list_del(&msginfo->msglistentry); diff --git a/drivers/hwmon/max1668.c b/drivers/hwmon/max1668.c index a7626358c95d..029b65e6c589 100644 --- a/drivers/hwmon/max1668.c +++ b/drivers/hwmon/max1668.c @@ -243,7 +243,7 @@ static ssize_t set_temp_min(struct device *dev, data->temp_min[index] = clamp_val(temp/1000, -128, 127); if (i2c_smbus_write_byte_data(client, MAX1668_REG_LIML_WR(index), - data->temp_max[index])) + data->temp_min[index])) count = -EIO; mutex_unlock(&data->update_lock); diff --git a/drivers/hwmon/ntc_thermistor.c b/drivers/hwmon/ntc_thermistor.c index 8c23203915af..8a17f01e8672 100644 --- a/drivers/hwmon/ntc_thermistor.c +++ b/drivers/hwmon/ntc_thermistor.c @@ -145,7 +145,7 @@ struct ntc_data { static int ntc_adc_iio_read(struct ntc_thermistor_platform_data *pdata) { struct iio_channel *channel = pdata->chan; - unsigned int result; + s64 result; int val, ret; ret = iio_read_channel_raw(channel, &val); @@ -155,10 +155,10 @@ static int ntc_adc_iio_read(struct ntc_thermistor_platform_data *pdata) } /* unit: mV */ - result = pdata->pullup_uv * val; + result = pdata->pullup_uv * (s64) val; result >>= 12; - return result; + return (int)result; } static const struct of_device_id ntc_match[] = { diff --git a/drivers/i2c/busses/i2c-mv64xxx.c b/drivers/i2c/busses/i2c-mv64xxx.c index b8c5187b9ee0..d52d84937ad3 100644 --- a/drivers/i2c/busses/i2c-mv64xxx.c +++ b/drivers/i2c/busses/i2c-mv64xxx.c @@ -97,7 +97,6 @@ enum { enum { MV64XXX_I2C_ACTION_INVALID, MV64XXX_I2C_ACTION_CONTINUE, - MV64XXX_I2C_ACTION_OFFLOAD_SEND_START, MV64XXX_I2C_ACTION_SEND_START, MV64XXX_I2C_ACTION_SEND_RESTART, MV64XXX_I2C_ACTION_OFFLOAD_RESTART, @@ -204,6 +203,9 @@ static int mv64xxx_i2c_offload_msg(struct mv64xxx_i2c_data *drv_data) unsigned long ctrl_reg; struct i2c_msg *msg = drv_data->msgs; + if (!drv_data->offload_enabled) + return -EOPNOTSUPP; + drv_data->msg = msg; drv_data->byte_posn = 0; drv_data->bytes_left = msg->len; @@ -433,8 +435,7 @@ mv64xxx_i2c_do_action(struct mv64xxx_i2c_data *drv_data) drv_data->msgs++; drv_data->num_msgs--; - if (!(drv_data->offload_enabled && - mv64xxx_i2c_offload_msg(drv_data))) { + if (mv64xxx_i2c_offload_msg(drv_data) < 0) { drv_data->cntl_bits |= MV64XXX_I2C_REG_CONTROL_START; writel(drv_data->cntl_bits, drv_data->reg_base + drv_data->reg_offsets.control); @@ -458,15 +459,14 @@ mv64xxx_i2c_do_action(struct mv64xxx_i2c_data *drv_data) drv_data->reg_base + drv_data->reg_offsets.control); break; - case MV64XXX_I2C_ACTION_OFFLOAD_SEND_START: - if (!mv64xxx_i2c_offload_msg(drv_data)) - break; - else - drv_data->action = MV64XXX_I2C_ACTION_SEND_START; - /* FALLTHRU */ case MV64XXX_I2C_ACTION_SEND_START: - writel(drv_data->cntl_bits | MV64XXX_I2C_REG_CONTROL_START, - drv_data->reg_base + drv_data->reg_offsets.control); + /* Can we offload this msg ? */ + if (mv64xxx_i2c_offload_msg(drv_data) < 0) { + /* No, switch to standard path */ + mv64xxx_i2c_prepare_for_io(drv_data, drv_data->msgs); + writel(drv_data->cntl_bits | MV64XXX_I2C_REG_CONTROL_START, + drv_data->reg_base + drv_data->reg_offsets.control); + } break; case MV64XXX_I2C_ACTION_SEND_ADDR_1: @@ -625,15 +625,10 @@ mv64xxx_i2c_execute_msg(struct mv64xxx_i2c_data *drv_data, struct i2c_msg *msg, unsigned long flags; spin_lock_irqsave(&drv_data->lock, flags); - if (drv_data->offload_enabled) { - drv_data->action = MV64XXX_I2C_ACTION_OFFLOAD_SEND_START; - drv_data->state = MV64XXX_I2C_STATE_WAITING_FOR_START_COND; - } else { - mv64xxx_i2c_prepare_for_io(drv_data, msg); - drv_data->action = MV64XXX_I2C_ACTION_SEND_START; - drv_data->state = MV64XXX_I2C_STATE_WAITING_FOR_START_COND; - } + drv_data->action = MV64XXX_I2C_ACTION_SEND_START; + drv_data->state = MV64XXX_I2C_STATE_WAITING_FOR_START_COND; + drv_data->send_stop = is_last; drv_data->block = 1; mv64xxx_i2c_do_action(drv_data); diff --git a/drivers/iio/accel/bma180.c b/drivers/iio/accel/bma180.c index 3bec9220df04..bfec313492b3 100644 --- a/drivers/iio/accel/bma180.c +++ b/drivers/iio/accel/bma180.c @@ -447,14 +447,14 @@ static const struct iio_chan_spec_ext_info bma180_ext_info[] = { { }, }; -#define BMA180_CHANNEL(_index) { \ +#define BMA180_CHANNEL(_axis) { \ .type = IIO_ACCEL, \ - .indexed = 1, \ - .channel = (_index), \ + .modified = 1, \ + .channel2 = IIO_MOD_##_axis, \ .info_mask_separate = BIT(IIO_CHAN_INFO_RAW) | \ BIT(IIO_CHAN_INFO_LOW_PASS_FILTER_3DB_FREQUENCY), \ .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), \ - .scan_index = (_index), \ + .scan_index = AXIS_##_axis, \ .scan_type = { \ .sign = 's', \ .realbits = 14, \ @@ -465,10 +465,10 @@ static const struct iio_chan_spec_ext_info bma180_ext_info[] = { } static const struct iio_chan_spec bma180_channels[] = { - BMA180_CHANNEL(AXIS_X), - BMA180_CHANNEL(AXIS_Y), - BMA180_CHANNEL(AXIS_Z), - IIO_CHAN_SOFT_TIMESTAMP(4), + BMA180_CHANNEL(X), + BMA180_CHANNEL(Y), + BMA180_CHANNEL(Z), + IIO_CHAN_SOFT_TIMESTAMP(3), }; static irqreturn_t bma180_trigger_handler(int irq, void *p) diff --git a/drivers/iio/adc/max1363.c b/drivers/iio/adc/max1363.c index e283f2f2ee2f..360259266d4f 100644 --- a/drivers/iio/adc/max1363.c +++ b/drivers/iio/adc/max1363.c @@ -1560,7 +1560,7 @@ static int max1363_probe(struct i2c_client *client, st->client = client; st->vref_uv = st->chip_info->int_vref_mv * 1000; - vref = devm_regulator_get(&client->dev, "vref"); + vref = devm_regulator_get_optional(&client->dev, "vref"); if (!IS_ERR(vref)) { int vref_uv; diff --git a/drivers/iio/gyro/Kconfig b/drivers/iio/gyro/Kconfig index 41c64a43bcab..ac2d69e34c8c 100644 --- a/drivers/iio/gyro/Kconfig +++ b/drivers/iio/gyro/Kconfig @@ -70,7 +70,7 @@ config IIO_ST_GYRO_3AXIS select IIO_TRIGGERED_BUFFER if (IIO_BUFFER) help Say yes here to build support for STMicroelectronics gyroscopes: - L3G4200D, LSM330DL, L3GD20, L3GD20H, LSM330DLC, L3G4IS, LSM330. + L3G4200D, LSM330DL, L3GD20, LSM330DLC, L3G4IS, LSM330. This driver can also be built as a module. If so, these modules will be created: diff --git a/drivers/iio/gyro/st_gyro.h b/drivers/iio/gyro/st_gyro.h index f8f2bf84a5a2..c197360c450b 100644 --- a/drivers/iio/gyro/st_gyro.h +++ b/drivers/iio/gyro/st_gyro.h @@ -19,7 +19,6 @@ #define LSM330DL_GYRO_DEV_NAME "lsm330dl_gyro" #define LSM330DLC_GYRO_DEV_NAME "lsm330dlc_gyro" #define L3GD20_GYRO_DEV_NAME "l3gd20" -#define L3GD20H_GYRO_DEV_NAME "l3gd20h" #define L3G4IS_GYRO_DEV_NAME "l3g4is_ui" #define LSM330_GYRO_DEV_NAME "lsm330_gyro" diff --git a/drivers/iio/gyro/st_gyro_core.c b/drivers/iio/gyro/st_gyro_core.c index d53d91adfb55..a8e174a47bc4 100644 --- a/drivers/iio/gyro/st_gyro_core.c +++ b/drivers/iio/gyro/st_gyro_core.c @@ -167,11 +167,10 @@ static const struct st_sensors st_gyro_sensors[] = { .wai = ST_GYRO_2_WAI_EXP, .sensors_supported = { [0] = L3GD20_GYRO_DEV_NAME, - [1] = L3GD20H_GYRO_DEV_NAME, - [2] = LSM330D_GYRO_DEV_NAME, - [3] = LSM330DLC_GYRO_DEV_NAME, - [4] = L3G4IS_GYRO_DEV_NAME, - [5] = LSM330_GYRO_DEV_NAME, + [1] = LSM330D_GYRO_DEV_NAME, + [2] = LSM330DLC_GYRO_DEV_NAME, + [3] = L3G4IS_GYRO_DEV_NAME, + [4] = LSM330_GYRO_DEV_NAME, }, .ch = (struct iio_chan_spec *)st_gyro_16bit_channels, .odr = { diff --git a/drivers/iio/gyro/st_gyro_i2c.c b/drivers/iio/gyro/st_gyro_i2c.c index 16b8b8d70bf1..23c12f361b05 100644 --- a/drivers/iio/gyro/st_gyro_i2c.c +++ b/drivers/iio/gyro/st_gyro_i2c.c @@ -55,7 +55,6 @@ static const struct i2c_device_id st_gyro_id_table[] = { { LSM330DL_GYRO_DEV_NAME }, { LSM330DLC_GYRO_DEV_NAME }, { L3GD20_GYRO_DEV_NAME }, - { L3GD20H_GYRO_DEV_NAME }, { L3G4IS_GYRO_DEV_NAME }, { LSM330_GYRO_DEV_NAME }, {}, diff --git a/drivers/iio/gyro/st_gyro_spi.c b/drivers/iio/gyro/st_gyro_spi.c index 94763e25caf9..b4ad3be26687 100644 --- a/drivers/iio/gyro/st_gyro_spi.c +++ b/drivers/iio/gyro/st_gyro_spi.c @@ -54,7 +54,6 @@ static const struct spi_device_id st_gyro_id_table[] = { { LSM330DL_GYRO_DEV_NAME }, { LSM330DLC_GYRO_DEV_NAME }, { L3GD20_GYRO_DEV_NAME }, - { L3GD20H_GYRO_DEV_NAME }, { L3G4IS_GYRO_DEV_NAME }, { LSM330_GYRO_DEV_NAME }, {}, diff --git a/drivers/iio/imu/adis16400.h b/drivers/iio/imu/adis16400.h index 2f8f9d632386..0916bf6b6c31 100644 --- a/drivers/iio/imu/adis16400.h +++ b/drivers/iio/imu/adis16400.h @@ -189,6 +189,7 @@ enum { ADIS16300_SCAN_INCLI_X, ADIS16300_SCAN_INCLI_Y, ADIS16400_SCAN_ADC, + ADIS16400_SCAN_TIMESTAMP, }; #ifdef CONFIG_IIO_BUFFER diff --git a/drivers/iio/imu/adis16400_core.c b/drivers/iio/imu/adis16400_core.c index 368660dfe135..7c582f7ae34e 100644 --- a/drivers/iio/imu/adis16400_core.c +++ b/drivers/iio/imu/adis16400_core.c @@ -632,7 +632,7 @@ static const struct iio_chan_spec adis16400_channels[] = { ADIS16400_MAGN_CHAN(Z, ADIS16400_ZMAGN_OUT, 14), ADIS16400_TEMP_CHAN(ADIS16400_TEMP_OUT, 12), ADIS16400_AUX_ADC_CHAN(ADIS16400_AUX_ADC, 12), - IIO_CHAN_SOFT_TIMESTAMP(12) + IIO_CHAN_SOFT_TIMESTAMP(ADIS16400_SCAN_TIMESTAMP), }; static const struct iio_chan_spec adis16448_channels[] = { @@ -659,7 +659,7 @@ static const struct iio_chan_spec adis16448_channels[] = { }, }, ADIS16400_TEMP_CHAN(ADIS16448_TEMP_OUT, 12), - IIO_CHAN_SOFT_TIMESTAMP(11) + IIO_CHAN_SOFT_TIMESTAMP(ADIS16400_SCAN_TIMESTAMP), }; static const struct iio_chan_spec adis16350_channels[] = { @@ -677,7 +677,7 @@ static const struct iio_chan_spec adis16350_channels[] = { ADIS16400_MOD_TEMP_CHAN(X, ADIS16350_XTEMP_OUT, 12), ADIS16400_MOD_TEMP_CHAN(Y, ADIS16350_YTEMP_OUT, 12), ADIS16400_MOD_TEMP_CHAN(Z, ADIS16350_ZTEMP_OUT, 12), - IIO_CHAN_SOFT_TIMESTAMP(11) + IIO_CHAN_SOFT_TIMESTAMP(ADIS16400_SCAN_TIMESTAMP), }; static const struct iio_chan_spec adis16300_channels[] = { @@ -690,7 +690,7 @@ static const struct iio_chan_spec adis16300_channels[] = { ADIS16400_AUX_ADC_CHAN(ADIS16300_AUX_ADC, 12), ADIS16400_INCLI_CHAN(X, ADIS16300_PITCH_OUT, 13), ADIS16400_INCLI_CHAN(Y, ADIS16300_ROLL_OUT, 13), - IIO_CHAN_SOFT_TIMESTAMP(14) + IIO_CHAN_SOFT_TIMESTAMP(ADIS16400_SCAN_TIMESTAMP), }; static const struct iio_chan_spec adis16334_channels[] = { @@ -701,7 +701,7 @@ static const struct iio_chan_spec adis16334_channels[] = { ADIS16400_ACCEL_CHAN(Y, ADIS16400_YACCL_OUT, 14), ADIS16400_ACCEL_CHAN(Z, ADIS16400_ZACCL_OUT, 14), ADIS16400_TEMP_CHAN(ADIS16350_XTEMP_OUT, 12), - IIO_CHAN_SOFT_TIMESTAMP(8) + IIO_CHAN_SOFT_TIMESTAMP(ADIS16400_SCAN_TIMESTAMP), }; static struct attribute *adis16400_attributes[] = { diff --git a/drivers/iio/light/cm32181.c b/drivers/iio/light/cm32181.c index f17b4e6183c6..47a6dbac2d0c 100644 --- a/drivers/iio/light/cm32181.c +++ b/drivers/iio/light/cm32181.c @@ -103,13 +103,13 @@ static int cm32181_reg_init(struct cm32181_chip *cm32181) /** * cm32181_read_als_it() - Get sensor integration time (ms) * @cm32181: pointer of struct cm32181 - * @val: pointer of int to load the als_it value. + * @val2: pointer of int to load the als_it value. * * Report the current integartion time by millisecond. * - * Return: IIO_VAL_INT for success, otherwise -EINVAL. + * Return: IIO_VAL_INT_PLUS_MICRO for success, otherwise -EINVAL. */ -static int cm32181_read_als_it(struct cm32181_chip *cm32181, int *val) +static int cm32181_read_als_it(struct cm32181_chip *cm32181, int *val2) { u16 als_it; int i; @@ -119,8 +119,8 @@ static int cm32181_read_als_it(struct cm32181_chip *cm32181, int *val) als_it >>= CM32181_CMD_ALS_IT_SHIFT; for (i = 0; i < ARRAY_SIZE(als_it_bits); i++) { if (als_it == als_it_bits[i]) { - *val = als_it_value[i]; - return IIO_VAL_INT; + *val2 = als_it_value[i]; + return IIO_VAL_INT_PLUS_MICRO; } } @@ -221,7 +221,7 @@ static int cm32181_read_raw(struct iio_dev *indio_dev, *val = cm32181->calibscale; return IIO_VAL_INT; case IIO_CHAN_INFO_INT_TIME: - ret = cm32181_read_als_it(cm32181, val); + ret = cm32181_read_als_it(cm32181, val2); return ret; } @@ -240,7 +240,7 @@ static int cm32181_write_raw(struct iio_dev *indio_dev, cm32181->calibscale = val; return val; case IIO_CHAN_INFO_INT_TIME: - ret = cm32181_write_als_it(cm32181, val); + ret = cm32181_write_als_it(cm32181, val2); return ret; } @@ -264,7 +264,7 @@ static ssize_t cm32181_get_it_available(struct device *dev, n = ARRAY_SIZE(als_it_value); for (i = 0, len = 0; i < n; i++) - len += sprintf(buf + len, "%d ", als_it_value[i]); + len += sprintf(buf + len, "0.%06u ", als_it_value[i]); return len + sprintf(buf + len, "\n"); } diff --git a/drivers/iio/light/cm36651.c b/drivers/iio/light/cm36651.c index 0a142af83e25..a45e07492db3 100644 --- a/drivers/iio/light/cm36651.c +++ b/drivers/iio/light/cm36651.c @@ -50,10 +50,10 @@ #define CM36651_CS_CONF2_DEFAULT_BIT 0x08 /* CS_CONF3 channel integration time */ -#define CM36651_CS_IT1 0x00 /* Integration time 80000 usec */ -#define CM36651_CS_IT2 0x40 /* Integration time 160000 usec */ -#define CM36651_CS_IT3 0x80 /* Integration time 320000 usec */ -#define CM36651_CS_IT4 0xC0 /* Integration time 640000 usec */ +#define CM36651_CS_IT1 0x00 /* Integration time 80 msec */ +#define CM36651_CS_IT2 0x40 /* Integration time 160 msec */ +#define CM36651_CS_IT3 0x80 /* Integration time 320 msec */ +#define CM36651_CS_IT4 0xC0 /* Integration time 640 msec */ /* PS_CONF1 command code */ #define CM36651_PS_ENABLE 0x00 @@ -64,10 +64,10 @@ #define CM36651_PS_PERS4 0x0C /* PS_CONF1 command code: integration time */ -#define CM36651_PS_IT1 0x00 /* Integration time 320 usec */ -#define CM36651_PS_IT2 0x10 /* Integration time 420 usec */ -#define CM36651_PS_IT3 0x20 /* Integration time 520 usec */ -#define CM36651_PS_IT4 0x30 /* Integration time 640 usec */ +#define CM36651_PS_IT1 0x00 /* Integration time 0.32 msec */ +#define CM36651_PS_IT2 0x10 /* Integration time 0.42 msec */ +#define CM36651_PS_IT3 0x20 /* Integration time 0.52 msec */ +#define CM36651_PS_IT4 0x30 /* Integration time 0.64 msec */ /* PS_CONF1 command code: duty ratio */ #define CM36651_PS_DR1 0x00 /* Duty ratio 1/80 */ @@ -93,8 +93,8 @@ #define CM36651_CLOSE_PROXIMITY 0x32 #define CM36651_FAR_PROXIMITY 0x33 -#define CM36651_CS_INT_TIME_AVAIL "80000 160000 320000 640000" -#define CM36651_PS_INT_TIME_AVAIL "320 420 520 640" +#define CM36651_CS_INT_TIME_AVAIL "0.08 0.16 0.32 0.64" +#define CM36651_PS_INT_TIME_AVAIL "0.000320 0.000420 0.000520 0.000640" enum cm36651_operation_mode { CM36651_LIGHT_EN, @@ -356,30 +356,30 @@ static int cm36651_read_channel(struct cm36651_data *cm36651, } static int cm36651_read_int_time(struct cm36651_data *cm36651, - struct iio_chan_spec const *chan, int *val) + struct iio_chan_spec const *chan, int *val2) { switch (chan->type) { case IIO_LIGHT: if (cm36651->cs_int_time[chan->address] == CM36651_CS_IT1) - *val = 80000; + *val2 = 80000; else if (cm36651->cs_int_time[chan->address] == CM36651_CS_IT2) - *val = 160000; + *val2 = 160000; else if (cm36651->cs_int_time[chan->address] == CM36651_CS_IT3) - *val = 320000; + *val2 = 320000; else if (cm36651->cs_int_time[chan->address] == CM36651_CS_IT4) - *val = 640000; + *val2 = 640000; else return -EINVAL; break; case IIO_PROXIMITY: if (cm36651->ps_int_time == CM36651_PS_IT1) - *val = 320; + *val2 = 320; else if (cm36651->ps_int_time == CM36651_PS_IT2) - *val = 420; + *val2 = 420; else if (cm36651->ps_int_time == CM36651_PS_IT3) - *val = 520; + *val2 = 520; else if (cm36651->ps_int_time == CM36651_PS_IT4) - *val = 640; + *val2 = 640; else return -EINVAL; break; @@ -387,7 +387,7 @@ static int cm36651_read_int_time(struct cm36651_data *cm36651, return -EINVAL; } - return IIO_VAL_INT; + return IIO_VAL_INT_PLUS_MICRO; } static int cm36651_write_int_time(struct cm36651_data *cm36651, @@ -459,7 +459,8 @@ static int cm36651_read_raw(struct iio_dev *indio_dev, ret = cm36651_read_channel(cm36651, chan, val); break; case IIO_CHAN_INFO_INT_TIME: - ret = cm36651_read_int_time(cm36651, chan, val); + *val = 0; + ret = cm36651_read_int_time(cm36651, chan, val2); break; default: ret = -EINVAL; @@ -479,7 +480,7 @@ static int cm36651_write_raw(struct iio_dev *indio_dev, int ret = -EINVAL; if (mask == IIO_CHAN_INFO_INT_TIME) { - ret = cm36651_write_int_time(cm36651, chan, val); + ret = cm36651_write_int_time(cm36651, chan, val2); if (ret < 0) dev_err(&client->dev, "Integration time write failed\n"); } diff --git a/drivers/iio/light/tsl2563.c b/drivers/iio/light/tsl2563.c index 3d8110157f2d..94daa9fc1247 100644 --- a/drivers/iio/light/tsl2563.c +++ b/drivers/iio/light/tsl2563.c @@ -460,10 +460,14 @@ static int tsl2563_write_raw(struct iio_dev *indio_dev, { struct tsl2563_chip *chip = iio_priv(indio_dev); - if (chan->channel == IIO_MOD_LIGHT_BOTH) + if (mask != IIO_CHAN_INFO_CALIBSCALE) + return -EINVAL; + if (chan->channel2 == IIO_MOD_LIGHT_BOTH) chip->calib0 = calib_from_sysfs(val); - else + else if (chan->channel2 == IIO_MOD_LIGHT_IR) chip->calib1 = calib_from_sysfs(val); + else + return -EINVAL; return 0; } @@ -472,14 +476,14 @@ static int tsl2563_read_raw(struct iio_dev *indio_dev, struct iio_chan_spec const *chan, int *val, int *val2, - long m) + long mask) { int ret = -EINVAL; u32 calib0, calib1; struct tsl2563_chip *chip = iio_priv(indio_dev); mutex_lock(&chip->lock); - switch (m) { + switch (mask) { case IIO_CHAN_INFO_RAW: case IIO_CHAN_INFO_PROCESSED: switch (chan->type) { @@ -498,7 +502,7 @@ static int tsl2563_read_raw(struct iio_dev *indio_dev, ret = tsl2563_get_adc(chip); if (ret) goto error_ret; - if (chan->channel == 0) + if (chan->channel2 == IIO_MOD_LIGHT_BOTH) *val = chip->data0; else *val = chip->data1; @@ -510,7 +514,7 @@ static int tsl2563_read_raw(struct iio_dev *indio_dev, break; case IIO_CHAN_INFO_CALIBSCALE: - if (chan->channel == 0) + if (chan->channel2 == IIO_MOD_LIGHT_BOTH) *val = calib_to_sysfs(chip->calib0); else *val = calib_to_sysfs(chip->calib1); diff --git a/drivers/iio/magnetometer/ak8975.c b/drivers/iio/magnetometer/ak8975.c index ff284e5afd95..05423543f89d 100644 --- a/drivers/iio/magnetometer/ak8975.c +++ b/drivers/iio/magnetometer/ak8975.c @@ -85,6 +85,7 @@ #define AK8975_MAX_CONVERSION_TIMEOUT 500 #define AK8975_CONVERSION_DONE_POLL_TIME 10 #define AK8975_DATA_READY_TIMEOUT ((100*HZ)/1000) +#define RAW_TO_GAUSS(asa) ((((asa) + 128) * 3000) / 256) /* * Per-instance context data for the device. @@ -265,15 +266,15 @@ static int ak8975_setup(struct i2c_client *client) * * Since 1uT = 0.01 gauss, our final scale factor becomes: * - * Hadj = H * ((ASA + 128) / 256) * 3/10 * 100 - * Hadj = H * ((ASA + 128) * 30 / 256 + * Hadj = H * ((ASA + 128) / 256) * 3/10 * 1/100 + * Hadj = H * ((ASA + 128) * 0.003) / 256 * * Since ASA doesn't change, we cache the resultant scale factor into the * device context in ak8975_setup(). */ - data->raw_to_gauss[0] = ((data->asa[0] + 128) * 30) >> 8; - data->raw_to_gauss[1] = ((data->asa[1] + 128) * 30) >> 8; - data->raw_to_gauss[2] = ((data->asa[2] + 128) * 30) >> 8; + data->raw_to_gauss[0] = RAW_TO_GAUSS(data->asa[0]); + data->raw_to_gauss[1] = RAW_TO_GAUSS(data->asa[1]); + data->raw_to_gauss[2] = RAW_TO_GAUSS(data->asa[2]); return 0; } @@ -428,8 +429,9 @@ static int ak8975_read_raw(struct iio_dev *indio_dev, case IIO_CHAN_INFO_RAW: return ak8975_read_axis(indio_dev, chan->address, val); case IIO_CHAN_INFO_SCALE: - *val = data->raw_to_gauss[chan->address]; - return IIO_VAL_INT; + *val = 0; + *val2 = data->raw_to_gauss[chan->address]; + return IIO_VAL_INT_PLUS_MICRO; } return -EINVAL; } diff --git a/drivers/iio/magnetometer/mag3110.c b/drivers/iio/magnetometer/mag3110.c index 4b65b6d3bdb1..f66955fb3509 100644 --- a/drivers/iio/magnetometer/mag3110.c +++ b/drivers/iio/magnetometer/mag3110.c @@ -106,7 +106,7 @@ static ssize_t mag3110_show_int_plus_micros(char *buf, while (n-- > 0) len += scnprintf(buf + len, PAGE_SIZE - len, - "%d.%d ", vals[n][0], vals[n][1]); + "%d.%06d ", vals[n][0], vals[n][1]); /* replace trailing space by newline */ buf[len - 1] = '\n'; @@ -154,6 +154,9 @@ static int mag3110_read_raw(struct iio_dev *indio_dev, switch (mask) { case IIO_CHAN_INFO_RAW: + if (iio_buffer_enabled(indio_dev)) + return -EBUSY; + switch (chan->type) { case IIO_MAGN: /* in 0.1 uT / LSB */ ret = mag3110_read(data, buffer); @@ -199,6 +202,9 @@ static int mag3110_write_raw(struct iio_dev *indio_dev, struct mag3110_data *data = iio_priv(indio_dev); int rate; + if (iio_buffer_enabled(indio_dev)) + return -EBUSY; + switch (mask) { case IIO_CHAN_INFO_SAMP_FREQ: rate = mag3110_get_samp_freq_index(data, val, val2); diff --git a/drivers/infiniband/hw/amso1100/c2.c b/drivers/infiniband/hw/amso1100/c2.c index d53cf519f42a..00400c352c1a 100644 --- a/drivers/infiniband/hw/amso1100/c2.c +++ b/drivers/infiniband/hw/amso1100/c2.c @@ -1082,6 +1082,7 @@ static int c2_probe(struct pci_dev *pcidev, const struct pci_device_id *ent) /* Initialize network device */ if ((netdev = c2_devinit(c2dev, mmio_regs)) == NULL) { + ret = -ENOMEM; iounmap(mmio_regs); goto bail4; } @@ -1151,7 +1152,8 @@ static int c2_probe(struct pci_dev *pcidev, const struct pci_device_id *ent) goto bail10; } - if (c2_register_device(c2dev)) + ret = c2_register_device(c2dev); + if (ret) goto bail10; return 0; diff --git a/drivers/infiniband/hw/amso1100/c2_rnic.c b/drivers/infiniband/hw/amso1100/c2_rnic.c index b7c986990053..d2a6d961344b 100644 --- a/drivers/infiniband/hw/amso1100/c2_rnic.c +++ b/drivers/infiniband/hw/amso1100/c2_rnic.c @@ -576,7 +576,8 @@ int c2_rnic_init(struct c2_dev *c2dev) goto bail4; /* Initialize cached the adapter limits */ - if (c2_rnic_query(c2dev, &c2dev->props)) + err = c2_rnic_query(c2dev, &c2dev->props); + if (err) goto bail5; /* Initialize the PD pool */ diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c index 45126879ad28..d286bdebe2ab 100644 --- a/drivers/infiniband/hw/cxgb4/cm.c +++ b/drivers/infiniband/hw/cxgb4/cm.c @@ -3352,6 +3352,7 @@ static int rx_pkt(struct c4iw_dev *dev, struct sk_buff *skb) goto free_dst; } + neigh_release(neigh); step = dev->rdev.lldi.nrxq / dev->rdev.lldi.nchan; rss_qid = dev->rdev.lldi.rxq_ids[pi->port_id * step]; window = (__force u16) htons((__force u16)tcph->window); diff --git a/drivers/infiniband/hw/mlx4/cm.c b/drivers/infiniband/hw/mlx4/cm.c index d1f5f1dd77b0..56a593e0ae5d 100644 --- a/drivers/infiniband/hw/mlx4/cm.c +++ b/drivers/infiniband/hw/mlx4/cm.c @@ -61,6 +61,11 @@ struct cm_generic_msg { __be32 remote_comm_id; }; +struct cm_sidr_generic_msg { + struct ib_mad_hdr hdr; + __be32 request_id; +}; + struct cm_req_msg { unsigned char unused[0x60]; union ib_gid primary_path_sgid; @@ -69,28 +74,62 @@ struct cm_req_msg { static void set_local_comm_id(struct ib_mad *mad, u32 cm_id) { - struct cm_generic_msg *msg = (struct cm_generic_msg *)mad; - msg->local_comm_id = cpu_to_be32(cm_id); + if (mad->mad_hdr.attr_id == CM_SIDR_REQ_ATTR_ID) { + struct cm_sidr_generic_msg *msg = + (struct cm_sidr_generic_msg *)mad; + msg->request_id = cpu_to_be32(cm_id); + } else if (mad->mad_hdr.attr_id == CM_SIDR_REP_ATTR_ID) { + pr_err("trying to set local_comm_id in SIDR_REP\n"); + return; + } else { + struct cm_generic_msg *msg = (struct cm_generic_msg *)mad; + msg->local_comm_id = cpu_to_be32(cm_id); + } } static u32 get_local_comm_id(struct ib_mad *mad) { - struct cm_generic_msg *msg = (struct cm_generic_msg *)mad; - - return be32_to_cpu(msg->local_comm_id); + if (mad->mad_hdr.attr_id == CM_SIDR_REQ_ATTR_ID) { + struct cm_sidr_generic_msg *msg = + (struct cm_sidr_generic_msg *)mad; + return be32_to_cpu(msg->request_id); + } else if (mad->mad_hdr.attr_id == CM_SIDR_REP_ATTR_ID) { + pr_err("trying to set local_comm_id in SIDR_REP\n"); + return -1; + } else { + struct cm_generic_msg *msg = (struct cm_generic_msg *)mad; + return be32_to_cpu(msg->local_comm_id); + } } static void set_remote_comm_id(struct ib_mad *mad, u32 cm_id) { - struct cm_generic_msg *msg = (struct cm_generic_msg *)mad; - msg->remote_comm_id = cpu_to_be32(cm_id); + if (mad->mad_hdr.attr_id == CM_SIDR_REP_ATTR_ID) { + struct cm_sidr_generic_msg *msg = + (struct cm_sidr_generic_msg *)mad; + msg->request_id = cpu_to_be32(cm_id); + } else if (mad->mad_hdr.attr_id == CM_SIDR_REQ_ATTR_ID) { + pr_err("trying to set remote_comm_id in SIDR_REQ\n"); + return; + } else { + struct cm_generic_msg *msg = (struct cm_generic_msg *)mad; + msg->remote_comm_id = cpu_to_be32(cm_id); + } } static u32 get_remote_comm_id(struct ib_mad *mad) { - struct cm_generic_msg *msg = (struct cm_generic_msg *)mad; - - return be32_to_cpu(msg->remote_comm_id); + if (mad->mad_hdr.attr_id == CM_SIDR_REP_ATTR_ID) { + struct cm_sidr_generic_msg *msg = + (struct cm_sidr_generic_msg *)mad; + return be32_to_cpu(msg->request_id); + } else if (mad->mad_hdr.attr_id == CM_SIDR_REQ_ATTR_ID) { + pr_err("trying to set remote_comm_id in SIDR_REQ\n"); + return -1; + } else { + struct cm_generic_msg *msg = (struct cm_generic_msg *)mad; + return be32_to_cpu(msg->remote_comm_id); + } } static union ib_gid gid_from_req_msg(struct ib_device *ibdev, struct ib_mad *mad) @@ -282,19 +321,21 @@ int mlx4_ib_multiplex_cm_handler(struct ib_device *ibdev, int port, int slave_id u32 sl_cm_id; int pv_cm_id = -1; - sl_cm_id = get_local_comm_id(mad); - if (mad->mad_hdr.attr_id == CM_REQ_ATTR_ID || - mad->mad_hdr.attr_id == CM_REP_ATTR_ID) { + mad->mad_hdr.attr_id == CM_REP_ATTR_ID || + mad->mad_hdr.attr_id == CM_SIDR_REQ_ATTR_ID) { + sl_cm_id = get_local_comm_id(mad); id = id_map_alloc(ibdev, slave_id, sl_cm_id); if (IS_ERR(id)) { mlx4_ib_warn(ibdev, "%s: id{slave: %d, sl_cm_id: 0x%x} Failed to id_map_alloc\n", __func__, slave_id, sl_cm_id); return PTR_ERR(id); } - } else if (mad->mad_hdr.attr_id == CM_REJ_ATTR_ID) { + } else if (mad->mad_hdr.attr_id == CM_REJ_ATTR_ID || + mad->mad_hdr.attr_id == CM_SIDR_REP_ATTR_ID) { return 0; } else { + sl_cm_id = get_local_comm_id(mad); id = id_map_get(ibdev, &pv_cm_id, slave_id, sl_cm_id); } @@ -315,14 +356,18 @@ int mlx4_ib_multiplex_cm_handler(struct ib_device *ibdev, int port, int slave_id } int mlx4_ib_demux_cm_handler(struct ib_device *ibdev, int port, int *slave, - struct ib_mad *mad) + struct ib_mad *mad) { u32 pv_cm_id; struct id_map_entry *id; - if (mad->mad_hdr.attr_id == CM_REQ_ATTR_ID) { + if (mad->mad_hdr.attr_id == CM_REQ_ATTR_ID || + mad->mad_hdr.attr_id == CM_SIDR_REQ_ATTR_ID) { union ib_gid gid; + if (!slave) + return 0; + gid = gid_from_req_msg(ibdev, mad); *slave = mlx4_ib_find_real_gid(ibdev, port, gid.global.interface_id); if (*slave < 0) { @@ -341,7 +386,8 @@ int mlx4_ib_demux_cm_handler(struct ib_device *ibdev, int port, int *slave, return -ENOENT; } - *slave = id->slave_id; + if (slave) + *slave = id->slave_id; set_remote_comm_id(mad, id->sl_cm_id); if (mad->mad_hdr.attr_id == CM_DREQ_ATTR_ID) diff --git a/drivers/infiniband/hw/mlx4/cq.c b/drivers/infiniband/hw/mlx4/cq.c index cc40f08ca8f1..5f640814cc81 100644 --- a/drivers/infiniband/hw/mlx4/cq.c +++ b/drivers/infiniband/hw/mlx4/cq.c @@ -564,7 +564,7 @@ static int mlx4_ib_ipoib_csum_ok(__be16 status, __be16 checksum) } static int use_tunnel_data(struct mlx4_ib_qp *qp, struct mlx4_ib_cq *cq, struct ib_wc *wc, - unsigned tail, struct mlx4_cqe *cqe) + unsigned tail, struct mlx4_cqe *cqe, int is_eth) { struct mlx4_ib_proxy_sqp_hdr *hdr; @@ -574,12 +574,20 @@ static int use_tunnel_data(struct mlx4_ib_qp *qp, struct mlx4_ib_cq *cq, struct DMA_FROM_DEVICE); hdr = (struct mlx4_ib_proxy_sqp_hdr *) (qp->sqp_proxy_rcv[tail].addr); wc->pkey_index = be16_to_cpu(hdr->tun.pkey_index); - wc->slid = be16_to_cpu(hdr->tun.slid_mac_47_32); - wc->sl = (u8) (be16_to_cpu(hdr->tun.sl_vid) >> 12); wc->src_qp = be32_to_cpu(hdr->tun.flags_src_qp) & 0xFFFFFF; wc->wc_flags |= (hdr->tun.g_ml_path & 0x80) ? (IB_WC_GRH) : 0; wc->dlid_path_bits = 0; + if (is_eth) { + wc->vlan_id = be16_to_cpu(hdr->tun.sl_vid); + memcpy(&(wc->smac[0]), (char *)&hdr->tun.mac_31_0, 4); + memcpy(&(wc->smac[4]), (char *)&hdr->tun.slid_mac_47_32, 2); + wc->wc_flags |= (IB_WC_WITH_VLAN | IB_WC_WITH_SMAC); + } else { + wc->slid = be16_to_cpu(hdr->tun.slid_mac_47_32); + wc->sl = (u8) (be16_to_cpu(hdr->tun.sl_vid) >> 12); + } + return 0; } @@ -594,6 +602,7 @@ static int mlx4_ib_poll_one(struct mlx4_ib_cq *cq, struct mlx4_srq *msrq = NULL; int is_send; int is_error; + int is_eth; u32 g_mlpath_rqpn; u16 wqe_ctr; unsigned tail = 0; @@ -778,11 +787,15 @@ repoll: break; } + is_eth = (rdma_port_get_link_layer(wc->qp->device, + (*cur_qp)->port) == + IB_LINK_LAYER_ETHERNET); if (mlx4_is_mfunc(to_mdev(cq->ibcq.device)->dev)) { if ((*cur_qp)->mlx4_ib_qp_type & (MLX4_IB_QPT_PROXY_SMI_OWNER | MLX4_IB_QPT_PROXY_SMI | MLX4_IB_QPT_PROXY_GSI)) - return use_tunnel_data(*cur_qp, cq, wc, tail, cqe); + return use_tunnel_data(*cur_qp, cq, wc, tail, + cqe, is_eth); } wc->slid = be16_to_cpu(cqe->rlid); @@ -793,20 +806,21 @@ repoll: wc->pkey_index = be32_to_cpu(cqe->immed_rss_invalid) & 0x7f; wc->wc_flags |= mlx4_ib_ipoib_csum_ok(cqe->status, cqe->checksum) ? IB_WC_IP_CSUM_OK : 0; - if (rdma_port_get_link_layer(wc->qp->device, - (*cur_qp)->port) == IB_LINK_LAYER_ETHERNET) + if (is_eth) { wc->sl = be16_to_cpu(cqe->sl_vid) >> 13; - else - wc->sl = be16_to_cpu(cqe->sl_vid) >> 12; - if (be32_to_cpu(cqe->vlan_my_qpn) & MLX4_CQE_VLAN_PRESENT_MASK) { - wc->vlan_id = be16_to_cpu(cqe->sl_vid) & - MLX4_CQE_VID_MASK; + if (be32_to_cpu(cqe->vlan_my_qpn) & + MLX4_CQE_VLAN_PRESENT_MASK) { + wc->vlan_id = be16_to_cpu(cqe->sl_vid) & + MLX4_CQE_VID_MASK; + } else { + wc->vlan_id = 0xffff; + } + memcpy(wc->smac, cqe->smac, ETH_ALEN); + wc->wc_flags |= (IB_WC_WITH_VLAN | IB_WC_WITH_SMAC); } else { + wc->sl = be16_to_cpu(cqe->sl_vid) >> 12; wc->vlan_id = 0xffff; } - wc->wc_flags |= IB_WC_WITH_VLAN; - memcpy(wc->smac, cqe->smac, ETH_ALEN); - wc->wc_flags |= IB_WC_WITH_SMAC; } return 0; diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c index f2a3f48107e7..2c572aed3f6f 100644 --- a/drivers/infiniband/hw/mlx4/mad.c +++ b/drivers/infiniband/hw/mlx4/mad.c @@ -467,6 +467,7 @@ int mlx4_ib_send_to_slave(struct mlx4_ib_dev *dev, int slave, u8 port, int ret = 0; u16 tun_pkey_ix; u16 cached_pkey; + u8 is_eth = dev->dev->caps.port_type[port] == MLX4_PORT_TYPE_ETH; if (dest_qpt > IB_QPT_GSI) return -EINVAL; @@ -509,6 +510,10 @@ int mlx4_ib_send_to_slave(struct mlx4_ib_dev *dev, int slave, u8 port, * The driver will set the force loopback bit in post_send */ memset(&attr, 0, sizeof attr); attr.port_num = port; + if (is_eth) { + memcpy(&attr.grh.dgid.raw[0], &grh->dgid.raw[0], 16); + attr.ah_flags = IB_AH_GRH; + } ah = ib_create_ah(tun_ctx->pd, &attr); if (IS_ERR(ah)) return -ENOMEM; @@ -540,11 +545,36 @@ int mlx4_ib_send_to_slave(struct mlx4_ib_dev *dev, int slave, u8 port, /* adjust tunnel data */ tun_mad->hdr.pkey_index = cpu_to_be16(tun_pkey_ix); - tun_mad->hdr.sl_vid = cpu_to_be16(((u16)(wc->sl)) << 12); - tun_mad->hdr.slid_mac_47_32 = cpu_to_be16(wc->slid); tun_mad->hdr.flags_src_qp = cpu_to_be32(wc->src_qp & 0xFFFFFF); tun_mad->hdr.g_ml_path = (grh && (wc->wc_flags & IB_WC_GRH)) ? 0x80 : 0; + if (is_eth) { + u16 vlan = 0; + if (mlx4_get_slave_default_vlan(dev->dev, port, slave, &vlan, + NULL)) { + /* VST mode */ + if (vlan != wc->vlan_id) + /* Packet vlan is not the VST-assigned vlan. + * Drop the packet. + */ + goto out; + else + /* Remove the vlan tag before forwarding + * the packet to the VF. + */ + vlan = 0xffff; + } else { + vlan = wc->vlan_id; + } + + tun_mad->hdr.sl_vid = cpu_to_be16(vlan); + memcpy((char *)&tun_mad->hdr.mac_31_0, &(wc->smac[0]), 4); + memcpy((char *)&tun_mad->hdr.slid_mac_47_32, &(wc->smac[4]), 2); + } else { + tun_mad->hdr.sl_vid = cpu_to_be16(((u16)(wc->sl)) << 12); + tun_mad->hdr.slid_mac_47_32 = cpu_to_be16(wc->slid); + } + ib_dma_sync_single_for_device(&dev->ib_dev, tun_qp->tx_ring[tun_tx_ix].buf.map, sizeof (struct mlx4_rcv_tunnel_mad), @@ -580,6 +610,41 @@ static int mlx4_ib_demux_mad(struct ib_device *ibdev, u8 port, int err; int slave; u8 *slave_id; + int is_eth = 0; + + if (rdma_port_get_link_layer(ibdev, port) == IB_LINK_LAYER_INFINIBAND) + is_eth = 0; + else + is_eth = 1; + + if (is_eth) { + if (!(wc->wc_flags & IB_WC_GRH)) { + mlx4_ib_warn(ibdev, "RoCE grh not present.\n"); + return -EINVAL; + } + if (mad->mad_hdr.mgmt_class != IB_MGMT_CLASS_CM) { + mlx4_ib_warn(ibdev, "RoCE mgmt class is not CM\n"); + return -EINVAL; + } + if (mlx4_get_slave_from_roce_gid(dev->dev, port, grh->dgid.raw, &slave)) { + mlx4_ib_warn(ibdev, "failed matching grh\n"); + return -ENOENT; + } + if (slave >= dev->dev->caps.sqp_demux) { + mlx4_ib_warn(ibdev, "slave id: %d is bigger than allowed:%d\n", + slave, dev->dev->caps.sqp_demux); + return -ENOENT; + } + + if (mlx4_ib_demux_cm_handler(ibdev, port, NULL, mad)) + return 0; + + err = mlx4_ib_send_to_slave(dev, slave, port, wc->qp->qp_type, wc, grh, mad); + if (err) + pr_debug("failed sending to slave %d via tunnel qp (%d)\n", + slave, err); + return 0; + } /* Initially assume that this mad is for us */ slave = mlx4_master_func_num(dev->dev); @@ -1076,8 +1141,9 @@ static int is_proxy_qp0(struct mlx4_ib_dev *dev, int qpn, int slave) int mlx4_ib_send_to_wire(struct mlx4_ib_dev *dev, int slave, u8 port, - enum ib_qp_type dest_qpt, u16 pkey_index, u32 remote_qpn, - u32 qkey, struct ib_ah_attr *attr, struct ib_mad *mad) + enum ib_qp_type dest_qpt, u16 pkey_index, + u32 remote_qpn, u32 qkey, struct ib_ah_attr *attr, + u8 *s_mac, struct ib_mad *mad) { struct ib_sge list; struct ib_send_wr wr, *bad_wr; @@ -1166,6 +1232,9 @@ int mlx4_ib_send_to_wire(struct mlx4_ib_dev *dev, int slave, u8 port, wr.num_sge = 1; wr.opcode = IB_WR_SEND; wr.send_flags = IB_SEND_SIGNALED; + if (s_mac) + memcpy(to_mah(ah)->av.eth.s_mac, s_mac, 6); + ret = ib_post_send(send_qp, &wr, &bad_wr); out: @@ -1174,6 +1243,34 @@ out: return ret; } +static int get_slave_base_gid_ix(struct mlx4_ib_dev *dev, int slave, int port) +{ + int gids; + int vfs; + + if (rdma_port_get_link_layer(&dev->ib_dev, port) == IB_LINK_LAYER_INFINIBAND) + return slave; + + gids = MLX4_ROCE_MAX_GIDS - MLX4_ROCE_PF_GIDS; + vfs = dev->dev->num_vfs; + + if (slave == 0) + return 0; + if (slave <= gids % vfs) + return MLX4_ROCE_PF_GIDS + ((gids / vfs) + 1) * (slave - 1); + + return MLX4_ROCE_PF_GIDS + (gids % vfs) + ((gids / vfs) * (slave - 1)); +} + +static void fill_in_real_sgid_index(struct mlx4_ib_dev *dev, int slave, int port, + struct ib_ah_attr *ah_attr) +{ + if (rdma_port_get_link_layer(&dev->ib_dev, port) == IB_LINK_LAYER_INFINIBAND) + ah_attr->grh.sgid_index = slave; + else + ah_attr->grh.sgid_index += get_slave_base_gid_ix(dev, slave, port); +} + static void mlx4_ib_multiplex_mad(struct mlx4_ib_demux_pv_ctx *ctx, struct ib_wc *wc) { struct mlx4_ib_dev *dev = to_mdev(ctx->ib_dev); @@ -1260,12 +1357,14 @@ static void mlx4_ib_multiplex_mad(struct mlx4_ib_demux_pv_ctx *ctx, struct ib_wc memcpy(&ah.av, &tunnel->hdr.av, sizeof (struct mlx4_av)); ah.ibah.device = ctx->ib_dev; mlx4_ib_query_ah(&ah.ibah, &ah_attr); - if ((ah_attr.ah_flags & IB_AH_GRH) && - (ah_attr.grh.sgid_index != slave)) { - mlx4_ib_warn(ctx->ib_dev, "slave:%d accessed invalid sgid_index:%d\n", - slave, ah_attr.grh.sgid_index); - return; - } + if (ah_attr.ah_flags & IB_AH_GRH) + fill_in_real_sgid_index(dev, slave, ctx->port, &ah_attr); + + memcpy(ah_attr.dmac, tunnel->hdr.mac, 6); + ah_attr.vlan_id = be16_to_cpu(tunnel->hdr.vlan); + /* if slave have default vlan use it */ + mlx4_get_slave_default_vlan(dev->dev, ctx->port, slave, + &ah_attr.vlan_id, &ah_attr.sl); mlx4_ib_send_to_wire(dev, slave, ctx->port, is_proxy_qp0(dev, wc->src_qp, slave) ? @@ -1273,7 +1372,7 @@ static void mlx4_ib_multiplex_mad(struct mlx4_ib_demux_pv_ctx *ctx, struct ib_wc be16_to_cpu(tunnel->hdr.pkey_index), be32_to_cpu(tunnel->hdr.remote_qpn), be32_to_cpu(tunnel->hdr.qkey), - &ah_attr, &tunnel->mad); + &ah_attr, wc->smac, &tunnel->mad); } static int mlx4_ib_alloc_pv_bufs(struct mlx4_ib_demux_pv_ctx *ctx, diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index c2702f549f10..1d1750ef000a 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -53,8 +53,8 @@ #include "user.h" #define DRV_NAME MLX4_IB_DRV_NAME -#define DRV_VERSION "1.0" -#define DRV_RELDATE "April 4, 2008" +#define DRV_VERSION "2.2-1" +#define DRV_RELDATE "Feb 2014" #define MLX4_IB_FLOW_MAX_PRIO 0xFFF #define MLX4_IB_FLOW_QPN_MASK 0xFFFFFF @@ -347,7 +347,7 @@ static int eth_link_query_port(struct ib_device *ibdev, u8 port, props->active_width = (((u8 *)mailbox->buf)[5] == 0x40) ? IB_WIDTH_4X : IB_WIDTH_1X; props->active_speed = IB_SPEED_QDR; - props->port_cap_flags = IB_PORT_CM_SUP; + props->port_cap_flags = IB_PORT_CM_SUP | IB_PORT_IP_BASED_GIDS; props->gid_tbl_len = mdev->dev->caps.gid_table_len[port]; props->max_msg_sz = mdev->dev->caps.max_msg_sz; props->pkey_tbl_len = 1; @@ -1357,6 +1357,21 @@ static struct device_attribute *mlx4_class_attributes[] = { &dev_attr_board_id }; +static void mlx4_addrconf_ifid_eui48(u8 *eui, u16 vlan_id, + struct net_device *dev) +{ + memcpy(eui, dev->dev_addr, 3); + memcpy(eui + 5, dev->dev_addr + 3, 3); + if (vlan_id < 0x1000) { + eui[3] = vlan_id >> 8; + eui[4] = vlan_id & 0xff; + } else { + eui[3] = 0xff; + eui[4] = 0xfe; + } + eui[0] ^= 2; +} + static void update_gids_task(struct work_struct *work) { struct update_gid_work *gw = container_of(work, struct update_gid_work, work); @@ -1393,7 +1408,6 @@ static void reset_gids_task(struct work_struct *work) struct mlx4_cmd_mailbox *mailbox; union ib_gid *gids; int err; - int i; struct mlx4_dev *dev = gw->dev->dev; mailbox = mlx4_alloc_cmd_mailbox(dev); @@ -1405,18 +1419,16 @@ static void reset_gids_task(struct work_struct *work) gids = mailbox->buf; memcpy(gids, gw->gids, sizeof(gw->gids)); - for (i = 1; i < gw->dev->num_ports + 1; i++) { - if (mlx4_ib_port_link_layer(&gw->dev->ib_dev, i) == - IB_LINK_LAYER_ETHERNET) { - err = mlx4_cmd(dev, mailbox->dma, - MLX4_SET_PORT_GID_TABLE << 8 | i, - 1, MLX4_CMD_SET_PORT, - MLX4_CMD_TIME_CLASS_B, - MLX4_CMD_WRAPPED); - if (err) - pr_warn(KERN_WARNING - "set port %d command failed\n", i); - } + if (mlx4_ib_port_link_layer(&gw->dev->ib_dev, gw->port) == + IB_LINK_LAYER_ETHERNET) { + err = mlx4_cmd(dev, mailbox->dma, + MLX4_SET_PORT_GID_TABLE << 8 | gw->port, + 1, MLX4_CMD_SET_PORT, + MLX4_CMD_TIME_CLASS_B, + MLX4_CMD_WRAPPED); + if (err) + pr_warn(KERN_WARNING + "set port %d command failed\n", gw->port); } mlx4_free_cmd_mailbox(dev, mailbox); @@ -1425,7 +1437,8 @@ free: } static int update_gid_table(struct mlx4_ib_dev *dev, int port, - union ib_gid *gid, int clear) + union ib_gid *gid, int clear, + int default_gid) { struct update_gid_work *work; int i; @@ -1434,26 +1447,31 @@ static int update_gid_table(struct mlx4_ib_dev *dev, int port, int found = -1; int max_gids; - max_gids = dev->dev->caps.gid_table_len[port]; - for (i = 0; i < max_gids; ++i) { - if (!memcmp(&dev->iboe.gid_table[port - 1][i], gid, - sizeof(*gid))) - found = i; - - if (clear) { - if (found >= 0) { - need_update = 1; - dev->iboe.gid_table[port - 1][found] = zgid; - break; - } - } else { - if (found >= 0) - break; - - if (free < 0 && - !memcmp(&dev->iboe.gid_table[port - 1][i], &zgid, + if (default_gid) { + free = 0; + } else { + max_gids = dev->dev->caps.gid_table_len[port]; + for (i = 1; i < max_gids; ++i) { + if (!memcmp(&dev->iboe.gid_table[port - 1][i], gid, sizeof(*gid))) - free = i; + found = i; + + if (clear) { + if (found >= 0) { + need_update = 1; + dev->iboe.gid_table[port - 1][found] = + zgid; + break; + } + } else { + if (found >= 0) + break; + + if (free < 0 && + !memcmp(&dev->iboe.gid_table[port - 1][i], + &zgid, sizeof(*gid))) + free = i; + } } } @@ -1478,18 +1496,26 @@ static int update_gid_table(struct mlx4_ib_dev *dev, int port, return 0; } -static int reset_gid_table(struct mlx4_ib_dev *dev) +static void mlx4_make_default_gid(struct net_device *dev, union ib_gid *gid) { - struct update_gid_work *work; + gid->global.subnet_prefix = cpu_to_be64(0xfe80000000000000LL); + mlx4_addrconf_ifid_eui48(&gid->raw[8], 0xffff, dev); +} + +static int reset_gid_table(struct mlx4_ib_dev *dev, u8 port) +{ + struct update_gid_work *work; work = kzalloc(sizeof(*work), GFP_ATOMIC); if (!work) return -ENOMEM; - memset(dev->iboe.gid_table, 0, sizeof(dev->iboe.gid_table)); + + memset(dev->iboe.gid_table[port - 1], 0, sizeof(work->gids)); memset(work->gids, 0, sizeof(work->gids)); INIT_WORK(&work->work, reset_gids_task); work->dev = dev; + work->port = port; queue_work(wq, &work->work); return 0; } @@ -1502,6 +1528,12 @@ static int mlx4_ib_addr_event(int event, struct net_device *event_netdev, struct net_device *real_dev = rdma_vlan_dev_real_dev(event_netdev) ? rdma_vlan_dev_real_dev(event_netdev) : event_netdev; + union ib_gid default_gid; + + mlx4_make_default_gid(real_dev, &default_gid); + + if (!memcmp(gid, &default_gid, sizeof(*gid))) + return 0; if (event != NETDEV_DOWN && event != NETDEV_UP) return 0; @@ -1520,7 +1552,7 @@ static int mlx4_ib_addr_event(int event, struct net_device *event_netdev, (!netif_is_bond_master(real_dev) && (real_dev == iboe->netdevs[port - 1]))) update_gid_table(ibdev, port, gid, - event == NETDEV_DOWN); + event == NETDEV_DOWN, 0); spin_unlock(&iboe->lock); return 0; @@ -1536,7 +1568,6 @@ static u8 mlx4_ib_get_dev_port(struct net_device *dev, rdma_vlan_dev_real_dev(dev) : dev; iboe = &ibdev->iboe; - spin_lock(&iboe->lock); for (port = 1; port <= MLX4_MAX_PORTS; ++port) if ((netif_is_bond_master(real_dev) && @@ -1545,8 +1576,6 @@ static u8 mlx4_ib_get_dev_port(struct net_device *dev, (real_dev == iboe->netdevs[port - 1]))) break; - spin_unlock(&iboe->lock); - if ((port == 0) || (port > MLX4_MAX_PORTS)) return 0; else @@ -1607,7 +1636,7 @@ static void mlx4_ib_get_dev_addr(struct net_device *dev, /*ifa->ifa_address;*/ ipv6_addr_set_v4mapped(ifa->ifa_address, (struct in6_addr *)&gid); - update_gid_table(ibdev, port, &gid, 0); + update_gid_table(ibdev, port, &gid, 0, 0); } endfor_ifa(in_dev); in_dev_put(in_dev); @@ -1619,7 +1648,7 @@ static void mlx4_ib_get_dev_addr(struct net_device *dev, read_lock_bh(&in6_dev->lock); list_for_each_entry(ifp, &in6_dev->addr_list, if_list) { pgid = (union ib_gid *)&ifp->addr; - update_gid_table(ibdev, port, pgid, 0); + update_gid_table(ibdev, port, pgid, 0, 0); } read_unlock_bh(&in6_dev->lock); in6_dev_put(in6_dev); @@ -1627,14 +1656,26 @@ static void mlx4_ib_get_dev_addr(struct net_device *dev, #endif } +static void mlx4_ib_set_default_gid(struct mlx4_ib_dev *ibdev, + struct net_device *dev, u8 port) +{ + union ib_gid gid; + mlx4_make_default_gid(dev, &gid); + update_gid_table(ibdev, port, &gid, 0, 1); +} + static int mlx4_ib_init_gid_table(struct mlx4_ib_dev *ibdev) { struct net_device *dev; + struct mlx4_ib_iboe *iboe = &ibdev->iboe; + int i; - if (reset_gid_table(ibdev)) - return -1; + for (i = 1; i <= ibdev->num_ports; ++i) + if (reset_gid_table(ibdev, i)) + return -1; read_lock(&dev_base_lock); + spin_lock(&iboe->lock); for_each_netdev(&init_net, dev) { u8 port = mlx4_ib_get_dev_port(dev, ibdev); @@ -1642,6 +1683,7 @@ static int mlx4_ib_init_gid_table(struct mlx4_ib_dev *ibdev) mlx4_ib_get_dev_addr(dev, ibdev, port); } + spin_unlock(&iboe->lock); read_unlock(&dev_base_lock); return 0; @@ -1656,25 +1698,57 @@ static void mlx4_ib_scan_netdevs(struct mlx4_ib_dev *ibdev) spin_lock(&iboe->lock); mlx4_foreach_ib_transport_port(port, ibdev->dev) { + enum ib_port_state port_state = IB_PORT_NOP; struct net_device *old_master = iboe->masters[port - 1]; + struct net_device *curr_netdev; struct net_device *curr_master; + iboe->netdevs[port - 1] = mlx4_get_protocol_dev(ibdev->dev, MLX4_PROT_ETH, port); + if (iboe->netdevs[port - 1]) + mlx4_ib_set_default_gid(ibdev, + iboe->netdevs[port - 1], port); + curr_netdev = iboe->netdevs[port - 1]; if (iboe->netdevs[port - 1] && netif_is_bond_slave(iboe->netdevs[port - 1])) { - rtnl_lock(); iboe->masters[port - 1] = netdev_master_upper_dev_get( iboe->netdevs[port - 1]); - rtnl_unlock(); + } else { + iboe->masters[port - 1] = NULL; } curr_master = iboe->masters[port - 1]; + if (curr_netdev) { + port_state = (netif_running(curr_netdev) && netif_carrier_ok(curr_netdev)) ? + IB_PORT_ACTIVE : IB_PORT_DOWN; + mlx4_ib_set_default_gid(ibdev, curr_netdev, port); + } else { + reset_gid_table(ibdev, port); + } + /* if using bonding/team and a slave port is down, we don't the bond IP + * based gids in the table since flows that select port by gid may get + * the down port. + */ + if (curr_master && (port_state == IB_PORT_DOWN)) { + reset_gid_table(ibdev, port); + mlx4_ib_set_default_gid(ibdev, curr_netdev, port); + } /* if bonding is used it is possible that we add it to masters - only after IP address is assigned to the net bonding - interface */ - if (curr_master && (old_master != curr_master)) + * only after IP address is assigned to the net bonding + * interface. + */ + if (curr_master && (old_master != curr_master)) { + reset_gid_table(ibdev, port); + mlx4_ib_set_default_gid(ibdev, curr_netdev, port); mlx4_ib_get_dev_addr(curr_master, ibdev, port); + } + + if (!curr_master && (old_master != curr_master)) { + reset_gid_table(ibdev, port); + mlx4_ib_set_default_gid(ibdev, curr_netdev, port); + mlx4_ib_get_dev_addr(curr_netdev, ibdev, port); + } } spin_unlock(&iboe->lock); @@ -1810,17 +1884,10 @@ static void *mlx4_ib_add(struct mlx4_dev *dev) int i, j; int err; struct mlx4_ib_iboe *iboe; + int ib_num_ports = 0; pr_info_once("%s", mlx4_ib_version); - mlx4_foreach_non_ib_transport_port(i, dev) - num_ports++; - - if (mlx4_is_mfunc(dev) && num_ports) { - dev_err(&dev->pdev->dev, "RoCE is not supported over SRIOV as yet\n"); - return NULL; - } - num_ports = 0; mlx4_foreach_ib_transport_port(i, dev) num_ports++; @@ -1985,10 +2052,14 @@ static void *mlx4_ib_add(struct mlx4_dev *dev) ibdev->counters[i] = -1; } + mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_IB) + ib_num_ports++; + spin_lock_init(&ibdev->sm_lock); mutex_init(&ibdev->cap_mask_mutex); - if (ibdev->steering_support == MLX4_STEERING_MODE_DEVICE_MANAGED) { + if (ibdev->steering_support == MLX4_STEERING_MODE_DEVICE_MANAGED && + ib_num_ports) { ibdev->steer_qpn_count = MLX4_IB_UC_MAX_NUM_QPS; err = mlx4_qp_reserve_range(dev, ibdev->steer_qpn_count, MLX4_IB_UC_STEER_QPN_ALIGN, @@ -2051,7 +2122,11 @@ static void *mlx4_ib_add(struct mlx4_dev *dev) } } #endif + for (i = 1 ; i <= ibdev->num_ports ; ++i) + reset_gid_table(ibdev, i); + rtnl_lock(); mlx4_ib_scan_netdevs(ibdev); + rtnl_unlock(); mlx4_ib_init_gid_table(ibdev); } diff --git a/drivers/infiniband/hw/mlx4/mcg.c b/drivers/infiniband/hw/mlx4/mcg.c index 25b2cdff00f8..ed327e6c8fdc 100644 --- a/drivers/infiniband/hw/mlx4/mcg.c +++ b/drivers/infiniband/hw/mlx4/mcg.c @@ -215,8 +215,9 @@ static int send_mad_to_wire(struct mlx4_ib_demux_ctx *ctx, struct ib_mad *mad) } mlx4_ib_query_ah(dev->sm_ah[ctx->port - 1], &ah_attr); spin_unlock(&dev->sm_lock); - return mlx4_ib_send_to_wire(dev, mlx4_master_func_num(dev->dev), ctx->port, - IB_QPT_GSI, 0, 1, IB_QP1_QKEY, &ah_attr, mad); + return mlx4_ib_send_to_wire(dev, mlx4_master_func_num(dev->dev), + ctx->port, IB_QPT_GSI, 0, 1, IB_QP1_QKEY, + &ah_attr, NULL, mad); } static int send_mad_to_slave(int slave, struct mlx4_ib_demux_ctx *ctx, diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h index a230683af940..f589522fddfd 100644 --- a/drivers/infiniband/hw/mlx4/mlx4_ib.h +++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h @@ -241,6 +241,22 @@ struct mlx4_ib_proxy_sqp_hdr { struct mlx4_rcv_tunnel_hdr tun; } __packed; +struct mlx4_roce_smac_vlan_info { + u64 smac; + int smac_index; + int smac_port; + u64 candidate_smac; + int candidate_smac_index; + int candidate_smac_port; + u16 vid; + int vlan_index; + int vlan_port; + u16 candidate_vid; + int candidate_vlan_index; + int candidate_vlan_port; + int update_vid; +}; + struct mlx4_ib_qp { struct ib_qp ibqp; struct mlx4_qp mqp; @@ -273,8 +289,9 @@ struct mlx4_ib_qp { struct list_head gid_list; struct list_head steering_rules; struct mlx4_ib_buf *sqp_proxy_rcv; + struct mlx4_roce_smac_vlan_info pri; + struct mlx4_roce_smac_vlan_info alt; u64 reg_id; - }; struct mlx4_ib_srq { @@ -720,9 +737,12 @@ void mlx4_ib_tunnels_update_work(struct work_struct *work); int mlx4_ib_send_to_slave(struct mlx4_ib_dev *dev, int slave, u8 port, enum ib_qp_type qpt, struct ib_wc *wc, struct ib_grh *grh, struct ib_mad *mad); + int mlx4_ib_send_to_wire(struct mlx4_ib_dev *dev, int slave, u8 port, enum ib_qp_type dest_qpt, u16 pkey_index, u32 remote_qpn, - u32 qkey, struct ib_ah_attr *attr, struct ib_mad *mad); + u32 qkey, struct ib_ah_attr *attr, u8 *s_mac, + struct ib_mad *mad); + __be64 mlx4_ib_get_new_demux_tid(struct mlx4_ib_demux_ctx *ctx); int mlx4_ib_demux_cm_handler(struct ib_device *ibdev, int port, int *slave, diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c index d8f4d1fe8494..aadf7f82e1f3 100644 --- a/drivers/infiniband/hw/mlx4/qp.c +++ b/drivers/infiniband/hw/mlx4/qp.c @@ -662,10 +662,14 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd, if (!sqp) return -ENOMEM; qp = &sqp->qp; + qp->pri.vid = 0xFFFF; + qp->alt.vid = 0xFFFF; } else { qp = kzalloc(sizeof (struct mlx4_ib_qp), GFP_KERNEL); if (!qp) return -ENOMEM; + qp->pri.vid = 0xFFFF; + qp->alt.vid = 0xFFFF; } } else qp = *caller_qp; @@ -940,11 +944,32 @@ static void destroy_qp_common(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp, { struct mlx4_ib_cq *send_cq, *recv_cq; - if (qp->state != IB_QPS_RESET) + if (qp->state != IB_QPS_RESET) { if (mlx4_qp_modify(dev->dev, NULL, to_mlx4_state(qp->state), MLX4_QP_STATE_RST, NULL, 0, 0, &qp->mqp)) pr_warn("modify QP %06x to RESET failed.\n", qp->mqp.qpn); + if (qp->pri.smac) { + mlx4_unregister_mac(dev->dev, qp->pri.smac_port, qp->pri.smac); + qp->pri.smac = 0; + } + if (qp->alt.smac) { + mlx4_unregister_mac(dev->dev, qp->alt.smac_port, qp->alt.smac); + qp->alt.smac = 0; + } + if (qp->pri.vid < 0x1000) { + mlx4_unregister_vlan(dev->dev, qp->pri.vlan_port, qp->pri.vid); + qp->pri.vid = 0xFFFF; + qp->pri.candidate_vid = 0xFFFF; + qp->pri.update_vid = 0; + } + if (qp->alt.vid < 0x1000) { + mlx4_unregister_vlan(dev->dev, qp->alt.vlan_port, qp->alt.vid); + qp->alt.vid = 0xFFFF; + qp->alt.candidate_vid = 0xFFFF; + qp->alt.update_vid = 0; + } + } get_cqs(qp, &send_cq, &recv_cq); @@ -1057,6 +1082,8 @@ struct ib_qp *mlx4_ib_create_qp(struct ib_pd *pd, qp = kzalloc(sizeof *qp, GFP_KERNEL); if (!qp) return ERR_PTR(-ENOMEM); + qp->pri.vid = 0xFFFF; + qp->alt.vid = 0xFFFF; /* fall through */ case IB_QPT_UD: { @@ -1188,12 +1215,13 @@ static void mlx4_set_sched(struct mlx4_qp_path *path, u8 port) static int _mlx4_set_path(struct mlx4_ib_dev *dev, const struct ib_ah_attr *ah, u64 smac, u16 vlan_tag, struct mlx4_qp_path *path, - u8 port) + struct mlx4_roce_smac_vlan_info *smac_info, u8 port) { int is_eth = rdma_port_get_link_layer(&dev->ib_dev, port) == IB_LINK_LAYER_ETHERNET; int vidx; int smac_index; + int err; path->grh_mylmc = ah->src_path_bits & 0x7f; @@ -1223,61 +1251,103 @@ static int _mlx4_set_path(struct mlx4_ib_dev *dev, const struct ib_ah_attr *ah, } if (is_eth) { - path->sched_queue = MLX4_IB_DEFAULT_SCHED_QUEUE | - ((port - 1) << 6) | ((ah->sl & 7) << 3); - if (!(ah->ah_flags & IB_AH_GRH)) return -1; - memcpy(path->dmac, ah->dmac, ETH_ALEN); - path->ackto = MLX4_IB_LINK_TYPE_ETH; - /* find the index into MAC table for IBoE */ - if (!is_zero_ether_addr((const u8 *)&smac)) { - if (mlx4_find_cached_mac(dev->dev, port, smac, - &smac_index)) - return -ENOENT; - } else { - smac_index = 0; - } - - path->grh_mylmc &= 0x80 | smac_index; + path->sched_queue = MLX4_IB_DEFAULT_SCHED_QUEUE | + ((port - 1) << 6) | ((ah->sl & 7) << 3); path->feup |= MLX4_FEUP_FORCE_ETH_UP; if (vlan_tag < 0x1000) { - if (mlx4_find_cached_vlan(dev->dev, port, vlan_tag, &vidx)) - return -ENOENT; - - path->vlan_index = vidx; - path->fl = 1 << 6; + if (smac_info->vid < 0x1000) { + /* both valid vlan ids */ + if (smac_info->vid != vlan_tag) { + /* different VIDs. unreg old and reg new */ + err = mlx4_register_vlan(dev->dev, port, vlan_tag, &vidx); + if (err) + return err; + smac_info->candidate_vid = vlan_tag; + smac_info->candidate_vlan_index = vidx; + smac_info->candidate_vlan_port = port; + smac_info->update_vid = 1; + path->vlan_index = vidx; + } else { + path->vlan_index = smac_info->vlan_index; + } + } else { + /* no current vlan tag in qp */ + err = mlx4_register_vlan(dev->dev, port, vlan_tag, &vidx); + if (err) + return err; + smac_info->candidate_vid = vlan_tag; + smac_info->candidate_vlan_index = vidx; + smac_info->candidate_vlan_port = port; + smac_info->update_vid = 1; + path->vlan_index = vidx; + } path->feup |= MLX4_FVL_FORCE_ETH_VLAN; + path->fl = 1 << 6; + } else { + /* have current vlan tag. unregister it at modify-qp success */ + if (smac_info->vid < 0x1000) { + smac_info->candidate_vid = 0xFFFF; + smac_info->update_vid = 1; + } } - } else + + /* get smac_index for RoCE use. + * If no smac was yet assigned, register one. + * If one was already assigned, but the new mac differs, + * unregister the old one and register the new one. + */ + if (!smac_info->smac || smac_info->smac != smac) { + /* register candidate now, unreg if needed, after success */ + smac_index = mlx4_register_mac(dev->dev, port, smac); + if (smac_index >= 0) { + smac_info->candidate_smac_index = smac_index; + smac_info->candidate_smac = smac; + smac_info->candidate_smac_port = port; + } else { + return -EINVAL; + } + } else { + smac_index = smac_info->smac_index; + } + + memcpy(path->dmac, ah->dmac, 6); + path->ackto = MLX4_IB_LINK_TYPE_ETH; + /* put MAC table smac index for IBoE */ + path->grh_mylmc = (u8) (smac_index) | 0x80; + } else { path->sched_queue = MLX4_IB_DEFAULT_SCHED_QUEUE | ((port - 1) << 6) | ((ah->sl & 0xf) << 2); + } return 0; } static int mlx4_set_path(struct mlx4_ib_dev *dev, const struct ib_qp_attr *qp, enum ib_qp_attr_mask qp_attr_mask, + struct mlx4_ib_qp *mqp, struct mlx4_qp_path *path, u8 port) { return _mlx4_set_path(dev, &qp->ah_attr, mlx4_mac_to_u64((u8 *)qp->smac), (qp_attr_mask & IB_QP_VID) ? qp->vlan_id : 0xffff, - path, port); + path, &mqp->pri, port); } static int mlx4_set_alt_path(struct mlx4_ib_dev *dev, const struct ib_qp_attr *qp, enum ib_qp_attr_mask qp_attr_mask, + struct mlx4_ib_qp *mqp, struct mlx4_qp_path *path, u8 port) { return _mlx4_set_path(dev, &qp->alt_ah_attr, mlx4_mac_to_u64((u8 *)qp->alt_smac), (qp_attr_mask & IB_QP_ALT_VID) ? qp->alt_vlan_id : 0xffff, - path, port); + path, &mqp->alt, port); } static void update_mcg_macs(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp) @@ -1292,6 +1362,37 @@ static void update_mcg_macs(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp) } } +static int handle_eth_ud_smac_index(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp, u8 *smac, + struct mlx4_qp_context *context) +{ + struct net_device *ndev; + u64 u64_mac; + int smac_index; + + + ndev = dev->iboe.netdevs[qp->port - 1]; + if (ndev) { + smac = ndev->dev_addr; + u64_mac = mlx4_mac_to_u64(smac); + } else { + u64_mac = dev->dev->caps.def_mac[qp->port]; + } + + context->pri_path.sched_queue = MLX4_IB_DEFAULT_SCHED_QUEUE | ((qp->port - 1) << 6); + if (!qp->pri.smac) { + smac_index = mlx4_register_mac(dev->dev, qp->port, u64_mac); + if (smac_index >= 0) { + qp->pri.candidate_smac_index = smac_index; + qp->pri.candidate_smac = u64_mac; + qp->pri.candidate_smac_port = qp->port; + context->pri_path.grh_mylmc = 0x80 | (u8) smac_index; + } else { + return -ENOENT; + } + } + return 0; +} + static int __mlx4_ib_modify_qp(struct ib_qp *ibqp, const struct ib_qp_attr *attr, int attr_mask, enum ib_qp_state cur_state, enum ib_qp_state new_state) @@ -1403,7 +1504,7 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp, } if (attr_mask & IB_QP_AV) { - if (mlx4_set_path(dev, attr, attr_mask, &context->pri_path, + if (mlx4_set_path(dev, attr, attr_mask, qp, &context->pri_path, attr_mask & IB_QP_PORT ? attr->port_num : qp->port)) goto out; @@ -1426,7 +1527,8 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp, dev->dev->caps.pkey_table_len[attr->alt_port_num]) goto out; - if (mlx4_set_alt_path(dev, attr, attr_mask, &context->alt_path, + if (mlx4_set_alt_path(dev, attr, attr_mask, qp, + &context->alt_path, attr->alt_port_num)) goto out; @@ -1532,6 +1634,20 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp, context->pri_path.fl = 0x80; context->pri_path.sched_queue |= MLX4_IB_DEFAULT_SCHED_QUEUE; } + if (rdma_port_get_link_layer(&dev->ib_dev, qp->port) == + IB_LINK_LAYER_ETHERNET) { + if (qp->mlx4_ib_qp_type == MLX4_IB_QPT_TUN_GSI || + qp->mlx4_ib_qp_type == MLX4_IB_QPT_GSI) + context->pri_path.feup = 1 << 7; /* don't fsm */ + /* handle smac_index */ + if (qp->mlx4_ib_qp_type == MLX4_IB_QPT_UD || + qp->mlx4_ib_qp_type == MLX4_IB_QPT_PROXY_GSI || + qp->mlx4_ib_qp_type == MLX4_IB_QPT_TUN_GSI) { + err = handle_eth_ud_smac_index(dev, qp, (u8 *)attr->smac, context); + if (err) + return -EINVAL; + } + } } if (qp->ibqp.qp_type == IB_QPT_RAW_PACKET) @@ -1619,28 +1735,113 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp, * If we moved a kernel QP to RESET, clean up all old CQ * entries and reinitialize the QP. */ - if (new_state == IB_QPS_RESET && !ibqp->uobject) { - mlx4_ib_cq_clean(recv_cq, qp->mqp.qpn, - ibqp->srq ? to_msrq(ibqp->srq): NULL); - if (send_cq != recv_cq) - mlx4_ib_cq_clean(send_cq, qp->mqp.qpn, NULL); + if (new_state == IB_QPS_RESET) { + if (!ibqp->uobject) { + mlx4_ib_cq_clean(recv_cq, qp->mqp.qpn, + ibqp->srq ? to_msrq(ibqp->srq) : NULL); + if (send_cq != recv_cq) + mlx4_ib_cq_clean(send_cq, qp->mqp.qpn, NULL); + + qp->rq.head = 0; + qp->rq.tail = 0; + qp->sq.head = 0; + qp->sq.tail = 0; + qp->sq_next_wqe = 0; + if (qp->rq.wqe_cnt) + *qp->db.db = 0; - qp->rq.head = 0; - qp->rq.tail = 0; - qp->sq.head = 0; - qp->sq.tail = 0; - qp->sq_next_wqe = 0; - if (qp->rq.wqe_cnt) - *qp->db.db = 0; + if (qp->flags & MLX4_IB_QP_NETIF) + mlx4_ib_steer_qp_reg(dev, qp, 0); + } + if (qp->pri.smac) { + mlx4_unregister_mac(dev->dev, qp->pri.smac_port, qp->pri.smac); + qp->pri.smac = 0; + } + if (qp->alt.smac) { + mlx4_unregister_mac(dev->dev, qp->alt.smac_port, qp->alt.smac); + qp->alt.smac = 0; + } + if (qp->pri.vid < 0x1000) { + mlx4_unregister_vlan(dev->dev, qp->pri.vlan_port, qp->pri.vid); + qp->pri.vid = 0xFFFF; + qp->pri.candidate_vid = 0xFFFF; + qp->pri.update_vid = 0; + } - if (qp->flags & MLX4_IB_QP_NETIF) - mlx4_ib_steer_qp_reg(dev, qp, 0); + if (qp->alt.vid < 0x1000) { + mlx4_unregister_vlan(dev->dev, qp->alt.vlan_port, qp->alt.vid); + qp->alt.vid = 0xFFFF; + qp->alt.candidate_vid = 0xFFFF; + qp->alt.update_vid = 0; + } } - out: if (err && steer_qp) mlx4_ib_steer_qp_reg(dev, qp, 0); kfree(context); + if (qp->pri.candidate_smac) { + if (err) { + mlx4_unregister_mac(dev->dev, qp->pri.candidate_smac_port, qp->pri.candidate_smac); + } else { + if (qp->pri.smac) + mlx4_unregister_mac(dev->dev, qp->pri.smac_port, qp->pri.smac); + qp->pri.smac = qp->pri.candidate_smac; + qp->pri.smac_index = qp->pri.candidate_smac_index; + qp->pri.smac_port = qp->pri.candidate_smac_port; + } + qp->pri.candidate_smac = 0; + qp->pri.candidate_smac_index = 0; + qp->pri.candidate_smac_port = 0; + } + if (qp->alt.candidate_smac) { + if (err) { + mlx4_unregister_mac(dev->dev, qp->alt.candidate_smac_port, qp->alt.candidate_smac); + } else { + if (qp->alt.smac) + mlx4_unregister_mac(dev->dev, qp->alt.smac_port, qp->alt.smac); + qp->alt.smac = qp->alt.candidate_smac; + qp->alt.smac_index = qp->alt.candidate_smac_index; + qp->alt.smac_port = qp->alt.candidate_smac_port; + } + qp->alt.candidate_smac = 0; + qp->alt.candidate_smac_index = 0; + qp->alt.candidate_smac_port = 0; + } + + if (qp->pri.update_vid) { + if (err) { + if (qp->pri.candidate_vid < 0x1000) + mlx4_unregister_vlan(dev->dev, qp->pri.candidate_vlan_port, + qp->pri.candidate_vid); + } else { + if (qp->pri.vid < 0x1000) + mlx4_unregister_vlan(dev->dev, qp->pri.vlan_port, + qp->pri.vid); + qp->pri.vid = qp->pri.candidate_vid; + qp->pri.vlan_port = qp->pri.candidate_vlan_port; + qp->pri.vlan_index = qp->pri.candidate_vlan_index; + } + qp->pri.candidate_vid = 0xFFFF; + qp->pri.update_vid = 0; + } + + if (qp->alt.update_vid) { + if (err) { + if (qp->alt.candidate_vid < 0x1000) + mlx4_unregister_vlan(dev->dev, qp->alt.candidate_vlan_port, + qp->alt.candidate_vid); + } else { + if (qp->alt.vid < 0x1000) + mlx4_unregister_vlan(dev->dev, qp->alt.vlan_port, + qp->alt.vid); + qp->alt.vid = qp->alt.candidate_vid; + qp->alt.vlan_port = qp->alt.candidate_vlan_port; + qp->alt.vlan_index = qp->alt.candidate_vlan_index; + } + qp->alt.candidate_vid = 0xFFFF; + qp->alt.update_vid = 0; + } + return err; } @@ -1842,9 +2043,9 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_send_wr *wr, { struct ib_device *ib_dev = sqp->qp.ibqp.device; struct mlx4_wqe_mlx_seg *mlx = wqe; + struct mlx4_wqe_ctrl_seg *ctrl = wqe; struct mlx4_wqe_inline_seg *inl = wqe + sizeof *mlx; struct mlx4_ib_ah *ah = to_mah(wr->wr.ud.ah); - struct net_device *ndev; union ib_gid sgid; u16 pkey; int send_size; @@ -1868,12 +2069,11 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_send_wr *wr, /* When multi-function is enabled, the ib_core gid * indexes don't necessarily match the hw ones, so * we must use our own cache */ - sgid.global.subnet_prefix = - to_mdev(ib_dev)->sriov.demux[sqp->qp.port - 1]. - subnet_prefix; - sgid.global.interface_id = - to_mdev(ib_dev)->sriov.demux[sqp->qp.port - 1]. - guid_cache[ah->av.ib.gid_index]; + err = mlx4_get_roce_gid_from_slave(to_mdev(ib_dev)->dev, + be32_to_cpu(ah->av.ib.port_pd) >> 24, + ah->av.ib.gid_index, &sgid.raw[0]); + if (err) + return err; } else { err = ib_get_cached_gid(ib_dev, be32_to_cpu(ah->av.ib.port_pd) >> 24, @@ -1902,6 +2102,9 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_send_wr *wr, sqp->ud_header.grh.flow_label = ah->av.ib.sl_tclass_flowlabel & cpu_to_be32(0xfffff); sqp->ud_header.grh.hop_limit = ah->av.ib.hop_limit; + if (is_eth) + memcpy(sqp->ud_header.grh.source_gid.raw, sgid.raw, 16); + else { if (mlx4_is_mfunc(to_mdev(ib_dev)->dev)) { /* When multi-function is enabled, the ib_core gid * indexes don't necessarily match the hw ones, so @@ -1917,6 +2120,7 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_send_wr *wr, be32_to_cpu(ah->av.ib.port_pd) >> 24, ah->av.ib.gid_index, &sqp->ud_header.grh.source_gid); + } memcpy(sqp->ud_header.grh.destination_gid.raw, ah->av.ib.dgid, 16); } @@ -1949,16 +2153,23 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_send_wr *wr, if (is_eth) { u8 *smac; + struct in6_addr in6; + u16 pcp = (be32_to_cpu(ah->av.ib.sl_tclass_flowlabel) >> 29) << 13; mlx->sched_prio = cpu_to_be16(pcp); memcpy(sqp->ud_header.eth.dmac_h, ah->av.eth.mac, 6); /* FIXME: cache smac value? */ - ndev = to_mdev(sqp->qp.ibqp.device)->iboe.netdevs[sqp->qp.port - 1]; - if (!ndev) - return -ENODEV; - smac = ndev->dev_addr; + memcpy(&ctrl->srcrb_flags16[0], ah->av.eth.mac, 2); + memcpy(&ctrl->imm, ah->av.eth.mac + 2, 4); + memcpy(&in6, sgid.raw, sizeof(in6)); + + if (!mlx4_is_mfunc(to_mdev(ib_dev)->dev)) + smac = to_mdev(sqp->qp.ibqp.device)-> + iboe.netdevs[sqp->qp.port - 1]->dev_addr; + else /* use the src mac of the tunnel */ + smac = ah->av.eth.s_mac; memcpy(sqp->ud_header.eth.smac_h, smac, 6); if (!memcmp(sqp->ud_header.eth.smac_h, sqp->ud_header.eth.dmac_h, 6)) mlx->flags |= cpu_to_be32(MLX4_WQE_CTRL_FORCE_LOOPBACK); @@ -2190,6 +2401,8 @@ static void build_tunnel_header(struct ib_send_wr *wr, void *wqe, unsigned *mlx_ hdr.remote_qpn = cpu_to_be32(wr->wr.ud.remote_qpn); hdr.pkey_index = cpu_to_be16(wr->wr.ud.pkey_index); hdr.qkey = cpu_to_be32(wr->wr.ud.remote_qkey); + memcpy(hdr.mac, ah->av.eth.mac, 6); + hdr.vlan = ah->av.eth.vlan; spc = MLX4_INLINE_ALIGN - ((unsigned long) (inl + 1) & (MLX4_INLINE_ALIGN - 1)); diff --git a/drivers/infiniband/hw/mlx5/Kconfig b/drivers/infiniband/hw/mlx5/Kconfig index 8e6aebfaf8a4..10df386c6344 100644 --- a/drivers/infiniband/hw/mlx5/Kconfig +++ b/drivers/infiniband/hw/mlx5/Kconfig @@ -1,6 +1,6 @@ config MLX5_INFINIBAND tristate "Mellanox Connect-IB HCA support" - depends on NETDEVICES && ETHERNET && PCI && X86 + depends on NETDEVICES && ETHERNET && PCI select NET_VENDOR_MELLANOX select MLX5_CORE ---help--- diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 9660d093f8cf..bf900579ac08 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -46,8 +46,8 @@ #include "mlx5_ib.h" #define DRIVER_NAME "mlx5_ib" -#define DRIVER_VERSION "1.0" -#define DRIVER_RELDATE "June 2013" +#define DRIVER_VERSION "2.2-1" +#define DRIVER_RELDATE "Feb 2014" MODULE_AUTHOR("Eli Cohen <eli@mellanox.com>"); MODULE_DESCRIPTION("Mellanox Connect-IB HCA IB driver"); @@ -261,8 +261,7 @@ static int mlx5_ib_query_device(struct ib_device *ibdev, props->device_cap_flags = IB_DEVICE_CHANGE_PHY_PORT | IB_DEVICE_PORT_ACTIVE_EVENT | IB_DEVICE_SYS_IMAGE_GUID | - IB_DEVICE_RC_RNR_NAK_GEN | - IB_DEVICE_BLOCK_MULTICAST_LOOPBACK; + IB_DEVICE_RC_RNR_NAK_GEN; flags = dev->mdev.caps.flags; if (flags & MLX5_DEV_CAP_FLAG_BAD_PKEY_CNTR) props->device_cap_flags |= IB_DEVICE_BAD_PKEY_CNTR; @@ -536,24 +535,38 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev, struct ib_udata *udata) { struct mlx5_ib_dev *dev = to_mdev(ibdev); - struct mlx5_ib_alloc_ucontext_req req; + struct mlx5_ib_alloc_ucontext_req_v2 req; struct mlx5_ib_alloc_ucontext_resp resp; struct mlx5_ib_ucontext *context; struct mlx5_uuar_info *uuari; struct mlx5_uar *uars; int gross_uuars; int num_uars; + int ver; int uuarn; int err; int i; + int reqlen; if (!dev->ib_active) return ERR_PTR(-EAGAIN); - err = ib_copy_from_udata(&req, udata, sizeof(req)); + memset(&req, 0, sizeof(req)); + reqlen = udata->inlen - sizeof(struct ib_uverbs_cmd_hdr); + if (reqlen == sizeof(struct mlx5_ib_alloc_ucontext_req)) + ver = 0; + else if (reqlen == sizeof(struct mlx5_ib_alloc_ucontext_req_v2)) + ver = 2; + else + return ERR_PTR(-EINVAL); + + err = ib_copy_from_udata(&req, udata, reqlen); if (err) return ERR_PTR(err); + if (req.flags || req.reserved) + return ERR_PTR(-EINVAL); + if (req.total_num_uuars > MLX5_MAX_UUARS) return ERR_PTR(-ENOMEM); @@ -626,6 +639,7 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev, if (err) goto out_uars; + uuari->ver = ver; uuari->num_low_latency_uuars = req.num_low_latency_uuars; uuari->uars = uars; uuari->num_uars = num_uars; diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c index ae37fb9bf262..7dfe8a1c84cf 100644 --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@ -216,7 +216,9 @@ static int sq_overhead(enum ib_qp_type qp_type) case IB_QPT_UC: size += sizeof(struct mlx5_wqe_ctrl_seg) + - sizeof(struct mlx5_wqe_raddr_seg); + sizeof(struct mlx5_wqe_raddr_seg) + + sizeof(struct mlx5_wqe_umr_ctrl_seg) + + sizeof(struct mlx5_mkey_seg); break; case IB_QPT_UD: @@ -428,11 +430,17 @@ static int alloc_uuar(struct mlx5_uuar_info *uuari, break; case MLX5_IB_LATENCY_CLASS_MEDIUM: - uuarn = alloc_med_class_uuar(uuari); + if (uuari->ver < 2) + uuarn = -ENOMEM; + else + uuarn = alloc_med_class_uuar(uuari); break; case MLX5_IB_LATENCY_CLASS_HIGH: - uuarn = alloc_high_class_uuar(uuari); + if (uuari->ver < 2) + uuarn = -ENOMEM; + else + uuarn = alloc_high_class_uuar(uuari); break; case MLX5_IB_LATENCY_CLASS_FAST_PATH: @@ -657,8 +665,8 @@ static int create_kernel_qp(struct mlx5_ib_dev *dev, int err; uuari = &dev->mdev.priv.uuari; - if (init_attr->create_flags & IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK) - qp->flags |= MLX5_IB_QP_BLOCK_MULTICAST_LOOPBACK; + if (init_attr->create_flags) + return -EINVAL; if (init_attr->qp_type == MLX5_IB_QPT_REG_UMR) lc = MLX5_IB_LATENCY_CLASS_FAST_PATH; diff --git a/drivers/infiniband/hw/mlx5/user.h b/drivers/infiniband/hw/mlx5/user.h index 32a2a5dfc523..0f4f8e42a17f 100644 --- a/drivers/infiniband/hw/mlx5/user.h +++ b/drivers/infiniband/hw/mlx5/user.h @@ -62,6 +62,13 @@ struct mlx5_ib_alloc_ucontext_req { __u32 num_low_latency_uuars; }; +struct mlx5_ib_alloc_ucontext_req_v2 { + __u32 total_num_uuars; + __u32 num_low_latency_uuars; + __u32 flags; + __u32 reserved; +}; + struct mlx5_ib_alloc_ucontext_resp { __u32 qp_tab_size; __u32 bf_reg_size; diff --git a/drivers/infiniband/hw/nes/nes.c b/drivers/infiniband/hw/nes/nes.c index 429141078eec..353c7b05a90a 100644 --- a/drivers/infiniband/hw/nes/nes.c +++ b/drivers/infiniband/hw/nes/nes.c @@ -675,8 +675,11 @@ static int nes_probe(struct pci_dev *pcidev, const struct pci_device_id *ent) INIT_DELAYED_WORK(&nesdev->work, nes_recheck_link_status); /* Initialize network devices */ - if ((netdev = nes_netdev_init(nesdev, mmio_regs)) == NULL) + netdev = nes_netdev_init(nesdev, mmio_regs); + if (netdev == NULL) { + ret = -ENOMEM; goto bail7; + } /* Register network device */ ret = register_netdev(netdev); diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_main.c b/drivers/infiniband/hw/ocrdma/ocrdma_main.c index 2ca86ca818bd..1a8a945efa60 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_main.c +++ b/drivers/infiniband/hw/ocrdma/ocrdma_main.c @@ -127,7 +127,7 @@ static int ocrdma_addr_event(unsigned long event, struct net_device *netdev, is_vlan = netdev->priv_flags & IFF_802_1Q_VLAN; if (is_vlan) - netdev = vlan_dev_real_dev(netdev); + netdev = rdma_vlan_dev_real_dev(netdev); rcu_read_lock(); list_for_each_entry_rcu(dev, &ocrdma_dev_list, entry) { diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c index aa92f40c9d50..e0cc201be41a 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c +++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c @@ -176,7 +176,7 @@ int ocrdma_query_port(struct ib_device *ibdev, props->port_cap_flags = IB_PORT_CM_SUP | IB_PORT_REINIT_SUP | - IB_PORT_DEVICE_MGMT_SUP | IB_PORT_VENDOR_CLASS_SUP; + IB_PORT_DEVICE_MGMT_SUP | IB_PORT_VENDOR_CLASS_SUP | IB_PORT_IP_BASED_GIDS; props->gid_tbl_len = OCRDMA_MAX_SGID; props->pkey_tbl_len = 1; props->bad_pkey_cntr = 0; @@ -1416,7 +1416,7 @@ int ocrdma_query_qp(struct ib_qp *ibqp, OCRDMA_QP_PARAMS_HOP_LMT_MASK) >> OCRDMA_QP_PARAMS_HOP_LMT_SHIFT; qp_attr->ah_attr.grh.traffic_class = (params.tclass_sq_psn & - OCRDMA_QP_PARAMS_SQ_PSN_MASK) >> + OCRDMA_QP_PARAMS_TCLASS_MASK) >> OCRDMA_QP_PARAMS_TCLASS_SHIFT; qp_attr->ah_attr.ah_flags = IB_AH_GRH; diff --git a/drivers/infiniband/hw/qib/qib_iba7322.c b/drivers/infiniband/hw/qib/qib_iba7322.c index 5bfc02f450e6..d1bd21319d7d 100644 --- a/drivers/infiniband/hw/qib/qib_iba7322.c +++ b/drivers/infiniband/hw/qib/qib_iba7322.c @@ -2395,6 +2395,11 @@ static int qib_7322_bringup_serdes(struct qib_pportdata *ppd) qib_write_kreg_port(ppd, krp_ibcctrl_a, ppd->cpspec->ibcctrl_a); qib_write_kreg(dd, kr_scratch, 0ULL); + /* ensure previous Tx parameters are not still forced */ + qib_write_kreg_port(ppd, krp_tx_deemph_override, + SYM_MASK(IBSD_TX_DEEMPHASIS_OVERRIDE_0, + reset_tx_deemphasis_override)); + if (qib_compat_ddr_negotiate) { ppd->cpspec->ibdeltainprog = 1; ppd->cpspec->ibsymsnap = read_7322_creg32_port(ppd, diff --git a/drivers/infiniband/hw/usnic/usnic_ib_qp_grp.c b/drivers/infiniband/hw/usnic/usnic_ib_qp_grp.c index 7ecc6061f1f4..f8dfd76be89f 100644 --- a/drivers/infiniband/hw/usnic/usnic_ib_qp_grp.c +++ b/drivers/infiniband/hw/usnic/usnic_ib_qp_grp.c @@ -629,6 +629,7 @@ static int qp_grp_id_from_flow(struct usnic_ib_qp_grp_flow *qp_flow, { enum usnic_transport_type trans_type = qp_flow->trans_type; int err; + uint16_t port_num = 0; switch (trans_type) { case USNIC_TRANSPORT_ROCE_CUSTOM: @@ -637,9 +638,15 @@ static int qp_grp_id_from_flow(struct usnic_ib_qp_grp_flow *qp_flow, case USNIC_TRANSPORT_IPV4_UDP: err = usnic_transport_sock_get_addr(qp_flow->udp.sock, NULL, NULL, - (uint16_t *) id); + &port_num); if (err) return err; + /* + * Copy port_num to stack first and then to *id, + * so that the short to int cast works for little + * and big endian systems. + */ + *id = port_num; break; default: usnic_err("Unsupported transport %u\n", trans_type); diff --git a/drivers/infiniband/ulp/iser/iser_initiator.c b/drivers/infiniband/ulp/iser/iser_initiator.c index 538822684d5b..334f34b1cd46 100644 --- a/drivers/infiniband/ulp/iser/iser_initiator.c +++ b/drivers/infiniband/ulp/iser/iser_initiator.c @@ -610,11 +610,12 @@ void iser_snd_completion(struct iser_tx_desc *tx_desc, ib_dma_unmap_single(device->ib_device, tx_desc->dma_addr, ISER_HEADERS_LEN, DMA_TO_DEVICE); kmem_cache_free(ig.desc_cache, tx_desc); + tx_desc = NULL; } atomic_dec(&ib_conn->post_send_buf_count); - if (tx_desc->type == ISCSI_TX_CONTROL) { + if (tx_desc && tx_desc->type == ISCSI_TX_CONTROL) { /* this arithmetic is legal by libiscsi dd_data allocation */ task = (void *) ((long)(void *)tx_desc - sizeof(struct iscsi_task)); diff --git a/drivers/infiniband/ulp/iser/iser_verbs.c b/drivers/infiniband/ulp/iser/iser_verbs.c index afe95674008b..ca37edef2791 100644 --- a/drivers/infiniband/ulp/iser/iser_verbs.c +++ b/drivers/infiniband/ulp/iser/iser_verbs.c @@ -652,9 +652,13 @@ static int iser_disconnected_handler(struct rdma_cm_id *cma_id) /* getting here when the state is UP means that the conn is being * * terminated asynchronously from the iSCSI layer's perspective. */ if (iser_conn_state_comp_exch(ib_conn, ISER_CONN_UP, - ISER_CONN_TERMINATING)) - iscsi_conn_failure(ib_conn->iser_conn->iscsi_conn, - ISCSI_ERR_CONN_FAILED); + ISER_CONN_TERMINATING)){ + if (ib_conn->iser_conn) + iscsi_conn_failure(ib_conn->iser_conn->iscsi_conn, + ISCSI_ERR_CONN_FAILED); + else + iser_err("iscsi_iser connection isn't bound\n"); + } /* Complete the termination process if no posts are pending */ if (ib_conn->post_recv_buf_count == 0 && diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c index 2b161be3c1a3..d18d08a076e8 100644 --- a/drivers/infiniband/ulp/isert/ib_isert.c +++ b/drivers/infiniband/ulp/isert/ib_isert.c @@ -453,6 +453,7 @@ isert_conn_create_fastreg_pool(struct isert_conn *isert_conn) if (ret) { pr_err("Failed to create fastreg descriptor err=%d\n", ret); + kfree(fr_desc); goto err; } diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c index 520a7e5a490b..0e537d8d0e47 100644 --- a/drivers/infiniband/ulp/srpt/ib_srpt.c +++ b/drivers/infiniband/ulp/srpt/ib_srpt.c @@ -3666,9 +3666,9 @@ static ssize_t srpt_tpg_attrib_store_srp_max_rdma_size( unsigned long val; int ret; - ret = strict_strtoul(page, 0, &val); + ret = kstrtoul(page, 0, &val); if (ret < 0) { - pr_err("strict_strtoul() failed with ret: %d\n", ret); + pr_err("kstrtoul() failed with ret: %d\n", ret); return -EINVAL; } if (val > MAX_SRPT_RDMA_SIZE) { @@ -3706,9 +3706,9 @@ static ssize_t srpt_tpg_attrib_store_srp_max_rsp_size( unsigned long val; int ret; - ret = strict_strtoul(page, 0, &val); + ret = kstrtoul(page, 0, &val); if (ret < 0) { - pr_err("strict_strtoul() failed with ret: %d\n", ret); + pr_err("kstrtoul() failed with ret: %d\n", ret); return -EINVAL; } if (val > MAX_SRPT_RSP_SIZE) { @@ -3746,9 +3746,9 @@ static ssize_t srpt_tpg_attrib_store_srp_sq_size( unsigned long val; int ret; - ret = strict_strtoul(page, 0, &val); + ret = kstrtoul(page, 0, &val); if (ret < 0) { - pr_err("strict_strtoul() failed with ret: %d\n", ret); + pr_err("kstrtoul() failed with ret: %d\n", ret); return -EINVAL; } if (val > MAX_SRPT_SRQ_SIZE) { @@ -3793,7 +3793,7 @@ static ssize_t srpt_tpg_store_enable( unsigned long tmp; int ret; - ret = strict_strtoul(page, 0, &tmp); + ret = kstrtoul(page, 0, &tmp); if (ret < 0) { printk(KERN_ERR "Unable to extract srpt_tpg_store_enable\n"); return -EINVAL; diff --git a/drivers/input/misc/arizona-haptics.c b/drivers/input/misc/arizona-haptics.c index 7a04f54ef961..ef2e281b0a43 100644 --- a/drivers/input/misc/arizona-haptics.c +++ b/drivers/input/misc/arizona-haptics.c @@ -37,7 +37,6 @@ static void arizona_haptics_work(struct work_struct *work) struct arizona_haptics, work); struct arizona *arizona = haptics->arizona; - struct mutex *dapm_mutex = &arizona->dapm->card->dapm_mutex; int ret; if (!haptics->arizona->dapm) { @@ -67,13 +66,10 @@ static void arizona_haptics_work(struct work_struct *work) return; } - mutex_lock_nested(dapm_mutex, SND_SOC_DAPM_CLASS_RUNTIME); - ret = snd_soc_dapm_enable_pin(arizona->dapm, "HAPTICS"); if (ret != 0) { dev_err(arizona->dev, "Failed to start HAPTICS: %d\n", ret); - mutex_unlock(dapm_mutex); return; } @@ -81,21 +77,14 @@ static void arizona_haptics_work(struct work_struct *work) if (ret != 0) { dev_err(arizona->dev, "Failed to sync DAPM: %d\n", ret); - mutex_unlock(dapm_mutex); return; } - - mutex_unlock(dapm_mutex); - } else { /* This disable sequence will be a noop if already enabled */ - mutex_lock_nested(dapm_mutex, SND_SOC_DAPM_CLASS_RUNTIME); - ret = snd_soc_dapm_disable_pin(arizona->dapm, "HAPTICS"); if (ret != 0) { dev_err(arizona->dev, "Failed to disable HAPTICS: %d\n", ret); - mutex_unlock(dapm_mutex); return; } @@ -103,12 +92,9 @@ static void arizona_haptics_work(struct work_struct *work) if (ret != 0) { dev_err(arizona->dev, "Failed to sync DAPM: %d\n", ret); - mutex_unlock(dapm_mutex); return; } - mutex_unlock(dapm_mutex); - ret = regmap_update_bits(arizona->regmap, ARIZONA_HAPTICS_CONTROL_1, ARIZONA_HAP_CTRL_MASK, @@ -155,16 +141,11 @@ static int arizona_haptics_play(struct input_dev *input, void *data, static void arizona_haptics_close(struct input_dev *input) { struct arizona_haptics *haptics = input_get_drvdata(input); - struct mutex *dapm_mutex = &haptics->arizona->dapm->card->dapm_mutex; cancel_work_sync(&haptics->work); - mutex_lock_nested(dapm_mutex, SND_SOC_DAPM_CLASS_RUNTIME); - if (haptics->arizona->dapm) snd_soc_dapm_disable_pin(haptics->arizona->dapm, "HAPTICS"); - - mutex_unlock(dapm_mutex); } static int arizona_haptics_probe(struct platform_device *pdev) diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c index 8911850c9444..1d9ab39af29f 100644 --- a/drivers/iommu/arm-smmu.c +++ b/drivers/iommu/arm-smmu.c @@ -79,7 +79,6 @@ #define ARM_SMMU_PTE_CONT_SIZE (PAGE_SIZE * ARM_SMMU_PTE_CONT_ENTRIES) #define ARM_SMMU_PTE_CONT_MASK (~(ARM_SMMU_PTE_CONT_SIZE - 1)) -#define ARM_SMMU_PTE_HWTABLE_SIZE (PTRS_PER_PTE * sizeof(pte_t)) /* Stage-1 PTE */ #define ARM_SMMU_PTE_AP_UNPRIV (((pteval_t)1) << 6) @@ -191,6 +190,9 @@ #define ARM_SMMU_GR1_CBAR(n) (0x0 + ((n) << 2)) #define CBAR_VMID_SHIFT 0 #define CBAR_VMID_MASK 0xff +#define CBAR_S1_BPSHCFG_SHIFT 8 +#define CBAR_S1_BPSHCFG_MASK 3 +#define CBAR_S1_BPSHCFG_NSH 3 #define CBAR_S1_MEMATTR_SHIFT 12 #define CBAR_S1_MEMATTR_MASK 0xf #define CBAR_S1_MEMATTR_WB 0xf @@ -393,7 +395,7 @@ struct arm_smmu_domain { struct arm_smmu_cfg root_cfg; phys_addr_t output_mask; - struct mutex lock; + spinlock_t lock; }; static DEFINE_SPINLOCK(arm_smmu_devices_lock); @@ -632,6 +634,28 @@ static irqreturn_t arm_smmu_global_fault(int irq, void *dev) return IRQ_HANDLED; } +static void arm_smmu_flush_pgtable(struct arm_smmu_device *smmu, void *addr, + size_t size) +{ + unsigned long offset = (unsigned long)addr & ~PAGE_MASK; + + + /* Ensure new page tables are visible to the hardware walker */ + if (smmu->features & ARM_SMMU_FEAT_COHERENT_WALK) { + dsb(); + } else { + /* + * If the SMMU can't walk tables in the CPU caches, treat them + * like non-coherent DMA since we need to flush the new entries + * all the way out to memory. There's no possibility of + * recursion here as the SMMU table walker will not be wired + * through another SMMU. + */ + dma_map_page(smmu->dev, virt_to_page(addr), offset, size, + DMA_TO_DEVICE); + } +} + static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain) { u32 reg; @@ -650,11 +674,16 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain) if (smmu->version == 1) reg |= root_cfg->irptndx << CBAR_IRPTNDX_SHIFT; - /* Use the weakest memory type, so it is overridden by the pte */ - if (stage1) - reg |= (CBAR_S1_MEMATTR_WB << CBAR_S1_MEMATTR_SHIFT); - else + /* + * Use the weakest shareability/memory types, so they are + * overridden by the ttbcr/pte. + */ + if (stage1) { + reg |= (CBAR_S1_BPSHCFG_NSH << CBAR_S1_BPSHCFG_SHIFT) | + (CBAR_S1_MEMATTR_WB << CBAR_S1_MEMATTR_SHIFT); + } else { reg |= ARM_SMMU_CB_VMID(root_cfg) << CBAR_VMID_SHIFT; + } writel_relaxed(reg, gr1_base + ARM_SMMU_GR1_CBAR(root_cfg->cbndx)); if (smmu->version > 1) { @@ -715,6 +744,8 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain) } /* TTBR0 */ + arm_smmu_flush_pgtable(smmu, root_cfg->pgd, + PTRS_PER_PGD * sizeof(pgd_t)); reg = __pa(root_cfg->pgd); writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBR0_LO); reg = (phys_addr_t)__pa(root_cfg->pgd) >> 32; @@ -901,7 +932,7 @@ static int arm_smmu_domain_init(struct iommu_domain *domain) goto out_free_domain; smmu_domain->root_cfg.pgd = pgd; - mutex_init(&smmu_domain->lock); + spin_lock_init(&smmu_domain->lock); domain->priv = smmu_domain; return 0; @@ -1128,6 +1159,7 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev) struct arm_smmu_domain *smmu_domain = domain->priv; struct arm_smmu_device *device_smmu = dev->archdata.iommu; struct arm_smmu_master *master; + unsigned long flags; if (!device_smmu) { dev_err(dev, "cannot attach to SMMU, is it on the same bus?\n"); @@ -1138,7 +1170,7 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev) * Sanity check the domain. We don't currently support domains * that cross between different SMMU chains. */ - mutex_lock(&smmu_domain->lock); + spin_lock_irqsave(&smmu_domain->lock, flags); if (!smmu_domain->leaf_smmu) { /* Now that we have a master, we can finalise the domain */ ret = arm_smmu_init_domain_context(domain, dev); @@ -1153,7 +1185,7 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev) dev_name(device_smmu->dev)); goto err_unlock; } - mutex_unlock(&smmu_domain->lock); + spin_unlock_irqrestore(&smmu_domain->lock, flags); /* Looks ok, so add the device to the domain */ master = find_smmu_master(smmu_domain->leaf_smmu, dev->of_node); @@ -1163,7 +1195,7 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev) return arm_smmu_domain_add_master(smmu_domain, master); err_unlock: - mutex_unlock(&smmu_domain->lock); + spin_unlock_irqrestore(&smmu_domain->lock, flags); return ret; } @@ -1177,23 +1209,6 @@ static void arm_smmu_detach_dev(struct iommu_domain *domain, struct device *dev) arm_smmu_domain_remove_master(smmu_domain, master); } -static void arm_smmu_flush_pgtable(struct arm_smmu_device *smmu, void *addr, - size_t size) -{ - unsigned long offset = (unsigned long)addr & ~PAGE_MASK; - - /* - * If the SMMU can't walk tables in the CPU caches, treat them - * like non-coherent DMA since we need to flush the new entries - * all the way out to memory. There's no possibility of recursion - * here as the SMMU table walker will not be wired through another - * SMMU. - */ - if (!(smmu->features & ARM_SMMU_FEAT_COHERENT_WALK)) - dma_map_page(smmu->dev, virt_to_page(addr), offset, size, - DMA_TO_DEVICE); -} - static bool arm_smmu_pte_is_contiguous_range(unsigned long addr, unsigned long end) { @@ -1210,12 +1225,11 @@ static int arm_smmu_alloc_init_pte(struct arm_smmu_device *smmu, pmd_t *pmd, if (pmd_none(*pmd)) { /* Allocate a new set of tables */ - pgtable_t table = alloc_page(PGALLOC_GFP); + pgtable_t table = alloc_page(GFP_ATOMIC|__GFP_ZERO); if (!table) return -ENOMEM; - arm_smmu_flush_pgtable(smmu, page_address(table), - ARM_SMMU_PTE_HWTABLE_SIZE); + arm_smmu_flush_pgtable(smmu, page_address(table), PAGE_SIZE); if (!pgtable_page_ctor(table)) { __free_page(table); return -ENOMEM; @@ -1317,9 +1331,15 @@ static int arm_smmu_alloc_init_pmd(struct arm_smmu_device *smmu, pud_t *pud, #ifndef __PAGETABLE_PMD_FOLDED if (pud_none(*pud)) { - pmd = pmd_alloc_one(NULL, addr); + pmd = (pmd_t *)get_zeroed_page(GFP_ATOMIC); if (!pmd) return -ENOMEM; + + arm_smmu_flush_pgtable(smmu, pmd, PAGE_SIZE); + pud_populate(NULL, pud, pmd); + arm_smmu_flush_pgtable(smmu, pud, sizeof(*pud)); + + pmd += pmd_index(addr); } else #endif pmd = pmd_offset(pud, addr); @@ -1328,8 +1348,6 @@ static int arm_smmu_alloc_init_pmd(struct arm_smmu_device *smmu, pud_t *pud, next = pmd_addr_end(addr, end); ret = arm_smmu_alloc_init_pte(smmu, pmd, addr, end, pfn, flags, stage); - pud_populate(NULL, pud, pmd); - arm_smmu_flush_pgtable(smmu, pud, sizeof(*pud)); phys += next - addr; } while (pmd++, addr = next, addr < end); @@ -1346,9 +1364,15 @@ static int arm_smmu_alloc_init_pud(struct arm_smmu_device *smmu, pgd_t *pgd, #ifndef __PAGETABLE_PUD_FOLDED if (pgd_none(*pgd)) { - pud = pud_alloc_one(NULL, addr); + pud = (pud_t *)get_zeroed_page(GFP_ATOMIC); if (!pud) return -ENOMEM; + + arm_smmu_flush_pgtable(smmu, pud, PAGE_SIZE); + pgd_populate(NULL, pgd, pud); + arm_smmu_flush_pgtable(smmu, pgd, sizeof(*pgd)); + + pud += pud_index(addr); } else #endif pud = pud_offset(pgd, addr); @@ -1357,8 +1381,6 @@ static int arm_smmu_alloc_init_pud(struct arm_smmu_device *smmu, pgd_t *pgd, next = pud_addr_end(addr, end); ret = arm_smmu_alloc_init_pmd(smmu, pud, addr, next, phys, flags, stage); - pgd_populate(NULL, pud, pgd); - arm_smmu_flush_pgtable(smmu, pgd, sizeof(*pgd)); phys += next - addr; } while (pud++, addr = next, addr < end); @@ -1375,6 +1397,7 @@ static int arm_smmu_handle_mapping(struct arm_smmu_domain *smmu_domain, struct arm_smmu_cfg *root_cfg = &smmu_domain->root_cfg; pgd_t *pgd = root_cfg->pgd; struct arm_smmu_device *smmu = root_cfg->smmu; + unsigned long irqflags; if (root_cfg->cbar == CBAR_TYPE_S2_TRANS) { stage = 2; @@ -1397,7 +1420,7 @@ static int arm_smmu_handle_mapping(struct arm_smmu_domain *smmu_domain, if (paddr & ~output_mask) return -ERANGE; - mutex_lock(&smmu_domain->lock); + spin_lock_irqsave(&smmu_domain->lock, irqflags); pgd += pgd_index(iova); end = iova + size; do { @@ -1413,11 +1436,7 @@ static int arm_smmu_handle_mapping(struct arm_smmu_domain *smmu_domain, } while (pgd++, iova != end); out_unlock: - mutex_unlock(&smmu_domain->lock); - - /* Ensure new page tables are visible to the hardware walker */ - if (smmu->features & ARM_SMMU_FEAT_COHERENT_WALK) - dsb(); + spin_unlock_irqrestore(&smmu_domain->lock, irqflags); return ret; } @@ -1987,8 +2006,10 @@ static int __init arm_smmu_init(void) if (!iommu_present(&platform_bus_type)) bus_set_iommu(&platform_bus_type, &arm_smmu_ops); +#ifdef CONFIG_ARM_AMBA if (!iommu_present(&amba_bustype)) bus_set_iommu(&amba_bustype, &arm_smmu_ops); +#endif return 0; } diff --git a/drivers/iommu/omap-iommu-debug.c b/drivers/iommu/omap-iommu-debug.c index d97fbe4fb9b1..80fffba7f12d 100644 --- a/drivers/iommu/omap-iommu-debug.c +++ b/drivers/iommu/omap-iommu-debug.c @@ -354,8 +354,8 @@ DEBUG_FOPS(mem); return -ENOMEM; \ } -#define DEBUG_ADD_FILE(name) __DEBUG_ADD_FILE(name, 600) -#define DEBUG_ADD_FILE_RO(name) __DEBUG_ADD_FILE(name, 400) +#define DEBUG_ADD_FILE(name) __DEBUG_ADD_FILE(name, 0600) +#define DEBUG_ADD_FILE_RO(name) __DEBUG_ADD_FILE(name, 0400) static int iommu_debug_register(struct device *dev, void *data) { diff --git a/drivers/irqchip/irq-metag-ext.c b/drivers/irqchip/irq-metag-ext.c index 92c41ab4dbfd..2cb474ad8809 100644 --- a/drivers/irqchip/irq-metag-ext.c +++ b/drivers/irqchip/irq-metag-ext.c @@ -515,7 +515,7 @@ static int meta_intc_set_affinity(struct irq_data *data, * one cpu (the interrupt code doesn't support it), so we just * pick the first cpu we find in 'cpumask'. */ - cpu = cpumask_any(cpumask); + cpu = cpumask_any_and(cpumask, cpu_online_mask); thread = cpu_2_hwthread_id[cpu]; metag_out32(TBI_TRIG_VEC(TBID_SIGNUM_TR2(thread)), vec_addr); diff --git a/drivers/irqchip/irq-metag.c b/drivers/irqchip/irq-metag.c index 8e94d7a3b20d..c16c186d97d3 100644 --- a/drivers/irqchip/irq-metag.c +++ b/drivers/irqchip/irq-metag.c @@ -201,7 +201,7 @@ static int metag_internal_irq_set_affinity(struct irq_data *data, * one cpu (the interrupt code doesn't support it), so we just * pick the first cpu we find in 'cpumask'. */ - cpu = cpumask_any(cpumask); + cpu = cpumask_any_and(cpumask, cpu_online_mask); thread = cpu_2_hwthread_id[cpu]; metag_out32(TBI_TRIG_VEC(TBID_SIGNUM_TR1(thread)), diff --git a/drivers/irqchip/irq-orion.c b/drivers/irqchip/irq-orion.c index e51d40031884..8e41be62812e 100644 --- a/drivers/irqchip/irq-orion.c +++ b/drivers/irqchip/irq-orion.c @@ -111,7 +111,8 @@ IRQCHIP_DECLARE(orion_intc, "marvell,orion-intc", orion_irq_init); static void orion_bridge_irq_handler(unsigned int irq, struct irq_desc *desc) { struct irq_domain *d = irq_get_handler_data(irq); - struct irq_chip_generic *gc = irq_get_domain_generic_chip(d, irq); + + struct irq_chip_generic *gc = irq_get_domain_generic_chip(d, 0); u32 stat = readl_relaxed(gc->reg_base + ORION_BRIDGE_IRQ_CAUSE) & gc->mask_cache; @@ -123,6 +124,19 @@ static void orion_bridge_irq_handler(unsigned int irq, struct irq_desc *desc) } } +/* + * Bridge IRQ_CAUSE is asserted regardless of IRQ_MASK register. + * To avoid interrupt events on stale irqs, we clear them before unmask. + */ +static unsigned int orion_bridge_irq_startup(struct irq_data *d) +{ + struct irq_chip_type *ct = irq_data_get_chip_type(d); + + ct->chip.irq_ack(d); + ct->chip.irq_unmask(d); + return 0; +} + static int __init orion_bridge_irq_init(struct device_node *np, struct device_node *parent) { @@ -143,7 +157,7 @@ static int __init orion_bridge_irq_init(struct device_node *np, } ret = irq_alloc_domain_generic_chips(domain, nrirqs, 1, np->name, - handle_level_irq, clr, 0, IRQ_GC_INIT_MASK_CACHE); + handle_edge_irq, clr, 0, IRQ_GC_INIT_MASK_CACHE); if (ret) { pr_err("%s: unable to alloc irq domain gc\n", np->name); return ret; @@ -176,12 +190,14 @@ static int __init orion_bridge_irq_init(struct device_node *np, gc->chip_types[0].regs.ack = ORION_BRIDGE_IRQ_CAUSE; gc->chip_types[0].regs.mask = ORION_BRIDGE_IRQ_MASK; + gc->chip_types[0].chip.irq_startup = orion_bridge_irq_startup; gc->chip_types[0].chip.irq_ack = irq_gc_ack_clr_bit; gc->chip_types[0].chip.irq_mask = irq_gc_mask_clr_bit; gc->chip_types[0].chip.irq_unmask = irq_gc_mask_set_bit; - /* mask all interrupts */ + /* mask and clear all interrupts */ writel(0, gc->reg_base + ORION_BRIDGE_IRQ_MASK); + writel(0, gc->reg_base + ORION_BRIDGE_IRQ_CAUSE); irq_set_handler_data(irq, domain); irq_set_chained_handler(irq, orion_bridge_irq_handler); diff --git a/drivers/isdn/divert/divert_procfs.c b/drivers/isdn/divert/divert_procfs.c index fb4f1bac0133..1c5dc345e7c5 100644 --- a/drivers/isdn/divert/divert_procfs.c +++ b/drivers/isdn/divert/divert_procfs.c @@ -86,12 +86,13 @@ isdn_divert_read(struct file *file, char __user *buf, size_t count, loff_t *off) struct divert_info *inf; int len; - if (!*((struct divert_info **) file->private_data)) { + if (!(inf = *((struct divert_info **) file->private_data))) { if (file->f_flags & O_NONBLOCK) return -EAGAIN; - interruptible_sleep_on(&(rd_queue)); + wait_event_interruptible(rd_queue, (inf = + *((struct divert_info **) file->private_data))); } - if (!(inf = *((struct divert_info **) file->private_data))) + if (!inf) return (0); inf->usage_cnt--; /* new usage count */ diff --git a/drivers/isdn/hisax/elsa.c b/drivers/isdn/hisax/elsa.c index 2be1c8a3bb5f..d8ef64da26f1 100644 --- a/drivers/isdn/hisax/elsa.c +++ b/drivers/isdn/hisax/elsa.c @@ -509,7 +509,8 @@ static void set_arcofi(struct IsdnCardState *cs, int bc) { cs->dc.isac.arcofi_bc = bc; arcofi_fsm(cs, ARCOFI_START, &ARCOFI_COP_5); - interruptible_sleep_on(&cs->dc.isac.arcofi_wait); + wait_event_interruptible(cs->dc.isac.arcofi_wait, + cs->dc.isac.arcofi_state == ARCOFI_NOP); } static int @@ -528,7 +529,8 @@ check_arcofi(struct IsdnCardState *cs) } cs->dc.isac.arcofi_bc = 0; arcofi_fsm(cs, ARCOFI_START, &ARCOFI_VERSION); - interruptible_sleep_on(&cs->dc.isac.arcofi_wait); + wait_event_interruptible(cs->dc.isac.arcofi_wait, + cs->dc.isac.arcofi_state == ARCOFI_NOP); if (!test_and_clear_bit(FLG_ARCOFI_ERROR, &cs->HW_Flags)) { debugl1(cs, "Arcofi response received %d bytes", cs->dc.isac.mon_rxp); p = cs->dc.isac.mon_rx; @@ -595,7 +597,8 @@ check_arcofi(struct IsdnCardState *cs) Elsa_Types[cs->subtyp], cs->hw.elsa.base + 8); arcofi_fsm(cs, ARCOFI_START, &ARCOFI_XOP_0); - interruptible_sleep_on(&cs->dc.isac.arcofi_wait); + wait_event_interruptible(cs->dc.isac.arcofi_wait, + cs->dc.isac.arcofi_state == ARCOFI_NOP); return (1); } return (0); diff --git a/drivers/isdn/hisax/elsa_ser.c b/drivers/isdn/hisax/elsa_ser.c index 3f84dd8f1757..a2a358c1dc8e 100644 --- a/drivers/isdn/hisax/elsa_ser.c +++ b/drivers/isdn/hisax/elsa_ser.c @@ -573,7 +573,8 @@ modem_l2l1(struct PStack *st, int pr, void *arg) test_and_clear_bit(BC_FLG_ACTIV, &bcs->Flag); bcs->cs->dc.isac.arcofi_bc = st->l1.bc; arcofi_fsm(bcs->cs, ARCOFI_START, &ARCOFI_XOP_0); - interruptible_sleep_on(&bcs->cs->dc.isac.arcofi_wait); + wait_event_interruptible(bcs->cs->dc.isac.arcofi_wait, + bcs->cs->dc.isac.arcofi_state == ARCOFI_NOP); bcs->cs->hw.elsa.MFlag = 1; } else { printk(KERN_WARNING "ElsaSer: unknown pr %x\n", pr); diff --git a/drivers/isdn/hisax/q931.c b/drivers/isdn/hisax/q931.c index af1b020a81f1..b420f8bd862e 100644 --- a/drivers/isdn/hisax/q931.c +++ b/drivers/isdn/hisax/q931.c @@ -810,7 +810,7 @@ prfeatureind(char *dest, u_char *p) dp += sprintf(dp, " octet 3 "); dp += prbits(dp, *p, 8, 8); *dp++ = '\n'; - if (!(*p++ & 80)) { + if (!(*p++ & 0x80)) { dp += sprintf(dp, " octet 4 "); dp += prbits(dp, *p++, 8, 8); *dp++ = '\n'; diff --git a/drivers/isdn/hysdn/hysdn_proclog.c b/drivers/isdn/hysdn/hysdn_proclog.c index b61e8d5e84ad..7b5fd8fb1761 100644 --- a/drivers/isdn/hysdn/hysdn_proclog.c +++ b/drivers/isdn/hysdn/hysdn_proclog.c @@ -175,14 +175,15 @@ hysdn_log_read(struct file *file, char __user *buf, size_t count, loff_t *off) int len; hysdn_card *card = PDE_DATA(file_inode(file)); - if (!*((struct log_data **) file->private_data)) { + if (!(inf = *((struct log_data **) file->private_data))) { struct procdata *pd = card->proclog; if (file->f_flags & O_NONBLOCK) return (-EAGAIN); - interruptible_sleep_on(&(pd->rd_queue)); + wait_event_interruptible(pd->rd_queue, (inf = + *((struct log_data **) file->private_data))); } - if (!(inf = *((struct log_data **) file->private_data))) + if (!inf) return (0); inf->usage_cnt--; /* new usage count */ diff --git a/drivers/isdn/i4l/isdn_common.c b/drivers/isdn/i4l/isdn_common.c index 9bb12ba3191f..130f21643154 100644 --- a/drivers/isdn/i4l/isdn_common.c +++ b/drivers/isdn/i4l/isdn_common.c @@ -777,7 +777,8 @@ isdn_readbchan(int di, int channel, u_char *buf, u_char *fp, int len, wait_queue return 0; if (skb_queue_empty(&dev->drv[di]->rpqueue[channel])) { if (sleep) - interruptible_sleep_on(sleep); + wait_event_interruptible(*sleep, + !skb_queue_empty(&dev->drv[di]->rpqueue[channel])); else return 0; } @@ -1072,7 +1073,8 @@ isdn_read(struct file *file, char __user *buf, size_t count, loff_t *off) retval = -EAGAIN; goto out; } - interruptible_sleep_on(&(dev->info_waitq)); + wait_event_interruptible(dev->info_waitq, + file->private_data); } p = isdn_statstr(); file->private_data = NULL; @@ -1128,7 +1130,8 @@ isdn_read(struct file *file, char __user *buf, size_t count, loff_t *off) retval = -EAGAIN; goto out; } - interruptible_sleep_on(&(dev->drv[drvidx]->st_waitq)); + wait_event_interruptible(dev->drv[drvidx]->st_waitq, + dev->drv[drvidx]->stavail); } if (dev->drv[drvidx]->interface->readstat) { if (count > dev->drv[drvidx]->stavail) @@ -1188,8 +1191,8 @@ isdn_write(struct file *file, const char __user *buf, size_t count, loff_t *off) goto out; } chidx = isdn_minor2chan(minor); - while ((retval = isdn_writebuf_stub(drvidx, chidx, buf, count)) == 0) - interruptible_sleep_on(&dev->drv[drvidx]->snd_waitq[chidx]); + wait_event_interruptible(dev->drv[drvidx]->snd_waitq[chidx], + (retval = isdn_writebuf_stub(drvidx, chidx, buf, count))); goto out; } if (minor <= ISDN_MINOR_CTRLMAX) { diff --git a/drivers/isdn/pcbit/drv.c b/drivers/isdn/pcbit/drv.c index 1eaf62273903..f02cc506fbfa 100644 --- a/drivers/isdn/pcbit/drv.c +++ b/drivers/isdn/pcbit/drv.c @@ -796,6 +796,7 @@ static void set_running_timeout(unsigned long ptr) #endif dev = (struct pcbit_dev *) ptr; + dev->l2_state = L2_DOWN; wake_up_interruptible(&dev->set_running_wq); } @@ -818,7 +819,8 @@ static int set_protocol_running(struct pcbit_dev *dev) add_timer(&dev->set_running_timer); - interruptible_sleep_on(&dev->set_running_wq); + wait_event(dev->set_running_wq, dev->l2_state == L2_RUNNING || + dev->l2_state == L2_DOWN); del_timer(&dev->set_running_timer); @@ -842,8 +844,6 @@ static int set_protocol_running(struct pcbit_dev *dev) printk(KERN_DEBUG "pcbit: initialization failed\n"); printk(KERN_DEBUG "pcbit: firmware not loaded\n"); - dev->l2_state = L2_DOWN; - #ifdef DEBUG printk(KERN_DEBUG "Bank3 = %02x\n", readb(dev->sh_mem + BANK3)); diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h index 0c707e4f4eaf..a4c7306ff43d 100644 --- a/drivers/md/bcache/bcache.h +++ b/drivers/md/bcache/bcache.h @@ -210,7 +210,9 @@ BITMASK(GC_MARK, struct bucket, gc_mark, 0, 2); #define GC_MARK_RECLAIMABLE 0 #define GC_MARK_DIRTY 1 #define GC_MARK_METADATA 2 -BITMASK(GC_SECTORS_USED, struct bucket, gc_mark, 2, 13); +#define GC_SECTORS_USED_SIZE 13 +#define MAX_GC_SECTORS_USED (~(~0ULL << GC_SECTORS_USED_SIZE)) +BITMASK(GC_SECTORS_USED, struct bucket, gc_mark, 2, GC_SECTORS_USED_SIZE); BITMASK(GC_MOVE, struct bucket, gc_mark, 15, 1); #include "journal.h" diff --git a/drivers/md/bcache/bset.c b/drivers/md/bcache/bset.c index 4f6b5940e609..3f74b4b0747b 100644 --- a/drivers/md/bcache/bset.c +++ b/drivers/md/bcache/bset.c @@ -23,7 +23,7 @@ void bch_dump_bset(struct btree_keys *b, struct bset *i, unsigned set) for (k = i->start; k < bset_bkey_last(i); k = next) { next = bkey_next(k); - printk(KERN_ERR "block %u key %zi/%u: ", set, + printk(KERN_ERR "block %u key %li/%u: ", set, (uint64_t *) k - i->d, i->keys); if (b->ops->key_dump) @@ -1185,9 +1185,12 @@ static void __btree_sort(struct btree_keys *b, struct btree_iter *iter, struct bset *out = (void *) __get_free_pages(__GFP_NOWARN|GFP_NOIO, order); if (!out) { + struct page *outp; + BUG_ON(order > state->page_order); - out = page_address(mempool_alloc(state->pool, GFP_NOIO)); + outp = mempool_alloc(state->pool, GFP_NOIO); + out = page_address(outp); used_mempool = true; order = state->page_order; } diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c index 98cc0a810a36..5f9c2a665ca5 100644 --- a/drivers/md/bcache/btree.c +++ b/drivers/md/bcache/btree.c @@ -1167,7 +1167,7 @@ uint8_t __bch_btree_mark_key(struct cache_set *c, int level, struct bkey *k) /* guard against overflow */ SET_GC_SECTORS_USED(g, min_t(unsigned, GC_SECTORS_USED(g) + KEY_SIZE(k), - (1 << 14) - 1)); + MAX_GC_SECTORS_USED)); BUG_ON(!GC_SECTORS_USED(g)); } @@ -1805,7 +1805,7 @@ static bool btree_insert_key(struct btree *b, struct bkey *k, static size_t insert_u64s_remaining(struct btree *b) { - ssize_t ret = bch_btree_keys_u64s_remaining(&b->keys); + long ret = bch_btree_keys_u64s_remaining(&b->keys); /* * Might land in the middle of an existing extent and have to split it diff --git a/drivers/md/bcache/extents.c b/drivers/md/bcache/extents.c index c3ead586dc27..416d1a3e028e 100644 --- a/drivers/md/bcache/extents.c +++ b/drivers/md/bcache/extents.c @@ -194,7 +194,7 @@ err: mutex_unlock(&b->c->bucket_lock); bch_extent_to_text(buf, sizeof(buf), k); btree_bug(b, -"inconsistent btree pointer %s: bucket %li pin %i prio %i gen %i last_gc %i mark %llu gc_gen %i", +"inconsistent btree pointer %s: bucket %zi pin %i prio %i gen %i last_gc %i mark %llu gc_gen %i", buf, PTR_BUCKET_NR(b->c, k, i), atomic_read(&g->pin), g->prio, g->gen, g->last_gc, GC_MARK(g), g->gc_gen); return true; diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c index 72cd213f213f..5d5d031cf381 100644 --- a/drivers/md/bcache/request.c +++ b/drivers/md/bcache/request.c @@ -353,14 +353,14 @@ static void bch_data_insert_start(struct closure *cl) struct data_insert_op *op = container_of(cl, struct data_insert_op, cl); struct bio *bio = op->bio, *n; - if (op->bypass) - return bch_data_invalidate(cl); - if (atomic_sub_return(bio_sectors(bio), &op->c->sectors_to_gc) < 0) { set_gc_sectors(op->c); wake_up_gc(op->c); } + if (op->bypass) + return bch_data_invalidate(cl); + /* * Journal writes are marked REQ_FLUSH; if the original write was a * flush, it'll wait on the journal write. diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c index c6ab69333a6d..d8458d477a12 100644 --- a/drivers/md/bcache/sysfs.c +++ b/drivers/md/bcache/sysfs.c @@ -416,7 +416,7 @@ static int btree_bset_stats(struct btree_op *b_op, struct btree *b) return MAP_CONTINUE; } -int bch_bset_print_stats(struct cache_set *c, char *buf) +static int bch_bset_print_stats(struct cache_set *c, char *buf) { struct bset_stats_op op; int ret; diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index ffd472e015ca..1af70145fab9 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -289,6 +289,7 @@ struct per_bio_data { bool tick:1; unsigned req_nr:2; struct dm_deferred_entry *all_io_entry; + struct dm_hook_info hook_info; /* * writethrough fields. These MUST remain at the end of this @@ -297,7 +298,6 @@ struct per_bio_data { */ struct cache *cache; dm_cblock_t cblock; - struct dm_hook_info hook_info; struct dm_bio_details bio_details; }; @@ -671,15 +671,16 @@ static void remap_to_cache(struct cache *cache, struct bio *bio, dm_cblock_t cblock) { sector_t bi_sector = bio->bi_iter.bi_sector; + sector_t block = from_cblock(cblock); bio->bi_bdev = cache->cache_dev->bdev; if (!block_size_is_power_of_two(cache)) bio->bi_iter.bi_sector = - (from_cblock(cblock) * cache->sectors_per_block) + + (block * cache->sectors_per_block) + sector_div(bi_sector, cache->sectors_per_block); else bio->bi_iter.bi_sector = - (from_cblock(cblock) << cache->sectors_per_block_shift) | + (block << cache->sectors_per_block_shift) | (bi_sector & (cache->sectors_per_block - 1)); } @@ -1010,13 +1011,15 @@ static void overwrite_endio(struct bio *bio, int err) struct per_bio_data *pb = get_per_bio_data(bio, pb_data_size); unsigned long flags; + dm_unhook_bio(&pb->hook_info, bio); + if (err) mg->err = true; + mg->requeue_holder = false; + spin_lock_irqsave(&cache->lock, flags); list_add_tail(&mg->list, &cache->completed_migrations); - dm_unhook_bio(&pb->hook_info, bio); - mg->requeue_holder = false; spin_unlock_irqrestore(&cache->lock, flags); wake_worker(cache); diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c index b2b8a10e8427..3842ac738f98 100644 --- a/drivers/md/dm-io.c +++ b/drivers/md/dm-io.c @@ -201,29 +201,28 @@ static void list_dp_init(struct dpages *dp, struct page_list *pl, unsigned offse /* * Functions for getting the pages from a bvec. */ -static void bio_get_page(struct dpages *dp, - struct page **p, unsigned long *len, unsigned *offset) +static void bio_get_page(struct dpages *dp, struct page **p, + unsigned long *len, unsigned *offset) { - struct bio *bio = dp->context_ptr; - struct bio_vec bvec = bio_iovec(bio); - *p = bvec.bv_page; - *len = bvec.bv_len; - *offset = bvec.bv_offset; + struct bio_vec *bvec = dp->context_ptr; + *p = bvec->bv_page; + *len = bvec->bv_len - dp->context_u; + *offset = bvec->bv_offset + dp->context_u; } static void bio_next_page(struct dpages *dp) { - struct bio *bio = dp->context_ptr; - struct bio_vec bvec = bio_iovec(bio); - - bio_advance(bio, bvec.bv_len); + struct bio_vec *bvec = dp->context_ptr; + dp->context_ptr = bvec + 1; + dp->context_u = 0; } static void bio_dp_init(struct dpages *dp, struct bio *bio) { dp->get_page = bio_get_page; dp->next_page = bio_next_page; - dp->context_ptr = bio; + dp->context_ptr = __bvec_iter_bvec(bio->bi_io_vec, bio->bi_iter); + dp->context_u = bio->bi_iter.bi_bvec_done; } /* diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index 6eb9dc9ef8f3..422a9fdeb53e 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -1626,8 +1626,11 @@ static int multipath_ioctl(struct dm_target *ti, unsigned int cmd, /* * Only pass ioctls through if the device sizes match exactly. */ - if (!r && ti->len != i_size_read(bdev->bd_inode) >> SECTOR_SHIFT) - r = scsi_verify_blk_ioctl(NULL, cmd); + if (!bdev || ti->len != i_size_read(bdev->bd_inode) >> SECTOR_SHIFT) { + int err = scsi_verify_blk_ioctl(NULL, cmd); + if (err) + r = err; + } if (r == -ENOTCONN && !fatal_signal_pending(current)) queue_work(kmultipathd, &m->process_queued_ios); diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c index f284e0bfb25f..7dfdb5c746d6 100644 --- a/drivers/md/dm-raid1.c +++ b/drivers/md/dm-raid1.c @@ -1244,6 +1244,9 @@ static int mirror_end_io(struct dm_target *ti, struct bio *bio, int error) dm_bio_restore(bd, bio); bio_record->details.bi_bdev = NULL; + + atomic_inc(&bio->bi_remaining); + queue_bio(ms, bio, rw); return DM_ENDIO_INCOMPLETE; } diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c index 7da347665552..baa87ff12816 100644 --- a/drivers/md/dm-thin-metadata.c +++ b/drivers/md/dm-thin-metadata.c @@ -483,7 +483,7 @@ static int __write_initial_superblock(struct dm_pool_metadata *pmd) disk_super->data_mapping_root = cpu_to_le64(pmd->root); disk_super->device_details_root = cpu_to_le64(pmd->details_root); - disk_super->metadata_block_size = cpu_to_le32(THIN_METADATA_BLOCK_SIZE >> SECTOR_SHIFT); + disk_super->metadata_block_size = cpu_to_le32(THIN_METADATA_BLOCK_SIZE); disk_super->metadata_nr_blocks = cpu_to_le64(bdev_size >> SECTOR_TO_BLOCK_SHIFT); disk_super->data_block_size = cpu_to_le32(pmd->data_block_size); @@ -651,7 +651,7 @@ static int __create_persistent_data_objects(struct dm_pool_metadata *pmd, bool f { int r; - pmd->bm = dm_block_manager_create(pmd->bdev, THIN_METADATA_BLOCK_SIZE, + pmd->bm = dm_block_manager_create(pmd->bdev, THIN_METADATA_BLOCK_SIZE << SECTOR_SHIFT, THIN_METADATA_CACHE_SIZE, THIN_MAX_CONCURRENT_LOCKS); if (IS_ERR(pmd->bm)) { @@ -1489,6 +1489,23 @@ bool dm_thin_changed_this_transaction(struct dm_thin_device *td) return r; } +bool dm_pool_changed_this_transaction(struct dm_pool_metadata *pmd) +{ + bool r = false; + struct dm_thin_device *td, *tmp; + + down_read(&pmd->root_lock); + list_for_each_entry_safe(td, tmp, &pmd->thin_devices, list) { + if (td->changed) { + r = td->changed; + break; + } + } + up_read(&pmd->root_lock); + + return r; +} + bool dm_thin_aborted_changes(struct dm_thin_device *td) { bool r; diff --git a/drivers/md/dm-thin-metadata.h b/drivers/md/dm-thin-metadata.h index 9a368567632f..82ea384d36ff 100644 --- a/drivers/md/dm-thin-metadata.h +++ b/drivers/md/dm-thin-metadata.h @@ -9,16 +9,14 @@ #include "persistent-data/dm-block-manager.h" #include "persistent-data/dm-space-map.h" +#include "persistent-data/dm-space-map-metadata.h" -#define THIN_METADATA_BLOCK_SIZE 4096 +#define THIN_METADATA_BLOCK_SIZE DM_SM_METADATA_BLOCK_SIZE /* * The metadata device is currently limited in size. - * - * We have one block of index, which can hold 255 index entries. Each - * index entry contains allocation info about 16k metadata blocks. */ -#define THIN_METADATA_MAX_SECTORS (255 * (1 << 14) * (THIN_METADATA_BLOCK_SIZE / (1 << SECTOR_SHIFT))) +#define THIN_METADATA_MAX_SECTORS DM_SM_METADATA_MAX_SECTORS /* * A metadata device larger than 16GB triggers a warning. @@ -161,6 +159,8 @@ int dm_thin_remove_block(struct dm_thin_device *td, dm_block_t block); */ bool dm_thin_changed_this_transaction(struct dm_thin_device *td); +bool dm_pool_changed_this_transaction(struct dm_pool_metadata *pmd); + bool dm_thin_aborted_changes(struct dm_thin_device *td); int dm_thin_get_highest_mapped_block(struct dm_thin_device *td, diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index faaf944597ab..7e84baccf0ad 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -1357,7 +1357,8 @@ static void process_deferred_bios(struct pool *pool) bio_list_init(&pool->deferred_flush_bios); spin_unlock_irqrestore(&pool->lock, flags); - if (bio_list_empty(&bios) && !need_commit_due_to_time(pool)) + if (bio_list_empty(&bios) && + !(dm_pool_changed_this_transaction(pool->pmd) && need_commit_due_to_time(pool))) return; if (commit(pool)) { @@ -1999,16 +2000,27 @@ static void metadata_low_callback(void *context) dm_table_event(pool->ti->table); } -static sector_t get_metadata_dev_size(struct block_device *bdev) +static sector_t get_dev_size(struct block_device *bdev) +{ + return i_size_read(bdev->bd_inode) >> SECTOR_SHIFT; +} + +static void warn_if_metadata_device_too_big(struct block_device *bdev) { - sector_t metadata_dev_size = i_size_read(bdev->bd_inode) >> SECTOR_SHIFT; + sector_t metadata_dev_size = get_dev_size(bdev); char buffer[BDEVNAME_SIZE]; - if (metadata_dev_size > THIN_METADATA_MAX_SECTORS_WARNING) { + if (metadata_dev_size > THIN_METADATA_MAX_SECTORS_WARNING) DMWARN("Metadata device %s is larger than %u sectors: excess space will not be used.", bdevname(bdev, buffer), THIN_METADATA_MAX_SECTORS); - metadata_dev_size = THIN_METADATA_MAX_SECTORS_WARNING; - } +} + +static sector_t get_metadata_dev_size(struct block_device *bdev) +{ + sector_t metadata_dev_size = get_dev_size(bdev); + + if (metadata_dev_size > THIN_METADATA_MAX_SECTORS) + metadata_dev_size = THIN_METADATA_MAX_SECTORS; return metadata_dev_size; } @@ -2017,7 +2029,7 @@ static dm_block_t get_metadata_dev_size_in_blocks(struct block_device *bdev) { sector_t metadata_dev_size = get_metadata_dev_size(bdev); - sector_div(metadata_dev_size, THIN_METADATA_BLOCK_SIZE >> SECTOR_SHIFT); + sector_div(metadata_dev_size, THIN_METADATA_BLOCK_SIZE); return metadata_dev_size; } @@ -2095,12 +2107,7 @@ static int pool_ctr(struct dm_target *ti, unsigned argc, char **argv) ti->error = "Error opening metadata block device"; goto out_unlock; } - - /* - * Run for the side-effect of possibly issuing a warning if the - * device is too big. - */ - (void) get_metadata_dev_size(metadata_dev->bdev); + warn_if_metadata_device_too_big(metadata_dev->bdev); r = dm_get_device(ti, argv[1], FMODE_READ | FMODE_WRITE, &data_dev); if (r) { @@ -2287,6 +2294,7 @@ static int maybe_resize_metadata_dev(struct dm_target *ti, bool *need_commit) return -EINVAL; } else if (metadata_dev_size > sb_metadata_dev_size) { + warn_if_metadata_device_too_big(pool->md_dev); DMINFO("%s: growing the metadata device from %llu to %llu blocks", dm_device_name(pool->pool_md), sb_metadata_dev_size, metadata_dev_size); @@ -2894,6 +2902,7 @@ static int thin_ctr(struct dm_target *ti, unsigned argc, char **argv) if (get_pool_mode(tc->pool) == PM_FAIL) { ti->error = "Couldn't open thin device, Pool is in fail mode"; + r = -EINVAL; goto bad_thin_open; } @@ -2905,7 +2914,7 @@ static int thin_ctr(struct dm_target *ti, unsigned argc, char **argv) r = dm_set_target_max_io_len(ti, tc->pool->sectors_per_block); if (r) - goto bad_thin_open; + goto bad_target_max_io_len; ti->num_flush_bios = 1; ti->flush_supported = true; @@ -2926,6 +2935,8 @@ static int thin_ctr(struct dm_target *ti, unsigned argc, char **argv) return 0; +bad_target_max_io_len: + dm_pool_close_thin_device(tc->td); bad_thin_open: __pool_dec(tc->pool); bad_pool_lookup: diff --git a/drivers/md/persistent-data/dm-space-map-metadata.c b/drivers/md/persistent-data/dm-space-map-metadata.c index 536782e3bcb7..e9bdd462f4f5 100644 --- a/drivers/md/persistent-data/dm-space-map-metadata.c +++ b/drivers/md/persistent-data/dm-space-map-metadata.c @@ -680,6 +680,8 @@ int dm_sm_metadata_create(struct dm_space_map *sm, if (r) return r; + if (nr_blocks > DM_SM_METADATA_MAX_BLOCKS) + nr_blocks = DM_SM_METADATA_MAX_BLOCKS; r = sm_ll_extend(&smm->ll, nr_blocks); if (r) return r; diff --git a/drivers/md/persistent-data/dm-space-map-metadata.h b/drivers/md/persistent-data/dm-space-map-metadata.h index 39bba0801cf2..64df923974d8 100644 --- a/drivers/md/persistent-data/dm-space-map-metadata.h +++ b/drivers/md/persistent-data/dm-space-map-metadata.h @@ -9,6 +9,17 @@ #include "dm-transaction-manager.h" +#define DM_SM_METADATA_BLOCK_SIZE (4096 >> SECTOR_SHIFT) + +/* + * The metadata device is currently limited in size. + * + * We have one block of index, which can hold 255 index entries. Each + * index entry contains allocation info about ~16k metadata blocks. + */ +#define DM_SM_METADATA_MAX_BLOCKS (255 * ((1 << 14) - 64)) +#define DM_SM_METADATA_MAX_SECTORS (DM_SM_METADATA_MAX_BLOCKS * DM_SM_METADATA_BLOCK_SIZE) + /* * Unfortunately we have to use two-phase construction due to the cycle * between the tm and sm. diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index fd3a2a14b587..4a6ca1cb2e78 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -1953,11 +1953,15 @@ static int process_checks(struct r1bio *r1_bio) for (i = 0; i < conf->raid_disks * 2; i++) { int j; int size; + int uptodate; struct bio *b = r1_bio->bios[i]; if (b->bi_end_io != end_sync_read) continue; - /* fixup the bio for reuse */ + /* fixup the bio for reuse, but preserve BIO_UPTODATE */ + uptodate = test_bit(BIO_UPTODATE, &b->bi_flags); bio_reset(b); + if (!uptodate) + clear_bit(BIO_UPTODATE, &b->bi_flags); b->bi_vcnt = vcnt; b->bi_iter.bi_size = r1_bio->sectors << 9; b->bi_iter.bi_sector = r1_bio->sector + @@ -1990,11 +1994,14 @@ static int process_checks(struct r1bio *r1_bio) int j; struct bio *pbio = r1_bio->bios[primary]; struct bio *sbio = r1_bio->bios[i]; + int uptodate = test_bit(BIO_UPTODATE, &sbio->bi_flags); if (sbio->bi_end_io != end_sync_read) continue; + /* Now we can 'fixup' the BIO_UPTODATE flag */ + set_bit(BIO_UPTODATE, &sbio->bi_flags); - if (test_bit(BIO_UPTODATE, &sbio->bi_flags)) { + if (uptodate) { for (j = vcnt; j-- ; ) { struct page *p, *s; p = pbio->bi_io_vec[j].bv_page; @@ -2009,7 +2016,7 @@ static int process_checks(struct r1bio *r1_bio) if (j >= 0) atomic64_add(r1_bio->sectors, &mddev->resync_mismatches); if (j < 0 || (test_bit(MD_RECOVERY_CHECK, &mddev->recovery) - && test_bit(BIO_UPTODATE, &sbio->bi_flags))) { + && uptodate)) { /* No need to write to this device. */ sbio->bi_end_io = NULL; rdev_dec_pending(conf->mirrors[i].rdev, mddev); diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index f1feadeb7bb2..16f5c21963db 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -5514,23 +5514,43 @@ raid5_size(struct mddev *mddev, sector_t sectors, int raid_disks) return sectors * (raid_disks - conf->max_degraded); } +static void free_scratch_buffer(struct r5conf *conf, struct raid5_percpu *percpu) +{ + safe_put_page(percpu->spare_page); + kfree(percpu->scribble); + percpu->spare_page = NULL; + percpu->scribble = NULL; +} + +static int alloc_scratch_buffer(struct r5conf *conf, struct raid5_percpu *percpu) +{ + if (conf->level == 6 && !percpu->spare_page) + percpu->spare_page = alloc_page(GFP_KERNEL); + if (!percpu->scribble) + percpu->scribble = kmalloc(conf->scribble_len, GFP_KERNEL); + + if (!percpu->scribble || (conf->level == 6 && !percpu->spare_page)) { + free_scratch_buffer(conf, percpu); + return -ENOMEM; + } + + return 0; +} + static void raid5_free_percpu(struct r5conf *conf) { - struct raid5_percpu *percpu; unsigned long cpu; if (!conf->percpu) return; - get_online_cpus(); - for_each_possible_cpu(cpu) { - percpu = per_cpu_ptr(conf->percpu, cpu); - safe_put_page(percpu->spare_page); - kfree(percpu->scribble); - } #ifdef CONFIG_HOTPLUG_CPU unregister_cpu_notifier(&conf->cpu_notify); #endif + + get_online_cpus(); + for_each_possible_cpu(cpu) + free_scratch_buffer(conf, per_cpu_ptr(conf->percpu, cpu)); put_online_cpus(); free_percpu(conf->percpu); @@ -5557,15 +5577,7 @@ static int raid456_cpu_notify(struct notifier_block *nfb, unsigned long action, switch (action) { case CPU_UP_PREPARE: case CPU_UP_PREPARE_FROZEN: - if (conf->level == 6 && !percpu->spare_page) - percpu->spare_page = alloc_page(GFP_KERNEL); - if (!percpu->scribble) - percpu->scribble = kmalloc(conf->scribble_len, GFP_KERNEL); - - if (!percpu->scribble || - (conf->level == 6 && !percpu->spare_page)) { - safe_put_page(percpu->spare_page); - kfree(percpu->scribble); + if (alloc_scratch_buffer(conf, percpu)) { pr_err("%s: failed memory allocation for cpu%ld\n", __func__, cpu); return notifier_from_errno(-ENOMEM); @@ -5573,10 +5585,7 @@ static int raid456_cpu_notify(struct notifier_block *nfb, unsigned long action, break; case CPU_DEAD: case CPU_DEAD_FROZEN: - safe_put_page(percpu->spare_page); - kfree(percpu->scribble); - percpu->spare_page = NULL; - percpu->scribble = NULL; + free_scratch_buffer(conf, per_cpu_ptr(conf->percpu, cpu)); break; default: break; @@ -5588,40 +5597,29 @@ static int raid456_cpu_notify(struct notifier_block *nfb, unsigned long action, static int raid5_alloc_percpu(struct r5conf *conf) { unsigned long cpu; - struct page *spare_page; - struct raid5_percpu __percpu *allcpus; - void *scribble; - int err; + int err = 0; - allcpus = alloc_percpu(struct raid5_percpu); - if (!allcpus) + conf->percpu = alloc_percpu(struct raid5_percpu); + if (!conf->percpu) return -ENOMEM; - conf->percpu = allcpus; + +#ifdef CONFIG_HOTPLUG_CPU + conf->cpu_notify.notifier_call = raid456_cpu_notify; + conf->cpu_notify.priority = 0; + err = register_cpu_notifier(&conf->cpu_notify); + if (err) + return err; +#endif get_online_cpus(); - err = 0; for_each_present_cpu(cpu) { - if (conf->level == 6) { - spare_page = alloc_page(GFP_KERNEL); - if (!spare_page) { - err = -ENOMEM; - break; - } - per_cpu_ptr(conf->percpu, cpu)->spare_page = spare_page; - } - scribble = kmalloc(conf->scribble_len, GFP_KERNEL); - if (!scribble) { - err = -ENOMEM; + err = alloc_scratch_buffer(conf, per_cpu_ptr(conf->percpu, cpu)); + if (err) { + pr_err("%s: failed memory allocation for cpu%ld\n", + __func__, cpu); break; } - per_cpu_ptr(conf->percpu, cpu)->scribble = scribble; } -#ifdef CONFIG_HOTPLUG_CPU - conf->cpu_notify.notifier_call = raid456_cpu_notify; - conf->cpu_notify.priority = 0; - if (err == 0) - err = register_cpu_notifier(&conf->cpu_notify); -#endif put_online_cpus(); return err; diff --git a/drivers/message/i2o/i2o_config.c b/drivers/message/i2o/i2o_config.c index a60c188c2bd9..04bd3b6de401 100644 --- a/drivers/message/i2o/i2o_config.c +++ b/drivers/message/i2o/i2o_config.c @@ -754,19 +754,19 @@ static long i2o_cfg_compat_ioctl(struct file *file, unsigned cmd, unsigned long arg) { int ret; - mutex_lock(&i2o_cfg_mutex); switch (cmd) { case I2OGETIOPS: ret = i2o_cfg_ioctl(file, cmd, arg); break; case I2OPASSTHRU32: + mutex_lock(&i2o_cfg_mutex); ret = i2o_cfg_passthru32(file, cmd, arg); + mutex_unlock(&i2o_cfg_mutex); break; default: ret = -ENOIOCTLCMD; break; } - mutex_unlock(&i2o_cfg_mutex); return ret; } diff --git a/drivers/mfd/da9055-i2c.c b/drivers/mfd/da9055-i2c.c index 13af7e50021e..8103e4362132 100644 --- a/drivers/mfd/da9055-i2c.c +++ b/drivers/mfd/da9055-i2c.c @@ -53,17 +53,25 @@ static int da9055_i2c_remove(struct i2c_client *i2c) return 0; } +/* + * DO NOT change the device Ids. The naming is intentionally specific as both + * the PMIC and CODEC parts of this chip are instantiated separately as I2C + * devices (both have configurable I2C addresses, and are to all intents and + * purposes separate). As a result there are specific DA9055 ids for PMIC + * and CODEC, which must be different to operate together. + */ static struct i2c_device_id da9055_i2c_id[] = { - {"da9055", 0}, + {"da9055-pmic", 0}, { } }; +MODULE_DEVICE_TABLE(i2c, da9055_i2c_id); static struct i2c_driver da9055_i2c_driver = { .probe = da9055_i2c_probe, .remove = da9055_i2c_remove, .id_table = da9055_i2c_id, .driver = { - .name = "da9055", + .name = "da9055-pmic", .owner = THIS_MODULE, }, }; diff --git a/drivers/mfd/max14577.c b/drivers/mfd/max14577.c index ac514fb2b877..71aa14a6bfbb 100644 --- a/drivers/mfd/max14577.c +++ b/drivers/mfd/max14577.c @@ -173,6 +173,7 @@ static const struct i2c_device_id max14577_i2c_id[] = { }; MODULE_DEVICE_TABLE(i2c, max14577_i2c_id); +#ifdef CONFIG_PM_SLEEP static int max14577_suspend(struct device *dev) { struct i2c_client *i2c = container_of(dev, struct i2c_client, dev); @@ -208,6 +209,7 @@ static int max14577_resume(struct device *dev) return 0; } +#endif /* CONFIG_PM_SLEEP */ static struct of_device_id max14577_dt_match[] = { { .compatible = "maxim,max14577", }, diff --git a/drivers/mfd/max8997.c b/drivers/mfd/max8997.c index be88a3bf7b85..5adede0fb04c 100644 --- a/drivers/mfd/max8997.c +++ b/drivers/mfd/max8997.c @@ -164,15 +164,15 @@ static struct max8997_platform_data *max8997_i2c_parse_dt_pdata( return pd; } -static inline int max8997_i2c_get_driver_data(struct i2c_client *i2c, +static inline unsigned long max8997_i2c_get_driver_data(struct i2c_client *i2c, const struct i2c_device_id *id) { if (IS_ENABLED(CONFIG_OF) && i2c->dev.of_node) { const struct of_device_id *match; match = of_match_node(max8997_pmic_dt_match, i2c->dev.of_node); - return (int)match->data; + return (unsigned long)match->data; } - return (int)id->driver_data; + return id->driver_data; } static int max8997_i2c_probe(struct i2c_client *i2c, diff --git a/drivers/mfd/max8998.c b/drivers/mfd/max8998.c index 612ca404e150..5d5e186b5d8b 100644 --- a/drivers/mfd/max8998.c +++ b/drivers/mfd/max8998.c @@ -169,16 +169,16 @@ static struct max8998_platform_data *max8998_i2c_parse_dt_pdata( return pd; } -static inline int max8998_i2c_get_driver_data(struct i2c_client *i2c, +static inline unsigned long max8998_i2c_get_driver_data(struct i2c_client *i2c, const struct i2c_device_id *id) { if (IS_ENABLED(CONFIG_OF) && i2c->dev.of_node) { const struct of_device_id *match; match = of_match_node(max8998_dt_match, i2c->dev.of_node); - return (int)(long)match->data; + return (unsigned long)match->data; } - return (int)id->driver_data; + return id->driver_data; } static int max8998_i2c_probe(struct i2c_client *i2c, diff --git a/drivers/mfd/sec-core.c b/drivers/mfd/sec-core.c index a139798b8065..714e2135210e 100644 --- a/drivers/mfd/sec-core.c +++ b/drivers/mfd/sec-core.c @@ -315,6 +315,7 @@ static int sec_pmic_remove(struct i2c_client *i2c) return 0; } +#ifdef CONFIG_PM_SLEEP static int sec_pmic_suspend(struct device *dev) { struct i2c_client *i2c = container_of(dev, struct i2c_client, dev); @@ -349,6 +350,7 @@ static int sec_pmic_resume(struct device *dev) return 0; } +#endif /* CONFIG_PM_SLEEP */ static SIMPLE_DEV_PM_OPS(sec_pmic_pm_ops, sec_pmic_suspend, sec_pmic_resume); diff --git a/drivers/mfd/tps65217.c b/drivers/mfd/tps65217.c index 966cf65c5c36..3cc4c7084b92 100644 --- a/drivers/mfd/tps65217.c +++ b/drivers/mfd/tps65217.c @@ -158,7 +158,7 @@ static int tps65217_probe(struct i2c_client *client, { struct tps65217 *tps; unsigned int version; - unsigned int chip_id = ids->driver_data; + unsigned long chip_id = ids->driver_data; const struct of_device_id *match; bool status_off = false; int ret; @@ -170,7 +170,7 @@ static int tps65217_probe(struct i2c_client *client, "Failed to find matching dt id\n"); return -EINVAL; } - chip_id = (unsigned int)(unsigned long)match->data; + chip_id = (unsigned long)match->data; status_off = of_property_read_bool(client->dev.of_node, "ti,pmic-shutdown-controller"); } diff --git a/drivers/mfd/wm8994-core.c b/drivers/mfd/wm8994-core.c index ba04f1bc70eb..e6fab94e2c8a 100644 --- a/drivers/mfd/wm8994-core.c +++ b/drivers/mfd/wm8994-core.c @@ -636,7 +636,7 @@ static int wm8994_i2c_probe(struct i2c_client *i2c, if (i2c->dev.of_node) { of_id = of_match_device(wm8994_of_match, &i2c->dev); if (of_id) - wm8994->type = (int)of_id->data; + wm8994->type = (enum wm8994_type)of_id->data; } else { wm8994->type = id->driver_data; } diff --git a/drivers/misc/genwqe/card_dev.c b/drivers/misc/genwqe/card_dev.c index 8f8a6b327cdb..2c2c9cc75231 100644 --- a/drivers/misc/genwqe/card_dev.c +++ b/drivers/misc/genwqe/card_dev.c @@ -787,6 +787,7 @@ static int genwqe_pin_mem(struct genwqe_file *cfile, struct genwqe_mem *m) if (rc != 0) { dev_err(&pci_dev->dev, "[%s] genwqe_user_vmap rc=%d\n", __func__, rc); + kfree(dma_map); return rc; } diff --git a/drivers/misc/mei/client.c b/drivers/misc/mei/client.c index 1ee2b9492a82..89a557972d1b 100644 --- a/drivers/misc/mei/client.c +++ b/drivers/misc/mei/client.c @@ -666,7 +666,6 @@ int mei_cl_read_start(struct mei_cl *cl, size_t length) goto err; cb->fop_type = MEI_FOP_READ; - cl->read_cb = cb; if (dev->hbuf_is_ready) { dev->hbuf_is_ready = false; if (mei_hbm_cl_flow_control_req(dev, cl)) { @@ -678,6 +677,9 @@ int mei_cl_read_start(struct mei_cl *cl, size_t length) } else { list_add_tail(&cb->list, &dev->ctrl_wr_list.list); } + + cl->read_cb = cb; + return rets; err: mei_io_cb_free(cb); @@ -908,7 +910,6 @@ void mei_cl_all_disconnect(struct mei_device *dev) list_for_each_entry_safe(cl, next, &dev->file_list, link) { cl->state = MEI_FILE_DISCONNECTED; cl->mei_flow_ctrl_creds = 0; - cl->read_cb = NULL; cl->timer_count = 0; } } @@ -942,8 +943,16 @@ void mei_cl_all_wakeup(struct mei_device *dev) void mei_cl_all_write_clear(struct mei_device *dev) { struct mei_cl_cb *cb, *next; + struct list_head *list; + + list = &dev->write_list.list; + list_for_each_entry_safe(cb, next, list, list) { + list_del(&cb->list); + mei_io_cb_free(cb); + } - list_for_each_entry_safe(cb, next, &dev->write_list.list, list) { + list = &dev->write_waiting_list.list; + list_for_each_entry_safe(cb, next, list, list) { list_del(&cb->list); mei_io_cb_free(cb); } diff --git a/drivers/misc/mic/host/mic_virtio.c b/drivers/misc/mic/host/mic_virtio.c index 752ff873f891..7e1ef0ebbb80 100644 --- a/drivers/misc/mic/host/mic_virtio.c +++ b/drivers/misc/mic/host/mic_virtio.c @@ -156,7 +156,8 @@ static int mic_vringh_copy(struct mic_vdev *mvdev, struct vringh_kiov *iov, static int _mic_virtio_copy(struct mic_vdev *mvdev, struct mic_copy_desc *copy) { - int ret = 0, iovcnt = copy->iovcnt; + int ret = 0; + u32 iovcnt = copy->iovcnt; struct iovec iov; struct iovec __user *u_iov = copy->iov; void __user *ubuf = NULL; diff --git a/drivers/misc/sgi-gru/grukdump.c b/drivers/misc/sgi-gru/grukdump.c index 9b2062d17327..2bef3f76032a 100644 --- a/drivers/misc/sgi-gru/grukdump.c +++ b/drivers/misc/sgi-gru/grukdump.c @@ -139,8 +139,11 @@ static int gru_dump_context(struct gru_state *gru, int ctxnum, ubuf += sizeof(hdr); ubufcch = ubuf; - if (gru_user_copy_handle(&ubuf, cch)) - goto fail; + if (gru_user_copy_handle(&ubuf, cch)) { + if (cch_locked) + unlock_cch_handle(cch); + return -EFAULT; + } if (cch_locked) ubufcch->delresp = 0; bytes = sizeof(hdr) + GRU_CACHE_LINE_BYTES; @@ -179,10 +182,6 @@ static int gru_dump_context(struct gru_state *gru, int ctxnum, ret = -EFAULT; return ret ? ret : bytes; - -fail: - unlock_cch_handle(cch); - return -EFAULT; } int gru_dump_chiplet_request(unsigned long arg) diff --git a/drivers/mmc/card/queue.c b/drivers/mmc/card/queue.c index 357bbc54fe4b..3e049c13429c 100644 --- a/drivers/mmc/card/queue.c +++ b/drivers/mmc/card/queue.c @@ -197,7 +197,7 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card, struct mmc_queue_req *mqrq_prev = &mq->mqrq[1]; if (mmc_dev(host)->dma_mask && *mmc_dev(host)->dma_mask) - limit = dma_max_pfn(mmc_dev(host)) << PAGE_SHIFT; + limit = (u64)dma_max_pfn(mmc_dev(host)) << PAGE_SHIFT; mq->card = card; mq->queue = blk_init_queue(mmc_request_fn, lock); diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c index 59eba5d2c685..9715a7ba164a 100644 --- a/drivers/mtd/nand/nand_base.c +++ b/drivers/mtd/nand/nand_base.c @@ -1584,7 +1584,7 @@ read_retry: } if (mtd->ecc_stats.failed - ecc_failures) { - if (retry_mode + 1 <= chip->read_retries) { + if (retry_mode + 1 < chip->read_retries) { retry_mode++; ret = nand_setup_read_retry(mtd, retry_mode); diff --git a/drivers/mtd/nand/omap2.c b/drivers/mtd/nand/omap2.c index ef4190a02b7b..bf642ceef681 100644 --- a/drivers/mtd/nand/omap2.c +++ b/drivers/mtd/nand/omap2.c @@ -1633,6 +1633,7 @@ static int omap_nand_probe(struct platform_device *pdev) int i; dma_cap_mask_t mask; unsigned sig; + unsigned oob_index; struct resource *res; struct mtd_part_parser_data ppdata = {}; @@ -1826,11 +1827,14 @@ static int omap_nand_probe(struct platform_device *pdev) (mtd->writesize / nand_chip->ecc.size); if (nand_chip->options & NAND_BUSWIDTH_16) - ecclayout->eccpos[0] = BADBLOCK_MARKER_LENGTH; + oob_index = BADBLOCK_MARKER_LENGTH; else - ecclayout->eccpos[0] = 1; - ecclayout->oobfree->offset = ecclayout->eccpos[0] + - ecclayout->eccbytes; + oob_index = 1; + for (i = 0; i < ecclayout->eccbytes; i++, oob_index++) + ecclayout->eccpos[i] = oob_index; + /* no reserved-marker in ecclayout for this ecc-scheme */ + ecclayout->oobfree->offset = + ecclayout->eccpos[ecclayout->eccbytes - 1] + 1; break; case OMAP_ECC_BCH4_CODE_HW_DETECTION_SW: @@ -1847,9 +1851,15 @@ static int omap_nand_probe(struct platform_device *pdev) ecclayout->eccbytes = nand_chip->ecc.bytes * (mtd->writesize / nand_chip->ecc.size); - ecclayout->eccpos[0] = BADBLOCK_MARKER_LENGTH; - ecclayout->oobfree->offset = ecclayout->eccpos[0] + - ecclayout->eccbytes; + oob_index = BADBLOCK_MARKER_LENGTH; + for (i = 0; i < ecclayout->eccbytes; i++, oob_index++) { + ecclayout->eccpos[i] = oob_index; + if (((i + 1) % nand_chip->ecc.bytes) == 0) + oob_index++; + } + /* include reserved-marker in ecclayout->oobfree calculation */ + ecclayout->oobfree->offset = 1 + + ecclayout->eccpos[ecclayout->eccbytes - 1] + 1; /* software bch library is used for locating errors */ nand_chip->ecc.priv = nand_bch_init(mtd, nand_chip->ecc.size, @@ -1883,9 +1893,12 @@ static int omap_nand_probe(struct platform_device *pdev) ecclayout->eccbytes = nand_chip->ecc.bytes * (mtd->writesize / nand_chip->ecc.size); - ecclayout->eccpos[0] = BADBLOCK_MARKER_LENGTH; - ecclayout->oobfree->offset = ecclayout->eccpos[0] + - ecclayout->eccbytes; + oob_index = BADBLOCK_MARKER_LENGTH; + for (i = 0; i < ecclayout->eccbytes; i++, oob_index++) + ecclayout->eccpos[i] = oob_index; + /* reserved marker already included in ecclayout->eccbytes */ + ecclayout->oobfree->offset = + ecclayout->eccpos[ecclayout->eccbytes - 1] + 1; /* This ECC scheme requires ELM H/W block */ if (is_elm_present(info, pdata->elm_of_node, BCH4_ECC) < 0) { pr_err("nand: error: could not initialize ELM\n"); @@ -1913,9 +1926,15 @@ static int omap_nand_probe(struct platform_device *pdev) ecclayout->eccbytes = nand_chip->ecc.bytes * (mtd->writesize / nand_chip->ecc.size); - ecclayout->eccpos[0] = BADBLOCK_MARKER_LENGTH; - ecclayout->oobfree->offset = ecclayout->eccpos[0] + - ecclayout->eccbytes; + oob_index = BADBLOCK_MARKER_LENGTH; + for (i = 0; i < ecclayout->eccbytes; i++, oob_index++) { + ecclayout->eccpos[i] = oob_index; + if (((i + 1) % nand_chip->ecc.bytes) == 0) + oob_index++; + } + /* include reserved-marker in ecclayout->oobfree calculation */ + ecclayout->oobfree->offset = 1 + + ecclayout->eccpos[ecclayout->eccbytes - 1] + 1; /* software bch library is used for locating errors */ nand_chip->ecc.priv = nand_bch_init(mtd, nand_chip->ecc.size, @@ -1956,9 +1975,12 @@ static int omap_nand_probe(struct platform_device *pdev) ecclayout->eccbytes = nand_chip->ecc.bytes * (mtd->writesize / nand_chip->ecc.size); - ecclayout->eccpos[0] = BADBLOCK_MARKER_LENGTH; - ecclayout->oobfree->offset = ecclayout->eccpos[0] + - ecclayout->eccbytes; + oob_index = BADBLOCK_MARKER_LENGTH; + for (i = 0; i < ecclayout->eccbytes; i++, oob_index++) + ecclayout->eccpos[i] = oob_index; + /* reserved marker already included in ecclayout->eccbytes */ + ecclayout->oobfree->offset = + ecclayout->eccpos[ecclayout->eccbytes - 1] + 1; break; #else pr_err("nand: error: CONFIG_MTD_NAND_OMAP_BCH not enabled\n"); @@ -1972,11 +1994,8 @@ static int omap_nand_probe(struct platform_device *pdev) goto return_error; } - /* populate remaining ECC layout data */ - ecclayout->oobfree->length = mtd->oobsize - (BADBLOCK_MARKER_LENGTH + - ecclayout->eccbytes); - for (i = 1; i < ecclayout->eccbytes; i++) - ecclayout->eccpos[i] = ecclayout->eccpos[0] + i; + /* all OOB bytes from oobfree->offset till end off OOB are free */ + ecclayout->oobfree->length = mtd->oobsize - ecclayout->oobfree->offset; /* check if NAND device's OOB is enough to store ECC signatures */ if (mtd->oobsize < (ecclayout->eccbytes + BADBLOCK_MARKER_LENGTH)) { pr_err("not enough OOB bytes required = %d, available=%d\n", diff --git a/drivers/mtd/ubi/fastmap.c b/drivers/mtd/ubi/fastmap.c index ead861307b3c..c5dad652614d 100644 --- a/drivers/mtd/ubi/fastmap.c +++ b/drivers/mtd/ubi/fastmap.c @@ -463,8 +463,8 @@ static int scan_pool(struct ubi_device *ubi, struct ubi_attach_info *ai, } } if (found_orphan) { - kmem_cache_free(ai->aeb_slab_cache, tmp_aeb); list_del(&tmp_aeb->u.list); + kmem_cache_free(ai->aeb_slab_cache, tmp_aeb); } new_aeb = kmem_cache_alloc(ai->aeb_slab_cache, @@ -846,16 +846,16 @@ fail_bad: ret = UBI_BAD_FASTMAP; fail: list_for_each_entry_safe(tmp_aeb, _tmp_aeb, &used, u.list) { - kmem_cache_free(ai->aeb_slab_cache, tmp_aeb); list_del(&tmp_aeb->u.list); + kmem_cache_free(ai->aeb_slab_cache, tmp_aeb); } list_for_each_entry_safe(tmp_aeb, _tmp_aeb, &eba_orphans, u.list) { - kmem_cache_free(ai->aeb_slab_cache, tmp_aeb); list_del(&tmp_aeb->u.list); + kmem_cache_free(ai->aeb_slab_cache, tmp_aeb); } list_for_each_entry_safe(tmp_aeb, _tmp_aeb, &free, u.list) { - kmem_cache_free(ai->aeb_slab_cache, tmp_aeb); list_del(&tmp_aeb->u.list); + kmem_cache_free(ai->aeb_slab_cache, tmp_aeb); } return ret; diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index f342278539d5..494b888a6568 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -139,7 +139,7 @@ config MACVTAP This adds a specialized tap character device driver that is based on the MAC-VLAN network interface, called macvtap. A macvtap device can be added in the same way as a macvlan device, using 'type - macvlan', and then be accessed through the tap user space interface. + macvtap', and then be accessed through the tap user space interface. To compile this driver as a module, choose M here: the module will be called macvtap. diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c index cce1f1bf90b4..dee2a84a2929 100644 --- a/drivers/net/bonding/bond_3ad.c +++ b/drivers/net/bonding/bond_3ad.c @@ -181,7 +181,7 @@ static inline int __agg_has_partner(struct aggregator *agg) */ static inline void __disable_port(struct port *port) { - bond_set_slave_inactive_flags(port->slave); + bond_set_slave_inactive_flags(port->slave, BOND_SLAVE_NOTIFY_LATER); } /** @@ -193,7 +193,7 @@ static inline void __enable_port(struct port *port) struct slave *slave = port->slave; if ((slave->link == BOND_LINK_UP) && IS_UP(slave->dev)) - bond_set_slave_active_flags(slave); + bond_set_slave_active_flags(slave, BOND_SLAVE_NOTIFY_LATER); } /** @@ -768,11 +768,11 @@ static int ad_lacpdu_send(struct port *port) lacpdu_header = (struct lacpdu_header *)skb_put(skb, length); - memcpy(lacpdu_header->hdr.h_dest, lacpdu_mcast_addr, ETH_ALEN); + ether_addr_copy(lacpdu_header->hdr.h_dest, lacpdu_mcast_addr); /* Note: source address is set to be the member's PERMANENT address, * because we use it to identify loopback lacpdus in receive. */ - memcpy(lacpdu_header->hdr.h_source, slave->perm_hwaddr, ETH_ALEN); + ether_addr_copy(lacpdu_header->hdr.h_source, slave->perm_hwaddr); lacpdu_header->hdr.h_proto = PKT_TYPE_LACPDU; lacpdu_header->lacpdu = port->lacpdu; @@ -810,11 +810,11 @@ static int ad_marker_send(struct port *port, struct bond_marker *marker) marker_header = (struct bond_marker_header *)skb_put(skb, length); - memcpy(marker_header->hdr.h_dest, lacpdu_mcast_addr, ETH_ALEN); + ether_addr_copy(marker_header->hdr.h_dest, lacpdu_mcast_addr); /* Note: source address is set to be the member's PERMANENT address, * because we use it to identify loopback MARKERs in receive. */ - memcpy(marker_header->hdr.h_source, slave->perm_hwaddr, ETH_ALEN); + ether_addr_copy(marker_header->hdr.h_source, slave->perm_hwaddr); marker_header->hdr.h_proto = PKT_TYPE_LACPDU; marker_header->marker = *marker; @@ -1079,7 +1079,8 @@ static void ad_rx_machine(struct lacpdu *lacpdu, struct port *port) /* detect loopback situation */ if (MAC_ADDRESS_EQUAL(&(lacpdu->actor_system), &(port->actor_system))) { - pr_err("%s: An illegal loopback occurred on adapter (%s).\nCheck the configuration to verify that all adapters are connected to 802.3ad compliant switch ports\n", + pr_err("%s: An illegal loopback occurred on adapter (%s)\n" + "Check the configuration to verify that all adapters are connected to 802.3ad compliant switch ports\n", port->slave->bond->dev->name, port->slave->dev->name); return; @@ -1796,8 +1797,6 @@ void bond_3ad_initiate_agg_selection(struct bonding *bond, int timeout) BOND_AD_INFO(bond).agg_select_timer = timeout; } -static u16 aggregator_identifier; - /** * bond_3ad_initialize - initialize a bond's 802.3ad parameters and structures * @bond: bonding struct to work on @@ -1811,7 +1810,7 @@ void bond_3ad_initialize(struct bonding *bond, u16 tick_resolution) if (!MAC_ADDRESS_EQUAL(&(BOND_AD_INFO(bond).system.sys_mac_addr), bond->dev->dev_addr)) { - aggregator_identifier = 0; + BOND_AD_INFO(bond).aggregator_identifier = 0; BOND_AD_INFO(bond).system.sys_priority = 0xFFFF; BOND_AD_INFO(bond).system.sys_mac_addr = *((struct mac_addr *)bond->dev->dev_addr); @@ -1880,7 +1879,7 @@ void bond_3ad_bind_slave(struct slave *slave) ad_initialize_agg(aggregator); aggregator->aggregator_mac_address = *((struct mac_addr *)bond->dev->dev_addr); - aggregator->aggregator_identifier = (++aggregator_identifier); + aggregator->aggregator_identifier = ++BOND_AD_INFO(bond).aggregator_identifier; aggregator->slave = slave; aggregator->is_active = 0; aggregator->num_of_ports = 0; @@ -1950,7 +1949,7 @@ void bond_3ad_unbind_slave(struct slave *slave) * new aggregator */ if ((new_aggregator) && ((!new_aggregator->lag_ports) || ((new_aggregator->lag_ports == port) && !new_aggregator->lag_ports->next_port_in_aggregator))) { - pr_debug("Some port(s) related to LAG %d - replaceing with LAG %d\n", + pr_debug("Some port(s) related to LAG %d - replacing with LAG %d\n", aggregator->aggregator_identifier, new_aggregator->aggregator_identifier); @@ -2064,6 +2063,7 @@ void bond_3ad_state_machine_handler(struct work_struct *work) struct list_head *iter; struct slave *slave; struct port *port; + bool should_notify_rtnl = BOND_SLAVE_NOTIFY_LATER; read_lock(&bond->lock); rcu_read_lock(); @@ -2121,8 +2121,19 @@ void bond_3ad_state_machine_handler(struct work_struct *work) } re_arm: + bond_for_each_slave_rcu(bond, slave, iter) { + if (slave->should_notify) { + should_notify_rtnl = BOND_SLAVE_NOTIFY_NOW; + break; + } + } rcu_read_unlock(); read_unlock(&bond->lock); + + if (should_notify_rtnl && rtnl_trylock()) { + bond_slave_state_notify(bond); + rtnl_unlock(); + } queue_delayed_work(bond->wq, &bond->ad_work, ad_delta_in_ticks); } @@ -2300,9 +2311,9 @@ void bond_3ad_handle_link_change(struct slave *slave, char link) port->actor_oper_port_key = (port->actor_admin_port_key &= ~AD_SPEED_KEY_BITS); } - pr_debug("Port %d changed link status to %s", - port->actor_port_number, - (link == BOND_LINK_UP) ? "UP" : "DOWN"); + pr_debug("Port %d changed link status to %s\n", + port->actor_port_number, + link == BOND_LINK_UP ? "UP" : "DOWN"); /* there is no need to reselect a new aggregator, just signal the * state machines to reinitialize */ @@ -2380,17 +2391,16 @@ int __bond_3ad_get_active_agg_info(struct bonding *bond, } } - if (aggregator) { - ad_info->aggregator_id = aggregator->aggregator_identifier; - ad_info->ports = aggregator->num_of_ports; - ad_info->actor_key = aggregator->actor_oper_aggregator_key; - ad_info->partner_key = aggregator->partner_oper_aggregator_key; - memcpy(ad_info->partner_system, - aggregator->partner_system.mac_addr_value, ETH_ALEN); - return 0; - } + if (!aggregator) + return -1; - return -1; + ad_info->aggregator_id = aggregator->aggregator_identifier; + ad_info->ports = aggregator->num_of_ports; + ad_info->actor_key = aggregator->actor_oper_aggregator_key; + ad_info->partner_key = aggregator->partner_oper_aggregator_key; + ether_addr_copy(ad_info->partner_system, + aggregator->partner_system.mac_addr_value); + return 0; } /* Wrapper used to hold bond->lock so no slave manipulation can occur */ @@ -2469,7 +2479,7 @@ out: return NETDEV_TX_OK; err_free: /* no suitable interface, frame not sent */ - kfree_skb(skb); + dev_kfree_skb_any(skb); goto out; } diff --git a/drivers/net/bonding/bond_3ad.h b/drivers/net/bonding/bond_3ad.h index 13dc9d3c5e34..bb03b1df2f3e 100644 --- a/drivers/net/bonding/bond_3ad.h +++ b/drivers/net/bonding/bond_3ad.h @@ -28,7 +28,7 @@ #include <linux/netdevice.h> #include <linux/if_ether.h> -// General definitions +/* General definitions */ #define PKT_TYPE_LACPDU cpu_to_be16(ETH_P_SLOW) #define AD_TIMER_INTERVAL 100 /*msec*/ @@ -47,54 +47,54 @@ enum { BOND_AD_COUNT = 2, }; -// rx machine states(43.4.11 in the 802.3ad standard) +/* rx machine states(43.4.11 in the 802.3ad standard) */ typedef enum { AD_RX_DUMMY, - AD_RX_INITIALIZE, // rx Machine - AD_RX_PORT_DISABLED, // rx Machine - AD_RX_LACP_DISABLED, // rx Machine - AD_RX_EXPIRED, // rx Machine - AD_RX_DEFAULTED, // rx Machine - AD_RX_CURRENT // rx Machine + AD_RX_INITIALIZE, /* rx Machine */ + AD_RX_PORT_DISABLED, /* rx Machine */ + AD_RX_LACP_DISABLED, /* rx Machine */ + AD_RX_EXPIRED, /* rx Machine */ + AD_RX_DEFAULTED, /* rx Machine */ + AD_RX_CURRENT /* rx Machine */ } rx_states_t; -// periodic machine states(43.4.12 in the 802.3ad standard) +/* periodic machine states(43.4.12 in the 802.3ad standard) */ typedef enum { AD_PERIODIC_DUMMY, - AD_NO_PERIODIC, // periodic machine - AD_FAST_PERIODIC, // periodic machine - AD_SLOW_PERIODIC, // periodic machine - AD_PERIODIC_TX // periodic machine + AD_NO_PERIODIC, /* periodic machine */ + AD_FAST_PERIODIC, /* periodic machine */ + AD_SLOW_PERIODIC, /* periodic machine */ + AD_PERIODIC_TX /* periodic machine */ } periodic_states_t; -// mux machine states(43.4.13 in the 802.3ad standard) +/* mux machine states(43.4.13 in the 802.3ad standard) */ typedef enum { AD_MUX_DUMMY, - AD_MUX_DETACHED, // mux machine - AD_MUX_WAITING, // mux machine - AD_MUX_ATTACHED, // mux machine - AD_MUX_COLLECTING_DISTRIBUTING // mux machine + AD_MUX_DETACHED, /* mux machine */ + AD_MUX_WAITING, /* mux machine */ + AD_MUX_ATTACHED, /* mux machine */ + AD_MUX_COLLECTING_DISTRIBUTING /* mux machine */ } mux_states_t; -// tx machine states(43.4.15 in the 802.3ad standard) +/* tx machine states(43.4.15 in the 802.3ad standard) */ typedef enum { AD_TX_DUMMY, - AD_TRANSMIT // tx Machine + AD_TRANSMIT /* tx Machine */ } tx_states_t; -// rx indication types +/* rx indication types */ typedef enum { - AD_TYPE_LACPDU = 1, // type lacpdu - AD_TYPE_MARKER // type marker + AD_TYPE_LACPDU = 1, /* type lacpdu */ + AD_TYPE_MARKER /* type marker */ } pdu_type_t; -// rx marker indication types +/* rx marker indication types */ typedef enum { - AD_MARKER_INFORMATION_SUBTYPE = 1, // marker imformation subtype - AD_MARKER_RESPONSE_SUBTYPE // marker response subtype + AD_MARKER_INFORMATION_SUBTYPE = 1, /* marker imformation subtype */ + AD_MARKER_RESPONSE_SUBTYPE /* marker response subtype */ } bond_marker_subtype_t; -// timers types(43.4.9 in the 802.3ad standard) +/* timers types(43.4.9 in the 802.3ad standard) */ typedef enum { AD_CURRENT_WHILE_TIMER, AD_ACTOR_CHURN_TIMER, @@ -105,35 +105,35 @@ typedef enum { #pragma pack(1) -// Link Aggregation Control Protocol(LACP) data unit structure(43.4.2.2 in the 802.3ad standard) +/* Link Aggregation Control Protocol(LACP) data unit structure(43.4.2.2 in the 802.3ad standard) */ typedef struct lacpdu { - u8 subtype; // = LACP(= 0x01) + u8 subtype; /* = LACP(= 0x01) */ u8 version_number; - u8 tlv_type_actor_info; // = actor information(type/length/value) - u8 actor_information_length; // = 20 + u8 tlv_type_actor_info; /* = actor information(type/length/value) */ + u8 actor_information_length; /* = 20 */ __be16 actor_system_priority; struct mac_addr actor_system; __be16 actor_key; __be16 actor_port_priority; __be16 actor_port; u8 actor_state; - u8 reserved_3_1[3]; // = 0 - u8 tlv_type_partner_info; // = partner information - u8 partner_information_length; // = 20 + u8 reserved_3_1[3]; /* = 0 */ + u8 tlv_type_partner_info; /* = partner information */ + u8 partner_information_length; /* = 20 */ __be16 partner_system_priority; struct mac_addr partner_system; __be16 partner_key; __be16 partner_port_priority; __be16 partner_port; u8 partner_state; - u8 reserved_3_2[3]; // = 0 - u8 tlv_type_collector_info; // = collector information - u8 collector_information_length; // = 16 + u8 reserved_3_2[3]; /* = 0 */ + u8 tlv_type_collector_info; /* = collector information */ + u8 collector_information_length;/* = 16 */ __be16 collector_max_delay; u8 reserved_12[12]; - u8 tlv_type_terminator; // = terminator - u8 terminator_length; // = 0 - u8 reserved_50[50]; // = 0 + u8 tlv_type_terminator; /* = terminator */ + u8 terminator_length; /* = 0 */ + u8 reserved_50[50]; /* = 0 */ } __packed lacpdu_t; typedef struct lacpdu_header { @@ -141,20 +141,20 @@ typedef struct lacpdu_header { struct lacpdu lacpdu; } __packed lacpdu_header_t; -// Marker Protocol Data Unit(PDU) structure(43.5.3.2 in the 802.3ad standard) +/* Marker Protocol Data Unit(PDU) structure(43.5.3.2 in the 802.3ad standard) */ typedef struct bond_marker { - u8 subtype; // = 0x02 (marker PDU) - u8 version_number; // = 0x01 - u8 tlv_type; // = 0x01 (marker information) - // = 0x02 (marker response information) - u8 marker_length; // = 0x16 - u16 requester_port; // The number assigned to the port by the requester - struct mac_addr requester_system; // The requester's system id - u32 requester_transaction_id; // The transaction id allocated by the requester, - u16 pad; // = 0 - u8 tlv_type_terminator; // = 0x00 - u8 terminator_length; // = 0x00 - u8 reserved_90[90]; // = 0 + u8 subtype; /* = 0x02 (marker PDU) */ + u8 version_number; /* = 0x01 */ + u8 tlv_type; /* = 0x01 (marker information) */ + /* = 0x02 (marker response information) */ + u8 marker_length; /* = 0x16 */ + u16 requester_port; /* The number assigned to the port by the requester */ + struct mac_addr requester_system; /* The requester's system id */ + u32 requester_transaction_id; /* The transaction id allocated by the requester, */ + u16 pad; /* = 0 */ + u8 tlv_type_terminator; /* = 0x00 */ + u8 terminator_length; /* = 0x00 */ + u8 reserved_90[90]; /* = 0 */ } __packed bond_marker_t; typedef struct bond_marker_header { @@ -173,7 +173,7 @@ struct port; #pragma pack(8) #endif -// aggregator structure(43.4.5 in the 802.3ad standard) +/* aggregator structure(43.4.5 in the 802.3ad standard) */ typedef struct aggregator { struct mac_addr aggregator_mac_address; u16 aggregator_identifier; @@ -183,12 +183,12 @@ typedef struct aggregator { struct mac_addr partner_system; u16 partner_system_priority; u16 partner_oper_aggregator_key; - u16 receive_state; // BOOLEAN - u16 transmit_state; // BOOLEAN + u16 receive_state; /* BOOLEAN */ + u16 transmit_state; /* BOOLEAN */ struct port *lag_ports; - // ****** PRIVATE PARAMETERS ****** - struct slave *slave; // pointer to the bond slave that this aggregator belongs to - u16 is_active; // BOOLEAN. Indicates if this aggregator is active + /* ****** PRIVATE PARAMETERS ****** */ + struct slave *slave; /* pointer to the bond slave that this aggregator belongs to */ + u16 is_active; /* BOOLEAN. Indicates if this aggregator is active */ u16 num_of_ports; } aggregator_t; @@ -201,12 +201,12 @@ struct port_params { u16 port_state; }; -// port structure(43.4.6 in the 802.3ad standard) +/* port structure(43.4.6 in the 802.3ad standard) */ typedef struct port { u16 actor_port_number; u16 actor_port_priority; - struct mac_addr actor_system; // This parameter is added here although it is not specified in the standard, just for simplification - u16 actor_system_priority; // This parameter is added here although it is not specified in the standard, just for simplification + struct mac_addr actor_system; /* This parameter is added here although it is not specified in the standard, just for simplification */ + u16 actor_system_priority; /* This parameter is added here although it is not specified in the standard, just for simplification */ u16 actor_port_aggregator_identifier; bool ntt; u16 actor_admin_port_key; @@ -219,24 +219,24 @@ typedef struct port { bool is_enabled; - // ****** PRIVATE PARAMETERS ****** - u16 sm_vars; // all state machines variables for this port - rx_states_t sm_rx_state; // state machine rx state - u16 sm_rx_timer_counter; // state machine rx timer counter - periodic_states_t sm_periodic_state;// state machine periodic state - u16 sm_periodic_timer_counter; // state machine periodic timer counter - mux_states_t sm_mux_state; // state machine mux state - u16 sm_mux_timer_counter; // state machine mux timer counter - tx_states_t sm_tx_state; // state machine tx state - u16 sm_tx_timer_counter; // state machine tx timer counter(allways on - enter to transmit state 3 time per second) - struct slave *slave; // pointer to the bond slave that this port belongs to - struct aggregator *aggregator; // pointer to an aggregator that this port related to - struct port *next_port_in_aggregator; // Next port on the linked list of the parent aggregator - u32 transaction_id; // continuous number for identification of Marker PDU's; - struct lacpdu lacpdu; // the lacpdu that will be sent for this port + /* ****** PRIVATE PARAMETERS ****** */ + u16 sm_vars; /* all state machines variables for this port */ + rx_states_t sm_rx_state; /* state machine rx state */ + u16 sm_rx_timer_counter; /* state machine rx timer counter */ + periodic_states_t sm_periodic_state; /* state machine periodic state */ + u16 sm_periodic_timer_counter; /* state machine periodic timer counter */ + mux_states_t sm_mux_state; /* state machine mux state */ + u16 sm_mux_timer_counter; /* state machine mux timer counter */ + tx_states_t sm_tx_state; /* state machine tx state */ + u16 sm_tx_timer_counter; /* state machine tx timer counter(allways on - enter to transmit state 3 time per second) */ + struct slave *slave; /* pointer to the bond slave that this port belongs to */ + struct aggregator *aggregator; /* pointer to an aggregator that this port related to */ + struct port *next_port_in_aggregator; /* Next port on the linked list of the parent aggregator */ + u32 transaction_id; /* continuous number for identification of Marker PDU's; */ + struct lacpdu lacpdu; /* the lacpdu that will be sent for this port */ } port_t; -// system structure +/* system structure */ struct ad_system { u16 sys_priority; struct mac_addr sys_mac_addr; @@ -246,26 +246,26 @@ struct ad_system { #pragma pack() #endif -// ================= AD Exported structures to the main bonding code ================== +/* ========== AD Exported structures to the main bonding code ========== */ #define BOND_AD_INFO(bond) ((bond)->ad_info) #define SLAVE_AD_INFO(slave) ((slave)->ad_info) struct ad_bond_info { - struct ad_system system; /* 802.3ad system structure */ - u32 agg_select_timer; // Timer to select aggregator after all adapter's hand shakes + struct ad_system system; /* 802.3ad system structure */ + u32 agg_select_timer; /* Timer to select aggregator after all adapter's hand shakes */ + u16 aggregator_identifier; }; struct ad_slave_info { - struct aggregator aggregator; // 802.3ad aggregator structure - struct port port; // 802.3ad port structure - spinlock_t state_machine_lock; /* mutex state machines vs. - incoming LACPDU */ + struct aggregator aggregator; /* 802.3ad aggregator structure */ + struct port port; /* 802.3ad port structure */ + spinlock_t state_machine_lock; /* mutex state machines vs. incoming LACPDU */ u16 id; }; -// ================= AD Exported functions to the main bonding code ================== +/* ========== AD Exported functions to the main bonding code ========== */ void bond_3ad_initialize(struct bonding *bond, u16 tick_resolution); -void bond_3ad_bind_slave(struct slave *slave); +void bond_3ad_bind_slave(struct slave *slave); void bond_3ad_unbind_slave(struct slave *slave); void bond_3ad_state_machine_handler(struct work_struct *); void bond_3ad_initiate_agg_selection(struct bonding *bond, int timeout); @@ -280,5 +280,5 @@ int bond_3ad_lacpdu_recv(const struct sk_buff *skb, struct bonding *bond, struct slave *slave); int bond_3ad_set_carrier(struct bonding *bond); void bond_3ad_update_lacp_rate(struct bonding *bond); -#endif //__BOND_3AD_H__ +#endif /* __BOND_3AD_H__ */ diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c index a2c47476804d..9cf836b67b15 100644 --- a/drivers/net/bonding/bond_alb.c +++ b/drivers/net/bonding/bond_alb.c @@ -93,9 +93,8 @@ static inline u8 _simple_hash(const u8 *hash_start, int hash_size) int i; u8 hash = 0; - for (i = 0; i < hash_size; i++) { + for (i = 0; i < hash_size; i++) hash ^= hash_start[i]; - } return hash; } @@ -190,9 +189,8 @@ static int tlb_initialize(struct bonding *bond) bond_info->tx_hashtbl = new_hashtbl; - for (i = 0; i < TLB_HASH_TABLE_SIZE; i++) { + for (i = 0; i < TLB_HASH_TABLE_SIZE; i++) tlb_init_table_entry(&bond_info->tx_hashtbl[i], 0); - } _unlock_tx_hashtbl_bh(bond); @@ -264,9 +262,8 @@ static struct slave *__tlb_choose_channel(struct bonding *bond, u32 hash_index, hash_table[hash_index].next = next_index; hash_table[hash_index].prev = TLB_NULL_INDEX; - if (next_index != TLB_NULL_INDEX) { + if (next_index != TLB_NULL_INDEX) hash_table[next_index].prev = hash_index; - } slave_info->head = hash_index; slave_info->load += @@ -274,9 +271,8 @@ static struct slave *__tlb_choose_channel(struct bonding *bond, u32 hash_index, } } - if (assigned_slave) { + if (assigned_slave) hash_table[hash_index].tx_bytes += skb_len; - } return assigned_slave; } @@ -329,7 +325,7 @@ static void rlb_update_entry_from_arp(struct bonding *bond, struct arp_pkt *arp) _lock_rx_hashtbl_bh(bond); - hash_index = _simple_hash((u8*)&(arp->ip_src), sizeof(arp->ip_src)); + hash_index = _simple_hash((u8 *)&(arp->ip_src), sizeof(arp->ip_src)); client_info = &(bond_info->rx_hashtbl[hash_index]); if ((client_info->assigned) && @@ -337,7 +333,7 @@ static void rlb_update_entry_from_arp(struct bonding *bond, struct arp_pkt *arp) (client_info->ip_dst == arp->ip_src) && (!ether_addr_equal_64bits(client_info->mac_dst, arp->mac_src))) { /* update the clients MAC address */ - memcpy(client_info->mac_dst, arp->mac_src, ETH_ALEN); + ether_addr_copy(client_info->mac_dst, arp->mac_src); client_info->ntt = 1; bond_info->rx_ntt = 1; } @@ -451,9 +447,8 @@ static struct slave *__rlb_next_rx_slave(struct bonding *bond) */ static void rlb_teach_disabled_mac_on_primary(struct bonding *bond, u8 addr[]) { - if (!bond->curr_active_slave) { + if (!bond->curr_active_slave) return; - } if (!bond->alb_info.primary_is_promisc) { if (!dev_set_promiscuity(bond->curr_active_slave->dev, 1)) @@ -513,9 +508,8 @@ static void rlb_clear_slave(struct bonding *bond, struct slave *slave) write_lock_bh(&bond->curr_slave_lock); - if (slave != bond->curr_active_slave) { + if (slave != bond->curr_active_slave) rlb_teach_disabled_mac_on_primary(bond, slave->dev->dev_addr); - } write_unlock_bh(&bond->curr_slave_lock); } @@ -524,9 +518,8 @@ static void rlb_update_client(struct rlb_client_info *client_info) { int i; - if (!client_info->slave) { + if (!client_info->slave) return; - } for (i = 0; i < RLB_ARP_BURST_SIZE; i++) { struct sk_buff *skb; @@ -574,9 +567,8 @@ static void rlb_update_rx_clients(struct bonding *bond) client_info = &(bond_info->rx_hashtbl[hash_index]); if (client_info->ntt) { rlb_update_client(client_info); - if (bond_info->rlb_update_retry_counter == 0) { + if (bond_info->rlb_update_retry_counter == 0) client_info->ntt = 0; - } } } @@ -610,10 +602,10 @@ static void rlb_req_update_slave_clients(struct bonding *bond, struct slave *sla } } - // update the team's flag only after the whole iteration + /* update the team's flag only after the whole iteration */ if (ntt) { bond_info->rx_ntt = 1; - //fasten the change + /* fasten the change */ bond_info->rlb_update_retry_counter = RLB_UPDATE_RETRY; } @@ -677,9 +669,9 @@ static struct slave *rlb_choose_channel(struct sk_buff *skb, struct bonding *bon /* the entry is already assigned to this client */ if (!ether_addr_equal_64bits(arp->mac_dst, mac_bcast)) { /* update mac address from arp */ - memcpy(client_info->mac_dst, arp->mac_dst, ETH_ALEN); + ether_addr_copy(client_info->mac_dst, arp->mac_dst); } - memcpy(client_info->mac_src, arp->mac_src, ETH_ALEN); + ether_addr_copy(client_info->mac_src, arp->mac_src); assigned_slave = client_info->slave; if (assigned_slave) { @@ -719,8 +711,8 @@ static struct slave *rlb_choose_channel(struct sk_buff *skb, struct bonding *bon * will be updated with clients actual unicast mac address * upon receiving an arp reply. */ - memcpy(client_info->mac_dst, arp->mac_dst, ETH_ALEN); - memcpy(client_info->mac_src, arp->mac_src, ETH_ALEN); + ether_addr_copy(client_info->mac_dst, arp->mac_dst); + ether_addr_copy(client_info->mac_src, arp->mac_src); client_info->slave = assigned_slave; if (!ether_addr_equal_64bits(client_info->mac_dst, mac_bcast)) { @@ -770,9 +762,8 @@ static struct slave *rlb_arp_xmit(struct sk_buff *skb, struct bonding *bond) * rx channel */ tx_slave = rlb_choose_channel(skb, bond); - if (tx_slave) { - memcpy(arp->mac_src,tx_slave->dev->dev_addr, ETH_ALEN); - } + if (tx_slave) + ether_addr_copy(arp->mac_src, tx_slave->dev->dev_addr); pr_debug("Server sent ARP Reply packet\n"); } else if (arp->op_code == htons(ARPOP_REQUEST)) { /* Create an entry in the rx_hashtbl for this client as a @@ -824,9 +815,8 @@ static void rlb_rebalance(struct bonding *bond) } /* update the team's flag only after the whole iteration */ - if (ntt) { + if (ntt) bond_info->rx_ntt = 1; - } _unlock_rx_hashtbl_bh(bond); } @@ -923,7 +913,7 @@ static void rlb_src_link(struct bonding *bond, u32 ip_src_hash, u32 ip_dst_hash) static void rlb_purge_src_ip(struct bonding *bond, struct arp_pkt *arp) { struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond)); - u32 ip_src_hash = _simple_hash((u8*)&(arp->ip_src), sizeof(arp->ip_src)); + u32 ip_src_hash = _simple_hash((u8 *)&(arp->ip_src), sizeof(arp->ip_src)); u32 index; _lock_rx_hashtbl_bh(bond); @@ -957,9 +947,8 @@ static int rlb_initialize(struct bonding *bond) bond_info->rx_hashtbl_used_head = RLB_NULL_INDEX; - for (i = 0; i < RLB_HASH_TABLE_SIZE; i++) { + for (i = 0; i < RLB_HASH_TABLE_SIZE; i++) rlb_init_table_entry(bond_info->rx_hashtbl + i); - } _unlock_rx_hashtbl_bh(bond); @@ -1014,8 +1003,8 @@ static void alb_send_lp_vid(struct slave *slave, u8 mac_addr[], char *data; memset(&pkt, 0, size); - memcpy(pkt.mac_dst, mac_addr, ETH_ALEN); - memcpy(pkt.mac_src, mac_addr, ETH_ALEN); + ether_addr_copy(pkt.mac_dst, mac_addr); + ether_addr_copy(pkt.mac_src, mac_addr); pkt.type = cpu_to_be16(ETH_P_LOOP); skb = dev_alloc_skb(size); @@ -1097,7 +1086,7 @@ static void alb_swap_mac_addr(struct slave *slave1, struct slave *slave2) { u8 tmp_mac_addr[ETH_ALEN]; - memcpy(tmp_mac_addr, slave1->dev->dev_addr, ETH_ALEN); + ether_addr_copy(tmp_mac_addr, slave1->dev->dev_addr); alb_set_slave_mac_addr(slave1, slave2->dev->dev_addr); alb_set_slave_mac_addr(slave2, tmp_mac_addr); @@ -1254,9 +1243,9 @@ static int alb_handle_addr_collision_on_attach(struct bonding *bond, struct slav if (free_mac_slave) { alb_set_slave_mac_addr(slave, free_mac_slave->perm_hwaddr); - pr_warning("%s: Warning: the hw address of slave %s is in use by the bond; giving it the hw address of %s\n", - bond->dev->name, slave->dev->name, - free_mac_slave->dev->name); + pr_warn("%s: Warning: the hw address of slave %s is in use by the bond; giving it the hw address of %s\n", + bond->dev->name, slave->dev->name, + free_mac_slave->dev->name); } else if (has_bond_addr) { pr_err("%s: Error: the hw address of slave %s is in use by the bond; couldn't find a slave with a free hw address to give it (this should not have happened)\n", @@ -1294,12 +1283,12 @@ static int alb_set_mac_address(struct bonding *bond, void *addr) bond_for_each_slave(bond, slave, iter) { /* save net_device's current hw address */ - memcpy(tmp_addr, slave->dev->dev_addr, ETH_ALEN); + ether_addr_copy(tmp_addr, slave->dev->dev_addr); res = dev_set_mac_address(slave->dev, addr); /* restore net_device's hw address */ - memcpy(slave->dev->dev_addr, tmp_addr, ETH_ALEN); + ether_addr_copy(slave->dev->dev_addr, tmp_addr); if (res) goto unwind; @@ -1315,9 +1304,9 @@ unwind: bond_for_each_slave(bond, rollback_slave, iter) { if (rollback_slave == slave) break; - memcpy(tmp_addr, rollback_slave->dev->dev_addr, ETH_ALEN); + ether_addr_copy(tmp_addr, rollback_slave->dev->dev_addr); dev_set_mac_address(rollback_slave->dev, &sa); - memcpy(rollback_slave->dev->dev_addr, tmp_addr, ETH_ALEN); + ether_addr_copy(rollback_slave->dev->dev_addr, tmp_addr); } return res; @@ -1330,9 +1319,8 @@ int bond_alb_initialize(struct bonding *bond, int rlb_enabled) int res; res = tlb_initialize(bond); - if (res) { + if (res) return res; - } if (rlb_enabled) { bond->alb_info.rlb_enabled = 1; @@ -1355,9 +1343,8 @@ void bond_alb_deinitialize(struct bonding *bond) tlb_deinitialize(bond); - if (bond_info->rlb_enabled) { + if (bond_info->rlb_enabled) rlb_deinitialize(bond); - } } int bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev) @@ -1436,14 +1423,13 @@ int bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev) break; } - hash_start = (char*)eth_data->h_dest; + hash_start = (char *)eth_data->h_dest; hash_size = ETH_ALEN; break; case ETH_P_ARP: do_tx_balance = 0; - if (bond_info->rlb_enabled) { + if (bond_info->rlb_enabled) tx_slave = rlb_arp_xmit(skb, bond); - } break; default: do_tx_balance = 0; @@ -1463,23 +1449,22 @@ int bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev) if (tx_slave && SLAVE_IS_OK(tx_slave)) { if (tx_slave != rcu_dereference(bond->curr_active_slave)) { - memcpy(eth_data->h_source, - tx_slave->dev->dev_addr, - ETH_ALEN); + ether_addr_copy(eth_data->h_source, + tx_slave->dev->dev_addr); } bond_dev_queue_xmit(bond, skb, tx_slave->dev); goto out; - } else { - if (tx_slave) { - _lock_tx_hashtbl(bond); - __tlb_clear_slave(bond, tx_slave, 0); - _unlock_tx_hashtbl(bond); - } + } + + if (tx_slave) { + _lock_tx_hashtbl(bond); + __tlb_clear_slave(bond, tx_slave, 0); + _unlock_tx_hashtbl(bond); } /* no suitable interface, frame not sent */ - kfree_skb(skb); + dev_kfree_skb_any(skb); out: return NETDEV_TX_OK; } @@ -1577,11 +1562,10 @@ void bond_alb_monitor(struct work_struct *work) --bond_info->rlb_update_delay_counter; } else { rlb_update_rx_clients(bond); - if (bond_info->rlb_update_retry_counter) { + if (bond_info->rlb_update_retry_counter) --bond_info->rlb_update_retry_counter; - } else { + else bond_info->rx_ntt = 0; - } } } } @@ -1598,23 +1582,20 @@ int bond_alb_init_slave(struct bonding *bond, struct slave *slave) int res; res = alb_set_slave_mac_addr(slave, slave->perm_hwaddr); - if (res) { + if (res) return res; - } res = alb_handle_addr_collision_on_attach(bond, slave); - if (res) { + if (res) return res; - } tlb_init_slave(slave); /* order a rebalance ASAP */ bond->alb_info.tx_rebalance_counter = BOND_TLB_REBALANCE_TICKS; - if (bond->alb_info.rlb_enabled) { + if (bond->alb_info.rlb_enabled) bond->alb_info.rlb_rebalance = 1; - } return 0; } @@ -1645,9 +1626,8 @@ void bond_alb_handle_link_change(struct bonding *bond, struct slave *slave, char if (link == BOND_LINK_DOWN) { tlb_clear_slave(bond, slave, 0); - if (bond->alb_info.rlb_enabled) { + if (bond->alb_info.rlb_enabled) rlb_clear_slave(bond, slave); - } } else if (link == BOND_LINK_UP) { /* order a rebalance ASAP */ bond_info->tx_rebalance_counter = BOND_TLB_REBALANCE_TICKS; @@ -1723,14 +1703,14 @@ void bond_alb_handle_active_change(struct bonding *bond, struct slave *new_slave struct sockaddr sa; u8 tmp_addr[ETH_ALEN]; - memcpy(tmp_addr, new_slave->dev->dev_addr, ETH_ALEN); + ether_addr_copy(tmp_addr, new_slave->dev->dev_addr); memcpy(sa.sa_data, bond->dev->dev_addr, bond->dev->addr_len); sa.sa_family = bond->dev->type; /* we don't care if it can't change its mac, best effort */ dev_set_mac_address(new_slave->dev, &sa); - memcpy(new_slave->dev->dev_addr, tmp_addr, ETH_ALEN); + ether_addr_copy(new_slave->dev->dev_addr, tmp_addr); } /* curr_active_slave must be set before calling alb_swap_mac_addr */ @@ -1759,14 +1739,12 @@ int bond_alb_set_mac_address(struct net_device *bond_dev, void *addr) struct slave *swap_slave; int res; - if (!is_valid_ether_addr(sa->sa_data)) { + if (!is_valid_ether_addr(sa->sa_data)) return -EADDRNOTAVAIL; - } res = alb_set_mac_address(bond, addr); - if (res) { + if (res) return res; - } memcpy(bond_dev->dev_addr, sa->sa_data, bond_dev->addr_len); @@ -1774,9 +1752,8 @@ int bond_alb_set_mac_address(struct net_device *bond_dev, void *addr) * Otherwise we'll need to pass the new address to it and handle * duplications. */ - if (!bond->curr_active_slave) { + if (!bond->curr_active_slave) return 0; - } swap_slave = bond_slave_has_mac(bond, bond_dev->dev_addr); @@ -1800,8 +1777,7 @@ int bond_alb_set_mac_address(struct net_device *bond_dev, void *addr) void bond_alb_clear_vlan(struct bonding *bond, unsigned short vlan_id) { - if (bond->alb_info.rlb_enabled) { + if (bond->alb_info.rlb_enabled) rlb_clear_vlan(bond, vlan_id); - } } diff --git a/drivers/net/bonding/bond_debugfs.c b/drivers/net/bonding/bond_debugfs.c index 5fc4c2351478..2d3f7fa541ff 100644 --- a/drivers/net/bonding/bond_debugfs.c +++ b/drivers/net/bonding/bond_debugfs.c @@ -69,7 +69,7 @@ void bond_debug_register(struct bonding *bond) debugfs_create_dir(bond->dev->name, bonding_debug_root); if (!bond->debug_dir) { - pr_warning("%s: Warning: failed to register to debugfs\n", + pr_warn("%s: Warning: failed to register to debugfs\n", bond->dev->name); return; } @@ -98,9 +98,8 @@ void bond_debug_reregister(struct bonding *bond) if (d) { bond->debug_dir = d; } else { - pr_warning("%s: Warning: failed to reregister, " - "so just unregister old one\n", - bond->dev->name); + pr_warn("%s: Warning: failed to reregister, so just unregister old one\n", + bond->dev->name); bond_debug_unregister(bond); } } @@ -110,8 +109,7 @@ void bond_create_debugfs(void) bonding_debug_root = debugfs_create_dir("bonding", NULL); if (!bonding_debug_root) { - pr_warning("Warning: Cannot create bonding directory" - " in debugfs\n"); + pr_warn("Warning: Cannot create bonding directory in debugfs\n"); } } diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 4c08018d7333..e717db301d46 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -673,12 +673,12 @@ static void bond_do_fail_over_mac(struct bonding *bond, write_unlock_bh(&bond->curr_slave_lock); if (old_active) { - memcpy(tmp_mac, new_active->dev->dev_addr, ETH_ALEN); - memcpy(saddr.sa_data, old_active->dev->dev_addr, - ETH_ALEN); + ether_addr_copy(tmp_mac, new_active->dev->dev_addr); + ether_addr_copy(saddr.sa_data, + old_active->dev->dev_addr); saddr.sa_family = new_active->dev->type; } else { - memcpy(saddr.sa_data, bond->dev->dev_addr, ETH_ALEN); + ether_addr_copy(saddr.sa_data, bond->dev->dev_addr); saddr.sa_family = bond->dev->type; } @@ -692,7 +692,7 @@ static void bond_do_fail_over_mac(struct bonding *bond, if (!old_active) goto out; - memcpy(saddr.sa_data, tmp_mac, ETH_ALEN); + ether_addr_copy(saddr.sa_data, tmp_mac); saddr.sa_family = old_active->dev->type; rv = dev_set_mac_address(old_active->dev, &saddr); @@ -798,11 +798,11 @@ void bond_change_active_slave(struct bonding *bond, struct slave *new_active) return; if (new_active) { - new_active->jiffies = jiffies; + new_active->last_link_up = jiffies; if (new_active->link == BOND_LINK_BACK) { if (USES_PRIMARY(bond->params.mode)) { - pr_info("%s: making interface %s the new active one %d ms earlier.\n", + pr_info("%s: making interface %s the new active one %d ms earlier\n", bond->dev->name, new_active->dev->name, (bond->params.updelay - new_active->delay) * bond->params.miimon); } @@ -817,7 +817,7 @@ void bond_change_active_slave(struct bonding *bond, struct slave *new_active) bond_alb_handle_link_change(bond, new_active, BOND_LINK_UP); } else { if (USES_PRIMARY(bond->params.mode)) { - pr_info("%s: making interface %s the new active one.\n", + pr_info("%s: making interface %s the new active one\n", bond->dev->name, new_active->dev->name); } } @@ -829,21 +829,25 @@ void bond_change_active_slave(struct bonding *bond, struct slave *new_active) if (bond_is_lb(bond)) { bond_alb_handle_active_change(bond, new_active); if (old_active) - bond_set_slave_inactive_flags(old_active); + bond_set_slave_inactive_flags(old_active, + BOND_SLAVE_NOTIFY_NOW); if (new_active) - bond_set_slave_active_flags(new_active); + bond_set_slave_active_flags(new_active, + BOND_SLAVE_NOTIFY_NOW); } else { rcu_assign_pointer(bond->curr_active_slave, new_active); } if (bond->params.mode == BOND_MODE_ACTIVEBACKUP) { if (old_active) - bond_set_slave_inactive_flags(old_active); + bond_set_slave_inactive_flags(old_active, + BOND_SLAVE_NOTIFY_NOW); if (new_active) { bool should_notify_peers = false; - bond_set_slave_active_flags(new_active); + bond_set_slave_active_flags(new_active, + BOND_SLAVE_NOTIFY_NOW); if (bond->params.fail_over_mac) bond_do_fail_over_mac(bond, new_active, @@ -906,7 +910,7 @@ void bond_select_active_slave(struct bonding *bond) pr_info("%s: first active interface up!\n", bond->dev->name); } else { - pr_info("%s: now running without any active interface !\n", + pr_info("%s: now running without any active interface!\n", bond->dev->name); } } @@ -942,14 +946,6 @@ static inline void slave_disable_netpoll(struct slave *slave) slave->np = NULL; __netpoll_free_async(np); } -static inline bool slave_dev_support_netpoll(struct net_device *slave_dev) -{ - if (slave_dev->priv_flags & IFF_DISABLE_NETPOLL) - return false; - if (!slave_dev->netdev_ops->ndo_poll_controller) - return false; - return true; -} static void bond_poll_controller(struct net_device *bond_dev) { @@ -1115,9 +1111,6 @@ static rx_handler_result_t bond_handle_frame(struct sk_buff **pskb) slave = bond_slave_get_rcu(skb->dev); bond = slave->bond; - if (bond->params.arp_interval) - slave->dev->last_rx = jiffies; - recv_probe = ACCESS_ONCE(bond->recv_probe); if (recv_probe) { ret = recv_probe(skb, bond, slave); @@ -1142,7 +1135,7 @@ static rx_handler_result_t bond_handle_frame(struct sk_buff **pskb) kfree_skb(skb); return RX_HANDLER_CONSUMED; } - memcpy(eth_hdr(skb)->h_dest, bond->dev->dev_addr, ETH_ALEN); + ether_addr_copy(eth_hdr(skb)->h_dest, bond->dev->dev_addr); } return ret; @@ -1183,16 +1176,21 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) if (!bond->params.use_carrier && slave_dev->ethtool_ops->get_link == NULL && slave_ops->ndo_do_ioctl == NULL) { - pr_warning("%s: Warning: no link monitoring support for %s\n", - bond_dev->name, slave_dev->name); + pr_warn("%s: Warning: no link monitoring support for %s\n", + bond_dev->name, slave_dev->name); } /* already enslaved */ if (slave_dev->flags & IFF_SLAVE) { - pr_debug("Error, Device was already enslaved\n"); + pr_debug("Error: Device was already enslaved\n"); return -EBUSY; } + if (bond_dev == slave_dev) { + pr_err("%s: cannot enslave bond to itself.\n", bond_dev->name); + return -EPERM; + } + /* vlan challenged mutual exclusion */ /* no need to lock since we're protected by rtnl_lock */ if (slave_dev->features & NETIF_F_VLAN_CHALLENGED) { @@ -1202,9 +1200,9 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) bond_dev->name, slave_dev->name, bond_dev->name); return -EPERM; } else { - pr_warning("%s: Warning: enslaved VLAN challenged slave %s. Adding VLANs will be blocked as long as %s is part of bond %s\n", - bond_dev->name, slave_dev->name, - slave_dev->name, bond_dev->name); + pr_warn("%s: Warning: enslaved VLAN challenged slave %s. Adding VLANs will be blocked as long as %s is part of bond %s\n", + bond_dev->name, slave_dev->name, + slave_dev->name, bond_dev->name); } } else { pr_debug("%s: ! NETIF_F_VLAN_CHALLENGED\n", slave_dev->name); @@ -1217,7 +1215,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) * enslaving it; the old ifenslave will not. */ if ((slave_dev->flags & IFF_UP)) { - pr_err("%s is up. This may be due to an out of date ifenslave.\n", + pr_err("%s is up - this may be due to an out of date ifenslave\n", slave_dev->name); res = -EPERM; goto err_undo_flags; @@ -1261,20 +1259,23 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) bond_dev); } } else if (bond_dev->type != slave_dev->type) { - pr_err("%s ether type (%d) is different from other slaves (%d), can not enslave it.\n", - slave_dev->name, - slave_dev->type, bond_dev->type); + pr_err("%s ether type (%d) is different from other slaves (%d), can not enslave it\n", + slave_dev->name, slave_dev->type, bond_dev->type); res = -EINVAL; goto err_undo_flags; } if (slave_ops->ndo_set_mac_address == NULL) { if (!bond_has_slaves(bond)) { - pr_warning("%s: Warning: The first slave device specified does not support setting the MAC address. Setting fail_over_mac to active.", - bond_dev->name); - bond->params.fail_over_mac = BOND_FOM_ACTIVE; + pr_warn("%s: Warning: The first slave device specified does not support setting the MAC address\n", + bond_dev->name); + if (bond->params.mode == BOND_MODE_ACTIVEBACKUP) { + bond->params.fail_over_mac = BOND_FOM_ACTIVE; + pr_warn("%s: Setting fail_over_mac to active for active-backup mode\n", + bond_dev->name); + } } else if (bond->params.fail_over_mac != BOND_FOM_ACTIVE) { - pr_err("%s: Error: The slave device specified does not support setting the MAC address, but fail_over_mac is not set to active.\n", + pr_err("%s: Error: The slave device specified does not support setting the MAC address, but fail_over_mac is not set to active\n", bond_dev->name); res = -EOPNOTSUPP; goto err_undo_flags; @@ -1313,9 +1314,10 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) * that need it, and for restoring it upon release, and then * set it to the master's address */ - memcpy(new_slave->perm_hwaddr, slave_dev->dev_addr, ETH_ALEN); + ether_addr_copy(new_slave->perm_hwaddr, slave_dev->dev_addr); - if (!bond->params.fail_over_mac) { + if (!bond->params.fail_over_mac || + bond->params.mode != BOND_MODE_ACTIVEBACKUP) { /* * Set slave to master's mac address. The application already * set the master's mac address to that of the first slave @@ -1396,10 +1398,10 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) bond_update_speed_duplex(new_slave); - new_slave->last_arp_rx = jiffies - + new_slave->last_rx = jiffies - (msecs_to_jiffies(bond->params.arp_interval) + 1); for (i = 0; i < BOND_MAX_ARP_TARGETS; i++) - new_slave->target_last_arp_rx[i] = new_slave->last_arp_rx; + new_slave->target_last_arp_rx[i] = new_slave->last_rx; if (bond->params.miimon && !bond->params.use_carrier) { link_reporting = bond_check_dev_link(bond, slave_dev, 1); @@ -1414,12 +1416,12 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) * supported); thus, we don't need to change * the messages for netif_carrier. */ - pr_warning("%s: Warning: MII and ETHTOOL support not available for interface %s, and arp_interval/arp_ip_target module parameters not specified, thus bonding will not detect link failures! see bonding.txt for details.\n", - bond_dev->name, slave_dev->name); + pr_warn("%s: Warning: MII and ETHTOOL support not available for interface %s, and arp_interval/arp_ip_target module parameters not specified, thus bonding will not detect link failures! see bonding.txt for details\n", + bond_dev->name, slave_dev->name); } else if (link_reporting == -1) { /* unable get link status using mii/ethtool */ - pr_warning("%s: Warning: can't get link status from interface %s; the network driver associated with this interface does not support MII or ETHTOOL link status reporting, thus miimon has no effect on this interface.\n", - bond_dev->name, slave_dev->name); + pr_warn("%s: Warning: can't get link status from interface %s; the network driver associated with this interface does not support MII or ETHTOOL link status reporting, thus miimon has no effect on this interface\n", + bond_dev->name, slave_dev->name); } } @@ -1443,10 +1445,10 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) } if (new_slave->link != BOND_LINK_DOWN) - new_slave->jiffies = jiffies; + new_slave->last_link_up = jiffies; pr_debug("Initial state of slave_dev is BOND_LINK_%s\n", - new_slave->link == BOND_LINK_DOWN ? "DOWN" : - (new_slave->link == BOND_LINK_UP ? "UP" : "BACK")); + new_slave->link == BOND_LINK_DOWN ? "DOWN" : + (new_slave->link == BOND_LINK_UP ? "UP" : "BACK")); if (USES_PRIMARY(bond->params.mode) && bond->params.primary[0]) { /* if there is a primary slave, remember it */ @@ -1458,14 +1460,15 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) switch (bond->params.mode) { case BOND_MODE_ACTIVEBACKUP: - bond_set_slave_inactive_flags(new_slave); + bond_set_slave_inactive_flags(new_slave, + BOND_SLAVE_NOTIFY_NOW); break; case BOND_MODE_8023AD: /* in 802.3ad mode, the internal mechanism * will activate the slaves in the selected * aggregator */ - bond_set_slave_inactive_flags(new_slave); + bond_set_slave_inactive_flags(new_slave, BOND_SLAVE_NOTIFY_NOW); /* if this is the first slave */ if (!prev_slave) { SLAVE_AD_INFO(new_slave).id = 1; @@ -1483,7 +1486,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) case BOND_MODE_TLB: case BOND_MODE_ALB: bond_set_active_slave(new_slave); - bond_set_slave_inactive_flags(new_slave); + bond_set_slave_inactive_flags(new_slave, BOND_SLAVE_NOTIFY_NOW); break; default: pr_debug("This slave is always active in trunk mode\n"); @@ -1505,10 +1508,8 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) slave_dev->npinfo = bond->dev->npinfo; if (slave_dev->npinfo) { if (slave_enable_netpoll(new_slave)) { - read_unlock(&bond->lock); - pr_info("Error, %s: master_dev is using netpoll, " - "but new slave device does not support netpoll.\n", - bond_dev->name); + pr_info("Error, %s: master_dev is using netpoll, but new slave device does not support netpoll\n", + bond_dev->name); res = -EBUSY; goto err_detach; } @@ -1539,15 +1540,17 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) bond_set_carrier(bond); if (USES_PRIMARY(bond->params.mode)) { + block_netpoll_tx(); write_lock_bh(&bond->curr_slave_lock); bond_select_active_slave(bond); write_unlock_bh(&bond->curr_slave_lock); + unblock_netpoll_tx(); } - pr_info("%s: enslaving %s as a%s interface with a%s link.\n", + pr_info("%s: Enslaving %s as %s interface with %s link\n", bond_dev->name, slave_dev->name, - bond_is_active_slave(new_slave) ? "n active" : " backup", - new_slave->link != BOND_LINK_DOWN ? "n up" : " down"); + bond_is_active_slave(new_slave) ? "an active" : "a backup", + new_slave->link != BOND_LINK_DOWN ? "an up" : "a down"); /* enslave is successful */ return 0; @@ -1567,10 +1570,12 @@ err_detach: if (bond->primary_slave == new_slave) bond->primary_slave = NULL; if (bond->curr_active_slave == new_slave) { + block_netpoll_tx(); write_lock_bh(&bond->curr_slave_lock); bond_change_active_slave(bond, NULL); bond_select_active_slave(bond); write_unlock_bh(&bond->curr_slave_lock); + unblock_netpoll_tx(); } slave_disable_netpoll(new_slave); @@ -1579,12 +1584,13 @@ err_close: dev_close(slave_dev); err_restore_mac: - if (!bond->params.fail_over_mac) { + if (!bond->params.fail_over_mac || + bond->params.mode != BOND_MODE_ACTIVEBACKUP) { /* XXX TODO - fom follow mode needs to change master's * MAC if this slave's MAC is in use by the bond, or at * least print a warning. */ - memcpy(addr.sa_data, new_slave->perm_hwaddr, ETH_ALEN); + ether_addr_copy(addr.sa_data, new_slave->perm_hwaddr); addr.sa_family = slave_dev->type; dev_set_mac_address(slave_dev, &addr); } @@ -1629,7 +1635,7 @@ static int __bond_release_one(struct net_device *bond_dev, /* slave is not a slave or master is not master of this slave */ if (!(slave_dev->flags & IFF_SLAVE) || !netdev_has_upper_dev(slave_dev, bond_dev)) { - pr_err("%s: Error: cannot release %s.\n", + pr_err("%s: Error: cannot release %s\n", bond_dev->name, slave_dev->name); return -EINVAL; } @@ -1645,9 +1651,6 @@ static int __bond_release_one(struct net_device *bond_dev, return -EINVAL; } - /* release the slave from its bond */ - bond->slave_cnt--; - bond_sysfs_slave_del(slave); bond_upper_dev_unlink(bond_dev, slave_dev); @@ -1663,7 +1666,7 @@ static int __bond_release_one(struct net_device *bond_dev, write_unlock_bh(&bond->lock); - pr_info("%s: releasing %s interface %s\n", + pr_info("%s: Releasing %s interface %s\n", bond_dev->name, bond_is_active_slave(slave) ? "active" : "backup", slave_dev->name); @@ -1672,13 +1675,14 @@ static int __bond_release_one(struct net_device *bond_dev, bond->current_arp_slave = NULL; - if (!all && !bond->params.fail_over_mac) { + if (!all && (!bond->params.fail_over_mac || + bond->params.mode != BOND_MODE_ACTIVEBACKUP)) { if (ether_addr_equal_64bits(bond_dev->dev_addr, slave->perm_hwaddr) && bond_has_slaves(bond)) - pr_warn("%s: Warning: the permanent HWaddr of %s - %pM - is still in use by %s. Set the HWaddr of %s to a different address to avoid conflicts.\n", - bond_dev->name, slave_dev->name, - slave->perm_hwaddr, - bond_dev->name, slave_dev->name); + pr_warn("%s: Warning: the permanent HWaddr of %s - %pM - is still in use by %s - set the HWaddr of %s to a different address to avoid conflicts\n", + bond_dev->name, slave_dev->name, + slave->perm_hwaddr, + bond_dev->name, slave_dev->name); } if (bond->primary_slave == slave) @@ -1719,15 +1723,16 @@ static int __bond_release_one(struct net_device *bond_dev, eth_hw_addr_random(bond_dev); if (vlan_uses_dev(bond_dev)) { - pr_warning("%s: Warning: clearing HW address of %s while it still has VLANs.\n", - bond_dev->name, bond_dev->name); - pr_warning("%s: When re-adding slaves, make sure the bond's HW address matches its VLANs'.\n", - bond_dev->name); + pr_warn("%s: Warning: clearing HW address of %s while it still has VLANs\n", + bond_dev->name, bond_dev->name); + pr_warn("%s: When re-adding slaves, make sure the bond's HW address matches its VLANs\n", + bond_dev->name); } } unblock_netpoll_tx(); synchronize_rcu(); + bond->slave_cnt--; if (!bond_has_slaves(bond)) { call_netdevice_notifiers(NETDEV_CHANGEADDR, bond->dev); @@ -1737,7 +1742,7 @@ static int __bond_release_one(struct net_device *bond_dev, bond_compute_features(bond); if (!(bond_dev->features & NETIF_F_VLAN_CHALLENGED) && (old_features & NETIF_F_VLAN_CHALLENGED)) - pr_info("%s: last VLAN challenged slave %s left bond %s. VLAN blocking is removed\n", + pr_info("%s: last VLAN challenged slave %s left bond %s - VLAN blocking is removed\n", bond_dev->name, slave_dev->name, bond_dev->name); /* must do this from outside any spinlocks */ @@ -1769,9 +1774,10 @@ static int __bond_release_one(struct net_device *bond_dev, /* close slave before restoring its mac address */ dev_close(slave_dev); - if (bond->params.fail_over_mac != BOND_FOM_ACTIVE) { + if (bond->params.fail_over_mac != BOND_FOM_ACTIVE || + bond->params.mode != BOND_MODE_ACTIVEBACKUP) { /* restore original ("permanent") mac address */ - memcpy(addr.sa_data, slave->perm_hwaddr, ETH_ALEN); + ether_addr_copy(addr.sa_data, slave->perm_hwaddr); addr.sa_family = slave_dev->type; dev_set_mac_address(slave_dev, &addr); } @@ -1804,7 +1810,7 @@ static int bond_release_and_destroy(struct net_device *bond_dev, ret = bond_release(bond_dev, slave_dev); if (ret == 0 && !bond_has_slaves(bond)) { bond_dev->priv_flags |= IFF_DISABLE_NETPOLL; - pr_info("%s: destroying bond %s.\n", + pr_info("%s: Destroying bond %s\n", bond_dev->name, bond_dev->name); unregister_netdevice(bond_dev); } @@ -1818,9 +1824,7 @@ static int bond_info_query(struct net_device *bond_dev, struct ifbond *info) info->bond_mode = bond->params.mode; info->miimon = bond->params.miimon; - read_lock(&bond->lock); info->num_slaves = bond->slave_cnt; - read_unlock(&bond->lock); return 0; } @@ -1832,7 +1836,6 @@ static int bond_slave_info_query(struct net_device *bond_dev, struct ifslave *in int i = 0, res = -ENODEV; struct slave *slave; - read_lock(&bond->lock); bond_for_each_slave(bond, slave, iter) { if (i++ == (int)info->slave_id) { res = 0; @@ -1843,7 +1846,6 @@ static int bond_slave_info_query(struct net_device *bond_dev, struct ifslave *in break; } } - read_unlock(&bond->lock); return res; } @@ -1873,7 +1875,7 @@ static int bond_miimon_inspect(struct bonding *bond) slave->link = BOND_LINK_FAIL; slave->delay = bond->params.downdelay; if (slave->delay) { - pr_info("%s: link status down for %sinterface %s, disabling it in %d ms.\n", + pr_info("%s: link status down for %sinterface %s, disabling it in %d ms\n", bond->dev->name, (bond->params.mode == BOND_MODE_ACTIVEBACKUP) ? @@ -1889,8 +1891,8 @@ static int bond_miimon_inspect(struct bonding *bond) * recovered before downdelay expired */ slave->link = BOND_LINK_UP; - slave->jiffies = jiffies; - pr_info("%s: link status up again after %d ms for interface %s.\n", + slave->last_link_up = jiffies; + pr_info("%s: link status up again after %d ms for interface %s\n", bond->dev->name, (bond->params.downdelay - slave->delay) * bond->params.miimon, @@ -1915,7 +1917,7 @@ static int bond_miimon_inspect(struct bonding *bond) slave->delay = bond->params.updelay; if (slave->delay) { - pr_info("%s: link status up for interface %s, enabling it in %d ms.\n", + pr_info("%s: link status up for interface %s, enabling it in %d ms\n", bond->dev->name, slave->dev->name, ignore_updelay ? 0 : bond->params.updelay * @@ -1925,7 +1927,7 @@ static int bond_miimon_inspect(struct bonding *bond) case BOND_LINK_BACK: if (!link_state) { slave->link = BOND_LINK_DOWN; - pr_info("%s: link status down again after %d ms for interface %s.\n", + pr_info("%s: link status down again after %d ms for interface %s\n", bond->dev->name, (bond->params.updelay - slave->delay) * bond->params.miimon, @@ -1964,7 +1966,7 @@ static void bond_miimon_commit(struct bonding *bond) case BOND_LINK_UP: slave->link = BOND_LINK_UP; - slave->jiffies = jiffies; + slave->last_link_up = jiffies; if (bond->params.mode == BOND_MODE_8023AD) { /* prevent it from being the active one */ @@ -1977,7 +1979,7 @@ static void bond_miimon_commit(struct bonding *bond) bond_set_backup_slave(slave); } - pr_info("%s: link status definitely up for interface %s, %u Mbps %s duplex.\n", + pr_info("%s: link status definitely up for interface %s, %u Mbps %s duplex\n", bond->dev->name, slave->dev->name, slave->speed == SPEED_UNKNOWN ? 0 : slave->speed, slave->duplex ? "full" : "half"); @@ -2004,7 +2006,8 @@ static void bond_miimon_commit(struct bonding *bond) if (bond->params.mode == BOND_MODE_ACTIVEBACKUP || bond->params.mode == BOND_MODE_8023AD) - bond_set_slave_inactive_flags(slave); + bond_set_slave_inactive_flags(slave, + BOND_SLAVE_NOTIFY_NOW); pr_info("%s: link status definitely down for interface %s, disabling it\n", bond->dev->name, slave->dev->name); @@ -2125,8 +2128,8 @@ static void bond_arp_send(struct net_device *slave_dev, int arp_op, __be32 dest_ { struct sk_buff *skb; - pr_debug("arp %d on slave %s: dst %pI4 src %pI4 vid %d\n", arp_op, - slave_dev->name, &dest_ip, &src_ip, vlan_id); + pr_debug("arp %d on slave %s: dst %pI4 src %pI4 vid %d\n", + arp_op, slave_dev->name, &dest_ip, &src_ip, vlan_id); skb = arp_create(arp_op, ETH_P_ARP, dest_ip, slave_dev, src_ip, NULL, slave_dev->dev_addr, NULL); @@ -2161,8 +2164,13 @@ static void bond_arp_send_all(struct bonding *bond, struct slave *slave) rt = ip_route_output(dev_net(bond->dev), targets[i], 0, RTO_ONLINK, 0); if (IS_ERR(rt)) { - pr_debug("%s: no route to arp_ip_target %pI4\n", - bond->dev->name, &targets[i]); + /* there's no route to target - try to send arp + * probe to generate any traffic (arp_validate=0) + */ + if (bond->params.arp_validate && net_ratelimit()) + pr_warn("%s: no route to arp_ip_target %pI4 and arp_validate is set\n", + bond->dev->name, &targets[i]); + bond_arp_send(slave->dev, ARPOP_REQUEST, targets[i], 0, 0); continue; } @@ -2240,7 +2248,7 @@ static void bond_validate_arp(struct bonding *bond, struct slave *slave, __be32 pr_debug("bva: sip %pI4 not found in targets\n", &sip); return; } - slave->last_arp_rx = jiffies; + slave->last_rx = jiffies; slave->target_last_arp_rx[i] = jiffies; } @@ -2248,17 +2256,19 @@ int bond_arp_rcv(const struct sk_buff *skb, struct bonding *bond, struct slave *slave) { struct arphdr *arp = (struct arphdr *)skb->data; + struct slave *curr_active_slave; unsigned char *arp_ptr; __be32 sip, tip; - int alen; + int alen, is_arp = skb->protocol == __cpu_to_be16(ETH_P_ARP); - if (skb->protocol != __cpu_to_be16(ETH_P_ARP)) + if (!slave_do_arp_validate(bond, slave)) { + if ((slave_do_arp_validate_only(bond, slave) && is_arp) || + !slave_do_arp_validate_only(bond, slave)) + slave->last_rx = jiffies; return RX_HANDLER_ANOTHER; - - read_lock(&bond->lock); - - if (!slave_do_arp_validate(bond, slave)) - goto out_unlock; + } else if (!is_arp) { + return RX_HANDLER_ANOTHER; + } alen = arp_hdr_len(bond->dev); @@ -2292,6 +2302,8 @@ int bond_arp_rcv(const struct sk_buff *skb, struct bonding *bond, bond->params.arp_validate, slave_do_arp_validate(bond, slave), &sip, &tip); + curr_active_slave = rcu_dereference(bond->curr_active_slave); + /* * Backup slaves won't see the ARP reply, but do come through * here for each ARP probe (so we swap the sip/tip to validate @@ -2305,15 +2317,15 @@ int bond_arp_rcv(const struct sk_buff *skb, struct bonding *bond, * is done to avoid endless looping when we can't reach the * arp_ip_target and fool ourselves with our own arp requests. */ + if (bond_is_active_slave(slave)) bond_validate_arp(bond, slave, sip, tip); - else if (bond->curr_active_slave && - time_after(slave_last_rx(bond, bond->curr_active_slave), - bond->curr_active_slave->jiffies)) + else if (curr_active_slave && + time_after(slave_last_rx(bond, curr_active_slave), + curr_active_slave->last_link_up)) bond_validate_arp(bond, slave, tip, sip); out_unlock: - read_unlock(&bond->lock); if (arp != (struct arphdr *)skb->data) kfree(arp); return RX_HANDLER_ANOTHER; @@ -2356,9 +2368,9 @@ static void bond_loadbalance_arp_mon(struct work_struct *work) oldcurrent = ACCESS_ONCE(bond->curr_active_slave); /* see if any of the previous devices are up now (i.e. they have * xmt and rcv traffic). the curr_active_slave does not come into - * the picture unless it is null. also, slave->jiffies is not needed - * here because we send an arp on each slave and give a slave as - * long as it needs to get the tx/rx within the delta. + * the picture unless it is null. also, slave->last_link_up is not + * needed here because we send an arp on each slave and give a slave + * as long as it needs to get the tx/rx within the delta. * TODO: what about up/down delay in arp mode? it wasn't here before * so it can wait */ @@ -2367,7 +2379,7 @@ static void bond_loadbalance_arp_mon(struct work_struct *work) if (slave->link != BOND_LINK_UP) { if (bond_time_in_interval(bond, trans_start, 1) && - bond_time_in_interval(bond, slave->dev->last_rx, 1)) { + bond_time_in_interval(bond, slave->last_rx, 1)) { slave->link = BOND_LINK_UP; slave_state_changed = 1; @@ -2378,7 +2390,7 @@ static void bond_loadbalance_arp_mon(struct work_struct *work) * is closed. */ if (!oldcurrent) { - pr_info("%s: link status definitely up for interface %s, ", + pr_info("%s: link status definitely up for interface %s\n", bond->dev->name, slave->dev->name); do_failover = 1; @@ -2396,7 +2408,7 @@ static void bond_loadbalance_arp_mon(struct work_struct *work) * if we don't know our ip yet */ if (!bond_time_in_interval(bond, trans_start, 2) || - !bond_time_in_interval(bond, slave->dev->last_rx, 2)) { + !bond_time_in_interval(bond, slave->last_rx, 2)) { slave->link = BOND_LINK_DOWN; slave_state_changed = 1; @@ -2404,9 +2416,8 @@ static void bond_loadbalance_arp_mon(struct work_struct *work) if (slave->link_failure_count < UINT_MAX) slave->link_failure_count++; - pr_info("%s: interface %s is now down.\n", - bond->dev->name, - slave->dev->name); + pr_info("%s: interface %s is now down\n", + bond->dev->name, slave->dev->name); if (slave == oldcurrent) do_failover = 1; @@ -2485,7 +2496,7 @@ static int bond_ab_arp_inspect(struct bonding *bond) * active. This avoids bouncing, as the last receive * times need a full ARP monitor cycle to be updated. */ - if (bond_time_in_interval(bond, slave->jiffies, 2)) + if (bond_time_in_interval(bond, slave->last_link_up, 2)) continue; /* @@ -2551,11 +2562,12 @@ static void bond_ab_arp_commit(struct bonding *bond) slave->link = BOND_LINK_UP; if (bond->current_arp_slave) { bond_set_slave_inactive_flags( - bond->current_arp_slave); + bond->current_arp_slave, + BOND_SLAVE_NOTIFY_NOW); bond->current_arp_slave = NULL; } - pr_info("%s: link status definitely up for interface %s.\n", + pr_info("%s: link status definitely up for interface %s\n", bond->dev->name, slave->dev->name); if (!bond->curr_active_slave || @@ -2571,7 +2583,8 @@ static void bond_ab_arp_commit(struct bonding *bond) slave->link_failure_count++; slave->link = BOND_LINK_DOWN; - bond_set_slave_inactive_flags(slave); + bond_set_slave_inactive_flags(slave, + BOND_SLAVE_NOTIFY_NOW); pr_info("%s: link status definitely down for interface %s, disabling it\n", bond->dev->name, slave->dev->name); @@ -2604,17 +2617,17 @@ do_failover: /* * Send ARP probes for active-backup mode ARP monitor. + * + * Called with rcu_read_lock hold. */ static bool bond_ab_arp_probe(struct bonding *bond) { struct slave *slave, *before = NULL, *new_slave = NULL, - *curr_arp_slave, *curr_active_slave; + *curr_arp_slave = rcu_dereference(bond->current_arp_slave), + *curr_active_slave = rcu_dereference(bond->curr_active_slave); struct list_head *iter; bool found = false; - - rcu_read_lock(); - curr_arp_slave = rcu_dereference(bond->current_arp_slave); - curr_active_slave = rcu_dereference(bond->curr_active_slave); + bool should_notify_rtnl = BOND_SLAVE_NOTIFY_LATER; if (curr_arp_slave && curr_active_slave) pr_info("PROBE: c_arp %s && cas %s BAD\n", @@ -2623,32 +2636,23 @@ static bool bond_ab_arp_probe(struct bonding *bond) if (curr_active_slave) { bond_arp_send_all(bond, curr_active_slave); - rcu_read_unlock(); - return true; + return should_notify_rtnl; } - rcu_read_unlock(); /* if we don't have a curr_active_slave, search for the next available * backup slave from the current_arp_slave and make it the candidate * for becoming the curr_active_slave */ - if (!rtnl_trylock()) - return false; - /* curr_arp_slave might have gone away */ - curr_arp_slave = ACCESS_ONCE(bond->current_arp_slave); - if (!curr_arp_slave) { - curr_arp_slave = bond_first_slave(bond); - if (!curr_arp_slave) { - rtnl_unlock(); - return true; - } + curr_arp_slave = bond_first_slave_rcu(bond); + if (!curr_arp_slave) + return should_notify_rtnl; } - bond_set_slave_inactive_flags(curr_arp_slave); + bond_set_slave_inactive_flags(curr_arp_slave, BOND_SLAVE_NOTIFY_LATER); - bond_for_each_slave(bond, slave, iter) { + bond_for_each_slave_rcu(bond, slave, iter) { if (!found && !before && IS_UP(slave->dev)) before = slave; @@ -2666,9 +2670,10 @@ static bool bond_ab_arp_probe(struct bonding *bond) if (slave->link_failure_count < UINT_MAX) slave->link_failure_count++; - bond_set_slave_inactive_flags(slave); + bond_set_slave_inactive_flags(slave, + BOND_SLAVE_NOTIFY_LATER); - pr_info("%s: backup interface %s is now down.\n", + pr_info("%s: backup interface %s is now down\n", bond->dev->name, slave->dev->name); } if (slave == curr_arp_slave) @@ -2678,26 +2683,31 @@ static bool bond_ab_arp_probe(struct bonding *bond) if (!new_slave && before) new_slave = before; - if (!new_slave) { - rtnl_unlock(); - return true; - } + if (!new_slave) + goto check_state; new_slave->link = BOND_LINK_BACK; - bond_set_slave_active_flags(new_slave); + bond_set_slave_active_flags(new_slave, BOND_SLAVE_NOTIFY_LATER); bond_arp_send_all(bond, new_slave); - new_slave->jiffies = jiffies; + new_slave->last_link_up = jiffies; rcu_assign_pointer(bond->current_arp_slave, new_slave); - rtnl_unlock(); - return true; +check_state: + bond_for_each_slave_rcu(bond, slave, iter) { + if (slave->should_notify) { + should_notify_rtnl = BOND_SLAVE_NOTIFY_NOW; + break; + } + } + return should_notify_rtnl; } static void bond_activebackup_arp_mon(struct work_struct *work) { struct bonding *bond = container_of(work, struct bonding, arp_work.work); - bool should_notify_peers = false, should_commit = false; + bool should_notify_peers = false; + bool should_notify_rtnl = false; int delta_in_ticks; delta_in_ticks = msecs_to_jiffies(bond->params.arp_interval); @@ -2706,11 +2716,12 @@ static void bond_activebackup_arp_mon(struct work_struct *work) goto re_arm; rcu_read_lock(); + should_notify_peers = bond_should_notify_peers(bond); - should_commit = bond_ab_arp_inspect(bond); - rcu_read_unlock(); - if (should_commit) { + if (bond_ab_arp_inspect(bond)) { + rcu_read_unlock(); + /* Race avoidance with bond_close flush of workqueue */ if (!rtnl_trylock()) { delta_in_ticks = 1; @@ -2719,23 +2730,28 @@ static void bond_activebackup_arp_mon(struct work_struct *work) } bond_ab_arp_commit(bond); + rtnl_unlock(); + rcu_read_lock(); } - if (!bond_ab_arp_probe(bond)) { - /* rtnl locking failed, re-arm */ - delta_in_ticks = 1; - should_notify_peers = false; - } + should_notify_rtnl = bond_ab_arp_probe(bond); + rcu_read_unlock(); re_arm: if (bond->params.arp_interval) queue_delayed_work(bond->wq, &bond->arp_work, delta_in_ticks); - if (should_notify_peers) { + if (should_notify_peers || should_notify_rtnl) { if (!rtnl_trylock()) return; - call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, bond->dev); + + if (should_notify_peers) + call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, + bond->dev); + if (should_notify_rtnl) + bond_slave_state_notify(bond); + rtnl_unlock(); } } @@ -2854,12 +2870,15 @@ static int bond_slave_netdev_event(unsigned long event, break; } - pr_info("%s: Primary slave changed to %s, reselecting active slave.\n", - bond->dev->name, bond->primary_slave ? slave_dev->name : - "none"); + pr_info("%s: Primary slave changed to %s, reselecting active slave\n", + bond->dev->name, + bond->primary_slave ? slave_dev->name : "none"); + + block_netpoll_tx(); write_lock_bh(&bond->curr_slave_lock); bond_select_active_slave(bond); write_unlock_bh(&bond->curr_slave_lock); + unblock_netpoll_tx(); break; case NETDEV_FEAT_CHANGE: bond_compute_features(bond); @@ -2889,8 +2908,7 @@ static int bond_netdev_event(struct notifier_block *this, struct net_device *event_dev = netdev_notifier_info_to_dev(ptr); pr_debug("event_dev: %s, event: %lx\n", - event_dev ? event_dev->name : "None", - event); + event_dev ? event_dev->name : "None", event); if (!(event_dev->priv_flags & IFF_BONDING)) return NOTIFY_DONE; @@ -3032,9 +3050,11 @@ static int bond_open(struct net_device *bond_dev) bond_for_each_slave(bond, slave, iter) { if ((bond->params.mode == BOND_MODE_ACTIVEBACKUP) && (slave != bond->curr_active_slave)) { - bond_set_slave_inactive_flags(slave); + bond_set_slave_inactive_flags(slave, + BOND_SLAVE_NOTIFY_NOW); } else { - bond_set_slave_active_flags(slave); + bond_set_slave_active_flags(slave, + BOND_SLAVE_NOTIFY_NOW); } } read_unlock(&bond->curr_slave_lock); @@ -3057,8 +3077,7 @@ static int bond_open(struct net_device *bond_dev) if (bond->params.arp_interval) { /* arp interval, in milliseconds. */ queue_delayed_work(bond->wq, &bond->arp_work, 0); - if (bond->params.arp_validate) - bond->recv_probe = bond_arp_rcv; + bond->recv_probe = bond_arp_rcv; } if (bond->params.mode == BOND_MODE_8023AD) { @@ -3345,8 +3364,8 @@ static int bond_change_mtu(struct net_device *bond_dev, int new_mtu) struct list_head *iter; int res = 0; - pr_debug("bond=%p, name=%s, new_mtu=%d\n", bond, - (bond_dev ? bond_dev->name : "None"), new_mtu); + pr_debug("bond=%p, name=%s, new_mtu=%d\n", + bond, bond_dev ? bond_dev->name : "None", new_mtu); /* Can't hold bond->lock with bh disabled here since * some base drivers panic. On the other hand we can't @@ -3365,8 +3384,7 @@ static int bond_change_mtu(struct net_device *bond_dev, int new_mtu) bond_for_each_slave(bond, slave, iter) { pr_debug("s %p c_m %p\n", - slave, - slave->dev->netdev_ops->ndo_change_mtu); + slave, slave->dev->netdev_ops->ndo_change_mtu); res = dev_set_mtu(slave->dev, new_mtu); @@ -3431,7 +3449,8 @@ static int bond_set_mac_address(struct net_device *bond_dev, void *addr) /* If fail_over_mac is enabled, do nothing and return success. * Returning an error causes ifenslave to fail. */ - if (bond->params.fail_over_mac) + if (bond->params.fail_over_mac && + bond->params.mode == BOND_MODE_ACTIVEBACKUP) return 0; if (!is_valid_ether_addr(sa->sa_data)) @@ -3453,15 +3472,7 @@ static int bond_set_mac_address(struct net_device *bond_dev, void *addr) */ bond_for_each_slave(bond, slave, iter) { - const struct net_device_ops *slave_ops = slave->dev->netdev_ops; pr_debug("slave %p %s\n", slave, slave->dev->name); - - if (slave_ops->ndo_set_mac_address == NULL) { - res = -EOPNOTSUPP; - pr_debug("EOPNOTSUPP %s\n", slave->dev->name); - goto unwind; - } - res = dev_set_mac_address(slave->dev, addr); if (res) { /* TODO: consider downing the slave @@ -3537,7 +3548,7 @@ static void bond_xmit_slave_id(struct bonding *bond, struct sk_buff *skb, int sl } } /* no slave that can tx has been found */ - kfree_skb(skb); + dev_kfree_skb_any(skb); } /** @@ -3613,7 +3624,7 @@ static int bond_xmit_activebackup(struct sk_buff *skb, struct net_device *bond_d if (slave) bond_dev_queue_xmit(bond, skb, slave->dev); else - kfree_skb(skb); + dev_kfree_skb_any(skb); return NETDEV_TX_OK; } @@ -3656,7 +3667,7 @@ static int bond_xmit_broadcast(struct sk_buff *skb, struct net_device *bond_dev) if (slave && IS_UP(slave->dev) && slave->link == BOND_LINK_UP) bond_dev_queue_xmit(bond, skb, slave->dev); else - kfree_skb(skb); + dev_kfree_skb_any(skb); return NETDEV_TX_OK; } @@ -3692,7 +3703,7 @@ static inline int bond_slave_override(struct bonding *bond, static u16 bond_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv) + void *accel_priv, select_queue_fallback_t fallback) { /* * This helper function exists to help dev_pick_tx get the correct @@ -3743,7 +3754,7 @@ static netdev_tx_t __bond_start_xmit(struct sk_buff *skb, struct net_device *dev pr_err("%s: Error: Unknown bonding mode %d\n", dev->name, bond->params.mode); WARN_ON_ONCE(1); - kfree_skb(skb); + dev_kfree_skb_any(skb); return NETDEV_TX_OK; } } @@ -3764,7 +3775,7 @@ static netdev_tx_t bond_start_xmit(struct sk_buff *skb, struct net_device *dev) if (bond_has_slaves(bond)) ret = __bond_start_xmit(skb, dev); else - kfree_skb(skb); + dev_kfree_skb_any(skb); rcu_read_unlock(); return ret; @@ -3927,7 +3938,7 @@ static void bond_uninit(struct net_device *bond_dev) /* Release the bonded slaves */ bond_for_each_slave(bond, slave, iter) __bond_release_one(bond_dev, slave->dev, true); - pr_info("%s: released all slaves\n", bond_dev->name); + pr_info("%s: Released all slaves\n", bond_dev->name); list_del(&bond->bond_list); @@ -3936,56 +3947,11 @@ static void bond_uninit(struct net_device *bond_dev) /*------------------------- Module initialization ---------------------------*/ -int bond_parm_tbl_lookup(int mode, const struct bond_parm_tbl *tbl) -{ - int i; - - for (i = 0; tbl[i].modename; i++) - if (mode == tbl[i].mode) - return tbl[i].mode; - - return -1; -} - -static int bond_parm_tbl_lookup_name(const char *modename, - const struct bond_parm_tbl *tbl) -{ - int i; - - for (i = 0; tbl[i].modename; i++) - if (strcmp(modename, tbl[i].modename) == 0) - return tbl[i].mode; - - return -1; -} - -/* - * Convert string input module parms. Accept either the - * number of the mode or its string name. A bit complicated because - * some mode names are substrings of other names, and calls from sysfs - * may have whitespace in the name (trailing newlines, for example). - */ -int bond_parse_parm(const char *buf, const struct bond_parm_tbl *tbl) -{ - int modeint; - char *p, modestr[BOND_MAX_MODENAME_LEN + 1]; - - for (p = (char *)buf; *p; p++) - if (!(isdigit(*p) || isspace(*p))) - break; - - if (*p && sscanf(buf, "%20s", modestr) != 0) - return bond_parm_tbl_lookup_name(modestr, tbl); - else if (sscanf(buf, "%d", &modeint) != 0) - return bond_parm_tbl_lookup(modeint, tbl); - - return -1; -} - static int bond_check_params(struct bond_params *params) { int arp_validate_value, fail_over_mac_value, primary_reselect_value, i; - struct bond_opt_value newval, *valptr; + struct bond_opt_value newval; + const struct bond_opt_value *valptr; int arp_all_targets_value; /* @@ -4005,7 +3971,7 @@ static int bond_check_params(struct bond_params *params) if ((bond_mode != BOND_MODE_XOR) && (bond_mode != BOND_MODE_8023AD)) { pr_info("xmit_hash_policy param is irrelevant in mode %s\n", - bond_mode_name(bond_mode)); + bond_mode_name(bond_mode)); } else { bond_opt_initstr(&newval, xmit_hash_policy); valptr = bond_opt_parse(bond_opt_get(BOND_OPT_XMIT_HASH), @@ -4046,74 +4012,71 @@ static int bond_check_params(struct bond_params *params) } params->ad_select = valptr->value; if (bond_mode != BOND_MODE_8023AD) - pr_warning("ad_select param only affects 802.3ad mode\n"); + pr_warn("ad_select param only affects 802.3ad mode\n"); } else { params->ad_select = BOND_AD_STABLE; } if (max_bonds < 0) { - pr_warning("Warning: max_bonds (%d) not in range %d-%d, so it was reset to BOND_DEFAULT_MAX_BONDS (%d)\n", - max_bonds, 0, INT_MAX, BOND_DEFAULT_MAX_BONDS); + pr_warn("Warning: max_bonds (%d) not in range %d-%d, so it was reset to BOND_DEFAULT_MAX_BONDS (%d)\n", + max_bonds, 0, INT_MAX, BOND_DEFAULT_MAX_BONDS); max_bonds = BOND_DEFAULT_MAX_BONDS; } if (miimon < 0) { - pr_warning("Warning: miimon module parameter (%d), not in range 0-%d, so it was reset to 0\n", - miimon, INT_MAX); + pr_warn("Warning: miimon module parameter (%d), not in range 0-%d, so it was reset to 0\n", + miimon, INT_MAX); miimon = 0; } if (updelay < 0) { - pr_warning("Warning: updelay module parameter (%d), not in range 0-%d, so it was reset to 0\n", - updelay, INT_MAX); + pr_warn("Warning: updelay module parameter (%d), not in range 0-%d, so it was reset to 0\n", + updelay, INT_MAX); updelay = 0; } if (downdelay < 0) { - pr_warning("Warning: downdelay module parameter (%d), not in range 0-%d, so it was reset to 0\n", - downdelay, INT_MAX); + pr_warn("Warning: downdelay module parameter (%d), not in range 0-%d, so it was reset to 0\n", + downdelay, INT_MAX); downdelay = 0; } if ((use_carrier != 0) && (use_carrier != 1)) { - pr_warning("Warning: use_carrier module parameter (%d), not of valid value (0/1), so it was set to 1\n", - use_carrier); + pr_warn("Warning: use_carrier module parameter (%d), not of valid value (0/1), so it was set to 1\n", + use_carrier); use_carrier = 1; } if (num_peer_notif < 0 || num_peer_notif > 255) { - pr_warning("Warning: num_grat_arp/num_unsol_na (%d) not in range 0-255 so it was reset to 1\n", - num_peer_notif); + pr_warn("Warning: num_grat_arp/num_unsol_na (%d) not in range 0-255 so it was reset to 1\n", + num_peer_notif); num_peer_notif = 1; } /* reset values for 802.3ad/TLB/ALB */ if (BOND_NO_USES_ARP(bond_mode)) { if (!miimon) { - pr_warning("Warning: miimon must be specified, otherwise bonding will not detect link failure, speed and duplex which are essential for 802.3ad operation\n"); - pr_warning("Forcing miimon to 100msec\n"); + pr_warn("Warning: miimon must be specified, otherwise bonding will not detect link failure, speed and duplex which are essential for 802.3ad operation\n"); + pr_warn("Forcing miimon to 100msec\n"); miimon = BOND_DEFAULT_MIIMON; } } if (tx_queues < 1 || tx_queues > 255) { - pr_warning("Warning: tx_queues (%d) should be between " - "1 and 255, resetting to %d\n", - tx_queues, BOND_DEFAULT_TX_QUEUES); + pr_warn("Warning: tx_queues (%d) should be between 1 and 255, resetting to %d\n", + tx_queues, BOND_DEFAULT_TX_QUEUES); tx_queues = BOND_DEFAULT_TX_QUEUES; } if ((all_slaves_active != 0) && (all_slaves_active != 1)) { - pr_warning("Warning: all_slaves_active module parameter (%d), " - "not of valid value (0/1), so it was set to " - "0\n", all_slaves_active); + pr_warn("Warning: all_slaves_active module parameter (%d), not of valid value (0/1), so it was set to 0\n", + all_slaves_active); all_slaves_active = 0; } if (resend_igmp < 0 || resend_igmp > 255) { - pr_warning("Warning: resend_igmp (%d) should be between " - "0 and 255, resetting to %d\n", - resend_igmp, BOND_DEFAULT_RESEND_IGMP); + pr_warn("Warning: resend_igmp (%d) should be between 0 and 255, resetting to %d\n", + resend_igmp, BOND_DEFAULT_RESEND_IGMP); resend_igmp = BOND_DEFAULT_RESEND_IGMP; } @@ -4134,37 +4097,36 @@ static int bond_check_params(struct bond_params *params) /* just warn the user the up/down delay will have * no effect since miimon is zero... */ - pr_warning("Warning: miimon module parameter not set and updelay (%d) or downdelay (%d) module parameter is set; updelay and downdelay have no effect unless miimon is set\n", - updelay, downdelay); + pr_warn("Warning: miimon module parameter not set and updelay (%d) or downdelay (%d) module parameter is set; updelay and downdelay have no effect unless miimon is set\n", + updelay, downdelay); } } else { /* don't allow arp monitoring */ if (arp_interval) { - pr_warning("Warning: miimon (%d) and arp_interval (%d) can't be used simultaneously, disabling ARP monitoring\n", - miimon, arp_interval); + pr_warn("Warning: miimon (%d) and arp_interval (%d) can't be used simultaneously, disabling ARP monitoring\n", + miimon, arp_interval); arp_interval = 0; } if ((updelay % miimon) != 0) { - pr_warning("Warning: updelay (%d) is not a multiple of miimon (%d), updelay rounded to %d ms\n", - updelay, miimon, - (updelay / miimon) * miimon); + pr_warn("Warning: updelay (%d) is not a multiple of miimon (%d), updelay rounded to %d ms\n", + updelay, miimon, (updelay / miimon) * miimon); } updelay /= miimon; if ((downdelay % miimon) != 0) { - pr_warning("Warning: downdelay (%d) is not a multiple of miimon (%d), downdelay rounded to %d ms\n", - downdelay, miimon, - (downdelay / miimon) * miimon); + pr_warn("Warning: downdelay (%d) is not a multiple of miimon (%d), downdelay rounded to %d ms\n", + downdelay, miimon, + (downdelay / miimon) * miimon); } downdelay /= miimon; } if (arp_interval < 0) { - pr_warning("Warning: arp_interval module parameter (%d) , not in range 0-%d, so it was reset to 0\n", - arp_interval, INT_MAX); + pr_warn("Warning: arp_interval module parameter (%d), not in range 0-%d, so it was reset to 0\n", + arp_interval, INT_MAX); arp_interval = 0; } @@ -4175,30 +4137,26 @@ static int bond_check_params(struct bond_params *params) __be32 ip; if (!in4_pton(arp_ip_target[i], -1, (u8 *)&ip, -1, NULL) || IS_IP_TARGET_UNUSABLE_ADDRESS(ip)) { - pr_warning("Warning: bad arp_ip_target module parameter (%s), ARP monitoring will not be performed\n", - arp_ip_target[i]); + pr_warn("Warning: bad arp_ip_target module parameter (%s), ARP monitoring will not be performed\n", + arp_ip_target[i]); arp_interval = 0; } else { if (bond_get_targets_ip(arp_target, ip) == -1) arp_target[arp_ip_count++] = ip; else - pr_warning("Warning: duplicate address %pI4 in arp_ip_target, skipping\n", - &ip); + pr_warn("Warning: duplicate address %pI4 in arp_ip_target, skipping\n", + &ip); } } if (arp_interval && !arp_ip_count) { /* don't allow arping if no arp_ip_target given... */ - pr_warning("Warning: arp_interval module parameter (%d) specified without providing an arp_ip_target parameter, arp_interval was reset to 0\n", - arp_interval); + pr_warn("Warning: arp_interval module parameter (%d) specified without providing an arp_ip_target parameter, arp_interval was reset to 0\n", + arp_interval); arp_interval = 0; } if (arp_validate) { - if (bond_mode != BOND_MODE_ACTIVEBACKUP) { - pr_err("arp_validate only supported in active-backup mode\n"); - return -EINVAL; - } if (!arp_interval) { pr_err("arp_validate requires arp_interval\n"); return -EINVAL; @@ -4240,23 +4198,23 @@ static int bond_check_params(struct bond_params *params) arp_interval, valptr->string, arp_ip_count); for (i = 0; i < arp_ip_count; i++) - pr_info(" %s", arp_ip_target[i]); + pr_cont(" %s", arp_ip_target[i]); - pr_info("\n"); + pr_cont("\n"); } else if (max_bonds) { /* miimon and arp_interval not set, we need one so things * work as expected, see bonding.txt for details */ - pr_debug("Warning: either miimon or arp_interval and arp_ip_target module parameters must be specified, otherwise bonding will not detect link failures! see bonding.txt for details.\n"); + pr_debug("Warning: either miimon or arp_interval and arp_ip_target module parameters must be specified, otherwise bonding will not detect link failures! see bonding.txt for details\n"); } if (primary && !USES_PRIMARY(bond_mode)) { /* currently, using a primary only makes sense * in active backup, TLB or ALB modes */ - pr_warning("Warning: %s primary device specified but has no effect in %s mode\n", - primary, bond_mode_name(bond_mode)); + pr_warn("Warning: %s primary device specified but has no effect in %s mode\n", + primary, bond_mode_name(bond_mode)); primary = NULL; } @@ -4285,14 +4243,14 @@ static int bond_check_params(struct bond_params *params) } fail_over_mac_value = valptr->value; if (bond_mode != BOND_MODE_ACTIVEBACKUP) - pr_warning("Warning: fail_over_mac only affects active-backup mode.\n"); + pr_warn("Warning: fail_over_mac only affects active-backup mode\n"); } else { fail_over_mac_value = BOND_FOM_NONE; } if (lp_interval == 0) { - pr_warning("Warning: ip_interval must be between 1 and %d, so it was reset to %d\n", - INT_MAX, BOND_ALB_DEFAULT_LP_INTERVAL); + pr_warn("Warning: ip_interval must be between 1 and %d, so it was reset to %d\n", + INT_MAX, BOND_ALB_DEFAULT_LP_INTERVAL); lp_interval = BOND_ALB_DEFAULT_LP_INTERVAL; } diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c index 70651f8e8e3b..f847e165d252 100644 --- a/drivers/net/bonding/bond_netlink.c +++ b/drivers/net/bonding/bond_netlink.c @@ -181,7 +181,7 @@ static int bond_changelink(struct net_device *bond_dev, int arp_interval = nla_get_u32(data[IFLA_BOND_ARP_INTERVAL]); if (arp_interval && miimon) { - pr_err("%s: ARP monitoring cannot be used with MII monitoring.\n", + pr_err("%s: ARP monitoring cannot be used with MII monitoring\n", bond->dev->name); return -EINVAL; } @@ -199,7 +199,7 @@ static int bond_changelink(struct net_device *bond_dev, nla_for_each_nested(attr, data[IFLA_BOND_ARP_IP_TARGET], rem) { __be32 target = nla_get_be32(attr); - bond_opt_initval(&newval, target); + bond_opt_initval(&newval, (__force u64)target); err = __bond_opt_set(bond, BOND_OPT_ARP_TARGETS, &newval); if (err) @@ -207,7 +207,7 @@ static int bond_changelink(struct net_device *bond_dev, i++; } if (i == 0 && bond->params.arp_interval) - pr_warn("%s: removing last arp target with arp_interval on\n", + pr_warn("%s: Removing last arp target with arp_interval on\n", bond->dev->name); if (err) return err; @@ -216,7 +216,7 @@ static int bond_changelink(struct net_device *bond_dev, int arp_validate = nla_get_u32(data[IFLA_BOND_ARP_VALIDATE]); if (arp_validate && miimon) { - pr_err("%s: ARP validating cannot be used with MII monitoring.\n", + pr_err("%s: ARP validating cannot be used with MII monitoring\n", bond->dev->name); return -EINVAL; } diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c index 11cb943222d5..22800bde9752 100644 --- a/drivers/net/bonding/bond_options.c +++ b/drivers/net/bonding/bond_options.c @@ -14,13 +14,65 @@ #include <linux/errno.h> #include <linux/if.h> #include <linux/netdevice.h> -#include <linux/rwlock.h> +#include <linux/spinlock.h> #include <linux/rcupdate.h> #include <linux/ctype.h> #include <linux/inet.h> #include "bonding.h" -static struct bond_opt_value bond_mode_tbl[] = { +static int bond_option_active_slave_set(struct bonding *bond, + const struct bond_opt_value *newval); +static int bond_option_miimon_set(struct bonding *bond, + const struct bond_opt_value *newval); +static int bond_option_updelay_set(struct bonding *bond, + const struct bond_opt_value *newval); +static int bond_option_downdelay_set(struct bonding *bond, + const struct bond_opt_value *newval); +static int bond_option_use_carrier_set(struct bonding *bond, + const struct bond_opt_value *newval); +static int bond_option_arp_interval_set(struct bonding *bond, + const struct bond_opt_value *newval); +static int bond_option_arp_ip_target_add(struct bonding *bond, __be32 target); +static int bond_option_arp_ip_target_rem(struct bonding *bond, __be32 target); +static int bond_option_arp_ip_targets_set(struct bonding *bond, + const struct bond_opt_value *newval); +static int bond_option_arp_validate_set(struct bonding *bond, + const struct bond_opt_value *newval); +static int bond_option_arp_all_targets_set(struct bonding *bond, + const struct bond_opt_value *newval); +static int bond_option_primary_set(struct bonding *bond, + const struct bond_opt_value *newval); +static int bond_option_primary_reselect_set(struct bonding *bond, + const struct bond_opt_value *newval); +static int bond_option_fail_over_mac_set(struct bonding *bond, + const struct bond_opt_value *newval); +static int bond_option_xmit_hash_policy_set(struct bonding *bond, + const struct bond_opt_value *newval); +static int bond_option_resend_igmp_set(struct bonding *bond, + const struct bond_opt_value *newval); +static int bond_option_num_peer_notif_set(struct bonding *bond, + const struct bond_opt_value *newval); +static int bond_option_all_slaves_active_set(struct bonding *bond, + const struct bond_opt_value *newval); +static int bond_option_min_links_set(struct bonding *bond, + const struct bond_opt_value *newval); +static int bond_option_lp_interval_set(struct bonding *bond, + const struct bond_opt_value *newval); +static int bond_option_pps_set(struct bonding *bond, + const struct bond_opt_value *newval); +static int bond_option_lacp_rate_set(struct bonding *bond, + const struct bond_opt_value *newval); +static int bond_option_ad_select_set(struct bonding *bond, + const struct bond_opt_value *newval); +static int bond_option_queue_id_set(struct bonding *bond, + const struct bond_opt_value *newval); +static int bond_option_mode_set(struct bonding *bond, + const struct bond_opt_value *newval); +static int bond_option_slaves_set(struct bonding *bond, + const struct bond_opt_value *newval); + + +static const struct bond_opt_value bond_mode_tbl[] = { { "balance-rr", BOND_MODE_ROUNDROBIN, BOND_VALFLAG_DEFAULT}, { "active-backup", BOND_MODE_ACTIVEBACKUP, 0}, { "balance-xor", BOND_MODE_XOR, 0}, @@ -31,13 +83,13 @@ static struct bond_opt_value bond_mode_tbl[] = { { NULL, -1, 0}, }; -static struct bond_opt_value bond_pps_tbl[] = { +static const struct bond_opt_value bond_pps_tbl[] = { { "default", 1, BOND_VALFLAG_DEFAULT}, { "maxval", USHRT_MAX, BOND_VALFLAG_MAX}, { NULL, -1, 0}, }; -static struct bond_opt_value bond_xmit_hashtype_tbl[] = { +static const struct bond_opt_value bond_xmit_hashtype_tbl[] = { { "layer2", BOND_XMIT_POLICY_LAYER2, BOND_VALFLAG_DEFAULT}, { "layer3+4", BOND_XMIT_POLICY_LAYER34, 0}, { "layer2+3", BOND_XMIT_POLICY_LAYER23, 0}, @@ -46,84 +98,87 @@ static struct bond_opt_value bond_xmit_hashtype_tbl[] = { { NULL, -1, 0}, }; -static struct bond_opt_value bond_arp_validate_tbl[] = { - { "none", BOND_ARP_VALIDATE_NONE, BOND_VALFLAG_DEFAULT}, - { "active", BOND_ARP_VALIDATE_ACTIVE, 0}, - { "backup", BOND_ARP_VALIDATE_BACKUP, 0}, - { "all", BOND_ARP_VALIDATE_ALL, 0}, - { NULL, -1, 0}, +static const struct bond_opt_value bond_arp_validate_tbl[] = { + { "none", BOND_ARP_VALIDATE_NONE, BOND_VALFLAG_DEFAULT}, + { "active", BOND_ARP_VALIDATE_ACTIVE, 0}, + { "backup", BOND_ARP_VALIDATE_BACKUP, 0}, + { "all", BOND_ARP_VALIDATE_ALL, 0}, + { "filter", BOND_ARP_FILTER, 0}, + { "filter_active", BOND_ARP_FILTER_ACTIVE, 0}, + { "filter_backup", BOND_ARP_FILTER_BACKUP, 0}, + { NULL, -1, 0}, }; -static struct bond_opt_value bond_arp_all_targets_tbl[] = { +static const struct bond_opt_value bond_arp_all_targets_tbl[] = { { "any", BOND_ARP_TARGETS_ANY, BOND_VALFLAG_DEFAULT}, { "all", BOND_ARP_TARGETS_ALL, 0}, { NULL, -1, 0}, }; -static struct bond_opt_value bond_fail_over_mac_tbl[] = { +static const struct bond_opt_value bond_fail_over_mac_tbl[] = { { "none", BOND_FOM_NONE, BOND_VALFLAG_DEFAULT}, { "active", BOND_FOM_ACTIVE, 0}, { "follow", BOND_FOM_FOLLOW, 0}, { NULL, -1, 0}, }; -static struct bond_opt_value bond_intmax_tbl[] = { +static const struct bond_opt_value bond_intmax_tbl[] = { { "off", 0, BOND_VALFLAG_DEFAULT}, { "maxval", INT_MAX, BOND_VALFLAG_MAX}, }; -static struct bond_opt_value bond_lacp_rate_tbl[] = { +static const struct bond_opt_value bond_lacp_rate_tbl[] = { { "slow", AD_LACP_SLOW, 0}, { "fast", AD_LACP_FAST, 0}, { NULL, -1, 0}, }; -static struct bond_opt_value bond_ad_select_tbl[] = { +static const struct bond_opt_value bond_ad_select_tbl[] = { { "stable", BOND_AD_STABLE, BOND_VALFLAG_DEFAULT}, { "bandwidth", BOND_AD_BANDWIDTH, 0}, { "count", BOND_AD_COUNT, 0}, { NULL, -1, 0}, }; -static struct bond_opt_value bond_num_peer_notif_tbl[] = { +static const struct bond_opt_value bond_num_peer_notif_tbl[] = { { "off", 0, 0}, { "maxval", 255, BOND_VALFLAG_MAX}, { "default", 1, BOND_VALFLAG_DEFAULT}, { NULL, -1, 0} }; -static struct bond_opt_value bond_primary_reselect_tbl[] = { +static const struct bond_opt_value bond_primary_reselect_tbl[] = { { "always", BOND_PRI_RESELECT_ALWAYS, BOND_VALFLAG_DEFAULT}, { "better", BOND_PRI_RESELECT_BETTER, 0}, { "failure", BOND_PRI_RESELECT_FAILURE, 0}, { NULL, -1}, }; -static struct bond_opt_value bond_use_carrier_tbl[] = { +static const struct bond_opt_value bond_use_carrier_tbl[] = { { "off", 0, 0}, { "on", 1, BOND_VALFLAG_DEFAULT}, { NULL, -1, 0} }; -static struct bond_opt_value bond_all_slaves_active_tbl[] = { +static const struct bond_opt_value bond_all_slaves_active_tbl[] = { { "off", 0, BOND_VALFLAG_DEFAULT}, { "on", 1, 0}, { NULL, -1, 0} }; -static struct bond_opt_value bond_resend_igmp_tbl[] = { +static const struct bond_opt_value bond_resend_igmp_tbl[] = { { "off", 0, 0}, { "maxval", 255, BOND_VALFLAG_MAX}, { "default", 1, BOND_VALFLAG_DEFAULT}, { NULL, -1, 0} }; -static struct bond_opt_value bond_lp_interval_tbl[] = { +static const struct bond_opt_value bond_lp_interval_tbl[] = { { "minval", 1, BOND_VALFLAG_MIN | BOND_VALFLAG_DEFAULT}, { "maxval", INT_MAX, BOND_VALFLAG_MAX}, }; -static struct bond_option bond_opts[] = { +static const struct bond_option bond_opts[] = { [BOND_OPT_MODE] = { .id = BOND_OPT_MODE, .name = "mode", @@ -151,7 +206,8 @@ static struct bond_option bond_opts[] = { .id = BOND_OPT_ARP_VALIDATE, .name = "arp_validate", .desc = "validate src/dst of ARP probes", - .unsuppmodes = BOND_MODE_ALL_EX(BIT(BOND_MODE_ACTIVEBACKUP)), + .unsuppmodes = BIT(BOND_MODE_8023AD) | BIT(BOND_MODE_TLB) | + BIT(BOND_MODE_ALB), .values = bond_arp_validate_tbl, .set = bond_option_arp_validate_set }, @@ -311,9 +367,9 @@ static struct bond_option bond_opts[] = { }; /* Searches for a value in opt's values[] table */ -struct bond_opt_value *bond_opt_get_val(unsigned int option, u64 val) +const struct bond_opt_value *bond_opt_get_val(unsigned int option, u64 val) { - struct bond_option *opt; + const struct bond_option *opt; int i; opt = bond_opt_get(option); @@ -327,7 +383,7 @@ struct bond_opt_value *bond_opt_get_val(unsigned int option, u64 val) } /* Searches for a value in opt's values[] table which matches the flagmask */ -static struct bond_opt_value *bond_opt_get_flags(const struct bond_option *opt, +static const struct bond_opt_value *bond_opt_get_flags(const struct bond_option *opt, u32 flagmask) { int i; @@ -344,7 +400,7 @@ static struct bond_opt_value *bond_opt_get_flags(const struct bond_option *opt, */ static bool bond_opt_check_range(const struct bond_option *opt, u64 val) { - struct bond_opt_value *minval, *maxval; + const struct bond_opt_value *minval, *maxval; minval = bond_opt_get_flags(opt, BOND_VALFLAG_MIN); maxval = bond_opt_get_flags(opt, BOND_VALFLAG_MAX); @@ -364,11 +420,12 @@ static bool bond_opt_check_range(const struct bond_option *opt, u64 val) * or the struct_opt_value that matched. It also strips the new line from * @val->string if it's present. */ -struct bond_opt_value *bond_opt_parse(const struct bond_option *opt, - struct bond_opt_value *val) +const struct bond_opt_value *bond_opt_parse(const struct bond_option *opt, + struct bond_opt_value *val) { char *p, valstr[BOND_OPT_MAX_NAMELEN + 1] = { 0, }; - struct bond_opt_value *tbl, *ret = NULL; + const struct bond_opt_value *tbl; + const struct bond_opt_value *ret = NULL; bool checkval; int i, rv; @@ -447,7 +504,7 @@ static int bond_opt_check_deps(struct bonding *bond, static void bond_opt_dep_print(struct bonding *bond, const struct bond_option *opt) { - struct bond_opt_value *modeval; + const struct bond_opt_value *modeval; struct bond_params *params; params = &bond->params; @@ -460,9 +517,9 @@ static void bond_opt_dep_print(struct bonding *bond, static void bond_opt_error_interpret(struct bonding *bond, const struct bond_option *opt, - int error, struct bond_opt_value *val) + int error, const struct bond_opt_value *val) { - struct bond_opt_value *minval, *maxval; + const struct bond_opt_value *minval, *maxval; char *p; switch (error) { @@ -473,10 +530,10 @@ static void bond_opt_error_interpret(struct bonding *bond, p = strchr(val->string, '\n'); if (p) *p = '\0'; - pr_err("%s: option %s: invalid value (%s).\n", + pr_err("%s: option %s: invalid value (%s)\n", bond->dev->name, opt->name, val->string); } else { - pr_err("%s: option %s: invalid value (%llu).\n", + pr_err("%s: option %s: invalid value (%llu)\n", bond->dev->name, opt->name, val->value); } } @@ -484,7 +541,7 @@ static void bond_opt_error_interpret(struct bonding *bond, maxval = bond_opt_get_flags(opt, BOND_VALFLAG_MAX); if (!maxval) break; - pr_err("%s: option %s: allowed values %llu - %llu.\n", + pr_err("%s: option %s: allowed values %llu - %llu\n", bond->dev->name, opt->name, minval ? minval->value : 0, maxval->value); break; @@ -492,11 +549,11 @@ static void bond_opt_error_interpret(struct bonding *bond, bond_opt_dep_print(bond, opt); break; case -ENOTEMPTY: - pr_err("%s: option %s: unable to set because the bond device has slaves.\n", + pr_err("%s: option %s: unable to set because the bond device has slaves\n", bond->dev->name, opt->name); break; case -EBUSY: - pr_err("%s: option %s: unable to set because the bond device is up.\n", + pr_err("%s: option %s: unable to set because the bond device is up\n", bond->dev->name, opt->name); break; default: @@ -517,7 +574,7 @@ static void bond_opt_error_interpret(struct bonding *bond, int __bond_opt_set(struct bonding *bond, unsigned int option, struct bond_opt_value *val) { - struct bond_opt_value *retval = NULL; + const struct bond_opt_value *retval = NULL; const struct bond_option *opt; int ret = -ENOENT; @@ -572,7 +629,7 @@ int bond_opt_tryset_rtnl(struct bonding *bond, unsigned int option, char *buf) * This function checks if option is valid and if so returns a pointer * to its entry in the bond_opts[] option array. */ -struct bond_option *bond_opt_get(unsigned int option) +const struct bond_option *bond_opt_get(unsigned int option) { if (!BOND_OPT_VALID(option)) return NULL; @@ -580,7 +637,7 @@ struct bond_option *bond_opt_get(unsigned int option) return &bond_opts[option]; } -int bond_option_mode_set(struct bonding *bond, struct bond_opt_value *newval) +int bond_option_mode_set(struct bonding *bond, const struct bond_opt_value *newval) { if (BOND_NO_USES_ARP(newval->value) && bond->params.arp_interval) { pr_info("%s: %s mode is incompatible with arp monitoring, start mii monitoring\n", @@ -589,7 +646,7 @@ int bond_option_mode_set(struct bonding *bond, struct bond_opt_value *newval) bond->params.arp_interval = 0; /* set miimon to default value */ bond->params.miimon = BOND_DEFAULT_MIIMON; - pr_info("%s: Setting MII monitoring interval to %d.\n", + pr_info("%s: Setting MII monitoring interval to %d\n", bond->dev->name, bond->params.miimon); } @@ -618,8 +675,8 @@ struct net_device *bond_option_active_slave_get(struct bonding *bond) return __bond_option_active_slave_get(bond, bond->curr_active_slave); } -int bond_option_active_slave_set(struct bonding *bond, - struct bond_opt_value *newval) +static int bond_option_active_slave_set(struct bonding *bond, + const struct bond_opt_value *newval) { char ifname[IFNAMSIZ] = { 0, }; struct net_device *slave_dev; @@ -636,13 +693,13 @@ int bond_option_active_slave_set(struct bonding *bond, if (slave_dev) { if (!netif_is_bond_slave(slave_dev)) { - pr_err("Device %s is not bonding slave.\n", + pr_err("Device %s is not bonding slave\n", slave_dev->name); return -EINVAL; } if (bond->dev != netdev_master_upper_dev_get(slave_dev)) { - pr_err("%s: Device %s is not our slave.\n", + pr_err("%s: Device %s is not our slave\n", bond->dev->name, slave_dev->name); return -EINVAL; } @@ -653,8 +710,7 @@ int bond_option_active_slave_set(struct bonding *bond, /* check to see if we are clearing active */ if (!slave_dev) { - pr_info("%s: Clearing current active slave.\n", - bond->dev->name); + pr_info("%s: Clearing current active slave\n", bond->dev->name); rcu_assign_pointer(bond->curr_active_slave, NULL); bond_select_active_slave(bond); } else { @@ -665,16 +721,16 @@ int bond_option_active_slave_set(struct bonding *bond, if (new_active == old_active) { /* do nothing */ - pr_info("%s: %s is already the current active slave.\n", + pr_info("%s: %s is already the current active slave\n", bond->dev->name, new_active->dev->name); } else { if (old_active && (new_active->link == BOND_LINK_UP) && IS_UP(new_active->dev)) { - pr_info("%s: Setting %s as active slave.\n", + pr_info("%s: Setting %s as active slave\n", bond->dev->name, new_active->dev->name); bond_change_active_slave(bond, new_active); } else { - pr_err("%s: Could not set %s as active slave; either %s is down or the link is down.\n", + pr_err("%s: Could not set %s as active slave; either %s is down or the link is down\n", bond->dev->name, new_active->dev->name, new_active->dev->name); ret = -EINVAL; @@ -688,21 +744,22 @@ int bond_option_active_slave_set(struct bonding *bond, return ret; } -int bond_option_miimon_set(struct bonding *bond, struct bond_opt_value *newval) +static int bond_option_miimon_set(struct bonding *bond, + const struct bond_opt_value *newval) { - pr_info("%s: Setting MII monitoring interval to %llu.\n", + pr_info("%s: Setting MII monitoring interval to %llu\n", bond->dev->name, newval->value); bond->params.miimon = newval->value; if (bond->params.updelay) - pr_info("%s: Note: Updating updelay (to %d) since it is a multiple of the miimon value.\n", + pr_info("%s: Note: Updating updelay (to %d) since it is a multiple of the miimon value\n", bond->dev->name, bond->params.updelay * bond->params.miimon); if (bond->params.downdelay) - pr_info("%s: Note: Updating downdelay (to %d) since it is a multiple of the miimon value.\n", + pr_info("%s: Note: Updating downdelay (to %d) since it is a multiple of the miimon value\n", bond->dev->name, bond->params.downdelay * bond->params.miimon); if (newval->value && bond->params.arp_interval) { - pr_info("%s: MII monitoring cannot be used with ARP monitoring. Disabling ARP monitoring...\n", + pr_info("%s: MII monitoring cannot be used with ARP monitoring - disabling ARP monitoring...\n", bond->dev->name); bond->params.arp_interval = 0; if (bond->params.arp_validate) @@ -725,7 +782,8 @@ int bond_option_miimon_set(struct bonding *bond, struct bond_opt_value *newval) return 0; } -int bond_option_updelay_set(struct bonding *bond, struct bond_opt_value *newval) +static int bond_option_updelay_set(struct bonding *bond, + const struct bond_opt_value *newval) { int value = newval->value; @@ -742,15 +800,14 @@ int bond_option_updelay_set(struct bonding *bond, struct bond_opt_value *newval) bond->params.miimon); } bond->params.updelay = value / bond->params.miimon; - pr_info("%s: Setting up delay to %d.\n", - bond->dev->name, - bond->params.updelay * bond->params.miimon); + pr_info("%s: Setting up delay to %d\n", + bond->dev->name, bond->params.updelay * bond->params.miimon); return 0; } -int bond_option_downdelay_set(struct bonding *bond, - struct bond_opt_value *newval) +static int bond_option_downdelay_set(struct bonding *bond, + const struct bond_opt_value *newval) { int value = newval->value; @@ -767,37 +824,36 @@ int bond_option_downdelay_set(struct bonding *bond, bond->params.miimon); } bond->params.downdelay = value / bond->params.miimon; - pr_info("%s: Setting down delay to %d.\n", - bond->dev->name, - bond->params.downdelay * bond->params.miimon); + pr_info("%s: Setting down delay to %d\n", + bond->dev->name, bond->params.downdelay * bond->params.miimon); return 0; } -int bond_option_use_carrier_set(struct bonding *bond, - struct bond_opt_value *newval) +static int bond_option_use_carrier_set(struct bonding *bond, + const struct bond_opt_value *newval) { - pr_info("%s: Setting use_carrier to %llu.\n", + pr_info("%s: Setting use_carrier to %llu\n", bond->dev->name, newval->value); bond->params.use_carrier = newval->value; return 0; } -int bond_option_arp_interval_set(struct bonding *bond, - struct bond_opt_value *newval) +static int bond_option_arp_interval_set(struct bonding *bond, + const struct bond_opt_value *newval) { - pr_info("%s: Setting ARP monitoring interval to %llu.\n", + pr_info("%s: Setting ARP monitoring interval to %llu\n", bond->dev->name, newval->value); bond->params.arp_interval = newval->value; if (newval->value) { if (bond->params.miimon) { - pr_info("%s: ARP monitoring cannot be used with MII monitoring. %s Disabling MII monitoring.\n", + pr_info("%s: ARP monitoring cannot be used with MII monitoring. %s Disabling MII monitoring\n", bond->dev->name, bond->dev->name); bond->params.miimon = 0; } if (!bond->params.arp_targets[0]) - pr_info("%s: ARP monitoring has been set up, but no ARP targets have been specified.\n", + pr_info("%s: ARP monitoring has been set up, but no ARP targets have been specified\n", bond->dev->name); } if (bond->dev->flags & IFF_UP) { @@ -812,8 +868,7 @@ int bond_option_arp_interval_set(struct bonding *bond, cancel_delayed_work_sync(&bond->arp_work); } else { /* arp_validate can be set only in active-backup mode */ - if (bond->params.arp_validate) - bond->recv_probe = bond_arp_rcv; + bond->recv_probe = bond_arp_rcv; cancel_delayed_work_sync(&bond->mii_work); queue_delayed_work(bond->wq, &bond->arp_work, 0); } @@ -856,19 +911,18 @@ static int _bond_option_arp_ip_target_add(struct bonding *bond, __be32 target) ind = bond_get_targets_ip(targets, 0); /* first free slot */ if (ind == -1) { - pr_err("%s: ARP target table is full!\n", - bond->dev->name); + pr_err("%s: ARP target table is full!\n", bond->dev->name); return -EINVAL; } - pr_info("%s: adding ARP target %pI4.\n", bond->dev->name, &target); + pr_info("%s: Adding ARP target %pI4\n", bond->dev->name, &target); _bond_options_arp_ip_target_set(bond, ind, target, jiffies); return 0; } -int bond_option_arp_ip_target_add(struct bonding *bond, __be32 target) +static int bond_option_arp_ip_target_add(struct bonding *bond, __be32 target) { int ret; @@ -880,7 +934,7 @@ int bond_option_arp_ip_target_add(struct bonding *bond, __be32 target) return ret; } -int bond_option_arp_ip_target_rem(struct bonding *bond, __be32 target) +static int bond_option_arp_ip_target_rem(struct bonding *bond, __be32 target) { __be32 *targets = bond->params.arp_targets; struct list_head *iter; @@ -896,17 +950,16 @@ int bond_option_arp_ip_target_rem(struct bonding *bond, __be32 target) ind = bond_get_targets_ip(targets, target); if (ind == -1) { - pr_err("%s: unable to remove nonexistent ARP target %pI4.\n", + pr_err("%s: unable to remove nonexistent ARP target %pI4\n", bond->dev->name, &target); return -EINVAL; } if (ind == 0 && !targets[1] && bond->params.arp_interval) - pr_warn("%s: removing last arp target with arp_interval on\n", + pr_warn("%s: Removing last arp target with arp_interval on\n", bond->dev->name); - pr_info("%s: removing ARP target %pI4.\n", bond->dev->name, - &target); + pr_info("%s: Removing ARP target %pI4\n", bond->dev->name, &target); /* not to race with bond_arp_rcv */ write_lock_bh(&bond->lock); @@ -937,8 +990,8 @@ void bond_option_arp_ip_targets_clear(struct bonding *bond) write_unlock_bh(&bond->lock); } -int bond_option_arp_ip_targets_set(struct bonding *bond, - struct bond_opt_value *newval) +static int bond_option_arp_ip_targets_set(struct bonding *bond, + const struct bond_opt_value *newval) { int ret = -EPERM; __be32 target; @@ -954,7 +1007,7 @@ int bond_option_arp_ip_targets_set(struct bonding *bond, else if (newval->string[0] == '-') ret = bond_option_arp_ip_target_rem(bond, target); else - pr_err("no command found in arp_ip_targets file for bond %s. Use +<addr> or -<addr>.\n", + pr_err("no command found in arp_ip_targets file for bond %s - use +<addr> or -<addr>\n", bond->dev->name); } else { target = newval->value; @@ -964,10 +1017,10 @@ int bond_option_arp_ip_targets_set(struct bonding *bond, return ret; } -int bond_option_arp_validate_set(struct bonding *bond, - struct bond_opt_value *newval) +static int bond_option_arp_validate_set(struct bonding *bond, + const struct bond_opt_value *newval) { - pr_info("%s: setting arp_validate to %s (%llu).\n", + pr_info("%s: Setting arp_validate to %s (%llu)\n", bond->dev->name, newval->string, newval->value); if (bond->dev->flags & IFF_UP) { @@ -981,17 +1034,18 @@ int bond_option_arp_validate_set(struct bonding *bond, return 0; } -int bond_option_arp_all_targets_set(struct bonding *bond, - struct bond_opt_value *newval) +static int bond_option_arp_all_targets_set(struct bonding *bond, + const struct bond_opt_value *newval) { - pr_info("%s: setting arp_all_targets to %s (%llu).\n", + pr_info("%s: Setting arp_all_targets to %s (%llu)\n", bond->dev->name, newval->string, newval->value); bond->params.arp_all_targets = newval->value; return 0; } -int bond_option_primary_set(struct bonding *bond, struct bond_opt_value *newval) +static int bond_option_primary_set(struct bonding *bond, + const struct bond_opt_value *newval) { char *p, *primary = newval->string; struct list_head *iter; @@ -1006,8 +1060,7 @@ int bond_option_primary_set(struct bonding *bond, struct bond_opt_value *newval) *p = '\0'; /* check to see if we are clearing primary */ if (!strlen(primary)) { - pr_info("%s: Setting primary slave to None.\n", - bond->dev->name); + pr_info("%s: Setting primary slave to None\n", bond->dev->name); bond->primary_slave = NULL; memset(bond->params.primary, 0, sizeof(bond->params.primary)); bond_select_active_slave(bond); @@ -1016,7 +1069,7 @@ int bond_option_primary_set(struct bonding *bond, struct bond_opt_value *newval) bond_for_each_slave(bond, slave, iter) { if (strncmp(slave->dev->name, primary, IFNAMSIZ) == 0) { - pr_info("%s: Setting %s as primary slave.\n", + pr_info("%s: Setting %s as primary slave\n", bond->dev->name, slave->dev->name); bond->primary_slave = slave; strcpy(bond->params.primary, slave->dev->name); @@ -1026,15 +1079,14 @@ int bond_option_primary_set(struct bonding *bond, struct bond_opt_value *newval) } if (bond->primary_slave) { - pr_info("%s: Setting primary slave to None.\n", - bond->dev->name); + pr_info("%s: Setting primary slave to None\n", bond->dev->name); bond->primary_slave = NULL; bond_select_active_slave(bond); } strncpy(bond->params.primary, primary, IFNAMSIZ); bond->params.primary[IFNAMSIZ - 1] = 0; - pr_info("%s: Recording %s as primary, but it has not been enslaved to %s yet.\n", + pr_info("%s: Recording %s as primary, but it has not been enslaved to %s yet\n", bond->dev->name, primary, bond->dev->name); out: @@ -1045,10 +1097,10 @@ out: return 0; } -int bond_option_primary_reselect_set(struct bonding *bond, - struct bond_opt_value *newval) +static int bond_option_primary_reselect_set(struct bonding *bond, + const struct bond_opt_value *newval) { - pr_info("%s: setting primary_reselect to %s (%llu).\n", + pr_info("%s: Setting primary_reselect to %s (%llu)\n", bond->dev->name, newval->string, newval->value); bond->params.primary_reselect = newval->value; @@ -1061,46 +1113,46 @@ int bond_option_primary_reselect_set(struct bonding *bond, return 0; } -int bond_option_fail_over_mac_set(struct bonding *bond, - struct bond_opt_value *newval) +static int bond_option_fail_over_mac_set(struct bonding *bond, + const struct bond_opt_value *newval) { - pr_info("%s: Setting fail_over_mac to %s (%llu).\n", + pr_info("%s: Setting fail_over_mac to %s (%llu)\n", bond->dev->name, newval->string, newval->value); bond->params.fail_over_mac = newval->value; return 0; } -int bond_option_xmit_hash_policy_set(struct bonding *bond, - struct bond_opt_value *newval) +static int bond_option_xmit_hash_policy_set(struct bonding *bond, + const struct bond_opt_value *newval) { - pr_info("%s: setting xmit hash policy to %s (%llu).\n", + pr_info("%s: Setting xmit hash policy to %s (%llu)\n", bond->dev->name, newval->string, newval->value); bond->params.xmit_policy = newval->value; return 0; } -int bond_option_resend_igmp_set(struct bonding *bond, - struct bond_opt_value *newval) +static int bond_option_resend_igmp_set(struct bonding *bond, + const struct bond_opt_value *newval) { - pr_info("%s: Setting resend_igmp to %llu.\n", + pr_info("%s: Setting resend_igmp to %llu\n", bond->dev->name, newval->value); bond->params.resend_igmp = newval->value; return 0; } -int bond_option_num_peer_notif_set(struct bonding *bond, - struct bond_opt_value *newval) +static int bond_option_num_peer_notif_set(struct bonding *bond, + const struct bond_opt_value *newval) { bond->params.num_peer_notif = newval->value; return 0; } -int bond_option_all_slaves_active_set(struct bonding *bond, - struct bond_opt_value *newval) +static int bond_option_all_slaves_active_set(struct bonding *bond, + const struct bond_opt_value *newval) { struct list_head *iter; struct slave *slave; @@ -1120,8 +1172,8 @@ int bond_option_all_slaves_active_set(struct bonding *bond, return 0; } -int bond_option_min_links_set(struct bonding *bond, - struct bond_opt_value *newval) +static int bond_option_min_links_set(struct bonding *bond, + const struct bond_opt_value *newval) { pr_info("%s: Setting min links value to %llu\n", bond->dev->name, newval->value); @@ -1130,15 +1182,16 @@ int bond_option_min_links_set(struct bonding *bond, return 0; } -int bond_option_lp_interval_set(struct bonding *bond, - struct bond_opt_value *newval) +static int bond_option_lp_interval_set(struct bonding *bond, + const struct bond_opt_value *newval) { bond->params.lp_interval = newval->value; return 0; } -int bond_option_pps_set(struct bonding *bond, struct bond_opt_value *newval) +static int bond_option_pps_set(struct bonding *bond, + const struct bond_opt_value *newval) { bond->params.packets_per_slave = newval->value; if (newval->value > 0) { @@ -1155,10 +1208,10 @@ int bond_option_pps_set(struct bonding *bond, struct bond_opt_value *newval) return 0; } -int bond_option_lacp_rate_set(struct bonding *bond, - struct bond_opt_value *newval) +static int bond_option_lacp_rate_set(struct bonding *bond, + const struct bond_opt_value *newval) { - pr_info("%s: Setting LACP rate to %s (%llu).\n", + pr_info("%s: Setting LACP rate to %s (%llu)\n", bond->dev->name, newval->string, newval->value); bond->params.lacp_fast = newval->value; bond_3ad_update_lacp_rate(bond); @@ -1166,18 +1219,18 @@ int bond_option_lacp_rate_set(struct bonding *bond, return 0; } -int bond_option_ad_select_set(struct bonding *bond, - struct bond_opt_value *newval) +static int bond_option_ad_select_set(struct bonding *bond, + const struct bond_opt_value *newval) { - pr_info("%s: Setting ad_select to %s (%llu).\n", + pr_info("%s: Setting ad_select to %s (%llu)\n", bond->dev->name, newval->string, newval->value); bond->params.ad_select = newval->value; return 0; } -int bond_option_queue_id_set(struct bonding *bond, - struct bond_opt_value *newval) +static int bond_option_queue_id_set(struct bonding *bond, + const struct bond_opt_value *newval) { struct slave *slave, *update_slave; struct net_device *sdev; @@ -1199,8 +1252,7 @@ int bond_option_queue_id_set(struct bonding *bond, goto err_no_cmd; /* Check buffer length, valid ifname and queue id */ - if (strlen(newval->string) > IFNAMSIZ || - !dev_valid_name(newval->string) || + if (!dev_valid_name(newval->string) || qid > bond->dev->real_num_tx_queues) goto err_no_cmd; @@ -1232,14 +1284,14 @@ out: return ret; err_no_cmd: - pr_info("invalid input for queue_id set for %s.\n", - bond->dev->name); + pr_info("invalid input for queue_id set for %s\n", bond->dev->name); ret = -EPERM; goto out; } -int bond_option_slaves_set(struct bonding *bond, struct bond_opt_value *newval) +static int bond_option_slaves_set(struct bonding *bond, + const struct bond_opt_value *newval) { char command[IFNAMSIZ + 1] = { 0, }; struct net_device *dev; @@ -1254,7 +1306,7 @@ int bond_option_slaves_set(struct bonding *bond, struct bond_opt_value *newval) dev = __dev_get_by_name(dev_net(bond->dev), ifname); if (!dev) { - pr_info("%s: Interface %s does not exist!\n", + pr_info("%s: interface %s does not exist!\n", bond->dev->name, ifname); ret = -ENODEV; goto out; @@ -1262,12 +1314,12 @@ int bond_option_slaves_set(struct bonding *bond, struct bond_opt_value *newval) switch (command[0]) { case '+': - pr_info("%s: Adding slave %s.\n", bond->dev->name, dev->name); + pr_info("%s: Adding slave %s\n", bond->dev->name, dev->name); ret = bond_enslave(bond->dev, dev); break; case '-': - pr_info("%s: Removing slave %s.\n", bond->dev->name, dev->name); + pr_info("%s: Removing slave %s\n", bond->dev->name, dev->name); ret = bond_release(bond->dev, dev); break; @@ -1279,7 +1331,7 @@ out: return ret; err_no_cmd: - pr_err("no command found in slaves file for bond %s. Use +ifname or -ifname.\n", + pr_err("no command found in slaves file for bond %s - use +ifname or -ifname\n", bond->dev->name); ret = -EPERM; goto out; diff --git a/drivers/net/bonding/bond_options.h b/drivers/net/bonding/bond_options.h index 433d37f6940b..12be9e1bfb0c 100644 --- a/drivers/net/bonding/bond_options.h +++ b/drivers/net/bonding/bond_options.h @@ -81,8 +81,8 @@ struct bonding; struct bond_option { int id; - char *name; - char *desc; + const char *name; + const char *desc; u32 flags; /* unsuppmodes is used to denote modes in which the option isn't @@ -92,18 +92,19 @@ struct bond_option { /* supported values which this option can have, can be a subset of * BOND_OPTVAL_RANGE's value range */ - struct bond_opt_value *values; + const struct bond_opt_value *values; - int (*set)(struct bonding *bond, struct bond_opt_value *val); + int (*set)(struct bonding *bond, const struct bond_opt_value *val); }; int __bond_opt_set(struct bonding *bond, unsigned int option, struct bond_opt_value *val); int bond_opt_tryset_rtnl(struct bonding *bond, unsigned int option, char *buf); -struct bond_opt_value *bond_opt_parse(const struct bond_option *opt, - struct bond_opt_value *val); -struct bond_option *bond_opt_get(unsigned int option); -struct bond_opt_value *bond_opt_get_val(unsigned int option, u64 val); + +const struct bond_opt_value *bond_opt_parse(const struct bond_option *opt, + struct bond_opt_value *val); +const struct bond_option *bond_opt_get(unsigned int option); +const struct bond_opt_value *bond_opt_get_val(unsigned int option, u64 val); /* This helper is used to initialize a bond_opt_value structure for parameter * passing. There should be either a valid string or value, but not both. @@ -122,49 +123,6 @@ static inline void __bond_opt_init(struct bond_opt_value *optval, #define bond_opt_initval(optval, value) __bond_opt_init(optval, NULL, value) #define bond_opt_initstr(optval, str) __bond_opt_init(optval, str, ULLONG_MAX) -int bond_option_mode_set(struct bonding *bond, struct bond_opt_value *newval); -int bond_option_pps_set(struct bonding *bond, struct bond_opt_value *newval); -int bond_option_xmit_hash_policy_set(struct bonding *bond, - struct bond_opt_value *newval); -int bond_option_arp_validate_set(struct bonding *bond, - struct bond_opt_value *newval); -int bond_option_arp_all_targets_set(struct bonding *bond, - struct bond_opt_value *newval); -int bond_option_fail_over_mac_set(struct bonding *bond, - struct bond_opt_value *newval); -int bond_option_arp_interval_set(struct bonding *bond, - struct bond_opt_value *newval); -int bond_option_arp_ip_targets_set(struct bonding *bond, - struct bond_opt_value *newval); void bond_option_arp_ip_targets_clear(struct bonding *bond); -int bond_option_downdelay_set(struct bonding *bond, - struct bond_opt_value *newval); -int bond_option_updelay_set(struct bonding *bond, - struct bond_opt_value *newval); -int bond_option_lacp_rate_set(struct bonding *bond, - struct bond_opt_value *newval); -int bond_option_min_links_set(struct bonding *bond, - struct bond_opt_value *newval); -int bond_option_ad_select_set(struct bonding *bond, - struct bond_opt_value *newval); -int bond_option_num_peer_notif_set(struct bonding *bond, - struct bond_opt_value *newval); -int bond_option_miimon_set(struct bonding *bond, struct bond_opt_value *newval); -int bond_option_primary_set(struct bonding *bond, - struct bond_opt_value *newval); -int bond_option_primary_reselect_set(struct bonding *bond, - struct bond_opt_value *newval); -int bond_option_use_carrier_set(struct bonding *bond, - struct bond_opt_value *newval); -int bond_option_active_slave_set(struct bonding *bond, - struct bond_opt_value *newval); -int bond_option_queue_id_set(struct bonding *bond, - struct bond_opt_value *newval); -int bond_option_all_slaves_active_set(struct bonding *bond, - struct bond_opt_value *newval); -int bond_option_resend_igmp_set(struct bonding *bond, - struct bond_opt_value *newval); -int bond_option_lp_interval_set(struct bonding *bond, - struct bond_opt_value *newval); -int bond_option_slaves_set(struct bonding *bond, struct bond_opt_value *newval); + #endif /* _BOND_OPTIONS_H */ diff --git a/drivers/net/bonding/bond_procfs.c b/drivers/net/bonding/bond_procfs.c index 3ac20e78eafc..013fdd0f45e9 100644 --- a/drivers/net/bonding/bond_procfs.c +++ b/drivers/net/bonding/bond_procfs.c @@ -65,13 +65,11 @@ static void bond_info_seq_stop(struct seq_file *seq, void *v) static void bond_info_show_master(struct seq_file *seq) { struct bonding *bond = seq->private; - struct bond_opt_value *optval; + const struct bond_opt_value *optval; struct slave *curr; int i; - read_lock(&bond->curr_slave_lock); - curr = bond->curr_active_slave; - read_unlock(&bond->curr_slave_lock); + curr = rcu_dereference(bond->curr_active_slave); seq_printf(seq, "Bonding Mode: %s", bond_mode_name(bond->params.mode)); @@ -254,8 +252,8 @@ void bond_create_proc_entry(struct bonding *bond) S_IRUGO, bn->proc_dir, &bond_info_fops, bond); if (bond->proc_entry == NULL) - pr_warning("Warning: Cannot create /proc/net/%s/%s\n", - DRV_NAME, bond_dev->name); + pr_warn("Warning: Cannot create /proc/net/%s/%s\n", + DRV_NAME, bond_dev->name); else memcpy(bond->proc_file_name, bond_dev->name, IFNAMSIZ); } @@ -281,8 +279,8 @@ void __net_init bond_create_proc_dir(struct bond_net *bn) if (!bn->proc_dir) { bn->proc_dir = proc_mkdir(DRV_NAME, bn->net->proc_net); if (!bn->proc_dir) - pr_warning("Warning: cannot create /proc/net/%s\n", - DRV_NAME); + pr_warn("Warning: Cannot create /proc/net/%s\n", + DRV_NAME); } } diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c index 643fcc110299..0e8b268da0a0 100644 --- a/drivers/net/bonding/bond_sysfs.c +++ b/drivers/net/bonding/bond_sysfs.c @@ -117,9 +117,9 @@ static ssize_t bonding_store_bonds(struct class *cls, rv = bond_create(bn->net, ifname); if (rv) { if (rv == -EEXIST) - pr_info("%s already exists.\n", ifname); + pr_info("%s already exists\n", ifname); else - pr_info("%s creation failed.\n", ifname); + pr_info("%s creation failed\n", ifname); res = rv; } } else if (command[0] == '-') { @@ -144,7 +144,7 @@ static ssize_t bonding_store_bonds(struct class *cls, return res; err_no_cmd: - pr_err("no command found in bonding_masters. Use +ifname or -ifname.\n"); + pr_err("no command found in bonding_masters - use +ifname or -ifname\n"); return -EPERM; } @@ -220,7 +220,7 @@ static ssize_t bonding_show_mode(struct device *d, struct device_attribute *attr, char *buf) { struct bonding *bond = to_bond(d); - struct bond_opt_value *val; + const struct bond_opt_value *val; val = bond_opt_get_val(BOND_OPT_MODE, bond->params.mode); @@ -251,7 +251,7 @@ static ssize_t bonding_show_xmit_hash(struct device *d, char *buf) { struct bonding *bond = to_bond(d); - struct bond_opt_value *val; + const struct bond_opt_value *val; val = bond_opt_get_val(BOND_OPT_XMIT_HASH, bond->params.xmit_policy); @@ -282,7 +282,7 @@ static ssize_t bonding_show_arp_validate(struct device *d, char *buf) { struct bonding *bond = to_bond(d); - struct bond_opt_value *val; + const struct bond_opt_value *val; val = bond_opt_get_val(BOND_OPT_ARP_VALIDATE, bond->params.arp_validate); @@ -314,7 +314,7 @@ static ssize_t bonding_show_arp_all_targets(struct device *d, char *buf) { struct bonding *bond = to_bond(d); - struct bond_opt_value *val; + const struct bond_opt_value *val; val = bond_opt_get_val(BOND_OPT_ARP_ALL_TARGETS, bond->params.arp_all_targets); @@ -348,7 +348,7 @@ static ssize_t bonding_show_fail_over_mac(struct device *d, char *buf) { struct bonding *bond = to_bond(d); - struct bond_opt_value *val; + const struct bond_opt_value *val; val = bond_opt_get_val(BOND_OPT_FAIL_OVER_MAC, bond->params.fail_over_mac); @@ -505,7 +505,7 @@ static ssize_t bonding_show_lacp(struct device *d, char *buf) { struct bonding *bond = to_bond(d); - struct bond_opt_value *val; + const struct bond_opt_value *val; val = bond_opt_get_val(BOND_OPT_LACP_RATE, bond->params.lacp_fast); @@ -558,7 +558,7 @@ static ssize_t bonding_show_ad_select(struct device *d, char *buf) { struct bonding *bond = to_bond(d); - struct bond_opt_value *val; + const struct bond_opt_value *val; val = bond_opt_get_val(BOND_OPT_AD_SELECT, bond->params.ad_select); @@ -686,7 +686,7 @@ static ssize_t bonding_show_primary_reselect(struct device *d, char *buf) { struct bonding *bond = to_bond(d); - struct bond_opt_value *val; + const struct bond_opt_value *val; val = bond_opt_get_val(BOND_OPT_PRIMARY_RESELECT, bond->params.primary_reselect); @@ -1135,7 +1135,7 @@ int bond_create_sysfs(struct bond_net *bn) /* Is someone being kinky and naming a device bonding_master? */ if (__dev_get_by_name(bn->net, class_attr_bonding_masters.attr.name)) - pr_err("network device named %s already exists in sysfs", + pr_err("network device named %s already exists in sysfs\n", class_attr_bonding_masters.attr.name); ret = 0; } diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h index 86ccfb9f71cc..0896f1db24db 100644 --- a/drivers/net/bonding/bonding.h +++ b/drivers/net/bonding/bonding.h @@ -188,14 +188,16 @@ struct slave { struct net_device *dev; /* first - useful for panic debug */ struct bonding *bond; /* our master */ int delay; - unsigned long jiffies; - unsigned long last_arp_rx; + /* all three in jiffies */ + unsigned long last_link_up; + unsigned long last_rx; unsigned long target_last_arp_rx[BOND_MAX_ARP_TARGETS]; s8 link; /* one of BOND_LINK_XXXX */ s8 new_link; u8 backup:1, /* indicates backup slave. Value corresponds with BOND_STATE_ACTIVE and BOND_STATE_BACKUP */ - inactive:1; /* indicates inactive slave */ + inactive:1, /* indicates inactive slave */ + should_notify:1; /* indicateds whether the state changed */ u8 duplex; u32 original_mtu; u32 link_failure_count; @@ -291,7 +293,7 @@ static inline void bond_set_active_slave(struct slave *slave) { if (slave->backup) { slave->backup = 0; - rtmsg_ifinfo(RTM_NEWLINK, slave->dev, 0, GFP_KERNEL); + rtmsg_ifinfo(RTM_NEWLINK, slave->dev, 0, GFP_ATOMIC); } } @@ -299,7 +301,25 @@ static inline void bond_set_backup_slave(struct slave *slave) { if (!slave->backup) { slave->backup = 1; - rtmsg_ifinfo(RTM_NEWLINK, slave->dev, 0, GFP_KERNEL); + rtmsg_ifinfo(RTM_NEWLINK, slave->dev, 0, GFP_ATOMIC); + } +} + +static inline void bond_set_slave_state(struct slave *slave, + int slave_state, bool notify) +{ + if (slave->backup == slave_state) + return; + + slave->backup = slave_state; + if (notify) { + rtmsg_ifinfo(RTM_NEWLINK, slave->dev, 0, GFP_ATOMIC); + slave->should_notify = 0; + } else { + if (slave->should_notify) + slave->should_notify = 0; + else + slave->should_notify = 1; } } @@ -316,6 +336,19 @@ static inline void bond_slave_state_change(struct bonding *bond) } } +static inline void bond_slave_state_notify(struct bonding *bond) +{ + struct list_head *iter; + struct slave *tmp; + + bond_for_each_slave(bond, tmp, iter) { + if (tmp->should_notify) { + rtmsg_ifinfo(RTM_NEWLINK, tmp->dev, 0, GFP_ATOMIC); + tmp->should_notify = 0; + } + } +} + static inline int bond_slave_state(struct slave *slave) { return slave->backup; @@ -342,6 +375,14 @@ static inline bool bond_is_active_slave(struct slave *slave) #define BOND_ARP_VALIDATE_BACKUP (1 << BOND_STATE_BACKUP) #define BOND_ARP_VALIDATE_ALL (BOND_ARP_VALIDATE_ACTIVE | \ BOND_ARP_VALIDATE_BACKUP) +#define BOND_ARP_FILTER (BOND_ARP_VALIDATE_ALL + 1) +#define BOND_ARP_FILTER_ACTIVE (BOND_ARP_VALIDATE_ACTIVE | \ + BOND_ARP_FILTER) +#define BOND_ARP_FILTER_BACKUP (BOND_ARP_VALIDATE_BACKUP | \ + BOND_ARP_FILTER) + +#define BOND_SLAVE_NOTIFY_NOW true +#define BOND_SLAVE_NOTIFY_LATER false static inline int slave_do_arp_validate(struct bonding *bond, struct slave *slave) @@ -349,6 +390,12 @@ static inline int slave_do_arp_validate(struct bonding *bond, return bond->params.arp_validate & (1 << bond_slave_state(slave)); } +static inline int slave_do_arp_validate_only(struct bonding *bond, + struct slave *slave) +{ + return bond->params.arp_validate & BOND_ARP_FILTER; +} + /* Get the oldest arp which we've received on this slave for bond's * arp_targets. */ @@ -368,14 +415,10 @@ static inline unsigned long slave_oldest_target_arp_rx(struct bonding *bond, static inline unsigned long slave_last_rx(struct bonding *bond, struct slave *slave) { - if (slave_do_arp_validate(bond, slave)) { - if (bond->params.arp_all_targets == BOND_ARP_TARGETS_ALL) - return slave_oldest_target_arp_rx(bond, slave); - else - return slave->last_arp_rx; - } + if (bond->params.arp_all_targets == BOND_ARP_TARGETS_ALL) + return slave_oldest_target_arp_rx(bond, slave); - return slave->dev->last_rx; + return slave->last_rx; } #ifdef CONFIG_NET_POLL_CONTROLLER @@ -394,17 +437,19 @@ static inline void bond_netpoll_send_skb(const struct slave *slave, } #endif -static inline void bond_set_slave_inactive_flags(struct slave *slave) +static inline void bond_set_slave_inactive_flags(struct slave *slave, + bool notify) { if (!bond_is_lb(slave->bond)) - bond_set_backup_slave(slave); + bond_set_slave_state(slave, BOND_STATE_BACKUP, notify); if (!slave->bond->params.all_slaves_active) slave->inactive = 1; } -static inline void bond_set_slave_active_flags(struct slave *slave) +static inline void bond_set_slave_active_flags(struct slave *slave, + bool notify) { - bond_set_active_slave(slave); + bond_set_slave_state(slave, BOND_STATE_ACTIVE, notify); slave->inactive = 0; } @@ -450,8 +495,6 @@ void bond_sysfs_slave_del(struct slave *slave); int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev); int bond_release(struct net_device *bond_dev, struct net_device *slave_dev); int bond_xmit_hash(struct bonding *bond, struct sk_buff *skb, int count); -int bond_parse_parm(const char *mode_arg, const struct bond_parm_tbl *tbl); -int bond_parm_tbl_lookup(int mode, const struct bond_parm_tbl *tbl); void bond_select_active_slave(struct bonding *bond); void bond_change_active_slave(struct bonding *bond, struct slave *new_active); void bond_create_debugfs(void); @@ -464,8 +507,6 @@ void bond_setup(struct net_device *bond_dev); unsigned int bond_get_num_tx_queues(void); int bond_netlink_init(void); void bond_netlink_fini(void); -int bond_option_arp_ip_target_add(struct bonding *bond, __be32 target); -int bond_option_arp_ip_target_rem(struct bonding *bond, __be32 target); struct net_device *bond_option_active_slave_get_rcu(struct bonding *bond); struct net_device *bond_option_active_slave_get(struct bonding *bond); const char *bond_slave_link_status(s8 link); diff --git a/drivers/net/caif/caif_serial.c b/drivers/net/caif/caif_serial.c index 88a6a5810ec6..fc73865bb83a 100644 --- a/drivers/net/caif/caif_serial.c +++ b/drivers/net/caif/caif_serial.c @@ -204,7 +204,6 @@ static void ldisc_receive(struct tty_struct *tty, const u8 *data, skb->protocol = htons(ETH_P_CAIF); skb_reset_mac_header(skb); - skb->dev = ser->dev; debugfs_rx(ser, data, count); /* Push received packet up the stack. */ ret = netif_rx_ni(skb); diff --git a/drivers/net/caif/caif_spi.c b/drivers/net/caif/caif_spi.c index 155db68e13ba..ff54c0eb2052 100644 --- a/drivers/net/caif/caif_spi.c +++ b/drivers/net/caif/caif_spi.c @@ -554,7 +554,6 @@ int cfspi_rxfrm(struct cfspi *cfspi, u8 *buf, size_t len) skb->protocol = htons(ETH_P_CAIF); skb_reset_mac_header(skb); - skb->dev = cfspi->ndev; /* * Push received packet up the stack. diff --git a/drivers/net/can/Kconfig b/drivers/net/can/Kconfig index d447b881bbde..9e7d95dae2c7 100644 --- a/drivers/net/can/Kconfig +++ b/drivers/net/can/Kconfig @@ -104,7 +104,7 @@ config CAN_JANZ_ICAN3 config CAN_FLEXCAN tristate "Support for Freescale FLEXCAN based chips" - depends on (ARM && CPU_LITTLE_ENDIAN) || PPC + depends on ARM || PPC ---help--- Say Y here if you want to support for Freescale FlexCAN. diff --git a/drivers/net/can/at91_can.c b/drivers/net/can/at91_can.c index 6efe27458116..1d00b95f8983 100644 --- a/drivers/net/can/at91_can.c +++ b/drivers/net/can/at91_can.c @@ -420,7 +420,11 @@ static void at91_chip_start(struct net_device *dev) at91_transceiver_switch(priv, 1); /* enable chip */ - at91_write(priv, AT91_MR, AT91_MR_CANEN); + if (priv->can.ctrlmode & CAN_CTRLMODE_LISTENONLY) + reg_mr = AT91_MR_CANEN | AT91_MR_ABM; + else + reg_mr = AT91_MR_CANEN; + at91_write(priv, AT91_MR, reg_mr); priv->can.state = CAN_STATE_ERROR_ACTIVE; @@ -1341,7 +1345,8 @@ static int at91_can_probe(struct platform_device *pdev) priv->can.bittiming_const = &at91_bittiming_const; priv->can.do_set_mode = at91_set_mode; priv->can.do_get_berr_counter = at91_get_berr_counter; - priv->can.ctrlmode_supported = CAN_CTRLMODE_3_SAMPLES; + priv->can.ctrlmode_supported = CAN_CTRLMODE_3_SAMPLES | + CAN_CTRLMODE_LISTENONLY; priv->dev = dev; priv->reg_base = addr; priv->devtype_data = *devtype_data; diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c index 13a909822e25..c7a260478749 100644 --- a/drivers/net/can/dev.c +++ b/drivers/net/can/dev.c @@ -99,10 +99,10 @@ static int can_update_spt(const struct can_bittiming_const *btc, return 1000 * (tseg + 1 - *tseg2) / (tseg + 1); } -static int can_calc_bittiming(struct net_device *dev, struct can_bittiming *bt) +static int can_calc_bittiming(struct net_device *dev, struct can_bittiming *bt, + const struct can_bittiming_const *btc) { struct can_priv *priv = netdev_priv(dev); - const struct can_bittiming_const *btc = priv->bittiming_const; long rate, best_rate = 0; long best_error = 1000000000, error = 0; int best_tseg = 0, best_brp = 0, brp = 0; @@ -110,9 +110,6 @@ static int can_calc_bittiming(struct net_device *dev, struct can_bittiming *bt) int spt_error = 1000, spt = 0, sampl_pt; u64 v64; - if (!priv->bittiming_const) - return -ENOTSUPP; - /* Use CIA recommended sample points */ if (bt->sample_point) { sampl_pt = bt->sample_point; @@ -204,7 +201,8 @@ static int can_calc_bittiming(struct net_device *dev, struct can_bittiming *bt) return 0; } #else /* !CONFIG_CAN_CALC_BITTIMING */ -static int can_calc_bittiming(struct net_device *dev, struct can_bittiming *bt) +static int can_calc_bittiming(struct net_device *dev, struct can_bittiming *bt, + const struct can_bittiming_const *btc) { netdev_err(dev, "bit-timing calculation not available\n"); return -EINVAL; @@ -217,16 +215,13 @@ static int can_calc_bittiming(struct net_device *dev, struct can_bittiming *bt) * prescaler value brp. You can find more information in the header * file linux/can/netlink.h. */ -static int can_fixup_bittiming(struct net_device *dev, struct can_bittiming *bt) +static int can_fixup_bittiming(struct net_device *dev, struct can_bittiming *bt, + const struct can_bittiming_const *btc) { struct can_priv *priv = netdev_priv(dev); - const struct can_bittiming_const *btc = priv->bittiming_const; int tseg1, alltseg; u64 brp64; - if (!priv->bittiming_const) - return -ENOTSUPP; - tseg1 = bt->prop_seg + bt->phase_seg1; if (!bt->sjw) bt->sjw = 1; @@ -254,26 +249,29 @@ static int can_fixup_bittiming(struct net_device *dev, struct can_bittiming *bt) return 0; } -static int can_get_bittiming(struct net_device *dev, struct can_bittiming *bt) +static int can_get_bittiming(struct net_device *dev, struct can_bittiming *bt, + const struct can_bittiming_const *btc) { - struct can_priv *priv = netdev_priv(dev); int err; /* Check if the CAN device has bit-timing parameters */ - if (priv->bittiming_const) { + if (!btc) + return -ENOTSUPP; - /* Non-expert mode? Check if the bitrate has been pre-defined */ - if (!bt->tq) - /* Determine bit-timing parameters */ - err = can_calc_bittiming(dev, bt); - else - /* Check bit-timing params and calculate proper brp */ - err = can_fixup_bittiming(dev, bt); - if (err) - return err; - } + /* + * Depending on the given can_bittiming parameter structure the CAN + * timing parameters are calculated based on the provided bitrate OR + * alternatively the CAN timing parameters (tq, prop_seg, etc.) are + * provided directly which are then checked and fixed up. + */ + if (!bt->tq && bt->bitrate) + err = can_calc_bittiming(dev, bt, btc); + else if (bt->tq && !bt->bitrate) + err = can_fixup_bittiming(dev, bt, btc); + else + err = -EINVAL; - return 0; + return err; } /* @@ -317,28 +315,20 @@ void can_put_echo_skb(struct sk_buff *skb, struct net_device *dev, BUG_ON(idx >= priv->echo_skb_max); /* check flag whether this packet has to be looped back */ - if (!(dev->flags & IFF_ECHO) || skb->pkt_type != PACKET_LOOPBACK) { + if (!(dev->flags & IFF_ECHO) || skb->pkt_type != PACKET_LOOPBACK || + (skb->protocol != htons(ETH_P_CAN) && + skb->protocol != htons(ETH_P_CANFD))) { kfree_skb(skb); return; } if (!priv->echo_skb[idx]) { - struct sock *srcsk = skb->sk; - if (atomic_read(&skb->users) != 1) { - struct sk_buff *old_skb = skb; - - skb = skb_clone(old_skb, GFP_ATOMIC); - kfree_skb(old_skb); - if (!skb) - return; - } else - skb_orphan(skb); - - skb->sk = srcsk; + skb = can_create_echo_skb(skb); + if (!skb) + return; /* make settings for echo to reduce code in irq context */ - skb->protocol = htons(ETH_P_CAN); skb->pkt_type = PACKET_BROADCAST; skb->ip_summed = CHECKSUM_UNNECESSARY; skb->dev = dev; @@ -521,6 +511,30 @@ struct sk_buff *alloc_can_skb(struct net_device *dev, struct can_frame **cf) } EXPORT_SYMBOL_GPL(alloc_can_skb); +struct sk_buff *alloc_canfd_skb(struct net_device *dev, + struct canfd_frame **cfd) +{ + struct sk_buff *skb; + + skb = netdev_alloc_skb(dev, sizeof(struct can_skb_priv) + + sizeof(struct canfd_frame)); + if (unlikely(!skb)) + return NULL; + + skb->protocol = htons(ETH_P_CANFD); + skb->pkt_type = PACKET_BROADCAST; + skb->ip_summed = CHECKSUM_UNNECESSARY; + + can_skb_reserve(skb); + can_skb_prv(skb)->ifindex = dev->ifindex; + + *cfd = (struct canfd_frame *)skb_put(skb, sizeof(struct canfd_frame)); + memset(*cfd, 0, sizeof(struct canfd_frame)); + + return skb; +} +EXPORT_SYMBOL_GPL(alloc_canfd_skb); + struct sk_buff *alloc_can_err_skb(struct net_device *dev, struct can_frame **cf) { struct sk_buff *skb; @@ -581,6 +595,39 @@ void free_candev(struct net_device *dev) EXPORT_SYMBOL_GPL(free_candev); /* + * changing MTU and control mode for CAN/CANFD devices + */ +int can_change_mtu(struct net_device *dev, int new_mtu) +{ + struct can_priv *priv = netdev_priv(dev); + + /* Do not allow changing the MTU while running */ + if (dev->flags & IFF_UP) + return -EBUSY; + + /* allow change of MTU according to the CANFD ability of the device */ + switch (new_mtu) { + case CAN_MTU: + priv->ctrlmode &= ~CAN_CTRLMODE_FD; + break; + + case CANFD_MTU: + if (!(priv->ctrlmode_supported & CAN_CTRLMODE_FD)) + return -EINVAL; + + priv->ctrlmode |= CAN_CTRLMODE_FD; + break; + + default: + return -EINVAL; + } + + dev->mtu = new_mtu; + return 0; +} +EXPORT_SYMBOL_GPL(can_change_mtu); + +/* * Common open function when the device gets opened. * * This function should be called in the open function of the device @@ -590,11 +637,19 @@ int open_candev(struct net_device *dev) { struct can_priv *priv = netdev_priv(dev); - if (!priv->bittiming.tq && !priv->bittiming.bitrate) { + if (!priv->bittiming.bitrate) { netdev_err(dev, "bit-timing not yet defined\n"); return -EINVAL; } + /* For CAN FD the data bitrate has to be >= the arbitration bitrate */ + if ((priv->ctrlmode & CAN_CTRLMODE_FD) && + (!priv->data_bittiming.bitrate || + (priv->data_bittiming.bitrate < priv->bittiming.bitrate))) { + netdev_err(dev, "incorrect/missing data bit-timing\n"); + return -EINVAL; + } + /* Switch carrier on if device was stopped while in bus-off state */ if (!netif_carrier_ok(dev)) netif_carrier_on(dev); @@ -633,6 +688,10 @@ static const struct nla_policy can_policy[IFLA_CAN_MAX + 1] = { = { .len = sizeof(struct can_bittiming_const) }, [IFLA_CAN_CLOCK] = { .len = sizeof(struct can_clock) }, [IFLA_CAN_BERR_COUNTER] = { .len = sizeof(struct can_berr_counter) }, + [IFLA_CAN_DATA_BITTIMING] + = { .len = sizeof(struct can_bittiming) }, + [IFLA_CAN_DATA_BITTIMING_CONST] + = { .len = sizeof(struct can_bittiming_const) }, }; static int can_changelink(struct net_device *dev, @@ -651,9 +710,7 @@ static int can_changelink(struct net_device *dev, if (dev->flags & IFF_UP) return -EBUSY; memcpy(&bt, nla_data(data[IFLA_CAN_BITTIMING]), sizeof(bt)); - if ((!bt.bitrate && !bt.tq) || (bt.bitrate && bt.tq)) - return -EINVAL; - err = can_get_bittiming(dev, &bt); + err = can_get_bittiming(dev, &bt, priv->bittiming_const); if (err) return err; memcpy(&priv->bittiming, &bt, sizeof(bt)); @@ -677,6 +734,12 @@ static int can_changelink(struct net_device *dev, return -EOPNOTSUPP; priv->ctrlmode &= ~cm->mask; priv->ctrlmode |= cm->flags; + + /* CAN_CTRLMODE_FD can only be set when driver supports FD */ + if (priv->ctrlmode & CAN_CTRLMODE_FD) + dev->mtu = CANFD_MTU; + else + dev->mtu = CAN_MTU; } if (data[IFLA_CAN_RESTART_MS]) { @@ -695,6 +758,27 @@ static int can_changelink(struct net_device *dev, return err; } + if (data[IFLA_CAN_DATA_BITTIMING]) { + struct can_bittiming dbt; + + /* Do not allow changing bittiming while running */ + if (dev->flags & IFF_UP) + return -EBUSY; + memcpy(&dbt, nla_data(data[IFLA_CAN_DATA_BITTIMING]), + sizeof(dbt)); + err = can_get_bittiming(dev, &dbt, priv->data_bittiming_const); + if (err) + return err; + memcpy(&priv->data_bittiming, &dbt, sizeof(dbt)); + + if (priv->do_set_data_bittiming) { + /* Finally, set the bit-timing registers */ + err = priv->do_set_data_bittiming(dev); + if (err) + return err; + } + } + return 0; } @@ -703,7 +787,8 @@ static size_t can_get_size(const struct net_device *dev) struct can_priv *priv = netdev_priv(dev); size_t size = 0; - size += nla_total_size(sizeof(struct can_bittiming)); /* IFLA_CAN_BITTIMING */ + if (priv->bittiming.bitrate) /* IFLA_CAN_BITTIMING */ + size += nla_total_size(sizeof(struct can_bittiming)); if (priv->bittiming_const) /* IFLA_CAN_BITTIMING_CONST */ size += nla_total_size(sizeof(struct can_bittiming_const)); size += nla_total_size(sizeof(struct can_clock)); /* IFLA_CAN_CLOCK */ @@ -712,6 +797,10 @@ static size_t can_get_size(const struct net_device *dev) size += nla_total_size(sizeof(u32)); /* IFLA_CAN_RESTART_MS */ if (priv->do_get_berr_counter) /* IFLA_CAN_BERR_COUNTER */ size += nla_total_size(sizeof(struct can_berr_counter)); + if (priv->data_bittiming.bitrate) /* IFLA_CAN_DATA_BITTIMING */ + size += nla_total_size(sizeof(struct can_bittiming)); + if (priv->data_bittiming_const) /* IFLA_CAN_DATA_BITTIMING_CONST */ + size += nla_total_size(sizeof(struct can_bittiming_const)); return size; } @@ -725,19 +814,34 @@ static int can_fill_info(struct sk_buff *skb, const struct net_device *dev) if (priv->do_get_state) priv->do_get_state(dev, &state); - if (nla_put(skb, IFLA_CAN_BITTIMING, - sizeof(priv->bittiming), &priv->bittiming) || + + if ((priv->bittiming.bitrate && + nla_put(skb, IFLA_CAN_BITTIMING, + sizeof(priv->bittiming), &priv->bittiming)) || + (priv->bittiming_const && nla_put(skb, IFLA_CAN_BITTIMING_CONST, sizeof(*priv->bittiming_const), priv->bittiming_const)) || + nla_put(skb, IFLA_CAN_CLOCK, sizeof(cm), &priv->clock) || nla_put_u32(skb, IFLA_CAN_STATE, state) || nla_put(skb, IFLA_CAN_CTRLMODE, sizeof(cm), &cm) || nla_put_u32(skb, IFLA_CAN_RESTART_MS, priv->restart_ms) || + (priv->do_get_berr_counter && !priv->do_get_berr_counter(dev, &bec) && - nla_put(skb, IFLA_CAN_BERR_COUNTER, sizeof(bec), &bec))) + nla_put(skb, IFLA_CAN_BERR_COUNTER, sizeof(bec), &bec)) || + + (priv->data_bittiming.bitrate && + nla_put(skb, IFLA_CAN_DATA_BITTIMING, + sizeof(priv->data_bittiming), &priv->data_bittiming)) || + + (priv->data_bittiming_const && + nla_put(skb, IFLA_CAN_DATA_BITTIMING_CONST, + sizeof(*priv->data_bittiming_const), + priv->data_bittiming_const))) return -EMSGSIZE; + return 0; } diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c index aaed97bee471..c94d698b73c2 100644 --- a/drivers/net/can/flexcan.c +++ b/drivers/net/can/flexcan.c @@ -144,6 +144,8 @@ #define FLEXCAN_MB_CODE_MASK (0xf0ffffff) +#define FLEXCAN_TIMEOUT_US (50) + /* * FLEXCAN hardware feature flags * @@ -235,9 +237,12 @@ static const struct can_bittiming_const flexcan_bittiming_const = { }; /* - * Abstract off the read/write for arm versus ppc. + * Abstract off the read/write for arm versus ppc. This + * assumes that PPC uses big-endian registers and everything + * else uses little-endian registers, independent of CPU + * endianess. */ -#if defined(__BIG_ENDIAN) +#if defined(CONFIG_PPC) static inline u32 flexcan_read(void __iomem *addr) { return in_be32(addr); @@ -259,6 +264,22 @@ static inline void flexcan_write(u32 val, void __iomem *addr) } #endif +static inline int flexcan_transceiver_enable(const struct flexcan_priv *priv) +{ + if (!priv->reg_xceiver) + return 0; + + return regulator_enable(priv->reg_xceiver); +} + +static inline int flexcan_transceiver_disable(const struct flexcan_priv *priv) +{ + if (!priv->reg_xceiver) + return 0; + + return regulator_disable(priv->reg_xceiver); +} + static inline int flexcan_has_and_handle_berr(const struct flexcan_priv *priv, u32 reg_esr) { @@ -266,26 +287,95 @@ static inline int flexcan_has_and_handle_berr(const struct flexcan_priv *priv, (reg_esr & FLEXCAN_ESR_ERR_BUS); } -static inline void flexcan_chip_enable(struct flexcan_priv *priv) +static int flexcan_chip_enable(struct flexcan_priv *priv) { struct flexcan_regs __iomem *regs = priv->base; + unsigned int timeout = FLEXCAN_TIMEOUT_US / 10; u32 reg; reg = flexcan_read(®s->mcr); reg &= ~FLEXCAN_MCR_MDIS; flexcan_write(reg, ®s->mcr); - udelay(10); + while (timeout-- && (flexcan_read(®s->mcr) & FLEXCAN_MCR_LPM_ACK)) + usleep_range(10, 20); + + if (flexcan_read(®s->mcr) & FLEXCAN_MCR_LPM_ACK) + return -ETIMEDOUT; + + return 0; } -static inline void flexcan_chip_disable(struct flexcan_priv *priv) +static int flexcan_chip_disable(struct flexcan_priv *priv) { struct flexcan_regs __iomem *regs = priv->base; + unsigned int timeout = FLEXCAN_TIMEOUT_US / 10; u32 reg; reg = flexcan_read(®s->mcr); reg |= FLEXCAN_MCR_MDIS; flexcan_write(reg, ®s->mcr); + + while (timeout-- && !(flexcan_read(®s->mcr) & FLEXCAN_MCR_LPM_ACK)) + usleep_range(10, 20); + + if (!(flexcan_read(®s->mcr) & FLEXCAN_MCR_LPM_ACK)) + return -ETIMEDOUT; + + return 0; +} + +static int flexcan_chip_freeze(struct flexcan_priv *priv) +{ + struct flexcan_regs __iomem *regs = priv->base; + unsigned int timeout = 1000 * 1000 * 10 / priv->can.bittiming.bitrate; + u32 reg; + + reg = flexcan_read(®s->mcr); + reg |= FLEXCAN_MCR_HALT; + flexcan_write(reg, ®s->mcr); + + while (timeout-- && !(flexcan_read(®s->mcr) & FLEXCAN_MCR_FRZ_ACK)) + usleep_range(100, 200); + + if (!(flexcan_read(®s->mcr) & FLEXCAN_MCR_FRZ_ACK)) + return -ETIMEDOUT; + + return 0; +} + +static int flexcan_chip_unfreeze(struct flexcan_priv *priv) +{ + struct flexcan_regs __iomem *regs = priv->base; + unsigned int timeout = FLEXCAN_TIMEOUT_US / 10; + u32 reg; + + reg = flexcan_read(®s->mcr); + reg &= ~FLEXCAN_MCR_HALT; + flexcan_write(reg, ®s->mcr); + + while (timeout-- && (flexcan_read(®s->mcr) & FLEXCAN_MCR_FRZ_ACK)) + usleep_range(10, 20); + + if (flexcan_read(®s->mcr) & FLEXCAN_MCR_FRZ_ACK) + return -ETIMEDOUT; + + return 0; +} + +static int flexcan_chip_softreset(struct flexcan_priv *priv) +{ + struct flexcan_regs __iomem *regs = priv->base; + unsigned int timeout = FLEXCAN_TIMEOUT_US / 10; + + flexcan_write(FLEXCAN_MCR_SOFTRST, ®s->mcr); + while (timeout-- && (flexcan_read(®s->mcr) & FLEXCAN_MCR_SOFTRST)) + usleep_range(10, 20); + + if (flexcan_read(®s->mcr) & FLEXCAN_MCR_SOFTRST) + return -ETIMEDOUT; + + return 0; } static int flexcan_get_berr_counter(const struct net_device *dev, @@ -706,19 +796,14 @@ static int flexcan_chip_start(struct net_device *dev) u32 reg_mcr, reg_ctrl; /* enable module */ - flexcan_chip_enable(priv); + err = flexcan_chip_enable(priv); + if (err) + return err; /* soft reset */ - flexcan_write(FLEXCAN_MCR_SOFTRST, ®s->mcr); - udelay(10); - - reg_mcr = flexcan_read(®s->mcr); - if (reg_mcr & FLEXCAN_MCR_SOFTRST) { - netdev_err(dev, "Failed to softreset can module (mcr=0x%08x)\n", - reg_mcr); - err = -ENODEV; - goto out; - } + err = flexcan_chip_softreset(priv); + if (err) + goto out_chip_disable; flexcan_set_bittiming(dev); @@ -785,16 +870,14 @@ static int flexcan_chip_start(struct net_device *dev) if (priv->devtype_data->features & FLEXCAN_HAS_V10_FEATURES) flexcan_write(0x0, ®s->rxfgmask); - if (priv->reg_xceiver) { - err = regulator_enable(priv->reg_xceiver); - if (err) - goto out; - } + err = flexcan_transceiver_enable(priv); + if (err) + goto out_chip_disable; /* synchronize with the can bus */ - reg_mcr = flexcan_read(®s->mcr); - reg_mcr &= ~FLEXCAN_MCR_HALT; - flexcan_write(reg_mcr, ®s->mcr); + err = flexcan_chip_unfreeze(priv); + if (err) + goto out_transceiver_disable; priv->can.state = CAN_STATE_ERROR_ACTIVE; @@ -807,7 +890,9 @@ static int flexcan_chip_start(struct net_device *dev) return 0; - out: + out_transceiver_disable: + flexcan_transceiver_disable(priv); + out_chip_disable: flexcan_chip_disable(priv); return err; } @@ -822,18 +907,17 @@ static void flexcan_chip_stop(struct net_device *dev) { struct flexcan_priv *priv = netdev_priv(dev); struct flexcan_regs __iomem *regs = priv->base; - u32 reg; + + /* freeze + disable module */ + flexcan_chip_freeze(priv); + flexcan_chip_disable(priv); /* Disable all interrupts */ flexcan_write(0, ®s->imask1); + flexcan_write(priv->reg_ctrl_default & ~FLEXCAN_CTRL_ERR_ALL, + ®s->ctrl); - /* Disable + halt module */ - reg = flexcan_read(®s->mcr); - reg |= FLEXCAN_MCR_MDIS | FLEXCAN_MCR_HALT; - flexcan_write(reg, ®s->mcr); - - if (priv->reg_xceiver) - regulator_disable(priv->reg_xceiver); + flexcan_transceiver_disable(priv); priv->can.state = CAN_STATE_STOPPED; return; @@ -863,7 +947,7 @@ static int flexcan_open(struct net_device *dev) /* start chip and queuing */ err = flexcan_chip_start(dev); if (err) - goto out_close; + goto out_free_irq; can_led_event(dev, CAN_LED_EVENT_OPEN); @@ -872,6 +956,8 @@ static int flexcan_open(struct net_device *dev) return 0; + out_free_irq: + free_irq(dev->irq, dev); out_close: close_candev(dev); out_disable_per: @@ -942,12 +1028,16 @@ static int register_flexcandev(struct net_device *dev) goto out_disable_ipg; /* select "bus clock", chip must be disabled */ - flexcan_chip_disable(priv); + err = flexcan_chip_disable(priv); + if (err) + goto out_disable_per; reg = flexcan_read(®s->ctrl); reg |= FLEXCAN_CTRL_CLK_SRC; flexcan_write(reg, ®s->ctrl); - flexcan_chip_enable(priv); + err = flexcan_chip_enable(priv); + if (err) + goto out_chip_disable; /* set freeze, halt and activate FIFO, restrict register access */ reg = flexcan_read(®s->mcr); @@ -964,14 +1054,15 @@ static int register_flexcandev(struct net_device *dev) if (!(reg & FLEXCAN_MCR_FEN)) { netdev_err(dev, "Could not enable RX FIFO, unsupported core\n"); err = -ENODEV; - goto out_disable_per; + goto out_chip_disable; } err = register_candev(dev); - out_disable_per: /* disable core and turn off clocks */ + out_chip_disable: flexcan_chip_disable(priv); + out_disable_per: clk_disable_unprepare(priv->clk_per); out_disable_ipg: clk_disable_unprepare(priv->clk_ipg); @@ -1041,9 +1132,9 @@ static int flexcan_probe(struct platform_device *pdev) of_id = of_match_device(flexcan_of_match, &pdev->dev); if (of_id) { devtype_data = of_id->data; - } else if (pdev->id_entry->driver_data) { + } else if (platform_get_device_id(pdev)->driver_data) { devtype_data = (struct flexcan_devtype_data *) - pdev->id_entry->driver_data; + platform_get_device_id(pdev)->driver_data; } else { return -ENODEV; } @@ -1101,21 +1192,24 @@ static int flexcan_probe(struct platform_device *pdev) static int flexcan_remove(struct platform_device *pdev) { struct net_device *dev = platform_get_drvdata(pdev); + struct flexcan_priv *priv = netdev_priv(dev); unregister_flexcandev(dev); - + netif_napi_del(&priv->napi); free_candev(dev); return 0; } -#ifdef CONFIG_PM_SLEEP -static int flexcan_suspend(struct device *device) +static int __maybe_unused flexcan_suspend(struct device *device) { struct net_device *dev = dev_get_drvdata(device); struct flexcan_priv *priv = netdev_priv(dev); + int err; - flexcan_chip_disable(priv); + err = flexcan_chip_disable(priv); + if (err) + return err; if (netif_running(dev)) { netif_stop_queue(dev); @@ -1126,7 +1220,7 @@ static int flexcan_suspend(struct device *device) return 0; } -static int flexcan_resume(struct device *device) +static int __maybe_unused flexcan_resume(struct device *device) { struct net_device *dev = dev_get_drvdata(device); struct flexcan_priv *priv = netdev_priv(dev); @@ -1136,11 +1230,8 @@ static int flexcan_resume(struct device *device) netif_device_attach(dev); netif_start_queue(dev); } - flexcan_chip_enable(priv); - - return 0; + return flexcan_chip_enable(priv); } -#endif /* CONFIG_PM_SLEEP */ static SIMPLE_DEV_PM_OPS(flexcan_pm_ops, flexcan_suspend, flexcan_resume); diff --git a/drivers/net/can/janz-ican3.c b/drivers/net/can/janz-ican3.c index e24e6690d672..b47df5e482fa 100644 --- a/drivers/net/can/janz-ican3.c +++ b/drivers/net/can/janz-ican3.c @@ -18,6 +18,7 @@ #include <linux/netdevice.h> #include <linux/can.h> #include <linux/can/dev.h> +#include <linux/can/skb.h> #include <linux/can/error.h> #include <linux/mfd/janz.h> @@ -197,9 +198,6 @@ struct ican3_dev { struct net_device *ndev; struct napi_struct napi; - /* Device for printing */ - struct device *dev; - /* module number */ unsigned int num; @@ -294,7 +292,7 @@ static int ican3_old_recv_msg(struct ican3_dev *mod, struct ican3_msg *msg) xord = locl ^ peer; if ((xord & MSYNC_RB_MASK) == 0x00) { - dev_dbg(mod->dev, "no mbox for reading\n"); + netdev_dbg(mod->ndev, "no mbox for reading\n"); return -ENOMEM; } @@ -339,7 +337,7 @@ static int ican3_old_send_msg(struct ican3_dev *mod, struct ican3_msg *msg) xord = locl ^ peer; if ((xord & MSYNC_WB_MASK) == MSYNC_WB_MASK) { - dev_err(mod->dev, "no mbox for writing\n"); + netdev_err(mod->ndev, "no mbox for writing\n"); return -ENOMEM; } @@ -541,7 +539,7 @@ static int ican3_new_send_msg(struct ican3_dev *mod, struct ican3_msg *msg) memcpy_fromio(&desc, desc_addr, sizeof(desc)); if (!(desc.control & DESC_VALID)) { - dev_dbg(mod->dev, "%s: no free buffers\n", __func__); + netdev_dbg(mod->ndev, "%s: no free buffers\n", __func__); return -ENOMEM; } @@ -572,7 +570,7 @@ static int ican3_new_recv_msg(struct ican3_dev *mod, struct ican3_msg *msg) memcpy_fromio(&desc, desc_addr, sizeof(desc)); if (!(desc.control & DESC_VALID)) { - dev_dbg(mod->dev, "%s: no buffers to recv\n", __func__); + netdev_dbg(mod->ndev, "%s: no buffers to recv\n", __func__); return -ENOMEM; } @@ -882,7 +880,7 @@ static void can_frame_to_ican3(struct ican3_dev *mod, */ static void ican3_handle_idvers(struct ican3_dev *mod, struct ican3_msg *msg) { - dev_dbg(mod->dev, "IDVERS response: %s\n", msg->data); + netdev_dbg(mod->ndev, "IDVERS response: %s\n", msg->data); } static void ican3_handle_msglost(struct ican3_dev *mod, struct ican3_msg *msg) @@ -898,7 +896,7 @@ static void ican3_handle_msglost(struct ican3_dev *mod, struct ican3_msg *msg) * error frame for userspace */ if (msg->spec == MSG_MSGLOST) { - dev_err(mod->dev, "lost %d control messages\n", msg->data[0]); + netdev_err(mod->ndev, "lost %d control messages\n", msg->data[0]); return; } @@ -938,13 +936,13 @@ static int ican3_handle_cevtind(struct ican3_dev *mod, struct ican3_msg *msg) /* we can only handle the SJA1000 part */ if (msg->data[1] != CEVTIND_CHIP_SJA1000) { - dev_err(mod->dev, "unable to handle errors on non-SJA1000\n"); + netdev_err(mod->ndev, "unable to handle errors on non-SJA1000\n"); return -ENODEV; } /* check the message length for sanity */ if (le16_to_cpu(msg->len) < 6) { - dev_err(mod->dev, "error message too short\n"); + netdev_err(mod->ndev, "error message too short\n"); return -EINVAL; } @@ -966,7 +964,7 @@ static int ican3_handle_cevtind(struct ican3_dev *mod, struct ican3_msg *msg) */ if (isrc == CEVTIND_BEI) { int ret; - dev_dbg(mod->dev, "bus error interrupt\n"); + netdev_dbg(mod->ndev, "bus error interrupt\n"); /* TX error */ if (!(ecc & ECC_DIR)) { @@ -982,7 +980,7 @@ static int ican3_handle_cevtind(struct ican3_dev *mod, struct ican3_msg *msg) */ ret = ican3_set_buserror(mod, 1); if (ret) { - dev_err(mod->dev, "unable to re-enable bus-error\n"); + netdev_err(mod->ndev, "unable to re-enable bus-error\n"); return ret; } @@ -997,7 +995,7 @@ static int ican3_handle_cevtind(struct ican3_dev *mod, struct ican3_msg *msg) /* data overrun interrupt */ if (isrc == CEVTIND_DOI || isrc == CEVTIND_LOST) { - dev_dbg(mod->dev, "data overrun interrupt\n"); + netdev_dbg(mod->ndev, "data overrun interrupt\n"); cf->can_id |= CAN_ERR_CRTL; cf->data[1] = CAN_ERR_CRTL_RX_OVERFLOW; stats->rx_over_errors++; @@ -1006,7 +1004,7 @@ static int ican3_handle_cevtind(struct ican3_dev *mod, struct ican3_msg *msg) /* error warning + passive interrupt */ if (isrc == CEVTIND_EI) { - dev_dbg(mod->dev, "error warning + passive interrupt\n"); + netdev_dbg(mod->ndev, "error warning + passive interrupt\n"); if (status & SR_BS) { state = CAN_STATE_BUS_OFF; cf->can_id |= CAN_ERR_BUSOFF; @@ -1087,7 +1085,7 @@ static void ican3_handle_inquiry(struct ican3_dev *mod, struct ican3_msg *msg) complete(&mod->termination_comp); break; default: - dev_err(mod->dev, "received an unknown inquiry response\n"); + netdev_err(mod->ndev, "received an unknown inquiry response\n"); break; } } @@ -1095,7 +1093,7 @@ static void ican3_handle_inquiry(struct ican3_dev *mod, struct ican3_msg *msg) static void ican3_handle_unknown_message(struct ican3_dev *mod, struct ican3_msg *msg) { - dev_warn(mod->dev, "received unknown message: spec 0x%.2x length %d\n", + netdev_warn(mod->ndev, "received unknown message: spec 0x%.2x length %d\n", msg->spec, le16_to_cpu(msg->len)); } @@ -1104,7 +1102,7 @@ static void ican3_handle_unknown_message(struct ican3_dev *mod, */ static void ican3_handle_message(struct ican3_dev *mod, struct ican3_msg *msg) { - dev_dbg(mod->dev, "%s: modno %d spec 0x%.2x len %d bytes\n", __func__, + netdev_dbg(mod->ndev, "%s: modno %d spec 0x%.2x len %d bytes\n", __func__, mod->num, msg->spec, le16_to_cpu(msg->len)); switch (msg->spec) { @@ -1133,20 +1131,9 @@ static void ican3_handle_message(struct ican3_dev *mod, struct ican3_msg *msg) */ static void ican3_put_echo_skb(struct ican3_dev *mod, struct sk_buff *skb) { - struct sock *srcsk = skb->sk; - - if (atomic_read(&skb->users) != 1) { - struct sk_buff *old_skb = skb; - - skb = skb_clone(old_skb, GFP_ATOMIC); - kfree_skb(old_skb); - if (!skb) - return; - } else { - skb_orphan(skb); - } - - skb->sk = srcsk; + skb = can_create_echo_skb(skb); + if (!skb) + return; /* save this skb for tx interrupt echo handling */ skb_queue_tail(&mod->echoq, skb); @@ -1322,7 +1309,7 @@ static int ican3_napi(struct napi_struct *napi, int budget) /* process all communication messages */ while (true) { - struct ican3_msg msg; + struct ican3_msg uninitialized_var(msg); ret = ican3_recv_msg(mod, &msg); if (ret) break; @@ -1416,7 +1403,7 @@ static int ican3_reset_module(struct ican3_dev *mod) msleep(10); } while (time_before(jiffies, start + HZ / 4)); - dev_err(mod->dev, "failed to reset CAN module\n"); + netdev_err(mod->ndev, "failed to reset CAN module\n"); return -ETIMEDOUT; } @@ -1435,7 +1422,7 @@ static int ican3_startup_module(struct ican3_dev *mod) ret = ican3_reset_module(mod); if (ret) { - dev_err(mod->dev, "unable to reset module\n"); + netdev_err(mod->ndev, "unable to reset module\n"); return ret; } @@ -1444,41 +1431,41 @@ static int ican3_startup_module(struct ican3_dev *mod) ret = ican3_msg_connect(mod); if (ret) { - dev_err(mod->dev, "unable to connect to module\n"); + netdev_err(mod->ndev, "unable to connect to module\n"); return ret; } ican3_init_new_host_interface(mod); ret = ican3_msg_newhostif(mod); if (ret) { - dev_err(mod->dev, "unable to switch to new-style interface\n"); + netdev_err(mod->ndev, "unable to switch to new-style interface\n"); return ret; } /* default to "termination on" */ ret = ican3_set_termination(mod, true); if (ret) { - dev_err(mod->dev, "unable to enable termination\n"); + netdev_err(mod->ndev, "unable to enable termination\n"); return ret; } /* default to "bus errors enabled" */ ret = ican3_set_buserror(mod, 1); if (ret) { - dev_err(mod->dev, "unable to set bus-error\n"); + netdev_err(mod->ndev, "unable to set bus-error\n"); return ret; } ican3_init_fast_host_interface(mod); ret = ican3_msg_fasthostif(mod); if (ret) { - dev_err(mod->dev, "unable to switch to fast host interface\n"); + netdev_err(mod->ndev, "unable to switch to fast host interface\n"); return ret; } ret = ican3_set_id_filter(mod, true); if (ret) { - dev_err(mod->dev, "unable to set acceptance filter\n"); + netdev_err(mod->ndev, "unable to set acceptance filter\n"); return ret; } @@ -1497,14 +1484,14 @@ static int ican3_open(struct net_device *ndev) /* open the CAN layer */ ret = open_candev(ndev); if (ret) { - dev_err(mod->dev, "unable to start CAN layer\n"); + netdev_err(mod->ndev, "unable to start CAN layer\n"); return ret; } /* bring the bus online */ ret = ican3_set_bus_state(mod, true); if (ret) { - dev_err(mod->dev, "unable to set bus-on\n"); + netdev_err(mod->ndev, "unable to set bus-on\n"); close_candev(ndev); return ret; } @@ -1528,7 +1515,7 @@ static int ican3_stop(struct net_device *ndev) /* bring the bus offline, stop receiving packets */ ret = ican3_set_bus_state(mod, false); if (ret) { - dev_err(mod->dev, "unable to set bus-off\n"); + netdev_err(mod->ndev, "unable to set bus-off\n"); return ret; } @@ -1555,7 +1542,7 @@ static int ican3_xmit(struct sk_buff *skb, struct net_device *ndev) /* check that we can actually transmit */ if (!ican3_txok(mod)) { - dev_err(mod->dev, "BUG: no free descriptors\n"); + netdev_err(mod->ndev, "BUG: no free descriptors\n"); spin_unlock_irqrestore(&mod->lock, flags); return NETDEV_TX_BUSY; } @@ -1667,7 +1654,7 @@ static int ican3_set_mode(struct net_device *ndev, enum can_mode mode) /* bring the bus online */ ret = ican3_set_bus_state(mod, true); if (ret) { - dev_err(mod->dev, "unable to set bus-on\n"); + netdev_err(ndev, "unable to set bus-on\n"); return ret; } @@ -1692,7 +1679,7 @@ static int ican3_get_berr_counter(const struct net_device *ndev, ret = wait_for_completion_timeout(&mod->buserror_comp, HZ); if (ret == 0) { - dev_info(mod->dev, "%s timed out\n", __func__); + netdev_info(mod->ndev, "%s timed out\n", __func__); return -ETIMEDOUT; } @@ -1718,7 +1705,7 @@ static ssize_t ican3_sysfs_show_term(struct device *dev, ret = wait_for_completion_timeout(&mod->termination_comp, HZ); if (ret == 0) { - dev_info(mod->dev, "%s timed out\n", __func__); + netdev_info(mod->ndev, "%s timed out\n", __func__); return -ETIMEDOUT; } @@ -1788,7 +1775,6 @@ static int ican3_probe(struct platform_device *pdev) platform_set_drvdata(pdev, ndev); mod = netdev_priv(ndev); mod->ndev = ndev; - mod->dev = &pdev->dev; mod->num = pdata->modno; netif_napi_add(ndev, &mod->napi, ican3_napi, ICAN3_RX_BUFFERS); skb_queue_head_init(&mod->echoq); diff --git a/drivers/net/can/mcp251x.c b/drivers/net/can/mcp251x.c index cdb9808d12db..50aa630c7dd4 100644 --- a/drivers/net/can/mcp251x.c +++ b/drivers/net/can/mcp251x.c @@ -601,10 +601,10 @@ static int mcp251x_do_set_bittiming(struct net_device *net) (bt->prop_seg - 1)); mcp251x_write_bits(spi, CNF3, CNF3_PHSEG2_MASK, (bt->phase_seg2 - 1)); - dev_info(&spi->dev, "CNF: 0x%02x 0x%02x 0x%02x\n", - mcp251x_read_reg(spi, CNF1), - mcp251x_read_reg(spi, CNF2), - mcp251x_read_reg(spi, CNF3)); + dev_dbg(&spi->dev, "CNF: 0x%02x 0x%02x 0x%02x\n", + mcp251x_read_reg(spi, CNF1), + mcp251x_read_reg(spi, CNF2), + mcp251x_read_reg(spi, CNF3)); return 0; } @@ -1155,8 +1155,6 @@ static int mcp251x_can_probe(struct spi_device *spi) devm_can_led_init(net); - dev_info(&spi->dev, "probed\n"); - return ret; error_probe: @@ -1197,9 +1195,7 @@ static int mcp251x_can_remove(struct spi_device *spi) return 0; } -#ifdef CONFIG_PM_SLEEP - -static int mcp251x_can_suspend(struct device *dev) +static int __maybe_unused mcp251x_can_suspend(struct device *dev) { struct spi_device *spi = to_spi_device(dev); struct mcp251x_priv *priv = spi_get_drvdata(spi); @@ -1229,7 +1225,7 @@ static int mcp251x_can_suspend(struct device *dev) return 0; } -static int mcp251x_can_resume(struct device *dev) +static int __maybe_unused mcp251x_can_resume(struct device *dev) { struct spi_device *spi = to_spi_device(dev); struct mcp251x_priv *priv = spi_get_drvdata(spi); @@ -1249,7 +1245,6 @@ static int mcp251x_can_resume(struct device *dev) enable_irq(spi->irq); return 0; } -#endif static SIMPLE_DEV_PM_OPS(mcp251x_can_pm_ops, mcp251x_can_suspend, mcp251x_can_resume); diff --git a/drivers/net/can/sja1000/Kconfig b/drivers/net/can/sja1000/Kconfig index ff2ba86cd4a4..4b18b8765523 100644 --- a/drivers/net/can/sja1000/Kconfig +++ b/drivers/net/can/sja1000/Kconfig @@ -17,16 +17,9 @@ config CAN_SJA1000_PLATFORM the "platform bus" (Linux abstraction for directly to the processor attached devices). Which can be found on various boards from Phytec (http://www.phytec.de) like the PCM027, - PCM038. - -config CAN_SJA1000_OF_PLATFORM - tristate "Generic OF Platform Bus based SJA1000 driver" - depends on OF - ---help--- - This driver adds support for the SJA1000 chips connected to - the OpenFirmware "platform bus" found on embedded systems with - OpenFirmware bindings, e.g. if you have a PowerPC based system - you may want to enable this option. + PCM038. It also provides the OpenFirmware "platform bus" found + on embedded systems with OpenFirmware bindings, e.g. if you + have a PowerPC based system you may want to enable this option. config CAN_EMS_PCMCIA tristate "EMS CPC-CARD Card" diff --git a/drivers/net/can/sja1000/Makefile b/drivers/net/can/sja1000/Makefile index b3d05cbfec36..531d5fcc97e5 100644 --- a/drivers/net/can/sja1000/Makefile +++ b/drivers/net/can/sja1000/Makefile @@ -5,7 +5,6 @@ obj-$(CONFIG_CAN_SJA1000) += sja1000.o obj-$(CONFIG_CAN_SJA1000_ISA) += sja1000_isa.o obj-$(CONFIG_CAN_SJA1000_PLATFORM) += sja1000_platform.o -obj-$(CONFIG_CAN_SJA1000_OF_PLATFORM) += sja1000_of_platform.o obj-$(CONFIG_CAN_EMS_PCMCIA) += ems_pcmcia.o obj-$(CONFIG_CAN_EMS_PCI) += ems_pci.o obj-$(CONFIG_CAN_KVASER_PCI) += kvaser_pci.o diff --git a/drivers/net/can/sja1000/sja1000.c b/drivers/net/can/sja1000/sja1000.c index f17c3018b7c7..55cce4737518 100644 --- a/drivers/net/can/sja1000/sja1000.c +++ b/drivers/net/can/sja1000/sja1000.c @@ -106,8 +106,7 @@ static int sja1000_probe_chip(struct net_device *dev) struct sja1000_priv *priv = netdev_priv(dev); if (priv->reg_base && sja1000_is_absent(priv)) { - printk(KERN_INFO "%s: probing @0x%lX failed\n", - DRV_NAME, dev->base_addr); + netdev_err(dev, "probing failed\n"); return 0; } return -1; diff --git a/drivers/net/can/sja1000/sja1000_of_platform.c b/drivers/net/can/sja1000/sja1000_of_platform.c deleted file mode 100644 index 2f6e24534231..000000000000 --- a/drivers/net/can/sja1000/sja1000_of_platform.c +++ /dev/null @@ -1,220 +0,0 @@ -/* - * Driver for SJA1000 CAN controllers on the OpenFirmware platform bus - * - * Copyright (C) 2008-2009 Wolfgang Grandegger <wg@grandegger.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the version 2 of the GNU General Public License - * as published by the Free Software Foundation - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, see <http://www.gnu.org/licenses/>. - */ - -/* This is a generic driver for SJA1000 chips on the OpenFirmware platform - * bus found on embedded PowerPC systems. You need a SJA1000 CAN node - * definition in your flattened device tree source (DTS) file similar to: - * - * can@3,100 { - * compatible = "nxp,sja1000"; - * reg = <3 0x100 0x80>; - * interrupts = <2 0>; - * interrupt-parent = <&mpic>; - * nxp,external-clock-frequency = <16000000>; - * }; - * - * See "Documentation/devicetree/bindings/net/can/sja1000.txt" for further - * information. - */ - -#include <linux/kernel.h> -#include <linux/module.h> -#include <linux/interrupt.h> -#include <linux/netdevice.h> -#include <linux/delay.h> -#include <linux/io.h> -#include <linux/can/dev.h> - -#include <linux/of_platform.h> -#include <linux/of_address.h> -#include <linux/of_irq.h> - -#include "sja1000.h" - -#define DRV_NAME "sja1000_of_platform" - -MODULE_AUTHOR("Wolfgang Grandegger <wg@grandegger.com>"); -MODULE_DESCRIPTION("Socket-CAN driver for SJA1000 on the OF platform bus"); -MODULE_LICENSE("GPL v2"); - -#define SJA1000_OFP_CAN_CLOCK (16000000 / 2) - -#define SJA1000_OFP_OCR OCR_TX0_PULLDOWN -#define SJA1000_OFP_CDR (CDR_CBP | CDR_CLK_OFF) - -static u8 sja1000_ofp_read_reg(const struct sja1000_priv *priv, int reg) -{ - return ioread8(priv->reg_base + reg); -} - -static void sja1000_ofp_write_reg(const struct sja1000_priv *priv, - int reg, u8 val) -{ - iowrite8(val, priv->reg_base + reg); -} - -static int sja1000_ofp_remove(struct platform_device *ofdev) -{ - struct net_device *dev = platform_get_drvdata(ofdev); - struct sja1000_priv *priv = netdev_priv(dev); - struct device_node *np = ofdev->dev.of_node; - struct resource res; - - unregister_sja1000dev(dev); - free_sja1000dev(dev); - iounmap(priv->reg_base); - irq_dispose_mapping(dev->irq); - - of_address_to_resource(np, 0, &res); - release_mem_region(res.start, resource_size(&res)); - - return 0; -} - -static int sja1000_ofp_probe(struct platform_device *ofdev) -{ - struct device_node *np = ofdev->dev.of_node; - struct net_device *dev; - struct sja1000_priv *priv; - struct resource res; - u32 prop; - int err, irq, res_size; - void __iomem *base; - - err = of_address_to_resource(np, 0, &res); - if (err) { - dev_err(&ofdev->dev, "invalid address\n"); - return err; - } - - res_size = resource_size(&res); - - if (!request_mem_region(res.start, res_size, DRV_NAME)) { - dev_err(&ofdev->dev, "couldn't request %pR\n", &res); - return -EBUSY; - } - - base = ioremap_nocache(res.start, res_size); - if (!base) { - dev_err(&ofdev->dev, "couldn't ioremap %pR\n", &res); - err = -ENOMEM; - goto exit_release_mem; - } - - irq = irq_of_parse_and_map(np, 0); - if (irq == 0) { - dev_err(&ofdev->dev, "no irq found\n"); - err = -ENODEV; - goto exit_unmap_mem; - } - - dev = alloc_sja1000dev(0); - if (!dev) { - err = -ENOMEM; - goto exit_dispose_irq; - } - - priv = netdev_priv(dev); - - priv->read_reg = sja1000_ofp_read_reg; - priv->write_reg = sja1000_ofp_write_reg; - - err = of_property_read_u32(np, "nxp,external-clock-frequency", &prop); - if (!err) - priv->can.clock.freq = prop / 2; - else - priv->can.clock.freq = SJA1000_OFP_CAN_CLOCK; /* default */ - - err = of_property_read_u32(np, "nxp,tx-output-mode", &prop); - if (!err) - priv->ocr |= prop & OCR_MODE_MASK; - else - priv->ocr |= OCR_MODE_NORMAL; /* default */ - - err = of_property_read_u32(np, "nxp,tx-output-config", &prop); - if (!err) - priv->ocr |= (prop << OCR_TX_SHIFT) & OCR_TX_MASK; - else - priv->ocr |= OCR_TX0_PULLDOWN; /* default */ - - err = of_property_read_u32(np, "nxp,clock-out-frequency", &prop); - if (!err && prop) { - u32 divider = priv->can.clock.freq * 2 / prop; - - if (divider > 1) - priv->cdr |= divider / 2 - 1; - else - priv->cdr |= CDR_CLKOUT_MASK; - } else { - priv->cdr |= CDR_CLK_OFF; /* default */ - } - - if (!of_property_read_bool(np, "nxp,no-comparator-bypass")) - priv->cdr |= CDR_CBP; /* default */ - - priv->irq_flags = IRQF_SHARED; - priv->reg_base = base; - - dev->irq = irq; - - dev_info(&ofdev->dev, - "reg_base=0x%p irq=%d clock=%d ocr=0x%02x cdr=0x%02x\n", - priv->reg_base, dev->irq, priv->can.clock.freq, - priv->ocr, priv->cdr); - - platform_set_drvdata(ofdev, dev); - SET_NETDEV_DEV(dev, &ofdev->dev); - - err = register_sja1000dev(dev); - if (err) { - dev_err(&ofdev->dev, "registering %s failed (err=%d)\n", - DRV_NAME, err); - goto exit_free_sja1000; - } - - return 0; - -exit_free_sja1000: - free_sja1000dev(dev); -exit_dispose_irq: - irq_dispose_mapping(irq); -exit_unmap_mem: - iounmap(base); -exit_release_mem: - release_mem_region(res.start, res_size); - - return err; -} - -static struct of_device_id sja1000_ofp_table[] = { - {.compatible = "nxp,sja1000"}, - {}, -}; -MODULE_DEVICE_TABLE(of, sja1000_ofp_table); - -static struct platform_driver sja1000_ofp_driver = { - .driver = { - .owner = THIS_MODULE, - .name = DRV_NAME, - .of_match_table = sja1000_ofp_table, - }, - .probe = sja1000_ofp_probe, - .remove = sja1000_ofp_remove, -}; - -module_platform_driver(sja1000_ofp_driver); diff --git a/drivers/net/can/sja1000/sja1000_platform.c b/drivers/net/can/sja1000/sja1000_platform.c index 943df645b459..95a844a7ee7b 100644 --- a/drivers/net/can/sja1000/sja1000_platform.c +++ b/drivers/net/can/sja1000/sja1000_platform.c @@ -26,12 +26,16 @@ #include <linux/can/dev.h> #include <linux/can/platform/sja1000.h> #include <linux/io.h> +#include <linux/of.h> +#include <linux/of_irq.h> #include "sja1000.h" #define DRV_NAME "sja1000_platform" +#define SP_CAN_CLOCK (16000000 / 2) MODULE_AUTHOR("Sascha Hauer <s.hauer@pengutronix.de>"); +MODULE_AUTHOR("Wolfgang Grandegger <wg@grandegger.com>"); MODULE_DESCRIPTION("Socket-CAN driver for SJA1000 on the platform bus"); MODULE_ALIAS("platform:" DRV_NAME); MODULE_LICENSE("GPL v2"); @@ -66,59 +70,16 @@ static void sp_write_reg32(const struct sja1000_priv *priv, int reg, u8 val) iowrite8(val, priv->reg_base + reg * 4); } -static int sp_probe(struct platform_device *pdev) +static void sp_populate(struct sja1000_priv *priv, + struct sja1000_platform_data *pdata, + unsigned long resource_mem_flags) { - int err; - void __iomem *addr; - struct net_device *dev; - struct sja1000_priv *priv; - struct resource *res_mem, *res_irq; - struct sja1000_platform_data *pdata; - - pdata = dev_get_platdata(&pdev->dev); - if (!pdata) { - dev_err(&pdev->dev, "No platform data provided!\n"); - err = -ENODEV; - goto exit; - } - - res_mem = platform_get_resource(pdev, IORESOURCE_MEM, 0); - res_irq = platform_get_resource(pdev, IORESOURCE_IRQ, 0); - if (!res_mem || !res_irq) { - err = -ENODEV; - goto exit; - } - - if (!request_mem_region(res_mem->start, resource_size(res_mem), - DRV_NAME)) { - err = -EBUSY; - goto exit; - } - - addr = ioremap_nocache(res_mem->start, resource_size(res_mem)); - if (!addr) { - err = -ENOMEM; - goto exit_release; - } - - dev = alloc_sja1000dev(0); - if (!dev) { - err = -ENOMEM; - goto exit_iounmap; - } - priv = netdev_priv(dev); - - dev->irq = res_irq->start; - priv->irq_flags = res_irq->flags & IRQF_TRIGGER_MASK; - if (res_irq->flags & IORESOURCE_IRQ_SHAREABLE) - priv->irq_flags |= IRQF_SHARED; - priv->reg_base = addr; /* The CAN clock frequency is half the oscillator clock frequency */ priv->can.clock.freq = pdata->osc_freq / 2; priv->ocr = pdata->ocr; priv->cdr = pdata->cdr; - switch (res_mem->flags & IORESOURCE_MEM_TYPE_MASK) { + switch (resource_mem_flags & IORESOURCE_MEM_TYPE_MASK) { case IORESOURCE_MEM_32BIT: priv->read_reg = sp_read_reg32; priv->write_reg = sp_write_reg32; @@ -133,6 +94,124 @@ static int sp_probe(struct platform_device *pdev) priv->write_reg = sp_write_reg8; break; } +} + +static void sp_populate_of(struct sja1000_priv *priv, struct device_node *of) +{ + int err; + u32 prop; + + err = of_property_read_u32(of, "reg-io-width", &prop); + if (err) + prop = 1; /* 8 bit is default */ + + switch (prop) { + case 4: + priv->read_reg = sp_read_reg32; + priv->write_reg = sp_write_reg32; + break; + case 2: + priv->read_reg = sp_read_reg16; + priv->write_reg = sp_write_reg16; + break; + case 1: /* fallthrough */ + default: + priv->read_reg = sp_read_reg8; + priv->write_reg = sp_write_reg8; + } + + err = of_property_read_u32(of, "nxp,external-clock-frequency", &prop); + if (!err) + priv->can.clock.freq = prop / 2; + else + priv->can.clock.freq = SP_CAN_CLOCK; /* default */ + + err = of_property_read_u32(of, "nxp,tx-output-mode", &prop); + if (!err) + priv->ocr |= prop & OCR_MODE_MASK; + else + priv->ocr |= OCR_MODE_NORMAL; /* default */ + + err = of_property_read_u32(of, "nxp,tx-output-config", &prop); + if (!err) + priv->ocr |= (prop << OCR_TX_SHIFT) & OCR_TX_MASK; + else + priv->ocr |= OCR_TX0_PULLDOWN; /* default */ + + err = of_property_read_u32(of, "nxp,clock-out-frequency", &prop); + if (!err && prop) { + u32 divider = priv->can.clock.freq * 2 / prop; + + if (divider > 1) + priv->cdr |= divider / 2 - 1; + else + priv->cdr |= CDR_CLKOUT_MASK; + } else { + priv->cdr |= CDR_CLK_OFF; /* default */ + } + + if (!of_property_read_bool(of, "nxp,no-comparator-bypass")) + priv->cdr |= CDR_CBP; /* default */ +} + +static int sp_probe(struct platform_device *pdev) +{ + int err, irq = 0; + void __iomem *addr; + struct net_device *dev; + struct sja1000_priv *priv; + struct resource *res_mem, *res_irq = NULL; + struct sja1000_platform_data *pdata; + struct device_node *of = pdev->dev.of_node; + + pdata = dev_get_platdata(&pdev->dev); + if (!pdata && !of) { + dev_err(&pdev->dev, "No platform data provided!\n"); + return -ENODEV; + } + + res_mem = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (!res_mem) + return -ENODEV; + + if (!devm_request_mem_region(&pdev->dev, res_mem->start, + resource_size(res_mem), DRV_NAME)) + return -EBUSY; + + addr = devm_ioremap_nocache(&pdev->dev, res_mem->start, + resource_size(res_mem)); + if (!addr) + return -ENOMEM; + + if (of) + irq = irq_of_parse_and_map(of, 0); + else + res_irq = platform_get_resource(pdev, IORESOURCE_IRQ, 0); + + if (!irq && !res_irq) + return -ENODEV; + + dev = alloc_sja1000dev(0); + if (!dev) + return -ENOMEM; + priv = netdev_priv(dev); + + if (res_irq) { + irq = res_irq->start; + priv->irq_flags = res_irq->flags & IRQF_TRIGGER_MASK; + if (res_irq->flags & IORESOURCE_IRQ_SHAREABLE) + priv->irq_flags |= IRQF_SHARED; + } else { + priv->irq_flags = IRQF_SHARED; + } + + dev->irq = irq; + priv->reg_base = addr; + + if (of) + sp_populate_of(priv, of); + else + sp_populate(priv, pdata, res_mem->flags); platform_set_drvdata(pdev, dev); SET_NETDEV_DEV(dev, &pdev->dev); @@ -150,39 +229,32 @@ static int sp_probe(struct platform_device *pdev) exit_free: free_sja1000dev(dev); - exit_iounmap: - iounmap(addr); - exit_release: - release_mem_region(res_mem->start, resource_size(res_mem)); - exit: return err; } static int sp_remove(struct platform_device *pdev) { struct net_device *dev = platform_get_drvdata(pdev); - struct sja1000_priv *priv = netdev_priv(dev); - struct resource *res; unregister_sja1000dev(dev); - - if (priv->reg_base) - iounmap(priv->reg_base); - - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - release_mem_region(res->start, resource_size(res)); - free_sja1000dev(dev); return 0; } +static struct of_device_id sp_of_table[] = { + {.compatible = "nxp,sja1000"}, + {}, +}; +MODULE_DEVICE_TABLE(of, sp_of_table); + static struct platform_driver sp_driver = { .probe = sp_probe, .remove = sp_remove, .driver = { .name = DRV_NAME, .owner = THIS_MODULE, + .of_match_table = sp_of_table, }, }; diff --git a/drivers/net/can/usb/kvaser_usb.c b/drivers/net/can/usb/kvaser_usb.c index 6c859bba8b65..e77d11049747 100644 --- a/drivers/net/can/usb/kvaser_usb.c +++ b/drivers/net/can/usb/kvaser_usb.c @@ -473,6 +473,8 @@ static int kvaser_usb_get_card_info(struct kvaser_usb *dev) return err; dev->nchannels = msg.u.cardinfo.nchannels; + if (dev->nchannels > MAX_NET_DEVICES) + return -EINVAL; return 0; } diff --git a/drivers/net/can/vcan.c b/drivers/net/can/vcan.c index 0a2a5ee79a17..4e94057ef5cf 100644 --- a/drivers/net/can/vcan.c +++ b/drivers/net/can/vcan.c @@ -46,6 +46,7 @@ #include <linux/if_ether.h> #include <linux/can.h> #include <linux/can/dev.h> +#include <linux/can/skb.h> #include <linux/slab.h> #include <net/rtnetlink.h> @@ -109,25 +110,23 @@ static netdev_tx_t vcan_tx(struct sk_buff *skb, struct net_device *dev) stats->rx_packets++; stats->rx_bytes += cfd->len; } - kfree_skb(skb); + consume_skb(skb); return NETDEV_TX_OK; } /* perform standard echo handling for CAN network interfaces */ if (loop) { - struct sock *srcsk = skb->sk; - skb = skb_share_check(skb, GFP_ATOMIC); + skb = can_create_echo_skb(skb); if (!skb) return NETDEV_TX_OK; /* receive with packet counting */ - skb->sk = srcsk; vcan_rx(skb, dev); } else { /* no looped packets => no counting */ - kfree_skb(skb); + consume_skb(skb); } return NETDEV_TX_OK; } diff --git a/drivers/net/dummy.c b/drivers/net/dummy.c index bd8f84b0b894..1656317c96f8 100644 --- a/drivers/net/dummy.c +++ b/drivers/net/dummy.c @@ -88,16 +88,10 @@ static netdev_tx_t dummy_xmit(struct sk_buff *skb, struct net_device *dev) static int dummy_dev_init(struct net_device *dev) { - int i; - dev->dstats = alloc_percpu(struct pcpu_dstats); + dev->dstats = netdev_alloc_pcpu_stats(struct pcpu_dstats); if (!dev->dstats) return -ENOMEM; - for_each_possible_cpu(i) { - struct pcpu_dstats *dstats; - dstats = per_cpu_ptr(dev->dstats, i); - u64_stats_init(&dstats->syncp); - } return 0; } diff --git a/drivers/net/ethernet/3com/3c589_cs.c b/drivers/net/ethernet/3com/3c589_cs.c index 5992860a39c9..063557e037f2 100644 --- a/drivers/net/ethernet/3com/3c589_cs.c +++ b/drivers/net/ethernet/3com/3c589_cs.c @@ -1,23 +1,24 @@ -/*====================================================================== - - A PCMCIA ethernet driver for the 3com 3c589 card. - - Copyright (C) 1999 David A. Hinds -- dahinds@users.sourceforge.net - - 3c589_cs.c 1.162 2001/10/13 00:08:50 - - The network driver code is based on Donald Becker's 3c589 code: - - Written 1994 by Donald Becker. - Copyright 1993 United States Government as represented by the - Director, National Security Agency. This software may be used and - distributed according to the terms of the GNU General Public License, - incorporated herein by reference. - Donald Becker may be reached at becker@scyld.com - - Updated for 2.5.x by Alan Cox <alan@lxorguk.ukuu.org.uk> - -======================================================================*/ +/* ====================================================================== + * + * A PCMCIA ethernet driver for the 3com 3c589 card. + * + * Copyright (C) 1999 David A. Hinds -- dahinds@users.sourceforge.net + * + * 3c589_cs.c 1.162 2001/10/13 00:08:50 + * + * The network driver code is based on Donald Becker's 3c589 code: + * + * Written 1994 by Donald Becker. + * Copyright 1993 United States Government as represented by the + * Director, National Security Agency. This software may be used and + * distributed according to the terms of the GNU General Public License, + * incorporated herein by reference. + * Donald Becker may be reached at becker@scyld.com + * + * Updated for 2.5.x by Alan Cox <alan@lxorguk.ukuu.org.uk> + * + * ====================================================================== + */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt @@ -41,18 +42,20 @@ #include <linux/ioport.h> #include <linux/bitops.h> #include <linux/jiffies.h> +#include <linux/uaccess.h> +#include <linux/io.h> #include <pcmcia/cistpl.h> #include <pcmcia/cisreg.h> #include <pcmcia/ciscode.h> #include <pcmcia/ds.h> -#include <asm/uaccess.h> -#include <asm/io.h> /* To minimize the size of the driver source I only define operating - constants if they are used several times. You'll need the manual - if you want to understand driver details. */ + * constants if they are used several times. You'll need the manual + * if you want to understand driver details. + */ + /* Offsets from base I/O address. */ #define EL3_DATA 0x00 #define EL3_TIMER 0x0a @@ -65,7 +68,9 @@ #define EL3WINDOW(win_num) outw(SelectWindow + (win_num), ioaddr + EL3_CMD) /* The top five bits written to EL3_CMD are a command, the lower - 11 bits are the parameter, if applicable. */ + * 11 bits are the parameter, if applicable. + */ + enum c509cmd { TotalReset = 0<<11, SelectWindow = 1<<11, @@ -190,138 +195,142 @@ static const struct net_device_ops el3_netdev_ops = { static int tc589_probe(struct pcmcia_device *link) { - struct el3_private *lp; - struct net_device *dev; + struct el3_private *lp; + struct net_device *dev; - dev_dbg(&link->dev, "3c589_attach()\n"); + dev_dbg(&link->dev, "3c589_attach()\n"); - /* Create new ethernet device */ - dev = alloc_etherdev(sizeof(struct el3_private)); - if (!dev) - return -ENOMEM; - lp = netdev_priv(dev); - link->priv = dev; - lp->p_dev = link; + /* Create new ethernet device */ + dev = alloc_etherdev(sizeof(struct el3_private)); + if (!dev) + return -ENOMEM; + lp = netdev_priv(dev); + link->priv = dev; + lp->p_dev = link; - spin_lock_init(&lp->lock); - link->resource[0]->end = 16; - link->resource[0]->flags |= IO_DATA_PATH_WIDTH_16; + spin_lock_init(&lp->lock); + link->resource[0]->end = 16; + link->resource[0]->flags |= IO_DATA_PATH_WIDTH_16; - link->config_flags |= CONF_ENABLE_IRQ; - link->config_index = 1; + link->config_flags |= CONF_ENABLE_IRQ; + link->config_index = 1; - dev->netdev_ops = &el3_netdev_ops; - dev->watchdog_timeo = TX_TIMEOUT; + dev->netdev_ops = &el3_netdev_ops; + dev->watchdog_timeo = TX_TIMEOUT; - SET_ETHTOOL_OPS(dev, &netdev_ethtool_ops); + SET_ETHTOOL_OPS(dev, &netdev_ethtool_ops); - return tc589_config(link); + return tc589_config(link); } static void tc589_detach(struct pcmcia_device *link) { - struct net_device *dev = link->priv; + struct net_device *dev = link->priv; - dev_dbg(&link->dev, "3c589_detach\n"); + dev_dbg(&link->dev, "3c589_detach\n"); - unregister_netdev(dev); + unregister_netdev(dev); - tc589_release(link); + tc589_release(link); - free_netdev(dev); + free_netdev(dev); } /* tc589_detach */ static int tc589_config(struct pcmcia_device *link) { - struct net_device *dev = link->priv; - __be16 *phys_addr; - int ret, i, j, multi = 0, fifo; - unsigned int ioaddr; - static const char * const ram_split[] = {"5:3", "3:1", "1:1", "3:5"}; - u8 *buf; - size_t len; - - dev_dbg(&link->dev, "3c589_config\n"); - - phys_addr = (__be16 *)dev->dev_addr; - /* Is this a 3c562? */ - if (link->manf_id != MANFID_3COM) - dev_info(&link->dev, "hmmm, is this really a 3Com card??\n"); - multi = (link->card_id == PRODID_3COM_3C562); - - link->io_lines = 16; - - /* For the 3c562, the base address must be xx00-xx7f */ - for (i = j = 0; j < 0x400; j += 0x10) { - if (multi && (j & 0x80)) continue; - link->resource[0]->start = j ^ 0x300; - i = pcmcia_request_io(link); - if (i == 0) - break; - } - if (i != 0) - goto failed; - - ret = pcmcia_request_irq(link, el3_interrupt); - if (ret) - goto failed; - - ret = pcmcia_enable_device(link); - if (ret) - goto failed; - - dev->irq = link->irq; - dev->base_addr = link->resource[0]->start; - ioaddr = dev->base_addr; - EL3WINDOW(0); - - /* The 3c589 has an extra EEPROM for configuration info, including - the hardware address. The 3c562 puts the address in the CIS. */ - len = pcmcia_get_tuple(link, 0x88, &buf); - if (buf && len >= 6) { - for (i = 0; i < 3; i++) - phys_addr[i] = htons(le16_to_cpu(buf[i*2])); - kfree(buf); - } else { - kfree(buf); /* 0 < len < 6 */ - for (i = 0; i < 3; i++) - phys_addr[i] = htons(read_eeprom(ioaddr, i)); - if (phys_addr[0] == htons(0x6060)) { - dev_err(&link->dev, "IO port conflict at 0x%03lx-0x%03lx\n", - dev->base_addr, dev->base_addr+15); - goto failed; + struct net_device *dev = link->priv; + __be16 *phys_addr; + int ret, i, j, multi = 0, fifo; + unsigned int ioaddr; + static const char * const ram_split[] = {"5:3", "3:1", "1:1", "3:5"}; + u8 *buf; + size_t len; + + dev_dbg(&link->dev, "3c589_config\n"); + + phys_addr = (__be16 *)dev->dev_addr; + /* Is this a 3c562? */ + if (link->manf_id != MANFID_3COM) + dev_info(&link->dev, "hmmm, is this really a 3Com card??\n"); + multi = (link->card_id == PRODID_3COM_3C562); + + link->io_lines = 16; + + /* For the 3c562, the base address must be xx00-xx7f */ + for (i = j = 0; j < 0x400; j += 0x10) { + if (multi && (j & 0x80)) + continue; + link->resource[0]->start = j ^ 0x300; + i = pcmcia_request_io(link); + if (i == 0) + break; } - } - - /* The address and resource configuration register aren't loaded from - the EEPROM and *must* be set to 0 and IRQ3 for the PCMCIA version. */ - outw(0x3f00, ioaddr + 8); - fifo = inl(ioaddr); - - /* The if_port symbol can be set when the module is loaded */ - if ((if_port >= 0) && (if_port <= 3)) - dev->if_port = if_port; - else - dev_err(&link->dev, "invalid if_port requested\n"); - - SET_NETDEV_DEV(dev, &link->dev); - - if (register_netdev(dev) != 0) { - dev_err(&link->dev, "register_netdev() failed\n"); - goto failed; - } - - netdev_info(dev, "3Com 3c%s, io %#3lx, irq %d, hw_addr %pM\n", - (multi ? "562" : "589"), dev->base_addr, dev->irq, - dev->dev_addr); - netdev_info(dev, " %dK FIFO split %s Rx:Tx, %s xcvr\n", - (fifo & 7) ? 32 : 8, ram_split[(fifo >> 16) & 3], - if_names[dev->if_port]); - return 0; + if (i != 0) + goto failed; + + ret = pcmcia_request_irq(link, el3_interrupt); + if (ret) + goto failed; + + ret = pcmcia_enable_device(link); + if (ret) + goto failed; + + dev->irq = link->irq; + dev->base_addr = link->resource[0]->start; + ioaddr = dev->base_addr; + EL3WINDOW(0); + + /* The 3c589 has an extra EEPROM for configuration info, including + * the hardware address. The 3c562 puts the address in the CIS. + */ + len = pcmcia_get_tuple(link, 0x88, &buf); + if (buf && len >= 6) { + for (i = 0; i < 3; i++) + phys_addr[i] = htons(le16_to_cpu(buf[i*2])); + kfree(buf); + } else { + kfree(buf); /* 0 < len < 6 */ + for (i = 0; i < 3; i++) + phys_addr[i] = htons(read_eeprom(ioaddr, i)); + if (phys_addr[0] == htons(0x6060)) { + dev_err(&link->dev, "IO port conflict at 0x%03lx-0x%03lx\n", + dev->base_addr, dev->base_addr+15); + goto failed; + } + } + + /* The address and resource configuration register aren't loaded from + * the EEPROM and *must* be set to 0 and IRQ3 for the PCMCIA version. + */ + + outw(0x3f00, ioaddr + 8); + fifo = inl(ioaddr); + + /* The if_port symbol can be set when the module is loaded */ + if ((if_port >= 0) && (if_port <= 3)) + dev->if_port = if_port; + else + dev_err(&link->dev, "invalid if_port requested\n"); + + SET_NETDEV_DEV(dev, &link->dev); + + if (register_netdev(dev) != 0) { + dev_err(&link->dev, "register_netdev() failed\n"); + goto failed; + } + + netdev_info(dev, "3Com 3c%s, io %#3lx, irq %d, hw_addr %pM\n", + (multi ? "562" : "589"), dev->base_addr, dev->irq, + dev->dev_addr); + netdev_info(dev, " %dK FIFO split %s Rx:Tx, %s xcvr\n", + (fifo & 7) ? 32 : 8, ram_split[(fifo >> 16) & 3], + if_names[dev->if_port]); + return 0; failed: - tc589_release(link); - return -ENODEV; + tc589_release(link); + return -ENODEV; } /* tc589_config */ static void tc589_release(struct pcmcia_device *link) @@ -353,113 +362,120 @@ static int tc589_resume(struct pcmcia_device *link) /*====================================================================*/ -/* - Use this for commands that may take time to finish -*/ +/* Use this for commands that may take time to finish */ + static void tc589_wait_for_completion(struct net_device *dev, int cmd) { - int i = 100; - outw(cmd, dev->base_addr + EL3_CMD); - while (--i > 0) - if (!(inw(dev->base_addr + EL3_STATUS) & 0x1000)) break; - if (i == 0) - netdev_warn(dev, "command 0x%04x did not complete!\n", cmd); + int i = 100; + outw(cmd, dev->base_addr + EL3_CMD); + while (--i > 0) + if (!(inw(dev->base_addr + EL3_STATUS) & 0x1000)) + break; + if (i == 0) + netdev_warn(dev, "command 0x%04x did not complete!\n", cmd); } -/* - Read a word from the EEPROM using the regular EEPROM access register. - Assume that we are in register window zero. -*/ +/* Read a word from the EEPROM using the regular EEPROM access register. + * Assume that we are in register window zero. + */ + static u16 read_eeprom(unsigned int ioaddr, int index) { - int i; - outw(EEPROM_READ + index, ioaddr + 10); - /* Reading the eeprom takes 162 us */ - for (i = 1620; i >= 0; i--) - if ((inw(ioaddr + 10) & EEPROM_BUSY) == 0) - break; - return inw(ioaddr + 12); + int i; + outw(EEPROM_READ + index, ioaddr + 10); + /* Reading the eeprom takes 162 us */ + for (i = 1620; i >= 0; i--) + if ((inw(ioaddr + 10) & EEPROM_BUSY) == 0) + break; + return inw(ioaddr + 12); } -/* - Set transceiver type, perhaps to something other than what the user - specified in dev->if_port. -*/ +/* Set transceiver type, perhaps to something other than what the user + * specified in dev->if_port. + */ + static void tc589_set_xcvr(struct net_device *dev, int if_port) { - struct el3_private *lp = netdev_priv(dev); - unsigned int ioaddr = dev->base_addr; - - EL3WINDOW(0); - switch (if_port) { - case 0: case 1: outw(0, ioaddr + 6); break; - case 2: outw(3<<14, ioaddr + 6); break; - case 3: outw(1<<14, ioaddr + 6); break; - } - /* On PCMCIA, this just turns on the LED */ - outw((if_port == 2) ? StartCoax : StopCoax, ioaddr + EL3_CMD); - /* 10baseT interface, enable link beat and jabber check. */ - EL3WINDOW(4); - outw(MEDIA_LED | ((if_port < 2) ? MEDIA_TP : 0), ioaddr + WN4_MEDIA); - EL3WINDOW(1); - if (if_port == 2) - lp->media_status = ((dev->if_port == 0) ? 0x8000 : 0x4000); - else - lp->media_status = ((dev->if_port == 0) ? 0x4010 : 0x8800); + struct el3_private *lp = netdev_priv(dev); + unsigned int ioaddr = dev->base_addr; + + EL3WINDOW(0); + switch (if_port) { + case 0: + case 1: + outw(0, ioaddr + 6); + break; + case 2: + outw(3<<14, ioaddr + 6); + break; + case 3: + outw(1<<14, ioaddr + 6); + break; + } + /* On PCMCIA, this just turns on the LED */ + outw((if_port == 2) ? StartCoax : StopCoax, ioaddr + EL3_CMD); + /* 10baseT interface, enable link beat and jabber check. */ + EL3WINDOW(4); + outw(MEDIA_LED | ((if_port < 2) ? MEDIA_TP : 0), ioaddr + WN4_MEDIA); + EL3WINDOW(1); + if (if_port == 2) + lp->media_status = ((dev->if_port == 0) ? 0x8000 : 0x4000); + else + lp->media_status = ((dev->if_port == 0) ? 0x4010 : 0x8800); } static void dump_status(struct net_device *dev) { - unsigned int ioaddr = dev->base_addr; - EL3WINDOW(1); - netdev_info(dev, " irq status %04x, rx status %04x, tx status %02x tx free %04x\n", - inw(ioaddr+EL3_STATUS), inw(ioaddr+RX_STATUS), - inb(ioaddr+TX_STATUS), inw(ioaddr+TX_FREE)); - EL3WINDOW(4); - netdev_info(dev, " diagnostics: fifo %04x net %04x ethernet %04x media %04x\n", - inw(ioaddr+0x04), inw(ioaddr+0x06), inw(ioaddr+0x08), - inw(ioaddr+0x0a)); - EL3WINDOW(1); + unsigned int ioaddr = dev->base_addr; + EL3WINDOW(1); + netdev_info(dev, " irq status %04x, rx status %04x, tx status %02x tx free %04x\n", + inw(ioaddr+EL3_STATUS), inw(ioaddr+RX_STATUS), + inb(ioaddr+TX_STATUS), inw(ioaddr+TX_FREE)); + EL3WINDOW(4); + netdev_info(dev, " diagnostics: fifo %04x net %04x ethernet %04x media %04x\n", + inw(ioaddr+0x04), inw(ioaddr+0x06), inw(ioaddr+0x08), + inw(ioaddr+0x0a)); + EL3WINDOW(1); } /* Reset and restore all of the 3c589 registers. */ static void tc589_reset(struct net_device *dev) { - unsigned int ioaddr = dev->base_addr; - int i; - - EL3WINDOW(0); - outw(0x0001, ioaddr + 4); /* Activate board. */ - outw(0x3f00, ioaddr + 8); /* Set the IRQ line. */ - - /* Set the station address in window 2. */ - EL3WINDOW(2); - for (i = 0; i < 6; i++) - outb(dev->dev_addr[i], ioaddr + i); - - tc589_set_xcvr(dev, dev->if_port); - - /* Switch to the stats window, and clear all stats by reading. */ - outw(StatsDisable, ioaddr + EL3_CMD); - EL3WINDOW(6); - for (i = 0; i < 9; i++) - inb(ioaddr+i); - inw(ioaddr + 10); - inw(ioaddr + 12); - - /* Switch to register set 1 for normal use. */ - EL3WINDOW(1); - - set_rx_mode(dev); - outw(StatsEnable, ioaddr + EL3_CMD); /* Turn on statistics. */ - outw(RxEnable, ioaddr + EL3_CMD); /* Enable the receiver. */ - outw(TxEnable, ioaddr + EL3_CMD); /* Enable transmitter. */ - /* Allow status bits to be seen. */ - outw(SetStatusEnb | 0xff, ioaddr + EL3_CMD); - /* Ack all pending events, and set active indicator mask. */ - outw(AckIntr | IntLatch | TxAvailable | RxEarly | IntReq, + unsigned int ioaddr = dev->base_addr; + int i; + + EL3WINDOW(0); + outw(0x0001, ioaddr + 4); /* Activate board. */ + outw(0x3f00, ioaddr + 8); /* Set the IRQ line. */ + + /* Set the station address in window 2. */ + EL3WINDOW(2); + for (i = 0; i < 6; i++) + outb(dev->dev_addr[i], ioaddr + i); + + tc589_set_xcvr(dev, dev->if_port); + + /* Switch to the stats window, and clear all stats by reading. */ + outw(StatsDisable, ioaddr + EL3_CMD); + EL3WINDOW(6); + for (i = 0; i < 9; i++) + inb(ioaddr+i); + inw(ioaddr + 10); + inw(ioaddr + 12); + + /* Switch to register set 1 for normal use. */ + EL3WINDOW(1); + + set_rx_mode(dev); + outw(StatsEnable, ioaddr + EL3_CMD); /* Turn on statistics. */ + outw(RxEnable, ioaddr + EL3_CMD); /* Enable the receiver. */ + outw(TxEnable, ioaddr + EL3_CMD); /* Enable transmitter. */ + /* Allow status bits to be seen. */ + outw(SetStatusEnb | 0xff, ioaddr + EL3_CMD); + /* Ack all pending events, and set active indicator mask. */ + outw(AckIntr | IntLatch | TxAvailable | RxEarly | IntReq, ioaddr + EL3_CMD); - outw(SetIntrEnb | IntLatch | TxAvailable | RxComplete | StatsFull + outw(SetIntrEnb | IntLatch | TxAvailable | RxComplete | StatsFull | AdapterFailure, ioaddr + EL3_CMD); } @@ -478,381 +494,406 @@ static const struct ethtool_ops netdev_ethtool_ops = { static int el3_config(struct net_device *dev, struct ifmap *map) { - if ((map->port != (u_char)(-1)) && (map->port != dev->if_port)) { - if (map->port <= 3) { - dev->if_port = map->port; - netdev_info(dev, "switched to %s port\n", if_names[dev->if_port]); - tc589_set_xcvr(dev, dev->if_port); - } else - return -EINVAL; - } - return 0; + if ((map->port != (u_char)(-1)) && (map->port != dev->if_port)) { + if (map->port <= 3) { + dev->if_port = map->port; + netdev_info(dev, "switched to %s port\n", if_names[dev->if_port]); + tc589_set_xcvr(dev, dev->if_port); + } else { + return -EINVAL; + } + } + return 0; } static int el3_open(struct net_device *dev) { - struct el3_private *lp = netdev_priv(dev); - struct pcmcia_device *link = lp->p_dev; + struct el3_private *lp = netdev_priv(dev); + struct pcmcia_device *link = lp->p_dev; - if (!pcmcia_dev_present(link)) - return -ENODEV; + if (!pcmcia_dev_present(link)) + return -ENODEV; - link->open++; - netif_start_queue(dev); + link->open++; + netif_start_queue(dev); - tc589_reset(dev); - init_timer(&lp->media); - lp->media.function = media_check; - lp->media.data = (unsigned long) dev; - lp->media.expires = jiffies + HZ; - add_timer(&lp->media); + tc589_reset(dev); + init_timer(&lp->media); + lp->media.function = media_check; + lp->media.data = (unsigned long) dev; + lp->media.expires = jiffies + HZ; + add_timer(&lp->media); - dev_dbg(&link->dev, "%s: opened, status %4.4x.\n", + dev_dbg(&link->dev, "%s: opened, status %4.4x.\n", dev->name, inw(dev->base_addr + EL3_STATUS)); - return 0; + return 0; } static void el3_tx_timeout(struct net_device *dev) { - unsigned int ioaddr = dev->base_addr; - - netdev_warn(dev, "Transmit timed out!\n"); - dump_status(dev); - dev->stats.tx_errors++; - dev->trans_start = jiffies; /* prevent tx timeout */ - /* Issue TX_RESET and TX_START commands. */ - tc589_wait_for_completion(dev, TxReset); - outw(TxEnable, ioaddr + EL3_CMD); - netif_wake_queue(dev); + unsigned int ioaddr = dev->base_addr; + + netdev_warn(dev, "Transmit timed out!\n"); + dump_status(dev); + dev->stats.tx_errors++; + dev->trans_start = jiffies; /* prevent tx timeout */ + /* Issue TX_RESET and TX_START commands. */ + tc589_wait_for_completion(dev, TxReset); + outw(TxEnable, ioaddr + EL3_CMD); + netif_wake_queue(dev); } static void pop_tx_status(struct net_device *dev) { - unsigned int ioaddr = dev->base_addr; - int i; - - /* Clear the Tx status stack. */ - for (i = 32; i > 0; i--) { - u_char tx_status = inb(ioaddr + TX_STATUS); - if (!(tx_status & 0x84)) break; - /* reset transmitter on jabber error or underrun */ - if (tx_status & 0x30) - tc589_wait_for_completion(dev, TxReset); - if (tx_status & 0x38) { - netdev_dbg(dev, "transmit error: status 0x%02x\n", tx_status); - outw(TxEnable, ioaddr + EL3_CMD); - dev->stats.tx_aborted_errors++; + unsigned int ioaddr = dev->base_addr; + int i; + + /* Clear the Tx status stack. */ + for (i = 32; i > 0; i--) { + u_char tx_status = inb(ioaddr + TX_STATUS); + if (!(tx_status & 0x84)) + break; + /* reset transmitter on jabber error or underrun */ + if (tx_status & 0x30) + tc589_wait_for_completion(dev, TxReset); + if (tx_status & 0x38) { + netdev_dbg(dev, "transmit error: status 0x%02x\n", tx_status); + outw(TxEnable, ioaddr + EL3_CMD); + dev->stats.tx_aborted_errors++; + } + outb(0x00, ioaddr + TX_STATUS); /* Pop the status stack. */ } - outb(0x00, ioaddr + TX_STATUS); /* Pop the status stack. */ - } } static netdev_tx_t el3_start_xmit(struct sk_buff *skb, struct net_device *dev) { - unsigned int ioaddr = dev->base_addr; - struct el3_private *priv = netdev_priv(dev); - unsigned long flags; + unsigned int ioaddr = dev->base_addr; + struct el3_private *priv = netdev_priv(dev); + unsigned long flags; - netdev_dbg(dev, "el3_start_xmit(length = %ld) called, status %4.4x.\n", + netdev_dbg(dev, "el3_start_xmit(length = %ld) called, status %4.4x.\n", (long)skb->len, inw(ioaddr + EL3_STATUS)); - spin_lock_irqsave(&priv->lock, flags); + spin_lock_irqsave(&priv->lock, flags); - dev->stats.tx_bytes += skb->len; + dev->stats.tx_bytes += skb->len; - /* Put out the doubleword header... */ - outw(skb->len, ioaddr + TX_FIFO); - outw(0x00, ioaddr + TX_FIFO); - /* ... and the packet rounded to a doubleword. */ - outsl(ioaddr + TX_FIFO, skb->data, (skb->len + 3) >> 2); + /* Put out the doubleword header... */ + outw(skb->len, ioaddr + TX_FIFO); + outw(0x00, ioaddr + TX_FIFO); + /* ... and the packet rounded to a doubleword. */ + outsl(ioaddr + TX_FIFO, skb->data, (skb->len + 3) >> 2); - if (inw(ioaddr + TX_FREE) <= 1536) { - netif_stop_queue(dev); - /* Interrupt us when the FIFO has room for max-sized packet. */ - outw(SetTxThreshold + 1536, ioaddr + EL3_CMD); - } + if (inw(ioaddr + TX_FREE) <= 1536) { + netif_stop_queue(dev); + /* Interrupt us when the FIFO has room for max-sized packet. */ + outw(SetTxThreshold + 1536, ioaddr + EL3_CMD); + } - pop_tx_status(dev); - spin_unlock_irqrestore(&priv->lock, flags); - dev_kfree_skb(skb); + pop_tx_status(dev); + spin_unlock_irqrestore(&priv->lock, flags); + dev_kfree_skb(skb); - return NETDEV_TX_OK; + return NETDEV_TX_OK; } /* The EL3 interrupt handler. */ static irqreturn_t el3_interrupt(int irq, void *dev_id) { - struct net_device *dev = (struct net_device *) dev_id; - struct el3_private *lp = netdev_priv(dev); - unsigned int ioaddr; - __u16 status; - int i = 0, handled = 1; + struct net_device *dev = (struct net_device *) dev_id; + struct el3_private *lp = netdev_priv(dev); + unsigned int ioaddr; + __u16 status; + int i = 0, handled = 1; - if (!netif_device_present(dev)) - return IRQ_NONE; + if (!netif_device_present(dev)) + return IRQ_NONE; - ioaddr = dev->base_addr; + ioaddr = dev->base_addr; - netdev_dbg(dev, "interrupt, status %4.4x.\n", inw(ioaddr + EL3_STATUS)); + netdev_dbg(dev, "interrupt, status %4.4x.\n", inw(ioaddr + EL3_STATUS)); - spin_lock(&lp->lock); - while ((status = inw(ioaddr + EL3_STATUS)) & + spin_lock(&lp->lock); + while ((status = inw(ioaddr + EL3_STATUS)) & (IntLatch | RxComplete | StatsFull)) { - if ((status & 0xe000) != 0x2000) { - netdev_dbg(dev, "interrupt from dead card\n"); - handled = 0; - break; - } - if (status & RxComplete) - el3_rx(dev); - if (status & TxAvailable) { - netdev_dbg(dev, " TX room bit was handled.\n"); - /* There's room in the FIFO for a full-sized packet. */ - outw(AckIntr | TxAvailable, ioaddr + EL3_CMD); - netif_wake_queue(dev); - } - if (status & TxComplete) - pop_tx_status(dev); - if (status & (AdapterFailure | RxEarly | StatsFull)) { - /* Handle all uncommon interrupts. */ - if (status & StatsFull) /* Empty statistics. */ - update_stats(dev); - if (status & RxEarly) { /* Rx early is unused. */ - el3_rx(dev); - outw(AckIntr | RxEarly, ioaddr + EL3_CMD); - } - if (status & AdapterFailure) { - u16 fifo_diag; - EL3WINDOW(4); - fifo_diag = inw(ioaddr + 4); - EL3WINDOW(1); - netdev_warn(dev, "adapter failure, FIFO diagnostic register %04x.\n", + if ((status & 0xe000) != 0x2000) { + netdev_dbg(dev, "interrupt from dead card\n"); + handled = 0; + break; + } + if (status & RxComplete) + el3_rx(dev); + if (status & TxAvailable) { + netdev_dbg(dev, " TX room bit was handled.\n"); + /* There's room in the FIFO for a full-sized packet. */ + outw(AckIntr | TxAvailable, ioaddr + EL3_CMD); + netif_wake_queue(dev); + } + if (status & TxComplete) + pop_tx_status(dev); + if (status & (AdapterFailure | RxEarly | StatsFull)) { + /* Handle all uncommon interrupts. */ + if (status & StatsFull) /* Empty statistics. */ + update_stats(dev); + if (status & RxEarly) { + /* Rx early is unused. */ + el3_rx(dev); + outw(AckIntr | RxEarly, ioaddr + EL3_CMD); + } + if (status & AdapterFailure) { + u16 fifo_diag; + EL3WINDOW(4); + fifo_diag = inw(ioaddr + 4); + EL3WINDOW(1); + netdev_warn(dev, "adapter failure, FIFO diagnostic register %04x.\n", fifo_diag); - if (fifo_diag & 0x0400) { - /* Tx overrun */ - tc589_wait_for_completion(dev, TxReset); - outw(TxEnable, ioaddr + EL3_CMD); + if (fifo_diag & 0x0400) { + /* Tx overrun */ + tc589_wait_for_completion(dev, TxReset); + outw(TxEnable, ioaddr + EL3_CMD); + } + if (fifo_diag & 0x2000) { + /* Rx underrun */ + tc589_wait_for_completion(dev, RxReset); + set_rx_mode(dev); + outw(RxEnable, ioaddr + EL3_CMD); + } + outw(AckIntr | AdapterFailure, ioaddr + EL3_CMD); + } } - if (fifo_diag & 0x2000) { - /* Rx underrun */ - tc589_wait_for_completion(dev, RxReset); - set_rx_mode(dev); - outw(RxEnable, ioaddr + EL3_CMD); + if (++i > 10) { + netdev_err(dev, "infinite loop in interrupt, status %4.4x.\n", + status); + /* Clear all interrupts */ + outw(AckIntr | 0xFF, ioaddr + EL3_CMD); + break; } - outw(AckIntr | AdapterFailure, ioaddr + EL3_CMD); - } + /* Acknowledge the IRQ. */ + outw(AckIntr | IntReq | IntLatch, ioaddr + EL3_CMD); } - if (++i > 10) { - netdev_err(dev, "infinite loop in interrupt, status %4.4x.\n", - status); - /* Clear all interrupts */ - outw(AckIntr | 0xFF, ioaddr + EL3_CMD); - break; - } - /* Acknowledge the IRQ. */ - outw(AckIntr | IntReq | IntLatch, ioaddr + EL3_CMD); - } - lp->last_irq = jiffies; - spin_unlock(&lp->lock); - netdev_dbg(dev, "exiting interrupt, status %4.4x.\n", - inw(ioaddr + EL3_STATUS)); - return IRQ_RETVAL(handled); + lp->last_irq = jiffies; + spin_unlock(&lp->lock); + netdev_dbg(dev, "exiting interrupt, status %4.4x.\n", + inw(ioaddr + EL3_STATUS)); + return IRQ_RETVAL(handled); } static void media_check(unsigned long arg) { - struct net_device *dev = (struct net_device *)(arg); - struct el3_private *lp = netdev_priv(dev); - unsigned int ioaddr = dev->base_addr; - u16 media, errs; - unsigned long flags; + struct net_device *dev = (struct net_device *)(arg); + struct el3_private *lp = netdev_priv(dev); + unsigned int ioaddr = dev->base_addr; + u16 media, errs; + unsigned long flags; - if (!netif_device_present(dev)) goto reschedule; + if (!netif_device_present(dev)) + goto reschedule; - /* Check for pending interrupt with expired latency timer: with - this, we can limp along even if the interrupt is blocked */ - if ((inw(ioaddr + EL3_STATUS) & IntLatch) && + /* Check for pending interrupt with expired latency timer: with + * this, we can limp along even if the interrupt is blocked + */ + if ((inw(ioaddr + EL3_STATUS) & IntLatch) && (inb(ioaddr + EL3_TIMER) == 0xff)) { - if (!lp->fast_poll) - netdev_warn(dev, "interrupt(s) dropped!\n"); - - local_irq_save(flags); - el3_interrupt(dev->irq, dev); - local_irq_restore(flags); - - lp->fast_poll = HZ; - } - if (lp->fast_poll) { - lp->fast_poll--; - lp->media.expires = jiffies + HZ/100; - add_timer(&lp->media); - return; - } - - /* lp->lock guards the EL3 window. Window should always be 1 except - when the lock is held */ - spin_lock_irqsave(&lp->lock, flags); - EL3WINDOW(4); - media = inw(ioaddr+WN4_MEDIA) & 0xc810; - - /* Ignore collisions unless we've had no irq's recently */ - if (time_before(jiffies, lp->last_irq + HZ)) { - media &= ~0x0010; - } else { - /* Try harder to detect carrier errors */ - EL3WINDOW(6); - outw(StatsDisable, ioaddr + EL3_CMD); - errs = inb(ioaddr + 0); - outw(StatsEnable, ioaddr + EL3_CMD); - dev->stats.tx_carrier_errors += errs; - if (errs || (lp->media_status & 0x0010)) media |= 0x0010; - } + if (!lp->fast_poll) + netdev_warn(dev, "interrupt(s) dropped!\n"); + + local_irq_save(flags); + el3_interrupt(dev->irq, dev); + local_irq_restore(flags); + + lp->fast_poll = HZ; + } + if (lp->fast_poll) { + lp->fast_poll--; + lp->media.expires = jiffies + HZ/100; + add_timer(&lp->media); + return; + } + + /* lp->lock guards the EL3 window. Window should always be 1 except + * when the lock is held + */ + + spin_lock_irqsave(&lp->lock, flags); + EL3WINDOW(4); + media = inw(ioaddr+WN4_MEDIA) & 0xc810; + + /* Ignore collisions unless we've had no irq's recently */ + if (time_before(jiffies, lp->last_irq + HZ)) { + media &= ~0x0010; + } else { + /* Try harder to detect carrier errors */ + EL3WINDOW(6); + outw(StatsDisable, ioaddr + EL3_CMD); + errs = inb(ioaddr + 0); + outw(StatsEnable, ioaddr + EL3_CMD); + dev->stats.tx_carrier_errors += errs; + if (errs || (lp->media_status & 0x0010)) + media |= 0x0010; + } - if (media != lp->media_status) { - if ((media & lp->media_status & 0x8000) && - ((lp->media_status ^ media) & 0x0800)) + if (media != lp->media_status) { + if ((media & lp->media_status & 0x8000) && + ((lp->media_status ^ media) & 0x0800)) netdev_info(dev, "%s link beat\n", - (lp->media_status & 0x0800 ? "lost" : "found")); - else if ((media & lp->media_status & 0x4000) && + (lp->media_status & 0x0800 ? "lost" : "found")); + else if ((media & lp->media_status & 0x4000) && ((lp->media_status ^ media) & 0x0010)) netdev_info(dev, "coax cable %s\n", - (lp->media_status & 0x0010 ? "ok" : "problem")); - if (dev->if_port == 0) { - if (media & 0x8000) { - if (media & 0x0800) - netdev_info(dev, "flipped to 10baseT\n"); - else + (lp->media_status & 0x0010 ? "ok" : "problem")); + if (dev->if_port == 0) { + if (media & 0x8000) { + if (media & 0x0800) + netdev_info(dev, "flipped to 10baseT\n"); + else tc589_set_xcvr(dev, 2); - } else if (media & 0x4000) { - if (media & 0x0010) - tc589_set_xcvr(dev, 1); - else - netdev_info(dev, "flipped to 10base2\n"); - } + } else if (media & 0x4000) { + if (media & 0x0010) + tc589_set_xcvr(dev, 1); + else + netdev_info(dev, "flipped to 10base2\n"); + } + } + lp->media_status = media; } - lp->media_status = media; - } - EL3WINDOW(1); - spin_unlock_irqrestore(&lp->lock, flags); + EL3WINDOW(1); + spin_unlock_irqrestore(&lp->lock, flags); reschedule: - lp->media.expires = jiffies + HZ; - add_timer(&lp->media); + lp->media.expires = jiffies + HZ; + add_timer(&lp->media); } static struct net_device_stats *el3_get_stats(struct net_device *dev) { - struct el3_private *lp = netdev_priv(dev); - unsigned long flags; - struct pcmcia_device *link = lp->p_dev; + struct el3_private *lp = netdev_priv(dev); + unsigned long flags; + struct pcmcia_device *link = lp->p_dev; - if (pcmcia_dev_present(link)) { - spin_lock_irqsave(&lp->lock, flags); - update_stats(dev); - spin_unlock_irqrestore(&lp->lock, flags); - } - return &dev->stats; + if (pcmcia_dev_present(link)) { + spin_lock_irqsave(&lp->lock, flags); + update_stats(dev); + spin_unlock_irqrestore(&lp->lock, flags); + } + return &dev->stats; } -/* - Update statistics. We change to register window 6, so this should be run - single-threaded if the device is active. This is expected to be a rare - operation, and it's simpler for the rest of the driver to assume that - window 1 is always valid rather than use a special window-state variable. - - Caller must hold the lock for this +/* Update statistics. We change to register window 6, so this should be run +* single-threaded if the device is active. This is expected to be a rare +* operation, and it's simpler for the rest of the driver to assume that +* window 1 is always valid rather than use a special window-state variable. +* +* Caller must hold the lock for this */ + static void update_stats(struct net_device *dev) { - unsigned int ioaddr = dev->base_addr; - - netdev_dbg(dev, "updating the statistics.\n"); - /* Turn off statistics updates while reading. */ - outw(StatsDisable, ioaddr + EL3_CMD); - /* Switch to the stats window, and read everything. */ - EL3WINDOW(6); - dev->stats.tx_carrier_errors += inb(ioaddr + 0); - dev->stats.tx_heartbeat_errors += inb(ioaddr + 1); - /* Multiple collisions. */ inb(ioaddr + 2); - dev->stats.collisions += inb(ioaddr + 3); - dev->stats.tx_window_errors += inb(ioaddr + 4); - dev->stats.rx_fifo_errors += inb(ioaddr + 5); - dev->stats.tx_packets += inb(ioaddr + 6); - /* Rx packets */ inb(ioaddr + 7); - /* Tx deferrals */ inb(ioaddr + 8); - /* Rx octets */ inw(ioaddr + 10); - /* Tx octets */ inw(ioaddr + 12); - - /* Back to window 1, and turn statistics back on. */ - EL3WINDOW(1); - outw(StatsEnable, ioaddr + EL3_CMD); + unsigned int ioaddr = dev->base_addr; + + netdev_dbg(dev, "updating the statistics.\n"); + /* Turn off statistics updates while reading. */ + outw(StatsDisable, ioaddr + EL3_CMD); + /* Switch to the stats window, and read everything. */ + EL3WINDOW(6); + dev->stats.tx_carrier_errors += inb(ioaddr + 0); + dev->stats.tx_heartbeat_errors += inb(ioaddr + 1); + /* Multiple collisions. */ + inb(ioaddr + 2); + dev->stats.collisions += inb(ioaddr + 3); + dev->stats.tx_window_errors += inb(ioaddr + 4); + dev->stats.rx_fifo_errors += inb(ioaddr + 5); + dev->stats.tx_packets += inb(ioaddr + 6); + /* Rx packets */ + inb(ioaddr + 7); + /* Tx deferrals */ + inb(ioaddr + 8); + /* Rx octets */ + inw(ioaddr + 10); + /* Tx octets */ + inw(ioaddr + 12); + + /* Back to window 1, and turn statistics back on. */ + EL3WINDOW(1); + outw(StatsEnable, ioaddr + EL3_CMD); } static int el3_rx(struct net_device *dev) { - unsigned int ioaddr = dev->base_addr; - int worklimit = 32; - short rx_status; + unsigned int ioaddr = dev->base_addr; + int worklimit = 32; + short rx_status; - netdev_dbg(dev, "in rx_packet(), status %4.4x, rx_status %4.4x.\n", + netdev_dbg(dev, "in rx_packet(), status %4.4x, rx_status %4.4x.\n", inw(ioaddr+EL3_STATUS), inw(ioaddr+RX_STATUS)); - while (!((rx_status = inw(ioaddr + RX_STATUS)) & 0x8000) && + while (!((rx_status = inw(ioaddr + RX_STATUS)) & 0x8000) && worklimit > 0) { - worklimit--; - if (rx_status & 0x4000) { /* Error, update stats. */ - short error = rx_status & 0x3800; - dev->stats.rx_errors++; - switch (error) { - case 0x0000: dev->stats.rx_over_errors++; break; - case 0x0800: dev->stats.rx_length_errors++; break; - case 0x1000: dev->stats.rx_frame_errors++; break; - case 0x1800: dev->stats.rx_length_errors++; break; - case 0x2000: dev->stats.rx_frame_errors++; break; - case 0x2800: dev->stats.rx_crc_errors++; break; - } - } else { - short pkt_len = rx_status & 0x7ff; - struct sk_buff *skb; - - skb = netdev_alloc_skb(dev, pkt_len + 5); - - netdev_dbg(dev, " Receiving packet size %d status %4.4x.\n", + worklimit--; + if (rx_status & 0x4000) { /* Error, update stats. */ + short error = rx_status & 0x3800; + dev->stats.rx_errors++; + switch (error) { + case 0x0000: + dev->stats.rx_over_errors++; + break; + case 0x0800: + dev->stats.rx_length_errors++; + break; + case 0x1000: + dev->stats.rx_frame_errors++; + break; + case 0x1800: + dev->stats.rx_length_errors++; + break; + case 0x2000: + dev->stats.rx_frame_errors++; + break; + case 0x2800: + dev->stats.rx_crc_errors++; + break; + } + } else { + short pkt_len = rx_status & 0x7ff; + struct sk_buff *skb; + + skb = netdev_alloc_skb(dev, pkt_len + 5); + + netdev_dbg(dev, " Receiving packet size %d status %4.4x.\n", pkt_len, rx_status); - if (skb != NULL) { - skb_reserve(skb, 2); - insl(ioaddr+RX_FIFO, skb_put(skb, pkt_len), + if (skb != NULL) { + skb_reserve(skb, 2); + insl(ioaddr+RX_FIFO, skb_put(skb, pkt_len), (pkt_len+3)>>2); - skb->protocol = eth_type_trans(skb, dev); - netif_rx(skb); - dev->stats.rx_packets++; - dev->stats.rx_bytes += pkt_len; - } else { - netdev_dbg(dev, "couldn't allocate a sk_buff of size %d.\n", + skb->protocol = eth_type_trans(skb, dev); + netif_rx(skb); + dev->stats.rx_packets++; + dev->stats.rx_bytes += pkt_len; + } else { + netdev_dbg(dev, "couldn't allocate a sk_buff of size %d.\n", pkt_len); - dev->stats.rx_dropped++; - } + dev->stats.rx_dropped++; + } + } + /* Pop the top of the Rx FIFO */ + tc589_wait_for_completion(dev, RxDiscard); } - /* Pop the top of the Rx FIFO */ - tc589_wait_for_completion(dev, RxDiscard); - } - if (worklimit == 0) - netdev_warn(dev, "too much work in el3_rx!\n"); - return 0; + if (worklimit == 0) + netdev_warn(dev, "too much work in el3_rx!\n"); + return 0; } static void set_rx_mode(struct net_device *dev) { - unsigned int ioaddr = dev->base_addr; - u16 opts = SetRxFilter | RxStation | RxBroadcast; - - if (dev->flags & IFF_PROMISC) - opts |= RxMulticast | RxProm; - else if (!netdev_mc_empty(dev) || (dev->flags & IFF_ALLMULTI)) - opts |= RxMulticast; - outw(opts, ioaddr + EL3_CMD); + unsigned int ioaddr = dev->base_addr; + u16 opts = SetRxFilter | RxStation | RxBroadcast; + + if (dev->flags & IFF_PROMISC) + opts |= RxMulticast | RxProm; + else if (!netdev_mc_empty(dev) || (dev->flags & IFF_ALLMULTI)) + opts |= RxMulticast; + outw(opts, ioaddr + EL3_CMD); } static void set_multicast_list(struct net_device *dev) @@ -867,44 +908,44 @@ static void set_multicast_list(struct net_device *dev) static int el3_close(struct net_device *dev) { - struct el3_private *lp = netdev_priv(dev); - struct pcmcia_device *link = lp->p_dev; - unsigned int ioaddr = dev->base_addr; - - dev_dbg(&link->dev, "%s: shutting down ethercard.\n", dev->name); + struct el3_private *lp = netdev_priv(dev); + struct pcmcia_device *link = lp->p_dev; + unsigned int ioaddr = dev->base_addr; + + dev_dbg(&link->dev, "%s: shutting down ethercard.\n", dev->name); + + if (pcmcia_dev_present(link)) { + /* Turn off statistics ASAP. We update dev->stats below. */ + outw(StatsDisable, ioaddr + EL3_CMD); + + /* Disable the receiver and transmitter. */ + outw(RxDisable, ioaddr + EL3_CMD); + outw(TxDisable, ioaddr + EL3_CMD); + + if (dev->if_port == 2) + /* Turn off thinnet power. Green! */ + outw(StopCoax, ioaddr + EL3_CMD); + else if (dev->if_port == 1) { + /* Disable link beat and jabber */ + EL3WINDOW(4); + outw(0, ioaddr + WN4_MEDIA); + } - if (pcmcia_dev_present(link)) { - /* Turn off statistics ASAP. We update dev->stats below. */ - outw(StatsDisable, ioaddr + EL3_CMD); + /* Switching back to window 0 disables the IRQ. */ + EL3WINDOW(0); + /* But we explicitly zero the IRQ line select anyway. */ + outw(0x0f00, ioaddr + WN0_IRQ); - /* Disable the receiver and transmitter. */ - outw(RxDisable, ioaddr + EL3_CMD); - outw(TxDisable, ioaddr + EL3_CMD); - - if (dev->if_port == 2) - /* Turn off thinnet power. Green! */ - outw(StopCoax, ioaddr + EL3_CMD); - else if (dev->if_port == 1) { - /* Disable link beat and jabber */ - EL3WINDOW(4); - outw(0, ioaddr + WN4_MEDIA); + /* Check if the card still exists */ + if ((inw(ioaddr+EL3_STATUS) & 0xe000) == 0x2000) + update_stats(dev); } - /* Switching back to window 0 disables the IRQ. */ - EL3WINDOW(0); - /* But we explicitly zero the IRQ line select anyway. */ - outw(0x0f00, ioaddr + WN0_IRQ); - - /* Check if the card still exists */ - if ((inw(ioaddr+EL3_STATUS) & 0xe000) == 0x2000) - update_stats(dev); - } - - link->open--; - netif_stop_queue(dev); - del_timer_sync(&lp->media); + link->open--; + netif_stop_queue(dev); + del_timer_sync(&lp->media); - return 0; + return 0; } static const struct pcmcia_device_id tc589_ids[] = { diff --git a/drivers/net/ethernet/3com/3c59x.c b/drivers/net/ethernet/3com/3c59x.c index 0f4241c6e97e..238ccea965c8 100644 --- a/drivers/net/ethernet/3com/3c59x.c +++ b/drivers/net/ethernet/3com/3c59x.c @@ -3294,7 +3294,6 @@ static int __init vortex_init(void) static void __exit vortex_eisa_cleanup(void) { - struct vortex_private *vp; void __iomem *ioaddr; #ifdef CONFIG_EISA @@ -3303,7 +3302,6 @@ static void __exit vortex_eisa_cleanup(void) #endif if (compaq_net_device) { - vp = netdev_priv(compaq_net_device); ioaddr = ioport_map(compaq_net_device->base_addr, VORTEX_TOTAL_SIZE); diff --git a/drivers/net/ethernet/allwinner/sun4i-emac.c b/drivers/net/ethernet/allwinner/sun4i-emac.c index 0cc21437478c..511f6eecd58b 100644 --- a/drivers/net/ethernet/allwinner/sun4i-emac.c +++ b/drivers/net/ethernet/allwinner/sun4i-emac.c @@ -929,6 +929,9 @@ static int emac_resume(struct platform_device *dev) } static const struct of_device_id emac_of_match[] = { + {.compatible = "allwinner,sun4i-a10-emac",}, + + /* Deprecated */ {.compatible = "allwinner,sun4i-emac",}, {}, }; diff --git a/drivers/net/ethernet/amd/pcnet32.c b/drivers/net/ethernet/amd/pcnet32.c index 9339cccfe05a..2ae00ed83afa 100644 --- a/drivers/net/ethernet/amd/pcnet32.c +++ b/drivers/net/ethernet/amd/pcnet32.c @@ -549,35 +549,35 @@ static void pcnet32_realloc_rx_ring(struct net_device *dev, struct pcnet32_rx_head *new_rx_ring; struct sk_buff **new_skb_list; int new, overlap; + unsigned int entries = 1 << size; new_rx_ring = pci_alloc_consistent(lp->pci_dev, sizeof(struct pcnet32_rx_head) * - (1 << size), + entries, &new_ring_dma_addr); if (new_rx_ring == NULL) { netif_err(lp, drv, dev, "Consistent memory allocation failed\n"); return; } - memset(new_rx_ring, 0, sizeof(struct pcnet32_rx_head) * (1 << size)); + memset(new_rx_ring, 0, sizeof(struct pcnet32_rx_head) * entries); - new_dma_addr_list = kcalloc(1 << size, sizeof(dma_addr_t), GFP_ATOMIC); + new_dma_addr_list = kcalloc(entries, sizeof(dma_addr_t), GFP_ATOMIC); if (!new_dma_addr_list) goto free_new_rx_ring; - new_skb_list = kcalloc(1 << size, sizeof(struct sk_buff *), - GFP_ATOMIC); + new_skb_list = kcalloc(entries, sizeof(struct sk_buff *), GFP_ATOMIC); if (!new_skb_list) goto free_new_lists; /* first copy the current receive buffers */ - overlap = min(size, lp->rx_ring_size); + overlap = min(entries, lp->rx_ring_size); for (new = 0; new < overlap; new++) { new_rx_ring[new] = lp->rx_ring[new]; new_dma_addr_list[new] = lp->rx_dma_addr[new]; new_skb_list[new] = lp->rx_skbuff[new]; } /* now allocate any new buffers needed */ - for (; new < size; new++) { + for (; new < entries; new++) { struct sk_buff *rx_skbuff; new_skb_list[new] = netdev_alloc_skb(dev, PKT_BUF_SKB); rx_skbuff = new_skb_list[new]; @@ -592,6 +592,13 @@ static void pcnet32_realloc_rx_ring(struct net_device *dev, new_dma_addr_list[new] = pci_map_single(lp->pci_dev, rx_skbuff->data, PKT_BUF_SIZE, PCI_DMA_FROMDEVICE); + if (pci_dma_mapping_error(lp->pci_dev, + new_dma_addr_list[new])) { + netif_err(lp, drv, dev, "%s dma mapping failed\n", + __func__); + dev_kfree_skb(new_skb_list[new]); + goto free_all_new; + } new_rx_ring[new].base = cpu_to_le32(new_dma_addr_list[new]); new_rx_ring[new].buf_length = cpu_to_le16(NEG_BUF_SIZE); new_rx_ring[new].status = cpu_to_le16(0x8000); @@ -599,8 +606,12 @@ static void pcnet32_realloc_rx_ring(struct net_device *dev, /* and free any unneeded buffers */ for (; new < lp->rx_ring_size; new++) { if (lp->rx_skbuff[new]) { - pci_unmap_single(lp->pci_dev, lp->rx_dma_addr[new], - PKT_BUF_SIZE, PCI_DMA_FROMDEVICE); + if (!pci_dma_mapping_error(lp->pci_dev, + lp->rx_dma_addr[new])) + pci_unmap_single(lp->pci_dev, + lp->rx_dma_addr[new], + PKT_BUF_SIZE, + PCI_DMA_FROMDEVICE); dev_kfree_skb(lp->rx_skbuff[new]); } } @@ -612,7 +623,7 @@ static void pcnet32_realloc_rx_ring(struct net_device *dev, lp->rx_ring_size, lp->rx_ring, lp->rx_ring_dma_addr); - lp->rx_ring_size = (1 << size); + lp->rx_ring_size = entries; lp->rx_mod_mask = lp->rx_ring_size - 1; lp->rx_len_bits = (size << 4); lp->rx_ring = new_rx_ring; @@ -624,8 +635,12 @@ static void pcnet32_realloc_rx_ring(struct net_device *dev, free_all_new: while (--new >= lp->rx_ring_size) { if (new_skb_list[new]) { - pci_unmap_single(lp->pci_dev, new_dma_addr_list[new], - PKT_BUF_SIZE, PCI_DMA_FROMDEVICE); + if (!pci_dma_mapping_error(lp->pci_dev, + new_dma_addr_list[new])) + pci_unmap_single(lp->pci_dev, + new_dma_addr_list[new], + PKT_BUF_SIZE, + PCI_DMA_FROMDEVICE); dev_kfree_skb(new_skb_list[new]); } } @@ -634,8 +649,7 @@ free_new_lists: kfree(new_dma_addr_list); free_new_rx_ring: pci_free_consistent(lp->pci_dev, - sizeof(struct pcnet32_rx_head) * - (1 << size), + sizeof(struct pcnet32_rx_head) * entries, new_rx_ring, new_ring_dma_addr); } @@ -650,8 +664,12 @@ static void pcnet32_purge_rx_ring(struct net_device *dev) lp->rx_ring[i].status = 0; /* CPU owns buffer */ wmb(); /* Make sure adapter sees owner change */ if (lp->rx_skbuff[i]) { - pci_unmap_single(lp->pci_dev, lp->rx_dma_addr[i], - PKT_BUF_SIZE, PCI_DMA_FROMDEVICE); + if (!pci_dma_mapping_error(lp->pci_dev, + lp->rx_dma_addr[i])) + pci_unmap_single(lp->pci_dev, + lp->rx_dma_addr[i], + PKT_BUF_SIZE, + PCI_DMA_FROMDEVICE); dev_kfree_skb_any(lp->rx_skbuff[i]); } lp->rx_skbuff[i] = NULL; @@ -930,6 +948,12 @@ static int pcnet32_loopback_test(struct net_device *dev, uint64_t * data1) lp->tx_dma_addr[x] = pci_map_single(lp->pci_dev, skb->data, skb->len, PCI_DMA_TODEVICE); + if (pci_dma_mapping_error(lp->pci_dev, lp->tx_dma_addr[x])) { + netif_printk(lp, hw, KERN_DEBUG, dev, + "DMA mapping error at line: %d!\n", + __LINE__); + goto clean_up; + } lp->tx_ring[x].base = cpu_to_le32(lp->tx_dma_addr[x]); wmb(); /* Make sure owner changes after all others are visible */ lp->tx_ring[x].status = cpu_to_le16(status); @@ -1142,24 +1166,36 @@ static void pcnet32_rx_entry(struct net_device *dev, if (pkt_len > rx_copybreak) { struct sk_buff *newskb; + dma_addr_t new_dma_addr; newskb = netdev_alloc_skb(dev, PKT_BUF_SKB); + /* + * map the new buffer, if mapping fails, drop the packet and + * reuse the old buffer + */ if (newskb) { skb_reserve(newskb, NET_IP_ALIGN); - skb = lp->rx_skbuff[entry]; - pci_unmap_single(lp->pci_dev, - lp->rx_dma_addr[entry], - PKT_BUF_SIZE, - PCI_DMA_FROMDEVICE); - skb_put(skb, pkt_len); - lp->rx_skbuff[entry] = newskb; - lp->rx_dma_addr[entry] = - pci_map_single(lp->pci_dev, - newskb->data, - PKT_BUF_SIZE, - PCI_DMA_FROMDEVICE); - rxp->base = cpu_to_le32(lp->rx_dma_addr[entry]); - rx_in_place = 1; + new_dma_addr = pci_map_single(lp->pci_dev, + newskb->data, + PKT_BUF_SIZE, + PCI_DMA_FROMDEVICE); + if (pci_dma_mapping_error(lp->pci_dev, new_dma_addr)) { + netif_err(lp, rx_err, dev, + "DMA mapping error.\n"); + dev_kfree_skb(newskb); + skb = NULL; + } else { + skb = lp->rx_skbuff[entry]; + pci_unmap_single(lp->pci_dev, + lp->rx_dma_addr[entry], + PKT_BUF_SIZE, + PCI_DMA_FROMDEVICE); + skb_put(skb, pkt_len); + lp->rx_skbuff[entry] = newskb; + lp->rx_dma_addr[entry] = new_dma_addr; + rxp->base = cpu_to_le32(new_dma_addr); + rx_in_place = 1; + } } else skb = NULL; } else @@ -2229,9 +2265,12 @@ static void pcnet32_purge_tx_ring(struct net_device *dev) lp->tx_ring[i].status = 0; /* CPU owns buffer */ wmb(); /* Make sure adapter sees owner change */ if (lp->tx_skbuff[i]) { - pci_unmap_single(lp->pci_dev, lp->tx_dma_addr[i], - lp->tx_skbuff[i]->len, - PCI_DMA_TODEVICE); + if (!pci_dma_mapping_error(lp->pci_dev, + lp->tx_dma_addr[i])) + pci_unmap_single(lp->pci_dev, + lp->tx_dma_addr[i], + lp->tx_skbuff[i]->len, + PCI_DMA_TODEVICE); dev_kfree_skb_any(lp->tx_skbuff[i]); } lp->tx_skbuff[i] = NULL; @@ -2264,10 +2303,19 @@ static int pcnet32_init_ring(struct net_device *dev) } rmb(); - if (lp->rx_dma_addr[i] == 0) + if (lp->rx_dma_addr[i] == 0) { lp->rx_dma_addr[i] = pci_map_single(lp->pci_dev, rx_skbuff->data, PKT_BUF_SIZE, PCI_DMA_FROMDEVICE); + if (pci_dma_mapping_error(lp->pci_dev, + lp->rx_dma_addr[i])) { + /* there is not much we can do at this point */ + netif_err(lp, drv, dev, + "%s pci dma mapping error\n", + __func__); + return -1; + } + } lp->rx_ring[i].base = cpu_to_le32(lp->rx_dma_addr[i]); lp->rx_ring[i].buf_length = cpu_to_le16(NEG_BUF_SIZE); wmb(); /* Make sure owner changes after all others are visible */ @@ -2397,9 +2445,14 @@ static netdev_tx_t pcnet32_start_xmit(struct sk_buff *skb, lp->tx_ring[entry].misc = 0x00000000; - lp->tx_skbuff[entry] = skb; lp->tx_dma_addr[entry] = pci_map_single(lp->pci_dev, skb->data, skb->len, PCI_DMA_TODEVICE); + if (pci_dma_mapping_error(lp->pci_dev, lp->tx_dma_addr[entry])) { + dev_kfree_skb(skb); + dev->stats.tx_dropped++; + goto drop_packet; + } + lp->tx_skbuff[entry] = skb; lp->tx_ring[entry].base = cpu_to_le32(lp->tx_dma_addr[entry]); wmb(); /* Make sure owner changes after all others are visible */ lp->tx_ring[entry].status = cpu_to_le16(status); @@ -2414,6 +2467,7 @@ static netdev_tx_t pcnet32_start_xmit(struct sk_buff *skb, lp->tx_full = 1; netif_stop_queue(dev); } +drop_packet: spin_unlock_irqrestore(&lp->lock, flags); return NETDEV_TX_OK; } diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c index e92ffd6e1c15..2e45f6ec1bf0 100644 --- a/drivers/net/ethernet/atheros/alx/main.c +++ b/drivers/net/ethernet/atheros/alx/main.c @@ -1292,6 +1292,7 @@ static int alx_probe(struct pci_dev *pdev, const struct pci_device_id *ent) alx = netdev_priv(netdev); spin_lock_init(&alx->hw.mdio_lock); spin_lock_init(&alx->irq_lock); + spin_lock_init(&alx->stats_lock); alx->dev = netdev; alx->hw.pdev = pdev; alx->msg_enable = NETIF_MSG_LINK | NETIF_MSG_HW | NETIF_MSG_IFUP | diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig index 3f97d9fd0a71..85dbddd03722 100644 --- a/drivers/net/ethernet/broadcom/Kconfig +++ b/drivers/net/ethernet/broadcom/Kconfig @@ -60,6 +60,17 @@ config BCM63XX_ENET This driver supports the ethernet MACs in the Broadcom 63xx MIPS chipset family (BCM63XX). +config BCMGENET + tristate "Broadcom GENET internal MAC support" + depends on OF + select MII + select PHYLIB + select FIXED_PHY if BCMGENET=y + select BCM7XXX_PHY + help + This driver supports the built-in Ethernet MACs found in the + Broadcom BCM7xxx Set Top Box family chipset. + config BNX2 tristate "Broadcom NetXtremeII support" depends on PCI diff --git a/drivers/net/ethernet/broadcom/Makefile b/drivers/net/ethernet/broadcom/Makefile index 68efa1a3fb88..fd639a0d4c7d 100644 --- a/drivers/net/ethernet/broadcom/Makefile +++ b/drivers/net/ethernet/broadcom/Makefile @@ -4,6 +4,7 @@ obj-$(CONFIG_B44) += b44.o obj-$(CONFIG_BCM63XX_ENET) += bcm63xx_enet.o +obj-$(CONFIG_BCMGENET) += genet/ obj-$(CONFIG_BNX2) += bnx2.o obj-$(CONFIG_CNIC) += cnic.o obj-$(CONFIG_BNX2X) += bnx2x/ diff --git a/drivers/net/ethernet/broadcom/b44.c b/drivers/net/ethernet/broadcom/b44.c index 1f7b5aa114fa..8a7bf7dad898 100644 --- a/drivers/net/ethernet/broadcom/b44.c +++ b/drivers/net/ethernet/broadcom/b44.c @@ -1484,6 +1484,10 @@ static int b44_open(struct net_device *dev) add_timer(&bp->timer); b44_enable_ints(bp); + + if (bp->flags & B44_FLAG_EXTERNAL_PHY) + phy_start(bp->phydev); + netif_start_queue(dev); out: return err; @@ -1646,6 +1650,9 @@ static int b44_close(struct net_device *dev) netif_stop_queue(dev); + if (bp->flags & B44_FLAG_EXTERNAL_PHY) + phy_stop(bp->phydev); + napi_disable(&bp->napi); del_timer_sync(&bp->timer); @@ -2222,7 +2229,12 @@ static void b44_adjust_link(struct net_device *dev) } if (status_changed) { - b44_check_phy(bp); + u32 val = br32(bp, B44_TX_CTRL); + if (bp->flags & B44_FLAG_FULL_DUPLEX) + val |= TX_CTRL_DUPLEX; + else + val &= ~TX_CTRL_DUPLEX; + bw32(bp, B44_TX_CTRL, val); phy_print_status(phydev); } } diff --git a/drivers/net/ethernet/broadcom/bnx2.c b/drivers/net/ethernet/broadcom/bnx2.c index 9d2dedadf2df..c251ca3056de 100644 --- a/drivers/net/ethernet/broadcom/bnx2.c +++ b/drivers/net/ethernet/broadcom/bnx2.c @@ -85,7 +85,7 @@ MODULE_FIRMWARE(FW_RV2P_FILE_09_Ax); static int disable_msi = 0; -module_param(disable_msi, int, 0); +module_param(disable_msi, int, S_IRUGO); MODULE_PARM_DESC(disable_msi, "Disable Message Signaled Interrupt (MSI)"); typedef enum { @@ -2885,7 +2885,7 @@ bnx2_tx_int(struct bnx2 *bp, struct bnx2_napi *bnapi, int budget) sw_cons = BNX2_NEXT_TX_BD(sw_cons); tx_bytes += skb->len; - dev_kfree_skb(skb); + dev_kfree_skb_any(skb); tx_pkt++; if (tx_pkt == budget) break; @@ -6206,7 +6206,7 @@ bnx2_free_irq(struct bnx2 *bp) static void bnx2_enable_msix(struct bnx2 *bp, int msix_vecs) { - int i, total_vecs, rc; + int i, total_vecs; struct msix_entry msix_ent[BNX2_MAX_MSIX_VEC]; struct net_device *dev = bp->dev; const int len = sizeof(bp->irq_tbl[0].name); @@ -6229,16 +6229,9 @@ bnx2_enable_msix(struct bnx2 *bp, int msix_vecs) #ifdef BCM_CNIC total_vecs++; #endif - rc = -ENOSPC; - while (total_vecs >= BNX2_MIN_MSIX_VEC) { - rc = pci_enable_msix(bp->pdev, msix_ent, total_vecs); - if (rc <= 0) - break; - if (rc > 0) - total_vecs = rc; - } - - if (rc != 0) + total_vecs = pci_enable_msix_range(bp->pdev, msix_ent, + BNX2_MIN_MSIX_VEC, total_vecs); + if (total_vecs < 0) return; msix_vecs = total_vecs; @@ -6611,7 +6604,7 @@ bnx2_start_xmit(struct sk_buff *skb, struct net_device *dev) mapping = dma_map_single(&bp->pdev->dev, skb->data, len, PCI_DMA_TODEVICE); if (dma_mapping_error(&bp->pdev->dev, mapping)) { - dev_kfree_skb(skb); + dev_kfree_skb_any(skb); return NETDEV_TX_OK; } @@ -6704,7 +6697,7 @@ dma_error: PCI_DMA_TODEVICE); } - dev_kfree_skb(skb); + dev_kfree_skb_any(skb); return NETDEV_TX_OK; } diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h index 391f29ef6d2e..722160940ab9 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h @@ -26,8 +26,8 @@ * (you will need to reboot afterwards) */ /* #define BNX2X_STOP_ON_ERROR */ -#define DRV_MODULE_VERSION "1.78.17-0" -#define DRV_MODULE_RELDATE "2013/04/11" +#define DRV_MODULE_VERSION "1.78.19-0" +#define DRV_MODULE_RELDATE "2014/02/10" #define BNX2X_BC_VER 0x040200 #if defined(CONFIG_DCB) @@ -75,13 +75,22 @@ enum bnx2x_int_mode { #define BNX2X_MSG_DCB 0x8000000 /* regular debug print */ +#define DP_INNER(fmt, ...) \ + pr_notice("[%s:%d(%s)]" fmt, \ + __func__, __LINE__, \ + bp->dev ? (bp->dev->name) : "?", \ + ##__VA_ARGS__); + #define DP(__mask, fmt, ...) \ do { \ if (unlikely(bp->msg_enable & (__mask))) \ - pr_notice("[%s:%d(%s)]" fmt, \ - __func__, __LINE__, \ - bp->dev ? (bp->dev->name) : "?", \ - ##__VA_ARGS__); \ + DP_INNER(fmt, ##__VA_ARGS__); \ +} while (0) + +#define DP_AND(__mask, fmt, ...) \ +do { \ + if (unlikely((bp->msg_enable & (__mask)) == __mask)) \ + DP_INNER(fmt, ##__VA_ARGS__); \ } while (0) #define DP_CONT(__mask, fmt, ...) \ @@ -1261,6 +1270,7 @@ struct bnx2x_slowpath { union { struct client_init_ramrod_data init_data; struct client_update_ramrod_data update_data; + struct tpa_update_ramrod_data tpa_data; } q_rdata; union { @@ -1392,7 +1402,7 @@ struct bnx2x_fw_stats_data { }; /* Public slow path states */ -enum { +enum sp_rtnl_flag { BNX2X_SP_RTNL_SETUP_TC, BNX2X_SP_RTNL_TX_TIMEOUT, BNX2X_SP_RTNL_FAN_FAILURE, diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index 9d7419e0390b..117b5c7f8ac9 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -61,10 +61,14 @@ static void bnx2x_add_all_napi(struct bnx2x *bp) static int bnx2x_calc_num_queues(struct bnx2x *bp) { - return bnx2x_num_queues ? - min_t(int, bnx2x_num_queues, BNX2X_MAX_QUEUES(bp)) : - min_t(int, netif_get_num_default_rss_queues(), - BNX2X_MAX_QUEUES(bp)); + int nq = bnx2x_num_queues ? : netif_get_num_default_rss_queues(); + + /* Reduce memory usage in kdump environment by using only one queue */ + if (reset_devices) + nq = 1; + + nq = clamp(nq, 1, BNX2X_MAX_QUEUES(bp)); + return nq; } /** @@ -1638,36 +1642,16 @@ int bnx2x_enable_msix(struct bnx2x *bp) DP(BNX2X_MSG_SP, "about to request enable msix with %d vectors\n", msix_vec); - rc = pci_enable_msix(bp->pdev, &bp->msix_table[0], msix_vec); - + rc = pci_enable_msix_range(bp->pdev, &bp->msix_table[0], + BNX2X_MIN_MSIX_VEC_CNT(bp), msix_vec); /* * reconfigure number of tx/rx queues according to available * MSI-X vectors */ - if (rc >= BNX2X_MIN_MSIX_VEC_CNT(bp)) { - /* how less vectors we will have? */ - int diff = msix_vec - rc; - - BNX2X_DEV_INFO("Trying to use less MSI-X vectors: %d\n", rc); - - rc = pci_enable_msix(bp->pdev, &bp->msix_table[0], rc); - - if (rc) { - BNX2X_DEV_INFO("MSI-X is not attainable rc %d\n", rc); - goto no_msix; - } - /* - * decrease number of queues by number of unallocated entries - */ - bp->num_ethernet_queues -= diff; - bp->num_queues = bp->num_ethernet_queues + bp->num_cnic_queues; - - BNX2X_DEV_INFO("New queue configuration set: %d\n", - bp->num_queues); - } else if (rc > 0) { + if (rc == -ENOSPC) { /* Get by with single vector */ - rc = pci_enable_msix(bp->pdev, &bp->msix_table[0], 1); - if (rc) { + rc = pci_enable_msix_range(bp->pdev, &bp->msix_table[0], 1, 1); + if (rc < 0) { BNX2X_DEV_INFO("Single MSI-X is not attainable rc %d\n", rc); goto no_msix; @@ -1680,8 +1664,22 @@ int bnx2x_enable_msix(struct bnx2x *bp) bp->num_ethernet_queues = 1; bp->num_queues = bp->num_ethernet_queues + bp->num_cnic_queues; } else if (rc < 0) { - BNX2X_DEV_INFO("MSI-X is not attainable rc %d\n", rc); + BNX2X_DEV_INFO("MSI-X is not attainable rc %d\n", rc); goto no_msix; + } else if (rc < msix_vec) { + /* how less vectors we will have? */ + int diff = msix_vec - rc; + + BNX2X_DEV_INFO("Trying to use less MSI-X vectors: %d\n", rc); + + /* + * decrease number of queues by number of unallocated entries + */ + bp->num_ethernet_queues -= diff; + bp->num_queues = bp->num_ethernet_queues + bp->num_cnic_queues; + + BNX2X_DEV_INFO("New queue configuration set: %d\n", + bp->num_queues); } bp->flags |= USING_MSIX_FLAG; @@ -1873,7 +1871,7 @@ void bnx2x_netif_stop(struct bnx2x *bp, int disable_hw) } u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv) + void *accel_priv, select_queue_fallback_t fallback) { struct bnx2x *bp = netdev_priv(dev); @@ -1895,7 +1893,7 @@ u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb, } /* select a non-FCoE queue */ - return __netdev_pick_tx(dev, skb) % BNX2X_NUM_ETH_QUEUES(bp); + return fallback(dev, skb) % BNX2X_NUM_ETH_QUEUES(bp); } void bnx2x_set_num_queues(struct bnx2x *bp) @@ -2234,8 +2232,10 @@ static int bnx2x_alloc_fw_stats_mem(struct bnx2x *bp) sizeof(struct per_queue_stats) * num_queue_stats + sizeof(struct stats_counter); - BNX2X_PCI_ALLOC(bp->fw_stats, &bp->fw_stats_mapping, - bp->fw_stats_data_sz + bp->fw_stats_req_sz); + bp->fw_stats = BNX2X_PCI_ALLOC(&bp->fw_stats_mapping, + bp->fw_stats_data_sz + bp->fw_stats_req_sz); + if (!bp->fw_stats) + goto alloc_mem_err; /* Set shortcuts */ bp->fw_stats_req = (struct bnx2x_fw_stats_req *)bp->fw_stats; @@ -3875,7 +3875,9 @@ netdev_tx_t bnx2x_start_xmit(struct sk_buff *skb, struct net_device *dev) xmit_type); } - /* Add the macs to the parsing BD this is a vf */ + /* Add the macs to the parsing BD if this is a vf or if + * Tx Switching is enabled. + */ if (IS_VF(bp)) { /* override GRE parameters in BD */ bnx2x_set_fw_mac_addr(&pbd_e2->data.mac_addr.src_hi, @@ -3887,6 +3889,11 @@ netdev_tx_t bnx2x_start_xmit(struct sk_buff *skb, struct net_device *dev) &pbd_e2->data.mac_addr.dst_mid, &pbd_e2->data.mac_addr.dst_lo, eth->h_dest); + } else if (bp->flags & TX_SWITCHING) { + bnx2x_set_fw_mac_addr(&pbd_e2->data.mac_addr.dst_hi, + &pbd_e2->data.mac_addr.dst_mid, + &pbd_e2->data.mac_addr.dst_lo, + eth->h_dest); } SET_FLAG(pbd_e2_parsing_data, @@ -4363,14 +4370,17 @@ static int bnx2x_alloc_fp_mem_at(struct bnx2x *bp, int index) if (!IS_FCOE_IDX(index)) { /* status blocks */ - if (!CHIP_IS_E1x(bp)) - BNX2X_PCI_ALLOC(sb->e2_sb, - &bnx2x_fp(bp, index, status_blk_mapping), - sizeof(struct host_hc_status_block_e2)); - else - BNX2X_PCI_ALLOC(sb->e1x_sb, - &bnx2x_fp(bp, index, status_blk_mapping), - sizeof(struct host_hc_status_block_e1x)); + if (!CHIP_IS_E1x(bp)) { + sb->e2_sb = BNX2X_PCI_ALLOC(&bnx2x_fp(bp, index, status_blk_mapping), + sizeof(struct host_hc_status_block_e2)); + if (!sb->e2_sb) + goto alloc_mem_err; + } else { + sb->e1x_sb = BNX2X_PCI_ALLOC(&bnx2x_fp(bp, index, status_blk_mapping), + sizeof(struct host_hc_status_block_e1x)); + if (!sb->e1x_sb) + goto alloc_mem_err; + } } /* FCoE Queue uses Default SB and doesn't ACK the SB, thus no need to @@ -4389,35 +4399,49 @@ static int bnx2x_alloc_fp_mem_at(struct bnx2x *bp, int index) "allocating tx memory of fp %d cos %d\n", index, cos); - BNX2X_ALLOC(txdata->tx_buf_ring, - sizeof(struct sw_tx_bd) * NUM_TX_BD); - BNX2X_PCI_ALLOC(txdata->tx_desc_ring, - &txdata->tx_desc_mapping, - sizeof(union eth_tx_bd_types) * NUM_TX_BD); + txdata->tx_buf_ring = kcalloc(NUM_TX_BD, + sizeof(struct sw_tx_bd), + GFP_KERNEL); + if (!txdata->tx_buf_ring) + goto alloc_mem_err; + txdata->tx_desc_ring = BNX2X_PCI_ALLOC(&txdata->tx_desc_mapping, + sizeof(union eth_tx_bd_types) * NUM_TX_BD); + if (!txdata->tx_desc_ring) + goto alloc_mem_err; } } /* Rx */ if (!skip_rx_queue(bp, index)) { /* fastpath rx rings: rx_buf rx_desc rx_comp */ - BNX2X_ALLOC(bnx2x_fp(bp, index, rx_buf_ring), - sizeof(struct sw_rx_bd) * NUM_RX_BD); - BNX2X_PCI_ALLOC(bnx2x_fp(bp, index, rx_desc_ring), - &bnx2x_fp(bp, index, rx_desc_mapping), - sizeof(struct eth_rx_bd) * NUM_RX_BD); + bnx2x_fp(bp, index, rx_buf_ring) = + kcalloc(NUM_RX_BD, sizeof(struct sw_rx_bd), GFP_KERNEL); + if (!bnx2x_fp(bp, index, rx_buf_ring)) + goto alloc_mem_err; + bnx2x_fp(bp, index, rx_desc_ring) = + BNX2X_PCI_ALLOC(&bnx2x_fp(bp, index, rx_desc_mapping), + sizeof(struct eth_rx_bd) * NUM_RX_BD); + if (!bnx2x_fp(bp, index, rx_desc_ring)) + goto alloc_mem_err; /* Seed all CQEs by 1s */ - BNX2X_PCI_FALLOC(bnx2x_fp(bp, index, rx_comp_ring), - &bnx2x_fp(bp, index, rx_comp_mapping), - sizeof(struct eth_fast_path_rx_cqe) * - NUM_RCQ_BD); + bnx2x_fp(bp, index, rx_comp_ring) = + BNX2X_PCI_FALLOC(&bnx2x_fp(bp, index, rx_comp_mapping), + sizeof(struct eth_fast_path_rx_cqe) * NUM_RCQ_BD); + if (!bnx2x_fp(bp, index, rx_comp_ring)) + goto alloc_mem_err; /* SGE ring */ - BNX2X_ALLOC(bnx2x_fp(bp, index, rx_page_ring), - sizeof(struct sw_rx_page) * NUM_RX_SGE); - BNX2X_PCI_ALLOC(bnx2x_fp(bp, index, rx_sge_ring), - &bnx2x_fp(bp, index, rx_sge_mapping), - BCM_PAGE_SIZE * NUM_RX_SGE_PAGES); + bnx2x_fp(bp, index, rx_page_ring) = + kcalloc(NUM_RX_SGE, sizeof(struct sw_rx_page), + GFP_KERNEL); + if (!bnx2x_fp(bp, index, rx_page_ring)) + goto alloc_mem_err; + bnx2x_fp(bp, index, rx_sge_ring) = + BNX2X_PCI_ALLOC(&bnx2x_fp(bp, index, rx_sge_mapping), + BCM_PAGE_SIZE * NUM_RX_SGE_PAGES); + if (!bnx2x_fp(bp, index, rx_sge_ring)) + goto alloc_mem_err; /* RX BD ring */ bnx2x_set_next_page_rx_bd(fp); @@ -4773,12 +4797,8 @@ void bnx2x_tx_timeout(struct net_device *dev) bnx2x_panic(); #endif - smp_mb__before_clear_bit(); - set_bit(BNX2X_SP_RTNL_TX_TIMEOUT, &bp->sp_rtnl_state); - smp_mb__after_clear_bit(); - /* This allows the netif to be shutdown gracefully before resetting */ - schedule_delayed_work(&bp->sp_rtnl_task, 0); + bnx2x_schedule_sp_rtnl(bp, BNX2X_SP_RTNL_TX_TIMEOUT, 0); } int bnx2x_suspend(struct pci_dev *pdev, pm_message_t state) @@ -4906,3 +4926,15 @@ void bnx2x_update_coalesce_sb_index(struct bnx2x *bp, u8 fw_sb_id, disable = disable ? 1 : (usec ? 0 : 1); storm_memset_hc_disable(bp, port, fw_sb_id, sb_index, disable); } + +void bnx2x_schedule_sp_rtnl(struct bnx2x *bp, enum sp_rtnl_flag flag, + u32 verbose) +{ + smp_mb__before_clear_bit(); + set_bit(flag, &bp->sp_rtnl_state); + smp_mb__after_clear_bit(); + DP((BNX2X_MSG_SP | verbose), "Scheduling sp_rtnl task [Flag: %d]\n", + flag); + schedule_delayed_work(&bp->sp_rtnl_task, 0); +} +EXPORT_SYMBOL(bnx2x_schedule_sp_rtnl); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h index 17d1689aec6b..05f4f5f52635 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h @@ -47,31 +47,26 @@ extern int bnx2x_num_queues; } \ } while (0) -#define BNX2X_PCI_ALLOC(x, y, size) \ - do { \ - x = dma_zalloc_coherent(&bp->pdev->dev, size, y, GFP_KERNEL); \ - if (x == NULL) \ - goto alloc_mem_err; \ - DP(NETIF_MSG_HW, "BNX2X_PCI_ALLOC: Physical %Lx Virtual %p\n", \ - (unsigned long long)(*y), x); \ - } while (0) - -#define BNX2X_PCI_FALLOC(x, y, size) \ - do { \ - x = dma_alloc_coherent(&bp->pdev->dev, size, y, GFP_KERNEL); \ - if (x == NULL) \ - goto alloc_mem_err; \ - memset((void *)x, 0xFFFFFFFF, size); \ - DP(NETIF_MSG_HW, "BNX2X_PCI_FALLOC: Physical %Lx Virtual %p\n",\ - (unsigned long long)(*y), x); \ - } while (0) - -#define BNX2X_ALLOC(x, size) \ - do { \ - x = kzalloc(size, GFP_KERNEL); \ - if (x == NULL) \ - goto alloc_mem_err; \ - } while (0) +#define BNX2X_PCI_ALLOC(y, size) \ +({ \ + void *x = dma_zalloc_coherent(&bp->pdev->dev, size, y, GFP_KERNEL); \ + if (x) \ + DP(NETIF_MSG_HW, \ + "BNX2X_PCI_ALLOC: Physical %Lx Virtual %p\n", \ + (unsigned long long)(*y), x); \ + x; \ +}) +#define BNX2X_PCI_FALLOC(y, size) \ +({ \ + void *x = dma_alloc_coherent(&bp->pdev->dev, size, y, GFP_KERNEL); \ + if (x) { \ + memset(x, 0xff, size); \ + DP(NETIF_MSG_HW, \ + "BNX2X_PCI_FALLOC: Physical %Lx Virtual %p\n", \ + (unsigned long long)(*y), x); \ + } \ + x; \ +}) /*********************** Interfaces **************************** * Functions that need to be implemented by each driver version @@ -496,7 +491,7 @@ int bnx2x_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos); /* select_queue callback */ u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv); + void *accel_priv, select_queue_fallback_t fallback); static inline void bnx2x_update_rx_prod(struct bnx2x *bp, struct bnx2x_fastpath *fp, @@ -936,7 +931,7 @@ static inline int bnx2x_func_start(struct bnx2x *bp) else /* CHIP_IS_E1X */ start_params->network_cos_mode = FW_WRR; - start_params->gre_tunnel_mode = IPGRE_TUNNEL; + start_params->gre_tunnel_mode = L2GRE_TUNNEL; start_params->gre_tunnel_rss = GRE_INNER_HEADERS_RSS; return bnx2x_func_state_change(bp, &func_params); @@ -1324,4 +1319,7 @@ void bnx2x_fill_fw_str(struct bnx2x *bp, char *buf, size_t buf_len); int bnx2x_drain_tx_queues(struct bnx2x *bp); void bnx2x_squeeze_objects(struct bnx2x *bp); +void bnx2x_schedule_sp_rtnl(struct bnx2x*, enum sp_rtnl_flag, + u32 verbose); + #endif /* BNX2X_CMN_H */ diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.c index fdace204b054..97ea5421dd96 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.c @@ -710,8 +710,7 @@ static inline void bnx2x_dcbx_update_tc_mapping(struct bnx2x *bp) * as we are handling an attention on a work queue which must be * flushed at some rtnl-locked contexts (e.g. if down) */ - if (!test_and_set_bit(BNX2X_SP_RTNL_SETUP_TC, &bp->sp_rtnl_state)) - schedule_delayed_work(&bp->sp_rtnl_task, 0); + bnx2x_schedule_sp_rtnl(bp, BNX2X_SP_RTNL_SETUP_TC, 0); } void bnx2x_dcbx_set_params(struct bnx2x *bp, u32 state) @@ -764,10 +763,7 @@ void bnx2x_dcbx_set_params(struct bnx2x *bp, u32 state) if (IS_MF(bp)) bnx2x_link_sync_notify(bp); - set_bit(BNX2X_SP_RTNL_TX_STOP, &bp->sp_rtnl_state); - - schedule_delayed_work(&bp->sp_rtnl_task, 0); - + bnx2x_schedule_sp_rtnl(bp, BNX2X_SP_RTNL_TX_STOP, 0); return; } case BNX2X_DCBX_STATE_TX_PAUSED: diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_fw_defs.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_fw_defs.h index 84aecdf06f7a..95dc36543548 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_fw_defs.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_fw_defs.h @@ -87,7 +87,6 @@ (IRO[156].base + ((vfId) * IRO[156].m1)) #define CSTORM_VF_TO_PF_OFFSET(funcId) \ (IRO[150].base + ((funcId) * IRO[150].m1)) -#define TSTORM_ACCEPT_CLASSIFY_FAILED_OFFSET (IRO[204].base) #define TSTORM_APPROXIMATE_MATCH_MULTICAST_FILTERING_OFFSET(pfId) \ (IRO[203].base + ((pfId) * IRO[203].m1)) #define TSTORM_ASSERT_LIST_INDEX_OFFSET (IRO[102].base) diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h index cf1df8b62e2c..46e2f18df2cb 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h @@ -2848,7 +2848,7 @@ struct afex_stats { #define BCM_5710_FW_MAJOR_VERSION 7 #define BCM_5710_FW_MINOR_VERSION 8 -#define BCM_5710_FW_REVISION_VERSION 17 +#define BCM_5710_FW_REVISION_VERSION 19 #define BCM_5710_FW_ENGINEERING_VERSION 0 #define BCM_5710_FW_COMPILE_FLAGS 1 diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index c9c445e7b4a5..5e74599b05c7 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -95,29 +95,29 @@ MODULE_FIRMWARE(FW_FILE_NAME_E1H); MODULE_FIRMWARE(FW_FILE_NAME_E2); int bnx2x_num_queues; -module_param_named(num_queues, bnx2x_num_queues, int, 0); +module_param_named(num_queues, bnx2x_num_queues, int, S_IRUGO); MODULE_PARM_DESC(num_queues, " Set number of queues (default is as a number of CPUs)"); static int disable_tpa; -module_param(disable_tpa, int, 0); +module_param(disable_tpa, int, S_IRUGO); MODULE_PARM_DESC(disable_tpa, " Disable the TPA (LRO) feature"); static int int_mode; -module_param(int_mode, int, 0); +module_param(int_mode, int, S_IRUGO); MODULE_PARM_DESC(int_mode, " Force interrupt mode other than MSI-X " "(1 INT#x; 2 MSI)"); static int dropless_fc; -module_param(dropless_fc, int, 0); +module_param(dropless_fc, int, S_IRUGO); MODULE_PARM_DESC(dropless_fc, " Pause on exhausted host ring"); static int mrrs = -1; -module_param(mrrs, int, 0); +module_param(mrrs, int, S_IRUGO); MODULE_PARM_DESC(mrrs, " Force Max Read Req Size (0..3) (for debug)"); static int debug; -module_param(debug, int, 0); +module_param(debug, int, S_IRUGO); MODULE_PARM_DESC(debug, " Default debug msglevel"); struct workqueue_struct *bnx2x_wq; @@ -918,7 +918,7 @@ void bnx2x_panic_dump(struct bnx2x *bp, bool disable_int) u16 start = 0, end = 0; u8 cos; #endif - if (disable_int) + if (IS_PF(bp) && disable_int) bnx2x_int_disable(bp); bp->stats_state = STATS_STATE_DISABLED; @@ -929,33 +929,41 @@ void bnx2x_panic_dump(struct bnx2x *bp, bool disable_int) /* Indices */ /* Common */ - BNX2X_ERR("def_idx(0x%x) def_att_idx(0x%x) attn_state(0x%x) spq_prod_idx(0x%x) next_stats_cnt(0x%x)\n", - bp->def_idx, bp->def_att_idx, bp->attn_state, - bp->spq_prod_idx, bp->stats_counter); - BNX2X_ERR("DSB: attn bits(0x%x) ack(0x%x) id(0x%x) idx(0x%x)\n", - bp->def_status_blk->atten_status_block.attn_bits, - bp->def_status_blk->atten_status_block.attn_bits_ack, - bp->def_status_blk->atten_status_block.status_block_id, - bp->def_status_blk->atten_status_block.attn_bits_index); - BNX2X_ERR(" def ("); - for (i = 0; i < HC_SP_SB_MAX_INDICES; i++) - pr_cont("0x%x%s", - bp->def_status_blk->sp_sb.index_values[i], - (i == HC_SP_SB_MAX_INDICES - 1) ? ") " : " "); - - for (i = 0; i < sizeof(struct hc_sp_status_block_data)/sizeof(u32); i++) - *((u32 *)&sp_sb_data + i) = REG_RD(bp, BAR_CSTRORM_INTMEM + - CSTORM_SP_STATUS_BLOCK_DATA_OFFSET(func) + - i*sizeof(u32)); - - pr_cont("igu_sb_id(0x%x) igu_seg_id(0x%x) pf_id(0x%x) vnic_id(0x%x) vf_id(0x%x) vf_valid (0x%x) state(0x%x)\n", - sp_sb_data.igu_sb_id, - sp_sb_data.igu_seg_id, - sp_sb_data.p_func.pf_id, - sp_sb_data.p_func.vnic_id, - sp_sb_data.p_func.vf_id, - sp_sb_data.p_func.vf_valid, - sp_sb_data.state); + if (IS_PF(bp)) { + struct host_sp_status_block *def_sb = bp->def_status_blk; + int data_size, cstorm_offset; + + BNX2X_ERR("def_idx(0x%x) def_att_idx(0x%x) attn_state(0x%x) spq_prod_idx(0x%x) next_stats_cnt(0x%x)\n", + bp->def_idx, bp->def_att_idx, bp->attn_state, + bp->spq_prod_idx, bp->stats_counter); + BNX2X_ERR("DSB: attn bits(0x%x) ack(0x%x) id(0x%x) idx(0x%x)\n", + def_sb->atten_status_block.attn_bits, + def_sb->atten_status_block.attn_bits_ack, + def_sb->atten_status_block.status_block_id, + def_sb->atten_status_block.attn_bits_index); + BNX2X_ERR(" def ("); + for (i = 0; i < HC_SP_SB_MAX_INDICES; i++) + pr_cont("0x%x%s", + def_sb->sp_sb.index_values[i], + (i == HC_SP_SB_MAX_INDICES - 1) ? ") " : " "); + + data_size = sizeof(struct hc_sp_status_block_data) / + sizeof(u32); + cstorm_offset = CSTORM_SP_STATUS_BLOCK_DATA_OFFSET(func); + for (i = 0; i < data_size; i++) + *((u32 *)&sp_sb_data + i) = + REG_RD(bp, BAR_CSTRORM_INTMEM + cstorm_offset + + i * sizeof(u32)); + + pr_cont("igu_sb_id(0x%x) igu_seg_id(0x%x) pf_id(0x%x) vnic_id(0x%x) vf_id(0x%x) vf_valid (0x%x) state(0x%x)\n", + sp_sb_data.igu_sb_id, + sp_sb_data.igu_seg_id, + sp_sb_data.p_func.pf_id, + sp_sb_data.p_func.vnic_id, + sp_sb_data.p_func.vf_id, + sp_sb_data.p_func.vf_valid, + sp_sb_data.state); + } for_each_eth_queue(bp, i) { struct bnx2x_fastpath *fp = &bp->fp[i]; @@ -1013,6 +1021,11 @@ void bnx2x_panic_dump(struct bnx2x *bp, bool disable_int) pr_cont("0x%x%s", fp->sb_index_values[j], (j == loop - 1) ? ")" : " "); + + /* VF cannot access FW refelection for status block */ + if (IS_VF(bp)) + continue; + /* fw sb data */ data_size = CHIP_IS_E1x(bp) ? sizeof(struct hc_status_block_data_e1x) : @@ -1064,16 +1077,18 @@ void bnx2x_panic_dump(struct bnx2x *bp, bool disable_int) } #ifdef BNX2X_STOP_ON_ERROR - - /* event queue */ - BNX2X_ERR("eq cons %x prod %x\n", bp->eq_cons, bp->eq_prod); - for (i = 0; i < NUM_EQ_DESC; i++) { - u32 *data = (u32 *)&bp->eq_ring[i].message.data; - - BNX2X_ERR("event queue [%d]: header: opcode %d, error %d\n", - i, bp->eq_ring[i].message.opcode, - bp->eq_ring[i].message.error); - BNX2X_ERR("data: %x %x %x\n", data[0], data[1], data[2]); + if (IS_PF(bp)) { + /* event queue */ + BNX2X_ERR("eq cons %x prod %x\n", bp->eq_cons, bp->eq_prod); + for (i = 0; i < NUM_EQ_DESC; i++) { + u32 *data = (u32 *)&bp->eq_ring[i].message.data; + + BNX2X_ERR("event queue [%d]: header: opcode %d, error %d\n", + i, bp->eq_ring[i].message.opcode, + bp->eq_ring[i].message.error); + BNX2X_ERR("data: %x %x %x\n", + data[0], data[1], data[2]); + } } /* Rings */ @@ -1140,8 +1155,10 @@ void bnx2x_panic_dump(struct bnx2x *bp, bool disable_int) } } #endif - bnx2x_fw_dump(bp); - bnx2x_mc_assert(bp); + if (IS_PF(bp)) { + bnx2x_fw_dump(bp); + bnx2x_mc_assert(bp); + } BNX2X_ERR("end crash dump -----------------\n"); } @@ -1814,6 +1831,11 @@ void bnx2x_sp_event(struct bnx2x_fastpath *fp, union eth_rx_cqe *rr_cqe) drv_cmd = BNX2X_Q_CMD_EMPTY; break; + case (RAMROD_CMD_ID_ETH_TPA_UPDATE): + DP(BNX2X_MSG_SP, "got tpa update ramrod CID=%d\n", cid); + drv_cmd = BNX2X_Q_CMD_UPDATE_TPA; + break; + default: BNX2X_ERR("unexpected MC reply (%d) on fp[%d]\n", command, fp->index); @@ -3644,10 +3666,18 @@ int bnx2x_sp_post(struct bnx2x *bp, int command, int cid, cpu_to_le32((command << SPE_HDR_CMD_ID_SHIFT) | HW_CID(bp, cid)); - type = (cmd_type << SPE_HDR_CONN_TYPE_SHIFT) & SPE_HDR_CONN_TYPE; - - type |= ((BP_FUNC(bp) << SPE_HDR_FUNCTION_ID_SHIFT) & - SPE_HDR_FUNCTION_ID); + /* In some cases, type may already contain the func-id + * mainly in SRIOV related use cases, so we add it here only + * if it's not already set. + */ + if (!(cmd_type & SPE_HDR_FUNCTION_ID)) { + type = (cmd_type << SPE_HDR_CONN_TYPE_SHIFT) & + SPE_HDR_CONN_TYPE; + type |= ((BP_FUNC(bp) << SPE_HDR_FUNCTION_ID_SHIFT) & + SPE_HDR_FUNCTION_ID); + } else { + type = cmd_type; + } spe->hdr.type = cpu_to_le16(type); @@ -3878,10 +3908,7 @@ static void bnx2x_fan_failure(struct bnx2x *bp) * This is due to some boards consuming sufficient power when driver is * up to overheat if fan fails. */ - smp_mb__before_clear_bit(); - set_bit(BNX2X_SP_RTNL_FAN_FAILURE, &bp->sp_rtnl_state); - smp_mb__after_clear_bit(); - schedule_delayed_work(&bp->sp_rtnl_task, 0); + bnx2x_schedule_sp_rtnl(bp, BNX2X_SP_RTNL_FAN_FAILURE, 0); } static void bnx2x_attn_int_deasserted0(struct bnx2x *bp, u32 attn) @@ -5221,9 +5248,9 @@ static void bnx2x_eq_int(struct bnx2x *bp) continue; case EVENT_RING_OPCODE_STAT_QUERY: - DP(BNX2X_MSG_SP | BNX2X_MSG_STATS, - "got statistics comp event %d\n", - bp->stats_comp++); + DP_AND((BNX2X_MSG_SP | BNX2X_MSG_STATS), + "got statistics comp event %d\n", + bp->stats_comp++); /* nothing to do with stats comp */ goto next_spqe; @@ -5273,6 +5300,8 @@ static void bnx2x_eq_int(struct bnx2x *bp) break; } else { + int cmd = BNX2X_SP_RTNL_AFEX_F_UPDATE; + DP(BNX2X_MSG_SP | BNX2X_MSG_MCP, "AFEX: ramrod completed FUNCTION_UPDATE\n"); f_obj->complete_cmd(bp, f_obj, @@ -5282,12 +5311,7 @@ static void bnx2x_eq_int(struct bnx2x *bp) * sp_rtnl task as all Queue SP operations * should run under rtnl_lock. */ - smp_mb__before_clear_bit(); - set_bit(BNX2X_SP_RTNL_AFEX_F_UPDATE, - &bp->sp_rtnl_state); - smp_mb__after_clear_bit(); - - schedule_delayed_work(&bp->sp_rtnl_task, 0); + bnx2x_schedule_sp_rtnl(bp, cmd, 0); } goto next_spqe; @@ -6005,18 +6029,6 @@ static void bnx2x_init_internal_common(struct bnx2x *bp) { int i; - if (IS_MF_SI(bp)) - /* - * In switch independent mode, the TSTORM needs to accept - * packets that failed classification, since approximate match - * mac addresses aren't written to NIG LLH - */ - REG_WR8(bp, BAR_TSTRORM_INTMEM + - TSTORM_ACCEPT_CLASSIFY_FAILED_OFFSET, 2); - else if (!CHIP_IS_E1(bp)) /* 57710 doesn't support MF */ - REG_WR8(bp, BAR_TSTRORM_INTMEM + - TSTORM_ACCEPT_CLASSIFY_FAILED_OFFSET, 0); - /* Zero this manually as its initialization is currently missing in the initTool */ for (i = 0; i < (USTORM_AGG_DATA_SIZE >> 2); i++) @@ -7989,19 +8001,25 @@ void bnx2x_free_mem(struct bnx2x *bp) int bnx2x_alloc_mem_cnic(struct bnx2x *bp) { - if (!CHIP_IS_E1x(bp)) + if (!CHIP_IS_E1x(bp)) { /* size = the status block + ramrod buffers */ - BNX2X_PCI_ALLOC(bp->cnic_sb.e2_sb, &bp->cnic_sb_mapping, - sizeof(struct host_hc_status_block_e2)); - else - BNX2X_PCI_ALLOC(bp->cnic_sb.e1x_sb, - &bp->cnic_sb_mapping, - sizeof(struct - host_hc_status_block_e1x)); + bp->cnic_sb.e2_sb = BNX2X_PCI_ALLOC(&bp->cnic_sb_mapping, + sizeof(struct host_hc_status_block_e2)); + if (!bp->cnic_sb.e2_sb) + goto alloc_mem_err; + } else { + bp->cnic_sb.e1x_sb = BNX2X_PCI_ALLOC(&bp->cnic_sb_mapping, + sizeof(struct host_hc_status_block_e1x)); + if (!bp->cnic_sb.e1x_sb) + goto alloc_mem_err; + } - if (CONFIGURE_NIC_MODE(bp) && !bp->t2) + if (CONFIGURE_NIC_MODE(bp) && !bp->t2) { /* allocate searcher T2 table, as it wasn't allocated before */ - BNX2X_PCI_ALLOC(bp->t2, &bp->t2_mapping, SRC_T2_SZ); + bp->t2 = BNX2X_PCI_ALLOC(&bp->t2_mapping, SRC_T2_SZ); + if (!bp->t2) + goto alloc_mem_err; + } /* write address to which L5 should insert its values */ bp->cnic_eth_dev.addr_drv_info_to_mcp = @@ -8022,15 +8040,22 @@ int bnx2x_alloc_mem(struct bnx2x *bp) { int i, allocated, context_size; - if (!CONFIGURE_NIC_MODE(bp) && !bp->t2) + if (!CONFIGURE_NIC_MODE(bp) && !bp->t2) { /* allocate searcher T2 table */ - BNX2X_PCI_ALLOC(bp->t2, &bp->t2_mapping, SRC_T2_SZ); + bp->t2 = BNX2X_PCI_ALLOC(&bp->t2_mapping, SRC_T2_SZ); + if (!bp->t2) + goto alloc_mem_err; + } - BNX2X_PCI_ALLOC(bp->def_status_blk, &bp->def_status_blk_mapping, - sizeof(struct host_sp_status_block)); + bp->def_status_blk = BNX2X_PCI_ALLOC(&bp->def_status_blk_mapping, + sizeof(struct host_sp_status_block)); + if (!bp->def_status_blk) + goto alloc_mem_err; - BNX2X_PCI_ALLOC(bp->slowpath, &bp->slowpath_mapping, - sizeof(struct bnx2x_slowpath)); + bp->slowpath = BNX2X_PCI_ALLOC(&bp->slowpath_mapping, + sizeof(struct bnx2x_slowpath)); + if (!bp->slowpath) + goto alloc_mem_err; /* Allocate memory for CDU context: * This memory is allocated separately and not in the generic ILT @@ -8050,12 +8075,16 @@ int bnx2x_alloc_mem(struct bnx2x *bp) for (i = 0, allocated = 0; allocated < context_size; i++) { bp->context[i].size = min(CDU_ILT_PAGE_SZ, (context_size - allocated)); - BNX2X_PCI_ALLOC(bp->context[i].vcxt, - &bp->context[i].cxt_mapping, - bp->context[i].size); + bp->context[i].vcxt = BNX2X_PCI_ALLOC(&bp->context[i].cxt_mapping, + bp->context[i].size); + if (!bp->context[i].vcxt) + goto alloc_mem_err; allocated += bp->context[i].size; } - BNX2X_ALLOC(bp->ilt->lines, sizeof(struct ilt_line) * ILT_MAX_LINES); + bp->ilt->lines = kcalloc(ILT_MAX_LINES, sizeof(struct ilt_line), + GFP_KERNEL); + if (!bp->ilt->lines) + goto alloc_mem_err; if (bnx2x_ilt_mem_op(bp, ILT_MEMOP_ALLOC)) goto alloc_mem_err; @@ -8064,11 +8093,15 @@ int bnx2x_alloc_mem(struct bnx2x *bp) goto alloc_mem_err; /* Slow path ring */ - BNX2X_PCI_ALLOC(bp->spq, &bp->spq_mapping, BCM_PAGE_SIZE); + bp->spq = BNX2X_PCI_ALLOC(&bp->spq_mapping, BCM_PAGE_SIZE); + if (!bp->spq) + goto alloc_mem_err; /* EQ */ - BNX2X_PCI_ALLOC(bp->eq_ring, &bp->eq_mapping, - BCM_PAGE_SIZE * NUM_EQ_PAGES); + bp->eq_ring = BNX2X_PCI_ALLOC(&bp->eq_mapping, + BCM_PAGE_SIZE * NUM_EQ_PAGES); + if (!bp->eq_ring) + goto alloc_mem_err; return 0; @@ -11771,6 +11804,8 @@ static int bnx2x_init_bp(struct bnx2x *bp) bp->disable_tpa = disable_tpa; bp->disable_tpa |= IS_MF_STORAGE_SD(bp) || IS_MF_FCOE_AFEX(bp); + /* Reduce memory usage in kdump environment by disabling TPA */ + bp->disable_tpa |= reset_devices; /* Set TPA flags */ if (bp->disable_tpa) { @@ -11942,7 +11977,7 @@ static int bnx2x_init_mcast_macs_list(struct bnx2x *bp, { int mc_count = netdev_mc_count(bp->dev); struct bnx2x_mcast_list_elem *mc_mac = - kzalloc(sizeof(*mc_mac) * mc_count, GFP_ATOMIC); + kcalloc(mc_count, sizeof(*mc_mac), GFP_ATOMIC); struct netdev_hw_addr *ha; if (!mc_mac) @@ -12064,11 +12099,8 @@ static void bnx2x_set_rx_mode(struct net_device *dev) return; } else { /* Schedule an SP task to handle rest of change */ - DP(NETIF_MSG_IFUP, "Scheduling an Rx mode change\n"); - smp_mb__before_clear_bit(); - set_bit(BNX2X_SP_RTNL_RX_MODE, &bp->sp_rtnl_state); - smp_mb__after_clear_bit(); - schedule_delayed_work(&bp->sp_rtnl_task, 0); + bnx2x_schedule_sp_rtnl(bp, BNX2X_SP_RTNL_RX_MODE, + NETIF_MSG_IFUP); } } @@ -12101,11 +12133,8 @@ void bnx2x_set_rx_mode_inner(struct bnx2x *bp) /* configuring mcast to a vf involves sleeping (when we * wait for the pf's response). */ - smp_mb__before_clear_bit(); - set_bit(BNX2X_SP_RTNL_VFPF_MCAST, - &bp->sp_rtnl_state); - smp_mb__after_clear_bit(); - schedule_delayed_work(&bp->sp_rtnl_task, 0); + bnx2x_schedule_sp_rtnl(bp, + BNX2X_SP_RTNL_VFPF_MCAST, 0); } } diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c index 0fb6ff2ac8e3..31297266b743 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c @@ -2277,11 +2277,11 @@ static int bnx2x_set_rx_mode_e2(struct bnx2x *bp, data->header.rule_cnt, p->rx_accept_flags, p->tx_accept_flags); - /* No need for an explicit memory barrier here as long we would - * need to ensure the ordering of writing to the SPQ element + /* No need for an explicit memory barrier here as long as we + * ensure the ordering of writing to the SPQ element * and updating of the SPQ producer which involves a memory - * read and we will have to put a full memory barrier there - * (inside bnx2x_sp_post()). + * read. If the memory read is removed we will have to put a + * full memory barrier there (inside bnx2x_sp_post()). */ /* Send a ramrod */ @@ -2982,11 +2982,11 @@ static int bnx2x_mcast_setup_e2(struct bnx2x *bp, raw->clear_pending(raw); return 0; } else { - /* No need for an explicit memory barrier here as long we would - * need to ensure the ordering of writing to the SPQ element + /* No need for an explicit memory barrier here as long as we + * ensure the ordering of writing to the SPQ element * and updating of the SPQ producer which involves a memory - * read and we will have to put a full memory barrier there - * (inside bnx2x_sp_post()). + * read. If the memory read is removed we will have to put a + * full memory barrier there (inside bnx2x_sp_post()). */ /* Send a ramrod */ @@ -3466,11 +3466,11 @@ static int bnx2x_mcast_setup_e1(struct bnx2x *bp, raw->clear_pending(raw); return 0; } else { - /* No need for an explicit memory barrier here as long we would - * need to ensure the ordering of writing to the SPQ element + /* No need for an explicit memory barrier here as long as we + * ensure the ordering of writing to the SPQ element * and updating of the SPQ producer which involves a memory - * read and we will have to put a full memory barrier there - * (inside bnx2x_sp_post()). + * read. If the memory read is removed we will have to put a + * full memory barrier there (inside bnx2x_sp_post()). */ /* Send a ramrod */ @@ -4091,11 +4091,11 @@ static int bnx2x_setup_rss(struct bnx2x *bp, data->capabilities |= ETH_RSS_UPDATE_RAMROD_DATA_UPDATE_RSS_KEY; } - /* No need for an explicit memory barrier here as long we would - * need to ensure the ordering of writing to the SPQ element + /* No need for an explicit memory barrier here as long as we + * ensure the ordering of writing to the SPQ element * and updating of the SPQ producer which involves a memory - * read and we will have to put a full memory barrier there - * (inside bnx2x_sp_post()). + * read. If the memory read is removed we will have to put a + * full memory barrier there (inside bnx2x_sp_post()). */ /* Send a ramrod */ @@ -4158,16 +4158,6 @@ void bnx2x_init_rss_config_obj(struct bnx2x *bp, rss_obj->config_rss = bnx2x_setup_rss; } -int validate_vlan_mac(struct bnx2x *bp, - struct bnx2x_vlan_mac_obj *vlan_mac) -{ - if (!vlan_mac->get_n_elements) { - BNX2X_ERR("vlan mac object was not intialized\n"); - return -EINVAL; - } - return 0; -} - /********************** Queue state object ***********************************/ /** @@ -4587,13 +4577,12 @@ static inline int bnx2x_q_send_setup_e1x(struct bnx2x *bp, /* Fill the ramrod data */ bnx2x_q_fill_setup_data_cmn(bp, params, rdata); - /* No need for an explicit memory barrier here as long we would - * need to ensure the ordering of writing to the SPQ element + /* No need for an explicit memory barrier here as long as we + * ensure the ordering of writing to the SPQ element * and updating of the SPQ producer which involves a memory - * read and we will have to put a full memory barrier there - * (inside bnx2x_sp_post()). + * read. If the memory read is removed we will have to put a + * full memory barrier there (inside bnx2x_sp_post()). */ - return bnx2x_sp_post(bp, ramrod, o->cids[BNX2X_PRIMARY_CID_INDEX], U64_HI(data_mapping), U64_LO(data_mapping), ETH_CONNECTION_TYPE); @@ -4615,13 +4604,12 @@ static inline int bnx2x_q_send_setup_e2(struct bnx2x *bp, bnx2x_q_fill_setup_data_cmn(bp, params, rdata); bnx2x_q_fill_setup_data_e2(bp, params, rdata); - /* No need for an explicit memory barrier here as long we would - * need to ensure the ordering of writing to the SPQ element + /* No need for an explicit memory barrier here as long as we + * ensure the ordering of writing to the SPQ element * and updating of the SPQ producer which involves a memory - * read and we will have to put a full memory barrier there - * (inside bnx2x_sp_post()). + * read. If the memory read is removed we will have to put a + * full memory barrier there (inside bnx2x_sp_post()). */ - return bnx2x_sp_post(bp, ramrod, o->cids[BNX2X_PRIMARY_CID_INDEX], U64_HI(data_mapping), U64_LO(data_mapping), ETH_CONNECTION_TYPE); @@ -4659,13 +4647,12 @@ static inline int bnx2x_q_send_setup_tx_only(struct bnx2x *bp, o->cids[cid_index], rdata->general.client_id, rdata->general.sp_client_id, rdata->general.cos); - /* No need for an explicit memory barrier here as long we would - * need to ensure the ordering of writing to the SPQ element + /* No need for an explicit memory barrier here as long as we + * ensure the ordering of writing to the SPQ element * and updating of the SPQ producer which involves a memory - * read and we will have to put a full memory barrier there - * (inside bnx2x_sp_post()). + * read. If the memory read is removed we will have to put a + * full memory barrier there (inside bnx2x_sp_post()). */ - return bnx2x_sp_post(bp, ramrod, o->cids[cid_index], U64_HI(data_mapping), U64_LO(data_mapping), ETH_CONNECTION_TYPE); @@ -4760,13 +4747,12 @@ static inline int bnx2x_q_send_update(struct bnx2x *bp, /* Fill the ramrod data */ bnx2x_q_fill_update_data(bp, o, update_params, rdata); - /* No need for an explicit memory barrier here as long we would - * need to ensure the ordering of writing to the SPQ element + /* No need for an explicit memory barrier here as long as we + * ensure the ordering of writing to the SPQ element * and updating of the SPQ producer which involves a memory - * read and we will have to put a full memory barrier there - * (inside bnx2x_sp_post()). + * read. If the memory read is removed we will have to put a + * full memory barrier there (inside bnx2x_sp_post()). */ - return bnx2x_sp_post(bp, RAMROD_CMD_ID_ETH_CLIENT_UPDATE, o->cids[cid_index], U64_HI(data_mapping), U64_LO(data_mapping), ETH_CONNECTION_TYPE); @@ -4813,11 +4799,62 @@ static inline int bnx2x_q_send_activate(struct bnx2x *bp, return bnx2x_q_send_update(bp, params); } +static void bnx2x_q_fill_update_tpa_data(struct bnx2x *bp, + struct bnx2x_queue_sp_obj *obj, + struct bnx2x_queue_update_tpa_params *params, + struct tpa_update_ramrod_data *data) +{ + data->client_id = obj->cl_id; + data->complete_on_both_clients = params->complete_on_both_clients; + data->dont_verify_rings_pause_thr_flg = + params->dont_verify_thr; + data->max_agg_size = cpu_to_le16(params->max_agg_sz); + data->max_sges_for_packet = params->max_sges_pkt; + data->max_tpa_queues = params->max_tpa_queues; + data->sge_buff_size = cpu_to_le16(params->sge_buff_sz); + data->sge_page_base_hi = cpu_to_le32(U64_HI(params->sge_map)); + data->sge_page_base_lo = cpu_to_le32(U64_LO(params->sge_map)); + data->sge_pause_thr_high = cpu_to_le16(params->sge_pause_thr_high); + data->sge_pause_thr_low = cpu_to_le16(params->sge_pause_thr_low); + data->tpa_mode = params->tpa_mode; + data->update_ipv4 = params->update_ipv4; + data->update_ipv6 = params->update_ipv6; +} + static inline int bnx2x_q_send_update_tpa(struct bnx2x *bp, struct bnx2x_queue_state_params *params) { - /* TODO: Not implemented yet. */ - return -1; + struct bnx2x_queue_sp_obj *o = params->q_obj; + struct tpa_update_ramrod_data *rdata = + (struct tpa_update_ramrod_data *)o->rdata; + dma_addr_t data_mapping = o->rdata_mapping; + struct bnx2x_queue_update_tpa_params *update_tpa_params = + ¶ms->params.update_tpa; + u16 type; + + /* Clear the ramrod data */ + memset(rdata, 0, sizeof(*rdata)); + + /* Fill the ramrod data */ + bnx2x_q_fill_update_tpa_data(bp, o, update_tpa_params, rdata); + + /* Add the function id inside the type, so that sp post function + * doesn't automatically add the PF func-id, this is required + * for operations done by PFs on behalf of their VFs + */ + type = ETH_CONNECTION_TYPE | + ((o->func_id) << SPE_HDR_FUNCTION_ID_SHIFT); + + /* No need for an explicit memory barrier here as long as we + * ensure the ordering of writing to the SPQ element + * and updating of the SPQ producer which involves a memory + * read. If the memory read is removed we will have to put a + * full memory barrier there (inside bnx2x_sp_post()). + */ + return bnx2x_sp_post(bp, RAMROD_CMD_ID_ETH_TPA_UPDATE, + o->cids[BNX2X_PRIMARY_CID_INDEX], + U64_HI(data_mapping), + U64_LO(data_mapping), type); } static inline int bnx2x_q_send_halt(struct bnx2x *bp, @@ -5647,6 +5684,12 @@ static inline int bnx2x_func_send_switch_update(struct bnx2x *bp, rdata->tx_switch_suspend = switch_update_params->suspend; rdata->echo = SWITCH_UPDATE; + /* No need for an explicit memory barrier here as long as we + * ensure the ordering of writing to the SPQ element + * and updating of the SPQ producer which involves a memory + * read. If the memory read is removed we will have to put a + * full memory barrier there (inside bnx2x_sp_post()). + */ return bnx2x_sp_post(bp, RAMROD_CMD_ID_COMMON_FUNCTION_UPDATE, 0, U64_HI(data_mapping), U64_LO(data_mapping), NONE_CONNECTION_TYPE); @@ -5674,11 +5717,11 @@ static inline int bnx2x_func_send_afex_update(struct bnx2x *bp, rdata->allowed_priorities = afex_update_params->allowed_priorities; rdata->echo = AFEX_UPDATE; - /* No need for an explicit memory barrier here as long we would - * need to ensure the ordering of writing to the SPQ element - * and updating of the SPQ producer which involves a memory - * read and we will have to put a full memory barrier there - * (inside bnx2x_sp_post()). + /* No need for an explicit memory barrier here as long as we + * ensure the ordering of writing to the SPQ element + * and updating of the SPQ producer which involves a memory + * read. If the memory read is removed we will have to put a + * full memory barrier there (inside bnx2x_sp_post()). */ DP(BNX2X_MSG_SP, "afex: sending func_update vif_id 0x%x dvlan 0x%x prio 0x%x\n", @@ -5763,6 +5806,12 @@ static inline int bnx2x_func_send_tx_start(struct bnx2x *bp, rdata->traffic_type_to_priority_cos[i] = tx_start_params->traffic_type_to_priority_cos[i]; + /* No need for an explicit memory barrier here as long as we + * ensure the ordering of writing to the SPQ element + * and updating of the SPQ producer which involves a memory + * read. If the memory read is removed we will have to put a + * full memory barrier there (inside bnx2x_sp_post()). + */ return bnx2x_sp_post(bp, RAMROD_CMD_ID_COMMON_START_TRAFFIC, 0, U64_HI(data_mapping), U64_LO(data_mapping), NONE_CONNECTION_TYPE); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h index 00d7f214a40a..80f6c790ed88 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h @@ -893,6 +893,24 @@ struct bnx2x_queue_update_params { u8 cid_index; }; +struct bnx2x_queue_update_tpa_params { + dma_addr_t sge_map; + u8 update_ipv4; + u8 update_ipv6; + u8 max_tpa_queues; + u8 max_sges_pkt; + u8 complete_on_both_clients; + u8 dont_verify_thr; + u8 tpa_mode; + u8 _pad; + + u16 sge_buff_sz; + u16 max_agg_sz; + + u16 sge_pause_thr_low; + u16 sge_pause_thr_high; +}; + struct rxq_pause_params { u16 bd_th_lo; u16 bd_th_hi; @@ -987,6 +1005,7 @@ struct bnx2x_queue_state_params { /* Params according to the current command */ union { struct bnx2x_queue_update_params update; + struct bnx2x_queue_update_tpa_params update_tpa; struct bnx2x_queue_setup_params setup; struct bnx2x_queue_init_params init; struct bnx2x_queue_setup_tx_only_params tx_only; @@ -1403,6 +1422,4 @@ int bnx2x_config_rss(struct bnx2x *bp, void bnx2x_get_rss_ind_table(struct bnx2x_rss_config_obj *rss_obj, u8 *ind_table); -int validate_vlan_mac(struct bnx2x *bp, - struct bnx2x_vlan_mac_obj *vlan_mac); #endif /* BNX2X_SP_VERBS */ diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c index aec5ef2ed7ce..61e6f606d8a4 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c @@ -102,6 +102,21 @@ static void bnx2x_vf_igu_ack_sb(struct bnx2x *bp, struct bnx2x_virtf *vf, mmiowb(); barrier(); } + +static bool bnx2x_validate_vf_sp_objs(struct bnx2x *bp, + struct bnx2x_virtf *vf, + bool print_err) +{ + if (!bnx2x_leading_vfq(vf, sp_initialized)) { + if (print_err) + BNX2X_ERR("Slowpath objects not yet initialized!\n"); + else + DP(BNX2X_MSG_IOV, "Slowpath objects not yet initialized!\n"); + return false; + } + return true; +} + /* VFOP - VF slow-path operation support */ #define BNX2X_VFOP_FILTER_ADD_CNT_MAX 0x10000 @@ -176,6 +191,11 @@ enum bnx2x_vfop_rss_state { BNX2X_VFOP_RSS_DONE }; +enum bnx2x_vfop_tpa_state { + BNX2X_VFOP_TPA_CONFIG, + BNX2X_VFOP_TPA_DONE +}; + #define bnx2x_vfop_reset_wq(vf) atomic_set(&vf->op_in_progress, 0) void bnx2x_vfop_qctor_dump_tx(struct bnx2x *bp, struct bnx2x_virtf *vf, @@ -716,7 +736,6 @@ static int bnx2x_vfop_mac_delall_cmd(struct bnx2x *bp, int qid, bool drv_only) { struct bnx2x_vfop *vfop = bnx2x_vfop_add(bp, vf); - int rc; if (vfop) { struct bnx2x_vfop_args_filters filters = { @@ -736,9 +755,6 @@ static int bnx2x_vfop_mac_delall_cmd(struct bnx2x *bp, bnx2x_vfop_mac_prep_ramrod(ramrod, &flags); /* set object */ - rc = validate_vlan_mac(bp, &bnx2x_vfq(vf, qid, mac_obj)); - if (rc) - return rc; ramrod->vlan_mac_obj = &bnx2x_vfq(vf, qid, mac_obj); /* set extra args */ @@ -758,9 +774,12 @@ int bnx2x_vfop_mac_list_cmd(struct bnx2x *bp, struct bnx2x_vfop_filters *macs, int qid, bool drv_only) { - struct bnx2x_vfop *vfop = bnx2x_vfop_add(bp, vf); - int rc; + struct bnx2x_vfop *vfop; + + if (!bnx2x_validate_vf_sp_objs(bp, vf, true)) + return -EINVAL; + vfop = bnx2x_vfop_add(bp, vf); if (vfop) { struct bnx2x_vfop_args_filters filters = { .multi_filter = macs, @@ -782,9 +801,6 @@ int bnx2x_vfop_mac_list_cmd(struct bnx2x *bp, bnx2x_vfop_mac_prep_ramrod(ramrod, &flags); /* set object */ - rc = validate_vlan_mac(bp, &bnx2x_vfq(vf, qid, mac_obj)); - if (rc) - return rc; ramrod->vlan_mac_obj = &bnx2x_vfq(vf, qid, mac_obj); /* set extra args */ @@ -804,9 +820,12 @@ static int bnx2x_vfop_vlan_set_cmd(struct bnx2x *bp, struct bnx2x_vfop_cmd *cmd, int qid, u16 vid, bool add) { - struct bnx2x_vfop *vfop = bnx2x_vfop_add(bp, vf); - int rc; + struct bnx2x_vfop *vfop; + if (!bnx2x_validate_vf_sp_objs(bp, vf, true)) + return -EINVAL; + + vfop = bnx2x_vfop_add(bp, vf); if (vfop) { struct bnx2x_vfop_args_filters filters = { .multi_filter = NULL, /* single command */ @@ -826,9 +845,6 @@ static int bnx2x_vfop_vlan_set_cmd(struct bnx2x *bp, ramrod->user_req.u.vlan.vlan = vid; /* set object */ - rc = validate_vlan_mac(bp, &bnx2x_vfq(vf, qid, vlan_obj)); - if (rc) - return rc; ramrod->vlan_mac_obj = &bnx2x_vfq(vf, qid, vlan_obj); /* set extra args */ @@ -848,7 +864,6 @@ static int bnx2x_vfop_vlan_delall_cmd(struct bnx2x *bp, int qid, bool drv_only) { struct bnx2x_vfop *vfop = bnx2x_vfop_add(bp, vf); - int rc; if (vfop) { struct bnx2x_vfop_args_filters filters = { @@ -868,9 +883,6 @@ static int bnx2x_vfop_vlan_delall_cmd(struct bnx2x *bp, bnx2x_vfop_vlan_mac_prep_ramrod(ramrod, &flags); /* set object */ - rc = validate_vlan_mac(bp, &bnx2x_vfq(vf, qid, vlan_obj)); - if (rc) - return rc; ramrod->vlan_mac_obj = &bnx2x_vfq(vf, qid, vlan_obj); /* set extra args */ @@ -890,9 +902,12 @@ int bnx2x_vfop_vlan_list_cmd(struct bnx2x *bp, struct bnx2x_vfop_filters *vlans, int qid, bool drv_only) { - struct bnx2x_vfop *vfop = bnx2x_vfop_add(bp, vf); - int rc; + struct bnx2x_vfop *vfop; + if (!bnx2x_validate_vf_sp_objs(bp, vf, true)) + return -EINVAL; + + vfop = bnx2x_vfop_add(bp, vf); if (vfop) { struct bnx2x_vfop_args_filters filters = { .multi_filter = vlans, @@ -911,9 +926,6 @@ int bnx2x_vfop_vlan_list_cmd(struct bnx2x *bp, bnx2x_vfop_vlan_mac_prep_ramrod(ramrod, &flags); /* set object */ - rc = validate_vlan_mac(bp, &bnx2x_vfq(vf, qid, vlan_obj)); - if (rc) - return rc; ramrod->vlan_mac_obj = &bnx2x_vfq(vf, qid, vlan_obj); /* set extra args */ @@ -971,11 +983,8 @@ op_err: op_done: case BNX2X_VFOP_QSETUP_DONE: vf->cfg_flags |= VF_CFG_VLAN; - smp_mb__before_clear_bit(); - set_bit(BNX2X_SP_RTNL_HYPERVISOR_VLAN, - &bp->sp_rtnl_state); - smp_mb__after_clear_bit(); - schedule_delayed_work(&bp->sp_rtnl_task, 0); + bnx2x_schedule_sp_rtnl(bp, BNX2X_SP_RTNL_HYPERVISOR_VLAN, + BNX2X_MSG_IOV); bnx2x_vfop_end(bp, vf, vfop); return; default: @@ -1025,34 +1034,20 @@ static void bnx2x_vfop_qflr(struct bnx2x *bp, struct bnx2x_virtf *vf) /* vlan-clear-all: driver-only, don't consume credit */ vfop->state = BNX2X_VFOP_QFLR_CLR_MAC; - if (!validate_vlan_mac(bp, &bnx2x_vfq(vf, qid, vlan_obj))) { - /* the vlan_mac vfop will re-schedule us */ - vfop->rc = bnx2x_vfop_vlan_delall_cmd(bp, vf, &cmd, - qid, true); - if (vfop->rc) - goto op_err; - return; - - } else { - /* need to reschedule ourselves */ - bnx2x_vfop_finalize(vf, vfop->rc, VFOP_CONT); - } + /* the vlan_mac vfop will re-schedule us */ + vfop->rc = bnx2x_vfop_vlan_delall_cmd(bp, vf, &cmd, qid, true); + if (vfop->rc) + goto op_err; + return; case BNX2X_VFOP_QFLR_CLR_MAC: /* mac-clear-all: driver only consume credit */ vfop->state = BNX2X_VFOP_QFLR_TERMINATE; - if (!validate_vlan_mac(bp, &bnx2x_vfq(vf, qid, mac_obj))) { - /* the vlan_mac vfop will re-schedule us */ - vfop->rc = bnx2x_vfop_mac_delall_cmd(bp, vf, &cmd, - qid, true); - if (vfop->rc) - goto op_err; - return; - - } else { - /* need to reschedule ourselves */ - bnx2x_vfop_finalize(vf, vfop->rc, VFOP_CONT); - } + /* the vlan_mac vfop will re-schedule us */ + vfop->rc = bnx2x_vfop_mac_delall_cmd(bp, vf, &cmd, qid, true); + if (vfop->rc) + goto op_err; + return; case BNX2X_VFOP_QFLR_TERMINATE: qstate = &vfop->op_p->qctor.qstate; @@ -1095,8 +1090,13 @@ static int bnx2x_vfop_qflr_cmd(struct bnx2x *bp, if (vfop) { vfop->args.qx.qid = qid; - bnx2x_vfop_opset(BNX2X_VFOP_QFLR_CLR_VLAN, - bnx2x_vfop_qflr, cmd->done); + if ((qid == LEADING_IDX) && + bnx2x_validate_vf_sp_objs(bp, vf, false)) + bnx2x_vfop_opset(BNX2X_VFOP_QFLR_CLR_VLAN, + bnx2x_vfop_qflr, cmd->done); + else + bnx2x_vfop_opset(BNX2X_VFOP_QFLR_TERMINATE, + bnx2x_vfop_qflr, cmd->done); return bnx2x_vfop_transition(bp, vf, bnx2x_vfop_qflr, cmd->block); } @@ -1310,7 +1310,10 @@ static void bnx2x_vfop_qdown(struct bnx2x *bp, struct bnx2x_virtf *vf) switch (state) { case BNX2X_VFOP_QTEARDOWN_RXMODE: /* Drop all */ - vfop->state = BNX2X_VFOP_QTEARDOWN_CLR_VLAN; + if (bnx2x_validate_vf_sp_objs(bp, vf, true)) + vfop->state = BNX2X_VFOP_QTEARDOWN_CLR_VLAN; + else + vfop->state = BNX2X_VFOP_QTEARDOWN_QDTOR; vfop->rc = bnx2x_vfop_rxmode_cmd(bp, vf, &cmd, qid, 0); if (vfop->rc) goto op_err; @@ -1446,12 +1449,12 @@ static void bnx2x_vf_igu_reset(struct bnx2x *bp, struct bnx2x_virtf *vf) if (vf->cfg_flags & VF_CFG_INT_SIMD) val |= IGU_VF_CONF_SINGLE_ISR_EN; val &= ~IGU_VF_CONF_PARENT_MASK; - val |= BP_FUNC(bp) << IGU_VF_CONF_PARENT_SHIFT; /* parent PF */ + val |= (BP_ABS_FUNC(bp) >> 1) << IGU_VF_CONF_PARENT_SHIFT; REG_WR(bp, IGU_REG_VF_CONFIGURATION, val); DP(BNX2X_MSG_IOV, - "value in IGU_REG_VF_CONFIGURATION of vf %d after write %x\n", - vf->abs_vfid, REG_RD(bp, IGU_REG_VF_CONFIGURATION)); + "value in IGU_REG_VF_CONFIGURATION of vf %d after write is 0x%08x\n", + vf->abs_vfid, val); bnx2x_pretend_func(bp, BP_ABS_FUNC(bp)); @@ -2117,7 +2120,9 @@ int bnx2x_iov_alloc_mem(struct bnx2x *bp) cxt->size = min_t(size_t, tot_size, CDU_ILT_PAGE_SZ); if (cxt->size) { - BNX2X_PCI_ALLOC(cxt->addr, &cxt->mapping, cxt->size); + cxt->addr = BNX2X_PCI_ALLOC(&cxt->mapping, cxt->size); + if (!cxt->addr) + goto alloc_mem_err; } else { cxt->addr = NULL; cxt->mapping = 0; @@ -2127,20 +2132,28 @@ int bnx2x_iov_alloc_mem(struct bnx2x *bp) /* allocate vfs ramrods dma memory - client_init and set_mac */ tot_size = BNX2X_NR_VIRTFN(bp) * sizeof(struct bnx2x_vf_sp); - BNX2X_PCI_ALLOC(BP_VFDB(bp)->sp_dma.addr, &BP_VFDB(bp)->sp_dma.mapping, - tot_size); + BP_VFDB(bp)->sp_dma.addr = BNX2X_PCI_ALLOC(&BP_VFDB(bp)->sp_dma.mapping, + tot_size); + if (!BP_VFDB(bp)->sp_dma.addr) + goto alloc_mem_err; BP_VFDB(bp)->sp_dma.size = tot_size; /* allocate mailboxes */ tot_size = BNX2X_NR_VIRTFN(bp) * MBX_MSG_ALIGNED_SIZE; - BNX2X_PCI_ALLOC(BP_VF_MBX_DMA(bp)->addr, &BP_VF_MBX_DMA(bp)->mapping, - tot_size); + BP_VF_MBX_DMA(bp)->addr = BNX2X_PCI_ALLOC(&BP_VF_MBX_DMA(bp)->mapping, + tot_size); + if (!BP_VF_MBX_DMA(bp)->addr) + goto alloc_mem_err; + BP_VF_MBX_DMA(bp)->size = tot_size; /* allocate local bulletin boards */ tot_size = BNX2X_NR_VIRTFN(bp) * BULLETIN_CONTENT_SIZE; - BNX2X_PCI_ALLOC(BP_VF_BULLETIN_DMA(bp)->addr, - &BP_VF_BULLETIN_DMA(bp)->mapping, tot_size); + BP_VF_BULLETIN_DMA(bp)->addr = BNX2X_PCI_ALLOC(&BP_VF_BULLETIN_DMA(bp)->mapping, + tot_size); + if (!BP_VF_BULLETIN_DMA(bp)->addr) + goto alloc_mem_err; + BP_VF_BULLETIN_DMA(bp)->size = tot_size; return 0; @@ -2166,6 +2179,9 @@ static void bnx2x_vfq_init(struct bnx2x *bp, struct bnx2x_virtf *vf, bnx2x_vf_sp_map(bp, vf, q_data), q_type); + /* sp indication is set only when vlan/mac/etc. are initialized */ + q->sp_initialized = false; + DP(BNX2X_MSG_IOV, "initialized vf %d's queue object. func id set to %d. cid set to 0x%x\n", vf->abs_vfid, q->sp_obj.func_id, q->cid); @@ -2527,10 +2543,10 @@ void bnx2x_iov_adjust_stats_req(struct bnx2x *bp) first_queue_query_index = BNX2X_FIRST_QUEUE_QUERY_IDX - (is_fcoe ? 0 : 1); - DP(BNX2X_MSG_IOV, - "BNX2X_NUM_ETH_QUEUES %d, is_fcoe %d, first_queue_query_index %d => determined the last non virtual statistics query index is %d. Will add queries on top of that\n", - BNX2X_NUM_ETH_QUEUES(bp), is_fcoe, first_queue_query_index, - first_queue_query_index + num_queues_req); + DP_AND((BNX2X_MSG_IOV | BNX2X_MSG_STATS), + "BNX2X_NUM_ETH_QUEUES %d, is_fcoe %d, first_queue_query_index %d => determined the last non virtual statistics query index is %d. Will add queries on top of that\n", + BNX2X_NUM_ETH_QUEUES(bp), is_fcoe, first_queue_query_index, + first_queue_query_index + num_queues_req); cur_data_offset = bp->fw_stats_data_mapping + offsetof(struct bnx2x_fw_stats_data, queue_stats) + @@ -2544,9 +2560,9 @@ void bnx2x_iov_adjust_stats_req(struct bnx2x *bp) struct bnx2x_virtf *vf = BP_VF(bp, i); if (vf->state != VF_ENABLED) { - DP(BNX2X_MSG_IOV, - "vf %d not enabled so no stats for it\n", - vf->abs_vfid); + DP_AND((BNX2X_MSG_IOV | BNX2X_MSG_STATS), + "vf %d not enabled so no stats for it\n", + vf->abs_vfid); continue; } @@ -2597,7 +2613,8 @@ void bnx2x_iov_sp_task(struct bnx2x *bp) /* Iterate over all VFs and invoke state transition for VFs with * 'in-progress' slow-path operations */ - DP(BNX2X_MSG_IOV, "searching for pending vf operations\n"); + DP_AND((BNX2X_MSG_IOV | BNX2X_MSG_SP), + "searching for pending vf operations\n"); for_each_vf(bp, i) { struct bnx2x_virtf *vf = BP_VF(bp, i); @@ -3046,6 +3063,83 @@ int bnx2x_vfop_rss_cmd(struct bnx2x *bp, return -ENOMEM; } +/* VFOP tpa update, send update on all queues */ +static void bnx2x_vfop_tpa(struct bnx2x *bp, struct bnx2x_virtf *vf) +{ + struct bnx2x_vfop *vfop = bnx2x_vfop_cur(bp, vf); + struct bnx2x_vfop_args_tpa *tpa_args = &vfop->args.tpa; + enum bnx2x_vfop_tpa_state state = vfop->state; + + bnx2x_vfop_reset_wq(vf); + + if (vfop->rc < 0) + goto op_err; + + DP(BNX2X_MSG_IOV, "vf[%d:%d] STATE: %d\n", + vf->abs_vfid, tpa_args->qid, + state); + + switch (state) { + case BNX2X_VFOP_TPA_CONFIG: + + if (tpa_args->qid < vf_rxq_count(vf)) { + struct bnx2x_queue_state_params *qstate = + &vf->op_params.qstate; + + qstate->q_obj = &bnx2x_vfq(vf, tpa_args->qid, sp_obj); + + /* The only thing that changes for the ramrod params + * between calls is the sge_map + */ + qstate->params.update_tpa.sge_map = + tpa_args->sge_map[tpa_args->qid]; + + DP(BNX2X_MSG_IOV, "sge_addr[%d] %08x:%08x\n", + tpa_args->qid, + U64_HI(qstate->params.update_tpa.sge_map), + U64_LO(qstate->params.update_tpa.sge_map)); + qstate->cmd = BNX2X_Q_CMD_UPDATE_TPA; + vfop->rc = bnx2x_queue_state_change(bp, qstate); + + tpa_args->qid++; + bnx2x_vfop_finalize(vf, vfop->rc, VFOP_CONT); + } + vfop->state = BNX2X_VFOP_TPA_DONE; + vfop->rc = 0; + bnx2x_vfop_finalize(vf, vfop->rc, VFOP_DONE); +op_err: + BNX2X_ERR("TPA update error: rc %d\n", vfop->rc); +op_done: + case BNX2X_VFOP_TPA_DONE: + bnx2x_vfop_end(bp, vf, vfop); + return; + default: + bnx2x_vfop_default(state); + } +op_pending: + return; +} + +int bnx2x_vfop_tpa_cmd(struct bnx2x *bp, + struct bnx2x_virtf *vf, + struct bnx2x_vfop_cmd *cmd, + struct vfpf_tpa_tlv *tpa_tlv) +{ + struct bnx2x_vfop *vfop = bnx2x_vfop_add(bp, vf); + + if (vfop) { + vfop->args.qx.qid = 0; /* loop */ + memcpy(&vfop->args.tpa.sge_map, + tpa_tlv->tpa_client_info.sge_addr, + sizeof(vfop->args.tpa.sge_map)); + bnx2x_vfop_opset(BNX2X_VFOP_TPA_CONFIG, + bnx2x_vfop_tpa, cmd->done); + return bnx2x_vfop_transition(bp, vf, bnx2x_vfop_tpa, + cmd->block); + } + return -ENOMEM; +} + /* VF release ~ VF close + VF release-resources * Release is the ultimate SW shutdown and is called whenever an * irrecoverable error is encountered. @@ -3074,16 +3168,6 @@ static inline void bnx2x_vf_get_sbdf(struct bnx2x *bp, *sbdf = vf->devfn | (vf->bus << 8); } -static inline void bnx2x_vf_get_bars(struct bnx2x *bp, struct bnx2x_virtf *vf, - struct bnx2x_vf_bar_info *bar_info) -{ - int n; - - bar_info->nr_bars = bp->vfdb->sriov.nres; - for (n = 0; n < bar_info->nr_bars; n++) - bar_info->bars[n] = vf->bars[n]; -} - void bnx2x_lock_vf_pf_channel(struct bnx2x *bp, struct bnx2x_virtf *vf, enum channel_tlvs tlv) { @@ -3405,13 +3489,13 @@ int bnx2x_get_vf_config(struct net_device *dev, int vfidx, ivi->spoofchk = 1; /*always enabled */ if (vf->state == VF_ENABLED) { /* mac and vlan are in vlan_mac objects */ - if (validate_vlan_mac(bp, &bnx2x_leading_vfq(vf, mac_obj))) + if (bnx2x_validate_vf_sp_objs(bp, vf, false)) { mac_obj->get_n_elements(bp, mac_obj, 1, (u8 *)&ivi->mac, 0, ETH_ALEN); - if (validate_vlan_mac(bp, &bnx2x_leading_vfq(vf, vlan_obj))) vlan_obj->get_n_elements(bp, vlan_obj, 1, (u8 *)&ivi->vlan, 0, VLAN_HLEN); + } } else { /* mac */ if (bulletin->valid_bitmap & (1 << MAC_ADDR_VALID)) @@ -3485,17 +3569,17 @@ int bnx2x_set_vf_mac(struct net_device *dev, int vfidx, u8 *mac) q_logical_state == BNX2X_Q_LOGICAL_STATE_ACTIVE) { /* configure the mac in device on this vf's queue */ unsigned long ramrod_flags = 0; - struct bnx2x_vlan_mac_obj *mac_obj = - &bnx2x_leading_vfq(vf, mac_obj); + struct bnx2x_vlan_mac_obj *mac_obj; - rc = validate_vlan_mac(bp, &bnx2x_leading_vfq(vf, mac_obj)); - if (rc) - return rc; + /* User should be able to see failure reason in system logs */ + if (!bnx2x_validate_vf_sp_objs(bp, vf, true)) + return -EINVAL; /* must lock vfpf channel to protect against vf flows */ bnx2x_lock_vf_pf_channel(bp, vf, CHANNEL_TLV_PF_SET_MAC); /* remove existing eth macs */ + mac_obj = &bnx2x_leading_vfq(vf, mac_obj); rc = bnx2x_del_all_macs(bp, mac_obj, BNX2X_ETH_MAC, true); if (rc) { BNX2X_ERR("failed to delete eth macs\n"); @@ -3569,17 +3653,16 @@ int bnx2x_set_vf_vlan(struct net_device *dev, int vfidx, u16 vlan, u8 qos) BNX2X_Q_LOGICAL_STATE_ACTIVE) return rc; - /* configure the vlan in device on this vf's queue */ - vlan_obj = &bnx2x_leading_vfq(vf, vlan_obj); - rc = validate_vlan_mac(bp, &bnx2x_leading_vfq(vf, mac_obj)); - if (rc) - return rc; + /* User should be able to see error in system logs */ + if (!bnx2x_validate_vf_sp_objs(bp, vf, true)) + return -EINVAL; /* must lock vfpf channel to protect against vf flows */ bnx2x_lock_vf_pf_channel(bp, vf, CHANNEL_TLV_PF_SET_VLAN); /* remove existing vlans */ __set_bit(RAMROD_COMP_WAIT, &ramrod_flags); + vlan_obj = &bnx2x_leading_vfq(vf, vlan_obj); rc = vlan_obj->delete_all(bp, vlan_obj, &vlan_mac_flags, &ramrod_flags); if (rc) { @@ -3736,13 +3819,9 @@ void bnx2x_timer_sriov(struct bnx2x *bp) bnx2x_sample_bulletin(bp); /* if channel is down we need to self destruct */ - if (bp->old_bulletin.valid_bitmap & 1 << CHANNEL_DOWN) { - smp_mb__before_clear_bit(); - set_bit(BNX2X_SP_RTNL_VFPF_CHANNEL_DOWN, - &bp->sp_rtnl_state); - smp_mb__after_clear_bit(); - schedule_delayed_work(&bp->sp_rtnl_task, 0); - } + if (bp->old_bulletin.valid_bitmap & 1 << CHANNEL_DOWN) + bnx2x_schedule_sp_rtnl(bp, BNX2X_SP_RTNL_VFPF_CHANNEL_DOWN, + BNX2X_MSG_IOV); } void __iomem *bnx2x_vf_doorbells(struct bnx2x *bp) @@ -3756,12 +3835,16 @@ int bnx2x_vf_pci_alloc(struct bnx2x *bp) mutex_init(&bp->vf2pf_mutex); /* allocate vf2pf mailbox for vf to pf channel */ - BNX2X_PCI_ALLOC(bp->vf2pf_mbox, &bp->vf2pf_mbox_mapping, - sizeof(struct bnx2x_vf_mbx_msg)); + bp->vf2pf_mbox = BNX2X_PCI_ALLOC(&bp->vf2pf_mbox_mapping, + sizeof(struct bnx2x_vf_mbx_msg)); + if (!bp->vf2pf_mbox) + goto alloc_mem_err; /* allocate pf 2 vf bulletin board */ - BNX2X_PCI_ALLOC(bp->pf2vf_bulletin, &bp->pf2vf_bulletin_mapping, - sizeof(union pf_vf_bulletin)); + bp->pf2vf_bulletin = BNX2X_PCI_ALLOC(&bp->pf2vf_bulletin_mapping, + sizeof(union pf_vf_bulletin)); + if (!bp->pf2vf_bulletin) + goto alloc_mem_err; return 0; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h index d9fcca1b5a9d..b1dc751c6175 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h @@ -83,6 +83,7 @@ struct bnx2x_vf_queue { u16 index; u16 sb_idx; bool is_leading; + bool sp_initialized; }; /* struct bnx2x_vfop_qctor_params - prepare queue construction parameters: @@ -100,6 +101,7 @@ union bnx2x_vfop_params { struct bnx2x_mcast_ramrod_params mcast; struct bnx2x_config_rss_params rss; struct bnx2x_vfop_qctor_params qctor; + struct bnx2x_queue_state_params qstate; }; /* forward */ @@ -166,6 +168,11 @@ struct bnx2x_vfop_args_filters { atomic_t *credit; /* non NULL means 'don't consume credit' */ }; +struct bnx2x_vfop_args_tpa { + int qid; + dma_addr_t sge_map[PFVF_MAX_QUEUES_PER_VF]; +}; + union bnx2x_vfop_args { struct bnx2x_vfop_args_mcast mc_list; struct bnx2x_vfop_args_qctor qctor; @@ -173,6 +180,7 @@ union bnx2x_vfop_args { struct bnx2x_vfop_args_defvlan defvlan; struct bnx2x_vfop_args_qx qx; struct bnx2x_vfop_args_filters filters; + struct bnx2x_vfop_args_tpa tpa; }; struct bnx2x_vfop { @@ -704,6 +712,11 @@ int bnx2x_vfop_rss_cmd(struct bnx2x *bp, struct bnx2x_virtf *vf, struct bnx2x_vfop_cmd *cmd); +int bnx2x_vfop_tpa_cmd(struct bnx2x *bp, + struct bnx2x_virtf *vf, + struct bnx2x_vfop_cmd *cmd, + struct vfpf_tpa_tlv *tpa_tlv); + /* VF release ~ VF close + VF release-resources * * Release is the ultimate SW shutdown and is called whenever an diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c index 3fa6c2a2a5a9..1117ed7776b6 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c @@ -548,6 +548,7 @@ static void bnx2x_leading_vfq_init(struct bnx2x *bp, struct bnx2x_virtf *vf, vf->leading_rss = cl_id; q->is_leading = true; + q->sp_initialized = true; } /* ask the pf to open a queue for the vf */ @@ -1159,7 +1160,8 @@ static void bnx2x_vf_mbx_acquire_resp(struct bnx2x *bp, struct bnx2x_virtf *vf, resp->pfdev_info.db_size = bp->db_size; resp->pfdev_info.indices_per_sb = HC_SB_MAX_INDICES_E2; resp->pfdev_info.pf_cap = (PFVF_CAP_RSS | - /* PFVF_CAP_DHC |*/ PFVF_CAP_TPA); + PFVF_CAP_TPA | + PFVF_CAP_TPA_UPDATE); bnx2x_fill_fw_str(bp, resp->pfdev_info.fw_ver, sizeof(resp->pfdev_info.fw_ver)); @@ -1694,16 +1696,12 @@ static int bnx2x_vfop_mbx_qfilters_cmd(struct bnx2x *bp, return -ENOMEM; } -static void bnx2x_vf_mbx_set_q_filters(struct bnx2x *bp, - struct bnx2x_virtf *vf, - struct bnx2x_vf_mbx *mbx) +static int bnx2x_filters_validate_mac(struct bnx2x *bp, + struct bnx2x_virtf *vf, + struct vfpf_set_q_filters_tlv *filters) { - struct vfpf_set_q_filters_tlv *filters = &mbx->msg->req.set_q_filters; struct pf_vf_bulletin_content *bulletin = BP_VF_BULLETIN(bp, vf->index); - struct bnx2x_vfop_cmd cmd = { - .done = bnx2x_vf_mbx_resp, - .block = false, - }; + int rc = 0; /* if a mac was already set for this VF via the set vf mac ndo, we only * accept mac configurations of that mac. Why accept them at all? @@ -1716,6 +1714,7 @@ static void bnx2x_vf_mbx_set_q_filters(struct bnx2x *bp, BNX2X_ERR("VF[%d] requested the addition of multiple macs after set_vf_mac ndo was called\n", vf->abs_vfid); vf->op_rc = -EPERM; + rc = -EPERM; goto response; } @@ -1726,9 +1725,22 @@ static void bnx2x_vf_mbx_set_q_filters(struct bnx2x *bp, vf->abs_vfid); vf->op_rc = -EPERM; + rc = -EPERM; goto response; } } + +response: + return rc; +} + +static int bnx2x_filters_validate_vlan(struct bnx2x *bp, + struct bnx2x_virtf *vf, + struct vfpf_set_q_filters_tlv *filters) +{ + struct pf_vf_bulletin_content *bulletin = BP_VF_BULLETIN(bp, vf->index); + int rc = 0; + /* if vlan was set by hypervisor we don't allow guest to config vlan */ if (bulletin->valid_bitmap & 1 << VLAN_VALID) { int i; @@ -1740,13 +1752,36 @@ static void bnx2x_vf_mbx_set_q_filters(struct bnx2x *bp, BNX2X_ERR("VF[%d] attempted to configure vlan but one was already set by Hypervisor. Aborting request\n", vf->abs_vfid); vf->op_rc = -EPERM; + rc = -EPERM; goto response; } } } /* verify vf_qid */ - if (filters->vf_qid > vf_rxq_count(vf)) + if (filters->vf_qid > vf_rxq_count(vf)) { + rc = -EPERM; + goto response; + } + +response: + return rc; +} + +static void bnx2x_vf_mbx_set_q_filters(struct bnx2x *bp, + struct bnx2x_virtf *vf, + struct bnx2x_vf_mbx *mbx) +{ + struct vfpf_set_q_filters_tlv *filters = &mbx->msg->req.set_q_filters; + struct bnx2x_vfop_cmd cmd = { + .done = bnx2x_vf_mbx_resp, + .block = false, + }; + + if (bnx2x_filters_validate_mac(bp, vf, filters)) + goto response; + + if (bnx2x_filters_validate_vlan(bp, vf, filters)) goto response; DP(BNX2X_MSG_IOV, "VF[%d] Q_FILTERS: queue[%d]\n", @@ -1877,6 +1912,75 @@ mbx_resp: bnx2x_vf_mbx_resp(bp, vf); } +static int bnx2x_validate_tpa_params(struct bnx2x *bp, + struct vfpf_tpa_tlv *tpa_tlv) +{ + int rc = 0; + + if (tpa_tlv->tpa_client_info.max_sges_for_packet > + U_ETH_MAX_SGES_FOR_PACKET) { + rc = -EINVAL; + BNX2X_ERR("TPA update: max_sges received %d, max is %d\n", + tpa_tlv->tpa_client_info.max_sges_for_packet, + U_ETH_MAX_SGES_FOR_PACKET); + } + + if (tpa_tlv->tpa_client_info.max_tpa_queues > MAX_AGG_QS(bp)) { + rc = -EINVAL; + BNX2X_ERR("TPA update: max_tpa_queues received %d, max is %d\n", + tpa_tlv->tpa_client_info.max_tpa_queues, + MAX_AGG_QS(bp)); + } + + return rc; +} + +static void bnx2x_vf_mbx_update_tpa(struct bnx2x *bp, struct bnx2x_virtf *vf, + struct bnx2x_vf_mbx *mbx) +{ + struct bnx2x_vfop_cmd cmd = { + .done = bnx2x_vf_mbx_resp, + .block = false, + }; + struct bnx2x_queue_update_tpa_params *vf_op_params = + &vf->op_params.qstate.params.update_tpa; + struct vfpf_tpa_tlv *tpa_tlv = &mbx->msg->req.update_tpa; + + memset(vf_op_params, 0, sizeof(*vf_op_params)); + + if (bnx2x_validate_tpa_params(bp, tpa_tlv)) + goto mbx_resp; + + vf_op_params->complete_on_both_clients = + tpa_tlv->tpa_client_info.complete_on_both_clients; + vf_op_params->dont_verify_thr = + tpa_tlv->tpa_client_info.dont_verify_thr; + vf_op_params->max_agg_sz = + tpa_tlv->tpa_client_info.max_agg_size; + vf_op_params->max_sges_pkt = + tpa_tlv->tpa_client_info.max_sges_for_packet; + vf_op_params->max_tpa_queues = + tpa_tlv->tpa_client_info.max_tpa_queues; + vf_op_params->sge_buff_sz = + tpa_tlv->tpa_client_info.sge_buff_size; + vf_op_params->sge_pause_thr_high = + tpa_tlv->tpa_client_info.sge_pause_thr_high; + vf_op_params->sge_pause_thr_low = + tpa_tlv->tpa_client_info.sge_pause_thr_low; + vf_op_params->tpa_mode = + tpa_tlv->tpa_client_info.tpa_mode; + vf_op_params->update_ipv4 = + tpa_tlv->tpa_client_info.update_ipv4; + vf_op_params->update_ipv6 = + tpa_tlv->tpa_client_info.update_ipv6; + + vf->op_rc = bnx2x_vfop_tpa_cmd(bp, vf, &cmd, tpa_tlv); + +mbx_resp: + if (vf->op_rc) + bnx2x_vf_mbx_resp(bp, vf); +} + /* dispatch request */ static void bnx2x_vf_mbx_request(struct bnx2x *bp, struct bnx2x_virtf *vf, struct bnx2x_vf_mbx *mbx) @@ -1916,6 +2020,9 @@ static void bnx2x_vf_mbx_request(struct bnx2x *bp, struct bnx2x_virtf *vf, case CHANNEL_TLV_UPDATE_RSS: bnx2x_vf_mbx_update_rss(bp, vf, mbx); return; + case CHANNEL_TLV_UPDATE_TPA: + bnx2x_vf_mbx_update_tpa(bp, vf, mbx); + return; } } else { diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.h index 208568bc7a71..c922b81170e5 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.h @@ -162,6 +162,7 @@ struct pfvf_acquire_resp_tlv { #define PFVF_CAP_RSS 0x00000001 #define PFVF_CAP_DHC 0x00000002 #define PFVF_CAP_TPA 0x00000004 +#define PFVF_CAP_TPA_UPDATE 0x00000008 char fw_ver[32]; u16 db_size; u8 indices_per_sb; @@ -303,6 +304,25 @@ struct vfpf_set_q_filters_tlv { u32 rx_mask; /* see mask constants at the top of the file */ }; +struct vfpf_tpa_tlv { + struct vfpf_first_tlv first_tlv; + + struct vf_pf_tpa_client_info { + aligned_u64 sge_addr[PFVF_MAX_QUEUES_PER_VF]; + u8 update_ipv4; + u8 update_ipv6; + u8 max_tpa_queues; + u8 max_sges_for_packet; + u8 complete_on_both_clients; + u8 dont_verify_thr; + u8 tpa_mode; + u16 sge_buff_size; + u16 max_agg_size; + u16 sge_pause_thr_low; + u16 sge_pause_thr_high; + } tpa_client_info; +}; + /* close VF (disable VF) */ struct vfpf_close_tlv { struct vfpf_first_tlv first_tlv; @@ -331,6 +351,7 @@ union vfpf_tlvs { struct vfpf_set_q_filters_tlv set_q_filters; struct vfpf_release_tlv release; struct vfpf_rss_tlv update_rss; + struct vfpf_tpa_tlv update_tpa; struct channel_list_end_tlv list_end; struct tlv_buffer_size tlv_buf_size; }; @@ -405,6 +426,7 @@ enum channel_tlvs { CHANNEL_TLV_PF_SET_VLAN, CHANNEL_TLV_UPDATE_RSS, CHANNEL_TLV_PHYS_PORT_ID, + CHANNEL_TLV_UPDATE_TPA, CHANNEL_TLV_MAX }; diff --git a/drivers/net/ethernet/broadcom/genet/Makefile b/drivers/net/ethernet/broadcom/genet/Makefile new file mode 100644 index 000000000000..31f55a90a197 --- /dev/null +++ b/drivers/net/ethernet/broadcom/genet/Makefile @@ -0,0 +1,2 @@ +obj-$(CONFIG_BCMGENET) += genet.o +genet-objs := bcmgenet.o bcmmii.o diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c new file mode 100644 index 000000000000..72ce6e8115fa --- /dev/null +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -0,0 +1,2578 @@ +/* + * Broadcom GENET (Gigabit Ethernet) controller driver + * + * Copyright (c) 2014 Broadcom Corporation + * + * 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. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + */ + +#define pr_fmt(fmt) "bcmgenet: " fmt + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/sched.h> +#include <linux/types.h> +#include <linux/fcntl.h> +#include <linux/interrupt.h> +#include <linux/string.h> +#include <linux/if_ether.h> +#include <linux/init.h> +#include <linux/errno.h> +#include <linux/delay.h> +#include <linux/platform_device.h> +#include <linux/dma-mapping.h> +#include <linux/pm.h> +#include <linux/clk.h> +#include <linux/version.h> +#include <linux/of.h> +#include <linux/of_address.h> +#include <linux/of_irq.h> +#include <linux/of_net.h> +#include <linux/of_platform.h> +#include <net/arp.h> + +#include <linux/mii.h> +#include <linux/ethtool.h> +#include <linux/netdevice.h> +#include <linux/inetdevice.h> +#include <linux/etherdevice.h> +#include <linux/skbuff.h> +#include <linux/in.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/phy.h> + +#include <asm/unaligned.h> + +#include "bcmgenet.h" + +/* Maximum number of hardware queues, downsized if needed */ +#define GENET_MAX_MQ_CNT 4 + +/* Default highest priority queue for multi queue support */ +#define GENET_Q0_PRIORITY 0 + +#define GENET_DEFAULT_BD_CNT \ + (TOTAL_DESC - priv->hw_params->tx_queues * priv->hw_params->bds_cnt) + +#define RX_BUF_LENGTH 2048 +#define SKB_ALIGNMENT 32 + +/* Tx/Rx DMA register offset, skip 256 descriptors */ +#define WORDS_PER_BD(p) (p->hw_params->words_per_bd) +#define DMA_DESC_SIZE (WORDS_PER_BD(priv) * sizeof(u32)) + +#define GENET_TDMA_REG_OFF (priv->hw_params->tdma_offset + \ + TOTAL_DESC * DMA_DESC_SIZE) + +#define GENET_RDMA_REG_OFF (priv->hw_params->rdma_offset + \ + TOTAL_DESC * DMA_DESC_SIZE) + +static inline void dmadesc_set_length_status(struct bcmgenet_priv *priv, + void __iomem *d, u32 value) +{ + __raw_writel(value, d + DMA_DESC_LENGTH_STATUS); +} + +static inline u32 dmadesc_get_length_status(struct bcmgenet_priv *priv, + void __iomem *d) +{ + return __raw_readl(d + DMA_DESC_LENGTH_STATUS); +} + +static inline void dmadesc_set_addr(struct bcmgenet_priv *priv, + void __iomem *d, + dma_addr_t addr) +{ + __raw_writel(lower_32_bits(addr), d + DMA_DESC_ADDRESS_LO); + + /* Register writes to GISB bus can take couple hundred nanoseconds + * and are done for each packet, save these expensive writes unless + * the platform is explicitely configured for 64-bits/LPAE. + */ +#ifdef CONFIG_PHYS_ADDR_T_64BIT + if (priv->hw_params->flags & GENET_HAS_40BITS) + __raw_writel(upper_32_bits(addr), d + DMA_DESC_ADDRESS_HI); +#endif +} + +/* Combined address + length/status setter */ +static inline void dmadesc_set(struct bcmgenet_priv *priv, + void __iomem *d, dma_addr_t addr, u32 val) +{ + dmadesc_set_length_status(priv, d, val); + dmadesc_set_addr(priv, d, addr); +} + +static inline dma_addr_t dmadesc_get_addr(struct bcmgenet_priv *priv, + void __iomem *d) +{ + dma_addr_t addr; + + addr = __raw_readl(d + DMA_DESC_ADDRESS_LO); + + /* Register writes to GISB bus can take couple hundred nanoseconds + * and are done for each packet, save these expensive writes unless + * the platform is explicitely configured for 64-bits/LPAE. + */ +#ifdef CONFIG_PHYS_ADDR_T_64BIT + if (priv->hw_params->flags & GENET_HAS_40BITS) + addr |= (u64)__raw_readl(d + DMA_DESC_ADDRESS_HI) << 32; +#endif + return addr; +} + +#define GENET_VER_FMT "%1d.%1d EPHY: 0x%04x" + +#define GENET_MSG_DEFAULT (NETIF_MSG_DRV | NETIF_MSG_PROBE | \ + NETIF_MSG_LINK) + +static inline u32 bcmgenet_rbuf_ctrl_get(struct bcmgenet_priv *priv) +{ + if (GENET_IS_V1(priv)) + return bcmgenet_rbuf_readl(priv, RBUF_FLUSH_CTRL_V1); + else + return bcmgenet_sys_readl(priv, SYS_RBUF_FLUSH_CTRL); +} + +static inline void bcmgenet_rbuf_ctrl_set(struct bcmgenet_priv *priv, u32 val) +{ + if (GENET_IS_V1(priv)) + bcmgenet_rbuf_writel(priv, val, RBUF_FLUSH_CTRL_V1); + else + bcmgenet_sys_writel(priv, val, SYS_RBUF_FLUSH_CTRL); +} + +/* These macros are defined to deal with register map change + * between GENET1.1 and GENET2. Only those currently being used + * by driver are defined. + */ +static inline u32 bcmgenet_tbuf_ctrl_get(struct bcmgenet_priv *priv) +{ + if (GENET_IS_V1(priv)) + return bcmgenet_rbuf_readl(priv, TBUF_CTRL_V1); + else + return __raw_readl(priv->base + + priv->hw_params->tbuf_offset + TBUF_CTRL); +} + +static inline void bcmgenet_tbuf_ctrl_set(struct bcmgenet_priv *priv, u32 val) +{ + if (GENET_IS_V1(priv)) + bcmgenet_rbuf_writel(priv, val, TBUF_CTRL_V1); + else + __raw_writel(val, priv->base + + priv->hw_params->tbuf_offset + TBUF_CTRL); +} + +static inline u32 bcmgenet_bp_mc_get(struct bcmgenet_priv *priv) +{ + if (GENET_IS_V1(priv)) + return bcmgenet_rbuf_readl(priv, TBUF_BP_MC_V1); + else + return __raw_readl(priv->base + + priv->hw_params->tbuf_offset + TBUF_BP_MC); +} + +static inline void bcmgenet_bp_mc_set(struct bcmgenet_priv *priv, u32 val) +{ + if (GENET_IS_V1(priv)) + bcmgenet_rbuf_writel(priv, val, TBUF_BP_MC_V1); + else + __raw_writel(val, priv->base + + priv->hw_params->tbuf_offset + TBUF_BP_MC); +} + +/* RX/TX DMA register accessors */ +enum dma_reg { + DMA_RING_CFG = 0, + DMA_CTRL, + DMA_STATUS, + DMA_SCB_BURST_SIZE, + DMA_ARB_CTRL, + DMA_PRIORITY, + DMA_RING_PRIORITY, +}; + +static const u8 bcmgenet_dma_regs_v3plus[] = { + [DMA_RING_CFG] = 0x00, + [DMA_CTRL] = 0x04, + [DMA_STATUS] = 0x08, + [DMA_SCB_BURST_SIZE] = 0x0C, + [DMA_ARB_CTRL] = 0x2C, + [DMA_PRIORITY] = 0x30, + [DMA_RING_PRIORITY] = 0x38, +}; + +static const u8 bcmgenet_dma_regs_v2[] = { + [DMA_RING_CFG] = 0x00, + [DMA_CTRL] = 0x04, + [DMA_STATUS] = 0x08, + [DMA_SCB_BURST_SIZE] = 0x0C, + [DMA_ARB_CTRL] = 0x30, + [DMA_PRIORITY] = 0x34, + [DMA_RING_PRIORITY] = 0x3C, +}; + +static const u8 bcmgenet_dma_regs_v1[] = { + [DMA_CTRL] = 0x00, + [DMA_STATUS] = 0x04, + [DMA_SCB_BURST_SIZE] = 0x0C, + [DMA_ARB_CTRL] = 0x30, + [DMA_PRIORITY] = 0x34, + [DMA_RING_PRIORITY] = 0x3C, +}; + +/* Set at runtime once bcmgenet version is known */ +static const u8 *bcmgenet_dma_regs; + +static inline struct bcmgenet_priv *dev_to_priv(struct device *dev) +{ + return netdev_priv(dev_get_drvdata(dev)); +} + +static inline u32 bcmgenet_tdma_readl(struct bcmgenet_priv *priv, + enum dma_reg r) +{ + return __raw_readl(priv->base + GENET_TDMA_REG_OFF + + DMA_RINGS_SIZE + bcmgenet_dma_regs[r]); +} + +static inline void bcmgenet_tdma_writel(struct bcmgenet_priv *priv, + u32 val, enum dma_reg r) +{ + __raw_writel(val, priv->base + GENET_TDMA_REG_OFF + + DMA_RINGS_SIZE + bcmgenet_dma_regs[r]); +} + +static inline u32 bcmgenet_rdma_readl(struct bcmgenet_priv *priv, + enum dma_reg r) +{ + return __raw_readl(priv->base + GENET_RDMA_REG_OFF + + DMA_RINGS_SIZE + bcmgenet_dma_regs[r]); +} + +static inline void bcmgenet_rdma_writel(struct bcmgenet_priv *priv, + u32 val, enum dma_reg r) +{ + __raw_writel(val, priv->base + GENET_RDMA_REG_OFF + + DMA_RINGS_SIZE + bcmgenet_dma_regs[r]); +} + +/* RDMA/TDMA ring registers and accessors + * we merge the common fields and just prefix with T/D the registers + * having different meaning depending on the direction + */ +enum dma_ring_reg { + TDMA_READ_PTR = 0, + RDMA_WRITE_PTR = TDMA_READ_PTR, + TDMA_READ_PTR_HI, + RDMA_WRITE_PTR_HI = TDMA_READ_PTR_HI, + TDMA_CONS_INDEX, + RDMA_PROD_INDEX = TDMA_CONS_INDEX, + TDMA_PROD_INDEX, + RDMA_CONS_INDEX = TDMA_PROD_INDEX, + DMA_RING_BUF_SIZE, + DMA_START_ADDR, + DMA_START_ADDR_HI, + DMA_END_ADDR, + DMA_END_ADDR_HI, + DMA_MBUF_DONE_THRESH, + TDMA_FLOW_PERIOD, + RDMA_XON_XOFF_THRESH = TDMA_FLOW_PERIOD, + TDMA_WRITE_PTR, + RDMA_READ_PTR = TDMA_WRITE_PTR, + TDMA_WRITE_PTR_HI, + RDMA_READ_PTR_HI = TDMA_WRITE_PTR_HI +}; + +/* GENET v4 supports 40-bits pointer addressing + * for obvious reasons the LO and HI word parts + * are contiguous, but this offsets the other + * registers. + */ +static const u8 genet_dma_ring_regs_v4[] = { + [TDMA_READ_PTR] = 0x00, + [TDMA_READ_PTR_HI] = 0x04, + [TDMA_CONS_INDEX] = 0x08, + [TDMA_PROD_INDEX] = 0x0C, + [DMA_RING_BUF_SIZE] = 0x10, + [DMA_START_ADDR] = 0x14, + [DMA_START_ADDR_HI] = 0x18, + [DMA_END_ADDR] = 0x1C, + [DMA_END_ADDR_HI] = 0x20, + [DMA_MBUF_DONE_THRESH] = 0x24, + [TDMA_FLOW_PERIOD] = 0x28, + [TDMA_WRITE_PTR] = 0x2C, + [TDMA_WRITE_PTR_HI] = 0x30, +}; + +static const u8 genet_dma_ring_regs_v123[] = { + [TDMA_READ_PTR] = 0x00, + [TDMA_CONS_INDEX] = 0x04, + [TDMA_PROD_INDEX] = 0x08, + [DMA_RING_BUF_SIZE] = 0x0C, + [DMA_START_ADDR] = 0x10, + [DMA_END_ADDR] = 0x14, + [DMA_MBUF_DONE_THRESH] = 0x18, + [TDMA_FLOW_PERIOD] = 0x1C, + [TDMA_WRITE_PTR] = 0x20, +}; + +/* Set at runtime once GENET version is known */ +static const u8 *genet_dma_ring_regs; + +static inline u32 bcmgenet_tdma_ring_readl(struct bcmgenet_priv *priv, + unsigned int ring, + enum dma_ring_reg r) +{ + return __raw_readl(priv->base + GENET_TDMA_REG_OFF + + (DMA_RING_SIZE * ring) + + genet_dma_ring_regs[r]); +} + +static inline void bcmgenet_tdma_ring_writel(struct bcmgenet_priv *priv, + unsigned int ring, + u32 val, + enum dma_ring_reg r) +{ + __raw_writel(val, priv->base + GENET_TDMA_REG_OFF + + (DMA_RING_SIZE * ring) + + genet_dma_ring_regs[r]); +} + +static inline u32 bcmgenet_rdma_ring_readl(struct bcmgenet_priv *priv, + unsigned int ring, + enum dma_ring_reg r) +{ + return __raw_readl(priv->base + GENET_RDMA_REG_OFF + + (DMA_RING_SIZE * ring) + + genet_dma_ring_regs[r]); +} + +static inline void bcmgenet_rdma_ring_writel(struct bcmgenet_priv *priv, + unsigned int ring, + u32 val, + enum dma_ring_reg r) +{ + __raw_writel(val, priv->base + GENET_RDMA_REG_OFF + + (DMA_RING_SIZE * ring) + + genet_dma_ring_regs[r]); +} + +static int bcmgenet_get_settings(struct net_device *dev, + struct ethtool_cmd *cmd) +{ + struct bcmgenet_priv *priv = netdev_priv(dev); + + if (!netif_running(dev)) + return -EINVAL; + + if (!priv->phydev) + return -ENODEV; + + return phy_ethtool_gset(priv->phydev, cmd); +} + +static int bcmgenet_set_settings(struct net_device *dev, + struct ethtool_cmd *cmd) +{ + struct bcmgenet_priv *priv = netdev_priv(dev); + + if (!netif_running(dev)) + return -EINVAL; + + if (!priv->phydev) + return -ENODEV; + + return phy_ethtool_sset(priv->phydev, cmd); +} + +static int bcmgenet_set_rx_csum(struct net_device *dev, + netdev_features_t wanted) +{ + struct bcmgenet_priv *priv = netdev_priv(dev); + u32 rbuf_chk_ctrl; + bool rx_csum_en; + + rx_csum_en = !!(wanted & NETIF_F_RXCSUM); + + rbuf_chk_ctrl = bcmgenet_rbuf_readl(priv, RBUF_CHK_CTRL); + + /* enable rx checksumming */ + if (rx_csum_en) + rbuf_chk_ctrl |= RBUF_RXCHK_EN; + else + rbuf_chk_ctrl &= ~RBUF_RXCHK_EN; + priv->desc_rxchk_en = rx_csum_en; + bcmgenet_rbuf_writel(priv, rbuf_chk_ctrl, RBUF_CHK_CTRL); + + return 0; +} + +static int bcmgenet_set_tx_csum(struct net_device *dev, + netdev_features_t wanted) +{ + struct bcmgenet_priv *priv = netdev_priv(dev); + bool desc_64b_en; + u32 tbuf_ctrl, rbuf_ctrl; + + tbuf_ctrl = bcmgenet_tbuf_ctrl_get(priv); + rbuf_ctrl = bcmgenet_rbuf_readl(priv, RBUF_CTRL); + + desc_64b_en = !!(wanted & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM)); + + /* enable 64 bytes descriptor in both directions (RBUF and TBUF) */ + if (desc_64b_en) { + tbuf_ctrl |= RBUF_64B_EN; + rbuf_ctrl |= RBUF_64B_EN; + } else { + tbuf_ctrl &= ~RBUF_64B_EN; + rbuf_ctrl &= ~RBUF_64B_EN; + } + priv->desc_64b_en = desc_64b_en; + + bcmgenet_tbuf_ctrl_set(priv, tbuf_ctrl); + bcmgenet_rbuf_writel(priv, rbuf_ctrl, RBUF_CTRL); + + return 0; +} + +static int bcmgenet_set_features(struct net_device *dev, + netdev_features_t features) +{ + netdev_features_t changed = features ^ dev->features; + netdev_features_t wanted = dev->wanted_features; + int ret = 0; + + if (changed & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM)) + ret = bcmgenet_set_tx_csum(dev, wanted); + if (changed & (NETIF_F_RXCSUM)) + ret = bcmgenet_set_rx_csum(dev, wanted); + + return ret; +} + +static u32 bcmgenet_get_msglevel(struct net_device *dev) +{ + struct bcmgenet_priv *priv = netdev_priv(dev); + + return priv->msg_enable; +} + +static void bcmgenet_set_msglevel(struct net_device *dev, u32 level) +{ + struct bcmgenet_priv *priv = netdev_priv(dev); + + priv->msg_enable = level; +} + +/* standard ethtool support functions. */ +enum bcmgenet_stat_type { + BCMGENET_STAT_NETDEV = -1, + BCMGENET_STAT_MIB_RX, + BCMGENET_STAT_MIB_TX, + BCMGENET_STAT_RUNT, + BCMGENET_STAT_MISC, +}; + +struct bcmgenet_stats { + char stat_string[ETH_GSTRING_LEN]; + int stat_sizeof; + int stat_offset; + enum bcmgenet_stat_type type; + /* reg offset from UMAC base for misc counters */ + u16 reg_offset; +}; + +#define STAT_NETDEV(m) { \ + .stat_string = __stringify(m), \ + .stat_sizeof = sizeof(((struct net_device_stats *)0)->m), \ + .stat_offset = offsetof(struct net_device_stats, m), \ + .type = BCMGENET_STAT_NETDEV, \ +} + +#define STAT_GENET_MIB(str, m, _type) { \ + .stat_string = str, \ + .stat_sizeof = sizeof(((struct bcmgenet_priv *)0)->m), \ + .stat_offset = offsetof(struct bcmgenet_priv, m), \ + .type = _type, \ +} + +#define STAT_GENET_MIB_RX(str, m) STAT_GENET_MIB(str, m, BCMGENET_STAT_MIB_RX) +#define STAT_GENET_MIB_TX(str, m) STAT_GENET_MIB(str, m, BCMGENET_STAT_MIB_TX) +#define STAT_GENET_RUNT(str, m) STAT_GENET_MIB(str, m, BCMGENET_STAT_RUNT) + +#define STAT_GENET_MISC(str, m, offset) { \ + .stat_string = str, \ + .stat_sizeof = sizeof(((struct bcmgenet_priv *)0)->m), \ + .stat_offset = offsetof(struct bcmgenet_priv, m), \ + .type = BCMGENET_STAT_MISC, \ + .reg_offset = offset, \ +} + + +/* There is a 0xC gap between the end of RX and beginning of TX stats and then + * between the end of TX stats and the beginning of the RX RUNT + */ +#define BCMGENET_STAT_OFFSET 0xc + +/* Hardware counters must be kept in sync because the order/offset + * is important here (order in structure declaration = order in hardware) + */ +static const struct bcmgenet_stats bcmgenet_gstrings_stats[] = { + /* general stats */ + STAT_NETDEV(rx_packets), + STAT_NETDEV(tx_packets), + STAT_NETDEV(rx_bytes), + STAT_NETDEV(tx_bytes), + STAT_NETDEV(rx_errors), + STAT_NETDEV(tx_errors), + STAT_NETDEV(rx_dropped), + STAT_NETDEV(tx_dropped), + STAT_NETDEV(multicast), + /* UniMAC RSV counters */ + STAT_GENET_MIB_RX("rx_64_octets", mib.rx.pkt_cnt.cnt_64), + STAT_GENET_MIB_RX("rx_65_127_oct", mib.rx.pkt_cnt.cnt_127), + STAT_GENET_MIB_RX("rx_128_255_oct", mib.rx.pkt_cnt.cnt_255), + STAT_GENET_MIB_RX("rx_256_511_oct", mib.rx.pkt_cnt.cnt_511), + STAT_GENET_MIB_RX("rx_512_1023_oct", mib.rx.pkt_cnt.cnt_1023), + STAT_GENET_MIB_RX("rx_1024_1518_oct", mib.rx.pkt_cnt.cnt_1518), + STAT_GENET_MIB_RX("rx_vlan_1519_1522_oct", mib.rx.pkt_cnt.cnt_mgv), + STAT_GENET_MIB_RX("rx_1522_2047_oct", mib.rx.pkt_cnt.cnt_2047), + STAT_GENET_MIB_RX("rx_2048_4095_oct", mib.rx.pkt_cnt.cnt_4095), + STAT_GENET_MIB_RX("rx_4096_9216_oct", mib.rx.pkt_cnt.cnt_9216), + STAT_GENET_MIB_RX("rx_pkts", mib.rx.pkt), + STAT_GENET_MIB_RX("rx_bytes", mib.rx.bytes), + STAT_GENET_MIB_RX("rx_multicast", mib.rx.mca), + STAT_GENET_MIB_RX("rx_broadcast", mib.rx.bca), + STAT_GENET_MIB_RX("rx_fcs", mib.rx.fcs), + STAT_GENET_MIB_RX("rx_control", mib.rx.cf), + STAT_GENET_MIB_RX("rx_pause", mib.rx.pf), + STAT_GENET_MIB_RX("rx_unknown", mib.rx.uo), + STAT_GENET_MIB_RX("rx_align", mib.rx.aln), + STAT_GENET_MIB_RX("rx_outrange", mib.rx.flr), + STAT_GENET_MIB_RX("rx_code", mib.rx.cde), + STAT_GENET_MIB_RX("rx_carrier", mib.rx.fcr), + STAT_GENET_MIB_RX("rx_oversize", mib.rx.ovr), + STAT_GENET_MIB_RX("rx_jabber", mib.rx.jbr), + STAT_GENET_MIB_RX("rx_mtu_err", mib.rx.mtue), + STAT_GENET_MIB_RX("rx_good_pkts", mib.rx.pok), + STAT_GENET_MIB_RX("rx_unicast", mib.rx.uc), + STAT_GENET_MIB_RX("rx_ppp", mib.rx.ppp), + STAT_GENET_MIB_RX("rx_crc", mib.rx.rcrc), + /* UniMAC TSV counters */ + STAT_GENET_MIB_TX("tx_64_octets", mib.tx.pkt_cnt.cnt_64), + STAT_GENET_MIB_TX("tx_65_127_oct", mib.tx.pkt_cnt.cnt_127), + STAT_GENET_MIB_TX("tx_128_255_oct", mib.tx.pkt_cnt.cnt_255), + STAT_GENET_MIB_TX("tx_256_511_oct", mib.tx.pkt_cnt.cnt_511), + STAT_GENET_MIB_TX("tx_512_1023_oct", mib.tx.pkt_cnt.cnt_1023), + STAT_GENET_MIB_TX("tx_1024_1518_oct", mib.tx.pkt_cnt.cnt_1518), + STAT_GENET_MIB_TX("tx_vlan_1519_1522_oct", mib.tx.pkt_cnt.cnt_mgv), + STAT_GENET_MIB_TX("tx_1522_2047_oct", mib.tx.pkt_cnt.cnt_2047), + STAT_GENET_MIB_TX("tx_2048_4095_oct", mib.tx.pkt_cnt.cnt_4095), + STAT_GENET_MIB_TX("tx_4096_9216_oct", mib.tx.pkt_cnt.cnt_9216), + STAT_GENET_MIB_TX("tx_pkts", mib.tx.pkts), + STAT_GENET_MIB_TX("tx_multicast", mib.tx.mca), + STAT_GENET_MIB_TX("tx_broadcast", mib.tx.bca), + STAT_GENET_MIB_TX("tx_pause", mib.tx.pf), + STAT_GENET_MIB_TX("tx_control", mib.tx.cf), + STAT_GENET_MIB_TX("tx_fcs_err", mib.tx.fcs), + STAT_GENET_MIB_TX("tx_oversize", mib.tx.ovr), + STAT_GENET_MIB_TX("tx_defer", mib.tx.drf), + STAT_GENET_MIB_TX("tx_excess_defer", mib.tx.edf), + STAT_GENET_MIB_TX("tx_single_col", mib.tx.scl), + STAT_GENET_MIB_TX("tx_multi_col", mib.tx.mcl), + STAT_GENET_MIB_TX("tx_late_col", mib.tx.lcl), + STAT_GENET_MIB_TX("tx_excess_col", mib.tx.ecl), + STAT_GENET_MIB_TX("tx_frags", mib.tx.frg), + STAT_GENET_MIB_TX("tx_total_col", mib.tx.ncl), + STAT_GENET_MIB_TX("tx_jabber", mib.tx.jbr), + STAT_GENET_MIB_TX("tx_bytes", mib.tx.bytes), + STAT_GENET_MIB_TX("tx_good_pkts", mib.tx.pok), + STAT_GENET_MIB_TX("tx_unicast", mib.tx.uc), + /* UniMAC RUNT counters */ + STAT_GENET_RUNT("rx_runt_pkts", mib.rx_runt_cnt), + STAT_GENET_RUNT("rx_runt_valid_fcs", mib.rx_runt_fcs), + STAT_GENET_RUNT("rx_runt_inval_fcs_align", mib.rx_runt_fcs_align), + STAT_GENET_RUNT("rx_runt_bytes", mib.rx_runt_bytes), + /* Misc UniMAC counters */ + STAT_GENET_MISC("rbuf_ovflow_cnt", mib.rbuf_ovflow_cnt, + UMAC_RBUF_OVFL_CNT), + STAT_GENET_MISC("rbuf_err_cnt", mib.rbuf_err_cnt, UMAC_RBUF_ERR_CNT), + STAT_GENET_MISC("mdf_err_cnt", mib.mdf_err_cnt, UMAC_MDF_ERR_CNT), +}; + +#define BCMGENET_STATS_LEN ARRAY_SIZE(bcmgenet_gstrings_stats) + +static void bcmgenet_get_drvinfo(struct net_device *dev, + struct ethtool_drvinfo *info) +{ + strlcpy(info->driver, "bcmgenet", sizeof(info->driver)); + strlcpy(info->version, "v2.0", sizeof(info->version)); + info->n_stats = BCMGENET_STATS_LEN; + +} + +static int bcmgenet_get_sset_count(struct net_device *dev, int string_set) +{ + switch (string_set) { + case ETH_SS_STATS: + return BCMGENET_STATS_LEN; + default: + return -EOPNOTSUPP; + } +} + +static void bcmgenet_get_strings(struct net_device *dev, + u32 stringset, u8 *data) +{ + int i; + + switch (stringset) { + case ETH_SS_STATS: + for (i = 0; i < BCMGENET_STATS_LEN; i++) { + memcpy(data + i * ETH_GSTRING_LEN, + bcmgenet_gstrings_stats[i].stat_string, + ETH_GSTRING_LEN); + } + break; + } +} + +static void bcmgenet_update_mib_counters(struct bcmgenet_priv *priv) +{ + int i, j = 0; + + for (i = 0; i < BCMGENET_STATS_LEN; i++) { + const struct bcmgenet_stats *s; + u8 offset = 0; + u32 val = 0; + char *p; + + s = &bcmgenet_gstrings_stats[i]; + switch (s->type) { + case BCMGENET_STAT_NETDEV: + continue; + case BCMGENET_STAT_MIB_RX: + case BCMGENET_STAT_MIB_TX: + case BCMGENET_STAT_RUNT: + if (s->type != BCMGENET_STAT_MIB_RX) + offset = BCMGENET_STAT_OFFSET; + val = bcmgenet_umac_readl(priv, UMAC_MIB_START + + j + offset); + break; + case BCMGENET_STAT_MISC: + val = bcmgenet_umac_readl(priv, s->reg_offset); + /* clear if overflowed */ + if (val == ~0) + bcmgenet_umac_writel(priv, 0, s->reg_offset); + break; + } + + j += s->stat_sizeof; + p = (char *)priv + s->stat_offset; + *(u32 *)p = val; + } +} + +static void bcmgenet_get_ethtool_stats(struct net_device *dev, + struct ethtool_stats *stats, + u64 *data) +{ + struct bcmgenet_priv *priv = netdev_priv(dev); + int i; + + if (netif_running(dev)) + bcmgenet_update_mib_counters(priv); + + for (i = 0; i < BCMGENET_STATS_LEN; i++) { + const struct bcmgenet_stats *s; + char *p; + + s = &bcmgenet_gstrings_stats[i]; + if (s->type == BCMGENET_STAT_NETDEV) + p = (char *)&dev->stats; + else + p = (char *)priv; + p += s->stat_offset; + data[i] = *(u32 *)p; + } +} + +/* standard ethtool support functions. */ +static struct ethtool_ops bcmgenet_ethtool_ops = { + .get_strings = bcmgenet_get_strings, + .get_sset_count = bcmgenet_get_sset_count, + .get_ethtool_stats = bcmgenet_get_ethtool_stats, + .get_settings = bcmgenet_get_settings, + .set_settings = bcmgenet_set_settings, + .get_drvinfo = bcmgenet_get_drvinfo, + .get_link = ethtool_op_get_link, + .get_msglevel = bcmgenet_get_msglevel, + .set_msglevel = bcmgenet_set_msglevel, +}; + +/* Power down the unimac, based on mode. */ +static void bcmgenet_power_down(struct bcmgenet_priv *priv, + enum bcmgenet_power_mode mode) +{ + u32 reg; + + switch (mode) { + case GENET_POWER_CABLE_SENSE: + phy_detach(priv->phydev); + break; + + case GENET_POWER_PASSIVE: + /* Power down LED */ + bcmgenet_mii_reset(priv->dev); + if (priv->hw_params->flags & GENET_HAS_EXT) { + reg = bcmgenet_ext_readl(priv, EXT_EXT_PWR_MGMT); + reg |= (EXT_PWR_DOWN_PHY | + EXT_PWR_DOWN_DLL | EXT_PWR_DOWN_BIAS); + bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT); + } + break; + default: + break; + } +} + +static void bcmgenet_power_up(struct bcmgenet_priv *priv, + enum bcmgenet_power_mode mode) +{ + u32 reg; + + if (!(priv->hw_params->flags & GENET_HAS_EXT)) + return; + + reg = bcmgenet_ext_readl(priv, EXT_EXT_PWR_MGMT); + + switch (mode) { + case GENET_POWER_PASSIVE: + reg &= ~(EXT_PWR_DOWN_DLL | EXT_PWR_DOWN_PHY | + EXT_PWR_DOWN_BIAS); + /* fallthrough */ + case GENET_POWER_CABLE_SENSE: + /* enable APD */ + reg |= EXT_PWR_DN_EN_LD; + break; + default: + break; + } + + bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT); + bcmgenet_mii_reset(priv->dev); +} + +/* ioctl handle special commands that are not present in ethtool. */ +static int bcmgenet_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) +{ + struct bcmgenet_priv *priv = netdev_priv(dev); + int val = 0; + + if (!netif_running(dev)) + return -EINVAL; + + switch (cmd) { + case SIOCGMIIPHY: + case SIOCGMIIREG: + case SIOCSMIIREG: + if (!priv->phydev) + val = -ENODEV; + else + val = phy_mii_ioctl(priv->phydev, rq, cmd); + break; + + default: + val = -EINVAL; + break; + } + + return val; +} + +static struct enet_cb *bcmgenet_get_txcb(struct bcmgenet_priv *priv, + struct bcmgenet_tx_ring *ring) +{ + struct enet_cb *tx_cb_ptr; + + tx_cb_ptr = ring->cbs; + tx_cb_ptr += ring->write_ptr - ring->cb_ptr; + tx_cb_ptr->bd_addr = priv->tx_bds + ring->write_ptr * DMA_DESC_SIZE; + /* Advancing local write pointer */ + if (ring->write_ptr == ring->end_ptr) + ring->write_ptr = ring->cb_ptr; + else + ring->write_ptr++; + + return tx_cb_ptr; +} + +/* Simple helper to free a control block's resources */ +static void bcmgenet_free_cb(struct enet_cb *cb) +{ + dev_kfree_skb_any(cb->skb); + cb->skb = NULL; + 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) +{ + bcmgenet_intrl2_0_writel(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) +{ + bcmgenet_intrl2_0_writel(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) +{ + bcmgenet_intrl2_1_writel(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) +{ + bcmgenet_intrl2_1_writel(priv, + (1 << ring->index), INTRL2_CPU_MASK_SET); + priv->int1_mask |= (1 << ring->index); +} + +/* Unlocked version of the reclaim routine */ +static void __bcmgenet_tx_reclaim(struct net_device *dev, + struct bcmgenet_tx_ring *ring) +{ + struct bcmgenet_priv *priv = netdev_priv(dev); + int last_tx_cn, last_c_index, num_tx_bds; + struct enet_cb *tx_cb_ptr; + unsigned int c_index; + + /* Compute how many buffers are transmited since last xmit call */ + c_index = bcmgenet_tdma_ring_readl(priv, ring->index, TDMA_CONS_INDEX); + + last_c_index = ring->c_index; + num_tx_bds = ring->size; + + c_index &= (num_tx_bds - 1); + + if (c_index >= last_c_index) + last_tx_cn = c_index - last_c_index; + else + last_tx_cn = num_tx_bds - last_c_index + c_index; + + netif_dbg(priv, tx_done, dev, + "%s ring=%d index=%d last_tx_cn=%d last_index=%d\n", + __func__, ring->index, + c_index, last_tx_cn, last_c_index); + + /* Reclaim transmitted buffers */ + while (last_tx_cn-- > 0) { + tx_cb_ptr = ring->cbs + last_c_index; + if (tx_cb_ptr->skb) { + dev->stats.tx_bytes += tx_cb_ptr->skb->len; + dma_unmap_single(&dev->dev, + dma_unmap_addr(tx_cb_ptr, dma_addr), + tx_cb_ptr->skb->len, + DMA_TO_DEVICE); + bcmgenet_free_cb(tx_cb_ptr); + } else if (dma_unmap_addr(tx_cb_ptr, dma_addr)) { + dev->stats.tx_bytes += + dma_unmap_len(tx_cb_ptr, dma_len); + dma_unmap_page(&dev->dev, + dma_unmap_addr(tx_cb_ptr, dma_addr), + dma_unmap_len(tx_cb_ptr, dma_len), + DMA_TO_DEVICE); + dma_unmap_addr_set(tx_cb_ptr, dma_addr, 0); + } + dev->stats.tx_packets++; + ring->free_bds += 1; + + last_c_index++; + last_c_index &= (num_tx_bds - 1); + } + + if (ring->free_bds > (MAX_SKB_FRAGS + 1)) + ring->int_disable(priv, ring); + + if (__netif_subqueue_stopped(dev, ring->queue)) + netif_wake_subqueue(dev, ring->queue); + + ring->c_index = c_index; +} + +static void bcmgenet_tx_reclaim(struct net_device *dev, + struct bcmgenet_tx_ring *ring) +{ + unsigned long flags; + + spin_lock_irqsave(&ring->lock, flags); + __bcmgenet_tx_reclaim(dev, ring); + spin_unlock_irqrestore(&ring->lock, flags); +} + +static void bcmgenet_tx_reclaim_all(struct net_device *dev) +{ + struct bcmgenet_priv *priv = netdev_priv(dev); + int i; + + if (netif_is_multiqueue(dev)) { + for (i = 0; i < priv->hw_params->tx_queues; i++) + bcmgenet_tx_reclaim(dev, &priv->tx_rings[i]); + } + + bcmgenet_tx_reclaim(dev, &priv->tx_rings[DESC_INDEX]); +} + +/* Transmits a single SKB (either head of a fragment or a single SKB) + * caller must hold priv->lock + */ +static int bcmgenet_xmit_single(struct net_device *dev, + struct sk_buff *skb, + u16 dma_desc_flags, + struct bcmgenet_tx_ring *ring) +{ + struct bcmgenet_priv *priv = netdev_priv(dev); + struct device *kdev = &priv->pdev->dev; + struct enet_cb *tx_cb_ptr; + unsigned int skb_len; + dma_addr_t mapping; + u32 length_status; + int ret; + + tx_cb_ptr = bcmgenet_get_txcb(priv, ring); + + if (unlikely(!tx_cb_ptr)) + BUG(); + + tx_cb_ptr->skb = skb; + + skb_len = skb_headlen(skb) < ETH_ZLEN ? ETH_ZLEN : skb_headlen(skb); + + mapping = dma_map_single(kdev, skb->data, skb_len, DMA_TO_DEVICE); + ret = dma_mapping_error(kdev, mapping); + if (ret) { + netif_err(priv, tx_err, dev, "Tx DMA map failed\n"); + dev_kfree_skb(skb); + return ret; + } + + dma_unmap_addr_set(tx_cb_ptr, dma_addr, mapping); + dma_unmap_len_set(tx_cb_ptr, dma_len, skb->len); + length_status = (skb_len << DMA_BUFLENGTH_SHIFT) | dma_desc_flags | + (priv->hw_params->qtag_mask << DMA_TX_QTAG_SHIFT) | + DMA_TX_APPEND_CRC; + + if (skb->ip_summed == CHECKSUM_PARTIAL) + length_status |= DMA_TX_DO_CSUM; + + dmadesc_set(priv, tx_cb_ptr->bd_addr, mapping, length_status); + + /* Decrement total BD count and advance our write pointer */ + ring->free_bds -= 1; + ring->prod_index += 1; + ring->prod_index &= DMA_P_INDEX_MASK; + + return 0; +} + +/* Transmit a SKB fragement */ +static int bcmgenet_xmit_frag(struct net_device *dev, + skb_frag_t *frag, + u16 dma_desc_flags, + struct bcmgenet_tx_ring *ring) +{ + struct bcmgenet_priv *priv = netdev_priv(dev); + struct device *kdev = &priv->pdev->dev; + struct enet_cb *tx_cb_ptr; + dma_addr_t mapping; + int ret; + + tx_cb_ptr = bcmgenet_get_txcb(priv, ring); + + if (unlikely(!tx_cb_ptr)) + BUG(); + tx_cb_ptr->skb = NULL; + + mapping = skb_frag_dma_map(kdev, frag, 0, + skb_frag_size(frag), DMA_TO_DEVICE); + ret = dma_mapping_error(kdev, mapping); + if (ret) { + netif_err(priv, tx_err, dev, "%s: Tx DMA map failed\n", + __func__); + return ret; + } + + dma_unmap_addr_set(tx_cb_ptr, dma_addr, mapping); + dma_unmap_len_set(tx_cb_ptr, dma_len, frag->size); + + dmadesc_set(priv, tx_cb_ptr->bd_addr, mapping, + (frag->size << DMA_BUFLENGTH_SHIFT) | dma_desc_flags | + (priv->hw_params->qtag_mask << DMA_TX_QTAG_SHIFT)); + + + ring->free_bds -= 1; + ring->prod_index += 1; + ring->prod_index &= DMA_P_INDEX_MASK; + + return 0; +} + +/* Reallocate the SKB to put enough headroom in front of it and insert + * the transmit checksum offsets in the descriptors + */ +static int bcmgenet_put_tx_csum(struct net_device *dev, struct sk_buff *skb) +{ + struct status_64 *status = NULL; + struct sk_buff *new_skb; + u16 offset; + u8 ip_proto; + u16 ip_ver; + u32 tx_csum_info; + + if (unlikely(skb_headroom(skb) < sizeof(*status))) { + /* If 64 byte status block enabled, must make sure skb has + * enough headroom for us to insert 64B status block. + */ + new_skb = skb_realloc_headroom(skb, sizeof(*status)); + dev_kfree_skb(skb); + if (!new_skb) { + dev->stats.tx_errors++; + dev->stats.tx_dropped++; + return -ENOMEM; + } + skb = new_skb; + } + + skb_push(skb, sizeof(*status)); + status = (struct status_64 *)skb->data; + + if (skb->ip_summed == CHECKSUM_PARTIAL) { + ip_ver = htons(skb->protocol); + switch (ip_ver) { + case ETH_P_IP: + ip_proto = ip_hdr(skb)->protocol; + break; + case ETH_P_IPV6: + ip_proto = ipv6_hdr(skb)->nexthdr; + break; + default: + return 0; + } + + offset = skb_checksum_start_offset(skb) - sizeof(*status); + tx_csum_info = (offset << STATUS_TX_CSUM_START_SHIFT) | + (offset + skb->csum_offset); + + /* Set the length valid bit for TCP and UDP and just set + * the special UDP flag for IPv4, else just set to 0. + */ + if (ip_proto == IPPROTO_TCP || ip_proto == IPPROTO_UDP) { + tx_csum_info |= STATUS_TX_CSUM_LV; + if (ip_proto == IPPROTO_UDP && ip_ver == ETH_P_IP) + tx_csum_info |= STATUS_TX_CSUM_PROTO_UDP; + } else + tx_csum_info = 0; + + status->tx_csum_info = tx_csum_info; + } + + return 0; +} + +static netdev_tx_t bcmgenet_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct bcmgenet_priv *priv = netdev_priv(dev); + struct bcmgenet_tx_ring *ring = NULL; + unsigned long flags = 0; + int nr_frags, index; + u16 dma_desc_flags; + int ret; + int i; + + index = skb_get_queue_mapping(skb); + /* Mapping strategy: + * queue_mapping = 0, unclassified, packet xmited through ring16 + * queue_mapping = 1, goes to ring 0. (highest priority queue + * queue_mapping = 2, goes to ring 1. + * queue_mapping = 3, goes to ring 2. + * queue_mapping = 4, goes to ring 3. + */ + if (index == 0) + index = DESC_INDEX; + else + index -= 1; + + if ((index != DESC_INDEX) && (index > priv->hw_params->tx_queues - 1)) { + netdev_err(dev, "%s: queue_mapping %d is invalid\n", + __func__, skb_get_queue_mapping(skb)); + dev->stats.tx_errors++; + dev->stats.tx_dropped++; + ret = NETDEV_TX_OK; + goto out; + } + nr_frags = skb_shinfo(skb)->nr_frags; + ring = &priv->tx_rings[index]; + + spin_lock_irqsave(&ring->lock, flags); + if (ring->free_bds <= nr_frags + 1) { + netif_stop_subqueue(dev, ring->queue); + netdev_err(dev, "%s: tx ring %d full when queue %d awake\n", + __func__, index, ring->queue); + ret = NETDEV_TX_BUSY; + goto out; + } + + /* set the SKB transmit checksum */ + if (priv->desc_64b_en) { + ret = bcmgenet_put_tx_csum(dev, skb); + if (ret) { + ret = NETDEV_TX_OK; + goto out; + } + } + + dma_desc_flags = DMA_SOP; + if (nr_frags == 0) + dma_desc_flags |= DMA_EOP; + + /* Transmit single SKB or head of fragment list */ + ret = bcmgenet_xmit_single(dev, skb, dma_desc_flags, ring); + if (ret) { + ret = NETDEV_TX_OK; + goto out; + } + + /* xmit fragment */ + for (i = 0; i < nr_frags; i++) { + ret = bcmgenet_xmit_frag(dev, + &skb_shinfo(skb)->frags[i], + (i == nr_frags - 1) ? DMA_EOP : 0, ring); + if (ret) { + ret = NETDEV_TX_OK; + goto out; + } + } + + /* we kept a software copy of how much we should advance the TDMA + * producer index, now write it down to the hardware + */ + bcmgenet_tdma_ring_writel(priv, ring->index, + ring->prod_index, TDMA_PROD_INDEX); + + if (ring->free_bds <= (MAX_SKB_FRAGS + 1)) { + netif_stop_subqueue(dev, ring->queue); + ring->int_enable(priv, ring); + } + +out: + spin_unlock_irqrestore(&ring->lock, flags); + + return ret; +} + + +static int bcmgenet_rx_refill(struct bcmgenet_priv *priv, + struct enet_cb *cb) +{ + struct device *kdev = &priv->pdev->dev; + struct sk_buff *skb; + dma_addr_t mapping; + int ret; + + skb = netdev_alloc_skb(priv->dev, + priv->rx_buf_len + SKB_ALIGNMENT); + if (!skb) + return -ENOMEM; + + /* a caller did not release this control block */ + WARN_ON(cb->skb != NULL); + cb->skb = skb; + mapping = dma_map_single(kdev, skb->data, + priv->rx_buf_len, DMA_FROM_DEVICE); + ret = dma_mapping_error(kdev, mapping); + if (ret) { + bcmgenet_free_cb(cb); + netif_err(priv, rx_err, priv->dev, + "%s DMA map failed\n", __func__); + return ret; + } + + dma_unmap_addr_set(cb, dma_addr, mapping); + /* assign packet, prepare descriptor, and advance pointer */ + + dmadesc_set_addr(priv, priv->rx_bd_assign_ptr, mapping); + + /* turn on the newly assigned BD for DMA to use */ + priv->rx_bd_assign_index++; + priv->rx_bd_assign_index &= (priv->num_rx_bds - 1); + + priv->rx_bd_assign_ptr = priv->rx_bds + + (priv->rx_bd_assign_index * DMA_DESC_SIZE); + + return 0; +} + +/* 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 budget) +{ + struct net_device *dev = priv->dev; + struct enet_cb *cb; + struct sk_buff *skb; + u32 dma_length_status; + unsigned long dma_flag; + int len, err; + unsigned int rxpktprocessed = 0, rxpkttoprocess; + unsigned int p_index; + unsigned int chksum_ok = 0; + + p_index = bcmgenet_rdma_ring_readl(priv, + DESC_INDEX, RDMA_PROD_INDEX); + p_index &= DMA_P_INDEX_MASK; + + if (p_index < priv->rx_c_index) + rxpkttoprocess = (DMA_C_INDEX_MASK + 1) - + priv->rx_c_index + p_index; + else + rxpkttoprocess = p_index - priv->rx_c_index; + + netif_dbg(priv, rx_status, dev, + "RDMA: rxpkttoprocess=%d\n", rxpkttoprocess); + + while ((rxpktprocessed < rxpkttoprocess) && + (rxpktprocessed < budget)) { + + /* Unmap the packet contents such that we can use the + * RSV from the 64 bytes descriptor when enabled and save + * a 32-bits register read + */ + cb = &priv->rx_cbs[priv->rx_read_ptr]; + skb = cb->skb; + dma_unmap_single(&dev->dev, dma_unmap_addr(cb, dma_addr), + priv->rx_buf_len, DMA_FROM_DEVICE); + + if (!priv->desc_64b_en) { + dma_length_status = dmadesc_get_length_status(priv, + priv->rx_bds + + (priv->rx_read_ptr * + DMA_DESC_SIZE)); + } else { + struct status_64 *status; + status = (struct status_64 *)skb->data; + dma_length_status = status->length_status; + } + + /* DMA flags and length are still valid no matter how + * we got the Receive Status Vector (64B RSB or register) + */ + dma_flag = dma_length_status & 0xffff; + len = dma_length_status >> DMA_BUFLENGTH_SHIFT; + + netif_dbg(priv, rx_status, dev, + "%s: p_ind=%d c_ind=%d read_ptr=%d len_stat=0x%08x\n", + __func__, p_index, priv->rx_c_index, priv->rx_read_ptr, + dma_length_status); + + rxpktprocessed++; + + priv->rx_read_ptr++; + priv->rx_read_ptr &= (priv->num_rx_bds - 1); + + /* out of memory, just drop packets at the hardware level */ + if (unlikely(!skb)) { + dev->stats.rx_dropped++; + dev->stats.rx_errors++; + goto refill; + } + + if (unlikely(!(dma_flag & DMA_EOP) || !(dma_flag & DMA_SOP))) { + netif_err(priv, rx_status, dev, + "Droping fragmented packet!\n"); + dev->stats.rx_dropped++; + dev->stats.rx_errors++; + dev_kfree_skb_any(cb->skb); + cb->skb = NULL; + goto refill; + } + /* report errors */ + if (unlikely(dma_flag & (DMA_RX_CRC_ERROR | + DMA_RX_OV | + DMA_RX_NO | + DMA_RX_LG | + DMA_RX_RXER))) { + netif_err(priv, rx_status, dev, "dma_flag=0x%x\n", + (unsigned int)dma_flag); + if (dma_flag & DMA_RX_CRC_ERROR) + dev->stats.rx_crc_errors++; + if (dma_flag & DMA_RX_OV) + dev->stats.rx_over_errors++; + if (dma_flag & DMA_RX_NO) + dev->stats.rx_frame_errors++; + if (dma_flag & DMA_RX_LG) + dev->stats.rx_length_errors++; + dev->stats.rx_dropped++; + dev->stats.rx_errors++; + + /* discard the packet and advance consumer index.*/ + dev_kfree_skb_any(cb->skb); + cb->skb = NULL; + goto refill; + } /* error packet */ + + chksum_ok = (dma_flag & priv->dma_rx_chk_bit) && + priv->desc_rxchk_en; + + skb_put(skb, len); + if (priv->desc_64b_en) { + skb_pull(skb, 64); + len -= 64; + } + + if (likely(chksum_ok)) + skb->ip_summed = CHECKSUM_UNNECESSARY; + + /* remove hardware 2bytes added for IP alignment */ + skb_pull(skb, 2); + len -= 2; + + if (priv->crc_fwd_en) { + skb_trim(skb, len - ETH_FCS_LEN); + len -= ETH_FCS_LEN; + } + + /*Finish setting up the received SKB and send it to the kernel*/ + skb->protocol = eth_type_trans(skb, priv->dev); + dev->stats.rx_packets++; + dev->stats.rx_bytes += len; + if (dma_flag & DMA_RX_MULT) + dev->stats.multicast++; + + /* Notify kernel */ + napi_gro_receive(&priv->napi, skb); + cb->skb = NULL; + netif_dbg(priv, rx_status, dev, "pushed up to kernel\n"); + + /* refill RX path on the current control block */ +refill: + err = bcmgenet_rx_refill(priv, cb); + if (err) + netif_err(priv, rx_err, dev, "Rx refill failed\n"); + } + + return rxpktprocessed; +} + +/* Assign skb to RX DMA descriptor. */ +static int bcmgenet_alloc_rx_buffers(struct bcmgenet_priv *priv) +{ + struct enet_cb *cb; + int ret = 0; + int i; + + netif_dbg(priv, hw, priv->dev, "%s:\n", __func__); + + /* loop here for each buffer needing assign */ + for (i = 0; i < priv->num_rx_bds; i++) { + cb = &priv->rx_cbs[priv->rx_bd_assign_index]; + if (cb->skb) + continue; + + /* set the DMA descriptor length once and for all + * it will only change if we support dynamically sizing + * priv->rx_buf_len, but we do not + */ + dmadesc_set_length_status(priv, priv->rx_bd_assign_ptr, + priv->rx_buf_len << DMA_BUFLENGTH_SHIFT); + + ret = bcmgenet_rx_refill(priv, cb); + if (ret) + break; + + } + + return ret; +} + +static void bcmgenet_free_rx_buffers(struct bcmgenet_priv *priv) +{ + struct enet_cb *cb; + int i; + + for (i = 0; i < priv->num_rx_bds; i++) { + cb = &priv->rx_cbs[i]; + + if (dma_unmap_addr(cb, dma_addr)) { + dma_unmap_single(&priv->dev->dev, + dma_unmap_addr(cb, dma_addr), + priv->rx_buf_len, DMA_FROM_DEVICE); + dma_unmap_addr_set(cb, dma_addr, 0); + } + + if (cb->skb) + bcmgenet_free_cb(cb); + } +} + +static int reset_umac(struct bcmgenet_priv *priv) +{ + struct device *kdev = &priv->pdev->dev; + unsigned int timeout = 0; + u32 reg; + + /* 7358a0/7552a0: bad default in RBUF_FLUSH_CTRL.umac_sw_rst */ + bcmgenet_rbuf_ctrl_set(priv, 0); + udelay(10); + + /* disable MAC while updating its registers */ + bcmgenet_umac_writel(priv, 0, UMAC_CMD); + + /* issue soft reset, wait for it to complete */ + bcmgenet_umac_writel(priv, CMD_SW_RESET, UMAC_CMD); + while (timeout++ < 1000) { + reg = bcmgenet_umac_readl(priv, UMAC_CMD); + if (!(reg & CMD_SW_RESET)) + return 0; + + udelay(1); + } + + if (timeout == 1000) { + dev_err(kdev, + "timeout waiting for MAC to come out of resetn\n"); + return -ETIMEDOUT; + } + + return 0; +} + +static int init_umac(struct bcmgenet_priv *priv) +{ + struct device *kdev = &priv->pdev->dev; + int ret; + u32 reg, cpu_mask_clear; + + dev_dbg(&priv->pdev->dev, "bcmgenet: init_umac\n"); + + ret = reset_umac(priv); + if (ret) + return ret; + + bcmgenet_umac_writel(priv, 0, UMAC_CMD); + /* clear tx/rx counter */ + bcmgenet_umac_writel(priv, + MIB_RESET_RX | MIB_RESET_TX | MIB_RESET_RUNT, UMAC_MIB_CTRL); + bcmgenet_umac_writel(priv, 0, UMAC_MIB_CTRL); + + bcmgenet_umac_writel(priv, ENET_MAX_MTU_SIZE, UMAC_MAX_FRAME_LEN); + + /* init rx registers, enable ip header optimization */ + reg = bcmgenet_rbuf_readl(priv, RBUF_CTRL); + reg |= RBUF_ALIGN_2B; + bcmgenet_rbuf_writel(priv, reg, RBUF_CTRL); + + if (!GENET_IS_V1(priv) && !GENET_IS_V2(priv)) + bcmgenet_rbuf_writel(priv, 1, RBUF_TBUF_SIZE_CTRL); + + /* Mask all interrupts.*/ + bcmgenet_intrl2_0_writel(priv, 0xFFFFFFFF, INTRL2_CPU_MASK_SET); + bcmgenet_intrl2_0_writel(priv, 0xFFFFFFFF, INTRL2_CPU_CLEAR); + bcmgenet_intrl2_0_writel(priv, 0, INTRL2_CPU_MASK_CLEAR); + + cpu_mask_clear = UMAC_IRQ_RXDMA_BDONE; + + dev_dbg(kdev, "%s:Enabling RXDMA_BDONE interrupt\n", __func__); + + /* Monitor cable plug/unpluged event for internal PHY */ + if (phy_is_internal(priv->phydev)) + cpu_mask_clear |= (UMAC_IRQ_LINK_DOWN | UMAC_IRQ_LINK_UP); + else if (priv->ext_phy) + cpu_mask_clear |= (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); + + /* bp_mask: back pressure mask */ + if (netif_is_multiqueue(priv->dev)) + reg |= priv->hw_params->bp_in_mask; + else + reg &= ~priv->hw_params->bp_in_mask; + bcmgenet_bp_mc_set(priv, reg); + } + + /* 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; + + bcmgenet_intrl2_0_writel(priv, cpu_mask_clear, + INTRL2_CPU_MASK_CLEAR); + + /* Enable rx/tx engine.*/ + dev_dbg(kdev, "done init umac\n"); + + return 0; +} + +/* Initialize all house-keeping variables for a TX ring, along + * with corresponding hardware registers + */ +static void bcmgenet_init_tx_ring(struct bcmgenet_priv *priv, + unsigned int index, unsigned int size, + unsigned int write_ptr, unsigned int end_ptr) +{ + struct bcmgenet_tx_ring *ring = &priv->tx_rings[index]; + u32 words_per_bd = WORDS_PER_BD(priv); + u32 flow_period_val = 0; + unsigned int first_bd; + + spin_lock_init(&ring->lock); + ring->index = index; + if (index == DESC_INDEX) { + ring->queue = 0; + ring->int_enable = bcmgenet_tx_ring16_int_enable; + ring->int_disable = bcmgenet_tx_ring16_int_disable; + } else { + ring->queue = index + 1; + ring->int_enable = bcmgenet_tx_ring_int_enable; + ring->int_disable = bcmgenet_tx_ring_int_disable; + } + ring->cbs = priv->tx_cbs + write_ptr; + ring->size = size; + ring->c_index = 0; + ring->free_bds = size; + ring->write_ptr = write_ptr; + ring->cb_ptr = write_ptr; + ring->end_ptr = end_ptr - 1; + ring->prod_index = 0; + + /* Set flow period for ring != 16 */ + if (index != DESC_INDEX) + flow_period_val = ENET_MAX_MTU_SIZE << 16; + + bcmgenet_tdma_ring_writel(priv, index, 0, TDMA_PROD_INDEX); + bcmgenet_tdma_ring_writel(priv, index, 0, TDMA_CONS_INDEX); + bcmgenet_tdma_ring_writel(priv, index, 1, DMA_MBUF_DONE_THRESH); + /* Disable rate control for now */ + bcmgenet_tdma_ring_writel(priv, index, flow_period_val, + TDMA_FLOW_PERIOD); + /* Unclassified traffic goes to ring 16 */ + bcmgenet_tdma_ring_writel(priv, index, + ((size << DMA_RING_SIZE_SHIFT) | RX_BUF_LENGTH), + DMA_RING_BUF_SIZE); + + first_bd = write_ptr; + + /* Set start and end address, read and write pointers */ + bcmgenet_tdma_ring_writel(priv, index, first_bd * words_per_bd, + DMA_START_ADDR); + bcmgenet_tdma_ring_writel(priv, index, first_bd * words_per_bd, + TDMA_READ_PTR); + bcmgenet_tdma_ring_writel(priv, index, first_bd, + TDMA_WRITE_PTR); + bcmgenet_tdma_ring_writel(priv, index, end_ptr * words_per_bd - 1, + DMA_END_ADDR); +} + +/* Initialize a RDMA ring */ +static int bcmgenet_init_rx_ring(struct bcmgenet_priv *priv, + unsigned int index, unsigned int size) +{ + u32 words_per_bd = WORDS_PER_BD(priv); + int ret; + + priv->num_rx_bds = TOTAL_DESC; + priv->rx_bds = priv->base + priv->hw_params->rdma_offset; + priv->rx_bd_assign_ptr = priv->rx_bds; + priv->rx_bd_assign_index = 0; + priv->rx_c_index = 0; + priv->rx_read_ptr = 0; + priv->rx_cbs = kzalloc(priv->num_rx_bds * sizeof(struct enet_cb), + GFP_KERNEL); + if (!priv->rx_cbs) + return -ENOMEM; + + ret = bcmgenet_alloc_rx_buffers(priv); + if (ret) { + kfree(priv->rx_cbs); + return ret; + } + + bcmgenet_rdma_ring_writel(priv, index, 0, RDMA_WRITE_PTR); + bcmgenet_rdma_ring_writel(priv, index, 0, RDMA_PROD_INDEX); + bcmgenet_rdma_ring_writel(priv, index, 0, RDMA_CONS_INDEX); + bcmgenet_rdma_ring_writel(priv, index, + ((size << DMA_RING_SIZE_SHIFT) | RX_BUF_LENGTH), + DMA_RING_BUF_SIZE); + bcmgenet_rdma_ring_writel(priv, index, 0, DMA_START_ADDR); + bcmgenet_rdma_ring_writel(priv, index, + words_per_bd * size - 1, DMA_END_ADDR); + bcmgenet_rdma_ring_writel(priv, index, + (DMA_FC_THRESH_LO << DMA_XOFF_THRESHOLD_SHIFT) | + DMA_FC_THRESH_HI, RDMA_XON_XOFF_THRESH); + bcmgenet_rdma_ring_writel(priv, index, 0, RDMA_READ_PTR); + + return ret; +} + +/* init multi xmit queues, only available for GENET2+ + * the queue is partitioned as follows: + * + * queue 0 - 3 is priority based, each one has 32 descriptors, + * with queue 0 being the highest priority queue. + * + * queue 16 is the default tx queue with GENET_DEFAULT_BD_CNT + * descriptors: 256 - (number of tx queues * bds per queues) = 128 + * descriptors. + * + * The transmit control block pool is then partitioned as following: + * - tx_cbs[0...127] are for queue 16 + * - tx_ring_cbs[0] points to tx_cbs[128..159] + * - tx_ring_cbs[1] points to tx_cbs[160..191] + * - tx_ring_cbs[2] points to tx_cbs[192..223] + * - tx_ring_cbs[3] points to tx_cbs[224..255] + */ +static void bcmgenet_init_multiq(struct net_device *dev) +{ + struct bcmgenet_priv *priv = netdev_priv(dev); + unsigned int i, dma_enable; + u32 reg, dma_ctrl, ring_cfg = 0, dma_priority = 0; + + if (!netif_is_multiqueue(dev)) { + netdev_warn(dev, "called with non multi queue aware HW\n"); + return; + } + + dma_ctrl = bcmgenet_tdma_readl(priv, DMA_CTRL); + dma_enable = dma_ctrl & DMA_EN; + dma_ctrl &= ~DMA_EN; + bcmgenet_tdma_writel(priv, dma_ctrl, DMA_CTRL); + + /* Enable strict priority arbiter mode */ + bcmgenet_tdma_writel(priv, DMA_ARBITER_SP, DMA_ARB_CTRL); + + for (i = 0; i < priv->hw_params->tx_queues; i++) { + /* first 64 tx_cbs are reserved for default tx queue + * (ring 16) + */ + bcmgenet_init_tx_ring(priv, i, priv->hw_params->bds_cnt, + i * priv->hw_params->bds_cnt, + (i + 1) * priv->hw_params->bds_cnt); + + /* Configure ring as decriptor ring and setup priority */ + ring_cfg |= 1 << i; + dma_priority |= ((GENET_Q0_PRIORITY + i) << + (GENET_MAX_MQ_CNT + 1) * i); + dma_ctrl |= 1 << (i + DMA_RING_BUF_EN_SHIFT); + } + + /* Enable rings */ + reg = bcmgenet_tdma_readl(priv, DMA_RING_CFG); + reg |= ring_cfg; + bcmgenet_tdma_writel(priv, reg, DMA_RING_CFG); + + /* Use configured rings priority and set ring #16 priority */ + reg = bcmgenet_tdma_readl(priv, DMA_RING_PRIORITY); + reg |= ((GENET_Q0_PRIORITY + priv->hw_params->tx_queues) << 20); + reg |= dma_priority; + bcmgenet_tdma_writel(priv, reg, DMA_PRIORITY); + + /* Configure ring as descriptor ring and re-enable DMA if enabled */ + reg = bcmgenet_tdma_readl(priv, DMA_CTRL); + reg |= dma_ctrl; + if (dma_enable) + reg |= DMA_EN; + bcmgenet_tdma_writel(priv, reg, DMA_CTRL); +} + +static void bcmgenet_fini_dma(struct bcmgenet_priv *priv) +{ + int i; + + /* disable DMA */ + bcmgenet_rdma_writel(priv, 0, DMA_CTRL); + bcmgenet_tdma_writel(priv, 0, DMA_CTRL); + + for (i = 0; i < priv->num_tx_bds; i++) { + if (priv->tx_cbs[i].skb != NULL) { + dev_kfree_skb(priv->tx_cbs[i].skb); + priv->tx_cbs[i].skb = NULL; + } + } + + bcmgenet_free_rx_buffers(priv); + kfree(priv->rx_cbs); + kfree(priv->tx_cbs); +} + +/* init_edma: Initialize DMA control register */ +static int bcmgenet_init_dma(struct bcmgenet_priv *priv) +{ + int ret; + + netif_dbg(priv, hw, priv->dev, "bcmgenet: init_edma\n"); + + /* by default, enable ring 16 (descriptor based) */ + ret = bcmgenet_init_rx_ring(priv, DESC_INDEX, TOTAL_DESC); + if (ret) { + netdev_err(priv->dev, "failed to initialize RX ring\n"); + return ret; + } + + /* init rDma */ + bcmgenet_rdma_writel(priv, DMA_MAX_BURST_LENGTH, DMA_SCB_BURST_SIZE); + + /* Init tDma */ + bcmgenet_tdma_writel(priv, DMA_MAX_BURST_LENGTH, DMA_SCB_BURST_SIZE); + + /* Initialize commont TX ring structures */ + priv->tx_bds = priv->base + priv->hw_params->tdma_offset; + priv->num_tx_bds = TOTAL_DESC; + priv->tx_cbs = kzalloc(priv->num_tx_bds * sizeof(struct enet_cb), + GFP_KERNEL); + if (!priv->tx_cbs) { + bcmgenet_fini_dma(priv); + return -ENOMEM; + } + + /* initialize multi xmit queue */ + bcmgenet_init_multiq(priv->dev); + + /* initialize special ring 16 */ + bcmgenet_init_tx_ring(priv, DESC_INDEX, GENET_DEFAULT_BD_CNT, + priv->hw_params->tx_queues * priv->hw_params->bds_cnt, + TOTAL_DESC); + + return 0; +} + +/* 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; + + /* tx reclaim */ + bcmgenet_tx_reclaim(priv->dev, &priv->tx_rings[DESC_INDEX]); + + work_done = bcmgenet_desc_rx(priv, budget); + + /* Advancing our consumer index*/ + priv->rx_c_index += work_done; + priv->rx_c_index &= DMA_C_INDEX_MASK; + bcmgenet_rdma_ring_writel(priv, DESC_INDEX, + priv->rx_c_index, RDMA_CONS_INDEX); + if (work_done < budget) { + napi_complete(napi); + bcmgenet_intrl2_0_writel(priv, + UMAC_IRQ_RXDMA_BDONE, INTRL2_CPU_MASK_CLEAR); + } + + return work_done; +} + +/* Interrupt bottom half */ +static void bcmgenet_irq_task(struct work_struct *work) +{ + struct bcmgenet_priv *priv = container_of( + work, struct bcmgenet_priv, bcmgenet_irq_work); + + netif_dbg(priv, intr, priv->dev, "%s\n", __func__); + + /* Link UP/DOWN event */ + if ((priv->hw_params->flags & GENET_HAS_MDIO_INTR) && + (priv->irq0_stat & (UMAC_IRQ_LINK_UP|UMAC_IRQ_LINK_DOWN))) { + phy_mac_interrupt(priv->phydev, + priv->irq0_stat & UMAC_IRQ_LINK_UP); + priv->irq0_stat &= ~(UMAC_IRQ_LINK_UP|UMAC_IRQ_LINK_DOWN); + } +} + +/* bcmgenet_isr1: interrupt handler for ring buffer. */ +static irqreturn_t bcmgenet_isr1(int irq, void *dev_id) +{ + struct bcmgenet_priv *priv = dev_id; + unsigned int index; + + /* Save irq status for bottom-half processing. */ + priv->irq1_stat = + bcmgenet_intrl2_1_readl(priv, INTRL2_CPU_STAT) & + ~priv->int1_mask; + /* clear inerrupts*/ + 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 + */ + if (priv->irq1_stat & 0x0000ffff) { + index = 0; + for (index = 0; index < 16; index++) { + if (priv->irq1_stat & (1 << index)) + bcmgenet_tx_reclaim(priv->dev, + &priv->tx_rings[index]); + } + } + return IRQ_HANDLED; +} + +/* bcmgenet_isr0: Handle various interrupts. */ +static irqreturn_t bcmgenet_isr0(int irq, void *dev_id) +{ + struct bcmgenet_priv *priv = dev_id; + + /* 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 inerrupts*/ + bcmgenet_intrl2_0_writel(priv, priv->irq0_stat, INTRL2_CPU_CLEAR); + + netif_dbg(priv, intr, priv->dev, + "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); + } + } + if (priv->irq0_stat & + (UMAC_IRQ_TXDMA_BDONE | UMAC_IRQ_TXDMA_PDONE)) { + /* Tx reclaim */ + bcmgenet_tx_reclaim(priv->dev, &priv->tx_rings[DESC_INDEX]); + } + if (priv->irq0_stat & (UMAC_IRQ_PHY_DET_R | + UMAC_IRQ_PHY_DET_F | + UMAC_IRQ_LINK_UP | + UMAC_IRQ_LINK_DOWN | + UMAC_IRQ_HFB_SM | + UMAC_IRQ_HFB_MM | + UMAC_IRQ_MPD_R)) { + /* all other interested interrupts handled in bottom half */ + schedule_work(&priv->bcmgenet_irq_work); + } + + if ((priv->hw_params->flags & GENET_HAS_MDIO_INTR) && + priv->irq0_stat & (UMAC_IRQ_MDIO_DONE | UMAC_IRQ_MDIO_ERROR)) { + priv->irq0_stat &= ~(UMAC_IRQ_MDIO_DONE | UMAC_IRQ_MDIO_ERROR); + wake_up(&priv->wq); + } + + return IRQ_HANDLED; +} + +static void bcmgenet_umac_reset(struct bcmgenet_priv *priv) +{ + u32 reg; + + reg = bcmgenet_rbuf_ctrl_get(priv); + reg |= BIT(1); + bcmgenet_rbuf_ctrl_set(priv, reg); + udelay(10); + + reg &= ~BIT(1); + bcmgenet_rbuf_ctrl_set(priv, reg); + udelay(10); +} + +static void bcmgenet_set_hw_addr(struct bcmgenet_priv *priv, + unsigned char *addr) +{ + bcmgenet_umac_writel(priv, (addr[0] << 24) | (addr[1] << 16) | + (addr[2] << 8) | addr[3], UMAC_MAC0); + bcmgenet_umac_writel(priv, (addr[4] << 8) | addr[5], UMAC_MAC1); +} + +static int bcmgenet_wol_resume(struct bcmgenet_priv *priv) +{ + int ret; + + /* From WOL-enabled suspend, switch to regular clock */ + clk_disable(priv->clk_wol); + /* init umac registers to synchronize s/w with h/w */ + ret = init_umac(priv); + if (ret) + return ret; + + phy_init_hw(priv->phydev); + /* Speed settings must be restored */ + bcmgenet_mii_config(priv->dev); + + return 0; +} + +/* Returns a reusable dma control register value */ +static u32 bcmgenet_dma_disable(struct bcmgenet_priv *priv) +{ + u32 reg; + u32 dma_ctrl; + + /* disable DMA */ + dma_ctrl = 1 << (DESC_INDEX + DMA_RING_BUF_EN_SHIFT) | DMA_EN; + reg = bcmgenet_tdma_readl(priv, DMA_CTRL); + reg &= ~dma_ctrl; + bcmgenet_tdma_writel(priv, reg, DMA_CTRL); + + reg = bcmgenet_rdma_readl(priv, DMA_CTRL); + reg &= ~dma_ctrl; + bcmgenet_rdma_writel(priv, reg, DMA_CTRL); + + bcmgenet_umac_writel(priv, 1, UMAC_TX_FLUSH); + udelay(10); + bcmgenet_umac_writel(priv, 0, UMAC_TX_FLUSH); + + return dma_ctrl; +} + +static void bcmgenet_enable_dma(struct bcmgenet_priv *priv, u32 dma_ctrl) +{ + u32 reg; + + reg = bcmgenet_rdma_readl(priv, DMA_CTRL); + reg |= dma_ctrl; + bcmgenet_rdma_writel(priv, reg, DMA_CTRL); + + reg = bcmgenet_tdma_readl(priv, DMA_CTRL); + reg |= dma_ctrl; + bcmgenet_tdma_writel(priv, reg, DMA_CTRL); +} + +static int bcmgenet_open(struct net_device *dev) +{ + struct bcmgenet_priv *priv = netdev_priv(dev); + unsigned long dma_ctrl; + u32 reg; + int ret; + + netif_dbg(priv, ifup, dev, "bcmgenet_open\n"); + + /* Turn on the clock */ + if (!IS_ERR(priv->clk)) + clk_prepare_enable(priv->clk); + + /* take MAC out of reset */ + bcmgenet_umac_reset(priv); + + ret = init_umac(priv); + if (ret) + goto err_clk_disable; + + /* disable ethernet MAC while updating its registers */ + reg = bcmgenet_umac_readl(priv, UMAC_CMD); + reg &= ~(CMD_TX_EN | CMD_RX_EN); + bcmgenet_umac_writel(priv, reg, UMAC_CMD); + + bcmgenet_set_hw_addr(priv, dev->dev_addr); + + if (priv->wol_enabled) { + ret = bcmgenet_wol_resume(priv); + if (ret) + return ret; + } + + if (phy_is_internal(priv->phydev)) { + reg = bcmgenet_ext_readl(priv, EXT_EXT_PWR_MGMT); + reg |= EXT_ENERGY_DET_MASK; + bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT); + } + + /* Disable RX/TX DMA and flush TX queues */ + dma_ctrl = bcmgenet_dma_disable(priv); + + /* Reinitialize TDMA and RDMA and SW housekeeping */ + ret = bcmgenet_init_dma(priv); + if (ret) { + netdev_err(dev, "failed to initialize DMA\n"); + goto err_fini_dma; + } + + /* Always enable ring 16 - descriptor ring */ + bcmgenet_enable_dma(priv, dma_ctrl); + + ret = request_irq(priv->irq0, bcmgenet_isr0, IRQF_SHARED, + dev->name, priv); + if (ret < 0) { + netdev_err(dev, "can't request IRQ %d\n", priv->irq0); + goto err_fini_dma; + } + + ret = request_irq(priv->irq1, bcmgenet_isr1, IRQF_SHARED, + dev->name, priv); + if (ret < 0) { + netdev_err(dev, "can't request IRQ %d\n", priv->irq1); + goto err_irq0; + } + + /* Start the network engine */ + napi_enable(&priv->napi); + + reg = bcmgenet_umac_readl(priv, UMAC_CMD); + reg |= (CMD_TX_EN | CMD_RX_EN); + bcmgenet_umac_writel(priv, reg, UMAC_CMD); + + /* Make sure we reflect the value of CRC_CMD_FWD */ + priv->crc_fwd_en = !!(reg & CMD_CRC_FWD); + + device_set_wakeup_capable(&dev->dev, 1); + + if (phy_is_internal(priv->phydev)) + bcmgenet_power_up(priv, GENET_POWER_PASSIVE); + + netif_tx_start_all_queues(dev); + + phy_start(priv->phydev); + + return 0; + +err_irq0: + free_irq(priv->irq0, dev); +err_fini_dma: + bcmgenet_fini_dma(priv); +err_clk_disable: + if (!IS_ERR(priv->clk)) + clk_disable_unprepare(priv->clk); + return ret; +} + +static int bcmgenet_dma_teardown(struct bcmgenet_priv *priv) +{ + int ret = 0; + int timeout = 0; + u32 reg; + + /* Disable TDMA to stop add more frames in TX DMA */ + reg = bcmgenet_tdma_readl(priv, DMA_CTRL); + reg &= ~DMA_EN; + bcmgenet_tdma_writel(priv, reg, DMA_CTRL); + + /* Check TDMA status register to confirm TDMA is disabled */ + while (timeout++ < DMA_TIMEOUT_VAL) { + reg = bcmgenet_tdma_readl(priv, DMA_STATUS); + if (reg & DMA_DISABLED) + break; + + udelay(1); + } + + if (timeout == DMA_TIMEOUT_VAL) { + netdev_warn(priv->dev, + "Timed out while disabling TX DMA\n"); + ret = -ETIMEDOUT; + } + + /* Wait 10ms for packet drain in both tx and rx dma */ + usleep_range(10000, 20000); + + /* Disable RDMA */ + reg = bcmgenet_rdma_readl(priv, DMA_CTRL); + reg &= ~DMA_EN; + bcmgenet_rdma_writel(priv, reg, DMA_CTRL); + + timeout = 0; + /* Check RDMA status register to confirm RDMA is disabled */ + while (timeout++ < DMA_TIMEOUT_VAL) { + reg = bcmgenet_rdma_readl(priv, DMA_STATUS); + if (reg & DMA_DISABLED) + break; + + udelay(1); + } + + if (timeout == DMA_TIMEOUT_VAL) { + netdev_warn(priv->dev, + "Timed out while disabling RX DMA\n"); + ret = -ETIMEDOUT; + } + + return ret; +} + +static int bcmgenet_close(struct net_device *dev) +{ + struct bcmgenet_priv *priv = netdev_priv(dev); + int ret; + u32 reg; + + netif_dbg(priv, ifdown, dev, "bcmgenet_close\n"); + + phy_stop(priv->phydev); + + /* Disable MAC receive */ + reg = bcmgenet_umac_readl(priv, UMAC_CMD); + reg &= ~CMD_RX_EN; + bcmgenet_umac_writel(priv, reg, UMAC_CMD); + + netif_tx_stop_all_queues(dev); + + ret = bcmgenet_dma_teardown(priv); + if (ret) + return ret; + + /* Disable MAC transmit. TX DMA disabled have to done before this */ + reg = bcmgenet_umac_readl(priv, UMAC_CMD); + reg &= ~CMD_TX_EN; + bcmgenet_umac_writel(priv, reg, UMAC_CMD); + + napi_disable(&priv->napi); + + /* tx reclaim */ + bcmgenet_tx_reclaim_all(dev); + bcmgenet_fini_dma(priv); + + free_irq(priv->irq0, priv); + free_irq(priv->irq1, priv); + + /* Wait for pending work items to complete - we are stopping + * the clock now. Since interrupts are disabled, no new work + * will be scheduled. + */ + cancel_work_sync(&priv->bcmgenet_irq_work); + + if (phy_is_internal(priv->phydev)) + bcmgenet_power_down(priv, GENET_POWER_PASSIVE); + + if (priv->wol_enabled) + clk_enable(priv->clk_wol); + + if (!IS_ERR(priv->clk)) + clk_disable_unprepare(priv->clk); + + return 0; +} + +static void bcmgenet_timeout(struct net_device *dev) +{ + struct bcmgenet_priv *priv = netdev_priv(dev); + + netif_dbg(priv, tx_err, dev, "bcmgenet_timeout\n"); + + dev->trans_start = jiffies; + + dev->stats.tx_errors++; + + netif_tx_wake_all_queues(dev); +} + +#define MAX_MC_COUNT 16 + +static inline void bcmgenet_set_mdf_addr(struct bcmgenet_priv *priv, + unsigned char *addr, + int *i, + int *mc) +{ + u32 reg; + + bcmgenet_umac_writel(priv, + addr[0] << 8 | addr[1], UMAC_MDF_ADDR + (*i * 4)); + bcmgenet_umac_writel(priv, + addr[2] << 24 | addr[3] << 16 | + addr[4] << 8 | addr[5], + UMAC_MDF_ADDR + ((*i + 1) * 4)); + reg = bcmgenet_umac_readl(priv, UMAC_MDF_CTRL); + reg |= (1 << (MAX_MC_COUNT - *mc)); + bcmgenet_umac_writel(priv, reg, UMAC_MDF_CTRL); + *i += 2; + (*mc)++; +} + +static void bcmgenet_set_rx_mode(struct net_device *dev) +{ + struct bcmgenet_priv *priv = netdev_priv(dev); + struct netdev_hw_addr *ha; + int i, mc; + u32 reg; + + netif_dbg(priv, hw, dev, "%s: %08X\n", __func__, dev->flags); + + /* Promiscous mode */ + reg = bcmgenet_umac_readl(priv, UMAC_CMD); + if (dev->flags & IFF_PROMISC) { + reg |= CMD_PROMISC; + bcmgenet_umac_writel(priv, reg, UMAC_CMD); + bcmgenet_umac_writel(priv, 0, UMAC_MDF_CTRL); + return; + } else { + reg &= ~CMD_PROMISC; + bcmgenet_umac_writel(priv, reg, UMAC_CMD); + } + + /* UniMac doesn't support ALLMULTI */ + if (dev->flags & IFF_ALLMULTI) { + netdev_warn(dev, "ALLMULTI is not supported\n"); + return; + } + + /* update MDF filter */ + i = 0; + mc = 0; + /* Broadcast */ + bcmgenet_set_mdf_addr(priv, dev->broadcast, &i, &mc); + /* my own address.*/ + bcmgenet_set_mdf_addr(priv, dev->dev_addr, &i, &mc); + /* Unicast list*/ + if (netdev_uc_count(dev) > (MAX_MC_COUNT - mc)) + return; + + if (!netdev_uc_empty(dev)) + netdev_for_each_uc_addr(ha, dev) + bcmgenet_set_mdf_addr(priv, ha->addr, &i, &mc); + /* Multicast */ + if (netdev_mc_empty(dev) || netdev_mc_count(dev) >= (MAX_MC_COUNT - mc)) + return; + + netdev_for_each_mc_addr(ha, dev) + bcmgenet_set_mdf_addr(priv, ha->addr, &i, &mc); +} + +/* Set the hardware MAC address. */ +static int bcmgenet_set_mac_addr(struct net_device *dev, void *p) +{ + struct sockaddr *addr = p; + + /* Setting the MAC address at the hardware level is not possible + * without disabling the UniMAC RX/TX enable bits. + */ + if (netif_running(dev)) + return -EBUSY; + + ether_addr_copy(dev->dev_addr, addr->sa_data); + + return 0; +} + +static const struct net_device_ops bcmgenet_netdev_ops = { + .ndo_open = bcmgenet_open, + .ndo_stop = bcmgenet_close, + .ndo_start_xmit = bcmgenet_xmit, + .ndo_tx_timeout = bcmgenet_timeout, + .ndo_set_rx_mode = bcmgenet_set_rx_mode, + .ndo_set_mac_address = bcmgenet_set_mac_addr, + .ndo_do_ioctl = bcmgenet_ioctl, + .ndo_set_features = bcmgenet_set_features, +}; + +/* Array of GENET hardware parameters/characteristics */ +static struct bcmgenet_hw_params bcmgenet_hw_params[] = { + [GENET_V1] = { + .tx_queues = 0, + .rx_queues = 0, + .bds_cnt = 0, + .bp_in_en_shift = 16, + .bp_in_mask = 0xffff, + .hfb_filter_cnt = 16, + .qtag_mask = 0x1F, + .hfb_offset = 0x1000, + .rdma_offset = 0x2000, + .tdma_offset = 0x3000, + .words_per_bd = 2, + }, + [GENET_V2] = { + .tx_queues = 4, + .rx_queues = 4, + .bds_cnt = 32, + .bp_in_en_shift = 16, + .bp_in_mask = 0xffff, + .hfb_filter_cnt = 16, + .qtag_mask = 0x1F, + .tbuf_offset = 0x0600, + .hfb_offset = 0x1000, + .hfb_reg_offset = 0x2000, + .rdma_offset = 0x3000, + .tdma_offset = 0x4000, + .words_per_bd = 2, + .flags = GENET_HAS_EXT, + }, + [GENET_V3] = { + .tx_queues = 4, + .rx_queues = 4, + .bds_cnt = 32, + .bp_in_en_shift = 17, + .bp_in_mask = 0x1ffff, + .hfb_filter_cnt = 48, + .qtag_mask = 0x3F, + .tbuf_offset = 0x0600, + .hfb_offset = 0x8000, + .hfb_reg_offset = 0xfc00, + .rdma_offset = 0x10000, + .tdma_offset = 0x11000, + .words_per_bd = 2, + .flags = GENET_HAS_EXT | GENET_HAS_MDIO_INTR, + }, + [GENET_V4] = { + .tx_queues = 4, + .rx_queues = 4, + .bds_cnt = 32, + .bp_in_en_shift = 17, + .bp_in_mask = 0x1ffff, + .hfb_filter_cnt = 48, + .qtag_mask = 0x3F, + .tbuf_offset = 0x0600, + .hfb_offset = 0x8000, + .hfb_reg_offset = 0xfc00, + .rdma_offset = 0x2000, + .tdma_offset = 0x4000, + .words_per_bd = 3, + .flags = GENET_HAS_40BITS | GENET_HAS_EXT | GENET_HAS_MDIO_INTR, + }, +}; + +/* Infer hardware parameters from the detected GENET version */ +static void bcmgenet_set_hw_params(struct bcmgenet_priv *priv) +{ + struct bcmgenet_hw_params *params; + u32 reg; + u8 major; + + if (GENET_IS_V4(priv)) { + bcmgenet_dma_regs = bcmgenet_dma_regs_v3plus; + genet_dma_ring_regs = genet_dma_ring_regs_v4; + priv->dma_rx_chk_bit = DMA_RX_CHK_V3PLUS; + priv->version = GENET_V4; + } else if (GENET_IS_V3(priv)) { + bcmgenet_dma_regs = bcmgenet_dma_regs_v3plus; + genet_dma_ring_regs = genet_dma_ring_regs_v123; + priv->dma_rx_chk_bit = DMA_RX_CHK_V3PLUS; + priv->version = GENET_V3; + } else if (GENET_IS_V2(priv)) { + bcmgenet_dma_regs = bcmgenet_dma_regs_v2; + genet_dma_ring_regs = genet_dma_ring_regs_v123; + priv->dma_rx_chk_bit = DMA_RX_CHK_V12; + priv->version = GENET_V2; + } else if (GENET_IS_V1(priv)) { + bcmgenet_dma_regs = bcmgenet_dma_regs_v1; + genet_dma_ring_regs = genet_dma_ring_regs_v123; + priv->dma_rx_chk_bit = DMA_RX_CHK_V12; + priv->version = GENET_V1; + } + + /* enum genet_version starts at 1 */ + priv->hw_params = &bcmgenet_hw_params[priv->version]; + params = priv->hw_params; + + /* Read GENET HW version */ + reg = bcmgenet_sys_readl(priv, SYS_REV_CTRL); + major = (reg >> 24 & 0x0f); + if (major == 5) + major = 4; + else if (major == 0) + major = 1; + if (major != priv->version) { + dev_err(&priv->pdev->dev, + "GENET version mismatch, got: %d, configured for: %d\n", + major, priv->version); + } + + /* Print the GENET core version */ + dev_info(&priv->pdev->dev, "GENET " GENET_VER_FMT, + major, (reg >> 16) & 0x0f, reg & 0xffff); + +#ifdef CONFIG_PHYS_ADDR_T_64BIT + if (!(params->flags & GENET_HAS_40BITS)) + pr_warn("GENET does not support 40-bits PA\n"); +#endif + + pr_debug("Configuration for version: %d\n" + "TXq: %1d, RXq: %1d, BDs: %1d\n" + "BP << en: %2d, BP msk: 0x%05x\n" + "HFB count: %2d, QTAQ msk: 0x%05x\n" + "TBUF: 0x%04x, HFB: 0x%04x, HFBreg: 0x%04x\n" + "RDMA: 0x%05x, TDMA: 0x%05x\n" + "Words/BD: %d\n", + priv->version, + params->tx_queues, params->rx_queues, params->bds_cnt, + params->bp_in_en_shift, params->bp_in_mask, + params->hfb_filter_cnt, params->qtag_mask, + params->tbuf_offset, params->hfb_offset, + params->hfb_reg_offset, + params->rdma_offset, params->tdma_offset, + params->words_per_bd); +} + +static const struct of_device_id bcmgenet_match[] = { + { .compatible = "brcm,genet-v1", .data = (void *)GENET_V1 }, + { .compatible = "brcm,genet-v2", .data = (void *)GENET_V2 }, + { .compatible = "brcm,genet-v3", .data = (void *)GENET_V3 }, + { .compatible = "brcm,genet-v4", .data = (void *)GENET_V4 }, + { }, +}; + +static int bcmgenet_probe(struct platform_device *pdev) +{ + struct device_node *dn = pdev->dev.of_node; + const struct of_device_id *of_id; + struct bcmgenet_priv *priv; + struct net_device *dev; + const void *macaddr; + struct resource *r; + int err = -EIO; + + /* Up to GENET_MAX_MQ_CNT + 1 TX queues and a single RX queue */ + dev = alloc_etherdev_mqs(sizeof(*priv), GENET_MAX_MQ_CNT + 1, 1); + if (!dev) { + dev_err(&pdev->dev, "can't allocate net device\n"); + return -ENOMEM; + } + + of_id = of_match_node(bcmgenet_match, dn); + if (!of_id) + return -EINVAL; + + priv = netdev_priv(dev); + priv->irq0 = platform_get_irq(pdev, 0); + priv->irq1 = platform_get_irq(pdev, 1); + if (!priv->irq0 || !priv->irq1) { + dev_err(&pdev->dev, "can't find IRQs\n"); + err = -EINVAL; + goto err; + } + + macaddr = of_get_mac_address(dn); + if (!macaddr) { + dev_err(&pdev->dev, "can't find MAC address\n"); + err = -EINVAL; + goto err; + } + + r = platform_get_resource(pdev, IORESOURCE_MEM, 0); + priv->base = devm_ioremap_resource(&pdev->dev, r); + if (IS_ERR(priv->base)) { + err = PTR_ERR(priv->base); + goto err; + } + + SET_NETDEV_DEV(dev, &pdev->dev); + dev_set_drvdata(&pdev->dev, dev); + ether_addr_copy(dev->dev_addr, macaddr); + dev->watchdog_timeo = 2 * HZ; + SET_ETHTOOL_OPS(dev, &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); + + /* Set hardware features */ + dev->hw_features |= NETIF_F_SG | NETIF_F_IP_CSUM | + NETIF_F_IPV6_CSUM | NETIF_F_RXCSUM; + + /* Set the needed headroom to account for any possible + * features enabling/disabling at runtime + */ + dev->needed_headroom += 64; + + netdev_boot_setup_check(dev); + + priv->dev = dev; + priv->pdev = pdev; + priv->version = (enum bcmgenet_version)of_id->data; + + bcmgenet_set_hw_params(priv); + + spin_lock_init(&priv->lock); + /* Mii wait queue */ + init_waitqueue_head(&priv->wq); + /* Always use RX_BUF_LENGTH (2KB) buffer for all chips */ + priv->rx_buf_len = RX_BUF_LENGTH; + INIT_WORK(&priv->bcmgenet_irq_work, bcmgenet_irq_task); + + priv->clk = devm_clk_get(&priv->pdev->dev, "enet"); + if (IS_ERR(priv->clk)) + dev_warn(&priv->pdev->dev, "failed to get enet clock\n"); + + priv->clk_wol = devm_clk_get(&priv->pdev->dev, "enet-wol"); + if (IS_ERR(priv->clk_wol)) + dev_warn(&priv->pdev->dev, "failed to get enet-wol clock\n"); + + if (!IS_ERR(priv->clk)) + clk_prepare_enable(priv->clk); + + err = reset_umac(priv); + if (err) + goto err_clk_disable; + + err = bcmgenet_mii_init(dev); + if (err) + goto err_clk_disable; + + /* setup number of real queues + 1 (GENET_V1 has 0 hardware queues + * just the ring 16 descriptor based TX + */ + netif_set_real_num_tx_queues(priv->dev, priv->hw_params->tx_queues + 1); + netif_set_real_num_rx_queues(priv->dev, priv->hw_params->rx_queues + 1); + + err = register_netdev(dev); + if (err) + goto err_clk_disable; + + /* Turn off the main clock, WOL clock is handled separately */ + if (!IS_ERR(priv->clk)) + clk_disable_unprepare(priv->clk); + + return err; + +err_clk_disable: + if (!IS_ERR(priv->clk)) + clk_disable_unprepare(priv->clk); +err: + free_netdev(dev); + return err; +} + +static int bcmgenet_remove(struct platform_device *pdev) +{ + struct bcmgenet_priv *priv = dev_to_priv(&pdev->dev); + + dev_set_drvdata(&pdev->dev, NULL); + unregister_netdev(priv->dev); + bcmgenet_mii_exit(priv->dev); + free_netdev(priv->dev); + + return 0; +} + + +static struct platform_driver bcmgenet_driver = { + .probe = bcmgenet_probe, + .remove = bcmgenet_remove, + .driver = { + .name = "bcmgenet", + .owner = THIS_MODULE, + .of_match_table = bcmgenet_match, + }, +}; +module_platform_driver(bcmgenet_driver); + +MODULE_AUTHOR("Broadcom Corporation"); +MODULE_DESCRIPTION("Broadcom GENET Ethernet controller driver"); +MODULE_ALIAS("platform:bcmgenet"); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h new file mode 100644 index 000000000000..a6758adefaab --- /dev/null +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h @@ -0,0 +1,629 @@ +/* + * Copyright (c) 2014 Broadcom Corporation + * + * 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. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + * +*/ +#ifndef __BCMGENET_H__ +#define __BCMGENET_H__ + +#include <linux/skbuff.h> +#include <linux/netdevice.h> +#include <linux/spinlock.h> +#include <linux/clk.h> +#include <linux/mii.h> +#include <linux/if_vlan.h> +#include <linux/phy.h> + +/* total number of Buffer Descriptors, same for Rx/Tx */ +#define TOTAL_DESC 256 + +/* which ring is descriptor based */ +#define DESC_INDEX 16 + +/* Body(1500) + EH_SIZE(14) + VLANTAG(4) + BRCMTAG(6) + FCS(4) = 1528. + * 1536 is multiple of 256 bytes + */ +#define ENET_BRCM_TAG_LEN 6 +#define ENET_PAD 8 +#define ENET_MAX_MTU_SIZE (ETH_DATA_LEN + ETH_HLEN + VLAN_HLEN + \ + ENET_BRCM_TAG_LEN + ETH_FCS_LEN + ENET_PAD) +#define DMA_MAX_BURST_LENGTH 0x10 + +/* misc. configuration */ +#define CLEAR_ALL_HFB 0xFF +#define DMA_FC_THRESH_HI (TOTAL_DESC >> 4) +#define DMA_FC_THRESH_LO 5 + +/* 64B receive/transmit status block */ +struct status_64 { + u32 length_status; /* length and peripheral status */ + u32 ext_status; /* Extended status*/ + u32 rx_csum; /* partial rx checksum */ + u32 unused1[9]; /* unused */ + u32 tx_csum_info; /* Tx checksum info. */ + u32 unused2[3]; /* unused */ +}; + +/* Rx status bits */ +#define STATUS_RX_EXT_MASK 0x1FFFFF +#define STATUS_RX_CSUM_MASK 0xFFFF +#define STATUS_RX_CSUM_OK 0x10000 +#define STATUS_RX_CSUM_FR 0x20000 +#define STATUS_RX_PROTO_TCP 0 +#define STATUS_RX_PROTO_UDP 1 +#define STATUS_RX_PROTO_ICMP 2 +#define STATUS_RX_PROTO_OTHER 3 +#define STATUS_RX_PROTO_MASK 3 +#define STATUS_RX_PROTO_SHIFT 18 +#define STATUS_FILTER_INDEX_MASK 0xFFFF +/* Tx status bits */ +#define STATUS_TX_CSUM_START_MASK 0X7FFF +#define STATUS_TX_CSUM_START_SHIFT 16 +#define STATUS_TX_CSUM_PROTO_UDP 0x8000 +#define STATUS_TX_CSUM_OFFSET_MASK 0x7FFF +#define STATUS_TX_CSUM_LV 0x80000000 + +/* DMA Descriptor */ +#define DMA_DESC_LENGTH_STATUS 0x00 /* in bytes of data in buffer */ +#define DMA_DESC_ADDRESS_LO 0x04 /* lower bits of PA */ +#define DMA_DESC_ADDRESS_HI 0x08 /* upper 32 bits of PA, GENETv4+ */ + +/* Rx/Tx common counter group */ +struct bcmgenet_pkt_counters { + u32 cnt_64; /* RO Received/Transmited 64 bytes packet */ + u32 cnt_127; /* RO Rx/Tx 127 bytes packet */ + u32 cnt_255; /* RO Rx/Tx 65-255 bytes packet */ + u32 cnt_511; /* RO Rx/Tx 256-511 bytes packet */ + u32 cnt_1023; /* RO Rx/Tx 512-1023 bytes packet */ + u32 cnt_1518; /* RO Rx/Tx 1024-1518 bytes packet */ + u32 cnt_mgv; /* RO Rx/Tx 1519-1522 good VLAN packet */ + u32 cnt_2047; /* RO Rx/Tx 1522-2047 bytes packet*/ + u32 cnt_4095; /* RO Rx/Tx 2048-4095 bytes packet*/ + u32 cnt_9216; /* RO Rx/Tx 4096-9216 bytes packet*/ +}; + +/* RSV, Receive Status Vector */ +struct bcmgenet_rx_counters { + struct bcmgenet_pkt_counters pkt_cnt; + u32 pkt; /* RO (0x428) Received pkt count*/ + u32 bytes; /* RO Received byte count */ + u32 mca; /* RO # of Received multicast pkt */ + u32 bca; /* RO # of Receive broadcast pkt */ + u32 fcs; /* RO # of Received FCS error */ + u32 cf; /* RO # of Received control frame pkt*/ + u32 pf; /* RO # of Received pause frame pkt */ + u32 uo; /* RO # of unknown op code pkt */ + u32 aln; /* RO # of alignment error count */ + u32 flr; /* RO # of frame length out of range count */ + u32 cde; /* RO # of code error pkt */ + u32 fcr; /* RO # of carrier sense error pkt */ + u32 ovr; /* RO # of oversize pkt*/ + u32 jbr; /* RO # of jabber count */ + u32 mtue; /* RO # of MTU error pkt*/ + u32 pok; /* RO # of Received good pkt */ + u32 uc; /* RO # of unicast pkt */ + u32 ppp; /* RO # of PPP pkt */ + u32 rcrc; /* RO (0x470),# of CRC match pkt */ +}; + +/* TSV, Transmit Status Vector */ +struct bcmgenet_tx_counters { + struct bcmgenet_pkt_counters pkt_cnt; + u32 pkts; /* RO (0x4a8) Transmited pkt */ + u32 mca; /* RO # of xmited multicast pkt */ + u32 bca; /* RO # of xmited broadcast pkt */ + u32 pf; /* RO # of xmited pause frame count */ + u32 cf; /* RO # of xmited control frame count */ + u32 fcs; /* RO # of xmited FCS error count */ + u32 ovr; /* RO # of xmited oversize pkt */ + u32 drf; /* RO # of xmited deferral pkt */ + u32 edf; /* RO # of xmited Excessive deferral pkt*/ + u32 scl; /* RO # of xmited single collision pkt */ + u32 mcl; /* RO # of xmited multiple collision pkt*/ + u32 lcl; /* RO # of xmited late collision pkt */ + u32 ecl; /* RO # of xmited excessive collision pkt*/ + u32 frg; /* RO # of xmited fragments pkt*/ + u32 ncl; /* RO # of xmited total collision count */ + u32 jbr; /* RO # of xmited jabber count*/ + u32 bytes; /* RO # of xmited byte count */ + u32 pok; /* RO # of xmited good pkt */ + u32 uc; /* RO (0x0x4f0)# of xmited unitcast pkt */ +}; + +struct bcmgenet_mib_counters { + struct bcmgenet_rx_counters rx; + struct bcmgenet_tx_counters tx; + u32 rx_runt_cnt; + u32 rx_runt_fcs; + u32 rx_runt_fcs_align; + u32 rx_runt_bytes; + u32 rbuf_ovflow_cnt; + u32 rbuf_err_cnt; + u32 mdf_err_cnt; +}; + +#define UMAC_HD_BKP_CTRL 0x004 +#define HD_FC_EN (1 << 0) +#define HD_FC_BKOFF_OK (1 << 1) +#define IPG_CONFIG_RX_SHIFT 2 +#define IPG_CONFIG_RX_MASK 0x1F + +#define UMAC_CMD 0x008 +#define CMD_TX_EN (1 << 0) +#define CMD_RX_EN (1 << 1) +#define UMAC_SPEED_10 0 +#define UMAC_SPEED_100 1 +#define UMAC_SPEED_1000 2 +#define UMAC_SPEED_2500 3 +#define CMD_SPEED_SHIFT 2 +#define CMD_SPEED_MASK 3 +#define CMD_PROMISC (1 << 4) +#define CMD_PAD_EN (1 << 5) +#define CMD_CRC_FWD (1 << 6) +#define CMD_PAUSE_FWD (1 << 7) +#define CMD_RX_PAUSE_IGNORE (1 << 8) +#define CMD_TX_ADDR_INS (1 << 9) +#define CMD_HD_EN (1 << 10) +#define CMD_SW_RESET (1 << 13) +#define CMD_LCL_LOOP_EN (1 << 15) +#define CMD_AUTO_CONFIG (1 << 22) +#define CMD_CNTL_FRM_EN (1 << 23) +#define CMD_NO_LEN_CHK (1 << 24) +#define CMD_RMT_LOOP_EN (1 << 25) +#define CMD_PRBL_EN (1 << 27) +#define CMD_TX_PAUSE_IGNORE (1 << 28) +#define CMD_TX_RX_EN (1 << 29) +#define CMD_RUNT_FILTER_DIS (1 << 30) + +#define UMAC_MAC0 0x00C +#define UMAC_MAC1 0x010 +#define UMAC_MAX_FRAME_LEN 0x014 + +#define UMAC_TX_FLUSH 0x334 + +#define UMAC_MIB_START 0x400 + +#define UMAC_MDIO_CMD 0x614 +#define MDIO_START_BUSY (1 << 29) +#define MDIO_READ_FAIL (1 << 28) +#define MDIO_RD (2 << 26) +#define MDIO_WR (1 << 26) +#define MDIO_PMD_SHIFT 21 +#define MDIO_PMD_MASK 0x1F +#define MDIO_REG_SHIFT 16 +#define MDIO_REG_MASK 0x1F + +#define UMAC_RBUF_OVFL_CNT 0x61C + +#define UMAC_MPD_CTRL 0x620 +#define MPD_EN (1 << 0) +#define MPD_PW_EN (1 << 27) +#define MPD_MSEQ_LEN_SHIFT 16 +#define MPD_MSEQ_LEN_MASK 0xFF + +#define UMAC_MPD_PW_MS 0x624 +#define UMAC_MPD_PW_LS 0x628 +#define UMAC_RBUF_ERR_CNT 0x634 +#define UMAC_MDF_ERR_CNT 0x638 +#define UMAC_MDF_CTRL 0x650 +#define UMAC_MDF_ADDR 0x654 +#define UMAC_MIB_CTRL 0x580 +#define MIB_RESET_RX (1 << 0) +#define MIB_RESET_RUNT (1 << 1) +#define MIB_RESET_TX (1 << 2) + +#define RBUF_CTRL 0x00 +#define RBUF_64B_EN (1 << 0) +#define RBUF_ALIGN_2B (1 << 1) +#define RBUF_BAD_DIS (1 << 2) + +#define RBUF_STATUS 0x0C +#define RBUF_STATUS_WOL (1 << 0) +#define RBUF_STATUS_MPD_INTR_ACTIVE (1 << 1) +#define RBUF_STATUS_ACPI_INTR_ACTIVE (1 << 2) + +#define RBUF_CHK_CTRL 0x14 +#define RBUF_RXCHK_EN (1 << 0) +#define RBUF_SKIP_FCS (1 << 4) + +#define RBUF_TBUF_SIZE_CTRL 0xb4 + +#define RBUF_HFB_CTRL_V1 0x38 +#define RBUF_HFB_FILTER_EN_SHIFT 16 +#define RBUF_HFB_FILTER_EN_MASK 0xffff0000 +#define RBUF_HFB_EN (1 << 0) +#define RBUF_HFB_256B (1 << 1) +#define RBUF_ACPI_EN (1 << 2) + +#define RBUF_HFB_LEN_V1 0x3C +#define RBUF_FLTR_LEN_MASK 0xFF +#define RBUF_FLTR_LEN_SHIFT 8 + +#define TBUF_CTRL 0x00 +#define TBUF_BP_MC 0x0C + +#define TBUF_CTRL_V1 0x80 +#define TBUF_BP_MC_V1 0xA0 + +#define HFB_CTRL 0x00 +#define HFB_FLT_ENABLE_V3PLUS 0x04 +#define HFB_FLT_LEN_V2 0x04 +#define HFB_FLT_LEN_V3PLUS 0x1C + +/* uniMac intrl2 registers */ +#define INTRL2_CPU_STAT 0x00 +#define INTRL2_CPU_SET 0x04 +#define INTRL2_CPU_CLEAR 0x08 +#define INTRL2_CPU_MASK_STATUS 0x0C +#define INTRL2_CPU_MASK_SET 0x10 +#define INTRL2_CPU_MASK_CLEAR 0x14 + +/* INTRL2 instance 0 definitions */ +#define UMAC_IRQ_SCB (1 << 0) +#define UMAC_IRQ_EPHY (1 << 1) +#define UMAC_IRQ_PHY_DET_R (1 << 2) +#define UMAC_IRQ_PHY_DET_F (1 << 3) +#define UMAC_IRQ_LINK_UP (1 << 4) +#define UMAC_IRQ_LINK_DOWN (1 << 5) +#define UMAC_IRQ_UMAC (1 << 6) +#define UMAC_IRQ_UMAC_TSV (1 << 7) +#define UMAC_IRQ_TBUF_UNDERRUN (1 << 8) +#define UMAC_IRQ_RBUF_OVERFLOW (1 << 9) +#define UMAC_IRQ_HFB_SM (1 << 10) +#define UMAC_IRQ_HFB_MM (1 << 11) +#define UMAC_IRQ_MPD_R (1 << 12) +#define UMAC_IRQ_RXDMA_MBDONE (1 << 13) +#define UMAC_IRQ_RXDMA_PDONE (1 << 14) +#define UMAC_IRQ_RXDMA_BDONE (1 << 15) +#define UMAC_IRQ_TXDMA_MBDONE (1 << 16) +#define UMAC_IRQ_TXDMA_PDONE (1 << 17) +#define UMAC_IRQ_TXDMA_BDONE (1 << 18) +/* Only valid for GENETv3+ */ +#define UMAC_IRQ_MDIO_DONE (1 << 23) +#define UMAC_IRQ_MDIO_ERROR (1 << 24) + +/* Register block offsets */ +#define GENET_SYS_OFF 0x0000 +#define GENET_GR_BRIDGE_OFF 0x0040 +#define GENET_EXT_OFF 0x0080 +#define GENET_INTRL2_0_OFF 0x0200 +#define GENET_INTRL2_1_OFF 0x0240 +#define GENET_RBUF_OFF 0x0300 +#define GENET_UMAC_OFF 0x0800 + +/* SYS block offsets and register definitions */ +#define SYS_REV_CTRL 0x00 +#define SYS_PORT_CTRL 0x04 +#define PORT_MODE_INT_EPHY 0 +#define PORT_MODE_INT_GPHY 1 +#define PORT_MODE_EXT_EPHY 2 +#define PORT_MODE_EXT_GPHY 3 +#define PORT_MODE_EXT_RVMII_25 (4 | BIT(4)) +#define PORT_MODE_EXT_RVMII_50 4 +#define LED_ACT_SOURCE_MAC (1 << 9) + +#define SYS_RBUF_FLUSH_CTRL 0x08 +#define SYS_TBUF_FLUSH_CTRL 0x0C +#define RBUF_FLUSH_CTRL_V1 0x04 + +/* Ext block register offsets and definitions */ +#define EXT_EXT_PWR_MGMT 0x00 +#define EXT_PWR_DOWN_BIAS (1 << 0) +#define EXT_PWR_DOWN_DLL (1 << 1) +#define EXT_PWR_DOWN_PHY (1 << 2) +#define EXT_PWR_DN_EN_LD (1 << 3) +#define EXT_ENERGY_DET (1 << 4) +#define EXT_IDDQ_FROM_PHY (1 << 5) +#define EXT_PHY_RESET (1 << 8) +#define EXT_ENERGY_DET_MASK (1 << 12) + +#define EXT_RGMII_OOB_CTRL 0x0C +#define RGMII_MODE_EN (1 << 0) +#define RGMII_LINK (1 << 4) +#define OOB_DISABLE (1 << 5) +#define ID_MODE_DIS (1 << 16) + +#define EXT_GPHY_CTRL 0x1C +#define EXT_CFG_IDDQ_BIAS (1 << 0) +#define EXT_CFG_PWR_DOWN (1 << 1) +#define EXT_GPHY_RESET (1 << 5) + +/* DMA rings size */ +#define DMA_RING_SIZE (0x40) +#define DMA_RINGS_SIZE (DMA_RING_SIZE * (DESC_INDEX + 1)) + +/* DMA registers common definitions */ +#define DMA_RW_POINTER_MASK 0x1FF +#define DMA_P_INDEX_DISCARD_CNT_MASK 0xFFFF +#define DMA_P_INDEX_DISCARD_CNT_SHIFT 16 +#define DMA_BUFFER_DONE_CNT_MASK 0xFFFF +#define DMA_BUFFER_DONE_CNT_SHIFT 16 +#define DMA_P_INDEX_MASK 0xFFFF +#define DMA_C_INDEX_MASK 0xFFFF + +/* DMA ring size register */ +#define DMA_RING_SIZE_MASK 0xFFFF +#define DMA_RING_SIZE_SHIFT 16 +#define DMA_RING_BUFFER_SIZE_MASK 0xFFFF + +/* DMA interrupt threshold register */ +#define DMA_INTR_THRESHOLD_MASK 0x00FF + +/* DMA XON/XOFF register */ +#define DMA_XON_THREHOLD_MASK 0xFFFF +#define DMA_XOFF_THRESHOLD_MASK 0xFFFF +#define DMA_XOFF_THRESHOLD_SHIFT 16 + +/* DMA flow period register */ +#define DMA_FLOW_PERIOD_MASK 0xFFFF +#define DMA_MAX_PKT_SIZE_MASK 0xFFFF +#define DMA_MAX_PKT_SIZE_SHIFT 16 + + +/* DMA control register */ +#define DMA_EN (1 << 0) +#define DMA_RING_BUF_EN_SHIFT 0x01 +#define DMA_RING_BUF_EN_MASK 0xFFFF +#define DMA_TSB_SWAP_EN (1 << 20) + +/* DMA status register */ +#define DMA_DISABLED (1 << 0) +#define DMA_DESC_RAM_INIT_BUSY (1 << 1) + +/* DMA SCB burst size register */ +#define DMA_SCB_BURST_SIZE_MASK 0x1F + +/* DMA activity vector register */ +#define DMA_ACTIVITY_VECTOR_MASK 0x1FFFF + +/* DMA backpressure mask register */ +#define DMA_BACKPRESSURE_MASK 0x1FFFF +#define DMA_PFC_ENABLE (1 << 31) + +/* DMA backpressure status register */ +#define DMA_BACKPRESSURE_STATUS_MASK 0x1FFFF + +/* DMA override register */ +#define DMA_LITTLE_ENDIAN_MODE (1 << 0) +#define DMA_REGISTER_MODE (1 << 1) + +/* DMA timeout register */ +#define DMA_TIMEOUT_MASK 0xFFFF +#define DMA_TIMEOUT_VAL 5000 /* micro seconds */ + +/* TDMA rate limiting control register */ +#define DMA_RATE_LIMIT_EN_MASK 0xFFFF + +/* TDMA arbitration control register */ +#define DMA_ARBITER_MODE_MASK 0x03 +#define DMA_RING_BUF_PRIORITY_MASK 0x1F +#define DMA_RING_BUF_PRIORITY_SHIFT 5 +#define DMA_RATE_ADJ_MASK 0xFF + +/* Tx/Rx Dma Descriptor common bits*/ +#define DMA_BUFLENGTH_MASK 0x0fff +#define DMA_BUFLENGTH_SHIFT 16 +#define DMA_OWN 0x8000 +#define DMA_EOP 0x4000 +#define DMA_SOP 0x2000 +#define DMA_WRAP 0x1000 +/* Tx specific Dma descriptor bits */ +#define DMA_TX_UNDERRUN 0x0200 +#define DMA_TX_APPEND_CRC 0x0040 +#define DMA_TX_OW_CRC 0x0020 +#define DMA_TX_DO_CSUM 0x0010 +#define DMA_TX_QTAG_SHIFT 7 + +/* Rx Specific Dma descriptor bits */ +#define DMA_RX_CHK_V3PLUS 0x8000 +#define DMA_RX_CHK_V12 0x1000 +#define DMA_RX_BRDCAST 0x0040 +#define DMA_RX_MULT 0x0020 +#define DMA_RX_LG 0x0010 +#define DMA_RX_NO 0x0008 +#define DMA_RX_RXER 0x0004 +#define DMA_RX_CRC_ERROR 0x0002 +#define DMA_RX_OV 0x0001 +#define DMA_RX_FI_MASK 0x001F +#define DMA_RX_FI_SHIFT 0x0007 +#define DMA_DESC_ALLOC_MASK 0x00FF + +#define DMA_ARBITER_RR 0x00 +#define DMA_ARBITER_WRR 0x01 +#define DMA_ARBITER_SP 0x02 + +struct enet_cb { + struct sk_buff *skb; + void __iomem *bd_addr; + DEFINE_DMA_UNMAP_ADDR(dma_addr); + DEFINE_DMA_UNMAP_LEN(dma_len); +}; + +/* power management mode */ +enum bcmgenet_power_mode { + GENET_POWER_CABLE_SENSE = 0, + GENET_POWER_PASSIVE, +}; + +struct bcmgenet_priv; + +/* We support both runtime GENET detection and compile-time + * to optimize code-paths for a given hardware + */ +enum bcmgenet_version { + GENET_V1 = 1, + GENET_V2, + GENET_V3, + GENET_V4 +}; + +#define GENET_IS_V1(p) ((p)->version == GENET_V1) +#define GENET_IS_V2(p) ((p)->version == GENET_V2) +#define GENET_IS_V3(p) ((p)->version == GENET_V3) +#define GENET_IS_V4(p) ((p)->version == GENET_V4) + +/* Hardware flags */ +#define GENET_HAS_40BITS (1 << 0) +#define GENET_HAS_EXT (1 << 1) +#define GENET_HAS_MDIO_INTR (1 << 2) + +/* BCMGENET hardware parameters, keep this structure nicely aligned + * since it is going to be used in hot paths + */ +struct bcmgenet_hw_params { + u8 tx_queues; + u8 rx_queues; + u8 bds_cnt; + u8 bp_in_en_shift; + u32 bp_in_mask; + u8 hfb_filter_cnt; + u8 qtag_mask; + u16 tbuf_offset; + u32 hfb_offset; + u32 hfb_reg_offset; + u32 rdma_offset; + u32 tdma_offset; + u32 words_per_bd; + u32 flags; +}; + +struct bcmgenet_tx_ring { + spinlock_t lock; /* ring lock */ + unsigned int index; /* ring index */ + unsigned int queue; /* queue index */ + struct enet_cb *cbs; /* tx ring buffer control block*/ + unsigned int size; /* size of each tx ring */ + unsigned int c_index; /* last consumer index of each ring*/ + unsigned int free_bds; /* # of free bds for each ring */ + unsigned int write_ptr; /* Tx ring write pointer SW copy */ + 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 *); +}; + +/* device context */ +struct bcmgenet_priv { + void __iomem *base; + enum bcmgenet_version version; + struct net_device *dev; + spinlock_t lock; + u32 int0_mask; + u32 int1_mask; + + /* NAPI for descriptor based rx */ + struct napi_struct napi ____cacheline_aligned; + + /* transmit variables */ + void __iomem *tx_bds; + struct enet_cb *tx_cbs; + unsigned int num_tx_bds; + + struct bcmgenet_tx_ring tx_rings[DESC_INDEX + 1]; + + /* receive variables */ + void __iomem *rx_bds; + void __iomem *rx_bd_assign_ptr; + int rx_bd_assign_index; + struct enet_cb *rx_cbs; + unsigned int num_rx_bds; + unsigned int rx_buf_len; + unsigned int rx_read_ptr; + unsigned int rx_c_index; + + /* other misc variables */ + struct bcmgenet_hw_params *hw_params; + + /* MDIO bus variables */ + wait_queue_head_t wq; + struct phy_device *phydev; + struct device_node *phy_dn; + struct mii_bus *mii_bus; + + /* PHY device variables */ + int old_duplex; + int old_link; + int old_pause; + phy_interface_t phy_interface; + int phy_addr; + int ext_phy; + + /* Interrupt variables */ + struct work_struct bcmgenet_irq_work; + int irq0; + int irq1; + unsigned int irq0_stat; + unsigned int irq1_stat; + + /* HW descriptors/checksum variables */ + bool desc_64b_en; + bool desc_rxchk_en; + bool crc_fwd_en; + + unsigned int dma_rx_chk_bit; + + u32 msg_enable; + + struct clk *clk; + struct platform_device *pdev; + + /* WOL */ + unsigned long wol_enabled; + struct clk *clk_wol; + u32 wolopts; + + struct bcmgenet_mib_counters mib; +}; + +#define GENET_IO_MACRO(name, offset) \ +static inline u32 bcmgenet_##name##_readl(struct bcmgenet_priv *priv, \ + u32 off) \ +{ \ + return __raw_readl(priv->base + offset + off); \ +} \ +static inline void bcmgenet_##name##_writel(struct bcmgenet_priv *priv, \ + u32 val, u32 off) \ +{ \ + __raw_writel(val, priv->base + offset + off); \ +} + +GENET_IO_MACRO(ext, GENET_EXT_OFF); +GENET_IO_MACRO(umac, GENET_UMAC_OFF); +GENET_IO_MACRO(sys, GENET_SYS_OFF); + +/* interrupt l2 registers accessors */ +GENET_IO_MACRO(intrl2_0, GENET_INTRL2_0_OFF); +GENET_IO_MACRO(intrl2_1, GENET_INTRL2_1_OFF); + +/* HFB register accessors */ +GENET_IO_MACRO(hfb, priv->hw_params->hfb_offset); + +/* GENET v2+ HFB control and filter len helpers */ +GENET_IO_MACRO(hfb_reg, priv->hw_params->hfb_reg_offset); + +/* RBUF register accessors */ +GENET_IO_MACRO(rbuf, GENET_RBUF_OFF); + +/* MDIO routines */ +int bcmgenet_mii_init(struct net_device *dev); +int bcmgenet_mii_config(struct net_device *dev); +void bcmgenet_mii_exit(struct net_device *dev); +void bcmgenet_mii_reset(struct net_device *dev); + +#endif /* __BCMGENET_H__ */ diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c new file mode 100644 index 000000000000..4608673beaff --- /dev/null +++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c @@ -0,0 +1,464 @@ +/* + * Broadcom GENET MDIO routines + * + * Copyright (c) 2014 Broadcom Corporation + * + * 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. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + */ + + +#include <linux/types.h> +#include <linux/delay.h> +#include <linux/wait.h> +#include <linux/mii.h> +#include <linux/ethtool.h> +#include <linux/bitops.h> +#include <linux/netdevice.h> +#include <linux/platform_device.h> +#include <linux/phy.h> +#include <linux/phy_fixed.h> +#include <linux/brcmphy.h> +#include <linux/of.h> +#include <linux/of_net.h> +#include <linux/of_mdio.h> + +#include "bcmgenet.h" + +/* read a value from the MII */ +static int bcmgenet_mii_read(struct mii_bus *bus, int phy_id, int location) +{ + int ret; + struct net_device *dev = bus->priv; + struct bcmgenet_priv *priv = netdev_priv(dev); + u32 reg; + + bcmgenet_umac_writel(priv, (MDIO_RD | (phy_id << MDIO_PMD_SHIFT) | + (location << MDIO_REG_SHIFT)), UMAC_MDIO_CMD); + /* Start MDIO transaction*/ + reg = bcmgenet_umac_readl(priv, UMAC_MDIO_CMD); + reg |= MDIO_START_BUSY; + bcmgenet_umac_writel(priv, reg, UMAC_MDIO_CMD); + wait_event_timeout(priv->wq, + !(bcmgenet_umac_readl(priv, UMAC_MDIO_CMD) + & MDIO_START_BUSY), + HZ / 100); + ret = bcmgenet_umac_readl(priv, UMAC_MDIO_CMD); + + if (ret & MDIO_READ_FAIL) + return -EIO; + + return ret & 0xffff; +} + +/* write a value to the MII */ +static int bcmgenet_mii_write(struct mii_bus *bus, int phy_id, + int location, u16 val) +{ + struct net_device *dev = bus->priv; + struct bcmgenet_priv *priv = netdev_priv(dev); + u32 reg; + + bcmgenet_umac_writel(priv, (MDIO_WR | (phy_id << MDIO_PMD_SHIFT) | + (location << MDIO_REG_SHIFT) | (0xffff & val)), + UMAC_MDIO_CMD); + reg = bcmgenet_umac_readl(priv, UMAC_MDIO_CMD); + reg |= MDIO_START_BUSY; + bcmgenet_umac_writel(priv, reg, UMAC_MDIO_CMD); + wait_event_timeout(priv->wq, + !(bcmgenet_umac_readl(priv, UMAC_MDIO_CMD) & + MDIO_START_BUSY), + HZ / 100); + + return 0; +} + +/* setup netdev link state when PHY link status change and + * update UMAC and RGMII block when link up + */ +static void bcmgenet_mii_setup(struct net_device *dev) +{ + struct bcmgenet_priv *priv = netdev_priv(dev); + struct phy_device *phydev = priv->phydev; + u32 reg, cmd_bits = 0; + unsigned int status_changed = 0; + + if (priv->old_link != phydev->link) { + status_changed = 1; + priv->old_link = phydev->link; + } + + if (phydev->link) { + /* program UMAC and RGMII block based on established link + * speed, pause, and duplex. + * the speed set in umac->cmd tell RGMII block which clock + * 25MHz(100Mbps)/125MHz(1Gbps) to use for transmit. + * receive clock is provided by PHY. + */ + reg = bcmgenet_ext_readl(priv, EXT_RGMII_OOB_CTRL); + reg &= ~OOB_DISABLE; + reg |= RGMII_LINK; + bcmgenet_ext_writel(priv, reg, EXT_RGMII_OOB_CTRL); + + /* speed */ + if (phydev->speed == SPEED_1000) + cmd_bits = UMAC_SPEED_1000; + else if (phydev->speed == SPEED_100) + cmd_bits = UMAC_SPEED_100; + else + cmd_bits = UMAC_SPEED_10; + cmd_bits <<= CMD_SPEED_SHIFT; + + if (priv->old_duplex != phydev->duplex) { + status_changed = 1; + priv->old_duplex = phydev->duplex; + } + + /* duplex */ + if (phydev->duplex != DUPLEX_FULL) + cmd_bits |= CMD_HD_EN; + + if (priv->old_pause != phydev->pause) { + status_changed = 1; + priv->old_pause = phydev->pause; + } + + /* pause capability */ + if (!phydev->pause) + cmd_bits |= CMD_RX_PAUSE_IGNORE | CMD_TX_PAUSE_IGNORE; + + reg = bcmgenet_umac_readl(priv, UMAC_CMD); + reg &= ~((CMD_SPEED_MASK << CMD_SPEED_SHIFT) | + CMD_HD_EN | + CMD_RX_PAUSE_IGNORE | CMD_TX_PAUSE_IGNORE); + reg |= cmd_bits; + bcmgenet_umac_writel(priv, reg, UMAC_CMD); + } + + if (status_changed) + phy_print_status(phydev); +} + +void bcmgenet_mii_reset(struct net_device *dev) +{ + struct bcmgenet_priv *priv = netdev_priv(dev); + + if (priv->phydev) { + phy_init_hw(priv->phydev); + phy_start_aneg(priv->phydev); + } +} + +static void bcmgenet_ephy_power_up(struct net_device *dev) +{ + struct bcmgenet_priv *priv = netdev_priv(dev); + u32 reg = 0; + + /* EXT_GPHY_CTRL is only valid for GENETv4 and onward */ + if (!GENET_IS_V4(priv)) + 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); + + reg &= ~EXT_GPHY_RESET; + bcmgenet_ext_writel(priv, reg, EXT_GPHY_CTRL); + udelay(20); +} + +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); + /* enable APD */ + reg = bcmgenet_ext_readl(priv, EXT_EXT_PWR_MGMT); + reg |= EXT_PWR_DN_EN_LD; + bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT); + bcmgenet_mii_reset(dev); +} + +static void bcmgenet_moca_phy_setup(struct bcmgenet_priv *priv) +{ + u32 reg; + + /* Speed settings are set in bcmgenet_mii_setup() */ + reg = bcmgenet_sys_readl(priv, SYS_PORT_CTRL); + reg |= LED_ACT_SOURCE_MAC; + bcmgenet_sys_writel(priv, reg, SYS_PORT_CTRL); +} + +int bcmgenet_mii_config(struct net_device *dev) +{ + struct bcmgenet_priv *priv = netdev_priv(dev); + struct phy_device *phydev = priv->phydev; + struct device *kdev = &priv->pdev->dev; + const char *phy_name = NULL; + u32 id_mode_dis = 0; + u32 port_ctrl; + u32 reg; + + priv->ext_phy = !phy_is_internal(priv->phydev) && + (priv->phy_interface != PHY_INTERFACE_MODE_MOCA); + + if (phy_is_internal(priv->phydev)) + priv->phy_interface = PHY_INTERFACE_MODE_NA; + + switch (priv->phy_interface) { + case PHY_INTERFACE_MODE_NA: + case PHY_INTERFACE_MODE_MOCA: + /* Irrespective of the actually configured PHY speed (100 or + * 1000) GENETv4 only has an internal GPHY so we will just end + * up masking the Gigabit features from what we support, not + * switching to the EPHY + */ + if (GENET_IS_V4(priv)) + port_ctrl = PORT_MODE_INT_GPHY; + else + port_ctrl = PORT_MODE_INT_EPHY; + + bcmgenet_sys_writel(priv, port_ctrl, SYS_PORT_CTRL); + + if (phy_is_internal(priv->phydev)) { + phy_name = "internal PHY"; + bcmgenet_internal_phy_setup(dev); + } else if (priv->phy_interface == PHY_INTERFACE_MODE_MOCA) { + phy_name = "MoCA"; + bcmgenet_moca_phy_setup(priv); + } + break; + + case PHY_INTERFACE_MODE_MII: + phy_name = "external MII"; + phydev->supported &= PHY_BASIC_FEATURES; + bcmgenet_sys_writel(priv, + PORT_MODE_EXT_EPHY, SYS_PORT_CTRL); + break; + + case PHY_INTERFACE_MODE_REVMII: + phy_name = "external RvMII"; + /* of_mdiobus_register took care of reading the 'max-speed' + * PHY property for us, effectively limiting the PHY supported + * capabilities, use that knowledge to also configure the + * Reverse MII interface correctly. + */ + if ((priv->phydev->supported & PHY_BASIC_FEATURES) == + PHY_BASIC_FEATURES) + port_ctrl = PORT_MODE_EXT_RVMII_25; + else + port_ctrl = PORT_MODE_EXT_RVMII_50; + bcmgenet_sys_writel(priv, port_ctrl, SYS_PORT_CTRL); + break; + + case PHY_INTERFACE_MODE_RGMII: + /* RGMII_NO_ID: TXC transitions at the same time as TXD + * (requires PCB or receiver-side delay) + * RGMII: Add 2ns delay on TXC (90 degree shift) + * + * ID is implicitly disabled for 100Mbps (RG)MII operation. + */ + id_mode_dis = BIT(16); + /* fall through */ + case PHY_INTERFACE_MODE_RGMII_TXID: + if (id_mode_dis) + phy_name = "external RGMII (no delay)"; + else + phy_name = "external RGMII (TX delay)"; + reg = bcmgenet_ext_readl(priv, EXT_RGMII_OOB_CTRL); + reg |= RGMII_MODE_EN | id_mode_dis; + bcmgenet_ext_writel(priv, reg, EXT_RGMII_OOB_CTRL); + bcmgenet_sys_writel(priv, + PORT_MODE_EXT_GPHY, SYS_PORT_CTRL); + break; + default: + dev_err(kdev, "unknown phy mode: %d\n", priv->phy_interface); + return -EINVAL; + } + + dev_info(kdev, "configuring instance for %s\n", phy_name); + + return 0; +} + +static int bcmgenet_mii_probe(struct net_device *dev) +{ + struct bcmgenet_priv *priv = netdev_priv(dev); + struct phy_device *phydev; + unsigned int phy_flags; + int ret; + + if (priv->phydev) { + pr_info("PHY already attached\n"); + return 0; + } + + if (priv->phy_dn) + phydev = of_phy_connect(dev, priv->phy_dn, + bcmgenet_mii_setup, 0, + priv->phy_interface); + else + phydev = of_phy_connect_fixed_link(dev, + bcmgenet_mii_setup, + priv->phy_interface); + + if (!phydev) { + pr_err("could not attach to PHY\n"); + return -ENODEV; + } + + priv->old_link = -1; + priv->old_duplex = -1; + priv->old_pause = -1; + priv->phydev = phydev; + + /* Configure port multiplexer based on what the probed PHY device since + * reading the 'max-speed' property determines the maximum supported + * PHY speed which is needed for bcmgenet_mii_config() to configure + * things appropriately. + */ + ret = bcmgenet_mii_config(dev); + if (ret) { + phy_disconnect(priv->phydev); + return ret; + } + + phy_flags = PHY_BRCM_100MBPS_WAR; + + /* workarounds are only needed for 100Mpbs PHYs, and + * never on GENET V1 hardware + */ + if ((phydev->supported & PHY_GBIT_FEATURES) || GENET_IS_V1(priv)) + phy_flags = 0; + + phydev->dev_flags |= phy_flags; + phydev->advertising = phydev->supported; + + /* The internal PHY has its link interrupts routed to the + * Ethernet MAC ISRs + */ + if (phy_is_internal(priv->phydev)) + priv->mii_bus->irq[phydev->addr] = PHY_IGNORE_INTERRUPT; + else + priv->mii_bus->irq[phydev->addr] = PHY_POLL; + + pr_info("attached PHY at address %d [%s]\n", + phydev->addr, phydev->drv->name); + + return 0; +} + +static int bcmgenet_mii_alloc(struct bcmgenet_priv *priv) +{ + struct mii_bus *bus; + + if (priv->mii_bus) + return 0; + + priv->mii_bus = mdiobus_alloc(); + if (!priv->mii_bus) { + pr_err("failed to allocate\n"); + return -ENOMEM; + } + + bus = priv->mii_bus; + bus->priv = priv->dev; + bus->name = "bcmgenet MII bus"; + bus->parent = &priv->pdev->dev; + bus->read = bcmgenet_mii_read; + bus->write = bcmgenet_mii_write; + snprintf(bus->id, MII_BUS_ID_SIZE, "%s-%d", + priv->pdev->name, priv->pdev->id); + + bus->irq = kzalloc(sizeof(int) * PHY_MAX_ADDR, GFP_KERNEL); + if (!bus->irq) { + mdiobus_free(priv->mii_bus); + return -ENOMEM; + } + + return 0; +} + +static int bcmgenet_mii_of_init(struct bcmgenet_priv *priv) +{ + struct device_node *dn = priv->pdev->dev.of_node; + struct device *kdev = &priv->pdev->dev; + struct device_node *mdio_dn; + char *compat; + int ret; + + compat = kasprintf(GFP_KERNEL, "brcm,genet-mdio-v%d", priv->version); + if (!compat) + return -ENOMEM; + + mdio_dn = of_find_compatible_node(dn, NULL, compat); + kfree(compat); + if (!mdio_dn) { + dev_err(kdev, "unable to find MDIO bus node\n"); + return -ENODEV; + } + + ret = of_mdiobus_register(priv->mii_bus, mdio_dn); + if (ret) { + dev_err(kdev, "failed to register MDIO bus\n"); + return ret; + } + + /* Fetch the PHY phandle */ + priv->phy_dn = of_parse_phandle(dn, "phy-handle", 0); + + /* Get the link mode */ + priv->phy_interface = of_get_phy_mode(dn); + + return 0; +} + +int bcmgenet_mii_init(struct net_device *dev) +{ + struct bcmgenet_priv *priv = netdev_priv(dev); + int ret; + + ret = bcmgenet_mii_alloc(priv); + if (ret) + return ret; + + ret = bcmgenet_mii_of_init(priv); + if (ret) + goto out_free; + + ret = bcmgenet_mii_probe(dev); + if (ret) + goto out; + + return 0; + +out: + mdiobus_unregister(priv->mii_bus); +out_free: + kfree(priv->mii_bus->irq); + mdiobus_free(priv->mii_bus); + return ret; +} + +void bcmgenet_mii_exit(struct net_device *dev) +{ + struct bcmgenet_priv *priv = netdev_priv(dev); + + mdiobus_unregister(priv->mii_bus); + kfree(priv->mii_bus->irq); + mdiobus_free(priv->mii_bus); +} diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index e2ca03e23dc1..bbbd2a4bc161 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -2609,13 +2609,14 @@ static int tg3_phy_reset_5703_4_5(struct tg3 *tp) tg3_writephy(tp, MII_CTRL1000, phy9_orig); - if (!tg3_readphy(tp, MII_TG3_EXT_CTRL, ®32)) { - reg32 &= ~0x3000; - tg3_writephy(tp, MII_TG3_EXT_CTRL, reg32); - } else if (!err) - err = -EBUSY; + err = tg3_readphy(tp, MII_TG3_EXT_CTRL, ®32); + if (err) + return err; - return err; + reg32 &= ~0x3000; + tg3_writephy(tp, MII_TG3_EXT_CTRL, reg32); + + return 0; } static void tg3_carrier_off(struct tg3 *tp) @@ -6592,7 +6593,7 @@ static void tg3_tx(struct tg3_napi *tnapi) pkts_compl++; bytes_compl += skb->len; - dev_kfree_skb(skb); + dev_kfree_skb_any(skb); if (unlikely(tx_bug)) { tg3_tx_recover(tp); @@ -6842,8 +6843,7 @@ static int tg3_rx(struct tg3_napi *tnapi, int budget) work_mask |= opaque_key; - if ((desc->err_vlan & RXD_ERR_MASK) != 0 && - (desc->err_vlan != RXD_ERR_ODD_NIBBLE_RCVD_MII)) { + if (desc->err_vlan & RXD_ERR_MASK) { drop_it: tg3_recycle_rx(tnapi, tpr, opaque_key, desc_idx, *post_ptr); @@ -6924,7 +6924,7 @@ static int tg3_rx(struct tg3_napi *tnapi, int budget) if (len > (tp->dev->mtu + ETH_HLEN) && skb->protocol != htons(ETH_P_8021Q)) { - dev_kfree_skb(skb); + dev_kfree_skb_any(skb); goto drop_it_no_recycle; } @@ -7807,7 +7807,7 @@ static int tigon3_dma_hwbug_workaround(struct tg3_napi *tnapi, PCI_DMA_TODEVICE); /* Make sure the mapping succeeded */ if (pci_dma_mapping_error(tp->pdev, new_addr)) { - dev_kfree_skb(new_skb); + dev_kfree_skb_any(new_skb); ret = -1; } else { u32 save_entry = *entry; @@ -7822,13 +7822,13 @@ static int tigon3_dma_hwbug_workaround(struct tg3_napi *tnapi, new_skb->len, base_flags, mss, vlan)) { tg3_tx_skb_unmap(tnapi, save_entry, -1); - dev_kfree_skb(new_skb); + dev_kfree_skb_any(new_skb); ret = -1; } } } - dev_kfree_skb(skb); + dev_kfree_skb_any(skb); *pskb = new_skb; return ret; } @@ -7871,7 +7871,7 @@ static int tg3_tso_bug(struct tg3 *tp, struct sk_buff *skb) } while (segs); tg3_tso_bug_end: - dev_kfree_skb(skb); + dev_kfree_skb_any(skb); return NETDEV_TX_OK; } @@ -8093,7 +8093,7 @@ dma_error: tg3_tx_skb_unmap(tnapi, tnapi->tx_prod, --i); tnapi->tx_buffers[tnapi->tx_prod].skb = NULL; drop: - dev_kfree_skb(skb); + dev_kfree_skb_any(skb); drop_nofree: tp->tx_dropped++; return NETDEV_TX_OK; @@ -11361,12 +11361,10 @@ static bool tg3_enable_msix(struct tg3 *tp) msix_ent[i].vector = 0; } - rc = pci_enable_msix(tp->pdev, msix_ent, tp->irq_cnt); + rc = pci_enable_msix_range(tp->pdev, msix_ent, 1, tp->irq_cnt); if (rc < 0) { return false; - } else if (rc != 0) { - if (pci_enable_msix(tp->pdev, msix_ent, rc)) - return false; + } else if (rc < tp->irq_cnt) { netdev_notice(tp->dev, "Requested %d MSI-X vectors, received %d\n", tp->irq_cnt, rc); tp->irq_cnt = rc; @@ -14113,12 +14111,12 @@ static int tg3_change_mtu(struct net_device *dev, int new_mtu) tg3_netif_stop(tp); + tg3_set_mtu(dev, tp, new_mtu); + tg3_full_lock(tp, 1); tg3_halt(tp, RESET_KIND_SHUTDOWN, 1); - tg3_set_mtu(dev, tp, new_mtu); - /* Reset PHY, otherwise the read DMA engine will be in a mode that * breaks all requests to 256 bytes. */ diff --git a/drivers/net/ethernet/broadcom/tg3.h b/drivers/net/ethernet/broadcom/tg3.h index ef472385bce4..04321e5a356e 100644 --- a/drivers/net/ethernet/broadcom/tg3.h +++ b/drivers/net/ethernet/broadcom/tg3.h @@ -2608,7 +2608,11 @@ struct tg3_rx_buffer_desc { #define RXD_ERR_TOO_SMALL 0x00400000 #define RXD_ERR_NO_RESOURCES 0x00800000 #define RXD_ERR_HUGE_FRAME 0x01000000 -#define RXD_ERR_MASK 0xffff0000 + +#define RXD_ERR_MASK (RXD_ERR_BAD_CRC | RXD_ERR_COLLISION | \ + RXD_ERR_LINK_LOST | RXD_ERR_PHY_DECODE | \ + RXD_ERR_MAC_ABRT | RXD_ERR_TOO_SMALL | \ + RXD_ERR_NO_RESOURCES | RXD_ERR_HUGE_FRAME) u32 reserved; u32 opaque; diff --git a/drivers/net/ethernet/brocade/bna/bnad.c b/drivers/net/ethernet/brocade/bna/bnad.c index cf64f3d0b60d..cb7625366ec2 100644 --- a/drivers/net/ethernet/brocade/bna/bnad.c +++ b/drivers/net/ethernet/brocade/bna/bnad.c @@ -707,7 +707,8 @@ bnad_cq_process(struct bnad *bnad, struct bna_ccb *ccb, int budget) else skb_checksum_none_assert(skb); - if (flags & BNA_CQ_EF_VLAN) + if ((flags & BNA_CQ_EF_VLAN) && + (bnad->netdev->features & NETIF_F_HW_VLAN_CTAG_RX)) __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), ntohs(cmpl->vlan_tag)); if (BNAD_RXBUF_IS_SK_BUFF(unmap_q->type)) @@ -2094,7 +2095,9 @@ bnad_init_rx_config(struct bnad *bnad, struct bna_rx_config *rx_config) rx_config->q1_buf_size = BFI_SMALL_RXBUF_SIZE; } - rx_config->vlan_strip_status = BNA_STATUS_T_ENABLED; + rx_config->vlan_strip_status = + (bnad->netdev->features & NETIF_F_HW_VLAN_CTAG_RX) ? + BNA_STATUS_T_ENABLED : BNA_STATUS_T_DISABLED; } static void @@ -2666,9 +2669,11 @@ bnad_enable_msix(struct bnad *bnad) for (i = 0; i < bnad->msix_num; i++) bnad->msix_table[i].entry = i; - ret = pci_enable_msix(bnad->pcidev, bnad->msix_table, bnad->msix_num); - if (ret > 0) { - /* Not enough MSI-X vectors. */ + ret = pci_enable_msix_range(bnad->pcidev, bnad->msix_table, + 1, bnad->msix_num); + if (ret < 0) { + goto intx_mode; + } else if (ret < bnad->msix_num) { pr_warn("BNA: %d MSI-X vectors allocated < %d requested\n", ret, bnad->msix_num); @@ -2681,18 +2686,11 @@ bnad_enable_msix(struct bnad *bnad) bnad->msix_num = BNAD_NUM_TXQ + BNAD_NUM_RXP + BNAD_MAILBOX_MSIX_VECTORS; - if (bnad->msix_num > ret) - goto intx_mode; - - /* Try once more with adjusted numbers */ - /* If this fails, fall back to INTx */ - ret = pci_enable_msix(bnad->pcidev, bnad->msix_table, - bnad->msix_num); - if (ret) + if (bnad->msix_num > ret) { + pci_disable_msix(bnad->pcidev); goto intx_mode; - - } else if (ret < 0) - goto intx_mode; + } + } pci_intx(bnad->pcidev, 0); @@ -2847,13 +2845,11 @@ bnad_txq_wi_prepare(struct bnad *bnad, struct bna_tcb *tcb, } if (unlikely((gso_size + skb_transport_offset(skb) + tcp_hdrlen(skb)) >= skb->len)) { - txqent->hdr.wi.opcode = - __constant_htons(BNA_TXQ_WI_SEND); + txqent->hdr.wi.opcode = htons(BNA_TXQ_WI_SEND); txqent->hdr.wi.lso_mss = 0; BNAD_UPDATE_CTR(bnad, tx_skb_tso_too_short); } else { - txqent->hdr.wi.opcode = - __constant_htons(BNA_TXQ_WI_SEND_LSO); + txqent->hdr.wi.opcode = htons(BNA_TXQ_WI_SEND_LSO); txqent->hdr.wi.lso_mss = htons(gso_size); } @@ -2867,7 +2863,7 @@ bnad_txq_wi_prepare(struct bnad *bnad, struct bna_tcb *tcb, htons(BNA_TXQ_WI_L4_HDR_N_OFFSET( tcp_hdrlen(skb) >> 2, skb_transport_offset(skb))); } else { - txqent->hdr.wi.opcode = __constant_htons(BNA_TXQ_WI_SEND); + txqent->hdr.wi.opcode = htons(BNA_TXQ_WI_SEND); txqent->hdr.wi.lso_mss = 0; if (unlikely(skb->len > (bnad->netdev->mtu + ETH_HLEN))) { @@ -2878,11 +2874,10 @@ bnad_txq_wi_prepare(struct bnad *bnad, struct bna_tcb *tcb, if (skb->ip_summed == CHECKSUM_PARTIAL) { u8 proto = 0; - if (skb->protocol == __constant_htons(ETH_P_IP)) + if (skb->protocol == htons(ETH_P_IP)) proto = ip_hdr(skb)->protocol; #ifdef NETIF_F_IPV6_CSUM - else if (skb->protocol == - __constant_htons(ETH_P_IPV6)) { + else if (skb->protocol == htons(ETH_P_IPV6)) { /* nexthdr may not be TCP immediately. */ proto = ipv6_hdr(skb)->nexthdr; } @@ -3064,8 +3059,7 @@ bnad_start_xmit(struct sk_buff *skb, struct net_device *netdev) vect_id = 0; BNA_QE_INDX_INC(prod, q_depth); txqent = &((struct bna_txq_entry *)tcb->sw_q)[prod]; - txqent->hdr.wi_ext.opcode = - __constant_htons(BNA_TXQ_WI_EXTENSION); + txqent->hdr.wi_ext.opcode = htons(BNA_TXQ_WI_EXTENSION); unmap = &unmap_q[prod]; } @@ -3245,11 +3239,6 @@ bnad_set_rx_mode(struct net_device *netdev) BNA_RXMODE_ALLMULTI; bna_rx_mode_set(bnad->rx_info[0].rx, new_mode, mode_mask, NULL); - if (bnad->cfg_flags & BNAD_CF_PROMISC) - bna_rx_vlan_strip_disable(bnad->rx_info[0].rx); - else - bna_rx_vlan_strip_enable(bnad->rx_info[0].rx); - spin_unlock_irqrestore(&bnad->bna_lock, flags); } @@ -3374,6 +3363,27 @@ bnad_vlan_rx_kill_vid(struct net_device *netdev, __be16 proto, u16 vid) return 0; } +static int bnad_set_features(struct net_device *dev, netdev_features_t features) +{ + struct bnad *bnad = netdev_priv(dev); + netdev_features_t changed = features ^ dev->features; + + if ((changed & NETIF_F_HW_VLAN_CTAG_RX) && netif_running(dev)) { + unsigned long flags; + + spin_lock_irqsave(&bnad->bna_lock, flags); + + if (features & NETIF_F_HW_VLAN_CTAG_RX) + bna_rx_vlan_strip_enable(bnad->rx_info[0].rx); + else + bna_rx_vlan_strip_disable(bnad->rx_info[0].rx); + + spin_unlock_irqrestore(&bnad->bna_lock, flags); + } + + return 0; +} + #ifdef CONFIG_NET_POLL_CONTROLLER static void bnad_netpoll(struct net_device *netdev) @@ -3421,6 +3431,7 @@ static const struct net_device_ops bnad_netdev_ops = { .ndo_change_mtu = bnad_change_mtu, .ndo_vlan_rx_add_vid = bnad_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = bnad_vlan_rx_kill_vid, + .ndo_set_features = bnad_set_features, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = bnad_netpoll #endif @@ -3433,14 +3444,14 @@ bnad_netdev_init(struct bnad *bnad, bool using_dac) netdev->hw_features = NETIF_F_SG | NETIF_F_RXCSUM | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | - NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_HW_VLAN_CTAG_TX; + NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_CTAG_RX; netdev->vlan_features = NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_TSO | NETIF_F_TSO6; - netdev->features |= netdev->hw_features | - NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_CTAG_FILTER; + netdev->features |= netdev->hw_features | NETIF_F_HW_VLAN_CTAG_FILTER; if (using_dac) netdev->features |= NETIF_F_HIGHDMA; diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c index 45d77334d7d9..07bbb711b7e5 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c +++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c @@ -3088,30 +3088,22 @@ static int cxgb_enable_msix(struct adapter *adap) { struct msix_entry entries[SGE_QSETS + 1]; int vectors; - int i, err; + int i; vectors = ARRAY_SIZE(entries); for (i = 0; i < vectors; ++i) entries[i].entry = i; - while ((err = pci_enable_msix(adap->pdev, entries, vectors)) > 0) - vectors = err; - - if (err < 0) - pci_disable_msix(adap->pdev); - - if (!err && vectors < (adap->params.nports + 1)) { - pci_disable_msix(adap->pdev); - err = -1; - } + vectors = pci_enable_msix_range(adap->pdev, entries, + adap->params.nports + 1, vectors); + if (vectors < 0) + return vectors; - if (!err) { - for (i = 0; i < vectors; ++i) - adap->msix_info[i].vec = entries[i].vector; - adap->msix_nvectors = vectors; - } + for (i = 0; i < vectors; ++i) + adap->msix_info[i].vec = entries[i].vector; + adap->msix_nvectors = vectors; - return err; + return 0; } static void print_port_info(struct adapter *adap, const struct adapter_info *ai) diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h index 1f4b9b30b9ed..944f2cbc1795 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h @@ -66,6 +66,7 @@ enum { SERNUM_LEN = 24, /* Serial # length */ EC_LEN = 16, /* E/C length */ ID_LEN = 16, /* ID length */ + PN_LEN = 16, /* Part Number length */ }; enum { @@ -254,6 +255,7 @@ struct vpd_params { u8 ec[EC_LEN + 1]; u8 sn[SERNUM_LEN + 1]; u8 id[ID_LEN + 1]; + u8 pn[PN_LEN + 1]; }; struct pci_params { @@ -306,6 +308,7 @@ struct adapter_params { unsigned char bypass; unsigned int ofldq_wr_cred; + bool ulptx_memwrite_dsgl; /* use of T5 DSGL allowed */ }; #include "t4fw_api.h" @@ -957,7 +960,7 @@ int t4_mc_read(struct adapter *adap, int idx, u32 addr, __be32 *data, u64 *parity); int t4_edc_read(struct adapter *adap, int idx, u32 addr, __be32 *data, u64 *parity); - +const char *t4_get_port_type_description(enum fw_port_type port_type); void t4_get_port_stats(struct adapter *adap, int idx, struct port_stats *p); void t4_read_mtu_tbl(struct adapter *adap, u16 *mtus, u8 *mtu_log); void t4_tp_wr_bits_indirect(struct adapter *adap, unsigned int addr, diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 43ab35fea48d..0ac53dd84c61 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -254,6 +254,8 @@ static DEFINE_PCI_DEVICE_TABLE(cxgb4_pci_tbl) = { CH_DEVICE(0x5011, 4), CH_DEVICE(0x5012, 4), CH_DEVICE(0x5013, 4), + CH_DEVICE(0x5014, 4), + CH_DEVICE(0x5015, 4), CH_DEVICE(0x5401, 4), CH_DEVICE(0x5402, 4), CH_DEVICE(0x5403, 4), @@ -273,6 +275,8 @@ static DEFINE_PCI_DEVICE_TABLE(cxgb4_pci_tbl) = { CH_DEVICE(0x5411, 4), CH_DEVICE(0x5412, 4), CH_DEVICE(0x5413, 4), + CH_DEVICE(0x5414, 4), + CH_DEVICE(0x5415, 4), { 0, } }; @@ -423,15 +427,18 @@ static void link_report(struct net_device *dev) const struct port_info *p = netdev_priv(dev); switch (p->link_cfg.speed) { - case SPEED_10000: + case 10000: s = "10Gbps"; break; - case SPEED_1000: + case 1000: s = "1000Mbps"; break; - case SPEED_100: + case 100: s = "100Mbps"; break; + case 40000: + s = "40Gbps"; + break; } netdev_info(dev, "link up, %s, full-duplex, %s PAUSE\n", s, @@ -2061,7 +2068,7 @@ static void get_regs(struct net_device *dev, struct ethtool_regs *regs, 0x40200, 0x40298, 0x402ac, 0x4033c, 0x403f8, 0x403fc, - 0x41300, 0x413c4, + 0x41304, 0x413c4, 0x41400, 0x4141c, 0x41480, 0x414d0, 0x44000, 0x44078, @@ -2089,7 +2096,7 @@ static void get_regs(struct net_device *dev, struct ethtool_regs *regs, 0x48200, 0x48298, 0x482ac, 0x4833c, 0x483f8, 0x483fc, - 0x49300, 0x493c4, + 0x49304, 0x493c4, 0x49400, 0x4941c, 0x49480, 0x494d0, 0x4c000, 0x4c078, @@ -2199,6 +2206,8 @@ static unsigned int from_fw_linkcaps(unsigned int type, unsigned int caps) else if (type == FW_PORT_TYPE_FIBER_XFI || type == FW_PORT_TYPE_FIBER_XAUI || type == FW_PORT_TYPE_SFP) v |= SUPPORTED_FIBRE; + else if (type == FW_PORT_TYPE_BP40_BA) + v |= SUPPORTED_40000baseSR4_Full; if (caps & FW_PORT_CAP_ANEG) v |= SUPPORTED_Autoneg; @@ -2215,6 +2224,8 @@ static unsigned int to_fw_linkcaps(unsigned int caps) v |= FW_PORT_CAP_SPEED_1G; if (caps & ADVERTISED_10000baseT_Full) v |= FW_PORT_CAP_SPEED_10G; + if (caps & ADVERTISED_40000baseSR4_Full) + v |= FW_PORT_CAP_SPEED_40G; return v; } @@ -2263,12 +2274,14 @@ static int get_settings(struct net_device *dev, struct ethtool_cmd *cmd) static unsigned int speed_to_caps(int speed) { - if (speed == SPEED_100) + if (speed == 100) return FW_PORT_CAP_SPEED_100M; - if (speed == SPEED_1000) + if (speed == 1000) return FW_PORT_CAP_SPEED_1G; - if (speed == SPEED_10000) + if (speed == 10000) return FW_PORT_CAP_SPEED_10G; + if (speed == 40000) + return FW_PORT_CAP_SPEED_40G; return 0; } @@ -2296,8 +2309,10 @@ static int set_settings(struct net_device *dev, struct ethtool_cmd *cmd) if (cmd->autoneg == AUTONEG_DISABLE) { cap = speed_to_caps(speed); - if (!(lc->supported & cap) || (speed == SPEED_1000) || - (speed == SPEED_10000)) + if (!(lc->supported & cap) || + (speed == 1000) || + (speed == 10000) || + (speed == 40000)) return -EINVAL; lc->requested_speed = cap; lc->advertising = 0; @@ -3765,6 +3780,7 @@ static void uld_attach(struct adapter *adap, unsigned int uld) lli.dbfifo_int_thresh = dbfifo_int_thresh; lli.sge_pktshift = adap->sge.pktshift; lli.enable_fw_ofld_conn = adap->flags & FW_OFLD_CONN; + lli.ulptx_memwrite_dsgl = adap->params.ulptx_memwrite_dsgl; handle = ulds[uld].add(&lli); if (IS_ERR(handle)) { @@ -5370,6 +5386,21 @@ static int adap_init0(struct adapter *adap) (void) t4_set_params(adap, adap->mbox, adap->fn, 0, 1, params, val); /* + * Find out whether we're allowed to use the T5+ ULPTX MEMWRITE DSGL + * capability. Earlier versions of the firmware didn't have the + * ULPTX_MEMWRITE_DSGL so we'll interpret a query failure as no + * permission to use ULPTX MEMWRITE DSGL. + */ + if (is_t4(adap->params.chip)) { + adap->params.ulptx_memwrite_dsgl = false; + } else { + params[0] = FW_PARAM_DEV(ULPTX_MEMWRITE_DSGL); + ret = t4_query_params(adap, adap->mbox, adap->fn, 0, + 1, params, val); + adap->params.ulptx_memwrite_dsgl = (ret == 0 && val[0] != 0); + } + + /* * Get device capabilities so we can determine what resources we need * to manage. */ @@ -5603,9 +5634,10 @@ static const struct pci_error_handlers cxgb4_eeh = { .resume = eeh_resume, }; -static inline bool is_10g_port(const struct link_config *lc) +static inline bool is_x_10g_port(const struct link_config *lc) { - return (lc->supported & FW_PORT_CAP_SPEED_10G) != 0; + return (lc->supported & FW_PORT_CAP_SPEED_10G) != 0 || + (lc->supported & FW_PORT_CAP_SPEED_40G) != 0; } static inline void init_rspq(struct sge_rspq *q, u8 timer_idx, u8 pkt_cnt_idx, @@ -5629,7 +5661,7 @@ static void cfg_queues(struct adapter *adap) int i, q10g = 0, n10g = 0, qidx = 0; for_each_port(adap, i) - n10g += is_10g_port(&adap2pinfo(adap, i)->link_cfg); + n10g += is_x_10g_port(&adap2pinfo(adap, i)->link_cfg); /* * We default to 1 queue per non-10G port and up to # of cores queues @@ -5644,7 +5676,7 @@ static void cfg_queues(struct adapter *adap) struct port_info *pi = adap2pinfo(adap, i); pi->first_qset = qidx; - pi->nqsets = is_10g_port(&pi->link_cfg) ? q10g : 1; + pi->nqsets = is_x_10g_port(&pi->link_cfg) ? q10g : 1; qidx += pi->nqsets; } @@ -5737,7 +5769,7 @@ static void reduce_ethqs(struct adapter *adap, int n) static int enable_msix(struct adapter *adap) { int ofld_need = 0; - int i, err, want, need; + int i, want, need; struct sge *s = &adap->sge; unsigned int nchan = adap->params.nports; struct msix_entry entries[MAX_INGQ + 1]; @@ -5753,32 +5785,30 @@ static int enable_msix(struct adapter *adap) } need = adap->params.nports + EXTRA_VECS + ofld_need; - while ((err = pci_enable_msix(adap->pdev, entries, want)) >= need) - want = err; + want = pci_enable_msix_range(adap->pdev, entries, need, want); + if (want < 0) + return want; - if (!err) { - /* - * Distribute available vectors to the various queue groups. - * Every group gets its minimum requirement and NIC gets top - * priority for leftovers. - */ - i = want - EXTRA_VECS - ofld_need; - if (i < s->max_ethqsets) { - s->max_ethqsets = i; - if (i < s->ethqsets) - reduce_ethqs(adap, i); - } - if (is_offload(adap)) { - i = want - EXTRA_VECS - s->max_ethqsets; - i -= ofld_need - nchan; - s->ofldqsets = (i / nchan) * nchan; /* round down */ - } - for (i = 0; i < want; ++i) - adap->msix_info[i].vec = entries[i].vector; - } else if (err > 0) - dev_info(adap->pdev_dev, - "only %d MSI-X vectors left, not using MSI-X\n", err); - return err; + /* + * Distribute available vectors to the various queue groups. + * Every group gets its minimum requirement and NIC gets top + * priority for leftovers. + */ + i = want - EXTRA_VECS - ofld_need; + if (i < s->max_ethqsets) { + s->max_ethqsets = i; + if (i < s->ethqsets) + reduce_ethqs(adap, i); + } + if (is_offload(adap)) { + i = want - EXTRA_VECS - s->max_ethqsets; + i -= ofld_need - nchan; + s->ofldqsets = (i / nchan) * nchan; /* round down */ + } + for (i = 0; i < want; ++i) + adap->msix_info[i].vec = entries[i].vector; + + return 0; } #undef EXTRA_VECS @@ -5801,11 +5831,6 @@ static int init_rss(struct adapter *adap) static void print_port_info(const struct net_device *dev) { - static const char *base[] = { - "R XFI", "R XAUI", "T SGMII", "T XFI", "T XAUI", "KX4", "CX4", - "KX", "KR", "R SFP+", "KR/KX", "KR/KX/KX4" - }; - char buf[80]; char *bufp = buf; const char *spd = ""; @@ -5823,9 +5848,11 @@ static void print_port_info(const struct net_device *dev) bufp += sprintf(bufp, "1000/"); if (pi->link_cfg.supported & FW_PORT_CAP_SPEED_10G) bufp += sprintf(bufp, "10G/"); + if (pi->link_cfg.supported & FW_PORT_CAP_SPEED_40G) + bufp += sprintf(bufp, "40G/"); if (bufp != buf) --bufp; - sprintf(bufp, "BASE-%s", base[pi->port_type]); + sprintf(bufp, "BASE-%s", t4_get_port_type_description(pi->port_type)); netdev_info(dev, "Chelsio %s rev %d %s %sNIC PCIe x%d%s%s\n", adap->params.vpd.id, @@ -5833,8 +5860,8 @@ static void print_port_info(const struct net_device *dev) is_offload(adap) ? "R" : "", adap->params.pci.width, spd, (adap->flags & USING_MSIX) ? " MSI-X" : (adap->flags & USING_MSI) ? " MSI" : ""); - netdev_info(dev, "S/N: %s, E/C: %s\n", - adap->params.vpd.sn, adap->params.vpd.ec); + netdev_info(dev, "S/N: %s, P/N: %s\n", + adap->params.vpd.sn, adap->params.vpd.pn); } static void enable_pcie_relaxed_ordering(struct pci_dev *dev) @@ -6179,6 +6206,7 @@ static struct pci_driver cxgb4_driver = { .id_table = cxgb4_pci_tbl, .probe = init_one, .remove = remove_one, + .shutdown = remove_one, .err_handler = &cxgb4_eeh, }; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h index 4dd0a82533e4..e274a047528f 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h @@ -253,6 +253,7 @@ struct cxgb4_lld_info { /* packet data */ bool enable_fw_ofld_conn; /* Enable connection through fw */ /* WR */ + bool ulptx_memwrite_dsgl; /* use of T5 DSGL allowed */ }; struct cxgb4_uld_info { diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c index 47ffa64fcf19..af76b25bb606 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c @@ -706,11 +706,17 @@ static inline unsigned int flits_to_desc(unsigned int n) * @skb: the packet * * Returns whether an Ethernet packet is small enough to fit as - * immediate data. + * immediate data. Return value corresponds to headroom required. */ static inline int is_eth_imm(const struct sk_buff *skb) { - return skb->len <= MAX_IMM_TX_PKT_LEN - sizeof(struct cpl_tx_pkt); + int hdrlen = skb_shinfo(skb)->gso_size ? + sizeof(struct cpl_tx_pkt_lso_core) : 0; + + hdrlen += sizeof(struct cpl_tx_pkt); + if (skb->len <= MAX_IMM_TX_PKT_LEN - hdrlen) + return hdrlen; + return 0; } /** @@ -723,9 +729,10 @@ static inline int is_eth_imm(const struct sk_buff *skb) static inline unsigned int calc_tx_flits(const struct sk_buff *skb) { unsigned int flits; + int hdrlen = is_eth_imm(skb); - if (is_eth_imm(skb)) - return DIV_ROUND_UP(skb->len + sizeof(struct cpl_tx_pkt), 8); + if (hdrlen) + return DIV_ROUND_UP(skb->len + hdrlen, sizeof(__be64)); flits = sgl_len(skb_shinfo(skb)->nr_frags + 1) + 4; if (skb_shinfo(skb)->gso_size) @@ -971,6 +978,7 @@ static inline void txq_advance(struct sge_txq *q, unsigned int n) */ netdev_tx_t t4_eth_xmit(struct sk_buff *skb, struct net_device *dev) { + int len; u32 wr_mid; u64 cntrl, *end; int qidx, credits; @@ -982,6 +990,7 @@ netdev_tx_t t4_eth_xmit(struct sk_buff *skb, struct net_device *dev) struct cpl_tx_pkt_core *cpl; const struct skb_shared_info *ssi; dma_addr_t addr[MAX_SKB_FRAGS + 1]; + bool immediate = false; /* * The chip min packet length is 10 octets but play safe and reject @@ -1011,7 +1020,10 @@ out_free: dev_kfree_skb(skb); return NETDEV_TX_BUSY; } - if (!is_eth_imm(skb) && + if (is_eth_imm(skb)) + immediate = true; + + if (!immediate && unlikely(map_skb(adap->pdev_dev, skb, addr) < 0)) { q->mapping_err++; goto out_free; @@ -1028,6 +1040,8 @@ out_free: dev_kfree_skb(skb); wr->r3 = cpu_to_be64(0); end = (u64 *)wr + flits; + len = immediate ? skb->len : 0; + len += sizeof(*cpl); ssi = skb_shinfo(skb); if (ssi->gso_size) { struct cpl_tx_pkt_lso *lso = (void *)wr; @@ -1035,8 +1049,9 @@ out_free: dev_kfree_skb(skb); int l3hdr_len = skb_network_header_len(skb); int eth_xtra_len = skb_network_offset(skb) - ETH_HLEN; + len += sizeof(*lso); wr->op_immdlen = htonl(FW_WR_OP(FW_ETH_TX_PKT_WR) | - FW_WR_IMMDLEN(sizeof(*lso))); + FW_WR_IMMDLEN(len)); lso->c.lso_ctrl = htonl(LSO_OPCODE(CPL_TX_PKT_LSO) | LSO_FIRST_SLICE | LSO_LAST_SLICE | LSO_IPV6(v6) | @@ -1054,9 +1069,6 @@ out_free: dev_kfree_skb(skb); q->tso++; q->tx_cso += ssi->gso_segs; } else { - int len; - - len = is_eth_imm(skb) ? skb->len + sizeof(*cpl) : sizeof(*cpl); wr->op_immdlen = htonl(FW_WR_OP(FW_ETH_TX_PKT_WR) | FW_WR_IMMDLEN(len)); cpl = (void *)(wr + 1); @@ -1078,7 +1090,7 @@ out_free: dev_kfree_skb(skb); cpl->len = htons(skb->len); cpl->ctrl1 = cpu_to_be64(cntrl); - if (is_eth_imm(skb)) { + if (immediate) { inline_tx_skb(skb, &q->q, cpl + 1); dev_kfree_skb(skb); } else { @@ -1467,8 +1479,12 @@ static inline int ofld_send(struct adapter *adap, struct sk_buff *skb) { unsigned int idx = skb_txq(skb); - if (unlikely(is_ctrl_pkt(skb))) + if (unlikely(is_ctrl_pkt(skb))) { + /* Single ctrl queue is a requirement for LE workaround path */ + if (adap->tids.nsftids) + idx = 0; return ctrl_xmit(&adap->sge.ctrlq[idx], skb); + } return ofld_xmit(&adap->sge.ofldtxq[idx], skb); } diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index 2c109343d570..d3c2a516fa88 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -573,7 +573,7 @@ int get_vpd_params(struct adapter *adapter, struct vpd_params *p) { u32 cclk_param, cclk_val; int i, ret, addr; - int ec, sn; + int ec, sn, pn; u8 *vpd, csum; unsigned int vpdr_len, kw_offset, id_len; @@ -638,6 +638,7 @@ int get_vpd_params(struct adapter *adapter, struct vpd_params *p) FIND_VPD_KW(ec, "EC"); FIND_VPD_KW(sn, "SN"); + FIND_VPD_KW(pn, "PN"); #undef FIND_VPD_KW memcpy(p->id, vpd + PCI_VPD_LRDT_TAG_SIZE, id_len); @@ -647,6 +648,8 @@ int get_vpd_params(struct adapter *adapter, struct vpd_params *p) i = pci_vpd_info_field_size(vpd + sn - PCI_VPD_INFO_FLD_HDR_SIZE); memcpy(p->sn, vpd + sn, min(i, SERNUM_LEN)); strim(p->sn); + memcpy(p->pn, vpd + pn, min(i, PN_LEN)); + strim(p->pn); /* * Ask firmware for the Core Clock since it knows how to translate the @@ -1155,7 +1158,8 @@ out: } #define ADVERT_MASK (FW_PORT_CAP_SPEED_100M | FW_PORT_CAP_SPEED_1G |\ - FW_PORT_CAP_SPEED_10G | FW_PORT_CAP_ANEG) + FW_PORT_CAP_SPEED_10G | FW_PORT_CAP_SPEED_40G | \ + FW_PORT_CAP_ANEG) /** * t4_link_start - apply link configuration to MAC/PHY @@ -2247,6 +2251,36 @@ static unsigned int get_mps_bg_map(struct adapter *adap, int idx) } /** + * t4_get_port_type_description - return Port Type string description + * @port_type: firmware Port Type enumeration + */ +const char *t4_get_port_type_description(enum fw_port_type port_type) +{ + static const char *const port_type_description[] = { + "R XFI", + "R XAUI", + "T SGMII", + "T XFI", + "T XAUI", + "KX4", + "CX4", + "KX", + "KR", + "R SFP+", + "KR/KX", + "KR/KX/KX4", + "R QSFP_10G", + "", + "R QSFP", + "R BP40_BA", + }; + + if (port_type < ARRAY_SIZE(port_type_description)) + return port_type_description[port_type]; + return "UNKNOWN"; +} + +/** * t4_get_port_stats - collect port statistics * @adap: the adapter * @idx: the port index @@ -3533,11 +3567,13 @@ int t4_handle_fw_rpl(struct adapter *adap, const __be64 *rpl) if (stat & FW_PORT_CMD_TXPAUSE) fc |= PAUSE_TX; if (stat & FW_PORT_CMD_LSPEED(FW_PORT_CAP_SPEED_100M)) - speed = SPEED_100; + speed = 100; else if (stat & FW_PORT_CMD_LSPEED(FW_PORT_CAP_SPEED_1G)) - speed = SPEED_1000; + speed = 1000; else if (stat & FW_PORT_CMD_LSPEED(FW_PORT_CAP_SPEED_10G)) - speed = SPEED_10000; + speed = 10000; + else if (stat & FW_PORT_CMD_LSPEED(FW_PORT_CAP_SPEED_40G)) + speed = 40000; if (link_ok != lc->link_ok || speed != lc->speed || fc != lc->fc) { /* something changed */ diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h index 74fea74ce0aa..9cc973fbcf26 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h @@ -932,6 +932,7 @@ enum fw_params_param_dev { FW_PARAMS_PARAM_DEV_FWREV = 0x0B, FW_PARAMS_PARAM_DEV_TPREV = 0x0C, FW_PARAMS_PARAM_DEV_CF = 0x0D, + FW_PARAMS_PARAM_DEV_ULPTX_MEMWRITE_DSGL = 0x17, }; /* @@ -1742,6 +1743,9 @@ enum fw_port_type { FW_PORT_TYPE_SFP, FW_PORT_TYPE_BP_AP, FW_PORT_TYPE_BP4_AP, + FW_PORT_TYPE_QSFP_10G, + FW_PORT_TYPE_QSFP, + FW_PORT_TYPE_BP40_BA, FW_PORT_TYPE_NONE = FW_PORT_CMD_PTYPE_MASK }; diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c index 0899c0983594..1d0fe9b60312 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c @@ -2444,7 +2444,7 @@ static void reduce_ethqs(struct adapter *adapter, int n) */ static int enable_msix(struct adapter *adapter) { - int i, err, want, need; + int i, want, need, nqsets; struct msix_entry entries[MSIX_ENTRIES]; struct sge *s = &adapter->sge; @@ -2460,26 +2460,23 @@ static int enable_msix(struct adapter *adapter) */ want = s->max_ethqsets + MSIX_EXTRAS; need = adapter->params.nports + MSIX_EXTRAS; - while ((err = pci_enable_msix(adapter->pdev, entries, want)) >= need) - want = err; - if (err == 0) { - int nqsets = want - MSIX_EXTRAS; - if (nqsets < s->max_ethqsets) { - dev_warn(adapter->pdev_dev, "only enough MSI-X vectors" - " for %d Queue Sets\n", nqsets); - s->max_ethqsets = nqsets; - if (nqsets < s->ethqsets) - reduce_ethqs(adapter, nqsets); - } - for (i = 0; i < want; ++i) - adapter->msix_info[i].vec = entries[i].vector; - } else if (err > 0) { - pci_disable_msix(adapter->pdev); - dev_info(adapter->pdev_dev, "only %d MSI-X vectors left," - " not using MSI-X\n", err); + want = pci_enable_msix_range(adapter->pdev, entries, need, want); + if (want < 0) + return want; + + nqsets = want - MSIX_EXTRAS; + if (nqsets < s->max_ethqsets) { + dev_warn(adapter->pdev_dev, "only enough MSI-X vectors" + " for %d Queue Sets\n", nqsets); + s->max_ethqsets = nqsets; + if (nqsets < s->ethqsets) + reduce_ethqs(adapter, nqsets); } - return err; + for (i = 0; i < want; ++i) + adapter->msix_info[i].vec = entries[i].vector; + + return 0; } static const struct net_device_ops cxgb4vf_netdev_ops = { diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c index b740bfce72ef..dcd58f23834a 100644 --- a/drivers/net/ethernet/cisco/enic/enic_main.c +++ b/drivers/net/ethernet/cisco/enic/enic_main.c @@ -1796,7 +1796,8 @@ static int enic_set_intr_mode(struct enic *enic) enic->cq_count >= n + m && enic->intr_count >= n + m + 2) { - if (!pci_enable_msix(enic->pdev, enic->msix_entry, n + m + 2)) { + if (pci_enable_msix_range(enic->pdev, enic->msix_entry, + n + m + 2, n + m + 2) > 0) { enic->rq_count = n; enic->wq_count = m; @@ -1815,7 +1816,8 @@ static int enic_set_intr_mode(struct enic *enic) enic->wq_count >= m && enic->cq_count >= 1 + m && enic->intr_count >= 1 + m + 2) { - if (!pci_enable_msix(enic->pdev, enic->msix_entry, 1 + m + 2)) { + if (pci_enable_msix_range(enic->pdev, enic->msix_entry, + 1 + m + 2, 1 + m + 2) > 0) { enic->rq_count = 1; enic->wq_count = m; diff --git a/drivers/net/ethernet/dec/tulip/tulip_core.c b/drivers/net/ethernet/dec/tulip/tulip_core.c index add05f14b38b..1642de78aac8 100644 --- a/drivers/net/ethernet/dec/tulip/tulip_core.c +++ b/drivers/net/ethernet/dec/tulip/tulip_core.c @@ -1939,6 +1939,7 @@ static void tulip_remove_one(struct pci_dev *pdev) pci_iounmap(pdev, tp->base_addr); free_netdev (dev); pci_release_regions (pdev); + pci_disable_device(pdev); /* pci_power_off (pdev, -1); */ } diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h index 8d09615da585..a587c8aa27ed 100644 --- a/drivers/net/ethernet/emulex/benet/be.h +++ b/drivers/net/ethernet/emulex/benet/be.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2005 - 2013 Emulex + * Copyright (C) 2005 - 2014 Emulex * All rights reserved. * * This program is free software; you can redistribute it and/or @@ -34,7 +34,7 @@ #include "be_hw.h" #include "be_roce.h" -#define DRV_VER "10.0.600.0u" +#define DRV_VER "10.2u" #define DRV_NAME "be2net" #define BE_NAME "Emulex BladeEngine2" #define BE3_NAME "Emulex BladeEngine3" @@ -88,7 +88,6 @@ static inline char *nic_name(struct pci_dev *pdev) #define BE_MIN_MTU 256 #define BE_NUM_VLANS_SUPPORTED 64 -#define BE_UMC_NUM_VLANS_SUPPORTED 15 #define BE_MAX_EQD 128u #define BE_MAX_TX_FRAG_COUNT 30 @@ -262,9 +261,10 @@ struct be_tx_obj { /* Struct to remember the pages posted for rx frags */ struct be_rx_page_info { struct page *page; + /* set to page-addr for last frag of the page & frag-addr otherwise */ DEFINE_DMA_UNMAP_ADDR(bus); u16 page_offset; - bool last_page_user; + bool last_frag; /* last frag of the page */ }; struct be_rx_stats { @@ -293,7 +293,7 @@ struct be_rx_compl_info { u8 ip_csum; u8 l4_csum; u8 ipv6; - u8 vtm; + u8 qnq; u8 pkt_type; u8 ip_frag; }; @@ -350,13 +350,16 @@ struct be_drv_stats { u32 roce_drops_crc; }; +/* A vlan-id of 0xFFFF must be used to clear transparent vlan-tagging */ +#define BE_RESET_VLAN_TAG_ID 0xFFFF + struct be_vf_cfg { unsigned char mac_addr[ETH_ALEN]; int if_handle; int pmac_id; - u16 def_vid; u16 vlan_tag; u32 tx_rate; + u32 plink_tracking; }; enum vf_state { @@ -465,6 +468,7 @@ struct be_adapter { u32 port_num; bool promiscuous; + u8 mc_type; u32 function_mode; u32 function_caps; u32 rx_fc; /* Rx flow control */ @@ -534,6 +538,14 @@ static inline u16 be_max_qs(struct be_adapter *adapter) return min_t(u16, num, num_online_cpus()); } +/* Is BE in pvid_tagging mode */ +#define be_pvid_tagging_enabled(adapter) (adapter->pvid) + +/* Is BE in QNQ multi-channel mode */ +#define be_is_qnq_mode(adapter) (adapter->mc_type == FLEX10 || \ + adapter->mc_type == vNIC1 || \ + adapter->mc_type == UFP) + #define lancer_chip(adapter) (adapter->pdev->device == OC_DEVICE_ID3 || \ adapter->pdev->device == OC_DEVICE_ID4) diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c index 48076a6370c3..cf5afe72f12f 100644 --- a/drivers/net/ethernet/emulex/benet/be_cmds.c +++ b/drivers/net/ethernet/emulex/benet/be_cmds.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2005 - 2013 Emulex + * Copyright (C) 2005 - 2014 Emulex * All rights reserved. * * This program is free software; you can redistribute it and/or @@ -202,8 +202,12 @@ static void be_async_link_state_process(struct be_adapter *adapter, /* When link status changes, link speed must be re-queried from FW */ adapter->phy.link_speed = -1; - /* Ignore physical link event */ - if (lancer_chip(adapter) && + /* On BEx the FW does not send a separate link status + * notification for physical and logical link. + * On other chips just process the logical link + * status notification + */ + if (!BEx_chip(adapter) && !(evt->port_link_status & LOGICAL_LINK_STATUS_MASK)) return; @@ -211,7 +215,8 @@ static void be_async_link_state_process(struct be_adapter *adapter, * it may not be received in some cases. */ if (adapter->flags & BE_FLAGS_LINK_STATUS_INIT) - be_link_status_update(adapter, evt->port_link_status); + be_link_status_update(adapter, + evt->port_link_status & LINK_STATUS_MASK); } /* Grp5 CoS Priority evt */ @@ -239,10 +244,12 @@ static void be_async_grp5_qos_speed_process(struct be_adapter *adapter, static void be_async_grp5_pvid_state_process(struct be_adapter *adapter, struct be_async_event_grp5_pvid_state *evt) { - if (evt->enabled) + if (evt->enabled) { adapter->pvid = le16_to_cpu(evt->tag) & VLAN_VID_MASK; - else + dev_info(&adapter->pdev->dev, "LPVID: %d\n", adapter->pvid); + } else { adapter->pvid = 0; + } } static void be_async_grp5_evt_process(struct be_adapter *adapter, @@ -3296,6 +3303,21 @@ static struct be_pcie_res_desc *be_get_pcie_desc(u8 devfn, u8 *buf, return NULL; } +static struct be_port_res_desc *be_get_port_desc(u8 *buf, u32 desc_count) +{ + struct be_res_desc_hdr *hdr = (struct be_res_desc_hdr *)buf; + int i; + + for (i = 0; i < desc_count; i++) { + if (hdr->desc_type == PORT_RESOURCE_DESC_TYPE_V1) + return (struct be_port_res_desc *)hdr; + + hdr->desc_len = hdr->desc_len ? : RESOURCE_DESC_SIZE_V0; + hdr = (void *)hdr + hdr->desc_len; + } + return NULL; +} + static void be_copy_nic_desc(struct be_resources *res, struct be_nic_res_desc *desc) { @@ -3439,6 +3461,7 @@ int be_cmd_get_profile_config(struct be_adapter *adapter, { struct be_cmd_resp_get_profile_config *resp; struct be_pcie_res_desc *pcie; + struct be_port_res_desc *port; struct be_nic_res_desc *nic; struct be_queue_info *mccq = &adapter->mcc_obj.q; struct be_dma_mem cmd; @@ -3466,6 +3489,10 @@ int be_cmd_get_profile_config(struct be_adapter *adapter, if (pcie) res->max_vfs = le16_to_cpu(pcie->num_vfs); + port = be_get_port_desc(resp->func_param, desc_count); + if (port) + adapter->mc_type = port->mc_type; + nic = be_get_nic_desc(resp->func_param, desc_count); if (nic) be_copy_nic_desc(res, nic); @@ -3723,6 +3750,45 @@ err: return status; } +int be_cmd_set_logical_link_config(struct be_adapter *adapter, + int link_state, u8 domain) +{ + struct be_mcc_wrb *wrb; + struct be_cmd_req_set_ll_link *req; + int status; + + if (BEx_chip(adapter) || lancer_chip(adapter)) + return 0; + + spin_lock_bh(&adapter->mcc_lock); + + wrb = wrb_from_mccq(adapter); + if (!wrb) { + status = -EBUSY; + goto err; + } + + req = embedded_payload(wrb); + + be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON, + OPCODE_COMMON_SET_LOGICAL_LINK_CONFIG, + sizeof(*req), wrb, NULL); + + req->hdr.version = 1; + req->hdr.domain = domain; + + if (link_state == IFLA_VF_LINK_STATE_ENABLE) + req->link_config |= 1; + + if (link_state == IFLA_VF_LINK_STATE_AUTO) + req->link_config |= 1 << PLINK_TRACK_SHIFT; + + status = be_mcc_notify_wait(adapter); +err: + spin_unlock_bh(&adapter->mcc_lock); + return status; +} + int be_roce_mcc_cmd(void *netdev_handle, void *wrb_payload, int wrb_payload_size, u16 *cmd_status, u16 *ext_status) { diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.h b/drivers/net/ethernet/emulex/benet/be_cmds.h index fc4e076dc202..fda3e8851e17 100644 --- a/drivers/net/ethernet/emulex/benet/be_cmds.h +++ b/drivers/net/ethernet/emulex/benet/be_cmds.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2005 - 2013 Emulex + * Copyright (C) 2005 - 2014 Emulex * All rights reserved. * * This program is free software; you can redistribute it and/or @@ -203,6 +203,7 @@ struct be_mcc_mailbox { #define OPCODE_COMMON_GET_BEACON_STATE 70 #define OPCODE_COMMON_READ_TRANSRECV_DATA 73 #define OPCODE_COMMON_GET_PORT_NAME 77 +#define OPCODE_COMMON_SET_LOGICAL_LINK_CONFIG 80 #define OPCODE_COMMON_SET_INTERRUPT_ENABLE 89 #define OPCODE_COMMON_SET_FN_PRIVILEGES 100 #define OPCODE_COMMON_GET_PHY_DETAILS 102 @@ -1098,14 +1099,6 @@ struct be_cmd_resp_query_fw_cfg { u32 function_caps; }; -/* Is BE in a multi-channel mode */ -static inline bool be_is_mc(struct be_adapter *adapter) -{ - return adapter->function_mode & FLEX10_MODE || - adapter->function_mode & VNIC_MODE || - adapter->function_mode & UMC_ENABLED; -} - /******************** RSS Config ****************************************/ /* RSS type Input parameters used to compute RX hash * RSS_ENABLE_IPV4 SRC IPv4, DST IPv4 @@ -1828,6 +1821,7 @@ struct be_cmd_req_set_ext_fat_caps { #define NIC_RESOURCE_DESC_TYPE_V0 0x41 #define PCIE_RESOURCE_DESC_TYPE_V1 0x50 #define NIC_RESOURCE_DESC_TYPE_V1 0x51 +#define PORT_RESOURCE_DESC_TYPE_V1 0x55 #define MAX_RESOURCE_DESC 264 /* QOS unit number */ @@ -1891,6 +1885,33 @@ struct be_nic_res_desc { u32 rsvd8[7]; } __packed; +/************ Multi-Channel type ***********/ +enum mc_type { + MC_NONE = 0x01, + UMC = 0x02, + FLEX10 = 0x03, + vNIC1 = 0x04, + nPAR = 0x05, + UFP = 0x06, + vNIC2 = 0x07 +}; + +struct be_port_res_desc { + struct be_res_desc_hdr hdr; + u8 rsvd0; + u8 flags; + u8 rsvd1; + u8 mc_type; + u16 rsvd2; + u32 rsvd3[20]; +} __packed; + +/* Is BE in a multi-channel mode */ +static inline bool be_is_mc(struct be_adapter *adapter) +{ + return adapter->mc_type > MC_NONE; +} + struct be_cmd_req_get_func_config { struct be_cmd_req_hdr hdr; }; @@ -1971,6 +1992,13 @@ struct be_cmd_resp_get_iface_list { struct be_if_desc if_desc; }; +/*************** Set logical link ********************/ +#define PLINK_TRACK_SHIFT 8 +struct be_cmd_req_set_ll_link { + struct be_cmd_req_hdr hdr; + u32 link_config; /* Bit 0: UP_DOWN, Bit 9: PLINK */ +}; + int be_pci_fnum_get(struct be_adapter *adapter); int be_fw_wait_ready(struct be_adapter *adapter); int be_cmd_mac_addr_query(struct be_adapter *adapter, u8 *mac_addr, @@ -2092,3 +2120,5 @@ int be_cmd_get_if_id(struct be_adapter *adapter, struct be_vf_cfg *vf_cfg, int vf_num); int be_cmd_enable_vf(struct be_adapter *adapter, u8 domain); int be_cmd_intr_set(struct be_adapter *adapter, bool intr_enable); +int be_cmd_set_logical_link_config(struct be_adapter *adapter, + int link_state, u8 domain); diff --git a/drivers/net/ethernet/emulex/benet/be_ethtool.c b/drivers/net/ethernet/emulex/benet/be_ethtool.c index 05be0070f55f..66759b6ce373 100644 --- a/drivers/net/ethernet/emulex/benet/be_ethtool.c +++ b/drivers/net/ethernet/emulex/benet/be_ethtool.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2005 - 2013 Emulex + * Copyright (C) 2005 - 2014 Emulex * All rights reserved. * * This program is free software; you can redistribute it and/or @@ -802,16 +802,18 @@ be_self_test(struct net_device *netdev, struct ethtool_test *test, u64 *data) if (test->flags & ETH_TEST_FL_OFFLINE) { if (be_loopback_test(adapter, BE_MAC_LOOPBACK, - &data[0]) != 0) { + &data[0]) != 0) test->flags |= ETH_TEST_FL_FAILED; - } + if (be_loopback_test(adapter, BE_PHY_LOOPBACK, - &data[1]) != 0) { - test->flags |= ETH_TEST_FL_FAILED; - } - if (be_loopback_test(adapter, BE_ONE_PORT_EXT_LOOPBACK, - &data[2]) != 0) { + &data[1]) != 0) test->flags |= ETH_TEST_FL_FAILED; + + if (test->flags & ETH_TEST_FL_EXTERNAL_LB) { + if (be_loopback_test(adapter, BE_ONE_PORT_EXT_LOOPBACK, + &data[2]) != 0) + test->flags |= ETH_TEST_FL_FAILED; + test->flags |= ETH_TEST_FL_EXTERNAL_LB_DONE; } } diff --git a/drivers/net/ethernet/emulex/benet/be_hw.h b/drivers/net/ethernet/emulex/benet/be_hw.h index dc88782185f2..28ac8dd0beaa 100644 --- a/drivers/net/ethernet/emulex/benet/be_hw.h +++ b/drivers/net/ethernet/emulex/benet/be_hw.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2005 - 2013 Emulex + * Copyright (C) 2005 - 2014 Emulex * All rights reserved. * * This program is free software; you can redistribute it and/or @@ -368,7 +368,7 @@ struct amap_eth_rx_compl_v0 { u8 numfrags[3]; /* dword 1 */ u8 rss_flush; /* dword 2 */ u8 cast_enc[2]; /* dword 2 */ - u8 vtm; /* dword 2 */ + u8 qnq; /* dword 2 */ u8 rss_bank; /* dword 2 */ u8 rsvd1[23]; /* dword 2 */ u8 lro_pkt; /* dword 2 */ @@ -401,7 +401,7 @@ struct amap_eth_rx_compl_v1 { u8 numfrags[3]; /* dword 1 */ u8 rss_flush; /* dword 2 */ u8 cast_enc[2]; /* dword 2 */ - u8 vtm; /* dword 2 */ + u8 qnq; /* dword 2 */ u8 rss_bank; /* dword 2 */ u8 port[2]; /* dword 2 */ u8 vntagp; /* dword 2 */ diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index 04ac9c6a0d39..239273b7b881 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2005 - 2013 Emulex + * Copyright (C) 2005 - 2014 Emulex * All rights reserved. * * This program is free software; you can redistribute it and/or @@ -652,7 +652,7 @@ void be_link_status_update(struct be_adapter *adapter, u8 link_status) adapter->flags |= BE_FLAGS_LINK_STATUS_INIT; } - if ((link_status & LINK_STATUS_MASK) == LINK_UP) + if (link_status) netif_carrier_on(netdev); else netif_carrier_off(netdev); @@ -913,24 +913,14 @@ static int be_ipv6_tx_stall_chk(struct be_adapter *adapter, return BE3_chip(adapter) && be_ipv6_exthdr_check(skb); } -static struct sk_buff *be_xmit_workarounds(struct be_adapter *adapter, - struct sk_buff *skb, - bool *skip_hw_vlan) +static struct sk_buff *be_lancer_xmit_workarounds(struct be_adapter *adapter, + struct sk_buff *skb, + bool *skip_hw_vlan) { struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data; unsigned int eth_hdr_len; struct iphdr *ip; - /* Lancer, SH-R ASICs have a bug wherein Packets that are 32 bytes or less - * may cause a transmit stall on that port. So the work-around is to - * pad short packets (<= 32 bytes) to a 36-byte length. - */ - if (unlikely(!BEx_chip(adapter) && skb->len <= 32)) { - if (skb_padto(skb, 36)) - goto tx_drop; - skb->len = 36; - } - /* For padded packets, BE HW modifies tot_len field in IP header * incorrecly when VLAN tag is inserted by HW. * For padded packets, Lancer computes incorrect checksum. @@ -945,9 +935,9 @@ static struct sk_buff *be_xmit_workarounds(struct be_adapter *adapter, } /* If vlan tag is already inlined in the packet, skip HW VLAN - * tagging in UMC mode + * tagging in pvid-tagging mode */ - if ((adapter->function_mode & UMC_ENABLED) && + if (be_pvid_tagging_enabled(adapter) && veh->h_vlan_proto == htons(ETH_P_8021Q)) *skip_hw_vlan = true; @@ -959,7 +949,7 @@ static struct sk_buff *be_xmit_workarounds(struct be_adapter *adapter, vlan_tx_tag_present(skb)) { skb = be_insert_vlan_in_pkt(adapter, skb, skip_hw_vlan); if (unlikely(!skb)) - goto tx_drop; + goto err; } /* HW may lockup when VLAN HW tagging is requested on @@ -981,15 +971,39 @@ static struct sk_buff *be_xmit_workarounds(struct be_adapter *adapter, be_vlan_tag_tx_chk(adapter, skb)) { skb = be_insert_vlan_in_pkt(adapter, skb, skip_hw_vlan); if (unlikely(!skb)) - goto tx_drop; + goto err; } return skb; tx_drop: dev_kfree_skb_any(skb); +err: return NULL; } +static struct sk_buff *be_xmit_workarounds(struct be_adapter *adapter, + struct sk_buff *skb, + bool *skip_hw_vlan) +{ + /* Lancer, SH-R ASICs have a bug wherein Packets that are 32 bytes or + * less may cause a transmit stall on that port. So the work-around is + * to pad short packets (<= 32 bytes) to a 36-byte length. + */ + if (unlikely(!BEx_chip(adapter) && skb->len <= 32)) { + if (skb_padto(skb, 36)) + return NULL; + skb->len = 36; + } + + if (BEx_chip(adapter) || lancer_chip(adapter)) { + skb = be_lancer_xmit_workarounds(adapter, skb, skip_hw_vlan); + if (!skb) + return NULL; + } + + return skb; +} + static netdev_tx_t be_xmit(struct sk_buff *skb, struct net_device *netdev) { struct be_adapter *adapter = netdev_priv(netdev); @@ -1124,7 +1138,10 @@ static int be_vlan_add_vid(struct net_device *netdev, __be16 proto, u16 vid) /* Packets with VID 0 are always received by Lancer by default */ if (lancer_chip(adapter) && vid == 0) - goto ret; + return status; + + if (adapter->vlan_tag[vid]) + return status; adapter->vlan_tag[vid] = 1; adapter->vlans_added++; @@ -1134,7 +1151,7 @@ static int be_vlan_add_vid(struct net_device *netdev, __be16 proto, u16 vid) adapter->vlans_added--; adapter->vlan_tag[vid] = 0; } -ret: + return status; } @@ -1157,6 +1174,14 @@ ret: return status; } +static void be_clear_promisc(struct be_adapter *adapter) +{ + adapter->promiscuous = false; + adapter->flags &= ~BE_FLAGS_VLAN_PROMISC; + + be_cmd_rx_filter(adapter, IFF_PROMISC, OFF); +} + static void be_set_rx_mode(struct net_device *netdev) { struct be_adapter *adapter = netdev_priv(netdev); @@ -1170,9 +1195,7 @@ static void be_set_rx_mode(struct net_device *netdev) /* BE was previously in promiscuous mode; disable it */ if (adapter->promiscuous) { - adapter->promiscuous = false; - be_cmd_rx_filter(adapter, IFF_PROMISC, OFF); - + be_clear_promisc(adapter); if (adapter->vlans_added) be_vid_config(adapter); } @@ -1268,6 +1291,7 @@ static int be_get_vf_config(struct net_device *netdev, int vf, vi->vlan = vf_cfg->vlan_tag & VLAN_VID_MASK; vi->qos = vf_cfg->vlan_tag >> VLAN_PRIO_SHIFT; memcpy(&vi->mac, vf_cfg->mac_addr, ETH_ALEN); + vi->linkstate = adapter->vf_cfg[vf].plink_tracking; return 0; } @@ -1287,24 +1311,20 @@ static int be_set_vf_vlan(struct net_device *netdev, if (vlan || qos) { vlan |= qos << VLAN_PRIO_SHIFT; - if (vf_cfg->vlan_tag != vlan) { - /* If this is new value, program it. Else skip. */ - vf_cfg->vlan_tag = vlan; + if (vf_cfg->vlan_tag != vlan) status = be_cmd_set_hsw_config(adapter, vlan, vf + 1, vf_cfg->if_handle, 0); - } } else { /* Reset Transparent Vlan Tagging. */ - vf_cfg->vlan_tag = 0; - vlan = vf_cfg->def_vid; - status = be_cmd_set_hsw_config(adapter, vlan, vf + 1, - vf_cfg->if_handle, 0); + status = be_cmd_set_hsw_config(adapter, BE_RESET_VLAN_TAG_ID, + vf + 1, vf_cfg->if_handle, 0); } - - if (status) + if (!status) + vf_cfg->vlan_tag = vlan; + else dev_info(&adapter->pdev->dev, - "VLAN %d config on VF %d failed\n", vlan, vf); + "VLAN %d config on VF %d failed\n", vlan, vf); return status; } @@ -1338,6 +1358,24 @@ static int be_set_vf_tx_rate(struct net_device *netdev, adapter->vf_cfg[vf].tx_rate = rate; return status; } +static int be_set_vf_link_state(struct net_device *netdev, int vf, + int link_state) +{ + struct be_adapter *adapter = netdev_priv(netdev); + int status; + + if (!sriov_enabled(adapter)) + return -EPERM; + + if (vf >= adapter->num_vfs) + return -EINVAL; + + status = be_cmd_set_logical_link_config(adapter, link_state, vf+1); + if (!status) + adapter->vf_cfg[vf].plink_tracking = link_state; + + return status; +} static void be_aic_update(struct be_aic_obj *aic, u64 rx_pkts, u64 tx_pkts, ulong now) @@ -1448,11 +1486,15 @@ static struct be_rx_page_info *get_rx_page_info(struct be_rx_obj *rxo) rx_page_info = &rxo->page_info_tbl[frag_idx]; BUG_ON(!rx_page_info->page); - if (rx_page_info->last_page_user) { + if (rx_page_info->last_frag) { dma_unmap_page(&adapter->pdev->dev, dma_unmap_addr(rx_page_info, bus), adapter->big_page_size, DMA_FROM_DEVICE); - rx_page_info->last_page_user = false; + rx_page_info->last_frag = false; + } else { + dma_sync_single_for_cpu(&adapter->pdev->dev, + dma_unmap_addr(rx_page_info, bus), + rx_frag_size, DMA_FROM_DEVICE); } queue_tail_inc(rxq); @@ -1660,7 +1702,7 @@ static void be_parse_rx_compl_v1(struct be_eth_rx_compl *compl, rxcp->rss_hash = AMAP_GET_BITS(struct amap_eth_rx_compl_v1, rsshash, compl); if (rxcp->vlanf) { - rxcp->vtm = AMAP_GET_BITS(struct amap_eth_rx_compl_v1, vtm, + rxcp->qnq = AMAP_GET_BITS(struct amap_eth_rx_compl_v1, qnq, compl); rxcp->vlan_tag = AMAP_GET_BITS(struct amap_eth_rx_compl_v1, vlan_tag, compl); @@ -1690,7 +1732,7 @@ static void be_parse_rx_compl_v0(struct be_eth_rx_compl *compl, rxcp->rss_hash = AMAP_GET_BITS(struct amap_eth_rx_compl_v0, rsshash, compl); if (rxcp->vlanf) { - rxcp->vtm = AMAP_GET_BITS(struct amap_eth_rx_compl_v0, vtm, + rxcp->qnq = AMAP_GET_BITS(struct amap_eth_rx_compl_v0, qnq, compl); rxcp->vlan_tag = AMAP_GET_BITS(struct amap_eth_rx_compl_v0, vlan_tag, compl); @@ -1723,9 +1765,11 @@ static struct be_rx_compl_info *be_rx_compl_get(struct be_rx_obj *rxo) rxcp->l4_csum = 0; if (rxcp->vlanf) { - /* vlanf could be wrongly set in some cards. - * ignore if vtm is not set */ - if ((adapter->function_mode & FLEX10_MODE) && !rxcp->vtm) + /* In QNQ modes, if qnq bit is not set, then the packet was + * tagged only with the transparent outer vlan-tag and must + * not be treated as a vlan packet by host + */ + if (be_is_qnq_mode(adapter) && !rxcp->qnq) rxcp->vlanf = 0; if (!lancer_chip(adapter)) @@ -1784,17 +1828,16 @@ static void be_post_rx_frags(struct be_rx_obj *rxo, gfp_t gfp) rx_stats(rxo)->rx_post_fail++; break; } - page_info->page_offset = 0; + page_offset = 0; } else { get_page(pagep); - page_info->page_offset = page_offset + rx_frag_size; + page_offset += rx_frag_size; } - page_offset = page_info->page_offset; + page_info->page_offset = page_offset; page_info->page = pagep; - dma_unmap_addr_set(page_info, bus, page_dmaaddr); - frag_dmaaddr = page_dmaaddr + page_info->page_offset; rxd = queue_head_node(rxq); + frag_dmaaddr = page_dmaaddr + page_info->page_offset; rxd->fragpa_lo = cpu_to_le32(frag_dmaaddr & 0xFFFFFFFF); rxd->fragpa_hi = cpu_to_le32(upper_32_bits(frag_dmaaddr)); @@ -1802,15 +1845,24 @@ static void be_post_rx_frags(struct be_rx_obj *rxo, gfp_t gfp) if ((page_offset + rx_frag_size + rx_frag_size) > adapter->big_page_size) { pagep = NULL; - page_info->last_page_user = true; + page_info->last_frag = true; + dma_unmap_addr_set(page_info, bus, page_dmaaddr); + } else { + dma_unmap_addr_set(page_info, bus, frag_dmaaddr); } prev_page_info = page_info; queue_head_inc(rxq); page_info = &rxo->page_info_tbl[rxq->head]; } - if (pagep) - prev_page_info->last_page_user = true; + + /* Mark the last frag of a page when we break out of the above loop + * with no more slots available in the RXQ + */ + if (pagep) { + prev_page_info->last_frag = true; + dma_unmap_addr_set(prev_page_info, bus, page_dmaaddr); + } if (posted) { atomic_add(posted, &rxq->used); @@ -1867,7 +1919,7 @@ static u16 be_tx_compl_process(struct be_adapter *adapter, queue_tail_inc(txq); } while (cur_index != last_index); - kfree_skb(sent_skb); + dev_kfree_skb_any(sent_skb); return num_wrbs; } @@ -2423,6 +2475,9 @@ void be_detect_error(struct be_adapter *adapter) u32 ue_lo = 0, ue_hi = 0, ue_lo_mask = 0, ue_hi_mask = 0; u32 sliport_status = 0, sliport_err1 = 0, sliport_err2 = 0; u32 i; + bool error_detected = false; + struct device *dev = &adapter->pdev->dev; + struct net_device *netdev = adapter->netdev; if (be_hw_error(adapter)) return; @@ -2434,6 +2489,21 @@ void be_detect_error(struct be_adapter *adapter) SLIPORT_ERROR1_OFFSET); sliport_err2 = ioread32(adapter->db + SLIPORT_ERROR2_OFFSET); + adapter->hw_error = true; + /* Do not log error messages if its a FW reset */ + if (sliport_err1 == SLIPORT_ERROR_FW_RESET1 && + sliport_err2 == SLIPORT_ERROR_FW_RESET2) { + dev_info(dev, "Firmware update in progress\n"); + } else { + error_detected = true; + dev_err(dev, "Error detected in the card\n"); + dev_err(dev, "ERR: sliport status 0x%x\n", + sliport_status); + dev_err(dev, "ERR: sliport error1 0x%x\n", + sliport_err1); + dev_err(dev, "ERR: sliport error2 0x%x\n", + sliport_err2); + } } } else { pci_read_config_dword(adapter->pdev, @@ -2447,51 +2517,33 @@ void be_detect_error(struct be_adapter *adapter) ue_lo = (ue_lo & ~ue_lo_mask); ue_hi = (ue_hi & ~ue_hi_mask); - } - - /* On certain platforms BE hardware can indicate spurious UEs. - * Allow the h/w to stop working completely in case of a real UE. - * Hence not setting the hw_error for UE detection. - */ - if (sliport_status & SLIPORT_STATUS_ERR_MASK) { - adapter->hw_error = true; - /* Do not log error messages if its a FW reset */ - if (sliport_err1 == SLIPORT_ERROR_FW_RESET1 && - sliport_err2 == SLIPORT_ERROR_FW_RESET2) { - dev_info(&adapter->pdev->dev, - "Firmware update in progress\n"); - return; - } else { - dev_err(&adapter->pdev->dev, - "Error detected in the card\n"); - } - } - - if (sliport_status & SLIPORT_STATUS_ERR_MASK) { - dev_err(&adapter->pdev->dev, - "ERR: sliport status 0x%x\n", sliport_status); - dev_err(&adapter->pdev->dev, - "ERR: sliport error1 0x%x\n", sliport_err1); - dev_err(&adapter->pdev->dev, - "ERR: sliport error2 0x%x\n", sliport_err2); - } - if (ue_lo) { - for (i = 0; ue_lo; ue_lo >>= 1, i++) { - if (ue_lo & 1) - dev_err(&adapter->pdev->dev, - "UE: %s bit set\n", ue_status_low_desc[i]); - } - } + /* On certain platforms BE hardware can indicate spurious UEs. + * Allow HW to stop working completely in case of a real UE. + * Hence not setting the hw_error for UE detection. + */ - if (ue_hi) { - for (i = 0; ue_hi; ue_hi >>= 1, i++) { - if (ue_hi & 1) - dev_err(&adapter->pdev->dev, - "UE: %s bit set\n", ue_status_hi_desc[i]); + if (ue_lo || ue_hi) { + error_detected = true; + dev_err(dev, + "Unrecoverable Error detected in the adapter"); + dev_err(dev, "Please reboot server to recover"); + if (skyhawk_chip(adapter)) + adapter->hw_error = true; + for (i = 0; ue_lo; ue_lo >>= 1, i++) { + if (ue_lo & 1) + dev_err(dev, "UE: %s bit set\n", + ue_status_low_desc[i]); + } + for (i = 0; ue_hi; ue_hi >>= 1, i++) { + if (ue_hi & 1) + dev_err(dev, "UE: %s bit set\n", + ue_status_hi_desc[i]); + } } } - + if (error_detected) + netif_carrier_off(netdev); } static void be_msix_disable(struct be_adapter *adapter) @@ -2505,7 +2557,7 @@ static void be_msix_disable(struct be_adapter *adapter) static int be_msix_enable(struct be_adapter *adapter) { - int i, status, num_vec; + int i, num_vec; struct device *dev = &adapter->pdev->dev; /* If RoCE is supported, program the max number of NIC vectors that @@ -2521,24 +2573,11 @@ static int be_msix_enable(struct be_adapter *adapter) for (i = 0; i < num_vec; i++) adapter->msix_entries[i].entry = i; - status = pci_enable_msix(adapter->pdev, adapter->msix_entries, num_vec); - if (status == 0) { - goto done; - } else if (status >= MIN_MSIX_VECTORS) { - num_vec = status; - status = pci_enable_msix(adapter->pdev, adapter->msix_entries, - num_vec); - if (!status) - goto done; - } - - dev_warn(dev, "MSIx enable failed\n"); + num_vec = pci_enable_msix_range(adapter->pdev, adapter->msix_entries, + MIN_MSIX_VECTORS, num_vec); + if (num_vec < 0) + goto fail; - /* INTx is not supported in VFs, so fail probe if enable_msix fails */ - if (!be_physfn(adapter)) - return status; - return 0; -done: if (be_roce_supported(adapter) && num_vec > MIN_MSIX_VECTORS) { adapter->num_msix_roce_vec = num_vec / 2; dev_info(dev, "enabled %d MSI-x vector(s) for RoCE\n", @@ -2550,6 +2589,14 @@ done: dev_info(dev, "enabled %d MSI-x vector(s) for NIC\n", adapter->num_msix_vec); return 0; + +fail: + dev_warn(dev, "MSIx enable failed\n"); + + /* INTx is not supported in VFs, so fail probe if enable_msix fails */ + if (!be_physfn(adapter)) + return num_vec; + return 0; } static inline int be_msix_vec_get(struct be_adapter *adapter, @@ -3013,11 +3060,11 @@ static int be_vf_setup_init(struct be_adapter *adapter) static int be_vf_setup(struct be_adapter *adapter) { + struct device *dev = &adapter->pdev->dev; struct be_vf_cfg *vf_cfg; - u16 def_vlan, lnk_speed; int status, old_vfs, vf; - struct device *dev = &adapter->pdev->dev; u32 privileges; + u16 lnk_speed; old_vfs = pci_num_vf(adapter->pdev); if (old_vfs) { @@ -3084,14 +3131,12 @@ static int be_vf_setup(struct be_adapter *adapter) if (!status) vf_cfg->tx_rate = lnk_speed; - status = be_cmd_get_hsw_config(adapter, &def_vlan, - vf + 1, vf_cfg->if_handle, NULL); - if (status) - goto err; - vf_cfg->def_vid = def_vlan; - - if (!old_vfs) + if (!old_vfs) { be_cmd_enable_vf(adapter, vf + 1); + be_cmd_set_logical_link_config(adapter, + IFLA_VF_LINK_STATE_AUTO, + vf+1); + } } if (!old_vfs) { @@ -3109,19 +3154,38 @@ err: return status; } +/* Converting function_mode bits on BE3 to SH mc_type enums */ + +static u8 be_convert_mc_type(u32 function_mode) +{ + if (function_mode & VNIC_MODE && function_mode & FLEX10_MODE) + return vNIC1; + else if (function_mode & FLEX10_MODE) + return FLEX10; + else if (function_mode & VNIC_MODE) + return vNIC2; + else if (function_mode & UMC_ENABLED) + return UMC; + else + return MC_NONE; +} + /* On BE2/BE3 FW does not suggest the supported limits */ static void BEx_get_resources(struct be_adapter *adapter, struct be_resources *res) { struct pci_dev *pdev = adapter->pdev; bool use_sriov = false; - int max_vfs; - - max_vfs = pci_sriov_get_totalvfs(pdev); - - if (BE3_chip(adapter) && sriov_want(adapter)) { - res->max_vfs = max_vfs > 0 ? min(MAX_VFS, max_vfs) : 0; - use_sriov = res->max_vfs; + int max_vfs = 0; + + if (be_physfn(adapter) && BE3_chip(adapter)) { + be_cmd_get_profile_config(adapter, res, 0); + /* Some old versions of BE3 FW don't report max_vfs value */ + if (res->max_vfs == 0) { + max_vfs = pci_sriov_get_totalvfs(pdev); + res->max_vfs = max_vfs > 0 ? min(MAX_VFS, max_vfs) : 0; + } + use_sriov = res->max_vfs && sriov_want(adapter); } if (be_physfn(adapter)) @@ -3129,17 +3193,32 @@ static void BEx_get_resources(struct be_adapter *adapter, else res->max_uc_mac = BE_VF_UC_PMAC_COUNT; - if (adapter->function_mode & FLEX10_MODE) - res->max_vlans = BE_NUM_VLANS_SUPPORTED/8; - else if (adapter->function_mode & UMC_ENABLED) - res->max_vlans = BE_UMC_NUM_VLANS_SUPPORTED; - else + adapter->mc_type = be_convert_mc_type(adapter->function_mode); + + if (be_is_mc(adapter)) { + /* Assuming that there are 4 channels per port, + * when multi-channel is enabled + */ + if (be_is_qnq_mode(adapter)) + res->max_vlans = BE_NUM_VLANS_SUPPORTED/8; + else + /* In a non-qnq multichannel mode, the pvid + * takes up one vlan entry + */ + res->max_vlans = (BE_NUM_VLANS_SUPPORTED / 4) - 1; + } else { res->max_vlans = BE_NUM_VLANS_SUPPORTED; + } + res->max_mcast_mac = BE_MAX_MC; - /* For BE3 1Gb ports, F/W does not properly support multiple TXQs */ - if (BE2_chip(adapter) || use_sriov || be_is_mc(adapter) || - !be_physfn(adapter) || (adapter->port_num > 1)) + /* 1) For BE3 1Gb ports, FW does not support multiple TXQs + * 2) Create multiple TX rings on a BE3-R multi-channel interface + * *only* if it is RSS-capable. + */ + if (BE2_chip(adapter) || use_sriov || (adapter->port_num > 1) || + !be_physfn(adapter) || (be_is_mc(adapter) && + !(adapter->function_caps & BE_FUNCTION_CAPS_RSS))) res->max_tx_qs = 1; else res->max_tx_qs = BE3_MAX_TX_QS; @@ -3151,7 +3230,7 @@ static void BEx_get_resources(struct be_adapter *adapter, res->max_rx_qs = res->max_rss_qs + 1; if (be_physfn(adapter)) - res->max_evt_qs = (max_vfs > 0) ? + res->max_evt_qs = (res->max_vfs > 0) ? BE3_SRIOV_MAX_EVT_QS : BE3_MAX_EVT_QS; else res->max_evt_qs = 1; @@ -3242,9 +3321,8 @@ static int be_get_config(struct be_adapter *adapter) if (status) return status; - /* primary mac needs 1 pmac entry */ - adapter->pmac_id = kcalloc(be_max_uc(adapter) + 1, sizeof(u32), - GFP_KERNEL); + adapter->pmac_id = kcalloc(be_max_uc(adapter), + sizeof(*adapter->pmac_id), GFP_KERNEL); if (!adapter->pmac_id) return -ENOMEM; @@ -3418,6 +3496,10 @@ static int be_setup(struct be_adapter *adapter) be_cmd_set_flow_control(adapter, adapter->tx_fc, adapter->rx_fc); + if (be_physfn(adapter)) + be_cmd_set_logical_link_config(adapter, + IFLA_VF_LINK_STATE_AUTO, 0); + if (sriov_want(adapter)) { if (be_max_vfs(adapter)) be_vf_setup(adapter); @@ -4057,6 +4139,7 @@ static const struct net_device_ops be_netdev_ops = { .ndo_set_vf_vlan = be_set_vf_vlan, .ndo_set_vf_tx_rate = be_set_vf_tx_rate, .ndo_get_vf_config = be_get_vf_config, + .ndo_set_vf_link_state = be_set_vf_link_state, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = be_netpoll, #endif @@ -4417,14 +4500,32 @@ static bool be_reset_required(struct be_adapter *adapter) static char *mc_name(struct be_adapter *adapter) { - if (adapter->function_mode & FLEX10_MODE) - return "FLEX10"; - else if (adapter->function_mode & VNIC_MODE) - return "vNIC"; - else if (adapter->function_mode & UMC_ENABLED) - return "UMC"; - else - return ""; + char *str = ""; /* default */ + + switch (adapter->mc_type) { + case UMC: + str = "UMC"; + break; + case FLEX10: + str = "FLEX10"; + break; + case vNIC1: + str = "vNIC-1"; + break; + case nPAR: + str = "nPAR"; + break; + case UFP: + str = "UFP"; + break; + case vNIC2: + str = "vNIC-2"; + break; + default: + str = ""; + } + + return str; } static inline char *func_name(struct be_adapter *adapter) diff --git a/drivers/net/ethernet/emulex/benet/be_roce.c b/drivers/net/ethernet/emulex/benet/be_roce.c index 9cd5415fe017..a5dae4a62bb3 100644 --- a/drivers/net/ethernet/emulex/benet/be_roce.c +++ b/drivers/net/ethernet/emulex/benet/be_roce.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2005 - 2013 Emulex + * Copyright (C) 2005 - 2014 Emulex * All rights reserved. * * This program is free software; you can redistribute it and/or diff --git a/drivers/net/ethernet/emulex/benet/be_roce.h b/drivers/net/ethernet/emulex/benet/be_roce.h index 2cd1129e19af..a3ef8f804b9e 100644 --- a/drivers/net/ethernet/emulex/benet/be_roce.h +++ b/drivers/net/ethernet/emulex/benet/be_roce.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2005 - 2013 Emulex + * Copyright (C) 2005 - 2014 Emulex * All rights reserved. * * This program is free software; you can redistribute it and/or diff --git a/drivers/net/ethernet/ethoc.c b/drivers/net/ethernet/ethoc.c index 4de8cfd149cf..55e0fa03dc90 100644 --- a/drivers/net/ethernet/ethoc.c +++ b/drivers/net/ethernet/ethoc.c @@ -13,6 +13,7 @@ #include <linux/dma-mapping.h> #include <linux/etherdevice.h> +#include <linux/clk.h> #include <linux/crc32.h> #include <linux/interrupt.h> #include <linux/io.h> @@ -51,6 +52,7 @@ MODULE_PARM_DESC(buffer_size, "DMA buffer allocation size"); #define ETH_HASH0 0x48 #define ETH_HASH1 0x4c #define ETH_TXCTRL 0x50 +#define ETH_END 0x54 /* mode register */ #define MODER_RXEN (1 << 0) /* receive enable */ @@ -179,6 +181,7 @@ MODULE_PARM_DESC(buffer_size, "DMA buffer allocation size"); * @membase: pointer to buffer memory region * @dma_alloc: dma allocated buffer size * @io_region_size: I/O memory region size + * @num_bd: number of buffer descriptors * @num_tx: number of send buffers * @cur_tx: last send buffer written * @dty_tx: last buffer actually sent @@ -199,6 +202,7 @@ struct ethoc { int dma_alloc; resource_size_t io_region_size; + unsigned int num_bd; unsigned int num_tx; unsigned int cur_tx; unsigned int dty_tx; @@ -216,6 +220,7 @@ struct ethoc { struct phy_device *phy; struct mii_bus *mdio; + struct clk *clk; s8 phy_id; }; @@ -688,6 +693,11 @@ static int ethoc_mdio_probe(struct net_device *dev) } priv->phy = phy; + phy->advertising &= ~(ADVERTISED_1000baseT_Full | + ADVERTISED_1000baseT_Half); + phy->supported &= ~(SUPPORTED_1000baseT_Full | + SUPPORTED_1000baseT_Half); + return 0; } @@ -890,6 +900,102 @@ out: return NETDEV_TX_OK; } +static int ethoc_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) +{ + struct ethoc *priv = netdev_priv(dev); + struct phy_device *phydev = priv->phy; + + if (!phydev) + return -EOPNOTSUPP; + + return phy_ethtool_gset(phydev, cmd); +} + +static int ethoc_set_settings(struct net_device *dev, struct ethtool_cmd *cmd) +{ + struct ethoc *priv = netdev_priv(dev); + struct phy_device *phydev = priv->phy; + + if (!phydev) + return -EOPNOTSUPP; + + return phy_ethtool_sset(phydev, cmd); +} + +static int ethoc_get_regs_len(struct net_device *netdev) +{ + return ETH_END; +} + +static void ethoc_get_regs(struct net_device *dev, struct ethtool_regs *regs, + void *p) +{ + struct ethoc *priv = netdev_priv(dev); + u32 *regs_buff = p; + unsigned i; + + regs->version = 0; + for (i = 0; i < ETH_END / sizeof(u32); ++i) + regs_buff[i] = ethoc_read(priv, i * sizeof(u32)); +} + +static void ethoc_get_ringparam(struct net_device *dev, + struct ethtool_ringparam *ring) +{ + struct ethoc *priv = netdev_priv(dev); + + ring->rx_max_pending = priv->num_bd - 1; + ring->rx_mini_max_pending = 0; + ring->rx_jumbo_max_pending = 0; + ring->tx_max_pending = priv->num_bd - 1; + + ring->rx_pending = priv->num_rx; + ring->rx_mini_pending = 0; + ring->rx_jumbo_pending = 0; + ring->tx_pending = priv->num_tx; +} + +static int ethoc_set_ringparam(struct net_device *dev, + struct ethtool_ringparam *ring) +{ + struct ethoc *priv = netdev_priv(dev); + + if (ring->tx_pending < 1 || ring->rx_pending < 1 || + ring->tx_pending + ring->rx_pending > priv->num_bd) + return -EINVAL; + if (ring->rx_mini_pending || ring->rx_jumbo_pending) + return -EINVAL; + + if (netif_running(dev)) { + netif_tx_disable(dev); + ethoc_disable_rx_and_tx(priv); + ethoc_disable_irq(priv, INT_MASK_TX | INT_MASK_RX); + synchronize_irq(dev->irq); + } + + priv->num_tx = rounddown_pow_of_two(ring->tx_pending); + priv->num_rx = ring->rx_pending; + ethoc_init_ring(priv, dev->mem_start); + + if (netif_running(dev)) { + ethoc_enable_irq(priv, INT_MASK_TX | INT_MASK_RX); + ethoc_enable_rx_and_tx(priv); + netif_wake_queue(dev); + } + return 0; +} + +const struct ethtool_ops ethoc_ethtool_ops = { + .get_settings = ethoc_get_settings, + .set_settings = ethoc_set_settings, + .get_regs_len = ethoc_get_regs_len, + .get_regs = ethoc_get_regs, + .get_link = ethtool_op_get_link, + .get_ringparam = ethoc_get_ringparam, + .set_ringparam = ethoc_set_ringparam, + .get_ts_info = ethtool_op_get_ts_info, +}; + static const struct net_device_ops ethoc_netdev_ops = { .ndo_open = ethoc_open, .ndo_stop = ethoc_stop, @@ -917,6 +1023,8 @@ static int ethoc_probe(struct platform_device *pdev) int num_bd; int ret = 0; bool random_mac = false; + struct ethoc_platform_data *pdata = dev_get_platdata(&pdev->dev); + u32 eth_clkfreq = pdata ? pdata->eth_clkfreq : 0; /* allocate networking device */ netdev = alloc_etherdev(sizeof(struct ethoc)); @@ -1016,6 +1124,7 @@ static int ethoc_probe(struct platform_device *pdev) ret = -ENODEV; goto error; } + priv->num_bd = num_bd; /* num_tx must be a power of two */ priv->num_tx = rounddown_pow_of_two(num_bd >> 1); priv->num_rx = num_bd - priv->num_tx; @@ -1030,8 +1139,7 @@ static int ethoc_probe(struct platform_device *pdev) } /* Allow the platform setup code to pass in a MAC address. */ - if (dev_get_platdata(&pdev->dev)) { - struct ethoc_platform_data *pdata = dev_get_platdata(&pdev->dev); + if (pdata) { memcpy(netdev->dev_addr, pdata->hwaddr, IFHWADDRLEN); priv->phy_id = pdata->phy_id; } else { @@ -1069,6 +1177,27 @@ static int ethoc_probe(struct platform_device *pdev) if (random_mac) netdev->addr_assign_type = NET_ADDR_RANDOM; + /* Allow the platform setup code to adjust MII management bus clock. */ + if (!eth_clkfreq) { + struct clk *clk = devm_clk_get(&pdev->dev, NULL); + + if (!IS_ERR(clk)) { + priv->clk = clk; + clk_prepare_enable(clk); + eth_clkfreq = clk_get_rate(clk); + } + } + if (eth_clkfreq) { + u32 clkdiv = MIIMODER_CLKDIV(eth_clkfreq / 2500000 + 1); + + if (!clkdiv) + clkdiv = 2; + dev_dbg(&pdev->dev, "setting MII clkdiv to %u\n", clkdiv); + ethoc_write(priv, MIIMODER, + (ethoc_read(priv, MIIMODER) & MIIMODER_NOPRE) | + clkdiv); + } + /* register MII bus */ priv->mdio = mdiobus_alloc(); if (!priv->mdio) { @@ -1111,6 +1240,7 @@ static int ethoc_probe(struct platform_device *pdev) netdev->netdev_ops = ðoc_netdev_ops; netdev->watchdog_timeo = ETHOC_TIMEOUT; netdev->features |= 0; + netdev->ethtool_ops = ðoc_ethtool_ops; /* setup NAPI */ netif_napi_add(netdev, &priv->napi, ethoc_poll, 64); @@ -1133,6 +1263,8 @@ free_mdio: kfree(priv->mdio->irq); mdiobus_free(priv->mdio); free: + if (priv->clk) + clk_disable_unprepare(priv->clk); free_netdev(netdev); out: return ret; @@ -1157,6 +1289,8 @@ static int ethoc_remove(struct platform_device *pdev) kfree(priv->mdio->irq); mdiobus_free(priv->mdio); } + if (priv->clk) + clk_disable_unprepare(priv->clk); unregister_netdev(netdev); free_netdev(netdev); } diff --git a/drivers/net/ethernet/freescale/Makefile b/drivers/net/ethernet/freescale/Makefile index 549ce13b92ac..71debd1c18c9 100644 --- a/drivers/net/ethernet/freescale/Makefile +++ b/drivers/net/ethernet/freescale/Makefile @@ -14,7 +14,6 @@ obj-$(CONFIG_FSL_XGMAC_MDIO) += xgmac_mdio.o obj-$(CONFIG_GIANFAR) += gianfar_driver.o obj-$(CONFIG_PTP_1588_CLOCK_GIANFAR) += gianfar_ptp.o gianfar_driver-objs := gianfar.o \ - gianfar_ethtool.o \ - gianfar_sysfs.o + gianfar_ethtool.o obj-$(CONFIG_UCC_GETH) += ucc_geth_driver.o ucc_geth_driver-objs := ucc_geth.o ucc_geth_ethtool.o diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index d4782b42401b..479a7cba45c0 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -389,12 +389,6 @@ fec_enet_start_xmit(struct sk_buff *skb, struct net_device *ndev) netdev_err(ndev, "Tx DMA memory map failed\n"); return NETDEV_TX_OK; } - /* Send it on its way. Tell FEC it's ready, interrupt when done, - * it's the last BD of the frame, and to put the CRC on the end. - */ - status |= (BD_ENET_TX_READY | BD_ENET_TX_INTR - | BD_ENET_TX_LAST | BD_ENET_TX_TC); - bdp->cbd_sc = status; if (fep->bufdesc_ex) { @@ -416,6 +410,13 @@ fec_enet_start_xmit(struct sk_buff *skb, struct net_device *ndev) } } + /* Send it on its way. Tell FEC it's ready, interrupt when done, + * it's the last BD of the frame, and to put the CRC on the end. + */ + status |= (BD_ENET_TX_READY | BD_ENET_TX_INTR + | BD_ENET_TX_LAST | BD_ENET_TX_TC); + bdp->cbd_sc = status; + bdp_pre = fec_enet_get_prevdesc(bdp, fep); if ((id_entry->driver_data & FEC_QUIRK_ERR006358) && !(bdp_pre->cbd_sc & BD_ENET_TX_READY)) { @@ -1778,8 +1779,6 @@ fec_enet_open(struct net_device *ndev) struct fec_enet_private *fep = netdev_priv(ndev); int ret; - napi_enable(&fep->napi); - /* I should reset the ring buffers here, but I don't yet know * a simple way to do that. */ @@ -1794,6 +1793,8 @@ fec_enet_open(struct net_device *ndev) fec_enet_free_buffers(ndev); return ret; } + + napi_enable(&fep->napi); phy_start(fep->phy_dev); netif_start_queue(ndev); fep->opened = 1; diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c index ad5a5aadc7e1..6e12f9365856 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -9,7 +9,7 @@ * Maintainer: Kumar Gala * Modifier: Sandeep Gopalpet <sandeep.kumar@freescale.com> * - * Copyright 2002-2009, 2011 Freescale Semiconductor, Inc. + * Copyright 2002-2009, 2011-2013 Freescale Semiconductor, Inc. * Copyright 2007 MontaVista Software, Inc. * * This program is free software; you can redistribute it and/or modify it @@ -121,7 +121,6 @@ static irqreturn_t gfar_error(int irq, void *dev_id); static irqreturn_t gfar_transmit(int irq, void *dev_id); static irqreturn_t gfar_interrupt(int irq, void *dev_id); static void adjust_link(struct net_device *dev); -static void init_registers(struct net_device *dev); static int init_phy(struct net_device *dev); static int gfar_probe(struct platform_device *ofdev); static int gfar_remove(struct platform_device *ofdev); @@ -129,8 +128,10 @@ static void free_skb_resources(struct gfar_private *priv); static void gfar_set_multi(struct net_device *dev); static void gfar_set_hash_for_addr(struct net_device *dev, u8 *addr); static void gfar_configure_serdes(struct net_device *dev); -static int gfar_poll(struct napi_struct *napi, int budget); -static int gfar_poll_sq(struct napi_struct *napi, int budget); +static int gfar_poll_rx(struct napi_struct *napi, int budget); +static int gfar_poll_tx(struct napi_struct *napi, int budget); +static int gfar_poll_rx_sq(struct napi_struct *napi, int budget); +static int gfar_poll_tx_sq(struct napi_struct *napi, int budget); #ifdef CONFIG_NET_POLL_CONTROLLER static void gfar_netpoll(struct net_device *dev); #endif @@ -138,9 +139,7 @@ int gfar_clean_rx_ring(struct gfar_priv_rx_q *rx_queue, int rx_work_limit); static void gfar_clean_tx_ring(struct gfar_priv_tx_q *tx_queue); static void gfar_process_frame(struct net_device *dev, struct sk_buff *skb, int amount_pull, struct napi_struct *napi); -void gfar_halt(struct net_device *dev); -static void gfar_halt_nodisable(struct net_device *dev); -void gfar_start(struct net_device *dev); +static void gfar_halt_nodisable(struct gfar_private *priv); static void gfar_clear_exact_match(struct net_device *dev); static void gfar_set_mac_for_addr(struct net_device *dev, int num, const u8 *addr); @@ -332,72 +331,76 @@ static void gfar_init_tx_rx_base(struct gfar_private *priv) } } -static void gfar_init_mac(struct net_device *ndev) +static void gfar_rx_buff_size_config(struct gfar_private *priv) { - struct gfar_private *priv = netdev_priv(ndev); - struct gfar __iomem *regs = priv->gfargrp[0].regs; - u32 rctrl = 0; - u32 tctrl = 0; - u32 attrs = 0; - - /* write the tx/rx base registers */ - gfar_init_tx_rx_base(priv); - - /* Configure the coalescing support */ - gfar_configure_coalescing_all(priv); + int frame_size = priv->ndev->mtu + ETH_HLEN; /* set this when rx hw offload (TOE) functions are being used */ priv->uses_rxfcb = 0; + if (priv->ndev->features & (NETIF_F_RXCSUM | NETIF_F_HW_VLAN_CTAG_RX)) + priv->uses_rxfcb = 1; + + if (priv->hwts_rx_en) + priv->uses_rxfcb = 1; + + if (priv->uses_rxfcb) + frame_size += GMAC_FCB_LEN; + + frame_size += priv->padding; + + frame_size = (frame_size & ~(INCREMENTAL_BUFFER_SIZE - 1)) + + INCREMENTAL_BUFFER_SIZE; + + priv->rx_buffer_size = frame_size; +} + +static void gfar_mac_rx_config(struct gfar_private *priv) +{ + struct gfar __iomem *regs = priv->gfargrp[0].regs; + u32 rctrl = 0; + if (priv->rx_filer_enable) { rctrl |= RCTRL_FILREN; /* Program the RIR0 reg with the required distribution */ - gfar_write(®s->rir0, DEFAULT_RIR0); + if (priv->poll_mode == GFAR_SQ_POLLING) + gfar_write(®s->rir0, DEFAULT_2RXQ_RIR0); + else /* GFAR_MQ_POLLING */ + gfar_write(®s->rir0, DEFAULT_8RXQ_RIR0); } /* Restore PROMISC mode */ - if (ndev->flags & IFF_PROMISC) + if (priv->ndev->flags & IFF_PROMISC) rctrl |= RCTRL_PROM; - if (ndev->features & NETIF_F_RXCSUM) { + if (priv->ndev->features & NETIF_F_RXCSUM) rctrl |= RCTRL_CHECKSUMMING; - priv->uses_rxfcb = 1; - } - if (priv->extended_hash) { - rctrl |= RCTRL_EXTHASH; - - gfar_clear_exact_match(ndev); - rctrl |= RCTRL_EMEN; - } + if (priv->extended_hash) + rctrl |= RCTRL_EXTHASH | RCTRL_EMEN; if (priv->padding) { rctrl &= ~RCTRL_PAL_MASK; rctrl |= RCTRL_PADDING(priv->padding); } - /* Insert receive time stamps into padding alignment bytes */ - if (priv->device_flags & FSL_GIANFAR_DEV_HAS_TIMER) { - rctrl &= ~RCTRL_PAL_MASK; - rctrl |= RCTRL_PADDING(8); - priv->padding = 8; - } - /* Enable HW time stamping if requested from user space */ - if (priv->hwts_rx_en) { + if (priv->hwts_rx_en) rctrl |= RCTRL_PRSDEP_INIT | RCTRL_TS_ENABLE; - priv->uses_rxfcb = 1; - } - if (ndev->features & NETIF_F_HW_VLAN_CTAG_RX) { + if (priv->ndev->features & NETIF_F_HW_VLAN_CTAG_RX) rctrl |= RCTRL_VLEX | RCTRL_PRSDEP_INIT; - priv->uses_rxfcb = 1; - } /* Init rctrl based on our settings */ gfar_write(®s->rctrl, rctrl); +} + +static void gfar_mac_tx_config(struct gfar_private *priv) +{ + struct gfar __iomem *regs = priv->gfargrp[0].regs; + u32 tctrl = 0; - if (ndev->features & NETIF_F_IP_CSUM) + if (priv->ndev->features & NETIF_F_IP_CSUM) tctrl |= TCTRL_INIT_CSUM; if (priv->prio_sched_en) @@ -408,30 +411,51 @@ static void gfar_init_mac(struct net_device *ndev) gfar_write(®s->tr47wt, DEFAULT_WRRS_WEIGHT); } - gfar_write(®s->tctrl, tctrl); + if (priv->ndev->features & NETIF_F_HW_VLAN_CTAG_TX) + tctrl |= TCTRL_VLINS; - /* Set the extraction length and index */ - attrs = ATTRELI_EL(priv->rx_stash_size) | - ATTRELI_EI(priv->rx_stash_index); + gfar_write(®s->tctrl, tctrl); +} - gfar_write(®s->attreli, attrs); +static void gfar_configure_coalescing(struct gfar_private *priv, + unsigned long tx_mask, unsigned long rx_mask) +{ + struct gfar __iomem *regs = priv->gfargrp[0].regs; + u32 __iomem *baddr; - /* Start with defaults, and add stashing or locking - * depending on the approprate variables - */ - attrs = ATTR_INIT_SETTINGS; + if (priv->mode == MQ_MG_MODE) { + int i = 0; - if (priv->bd_stash_en) - attrs |= ATTR_BDSTASH; + baddr = ®s->txic0; + for_each_set_bit(i, &tx_mask, priv->num_tx_queues) { + gfar_write(baddr + i, 0); + if (likely(priv->tx_queue[i]->txcoalescing)) + gfar_write(baddr + i, priv->tx_queue[i]->txic); + } - if (priv->rx_stash_size != 0) - attrs |= ATTR_BUFSTASH; + baddr = ®s->rxic0; + for_each_set_bit(i, &rx_mask, priv->num_rx_queues) { + gfar_write(baddr + i, 0); + if (likely(priv->rx_queue[i]->rxcoalescing)) + gfar_write(baddr + i, priv->rx_queue[i]->rxic); + } + } else { + /* Backward compatible case -- even if we enable + * multiple queues, there's only single reg to program + */ + gfar_write(®s->txic, 0); + if (likely(priv->tx_queue[0]->txcoalescing)) + gfar_write(®s->txic, priv->tx_queue[0]->txic); - gfar_write(®s->attr, attrs); + gfar_write(®s->rxic, 0); + if (unlikely(priv->rx_queue[0]->rxcoalescing)) + gfar_write(®s->rxic, priv->rx_queue[0]->rxic); + } +} - gfar_write(®s->fifo_tx_thr, priv->fifo_threshold); - gfar_write(®s->fifo_tx_starve, priv->fifo_starve); - gfar_write(®s->fifo_tx_starve_shutoff, priv->fifo_starve_off); +void gfar_configure_coalescing_all(struct gfar_private *priv) +{ + gfar_configure_coalescing(priv, 0xFF, 0xFF); } static struct net_device_stats *gfar_get_stats(struct net_device *dev) @@ -479,12 +503,27 @@ static const struct net_device_ops gfar_netdev_ops = { #endif }; -void lock_rx_qs(struct gfar_private *priv) +static void gfar_ints_disable(struct gfar_private *priv) { int i; + for (i = 0; i < priv->num_grps; i++) { + struct gfar __iomem *regs = priv->gfargrp[i].regs; + /* Clear IEVENT */ + gfar_write(®s->ievent, IEVENT_INIT_CLEAR); - for (i = 0; i < priv->num_rx_queues; i++) - spin_lock(&priv->rx_queue[i]->rxlock); + /* Initialize IMASK */ + gfar_write(®s->imask, IMASK_INIT_CLEAR); + } +} + +static void gfar_ints_enable(struct gfar_private *priv) +{ + int i; + for (i = 0; i < priv->num_grps; i++) { + struct gfar __iomem *regs = priv->gfargrp[i].regs; + /* Unmask the interrupts we look for */ + gfar_write(®s->imask, IMASK_DEFAULT); + } } void lock_tx_qs(struct gfar_private *priv) @@ -495,23 +534,50 @@ void lock_tx_qs(struct gfar_private *priv) spin_lock(&priv->tx_queue[i]->txlock); } -void unlock_rx_qs(struct gfar_private *priv) +void unlock_tx_qs(struct gfar_private *priv) { int i; - for (i = 0; i < priv->num_rx_queues; i++) - spin_unlock(&priv->rx_queue[i]->rxlock); + for (i = 0; i < priv->num_tx_queues; i++) + spin_unlock(&priv->tx_queue[i]->txlock); } -void unlock_tx_qs(struct gfar_private *priv) +static int gfar_alloc_tx_queues(struct gfar_private *priv) { int i; - for (i = 0; i < priv->num_tx_queues; i++) - spin_unlock(&priv->tx_queue[i]->txlock); + for (i = 0; i < priv->num_tx_queues; i++) { + priv->tx_queue[i] = kzalloc(sizeof(struct gfar_priv_tx_q), + GFP_KERNEL); + if (!priv->tx_queue[i]) + return -ENOMEM; + + priv->tx_queue[i]->tx_skbuff = NULL; + priv->tx_queue[i]->qindex = i; + priv->tx_queue[i]->dev = priv->ndev; + spin_lock_init(&(priv->tx_queue[i]->txlock)); + } + return 0; } -static void free_tx_pointers(struct gfar_private *priv) +static int gfar_alloc_rx_queues(struct gfar_private *priv) +{ + int i; + + for (i = 0; i < priv->num_rx_queues; i++) { + priv->rx_queue[i] = kzalloc(sizeof(struct gfar_priv_rx_q), + GFP_KERNEL); + if (!priv->rx_queue[i]) + return -ENOMEM; + + priv->rx_queue[i]->rx_skbuff = NULL; + priv->rx_queue[i]->qindex = i; + priv->rx_queue[i]->dev = priv->ndev; + } + return 0; +} + +static void gfar_free_tx_queues(struct gfar_private *priv) { int i; @@ -519,7 +585,7 @@ static void free_tx_pointers(struct gfar_private *priv) kfree(priv->tx_queue[i]); } -static void free_rx_pointers(struct gfar_private *priv) +static void gfar_free_rx_queues(struct gfar_private *priv) { int i; @@ -553,23 +619,26 @@ static void disable_napi(struct gfar_private *priv) { int i; - for (i = 0; i < priv->num_grps; i++) - napi_disable(&priv->gfargrp[i].napi); + for (i = 0; i < priv->num_grps; i++) { + napi_disable(&priv->gfargrp[i].napi_rx); + napi_disable(&priv->gfargrp[i].napi_tx); + } } static void enable_napi(struct gfar_private *priv) { int i; - for (i = 0; i < priv->num_grps; i++) - napi_enable(&priv->gfargrp[i].napi); + for (i = 0; i < priv->num_grps; i++) { + napi_enable(&priv->gfargrp[i].napi_rx); + napi_enable(&priv->gfargrp[i].napi_tx); + } } static int gfar_parse_group(struct device_node *np, struct gfar_private *priv, const char *model) { struct gfar_priv_grp *grp = &priv->gfargrp[priv->num_grps]; - u32 *queue_mask; int i; for (i = 0; i < GFAR_NUM_IRQS; i++) { @@ -598,16 +667,52 @@ static int gfar_parse_group(struct device_node *np, grp->priv = priv; spin_lock_init(&grp->grplock); if (priv->mode == MQ_MG_MODE) { - queue_mask = (u32 *)of_get_property(np, "fsl,rx-bit-map", NULL); - grp->rx_bit_map = queue_mask ? - *queue_mask : (DEFAULT_MAPPING >> priv->num_grps); - queue_mask = (u32 *)of_get_property(np, "fsl,tx-bit-map", NULL); - grp->tx_bit_map = queue_mask ? - *queue_mask : (DEFAULT_MAPPING >> priv->num_grps); + 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); + + 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; grp->tx_bit_map = 0xFF; } + + /* bit_map's MSB is q0 (from q0 to q7) but, for_each_set_bit parses + * right to left, so we need to revert the 8 bits to get the q index + */ + grp->rx_bit_map = bitrev8(grp->rx_bit_map); + grp->tx_bit_map = bitrev8(grp->tx_bit_map); + + /* Calculate RSTAT, TSTAT, RQUEUE and TQUEUE values, + * also assign queues to groups + */ + for_each_set_bit(i, &grp->rx_bit_map, priv->num_rx_queues) { + if (!grp->rx_queue) + grp->rx_queue = priv->rx_queue[i]; + grp->num_rx_queues++; + grp->rstat |= (RSTAT_CLEAR_RHALT >> i); + priv->rqueue |= ((RQUEUE_EN0 | RQUEUE_EX0) >> i); + priv->rx_queue[i]->grp = grp; + } + + for_each_set_bit(i, &grp->tx_bit_map, priv->num_tx_queues) { + if (!grp->tx_queue) + grp->tx_queue = priv->tx_queue[i]; + grp->num_tx_queues++; + grp->tstat |= (TSTAT_CLEAR_THALT >> i); + priv->tqueue |= (TQUEUE_EN0 >> i); + priv->tx_queue[i]->grp = grp; + } + priv->num_grps++; return 0; @@ -628,13 +733,35 @@ static int gfar_of_init(struct platform_device *ofdev, struct net_device **pdev) const u32 *stash_idx; unsigned int num_tx_qs, num_rx_qs; u32 *tx_queues, *rx_queues; + unsigned short mode, poll_mode; if (!np || !of_device_is_available(np)) return -ENODEV; - /* parse the num of tx and rx queues */ + if (of_device_is_compatible(np, "fsl,etsec2")) { + mode = MQ_MG_MODE; + poll_mode = GFAR_SQ_POLLING; + } else { + mode = SQ_SG_MODE; + 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); - num_tx_qs = tx_queues ? *tx_queues : 1; + 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; + } else { /* MQ_MG_MODE */ + if (poll_mode == GFAR_SQ_POLLING) { + num_tx_qs = 2; /* one txq per int group */ + num_rx_qs = 2; /* 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; + } + } if (num_tx_qs > MAX_TX_QS) { pr_err("num_tx_qs(=%d) greater than MAX_TX_QS(=%d)\n", @@ -643,9 +770,6 @@ static int gfar_of_init(struct platform_device *ofdev, struct net_device **pdev) return -EINVAL; } - rx_queues = (u32 *)of_get_property(np, "fsl,num_rx_queues", NULL); - num_rx_qs = rx_queues ? *rx_queues : 1; - if (num_rx_qs > MAX_RX_QS) { pr_err("num_rx_qs(=%d) greater than MAX_RX_QS(=%d)\n", num_rx_qs, MAX_RX_QS); @@ -661,10 +785,20 @@ static int gfar_of_init(struct platform_device *ofdev, struct net_device **pdev) priv = netdev_priv(dev); priv->ndev = dev; + priv->mode = mode; + priv->poll_mode = poll_mode; + priv->num_tx_queues = num_tx_qs; netif_set_real_num_rx_queues(dev, num_rx_qs); priv->num_rx_queues = num_rx_qs; - priv->num_grps = 0x0; + + err = gfar_alloc_tx_queues(priv); + if (err) + goto tx_alloc_failed; + + err = gfar_alloc_rx_queues(priv); + if (err) + goto rx_alloc_failed; /* Init Rx queue filer rule set linked list */ INIT_LIST_HEAD(&priv->rx_list.list); @@ -677,52 +811,18 @@ static int gfar_of_init(struct platform_device *ofdev, struct net_device **pdev) priv->gfargrp[i].regs = NULL; /* Parse and initialize group specific information */ - if (of_device_is_compatible(np, "fsl,etsec2")) { - priv->mode = MQ_MG_MODE; + if (priv->mode == MQ_MG_MODE) { for_each_child_of_node(np, child) { err = gfar_parse_group(child, priv, model); if (err) goto err_grp_init; } - } else { - priv->mode = SQ_SG_MODE; + } else { /* SQ_SG_MODE */ err = gfar_parse_group(np, priv, model); if (err) goto err_grp_init; } - for (i = 0; i < priv->num_tx_queues; i++) - priv->tx_queue[i] = NULL; - for (i = 0; i < priv->num_rx_queues; i++) - priv->rx_queue[i] = NULL; - - for (i = 0; i < priv->num_tx_queues; i++) { - priv->tx_queue[i] = kzalloc(sizeof(struct gfar_priv_tx_q), - GFP_KERNEL); - if (!priv->tx_queue[i]) { - err = -ENOMEM; - goto tx_alloc_failed; - } - priv->tx_queue[i]->tx_skbuff = NULL; - priv->tx_queue[i]->qindex = i; - priv->tx_queue[i]->dev = dev; - spin_lock_init(&(priv->tx_queue[i]->txlock)); - } - - for (i = 0; i < priv->num_rx_queues; i++) { - priv->rx_queue[i] = kzalloc(sizeof(struct gfar_priv_rx_q), - GFP_KERNEL); - if (!priv->rx_queue[i]) { - err = -ENOMEM; - goto rx_alloc_failed; - } - priv->rx_queue[i]->rx_skbuff = NULL; - priv->rx_queue[i]->qindex = i; - priv->rx_queue[i]->dev = dev; - spin_lock_init(&(priv->rx_queue[i]->rxlock)); - } - - stash = of_get_property(np, "bd-stash", NULL); if (stash) { @@ -749,17 +849,16 @@ static int gfar_of_init(struct platform_device *ofdev, struct net_device **pdev) memcpy(dev->dev_addr, mac_addr, ETH_ALEN); if (model && !strcasecmp(model, "TSEC")) - priv->device_flags = FSL_GIANFAR_DEV_HAS_GIGABIT | + priv->device_flags |= FSL_GIANFAR_DEV_HAS_GIGABIT | FSL_GIANFAR_DEV_HAS_COALESCE | FSL_GIANFAR_DEV_HAS_RMON | FSL_GIANFAR_DEV_HAS_MULTI_INTR; if (model && !strcasecmp(model, "eTSEC")) - priv->device_flags = FSL_GIANFAR_DEV_HAS_GIGABIT | + priv->device_flags |= FSL_GIANFAR_DEV_HAS_GIGABIT | FSL_GIANFAR_DEV_HAS_COALESCE | FSL_GIANFAR_DEV_HAS_RMON | FSL_GIANFAR_DEV_HAS_MULTI_INTR | - FSL_GIANFAR_DEV_HAS_PADDING | FSL_GIANFAR_DEV_HAS_CSUM | FSL_GIANFAR_DEV_HAS_VLAN | FSL_GIANFAR_DEV_HAS_MAGIC_PACKET | @@ -784,12 +883,12 @@ static int gfar_of_init(struct platform_device *ofdev, struct net_device **pdev) return 0; -rx_alloc_failed: - free_rx_pointers(priv); -tx_alloc_failed: - free_tx_pointers(priv); err_grp_init: unmap_group_regs(priv); +rx_alloc_failed: + gfar_free_rx_queues(priv); +tx_alloc_failed: + gfar_free_tx_queues(priv); free_gfar_dev(priv); return err; } @@ -822,18 +921,16 @@ static int gfar_hwtstamp_set(struct net_device *netdev, struct ifreq *ifr) switch (config.rx_filter) { case HWTSTAMP_FILTER_NONE: if (priv->hwts_rx_en) { - stop_gfar(netdev); priv->hwts_rx_en = 0; - startup_gfar(netdev); + reset_gfar(netdev); } break; default: if (!(priv->device_flags & FSL_GIANFAR_DEV_HAS_TIMER)) return -ERANGE; if (!priv->hwts_rx_en) { - stop_gfar(netdev); priv->hwts_rx_en = 1; - startup_gfar(netdev); + reset_gfar(netdev); } config.rx_filter = HWTSTAMP_FILTER_ALL; break; @@ -875,19 +972,6 @@ static int gfar_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) return phy_mii_ioctl(priv->phydev, rq, cmd); } -static unsigned int reverse_bitmap(unsigned int bit_map, unsigned int max_qs) -{ - unsigned int new_bit_map = 0x0; - int mask = 0x1 << (max_qs - 1), i; - - for (i = 0; i < max_qs; i++) { - if (bit_map & mask) - new_bit_map = new_bit_map + (1 << i); - mask = mask >> 0x1; - } - return new_bit_map; -} - static u32 cluster_entry_per_class(struct gfar_private *priv, u32 rqfar, u32 class) { @@ -1005,99 +1089,140 @@ static void gfar_detect_errata(struct gfar_private *priv) priv->errata); } -/* Set up the ethernet device structure, private data, - * and anything else we need before we start - */ -static int gfar_probe(struct platform_device *ofdev) +void gfar_mac_reset(struct gfar_private *priv) { + struct gfar __iomem *regs = priv->gfargrp[0].regs; u32 tempval; - struct net_device *dev = NULL; - struct gfar_private *priv = NULL; - struct gfar __iomem *regs = NULL; - int err = 0, i, grp_idx = 0; - u32 rstat = 0, tstat = 0, rqueue = 0, tqueue = 0; - u32 isrg = 0; - u32 __iomem *baddr; - - err = gfar_of_init(ofdev, &dev); - - if (err) - return err; - - priv = netdev_priv(dev); - priv->ndev = dev; - priv->ofdev = ofdev; - priv->dev = &ofdev->dev; - SET_NETDEV_DEV(dev, &ofdev->dev); - - spin_lock_init(&priv->bflock); - INIT_WORK(&priv->reset_task, gfar_reset_task); - - platform_set_drvdata(ofdev, priv); - regs = priv->gfargrp[0].regs; - - gfar_detect_errata(priv); - - /* Stop the DMA engine now, in case it was running before - * (The firmware could have used it, and left it running). - */ - gfar_halt(dev); /* Reset MAC layer */ gfar_write(®s->maccfg1, MACCFG1_SOFT_RESET); /* We need to delay at least 3 TX clocks */ - udelay(2); + udelay(3); - tempval = 0; - if (!priv->pause_aneg_en && priv->tx_pause_en) - tempval |= MACCFG1_TX_FLOW; - if (!priv->pause_aneg_en && priv->rx_pause_en) - tempval |= MACCFG1_RX_FLOW; /* the soft reset bit is not self-resetting, so we need to * clear it before resuming normal operation */ - gfar_write(®s->maccfg1, tempval); + gfar_write(®s->maccfg1, 0); + + udelay(3); + + /* Compute rx_buff_size based on config flags */ + gfar_rx_buff_size_config(priv); + + /* Initialize the max receive frame/buffer lengths */ + gfar_write(®s->maxfrm, priv->rx_buffer_size); + gfar_write(®s->mrblr, priv->rx_buffer_size); + + /* Initialize the Minimum Frame Length Register */ + gfar_write(®s->minflr, MINFLR_INIT_SETTINGS); /* Initialize MACCFG2. */ tempval = MACCFG2_INIT_SETTINGS; - if (gfar_has_errata(priv, GFAR_ERRATA_74)) + + /* If the mtu is larger than the max size for standard + * ethernet frames (ie, a jumbo frame), then set maccfg2 + * to allow huge frames, and to check the length + */ + if (priv->rx_buffer_size > DEFAULT_RX_BUFFER_SIZE || + gfar_has_errata(priv, GFAR_ERRATA_74)) tempval |= MACCFG2_HUGEFRAME | MACCFG2_LENGTHCHECK; + gfar_write(®s->maccfg2, tempval); + /* Clear mac addr hash registers */ + gfar_write(®s->igaddr0, 0); + gfar_write(®s->igaddr1, 0); + gfar_write(®s->igaddr2, 0); + gfar_write(®s->igaddr3, 0); + gfar_write(®s->igaddr4, 0); + gfar_write(®s->igaddr5, 0); + gfar_write(®s->igaddr6, 0); + gfar_write(®s->igaddr7, 0); + + gfar_write(®s->gaddr0, 0); + gfar_write(®s->gaddr1, 0); + gfar_write(®s->gaddr2, 0); + gfar_write(®s->gaddr3, 0); + gfar_write(®s->gaddr4, 0); + gfar_write(®s->gaddr5, 0); + gfar_write(®s->gaddr6, 0); + gfar_write(®s->gaddr7, 0); + + if (priv->extended_hash) + gfar_clear_exact_match(priv->ndev); + + gfar_mac_rx_config(priv); + + gfar_mac_tx_config(priv); + + gfar_set_mac_address(priv->ndev); + + gfar_set_multi(priv->ndev); + + /* clear ievent and imask before configuring coalescing */ + gfar_ints_disable(priv); + + /* Configure the coalescing support */ + gfar_configure_coalescing_all(priv); +} + +static void gfar_hw_init(struct gfar_private *priv) +{ + struct gfar __iomem *regs = priv->gfargrp[0].regs; + u32 attrs; + + /* Stop the DMA engine now, in case it was running before + * (The firmware could have used it, and left it running). + */ + gfar_halt(priv); + + gfar_mac_reset(priv); + + /* Zero out the rmon mib registers if it has them */ + if (priv->device_flags & FSL_GIANFAR_DEV_HAS_RMON) { + memset_io(&(regs->rmon), 0, sizeof(struct rmon_mib)); + + /* Mask off the CAM interrupts */ + gfar_write(®s->rmon.cam1, 0xffffffff); + gfar_write(®s->rmon.cam2, 0xffffffff); + } + /* Initialize ECNTRL */ gfar_write(®s->ecntrl, ECNTRL_INIT_SETTINGS); - /* Set the dev->base_addr to the gfar reg region */ - dev->base_addr = (unsigned long) regs; + /* Set the extraction length and index */ + attrs = ATTRELI_EL(priv->rx_stash_size) | + ATTRELI_EI(priv->rx_stash_index); - /* Fill in the dev structure */ - dev->watchdog_timeo = TX_TIMEOUT; - dev->mtu = 1500; - dev->netdev_ops = &gfar_netdev_ops; - dev->ethtool_ops = &gfar_ethtool_ops; + gfar_write(®s->attreli, attrs); - /* Register for napi ...We are registering NAPI for each grp */ - if (priv->mode == SQ_SG_MODE) - netif_napi_add(dev, &priv->gfargrp[0].napi, gfar_poll_sq, - GFAR_DEV_WEIGHT); - else - for (i = 0; i < priv->num_grps; i++) - netif_napi_add(dev, &priv->gfargrp[i].napi, gfar_poll, - GFAR_DEV_WEIGHT); + /* Start with defaults, and add stashing + * depending on driver parameters + */ + attrs = ATTR_INIT_SETTINGS; - if (priv->device_flags & FSL_GIANFAR_DEV_HAS_CSUM) { - dev->hw_features = NETIF_F_IP_CSUM | NETIF_F_SG | - NETIF_F_RXCSUM; - dev->features |= NETIF_F_IP_CSUM | NETIF_F_SG | - NETIF_F_RXCSUM | NETIF_F_HIGHDMA; - } + if (priv->bd_stash_en) + attrs |= ATTR_BDSTASH; - if (priv->device_flags & FSL_GIANFAR_DEV_HAS_VLAN) { - dev->hw_features |= NETIF_F_HW_VLAN_CTAG_TX | - NETIF_F_HW_VLAN_CTAG_RX; - dev->features |= NETIF_F_HW_VLAN_CTAG_RX; - } + if (priv->rx_stash_size != 0) + attrs |= ATTR_BUFSTASH; + + gfar_write(®s->attr, attrs); + + /* FIFO configs */ + gfar_write(®s->fifo_tx_thr, DEFAULT_FIFO_TX_THR); + gfar_write(®s->fifo_tx_starve, DEFAULT_FIFO_TX_STARVE); + gfar_write(®s->fifo_tx_starve_shutoff, DEFAULT_FIFO_TX_STARVE_OFF); + + /* Program the interrupt steering regs, only for MG devices */ + if (priv->num_grps > 1) + gfar_write_isrg(priv); +} + +static void __init gfar_init_addr_hash_table(struct gfar_private *priv) +{ + struct gfar __iomem *regs = priv->gfargrp[0].regs; if (priv->device_flags & FSL_GIANFAR_DEV_HAS_EXTENDED_HASH) { priv->extended_hash = 1; @@ -1133,68 +1258,81 @@ static int gfar_probe(struct platform_device *ofdev) priv->hash_regs[6] = ®s->gaddr6; priv->hash_regs[7] = ®s->gaddr7; } +} - if (priv->device_flags & FSL_GIANFAR_DEV_HAS_PADDING) - priv->padding = DEFAULT_PADDING; - else - priv->padding = 0; +/* Set up the ethernet device structure, private data, + * and anything else we need before we start + */ +static int gfar_probe(struct platform_device *ofdev) +{ + struct net_device *dev = NULL; + struct gfar_private *priv = NULL; + int err = 0, i; - if (dev->features & NETIF_F_IP_CSUM || - priv->device_flags & FSL_GIANFAR_DEV_HAS_TIMER) - dev->needed_headroom = GMAC_FCB_LEN; + err = gfar_of_init(ofdev, &dev); - /* Program the isrg regs only if number of grps > 1 */ - if (priv->num_grps > 1) { - baddr = ®s->isrg0; - for (i = 0; i < priv->num_grps; i++) { - isrg |= (priv->gfargrp[i].rx_bit_map << ISRG_SHIFT_RX); - isrg |= (priv->gfargrp[i].tx_bit_map << ISRG_SHIFT_TX); - gfar_write(baddr, isrg); - baddr++; - isrg = 0x0; + if (err) + return err; + + priv = netdev_priv(dev); + priv->ndev = dev; + priv->ofdev = ofdev; + priv->dev = &ofdev->dev; + SET_NETDEV_DEV(dev, &ofdev->dev); + + spin_lock_init(&priv->bflock); + INIT_WORK(&priv->reset_task, gfar_reset_task); + + platform_set_drvdata(ofdev, priv); + + gfar_detect_errata(priv); + + /* Set the dev->base_addr to the gfar reg region */ + dev->base_addr = (unsigned long) priv->gfargrp[0].regs; + + /* Fill in the dev structure */ + dev->watchdog_timeo = TX_TIMEOUT; + dev->mtu = 1500; + dev->netdev_ops = &gfar_netdev_ops; + dev->ethtool_ops = &gfar_ethtool_ops; + + /* Register for napi ...We are registering NAPI for each grp */ + for (i = 0; i < priv->num_grps; i++) { + if (priv->poll_mode == GFAR_SQ_POLLING) { + netif_napi_add(dev, &priv->gfargrp[i].napi_rx, + gfar_poll_rx_sq, GFAR_DEV_WEIGHT); + netif_napi_add(dev, &priv->gfargrp[i].napi_tx, + gfar_poll_tx_sq, 2); + } else { + netif_napi_add(dev, &priv->gfargrp[i].napi_rx, + gfar_poll_rx, GFAR_DEV_WEIGHT); + netif_napi_add(dev, &priv->gfargrp[i].napi_tx, + gfar_poll_tx, 2); } } - /* Need to reverse the bit maps as bit_map's MSB is q0 - * but, for_each_set_bit parses from right to left, which - * basically reverses the queue numbers - */ - for (i = 0; i< priv->num_grps; i++) { - priv->gfargrp[i].tx_bit_map = - reverse_bitmap(priv->gfargrp[i].tx_bit_map, MAX_TX_QS); - priv->gfargrp[i].rx_bit_map = - reverse_bitmap(priv->gfargrp[i].rx_bit_map, MAX_RX_QS); + if (priv->device_flags & FSL_GIANFAR_DEV_HAS_CSUM) { + dev->hw_features = NETIF_F_IP_CSUM | NETIF_F_SG | + NETIF_F_RXCSUM; + dev->features |= NETIF_F_IP_CSUM | NETIF_F_SG | + NETIF_F_RXCSUM | NETIF_F_HIGHDMA; } - /* Calculate RSTAT, TSTAT, RQUEUE and TQUEUE values, - * also assign queues to groups - */ - for (grp_idx = 0; grp_idx < priv->num_grps; grp_idx++) { - priv->gfargrp[grp_idx].num_rx_queues = 0x0; - - for_each_set_bit(i, &priv->gfargrp[grp_idx].rx_bit_map, - priv->num_rx_queues) { - priv->gfargrp[grp_idx].num_rx_queues++; - priv->rx_queue[i]->grp = &priv->gfargrp[grp_idx]; - rstat = rstat | (RSTAT_CLEAR_RHALT >> i); - rqueue = rqueue | ((RQUEUE_EN0 | RQUEUE_EX0) >> i); - } - priv->gfargrp[grp_idx].num_tx_queues = 0x0; - - for_each_set_bit(i, &priv->gfargrp[grp_idx].tx_bit_map, - priv->num_tx_queues) { - priv->gfargrp[grp_idx].num_tx_queues++; - priv->tx_queue[i]->grp = &priv->gfargrp[grp_idx]; - tstat = tstat | (TSTAT_CLEAR_THALT >> i); - tqueue = tqueue | (TQUEUE_EN0 >> i); - } - priv->gfargrp[grp_idx].rstat = rstat; - priv->gfargrp[grp_idx].tstat = tstat; - rstat = tstat =0; + if (priv->device_flags & FSL_GIANFAR_DEV_HAS_VLAN) { + dev->hw_features |= NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_CTAG_RX; + dev->features |= NETIF_F_HW_VLAN_CTAG_RX; } - gfar_write(®s->rqueue, rqueue); - gfar_write(®s->tqueue, tqueue); + gfar_init_addr_hash_table(priv); + + /* Insert receive time stamps into padding alignment bytes */ + if (priv->device_flags & FSL_GIANFAR_DEV_HAS_TIMER) + priv->padding = 8; + + if (dev->features & NETIF_F_IP_CSUM || + priv->device_flags & FSL_GIANFAR_DEV_HAS_TIMER) + dev->needed_headroom = GMAC_FCB_LEN; priv->rx_buffer_size = DEFAULT_RX_BUFFER_SIZE; @@ -1220,8 +1358,9 @@ static int gfar_probe(struct platform_device *ofdev) if (priv->num_tx_queues == 1) priv->prio_sched_en = 1; - /* Carrier starts down, phylib will bring it up */ - netif_carrier_off(dev); + set_bit(GFAR_DOWN, &priv->state); + + gfar_hw_init(priv); err = register_netdev(dev); @@ -1230,6 +1369,9 @@ static int gfar_probe(struct platform_device *ofdev) goto register_fail; } + /* Carrier starts down, phylib will bring it up */ + netif_carrier_off(dev); + device_init_wakeup(&dev->dev, priv->device_flags & FSL_GIANFAR_DEV_HAS_MAGIC_PACKET); @@ -1251,9 +1393,6 @@ static int gfar_probe(struct platform_device *ofdev) /* Initialize the filer table */ gfar_init_filer_table(priv); - /* Create all the sysfs files */ - gfar_init_sysfs(dev); - /* Print out the device info */ netdev_info(dev, "mac: %pM\n", dev->dev_addr); @@ -1272,8 +1411,8 @@ static int gfar_probe(struct platform_device *ofdev) register_fail: unmap_group_regs(priv); - free_tx_pointers(priv); - free_rx_pointers(priv); + gfar_free_rx_queues(priv); + gfar_free_tx_queues(priv); if (priv->phy_node) of_node_put(priv->phy_node); if (priv->tbi_node) @@ -1293,6 +1432,8 @@ static int gfar_remove(struct platform_device *ofdev) unregister_netdev(priv->ndev); unmap_group_regs(priv); + gfar_free_rx_queues(priv); + gfar_free_tx_queues(priv); free_gfar_dev(priv); return 0; @@ -1318,9 +1459,8 @@ static int gfar_suspend(struct device *dev) local_irq_save(flags); lock_tx_qs(priv); - lock_rx_qs(priv); - gfar_halt_nodisable(ndev); + gfar_halt_nodisable(priv); /* Disable Tx, and Rx if wake-on-LAN is disabled. */ tempval = gfar_read(®s->maccfg1); @@ -1332,7 +1472,6 @@ static int gfar_suspend(struct device *dev) gfar_write(®s->maccfg1, tempval); - unlock_rx_qs(priv); unlock_tx_qs(priv); local_irq_restore(flags); @@ -1378,15 +1517,13 @@ static int gfar_resume(struct device *dev) */ local_irq_save(flags); lock_tx_qs(priv); - lock_rx_qs(priv); tempval = gfar_read(®s->maccfg2); tempval &= ~MACCFG2_MPEN; gfar_write(®s->maccfg2, tempval); - gfar_start(ndev); + gfar_start(priv); - unlock_rx_qs(priv); unlock_tx_qs(priv); local_irq_restore(flags); @@ -1413,10 +1550,11 @@ static int gfar_restore(struct device *dev) return -ENOMEM; } - init_registers(ndev); - gfar_set_mac_address(ndev); - gfar_init_mac(ndev); - gfar_start(ndev); + gfar_mac_reset(priv); + + gfar_init_tx_rx_base(priv); + + gfar_start(priv); priv->oldlink = 0; priv->oldspeed = 0; @@ -1574,57 +1712,6 @@ static void gfar_configure_serdes(struct net_device *dev) BMCR_SPEED1000); } -static void init_registers(struct net_device *dev) -{ - struct gfar_private *priv = netdev_priv(dev); - struct gfar __iomem *regs = NULL; - int i; - - for (i = 0; i < priv->num_grps; i++) { - regs = priv->gfargrp[i].regs; - /* Clear IEVENT */ - gfar_write(®s->ievent, IEVENT_INIT_CLEAR); - - /* Initialize IMASK */ - gfar_write(®s->imask, IMASK_INIT_CLEAR); - } - - regs = priv->gfargrp[0].regs; - /* Init hash registers to zero */ - gfar_write(®s->igaddr0, 0); - gfar_write(®s->igaddr1, 0); - gfar_write(®s->igaddr2, 0); - gfar_write(®s->igaddr3, 0); - gfar_write(®s->igaddr4, 0); - gfar_write(®s->igaddr5, 0); - gfar_write(®s->igaddr6, 0); - gfar_write(®s->igaddr7, 0); - - gfar_write(®s->gaddr0, 0); - gfar_write(®s->gaddr1, 0); - gfar_write(®s->gaddr2, 0); - gfar_write(®s->gaddr3, 0); - gfar_write(®s->gaddr4, 0); - gfar_write(®s->gaddr5, 0); - gfar_write(®s->gaddr6, 0); - gfar_write(®s->gaddr7, 0); - - /* Zero out the rmon mib registers if it has them */ - if (priv->device_flags & FSL_GIANFAR_DEV_HAS_RMON) { - memset_io(&(regs->rmon), 0, sizeof (struct rmon_mib)); - - /* Mask off the CAM interrupts */ - gfar_write(®s->rmon.cam1, 0xffffffff); - gfar_write(®s->rmon.cam2, 0xffffffff); - } - - /* Initialize the max receive buffer length */ - gfar_write(®s->mrblr, priv->rx_buffer_size); - - /* Initialize the Minimum Frame Length Register */ - gfar_write(®s->minflr, MINFLR_INIT_SETTINGS); -} - static int __gfar_is_rx_idle(struct gfar_private *priv) { u32 res; @@ -1648,23 +1735,13 @@ static int __gfar_is_rx_idle(struct gfar_private *priv) } /* Halt the receive and transmit queues */ -static void gfar_halt_nodisable(struct net_device *dev) +static void gfar_halt_nodisable(struct gfar_private *priv) { - struct gfar_private *priv = netdev_priv(dev); - struct gfar __iomem *regs = NULL; + struct gfar __iomem *regs = priv->gfargrp[0].regs; u32 tempval; - int i; - - for (i = 0; i < priv->num_grps; i++) { - regs = priv->gfargrp[i].regs; - /* Mask all interrupts */ - gfar_write(®s->imask, IMASK_INIT_CLEAR); - /* Clear all interrupts */ - gfar_write(®s->ievent, IEVENT_INIT_CLEAR); - } + gfar_ints_disable(priv); - regs = priv->gfargrp[0].regs; /* Stop the DMA, and wait for it to stop */ tempval = gfar_read(®s->dmactrl); if ((tempval & (DMACTRL_GRS | DMACTRL_GTS)) != @@ -1685,56 +1762,41 @@ static void gfar_halt_nodisable(struct net_device *dev) } /* Halt the receive and transmit queues */ -void gfar_halt(struct net_device *dev) +void gfar_halt(struct gfar_private *priv) { - struct gfar_private *priv = netdev_priv(dev); struct gfar __iomem *regs = priv->gfargrp[0].regs; u32 tempval; - gfar_halt_nodisable(dev); + /* Dissable the Rx/Tx hw queues */ + gfar_write(®s->rqueue, 0); + gfar_write(®s->tqueue, 0); + + mdelay(10); - /* Disable Rx and Tx */ + gfar_halt_nodisable(priv); + + /* Disable Rx/Tx DMA */ tempval = gfar_read(®s->maccfg1); tempval &= ~(MACCFG1_RX_EN | MACCFG1_TX_EN); gfar_write(®s->maccfg1, tempval); } -static void free_grp_irqs(struct gfar_priv_grp *grp) -{ - free_irq(gfar_irq(grp, TX)->irq, grp); - free_irq(gfar_irq(grp, RX)->irq, grp); - free_irq(gfar_irq(grp, ER)->irq, grp); -} - void stop_gfar(struct net_device *dev) { struct gfar_private *priv = netdev_priv(dev); - unsigned long flags; - int i; - - phy_stop(priv->phydev); + netif_tx_stop_all_queues(dev); - /* Lock it down */ - local_irq_save(flags); - lock_tx_qs(priv); - lock_rx_qs(priv); + smp_mb__before_clear_bit(); + set_bit(GFAR_DOWN, &priv->state); + smp_mb__after_clear_bit(); - gfar_halt(dev); + disable_napi(priv); - unlock_rx_qs(priv); - unlock_tx_qs(priv); - local_irq_restore(flags); + /* disable ints and gracefully shut down Rx/Tx DMA */ + gfar_halt(priv); - /* Free the IRQs */ - if (priv->device_flags & FSL_GIANFAR_DEV_HAS_MULTI_INTR) { - for (i = 0; i < priv->num_grps; i++) - free_grp_irqs(&priv->gfargrp[i]); - } else { - for (i = 0; i < priv->num_grps; i++) - free_irq(gfar_irq(&priv->gfargrp[i], TX)->irq, - &priv->gfargrp[i]); - } + phy_stop(priv->phydev); free_skb_resources(priv); } @@ -1825,17 +1887,15 @@ static void free_skb_resources(struct gfar_private *priv) priv->tx_queue[0]->tx_bd_dma_base); } -void gfar_start(struct net_device *dev) +void gfar_start(struct gfar_private *priv) { - struct gfar_private *priv = netdev_priv(dev); struct gfar __iomem *regs = priv->gfargrp[0].regs; u32 tempval; int i = 0; - /* Enable Rx and Tx in MACCFG1 */ - tempval = gfar_read(®s->maccfg1); - tempval |= (MACCFG1_RX_EN | MACCFG1_TX_EN); - gfar_write(®s->maccfg1, tempval); + /* Enable Rx/Tx hw queues */ + gfar_write(®s->rqueue, priv->rqueue); + gfar_write(®s->tqueue, priv->tqueue); /* Initialize DMACTRL to have WWR and WOP */ tempval = gfar_read(®s->dmactrl); @@ -1852,52 +1912,23 @@ void gfar_start(struct net_device *dev) /* Clear THLT/RHLT, so that the DMA starts polling now */ gfar_write(®s->tstat, priv->gfargrp[i].tstat); gfar_write(®s->rstat, priv->gfargrp[i].rstat); - /* Unmask the interrupts we look for */ - gfar_write(®s->imask, IMASK_DEFAULT); } - dev->trans_start = jiffies; /* prevent tx timeout */ -} - -static void gfar_configure_coalescing(struct gfar_private *priv, - unsigned long tx_mask, unsigned long rx_mask) -{ - struct gfar __iomem *regs = priv->gfargrp[0].regs; - u32 __iomem *baddr; - - if (priv->mode == MQ_MG_MODE) { - int i = 0; - - baddr = ®s->txic0; - for_each_set_bit(i, &tx_mask, priv->num_tx_queues) { - gfar_write(baddr + i, 0); - if (likely(priv->tx_queue[i]->txcoalescing)) - gfar_write(baddr + i, priv->tx_queue[i]->txic); - } + /* Enable Rx/Tx DMA */ + tempval = gfar_read(®s->maccfg1); + tempval |= (MACCFG1_RX_EN | MACCFG1_TX_EN); + gfar_write(®s->maccfg1, tempval); - baddr = ®s->rxic0; - for_each_set_bit(i, &rx_mask, priv->num_rx_queues) { - gfar_write(baddr + i, 0); - if (likely(priv->rx_queue[i]->rxcoalescing)) - gfar_write(baddr + i, priv->rx_queue[i]->rxic); - } - } else { - /* Backward compatible case -- even if we enable - * multiple queues, there's only single reg to program - */ - gfar_write(®s->txic, 0); - if (likely(priv->tx_queue[0]->txcoalescing)) - gfar_write(®s->txic, priv->tx_queue[0]->txic); + gfar_ints_enable(priv); - gfar_write(®s->rxic, 0); - if (unlikely(priv->rx_queue[0]->rxcoalescing)) - gfar_write(®s->rxic, priv->rx_queue[0]->rxic); - } + priv->ndev->trans_start = jiffies; /* prevent tx timeout */ } -void gfar_configure_coalescing_all(struct gfar_private *priv) +static void free_grp_irqs(struct gfar_priv_grp *grp) { - gfar_configure_coalescing(priv, 0xFF, 0xFF); + free_irq(gfar_irq(grp, TX)->irq, grp); + free_irq(gfar_irq(grp, RX)->irq, grp); + free_irq(gfar_irq(grp, ER)->irq, grp); } static int register_grp_irqs(struct gfar_priv_grp *grp) @@ -1956,46 +1987,65 @@ err_irq_fail: } -/* Bring the controller up and running */ -int startup_gfar(struct net_device *ndev) +static void gfar_free_irq(struct gfar_private *priv) { - struct gfar_private *priv = netdev_priv(ndev); - struct gfar __iomem *regs = NULL; - int err, i, j; + int i; - for (i = 0; i < priv->num_grps; i++) { - regs= priv->gfargrp[i].regs; - gfar_write(®s->imask, IMASK_INIT_CLEAR); + /* Free the IRQs */ + if (priv->device_flags & FSL_GIANFAR_DEV_HAS_MULTI_INTR) { + for (i = 0; i < priv->num_grps; i++) + free_grp_irqs(&priv->gfargrp[i]); + } else { + for (i = 0; i < priv->num_grps; i++) + free_irq(gfar_irq(&priv->gfargrp[i], TX)->irq, + &priv->gfargrp[i]); } +} - regs= priv->gfargrp[0].regs; - err = gfar_alloc_skb_resources(ndev); - if (err) - return err; - - gfar_init_mac(ndev); +static int gfar_request_irq(struct gfar_private *priv) +{ + int err, i, j; for (i = 0; i < priv->num_grps; i++) { err = register_grp_irqs(&priv->gfargrp[i]); if (err) { for (j = 0; j < i; j++) free_grp_irqs(&priv->gfargrp[j]); - goto irq_fail; + return err; } } - /* Start the controller */ - gfar_start(ndev); + return 0; +} + +/* Bring the controller up and running */ +int startup_gfar(struct net_device *ndev) +{ + struct gfar_private *priv = netdev_priv(ndev); + int err; + + gfar_mac_reset(priv); + + err = gfar_alloc_skb_resources(ndev); + if (err) + return err; + + gfar_init_tx_rx_base(priv); + + smp_mb__before_clear_bit(); + clear_bit(GFAR_DOWN, &priv->state); + smp_mb__after_clear_bit(); + + /* Start Rx/Tx DMA and enable the interrupts */ + gfar_start(priv); phy_start(priv->phydev); - gfar_configure_coalescing_all(priv); + enable_napi(priv); - return 0; + netif_tx_wake_all_queues(ndev); -irq_fail: - free_skb_resources(priv); - return err; + return 0; } /* Called when something needs to use the ethernet device @@ -2006,27 +2056,17 @@ static int gfar_enet_open(struct net_device *dev) struct gfar_private *priv = netdev_priv(dev); int err; - enable_napi(priv); - - /* Initialize a bunch of registers */ - init_registers(dev); - - gfar_set_mac_address(dev); - err = init_phy(dev); + if (err) + return err; - if (err) { - disable_napi(priv); + err = gfar_request_irq(priv); + if (err) return err; - } err = startup_gfar(dev); - if (err) { - disable_napi(priv); + if (err) return err; - } - - netif_tx_start_all_queues(dev); device_set_wakeup_enable(&dev->dev, priv->wol_en); @@ -2152,13 +2192,13 @@ static int gfar_start_xmit(struct sk_buff *skb, struct net_device *dev) skb_new = skb_realloc_headroom(skb, fcb_len); if (!skb_new) { dev->stats.tx_errors++; - kfree_skb(skb); + dev_kfree_skb_any(skb); return NETDEV_TX_OK; } if (skb->sk) skb_set_owner_w(skb_new, skb->sk); - consume_skb(skb); + dev_consume_skb_any(skb); skb = skb_new; } @@ -2351,8 +2391,6 @@ static int gfar_close(struct net_device *dev) { struct gfar_private *priv = netdev_priv(dev); - disable_napi(priv); - cancel_work_sync(&priv->reset_task); stop_gfar(dev); @@ -2360,7 +2398,7 @@ static int gfar_close(struct net_device *dev) phy_disconnect(priv->phydev); priv->phydev = NULL; - netif_tx_stop_all_queues(dev); + gfar_free_irq(priv); return 0; } @@ -2373,77 +2411,9 @@ static int gfar_set_mac_address(struct net_device *dev) return 0; } -/* Check if rx parser should be activated */ -void gfar_check_rx_parser_mode(struct gfar_private *priv) -{ - struct gfar __iomem *regs; - u32 tempval; - - regs = priv->gfargrp[0].regs; - - tempval = gfar_read(®s->rctrl); - /* If parse is no longer required, then disable parser */ - if (tempval & RCTRL_REQ_PARSER) { - tempval |= RCTRL_PRSDEP_INIT; - priv->uses_rxfcb = 1; - } else { - tempval &= ~RCTRL_PRSDEP_INIT; - priv->uses_rxfcb = 0; - } - gfar_write(®s->rctrl, tempval); -} - -/* Enables and disables VLAN insertion/extraction */ -void gfar_vlan_mode(struct net_device *dev, netdev_features_t features) -{ - struct gfar_private *priv = netdev_priv(dev); - struct gfar __iomem *regs = NULL; - unsigned long flags; - u32 tempval; - - regs = priv->gfargrp[0].regs; - local_irq_save(flags); - lock_rx_qs(priv); - - if (features & NETIF_F_HW_VLAN_CTAG_TX) { - /* Enable VLAN tag insertion */ - tempval = gfar_read(®s->tctrl); - tempval |= TCTRL_VLINS; - gfar_write(®s->tctrl, tempval); - } else { - /* Disable VLAN tag insertion */ - tempval = gfar_read(®s->tctrl); - tempval &= ~TCTRL_VLINS; - gfar_write(®s->tctrl, tempval); - } - - if (features & NETIF_F_HW_VLAN_CTAG_RX) { - /* Enable VLAN tag extraction */ - tempval = gfar_read(®s->rctrl); - tempval |= (RCTRL_VLEX | RCTRL_PRSDEP_INIT); - gfar_write(®s->rctrl, tempval); - priv->uses_rxfcb = 1; - } else { - /* Disable VLAN tag extraction */ - tempval = gfar_read(®s->rctrl); - tempval &= ~RCTRL_VLEX; - gfar_write(®s->rctrl, tempval); - - gfar_check_rx_parser_mode(priv); - } - - gfar_change_mtu(dev, dev->mtu); - - unlock_rx_qs(priv); - local_irq_restore(flags); -} - static int gfar_change_mtu(struct net_device *dev, int new_mtu) { - int tempsize, tempval; struct gfar_private *priv = netdev_priv(dev); - struct gfar __iomem *regs = priv->gfargrp[0].regs; - int oldsize = priv->rx_buffer_size; int frame_size = new_mtu + ETH_HLEN; if ((frame_size < 64) || (frame_size > JUMBO_FRAME_SIZE)) { @@ -2451,45 +2421,33 @@ static int gfar_change_mtu(struct net_device *dev, int new_mtu) return -EINVAL; } - if (priv->uses_rxfcb) - frame_size += GMAC_FCB_LEN; + while (test_and_set_bit_lock(GFAR_RESETTING, &priv->state)) + cpu_relax(); - frame_size += priv->padding; - - tempsize = (frame_size & ~(INCREMENTAL_BUFFER_SIZE - 1)) + - INCREMENTAL_BUFFER_SIZE; - - /* Only stop and start the controller if it isn't already - * stopped, and we changed something - */ - if ((oldsize != tempsize) && (dev->flags & IFF_UP)) + if (dev->flags & IFF_UP) stop_gfar(dev); - priv->rx_buffer_size = tempsize; - dev->mtu = new_mtu; - gfar_write(®s->mrblr, priv->rx_buffer_size); - gfar_write(®s->maxfrm, priv->rx_buffer_size); + if (dev->flags & IFF_UP) + startup_gfar(dev); - /* If the mtu is larger than the max size for standard - * ethernet frames (ie, a jumbo frame), then set maccfg2 - * to allow huge frames, and to check the length - */ - tempval = gfar_read(®s->maccfg2); + clear_bit_unlock(GFAR_RESETTING, &priv->state); - if (priv->rx_buffer_size > DEFAULT_RX_BUFFER_SIZE || - gfar_has_errata(priv, GFAR_ERRATA_74)) - tempval |= (MACCFG2_HUGEFRAME | MACCFG2_LENGTHCHECK); - else - tempval &= ~(MACCFG2_HUGEFRAME | MACCFG2_LENGTHCHECK); + return 0; +} - gfar_write(®s->maccfg2, tempval); +void reset_gfar(struct net_device *ndev) +{ + struct gfar_private *priv = netdev_priv(ndev); - if ((oldsize != tempsize) && (dev->flags & IFF_UP)) - startup_gfar(dev); + while (test_and_set_bit_lock(GFAR_RESETTING, &priv->state)) + cpu_relax(); - return 0; + stop_gfar(ndev); + startup_gfar(ndev); + + clear_bit_unlock(GFAR_RESETTING, &priv->state); } /* gfar_reset_task gets scheduled when a packet has not been @@ -2501,16 +2459,7 @@ static void gfar_reset_task(struct work_struct *work) { struct gfar_private *priv = container_of(work, struct gfar_private, reset_task); - struct net_device *dev = priv->ndev; - - if (dev->flags & IFF_UP) { - netif_tx_stop_all_queues(dev); - stop_gfar(dev); - startup_gfar(dev); - netif_tx_start_all_queues(dev); - } - - netif_tx_schedule_all(dev); + reset_gfar(priv->ndev); } static void gfar_timeout(struct net_device *dev) @@ -2623,8 +2572,10 @@ static void gfar_clean_tx_ring(struct gfar_priv_tx_q *tx_queue) } /* If we freed a buffer, we can restart transmission, if necessary */ - if (netif_tx_queue_stopped(txq) && tx_queue->num_txbdfree) - netif_wake_subqueue(dev, tqi); + if (tx_queue->num_txbdfree && + netif_tx_queue_stopped(txq) && + !(test_bit(GFAR_DOWN, &priv->state))) + netif_wake_subqueue(priv->ndev, tqi); /* Update dirty indicators */ tx_queue->skb_dirtytx = skb_dirtytx; @@ -2633,31 +2584,6 @@ static void gfar_clean_tx_ring(struct gfar_priv_tx_q *tx_queue) netdev_tx_completed_queue(txq, howmany, bytes_sent); } -static void gfar_schedule_cleanup(struct gfar_priv_grp *gfargrp) -{ - unsigned long flags; - - spin_lock_irqsave(&gfargrp->grplock, flags); - if (napi_schedule_prep(&gfargrp->napi)) { - gfar_write(&gfargrp->regs->imask, IMASK_RTX_DISABLED); - __napi_schedule(&gfargrp->napi); - } else { - /* Clear IEVENT, so interrupts aren't called again - * because of the packets that have already arrived. - */ - gfar_write(&gfargrp->regs->ievent, IEVENT_RTX_MASK); - } - spin_unlock_irqrestore(&gfargrp->grplock, flags); - -} - -/* Interrupt Handler for Transmit complete */ -static irqreturn_t gfar_transmit(int irq, void *grp_id) -{ - gfar_schedule_cleanup((struct gfar_priv_grp *)grp_id); - return IRQ_HANDLED; -} - static void gfar_new_rxbdp(struct gfar_priv_rx_q *rx_queue, struct rxbd8 *bdp, struct sk_buff *skb) { @@ -2728,7 +2654,48 @@ static inline void count_errors(unsigned short status, struct net_device *dev) irqreturn_t gfar_receive(int irq, void *grp_id) { - gfar_schedule_cleanup((struct gfar_priv_grp *)grp_id); + struct gfar_priv_grp *grp = (struct gfar_priv_grp *)grp_id; + unsigned long flags; + u32 imask; + + if (likely(napi_schedule_prep(&grp->napi_rx))) { + spin_lock_irqsave(&grp->grplock, flags); + imask = gfar_read(&grp->regs->imask); + imask &= IMASK_RX_DISABLED; + gfar_write(&grp->regs->imask, imask); + spin_unlock_irqrestore(&grp->grplock, flags); + __napi_schedule(&grp->napi_rx); + } else { + /* Clear IEVENT, so interrupts aren't called again + * because of the packets that have already arrived. + */ + gfar_write(&grp->regs->ievent, IEVENT_RX_MASK); + } + + return IRQ_HANDLED; +} + +/* Interrupt Handler for Transmit complete */ +static irqreturn_t gfar_transmit(int irq, void *grp_id) +{ + struct gfar_priv_grp *grp = (struct gfar_priv_grp *)grp_id; + unsigned long flags; + u32 imask; + + if (likely(napi_schedule_prep(&grp->napi_tx))) { + spin_lock_irqsave(&grp->grplock, flags); + imask = gfar_read(&grp->regs->imask); + imask &= IMASK_TX_DISABLED; + gfar_write(&grp->regs->imask, imask); + spin_unlock_irqrestore(&grp->grplock, flags); + __napi_schedule(&grp->napi_tx); + } else { + /* Clear IEVENT, so interrupts aren't called again + * because of the packets that have already arrived. + */ + gfar_write(&grp->regs->ievent, IEVENT_TX_MASK); + } + return IRQ_HANDLED; } @@ -2852,7 +2819,7 @@ int gfar_clean_rx_ring(struct gfar_priv_rx_q *rx_queue, int rx_work_limit) rx_queue->stats.rx_bytes += pkt_len; skb_record_rx_queue(skb, rx_queue->qindex); gfar_process_frame(dev, skb, amount_pull, - &rx_queue->grp->napi); + &rx_queue->grp->napi_rx); } else { netif_warn(priv, rx_err, dev, "Missing skb!\n"); @@ -2881,66 +2848,81 @@ int gfar_clean_rx_ring(struct gfar_priv_rx_q *rx_queue, int rx_work_limit) return howmany; } -static int gfar_poll_sq(struct napi_struct *napi, int budget) +static int gfar_poll_rx_sq(struct napi_struct *napi, int budget) { struct gfar_priv_grp *gfargrp = - container_of(napi, struct gfar_priv_grp, napi); + container_of(napi, struct gfar_priv_grp, napi_rx); struct gfar __iomem *regs = gfargrp->regs; - struct gfar_priv_tx_q *tx_queue = gfargrp->priv->tx_queue[0]; - struct gfar_priv_rx_q *rx_queue = gfargrp->priv->rx_queue[0]; + struct gfar_priv_rx_q *rx_queue = gfargrp->rx_queue; int work_done = 0; /* Clear IEVENT, so interrupts aren't called again * because of the packets that have already arrived */ - gfar_write(®s->ievent, IEVENT_RTX_MASK); - - /* run Tx cleanup to completion */ - if (tx_queue->tx_skbuff[tx_queue->skb_dirtytx]) - gfar_clean_tx_ring(tx_queue); + gfar_write(®s->ievent, IEVENT_RX_MASK); work_done = gfar_clean_rx_ring(rx_queue, budget); if (work_done < budget) { + u32 imask; napi_complete(napi); /* Clear the halt bit in RSTAT */ gfar_write(®s->rstat, gfargrp->rstat); - gfar_write(®s->imask, IMASK_DEFAULT); - - /* If we are coalescing interrupts, update the timer - * Otherwise, clear it - */ - gfar_write(®s->txic, 0); - if (likely(tx_queue->txcoalescing)) - gfar_write(®s->txic, tx_queue->txic); - - gfar_write(®s->rxic, 0); - if (unlikely(rx_queue->rxcoalescing)) - gfar_write(®s->rxic, rx_queue->rxic); + spin_lock_irq(&gfargrp->grplock); + imask = gfar_read(®s->imask); + imask |= IMASK_RX_DEFAULT; + gfar_write(®s->imask, imask); + spin_unlock_irq(&gfargrp->grplock); } return work_done; } -static int gfar_poll(struct napi_struct *napi, int budget) +static int gfar_poll_tx_sq(struct napi_struct *napi, int budget) +{ + struct gfar_priv_grp *gfargrp = + container_of(napi, struct gfar_priv_grp, napi_tx); + struct gfar __iomem *regs = gfargrp->regs; + struct gfar_priv_tx_q *tx_queue = gfargrp->tx_queue; + u32 imask; + + /* Clear IEVENT, so interrupts aren't called again + * because of the packets that have already arrived + */ + gfar_write(®s->ievent, IEVENT_TX_MASK); + + /* run Tx cleanup to completion */ + if (tx_queue->tx_skbuff[tx_queue->skb_dirtytx]) + gfar_clean_tx_ring(tx_queue); + + napi_complete(napi); + + spin_lock_irq(&gfargrp->grplock); + imask = gfar_read(®s->imask); + imask |= IMASK_TX_DEFAULT; + gfar_write(®s->imask, imask); + spin_unlock_irq(&gfargrp->grplock); + + return 0; +} + +static int gfar_poll_rx(struct napi_struct *napi, int budget) { struct gfar_priv_grp *gfargrp = - container_of(napi, struct gfar_priv_grp, napi); + container_of(napi, struct gfar_priv_grp, napi_rx); struct gfar_private *priv = gfargrp->priv; struct gfar __iomem *regs = gfargrp->regs; - struct gfar_priv_tx_q *tx_queue = NULL; struct gfar_priv_rx_q *rx_queue = NULL; int work_done = 0, work_done_per_q = 0; int i, budget_per_q = 0; - int has_tx_work = 0; unsigned long rstat_rxf; int num_act_queues; /* Clear IEVENT, so interrupts aren't called again * because of the packets that have already arrived */ - gfar_write(®s->ievent, IEVENT_RTX_MASK); + gfar_write(®s->ievent, IEVENT_RX_MASK); rstat_rxf = gfar_read(®s->rstat) & RSTAT_RXF_MASK; @@ -2948,15 +2930,6 @@ static int gfar_poll(struct napi_struct *napi, int budget) if (num_act_queues) budget_per_q = budget/num_act_queues; - for_each_set_bit(i, &gfargrp->tx_bit_map, priv->num_tx_queues) { - tx_queue = priv->tx_queue[i]; - /* run Tx cleanup to completion */ - if (tx_queue->tx_skbuff[tx_queue->skb_dirtytx]) { - gfar_clean_tx_ring(tx_queue); - has_tx_work = 1; - } - } - for_each_set_bit(i, &gfargrp->rx_bit_map, priv->num_rx_queues) { /* skip queue if not active */ if (!(rstat_rxf & (RSTAT_CLEAR_RXF0 >> i))) @@ -2979,25 +2952,62 @@ static int gfar_poll(struct napi_struct *napi, int budget) } } - if (!num_act_queues && !has_tx_work) { - + if (!num_act_queues) { + u32 imask; napi_complete(napi); /* Clear the halt bit in RSTAT */ gfar_write(®s->rstat, gfargrp->rstat); - gfar_write(®s->imask, IMASK_DEFAULT); - - /* If we are coalescing interrupts, update the timer - * Otherwise, clear it - */ - gfar_configure_coalescing(priv, gfargrp->rx_bit_map, - gfargrp->tx_bit_map); + spin_lock_irq(&gfargrp->grplock); + imask = gfar_read(®s->imask); + imask |= IMASK_RX_DEFAULT; + gfar_write(®s->imask, imask); + spin_unlock_irq(&gfargrp->grplock); } return work_done; } +static int gfar_poll_tx(struct napi_struct *napi, int budget) +{ + struct gfar_priv_grp *gfargrp = + container_of(napi, struct gfar_priv_grp, napi_tx); + struct gfar_private *priv = gfargrp->priv; + struct gfar __iomem *regs = gfargrp->regs; + struct gfar_priv_tx_q *tx_queue = NULL; + int has_tx_work = 0; + int i; + + /* Clear IEVENT, so interrupts aren't called again + * because of the packets that have already arrived + */ + gfar_write(®s->ievent, IEVENT_TX_MASK); + + for_each_set_bit(i, &gfargrp->tx_bit_map, priv->num_tx_queues) { + tx_queue = priv->tx_queue[i]; + /* run Tx cleanup to completion */ + if (tx_queue->tx_skbuff[tx_queue->skb_dirtytx]) { + gfar_clean_tx_ring(tx_queue); + has_tx_work = 1; + } + } + + if (!has_tx_work) { + u32 imask; + napi_complete(napi); + + spin_lock_irq(&gfargrp->grplock); + imask = gfar_read(®s->imask); + imask |= IMASK_TX_DEFAULT; + gfar_write(®s->imask, imask); + spin_unlock_irq(&gfargrp->grplock); + } + + return 0; +} + + #ifdef CONFIG_NET_POLL_CONTROLLER /* Polling 'interrupt' - used by things like netconsole to send skbs * without having to re-enable interrupts. It's not called while @@ -3101,12 +3111,11 @@ static void adjust_link(struct net_device *dev) { struct gfar_private *priv = netdev_priv(dev); struct gfar __iomem *regs = priv->gfargrp[0].regs; - unsigned long flags; struct phy_device *phydev = priv->phydev; int new_state = 0; - local_irq_save(flags); - lock_tx_qs(priv); + if (test_bit(GFAR_RESETTING, &priv->state)) + return; if (phydev->link) { u32 tempval1 = gfar_read(®s->maccfg1); @@ -3178,8 +3187,6 @@ static void adjust_link(struct net_device *dev) if (new_state && netif_msg_link(priv)) phy_print_status(phydev); - unlock_tx_qs(priv); - local_irq_restore(flags); } /* Update the hash table based on the current list of multicast diff --git a/drivers/net/ethernet/freescale/gianfar.h b/drivers/net/ethernet/freescale/gianfar.h index 52bb2b0195cc..84632c569f2c 100644 --- a/drivers/net/ethernet/freescale/gianfar.h +++ b/drivers/net/ethernet/freescale/gianfar.h @@ -9,7 +9,7 @@ * Maintainer: Kumar Gala * Modifier: Sandeep Gopalpet <sandeep.kumar@freescale.com> * - * Copyright 2002-2009, 2011 Freescale Semiconductor, Inc. + * Copyright 2002-2009, 2011-2013 Freescale Semiconductor, Inc. * * 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 @@ -377,8 +377,11 @@ extern const char gfar_driver_version[]; IMASK_RXFEN0 | IMASK_BSY | IMASK_EBERR | IMASK_BABR | \ IMASK_XFUN | IMASK_RXC | IMASK_BABT | IMASK_DPE \ | IMASK_PERR) -#define IMASK_RTX_DISABLED ((~(IMASK_RXFEN0 | IMASK_TXFEN | IMASK_BSY)) \ - & IMASK_DEFAULT) +#define IMASK_RX_DEFAULT (IMASK_RXFEN0 | IMASK_BSY) +#define IMASK_TX_DEFAULT (IMASK_TXFEN | IMASK_TXBEN) + +#define IMASK_RX_DISABLED ((~(IMASK_RX_DEFAULT)) & IMASK_DEFAULT) +#define IMASK_TX_DISABLED ((~(IMASK_TX_DEFAULT)) & IMASK_DEFAULT) /* Fifo management */ #define FIFO_TX_THR_MASK 0x01ff @@ -409,7 +412,9 @@ extern const char gfar_driver_version[]; /* This default RIR value directly corresponds * to the 3-bit hash value generated */ -#define DEFAULT_RIR0 0x05397700 +#define DEFAULT_8RXQ_RIR0 0x05397700 +/* Map even hash values to Q0, and odd ones to Q1 */ +#define DEFAULT_2RXQ_RIR0 0x04104100 /* RQFCR register bits */ #define RQFCR_GPI 0x80000000 @@ -880,7 +885,6 @@ struct gfar { #define FSL_GIANFAR_DEV_HAS_CSUM 0x00000010 #define FSL_GIANFAR_DEV_HAS_VLAN 0x00000020 #define FSL_GIANFAR_DEV_HAS_EXTENDED_HASH 0x00000040 -#define FSL_GIANFAR_DEV_HAS_PADDING 0x00000080 #define FSL_GIANFAR_DEV_HAS_MAGIC_PACKET 0x00000100 #define FSL_GIANFAR_DEV_HAS_BD_STASHING 0x00000200 #define FSL_GIANFAR_DEV_HAS_BUF_STASHING 0x00000400 @@ -892,8 +896,8 @@ struct gfar { #define DEFAULT_MAPPING 0xFF #endif -#define ISRG_SHIFT_TX 0x10 -#define ISRG_SHIFT_RX 0x18 +#define ISRG_RR0 0x80000000 +#define ISRG_TR0 0x00800000 /* The same driver can operate in two modes */ /* SQ_SG_MODE: Single Queue Single Group Mode @@ -905,6 +909,22 @@ enum { MQ_MG_MODE }; +/* GFAR_SQ_POLLING: Single Queue NAPI polling mode + * The driver supports a single pair of RX/Tx queues + * per interrupt group (Rx/Tx int line). MQ_MG mode + * devices have 2 interrupt groups, so the device will + * have a total of 2 Tx and 2 Rx queues in this case. + * GFAR_MQ_POLLING: Multi Queue NAPI polling mode + * The driver supports all the 8 Rx and Tx HW queues + * each queue mapped by the Device Tree to one of + * the 2 interrupt groups. This mode implies significant + * processing overhead (CPU and controller level). + */ +enum gfar_poll_mode { + GFAR_SQ_POLLING = 0, + GFAR_MQ_POLLING +}; + /* * Per TX queue stats */ @@ -966,7 +986,6 @@ struct rx_q_stats { /** * struct gfar_priv_rx_q - per rx queue structure - * @rxlock: per queue rx spin lock * @rx_skbuff: skb pointers * @skb_currx: currently use skb pointer * @rx_bd_base: First rx buffer descriptor @@ -979,8 +998,7 @@ struct rx_q_stats { */ struct gfar_priv_rx_q { - spinlock_t rxlock __attribute__ ((aligned (SMP_CACHE_BYTES))); - struct sk_buff ** rx_skbuff; + struct sk_buff **rx_skbuff __aligned(SMP_CACHE_BYTES); dma_addr_t rx_bd_dma_base; struct rxbd8 *rx_bd_base; struct rxbd8 *cur_rx; @@ -1016,17 +1034,20 @@ struct gfar_irqinfo { */ struct gfar_priv_grp { - spinlock_t grplock __attribute__ ((aligned (SMP_CACHE_BYTES))); - struct napi_struct napi; - struct gfar_private *priv; + spinlock_t grplock __aligned(SMP_CACHE_BYTES); + struct napi_struct napi_rx; + struct napi_struct napi_tx; struct gfar __iomem *regs; - unsigned int rstat; - unsigned long num_rx_queues; - unsigned long rx_bit_map; - /* cacheline 3 */ + struct gfar_priv_tx_q *tx_queue; + struct gfar_priv_rx_q *rx_queue; unsigned int tstat; + unsigned int rstat; + + struct gfar_private *priv; unsigned long num_tx_queues; unsigned long tx_bit_map; + unsigned long num_rx_queues; + unsigned long rx_bit_map; struct gfar_irqinfo *irqinfo[GFAR_NUM_IRQS]; }; @@ -1041,6 +1062,11 @@ enum gfar_errata { GFAR_ERRATA_12 = 0x08, /* a.k.a errata eTSEC49 */ }; +enum gfar_dev_state { + GFAR_DOWN = 1, + GFAR_RESETTING +}; + /* Struct stolen almost completely (and shamelessly) from the FCC enet source * (Ok, that's not so true anymore, but there is a family resemblance) * The GFAR buffer descriptors track the ring buffers. The rx_bd_base @@ -1051,8 +1077,6 @@ enum gfar_errata { * the buffer descriptor determines the actual condition. */ struct gfar_private { - unsigned int num_rx_queues; - struct device *dev; struct net_device *ndev; enum gfar_errata errata; @@ -1060,6 +1084,7 @@ struct gfar_private { u16 uses_rxfcb; u16 padding; + u32 device_flags; /* HW time stamping enabled flag */ int hwts_rx_en; @@ -1069,10 +1094,12 @@ struct gfar_private { struct gfar_priv_rx_q *rx_queue[MAX_RX_QS]; struct gfar_priv_grp gfargrp[MAXGROUPS]; - u32 device_flags; + unsigned long state; - unsigned int mode; + unsigned short mode; + unsigned short poll_mode; unsigned int num_tx_queues; + unsigned int num_rx_queues; unsigned int num_grps; /* Network Statistics */ @@ -1113,6 +1140,9 @@ struct gfar_private { unsigned int total_tx_ring_size; unsigned int total_rx_ring_size; + u32 rqueue; + u32 tqueue; + /* RX per device parameters */ unsigned int rx_stash_size; unsigned int rx_stash_index; @@ -1127,11 +1157,6 @@ struct gfar_private { u32 __iomem *hash_regs[16]; int hash_width; - /* global parameters */ - unsigned int fifo_threshold; - unsigned int fifo_starve; - unsigned int fifo_starve_off; - /*Filer table*/ unsigned int ftp_rqfpr[MAX_FILER_IDX + 1]; unsigned int ftp_rqfcr[MAX_FILER_IDX + 1]; @@ -1176,21 +1201,42 @@ static inline void gfar_read_filer(struct gfar_private *priv, *fpr = gfar_read(®s->rqfpr); } -void lock_rx_qs(struct gfar_private *priv); -void lock_tx_qs(struct gfar_private *priv); -void unlock_rx_qs(struct gfar_private *priv); -void unlock_tx_qs(struct gfar_private *priv); +static inline void gfar_write_isrg(struct gfar_private *priv) +{ + struct gfar __iomem *regs = priv->gfargrp[0].regs; + u32 __iomem *baddr = ®s->isrg0; + u32 isrg = 0; + int grp_idx, i; + + for (grp_idx = 0; grp_idx < priv->num_grps; grp_idx++) { + struct gfar_priv_grp *grp = &priv->gfargrp[grp_idx]; + + for_each_set_bit(i, &grp->rx_bit_map, priv->num_rx_queues) { + isrg |= (ISRG_RR0 >> i); + } + + for_each_set_bit(i, &grp->tx_bit_map, priv->num_tx_queues) { + isrg |= (ISRG_TR0 >> i); + } + + gfar_write(baddr, isrg); + + baddr++; + isrg = 0; + } +} + irqreturn_t gfar_receive(int irq, void *dev_id); int startup_gfar(struct net_device *dev); void stop_gfar(struct net_device *dev); -void gfar_halt(struct net_device *dev); +void reset_gfar(struct net_device *dev); +void gfar_mac_reset(struct gfar_private *priv); +void gfar_halt(struct gfar_private *priv); +void gfar_start(struct gfar_private *priv); void gfar_phy_test(struct mii_bus *bus, struct phy_device *phydev, int enable, u32 regnum, u32 read); void gfar_configure_coalescing_all(struct gfar_private *priv); -void gfar_init_sysfs(struct net_device *dev); int gfar_set_features(struct net_device *dev, netdev_features_t features); -void gfar_check_rx_parser_mode(struct gfar_private *priv); -void gfar_vlan_mode(struct net_device *dev, netdev_features_t features); extern const struct ethtool_ops gfar_ethtool_ops; diff --git a/drivers/net/ethernet/freescale/gianfar_ethtool.c b/drivers/net/ethernet/freescale/gianfar_ethtool.c index 63d234419cc1..891dbee6e6c1 100644 --- a/drivers/net/ethernet/freescale/gianfar_ethtool.c +++ b/drivers/net/ethernet/freescale/gianfar_ethtool.c @@ -44,10 +44,6 @@ #include "gianfar.h" -extern void gfar_start(struct net_device *dev); -extern int gfar_clean_rx_ring(struct gfar_priv_rx_q *rx_queue, - int rx_work_limit); - #define GFAR_MAX_COAL_USECS 0xffff #define GFAR_MAX_COAL_FRAMES 0xff static void gfar_fill_stats(struct net_device *dev, struct ethtool_stats *dummy, @@ -364,25 +360,11 @@ static int gfar_scoalesce(struct net_device *dev, struct ethtool_coalesce *cvals) { struct gfar_private *priv = netdev_priv(dev); - int i = 0; + int i, err = 0; if (!(priv->device_flags & FSL_GIANFAR_DEV_HAS_COALESCE)) return -EOPNOTSUPP; - /* Set up rx coalescing */ - /* As of now, we will enable/disable coalescing for all - * queues together in case of eTSEC2, this will be modified - * along with the ethtool interface - */ - if ((cvals->rx_coalesce_usecs == 0) || - (cvals->rx_max_coalesced_frames == 0)) { - for (i = 0; i < priv->num_rx_queues; i++) - priv->rx_queue[i]->rxcoalescing = 0; - } else { - for (i = 0; i < priv->num_rx_queues; i++) - priv->rx_queue[i]->rxcoalescing = 1; - } - if (NULL == priv->phydev) return -ENODEV; @@ -399,6 +381,32 @@ static int gfar_scoalesce(struct net_device *dev, return -EINVAL; } + /* Check the bounds of the values */ + if (cvals->tx_coalesce_usecs > GFAR_MAX_COAL_USECS) { + netdev_info(dev, "Coalescing is limited to %d microseconds\n", + GFAR_MAX_COAL_USECS); + return -EINVAL; + } + + if (cvals->tx_max_coalesced_frames > GFAR_MAX_COAL_FRAMES) { + netdev_info(dev, "Coalescing is limited to %d frames\n", + GFAR_MAX_COAL_FRAMES); + return -EINVAL; + } + + while (test_and_set_bit_lock(GFAR_RESETTING, &priv->state)) + cpu_relax(); + + /* Set up rx coalescing */ + if ((cvals->rx_coalesce_usecs == 0) || + (cvals->rx_max_coalesced_frames == 0)) { + for (i = 0; i < priv->num_rx_queues; i++) + priv->rx_queue[i]->rxcoalescing = 0; + } else { + for (i = 0; i < priv->num_rx_queues; i++) + priv->rx_queue[i]->rxcoalescing = 1; + } + for (i = 0; i < priv->num_rx_queues; i++) { priv->rx_queue[i]->rxic = mk_ic_value( cvals->rx_max_coalesced_frames, @@ -415,28 +423,22 @@ static int gfar_scoalesce(struct net_device *dev, priv->tx_queue[i]->txcoalescing = 1; } - /* Check the bounds of the values */ - if (cvals->tx_coalesce_usecs > GFAR_MAX_COAL_USECS) { - netdev_info(dev, "Coalescing is limited to %d microseconds\n", - GFAR_MAX_COAL_USECS); - return -EINVAL; - } - - if (cvals->tx_max_coalesced_frames > GFAR_MAX_COAL_FRAMES) { - netdev_info(dev, "Coalescing is limited to %d frames\n", - GFAR_MAX_COAL_FRAMES); - return -EINVAL; - } - for (i = 0; i < priv->num_tx_queues; i++) { priv->tx_queue[i]->txic = mk_ic_value( cvals->tx_max_coalesced_frames, gfar_usecs2ticks(priv, cvals->tx_coalesce_usecs)); } - gfar_configure_coalescing_all(priv); + if (dev->flags & IFF_UP) { + stop_gfar(dev); + err = startup_gfar(dev); + } else { + gfar_mac_reset(priv); + } + + clear_bit_unlock(GFAR_RESETTING, &priv->state); - return 0; + return err; } /* Fills in rvals with the current ring parameters. Currently, @@ -467,15 +469,13 @@ static void gfar_gringparam(struct net_device *dev, } /* Change the current ring parameters, stopping the controller if - * necessary so that we don't mess things up while we're in - * motion. We wait for the ring to be clean before reallocating - * the rings. + * necessary so that we don't mess things up while we're in motion. */ static int gfar_sringparam(struct net_device *dev, struct ethtool_ringparam *rvals) { struct gfar_private *priv = netdev_priv(dev); - int err = 0, i = 0; + int err = 0, i; if (rvals->rx_pending > GFAR_RX_MAX_RING_SIZE) return -EINVAL; @@ -493,44 +493,25 @@ static int gfar_sringparam(struct net_device *dev, return -EINVAL; } + while (test_and_set_bit_lock(GFAR_RESETTING, &priv->state)) + cpu_relax(); - if (dev->flags & IFF_UP) { - unsigned long flags; - - /* Halt TX and RX, and process the frames which - * have already been received - */ - local_irq_save(flags); - lock_tx_qs(priv); - lock_rx_qs(priv); - - gfar_halt(dev); - - unlock_rx_qs(priv); - unlock_tx_qs(priv); - local_irq_restore(flags); - - for (i = 0; i < priv->num_rx_queues; i++) - gfar_clean_rx_ring(priv->rx_queue[i], - priv->rx_queue[i]->rx_ring_size); - - /* Now we take down the rings to rebuild them */ + if (dev->flags & IFF_UP) stop_gfar(dev); - } - /* Change the size */ - for (i = 0; i < priv->num_rx_queues; i++) { + /* Change the sizes */ + for (i = 0; i < priv->num_rx_queues; i++) priv->rx_queue[i]->rx_ring_size = rvals->rx_pending; + + for (i = 0; i < priv->num_tx_queues; i++) priv->tx_queue[i]->tx_ring_size = rvals->tx_pending; - priv->tx_queue[i]->num_txbdfree = - priv->tx_queue[i]->tx_ring_size; - } /* Rebuild the rings with the new size */ - if (dev->flags & IFF_UP) { + if (dev->flags & IFF_UP) err = startup_gfar(dev); - netif_tx_wake_all_queues(dev); - } + + clear_bit_unlock(GFAR_RESETTING, &priv->state); + return err; } @@ -608,43 +589,29 @@ static int gfar_spauseparam(struct net_device *dev, int gfar_set_features(struct net_device *dev, netdev_features_t features) { - struct gfar_private *priv = netdev_priv(dev); - unsigned long flags; - int err = 0, i = 0; netdev_features_t changed = dev->features ^ features; + struct gfar_private *priv = netdev_priv(dev); + int err = 0; - if (changed & (NETIF_F_HW_VLAN_CTAG_TX|NETIF_F_HW_VLAN_CTAG_RX)) - gfar_vlan_mode(dev, features); - - if (!(changed & NETIF_F_RXCSUM)) + if (!(changed & (NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX | + NETIF_F_RXCSUM))) return 0; - if (dev->flags & IFF_UP) { - /* Halt TX and RX, and process the frames which - * have already been received - */ - local_irq_save(flags); - lock_tx_qs(priv); - lock_rx_qs(priv); - - gfar_halt(dev); + while (test_and_set_bit_lock(GFAR_RESETTING, &priv->state)) + cpu_relax(); - unlock_tx_qs(priv); - unlock_rx_qs(priv); - local_irq_restore(flags); - - for (i = 0; i < priv->num_rx_queues; i++) - gfar_clean_rx_ring(priv->rx_queue[i], - priv->rx_queue[i]->rx_ring_size); + dev->features = features; + if (dev->flags & IFF_UP) { /* Now we take down the rings to rebuild them */ stop_gfar(dev); - - dev->features = features; - err = startup_gfar(dev); - netif_tx_wake_all_queues(dev); + } else { + gfar_mac_reset(priv); } + + clear_bit_unlock(GFAR_RESETTING, &priv->state); + return err; } @@ -1610,9 +1577,6 @@ static int gfar_write_filer_table(struct gfar_private *priv, if (tab->index > MAX_FILER_IDX - 1) return -EBUSY; - /* Avoid inconsistent filer table to be processed */ - lock_rx_qs(priv); - /* Fill regular entries */ for (; i < MAX_FILER_IDX - 1 && (tab->fe[i].ctrl | tab->fe[i].ctrl); i++) @@ -1625,8 +1589,6 @@ static int gfar_write_filer_table(struct gfar_private *priv, */ gfar_write_filer(priv, i, 0x20, 0x0); - unlock_rx_qs(priv); - return 0; } @@ -1831,6 +1793,9 @@ static int gfar_set_nfc(struct net_device *dev, struct ethtool_rxnfc *cmd) struct gfar_private *priv = netdev_priv(dev); int ret = 0; + if (test_bit(GFAR_RESETTING, &priv->state)) + return -EBUSY; + mutex_lock(&priv->rx_queue_access); switch (cmd->cmd) { diff --git a/drivers/net/ethernet/freescale/gianfar_sysfs.c b/drivers/net/ethernet/freescale/gianfar_sysfs.c deleted file mode 100644 index e02dd1378751..000000000000 --- a/drivers/net/ethernet/freescale/gianfar_sysfs.c +++ /dev/null @@ -1,340 +0,0 @@ -/* - * drivers/net/ethernet/freescale/gianfar_sysfs.c - * - * Gianfar Ethernet Driver - * This driver is designed for the non-CPM ethernet controllers - * on the 85xx and 83xx family of integrated processors - * Based on 8260_io/fcc_enet.c - * - * Author: Andy Fleming - * Maintainer: Kumar Gala (galak@kernel.crashing.org) - * Modifier: Sandeep Gopalpet <sandeep.kumar@freescale.com> - * - * Copyright 2002-2009 Freescale Semiconductor, Inc. - * - * 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. - * - * Sysfs file creation and management - */ - -#include <linux/kernel.h> -#include <linux/string.h> -#include <linux/errno.h> -#include <linux/unistd.h> -#include <linux/delay.h> -#include <linux/etherdevice.h> -#include <linux/spinlock.h> -#include <linux/mm.h> -#include <linux/device.h> - -#include <asm/uaccess.h> -#include <linux/module.h> - -#include "gianfar.h" - -static ssize_t gfar_show_bd_stash(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct gfar_private *priv = netdev_priv(to_net_dev(dev)); - - return sprintf(buf, "%s\n", priv->bd_stash_en ? "on" : "off"); -} - -static ssize_t gfar_set_bd_stash(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) -{ - struct gfar_private *priv = netdev_priv(to_net_dev(dev)); - struct gfar __iomem *regs = priv->gfargrp[0].regs; - int new_setting = 0; - u32 temp; - unsigned long flags; - - if (!(priv->device_flags & FSL_GIANFAR_DEV_HAS_BD_STASHING)) - return count; - - - /* Find out the new setting */ - if (!strncmp("on", buf, count - 1) || !strncmp("1", buf, count - 1)) - new_setting = 1; - else if (!strncmp("off", buf, count - 1) || - !strncmp("0", buf, count - 1)) - new_setting = 0; - else - return count; - - - local_irq_save(flags); - lock_rx_qs(priv); - - /* Set the new stashing value */ - priv->bd_stash_en = new_setting; - - temp = gfar_read(®s->attr); - - if (new_setting) - temp |= ATTR_BDSTASH; - else - temp &= ~(ATTR_BDSTASH); - - gfar_write(®s->attr, temp); - - unlock_rx_qs(priv); - local_irq_restore(flags); - - return count; -} - -static DEVICE_ATTR(bd_stash, 0644, gfar_show_bd_stash, gfar_set_bd_stash); - -static ssize_t gfar_show_rx_stash_size(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct gfar_private *priv = netdev_priv(to_net_dev(dev)); - - return sprintf(buf, "%d\n", priv->rx_stash_size); -} - -static ssize_t gfar_set_rx_stash_size(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) -{ - struct gfar_private *priv = netdev_priv(to_net_dev(dev)); - struct gfar __iomem *regs = priv->gfargrp[0].regs; - unsigned int length = simple_strtoul(buf, NULL, 0); - u32 temp; - unsigned long flags; - - if (!(priv->device_flags & FSL_GIANFAR_DEV_HAS_BUF_STASHING)) - return count; - - local_irq_save(flags); - lock_rx_qs(priv); - - if (length > priv->rx_buffer_size) - goto out; - - if (length == priv->rx_stash_size) - goto out; - - priv->rx_stash_size = length; - - temp = gfar_read(®s->attreli); - temp &= ~ATTRELI_EL_MASK; - temp |= ATTRELI_EL(length); - gfar_write(®s->attreli, temp); - - /* Turn stashing on/off as appropriate */ - temp = gfar_read(®s->attr); - - if (length) - temp |= ATTR_BUFSTASH; - else - temp &= ~(ATTR_BUFSTASH); - - gfar_write(®s->attr, temp); - -out: - unlock_rx_qs(priv); - local_irq_restore(flags); - - return count; -} - -static DEVICE_ATTR(rx_stash_size, 0644, gfar_show_rx_stash_size, - gfar_set_rx_stash_size); - -/* Stashing will only be enabled when rx_stash_size != 0 */ -static ssize_t gfar_show_rx_stash_index(struct device *dev, - struct device_attribute *attr, - char *buf) -{ - struct gfar_private *priv = netdev_priv(to_net_dev(dev)); - - return sprintf(buf, "%d\n", priv->rx_stash_index); -} - -static ssize_t gfar_set_rx_stash_index(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) -{ - struct gfar_private *priv = netdev_priv(to_net_dev(dev)); - struct gfar __iomem *regs = priv->gfargrp[0].regs; - unsigned short index = simple_strtoul(buf, NULL, 0); - u32 temp; - unsigned long flags; - - if (!(priv->device_flags & FSL_GIANFAR_DEV_HAS_BUF_STASHING)) - return count; - - local_irq_save(flags); - lock_rx_qs(priv); - - if (index > priv->rx_stash_size) - goto out; - - if (index == priv->rx_stash_index) - goto out; - - priv->rx_stash_index = index; - - temp = gfar_read(®s->attreli); - temp &= ~ATTRELI_EI_MASK; - temp |= ATTRELI_EI(index); - gfar_write(®s->attreli, temp); - -out: - unlock_rx_qs(priv); - local_irq_restore(flags); - - return count; -} - -static DEVICE_ATTR(rx_stash_index, 0644, gfar_show_rx_stash_index, - gfar_set_rx_stash_index); - -static ssize_t gfar_show_fifo_threshold(struct device *dev, - struct device_attribute *attr, - char *buf) -{ - struct gfar_private *priv = netdev_priv(to_net_dev(dev)); - - return sprintf(buf, "%d\n", priv->fifo_threshold); -} - -static ssize_t gfar_set_fifo_threshold(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) -{ - struct gfar_private *priv = netdev_priv(to_net_dev(dev)); - struct gfar __iomem *regs = priv->gfargrp[0].regs; - unsigned int length = simple_strtoul(buf, NULL, 0); - u32 temp; - unsigned long flags; - - if (length > GFAR_MAX_FIFO_THRESHOLD) - return count; - - local_irq_save(flags); - lock_tx_qs(priv); - - priv->fifo_threshold = length; - - temp = gfar_read(®s->fifo_tx_thr); - temp &= ~FIFO_TX_THR_MASK; - temp |= length; - gfar_write(®s->fifo_tx_thr, temp); - - unlock_tx_qs(priv); - local_irq_restore(flags); - - return count; -} - -static DEVICE_ATTR(fifo_threshold, 0644, gfar_show_fifo_threshold, - gfar_set_fifo_threshold); - -static ssize_t gfar_show_fifo_starve(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct gfar_private *priv = netdev_priv(to_net_dev(dev)); - - return sprintf(buf, "%d\n", priv->fifo_starve); -} - -static ssize_t gfar_set_fifo_starve(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) -{ - struct gfar_private *priv = netdev_priv(to_net_dev(dev)); - struct gfar __iomem *regs = priv->gfargrp[0].regs; - unsigned int num = simple_strtoul(buf, NULL, 0); - u32 temp; - unsigned long flags; - - if (num > GFAR_MAX_FIFO_STARVE) - return count; - - local_irq_save(flags); - lock_tx_qs(priv); - - priv->fifo_starve = num; - - temp = gfar_read(®s->fifo_tx_starve); - temp &= ~FIFO_TX_STARVE_MASK; - temp |= num; - gfar_write(®s->fifo_tx_starve, temp); - - unlock_tx_qs(priv); - local_irq_restore(flags); - - return count; -} - -static DEVICE_ATTR(fifo_starve, 0644, gfar_show_fifo_starve, - gfar_set_fifo_starve); - -static ssize_t gfar_show_fifo_starve_off(struct device *dev, - struct device_attribute *attr, - char *buf) -{ - struct gfar_private *priv = netdev_priv(to_net_dev(dev)); - - return sprintf(buf, "%d\n", priv->fifo_starve_off); -} - -static ssize_t gfar_set_fifo_starve_off(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) -{ - struct gfar_private *priv = netdev_priv(to_net_dev(dev)); - struct gfar __iomem *regs = priv->gfargrp[0].regs; - unsigned int num = simple_strtoul(buf, NULL, 0); - u32 temp; - unsigned long flags; - - if (num > GFAR_MAX_FIFO_STARVE_OFF) - return count; - - local_irq_save(flags); - lock_tx_qs(priv); - - priv->fifo_starve_off = num; - - temp = gfar_read(®s->fifo_tx_starve_shutoff); - temp &= ~FIFO_TX_STARVE_OFF_MASK; - temp |= num; - gfar_write(®s->fifo_tx_starve_shutoff, temp); - - unlock_tx_qs(priv); - local_irq_restore(flags); - - return count; -} - -static DEVICE_ATTR(fifo_starve_off, 0644, gfar_show_fifo_starve_off, - gfar_set_fifo_starve_off); - -void gfar_init_sysfs(struct net_device *dev) -{ - struct gfar_private *priv = netdev_priv(dev); - int rc; - - /* Initialize the default values */ - priv->fifo_threshold = DEFAULT_FIFO_TX_THR; - priv->fifo_starve = DEFAULT_FIFO_TX_STARVE; - priv->fifo_starve_off = DEFAULT_FIFO_TX_STARVE_OFF; - - /* Create our sysfs files */ - rc = device_create_file(&dev->dev, &dev_attr_bd_stash); - rc |= device_create_file(&dev->dev, &dev_attr_rx_stash_size); - rc |= device_create_file(&dev->dev, &dev_attr_rx_stash_index); - rc |= device_create_file(&dev->dev, &dev_attr_fifo_threshold); - rc |= device_create_file(&dev->dev, &dev_attr_fifo_starve); - rc |= device_create_file(&dev->dev, &dev_attr_fifo_starve_off); - if (rc) - dev_err(&dev->dev, "Error creating gianfar sysfs files\n"); -} diff --git a/drivers/net/ethernet/intel/e100.c b/drivers/net/ethernet/intel/e100.c index cbaba4442d4b..bf7a01ef9a57 100644 --- a/drivers/net/ethernet/intel/e100.c +++ b/drivers/net/ethernet/intel/e100.c @@ -3034,7 +3034,7 @@ static void __e100_shutdown(struct pci_dev *pdev, bool *enable_wake) *enable_wake = false; } - pci_disable_device(pdev); + pci_clear_master(pdev); } static int __e100_power_off(struct pci_dev *pdev, bool wake) diff --git a/drivers/net/ethernet/intel/e1000e/80003es2lan.c b/drivers/net/ethernet/intel/e1000e/80003es2lan.c index ff2d806eaef7..a5f6b11d6992 100644 --- a/drivers/net/ethernet/intel/e1000e/80003es2lan.c +++ b/drivers/net/ethernet/intel/e1000e/80003es2lan.c @@ -1,30 +1,23 @@ -/******************************************************************************* - - Intel PRO/1000 Linux driver - Copyright(c) 1999 - 2013 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +/* Intel PRO/1000 Linux driver + * Copyright(c) 1999 - 2014 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + * Contact Information: + * Linux NICS <linux.nics@intel.com> + * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> + * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 + */ /* 80003ES2LAN Gigabit Ethernet Controller (Copper) * 80003ES2LAN Gigabit Ethernet Controller (Serdes) diff --git a/drivers/net/ethernet/intel/e1000e/80003es2lan.h b/drivers/net/ethernet/intel/e1000e/80003es2lan.h index 90d363b2d280..535a9430976d 100644 --- a/drivers/net/ethernet/intel/e1000e/80003es2lan.h +++ b/drivers/net/ethernet/intel/e1000e/80003es2lan.h @@ -1,30 +1,23 @@ -/******************************************************************************* - - Intel PRO/1000 Linux driver - Copyright(c) 1999 - 2013 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +/* Intel PRO/1000 Linux driver + * Copyright(c) 1999 - 2014 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + * Contact Information: + * Linux NICS <linux.nics@intel.com> + * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> + * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 + */ #ifndef _E1000E_80003ES2LAN_H_ #define _E1000E_80003ES2LAN_H_ diff --git a/drivers/net/ethernet/intel/e1000e/82571.c b/drivers/net/ethernet/intel/e1000e/82571.c index 8fed74e3fa53..e0aa7f1efb08 100644 --- a/drivers/net/ethernet/intel/e1000e/82571.c +++ b/drivers/net/ethernet/intel/e1000e/82571.c @@ -1,30 +1,23 @@ -/******************************************************************************* - - Intel PRO/1000 Linux driver - Copyright(c) 1999 - 2013 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +/* Intel PRO/1000 Linux driver + * Copyright(c) 1999 - 2014 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + * Contact Information: + * Linux NICS <linux.nics@intel.com> + * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> + * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 + */ /* 82571EB Gigabit Ethernet Controller * 82571EB Gigabit Ethernet Controller (Copper) diff --git a/drivers/net/ethernet/intel/e1000e/82571.h b/drivers/net/ethernet/intel/e1000e/82571.h index 08e24dc3dc0e..2e758f796d60 100644 --- a/drivers/net/ethernet/intel/e1000e/82571.h +++ b/drivers/net/ethernet/intel/e1000e/82571.h @@ -1,30 +1,23 @@ -/******************************************************************************* - - Intel PRO/1000 Linux driver - Copyright(c) 1999 - 2013 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +/* Intel PRO/1000 Linux driver + * Copyright(c) 1999 - 2014 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + * Contact Information: + * Linux NICS <linux.nics@intel.com> + * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> + * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 + */ #ifndef _E1000E_82571_H_ #define _E1000E_82571_H_ diff --git a/drivers/net/ethernet/intel/e1000e/Makefile b/drivers/net/ethernet/intel/e1000e/Makefile index c2dcfcc10857..106de493373c 100644 --- a/drivers/net/ethernet/intel/e1000e/Makefile +++ b/drivers/net/ethernet/intel/e1000e/Makefile @@ -1,7 +1,7 @@ ################################################################################ # # Intel PRO/1000 Linux driver -# Copyright(c) 1999 - 2013 Intel Corporation. +# Copyright(c) 1999 - 2014 Intel Corporation. # # This program is free software; you can redistribute it and/or modify it # under the terms and conditions of the GNU General Public License, @@ -12,9 +12,8 @@ # FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for # more details. # -# You should have received a copy of the GNU General Public License along with -# this program; if not, write to the Free Software Foundation, Inc., -# 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. +# You should have received a copy of the GNU General Public License +# along with this program; if not, see <http://www.gnu.org/licenses/>. # # The full GNU General Public License is included in this distribution in # the file called "COPYING". diff --git a/drivers/net/ethernet/intel/e1000e/defines.h b/drivers/net/ethernet/intel/e1000e/defines.h index 351c94a0cf74..d18e89212575 100644 --- a/drivers/net/ethernet/intel/e1000e/defines.h +++ b/drivers/net/ethernet/intel/e1000e/defines.h @@ -1,30 +1,23 @@ -/******************************************************************************* - - Intel PRO/1000 Linux driver - Copyright(c) 1999 - 2013 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +/* Intel PRO/1000 Linux driver + * Copyright(c) 1999 - 2014 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + * Contact Information: + * Linux NICS <linux.nics@intel.com> + * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> + * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 + */ #ifndef _E1000_DEFINES_H_ #define _E1000_DEFINES_H_ @@ -35,9 +28,11 @@ /* Definitions for power management and wakeup registers */ /* Wake Up Control */ -#define E1000_WUC_APME 0x00000001 /* APM Enable */ -#define E1000_WUC_PME_EN 0x00000002 /* PME Enable */ -#define E1000_WUC_PHY_WAKE 0x00000100 /* if PHY supports wakeup */ +#define E1000_WUC_APME 0x00000001 /* APM Enable */ +#define E1000_WUC_PME_EN 0x00000002 /* PME Enable */ +#define E1000_WUC_PME_STATUS 0x00000004 /* PME Status */ +#define E1000_WUC_APMPME 0x00000008 /* Assert PME on APM Wakeup */ +#define E1000_WUC_PHY_WAKE 0x00000100 /* if PHY supports wakeup */ /* Wake Up Filter Control */ #define E1000_WUFC_LNKC 0x00000001 /* Link Status Change Wakeup Enable */ diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h index 0150f7fc893d..5325e3e2154e 100644 --- a/drivers/net/ethernet/intel/e1000e/e1000.h +++ b/drivers/net/ethernet/intel/e1000e/e1000.h @@ -1,30 +1,23 @@ -/******************************************************************************* - - Intel PRO/1000 Linux driver - Copyright(c) 1999 - 2013 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +/* Intel PRO/1000 Linux driver + * Copyright(c) 1999 - 2014 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + * Contact Information: + * Linux NICS <linux.nics@intel.com> + * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> + * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 + */ /* Linux PRO/1000 Ethernet Driver main header file */ @@ -333,7 +326,6 @@ struct e1000_adapter { struct work_struct update_phy_task; struct work_struct print_hang_task; - bool idle_check; int phy_hang_count; u16 tx_ring_count; @@ -476,7 +468,7 @@ void e1000e_check_options(struct e1000_adapter *adapter); void e1000e_set_ethtool_ops(struct net_device *netdev); int e1000e_up(struct e1000_adapter *adapter); -void e1000e_down(struct e1000_adapter *adapter); +void e1000e_down(struct e1000_adapter *adapter, bool reset); void e1000e_reinit_locked(struct e1000_adapter *adapter); void e1000e_reset(struct e1000_adapter *adapter); void e1000e_power_up_phy(struct e1000_adapter *adapter); diff --git a/drivers/net/ethernet/intel/e1000e/ethtool.c b/drivers/net/ethernet/intel/e1000e/ethtool.c index d14c8f53384c..3c2898d0c2aa 100644 --- a/drivers/net/ethernet/intel/e1000e/ethtool.c +++ b/drivers/net/ethernet/intel/e1000e/ethtool.c @@ -1,30 +1,23 @@ -/******************************************************************************* - - Intel PRO/1000 Linux driver - Copyright(c) 1999 - 2013 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +/* Intel PRO/1000 Linux driver + * Copyright(c) 1999 - 2014 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + * Contact Information: + * Linux NICS <linux.nics@intel.com> + * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> + * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 + */ /* ethtool support for e1000 */ @@ -332,7 +325,7 @@ static int e1000_set_settings(struct net_device *netdev, /* reset the link */ if (netif_running(adapter->netdev)) { - e1000e_down(adapter); + e1000e_down(adapter, true); e1000e_up(adapter); } else { e1000e_reset(adapter); @@ -380,7 +373,7 @@ static int e1000_set_pauseparam(struct net_device *netdev, if (adapter->fc_autoneg == AUTONEG_ENABLE) { hw->fc.requested_mode = e1000_fc_default; if (netif_running(adapter->netdev)) { - e1000e_down(adapter); + e1000e_down(adapter, true); e1000e_up(adapter); } else { e1000e_reset(adapter); @@ -726,7 +719,7 @@ static int e1000_set_ringparam(struct net_device *netdev, pm_runtime_get_sync(netdev->dev.parent); - e1000e_down(adapter); + e1000e_down(adapter, true); /* We can't just free everything and then setup again, because the * ISRs in MSI-X mode get passed pointers to the Tx and Rx ring @@ -924,15 +917,21 @@ static int e1000_reg_test(struct e1000_adapter *adapter, u64 *data) } if (mac->type == e1000_pch2lan) { /* SHRAH[0,1,2] different than previous */ - if (i == 7) + if (i == 1) mask &= 0xFFF4FFFF; /* SHRAH[3] different than SHRAH[0,1,2] */ - if (i == 10) + if (i == 4) mask |= (1 << 30); + /* RAR[1-6] owned by management engine - skipping */ + if (i > 0) + i += 6; } REG_PATTERN_TEST_ARRAY(E1000_RA, ((i << 1) + 1), mask, 0xFFFFFFFF); + /* reset index to actual value */ + if ((mac->type == e1000_pch2lan) && (i > 6)) + i -= 6; } for (i = 0; i < mac->mta_reg_count; i++) diff --git a/drivers/net/ethernet/intel/e1000e/hw.h b/drivers/net/ethernet/intel/e1000e/hw.h index b7f38435d1fd..6b3de5f39a97 100644 --- a/drivers/net/ethernet/intel/e1000e/hw.h +++ b/drivers/net/ethernet/intel/e1000e/hw.h @@ -1,30 +1,23 @@ -/******************************************************************************* - - Intel PRO/1000 Linux driver - Copyright(c) 1999 - 2013 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +/* Intel PRO/1000 Linux driver + * Copyright(c) 1999 - 2014 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + * Contact Information: + * Linux NICS <linux.nics@intel.com> + * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> + * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 + */ #ifndef _E1000_HW_H_ #define _E1000_HW_H_ @@ -655,12 +648,20 @@ struct e1000_shadow_ram { #define E1000_ICH8_SHADOW_RAM_WORDS 2048 +/* I218 PHY Ultra Low Power (ULP) states */ +enum e1000_ulp_state { + e1000_ulp_state_unknown, + e1000_ulp_state_off, + e1000_ulp_state_on, +}; + struct e1000_dev_spec_ich8lan { bool kmrn_lock_loss_workaround_enabled; struct e1000_shadow_ram shadow_ram[E1000_ICH8_SHADOW_RAM_WORDS]; bool nvm_k1_enabled; bool eee_disable; u16 eee_lp_ability; + enum e1000_ulp_state ulp_state; }; struct e1000_hw { diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c index 42f0f6717511..9866f264f55e 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.c +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c @@ -1,30 +1,23 @@ -/******************************************************************************* - - Intel PRO/1000 Linux driver - Copyright(c) 1999 - 2013 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +/* Intel PRO/1000 Linux driver + * Copyright(c) 1999 - 2014 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + * Contact Information: + * Linux NICS <linux.nics@intel.com> + * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> + * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 + */ /* 82562G 10/100 Network Connection * 82562G-2 10/100 Network Connection @@ -53,6 +46,14 @@ * 82578DC Gigabit Network Connection * 82579LM Gigabit Network Connection * 82579V Gigabit Network Connection + * Ethernet Connection I217-LM + * Ethernet Connection I217-V + * Ethernet Connection I218-V + * Ethernet Connection I218-LM + * Ethernet Connection (2) I218-LM + * Ethernet Connection (2) I218-V + * Ethernet Connection (3) I218-LM + * Ethernet Connection (3) I218-V */ #include "e1000.h" @@ -142,7 +143,9 @@ static void e1000_rar_set_pch2lan(struct e1000_hw *hw, u8 *addr, u32 index); static void e1000_rar_set_pch_lpt(struct e1000_hw *hw, u8 *addr, u32 index); static s32 e1000_k1_workaround_lv(struct e1000_hw *hw); static void e1000_gate_hw_phy_config_ich8lan(struct e1000_hw *hw, bool gate); +static s32 e1000_disable_ulp_lpt_lp(struct e1000_hw *hw, bool force); static s32 e1000_setup_copper_link_pch_lpt(struct e1000_hw *hw); +static s32 e1000_oem_bits_config_ich8lan(struct e1000_hw *hw, bool d0_state); static inline u16 __er16flash(struct e1000_hw *hw, unsigned long reg) { @@ -239,6 +242,47 @@ out: } /** + * e1000_toggle_lanphypc_pch_lpt - toggle the LANPHYPC pin value + * @hw: pointer to the HW structure + * + * Toggling the LANPHYPC pin value fully power-cycles the PHY and is + * used to reset the PHY to a quiescent state when necessary. + **/ +static void e1000_toggle_lanphypc_pch_lpt(struct e1000_hw *hw) +{ + u32 mac_reg; + + /* Set Phy Config Counter to 50msec */ + mac_reg = er32(FEXTNVM3); + mac_reg &= ~E1000_FEXTNVM3_PHY_CFG_COUNTER_MASK; + mac_reg |= E1000_FEXTNVM3_PHY_CFG_COUNTER_50MSEC; + ew32(FEXTNVM3, mac_reg); + + /* Toggle LANPHYPC Value bit */ + mac_reg = er32(CTRL); + mac_reg |= E1000_CTRL_LANPHYPC_OVERRIDE; + mac_reg &= ~E1000_CTRL_LANPHYPC_VALUE; + ew32(CTRL, mac_reg); + e1e_flush(); + usleep_range(10, 20); + mac_reg &= ~E1000_CTRL_LANPHYPC_OVERRIDE; + ew32(CTRL, mac_reg); + e1e_flush(); + + if (hw->mac.type < e1000_pch_lpt) { + msleep(50); + } else { + u16 count = 20; + + do { + usleep_range(5000, 10000); + } while (!(er32(CTRL_EXT) & E1000_CTRL_EXT_LPCD) && count--); + + msleep(30); + } +} + +/** * e1000_init_phy_workarounds_pchlan - PHY initialization workarounds * @hw: pointer to the HW structure * @@ -247,6 +291,7 @@ out: **/ static s32 e1000_init_phy_workarounds_pchlan(struct e1000_hw *hw) { + struct e1000_adapter *adapter = hw->adapter; u32 mac_reg, fwsm = er32(FWSM); s32 ret_val; @@ -255,6 +300,12 @@ static s32 e1000_init_phy_workarounds_pchlan(struct e1000_hw *hw) */ e1000_gate_hw_phy_config_ich8lan(hw, true); + /* It is not possible to be certain of the current state of ULP + * so forcibly disable it. + */ + hw->dev_spec.ich8lan.ulp_state = e1000_ulp_state_unknown; + e1000_disable_ulp_lpt_lp(hw, true); + ret_val = hw->phy.ops.acquire(hw); if (ret_val) { e_dbg("Failed to initialize PHY flow\n"); @@ -300,33 +351,9 @@ static s32 e1000_init_phy_workarounds_pchlan(struct e1000_hw *hw) break; } - e_dbg("Toggling LANPHYPC\n"); - - /* Set Phy Config Counter to 50msec */ - mac_reg = er32(FEXTNVM3); - mac_reg &= ~E1000_FEXTNVM3_PHY_CFG_COUNTER_MASK; - mac_reg |= E1000_FEXTNVM3_PHY_CFG_COUNTER_50MSEC; - ew32(FEXTNVM3, mac_reg); - /* Toggle LANPHYPC Value bit */ - mac_reg = er32(CTRL); - mac_reg |= E1000_CTRL_LANPHYPC_OVERRIDE; - mac_reg &= ~E1000_CTRL_LANPHYPC_VALUE; - ew32(CTRL, mac_reg); - e1e_flush(); - usleep_range(10, 20); - mac_reg &= ~E1000_CTRL_LANPHYPC_OVERRIDE; - ew32(CTRL, mac_reg); - e1e_flush(); - if (hw->mac.type < e1000_pch_lpt) { - msleep(50); - } else { - u16 count = 20; - do { - usleep_range(5000, 10000); - } while (!(er32(CTRL_EXT) & - E1000_CTRL_EXT_LPCD) && count--); - usleep_range(30000, 60000); + e1000_toggle_lanphypc_pch_lpt(hw); + if (hw->mac.type >= e1000_pch_lpt) { if (e1000_phy_is_accessible_pchlan(hw)) break; @@ -349,12 +376,31 @@ static s32 e1000_init_phy_workarounds_pchlan(struct e1000_hw *hw) hw->phy.ops.release(hw); if (!ret_val) { + + /* Check to see if able to reset PHY. Print error if not */ + if (hw->phy.ops.check_reset_block(hw)) { + e_err("Reset blocked by ME\n"); + goto out; + } + /* Reset the PHY before any access to it. Doing so, ensures * that the PHY is in a known good state before we read/write * PHY registers. The generic reset is sufficient here, * because we haven't determined the PHY type yet. */ ret_val = e1000e_phy_hw_reset_generic(hw); + if (ret_val) + goto out; + + /* On a successful reset, possibly need to wait for the PHY + * to quiesce to an accessible state before returning control + * to the calling function. If the PHY does not quiesce, then + * return E1000E_BLK_PHY_RESET, as this is the condition that + * the PHY is in. + */ + ret_val = hw->phy.ops.check_reset_block(hw); + if (ret_val) + e_err("ME blocked access to PHY after reset\n"); } out: @@ -724,8 +770,14 @@ s32 e1000_write_emi_reg_locked(struct e1000_hw *hw, u16 addr, u16 data) * Enable/disable EEE based on setting in dev_spec structure, the duplex of * the link and the EEE capabilities of the link partner. The LPI Control * register bits will remain set only if/when link is up. + * + * EEE LPI must not be asserted earlier than one second after link is up. + * On 82579, EEE LPI should not be enabled until such time otherwise there + * can be link issues with some switches. Other devices can have EEE LPI + * enabled immediately upon link up since they have a timer in hardware which + * prevents LPI from being asserted too early. **/ -static s32 e1000_set_eee_pchlan(struct e1000_hw *hw) +s32 e1000_set_eee_pchlan(struct e1000_hw *hw) { struct e1000_dev_spec_ich8lan *dev_spec = &hw->dev_spec.ich8lan; s32 ret_val; @@ -979,6 +1031,253 @@ static s32 e1000_platform_pm_pch_lpt(struct e1000_hw *hw, bool link) } /** + * e1000_enable_ulp_lpt_lp - configure Ultra Low Power mode for LynxPoint-LP + * @hw: pointer to the HW structure + * @to_sx: boolean indicating a system power state transition to Sx + * + * When link is down, configure ULP mode to significantly reduce the power + * to the PHY. If on a Manageability Engine (ME) enabled system, tell the + * ME firmware to start the ULP configuration. If not on an ME enabled + * system, configure the ULP mode by software. + */ +s32 e1000_enable_ulp_lpt_lp(struct e1000_hw *hw, bool to_sx) +{ + u32 mac_reg; + s32 ret_val = 0; + u16 phy_reg; + + if ((hw->mac.type < e1000_pch_lpt) || + (hw->adapter->pdev->device == E1000_DEV_ID_PCH_LPT_I217_LM) || + (hw->adapter->pdev->device == E1000_DEV_ID_PCH_LPT_I217_V) || + (hw->adapter->pdev->device == E1000_DEV_ID_PCH_I218_LM2) || + (hw->adapter->pdev->device == E1000_DEV_ID_PCH_I218_V2) || + (hw->dev_spec.ich8lan.ulp_state == e1000_ulp_state_on)) + return 0; + + if (er32(FWSM) & E1000_ICH_FWSM_FW_VALID) { + /* Request ME configure ULP mode in the PHY */ + mac_reg = er32(H2ME); + mac_reg |= E1000_H2ME_ULP | E1000_H2ME_ENFORCE_SETTINGS; + ew32(H2ME, mac_reg); + + goto out; + } + + if (!to_sx) { + int i = 0; + + /* Poll up to 5 seconds for Cable Disconnected indication */ + while (!(er32(FEXT) & E1000_FEXT_PHY_CABLE_DISCONNECTED)) { + /* Bail if link is re-acquired */ + if (er32(STATUS) & E1000_STATUS_LU) + return -E1000_ERR_PHY; + + if (i++ == 100) + break; + + msleep(50); + } + e_dbg("CABLE_DISCONNECTED %s set after %dmsec\n", + (er32(FEXT) & + E1000_FEXT_PHY_CABLE_DISCONNECTED) ? "" : "not", i * 50); + } + + ret_val = hw->phy.ops.acquire(hw); + if (ret_val) + goto out; + + /* Force SMBus mode in PHY */ + ret_val = e1000_read_phy_reg_hv_locked(hw, CV_SMB_CTRL, &phy_reg); + if (ret_val) + goto release; + phy_reg |= CV_SMB_CTRL_FORCE_SMBUS; + e1000_write_phy_reg_hv_locked(hw, CV_SMB_CTRL, phy_reg); + + /* Force SMBus mode in MAC */ + mac_reg = er32(CTRL_EXT); + mac_reg |= E1000_CTRL_EXT_FORCE_SMBUS; + ew32(CTRL_EXT, mac_reg); + + /* Set Inband ULP Exit, Reset to SMBus mode and + * Disable SMBus Release on PERST# in PHY + */ + ret_val = e1000_read_phy_reg_hv_locked(hw, I218_ULP_CONFIG1, &phy_reg); + if (ret_val) + goto release; + phy_reg |= (I218_ULP_CONFIG1_RESET_TO_SMBUS | + I218_ULP_CONFIG1_DISABLE_SMB_PERST); + if (to_sx) { + if (er32(WUFC) & E1000_WUFC_LNKC) + phy_reg |= I218_ULP_CONFIG1_WOL_HOST; + + phy_reg |= I218_ULP_CONFIG1_STICKY_ULP; + } else { + phy_reg |= I218_ULP_CONFIG1_INBAND_EXIT; + } + e1000_write_phy_reg_hv_locked(hw, I218_ULP_CONFIG1, phy_reg); + + /* Set Disable SMBus Release on PERST# in MAC */ + mac_reg = er32(FEXTNVM7); + mac_reg |= E1000_FEXTNVM7_DISABLE_SMB_PERST; + ew32(FEXTNVM7, mac_reg); + + /* Commit ULP changes in PHY by starting auto ULP configuration */ + phy_reg |= I218_ULP_CONFIG1_START; + e1000_write_phy_reg_hv_locked(hw, I218_ULP_CONFIG1, phy_reg); +release: + hw->phy.ops.release(hw); +out: + if (ret_val) + e_dbg("Error in ULP enable flow: %d\n", ret_val); + else + hw->dev_spec.ich8lan.ulp_state = e1000_ulp_state_on; + + return ret_val; +} + +/** + * e1000_disable_ulp_lpt_lp - unconfigure Ultra Low Power mode for LynxPoint-LP + * @hw: pointer to the HW structure + * @force: boolean indicating whether or not to force disabling ULP + * + * Un-configure ULP mode when link is up, the system is transitioned from + * Sx or the driver is unloaded. If on a Manageability Engine (ME) enabled + * system, poll for an indication from ME that ULP has been un-configured. + * If not on an ME enabled system, un-configure the ULP mode by software. + * + * During nominal operation, this function is called when link is acquired + * to disable ULP mode (force=false); otherwise, for example when unloading + * the driver or during Sx->S0 transitions, this is called with force=true + * to forcibly disable ULP. + */ +static s32 e1000_disable_ulp_lpt_lp(struct e1000_hw *hw, bool force) +{ + s32 ret_val = 0; + u32 mac_reg; + u16 phy_reg; + int i = 0; + + if ((hw->mac.type < e1000_pch_lpt) || + (hw->adapter->pdev->device == E1000_DEV_ID_PCH_LPT_I217_LM) || + (hw->adapter->pdev->device == E1000_DEV_ID_PCH_LPT_I217_V) || + (hw->adapter->pdev->device == E1000_DEV_ID_PCH_I218_LM2) || + (hw->adapter->pdev->device == E1000_DEV_ID_PCH_I218_V2) || + (hw->dev_spec.ich8lan.ulp_state == e1000_ulp_state_off)) + return 0; + + if (er32(FWSM) & E1000_ICH_FWSM_FW_VALID) { + if (force) { + /* Request ME un-configure ULP mode in the PHY */ + mac_reg = er32(H2ME); + mac_reg &= ~E1000_H2ME_ULP; + mac_reg |= E1000_H2ME_ENFORCE_SETTINGS; + ew32(H2ME, mac_reg); + } + + /* Poll up to 100msec for ME to clear ULP_CFG_DONE */ + while (er32(FWSM) & E1000_FWSM_ULP_CFG_DONE) { + if (i++ == 10) { + ret_val = -E1000_ERR_PHY; + goto out; + } + + usleep_range(10000, 20000); + } + e_dbg("ULP_CONFIG_DONE cleared after %dmsec\n", i * 10); + + if (force) { + mac_reg = er32(H2ME); + mac_reg &= ~E1000_H2ME_ENFORCE_SETTINGS; + ew32(H2ME, mac_reg); + } else { + /* Clear H2ME.ULP after ME ULP configuration */ + mac_reg = er32(H2ME); + mac_reg &= ~E1000_H2ME_ULP; + ew32(H2ME, mac_reg); + } + + goto out; + } + + ret_val = hw->phy.ops.acquire(hw); + if (ret_val) + goto out; + + if (force) + /* Toggle LANPHYPC Value bit */ + e1000_toggle_lanphypc_pch_lpt(hw); + + /* Unforce SMBus mode in PHY */ + ret_val = e1000_read_phy_reg_hv_locked(hw, CV_SMB_CTRL, &phy_reg); + if (ret_val) { + /* The MAC might be in PCIe mode, so temporarily force to + * SMBus mode in order to access the PHY. + */ + mac_reg = er32(CTRL_EXT); + mac_reg |= E1000_CTRL_EXT_FORCE_SMBUS; + ew32(CTRL_EXT, mac_reg); + + msleep(50); + + ret_val = e1000_read_phy_reg_hv_locked(hw, CV_SMB_CTRL, + &phy_reg); + if (ret_val) + goto release; + } + phy_reg &= ~CV_SMB_CTRL_FORCE_SMBUS; + e1000_write_phy_reg_hv_locked(hw, CV_SMB_CTRL, phy_reg); + + /* Unforce SMBus mode in MAC */ + mac_reg = er32(CTRL_EXT); + mac_reg &= ~E1000_CTRL_EXT_FORCE_SMBUS; + ew32(CTRL_EXT, mac_reg); + + /* When ULP mode was previously entered, K1 was disabled by the + * hardware. Re-Enable K1 in the PHY when exiting ULP. + */ + ret_val = e1000_read_phy_reg_hv_locked(hw, HV_PM_CTRL, &phy_reg); + if (ret_val) + goto release; + phy_reg |= HV_PM_CTRL_K1_ENABLE; + e1000_write_phy_reg_hv_locked(hw, HV_PM_CTRL, phy_reg); + + /* Clear ULP enabled configuration */ + ret_val = e1000_read_phy_reg_hv_locked(hw, I218_ULP_CONFIG1, &phy_reg); + if (ret_val) + goto release; + phy_reg &= ~(I218_ULP_CONFIG1_IND | + I218_ULP_CONFIG1_STICKY_ULP | + I218_ULP_CONFIG1_RESET_TO_SMBUS | + I218_ULP_CONFIG1_WOL_HOST | + I218_ULP_CONFIG1_INBAND_EXIT | + I218_ULP_CONFIG1_DISABLE_SMB_PERST); + e1000_write_phy_reg_hv_locked(hw, I218_ULP_CONFIG1, phy_reg); + + /* Commit ULP changes by starting auto ULP configuration */ + phy_reg |= I218_ULP_CONFIG1_START; + e1000_write_phy_reg_hv_locked(hw, I218_ULP_CONFIG1, phy_reg); + + /* Clear Disable SMBus Release on PERST# in MAC */ + mac_reg = er32(FEXTNVM7); + mac_reg &= ~E1000_FEXTNVM7_DISABLE_SMB_PERST; + ew32(FEXTNVM7, mac_reg); + +release: + hw->phy.ops.release(hw); + if (force) { + e1000_phy_hw_reset(hw); + msleep(50); + } +out: + if (ret_val) + e_dbg("Error in ULP disable flow: %d\n", ret_val); + else + hw->dev_spec.ich8lan.ulp_state = e1000_ulp_state_off; + + return ret_val; +} + +/** * e1000_check_for_copper_link_ich8lan - Check for link (Copper) * @hw: pointer to the HW structure * @@ -1106,9 +1405,11 @@ static s32 e1000_check_for_copper_link_ich8lan(struct e1000_hw *hw) e1000e_check_downshift(hw); /* Enable/Disable EEE after link up */ - ret_val = e1000_set_eee_pchlan(hw); - if (ret_val) - return ret_val; + if (hw->phy.type > e1000_phy_82579) { + ret_val = e1000_set_eee_pchlan(hw); + if (ret_val) + return ret_val; + } /* If we are forcing speed/duplex, then we simply return since * we have already determined whether we have link or not. @@ -1374,7 +1675,7 @@ static void e1000_rar_set_pch2lan(struct e1000_hw *hw, u8 *addr, u32 index) /* RAR[1-6] are owned by manageability. Skip those and program the * next address into the SHRA register array. */ - if (index < (u32)(hw->mac.rar_entry_count - 6)) { + if (index < (u32)(hw->mac.rar_entry_count)) { s32 ret_val; ret_val = e1000_acquire_swflag_ich8lan(hw); @@ -1484,11 +1785,13 @@ out: **/ static s32 e1000_check_reset_block_ich8lan(struct e1000_hw *hw) { - u32 fwsm; + bool blocked = false; + int i = 0; - fwsm = er32(FWSM); - - return (fwsm & E1000_ICH_FWSM_RSPCIPHY) ? 0 : E1000_BLK_PHY_RESET; + while ((blocked = !(er32(FWSM) & E1000_ICH_FWSM_RSPCIPHY)) && + (i++ < 10)) + usleep_range(10000, 20000); + return blocked ? E1000_BLK_PHY_RESET : 0; } /** diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.h b/drivers/net/ethernet/intel/e1000e/ich8lan.h index 217090df33e7..bead50f9187b 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.h +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.h @@ -1,30 +1,23 @@ -/******************************************************************************* - - Intel PRO/1000 Linux driver - Copyright(c) 1999 - 2013 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +/* Intel PRO/1000 Linux driver + * Copyright(c) 1999 - 2014 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + * Contact Information: + * Linux NICS <linux.nics@intel.com> + * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> + * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 + */ #ifndef _E1000E_ICH8LAN_H_ #define _E1000E_ICH8LAN_H_ @@ -65,11 +58,16 @@ #define E1000_FWSM_WLOCK_MAC_MASK 0x0380 #define E1000_FWSM_WLOCK_MAC_SHIFT 7 +#define E1000_FWSM_ULP_CFG_DONE 0x00000400 /* Low power cfg done */ /* Shared Receive Address Registers */ #define E1000_SHRAL_PCH_LPT(_i) (0x05408 + ((_i) * 8)) #define E1000_SHRAH_PCH_LPT(_i) (0x0540C + ((_i) * 8)) +#define E1000_H2ME 0x05B50 /* Host to ME */ +#define E1000_H2ME_ULP 0x00000800 /* ULP Indication Bit */ +#define E1000_H2ME_ENFORCE_SETTINGS 0x00001000 /* Enforce Settings */ + #define ID_LED_DEFAULT_ICH8LAN ((ID_LED_DEF1_DEF2 << 12) | \ (ID_LED_OFF1_OFF2 << 8) | \ (ID_LED_OFF1_ON2 << 4) | \ @@ -82,6 +80,9 @@ #define E1000_ICH8_LAN_INIT_TIMEOUT 1500 +/* FEXT register bit definition */ +#define E1000_FEXT_PHY_CABLE_DISCONNECTED 0x00000004 + #define E1000_FEXTNVM_SW_CONFIG 1 #define E1000_FEXTNVM_SW_CONFIG_ICH8M (1 << 27) /* different on ICH8M */ @@ -95,10 +96,12 @@ #define E1000_FEXTNVM6_REQ_PLL_CLK 0x00000100 #define E1000_FEXTNVM6_ENABLE_K1_ENTRY_CONDITION 0x00000200 +#define E1000_FEXTNVM7_DISABLE_SMB_PERST 0x00000020 + #define PCIE_ICH8_SNOOP_ALL PCIE_NO_SNOOP_ALL #define E1000_ICH_RAR_ENTRIES 7 -#define E1000_PCH2_RAR_ENTRIES 11 /* RAR[0-6], SHRA[0-3] */ +#define E1000_PCH2_RAR_ENTRIES 5 /* RAR[0], SHRA[0-3] */ #define E1000_PCH_LPT_RAR_ENTRIES 12 /* RAR[0], SHRA[0-10] */ #define PHY_PAGE_SHIFT 5 @@ -161,6 +164,16 @@ #define CV_SMB_CTRL PHY_REG(769, 23) #define CV_SMB_CTRL_FORCE_SMBUS 0x0001 +/* I218 Ultra Low Power Configuration 1 Register */ +#define I218_ULP_CONFIG1 PHY_REG(779, 16) +#define I218_ULP_CONFIG1_START 0x0001 /* Start auto ULP config */ +#define I218_ULP_CONFIG1_IND 0x0004 /* Pwr up from ULP indication */ +#define I218_ULP_CONFIG1_STICKY_ULP 0x0010 /* Set sticky ULP mode */ +#define I218_ULP_CONFIG1_INBAND_EXIT 0x0020 /* Inband on ULP exit */ +#define I218_ULP_CONFIG1_WOL_HOST 0x0040 /* WoL Host on ULP exit */ +#define I218_ULP_CONFIG1_RESET_TO_SMBUS 0x0100 /* Reset to SMBus mode */ +#define I218_ULP_CONFIG1_DISABLE_SMB_PERST 0x1000 /* Disable on PERST# */ + /* SMBus Address Phy Register */ #define HV_SMB_ADDR PHY_REG(768, 26) #define HV_SMB_ADDR_MASK 0x007F @@ -195,6 +208,7 @@ /* PHY Power Management Control */ #define HV_PM_CTRL PHY_REG(770, 17) #define HV_PM_CTRL_PLL_STOP_IN_K1_GIGA 0x100 +#define HV_PM_CTRL_K1_ENABLE 0x4000 #define SW_FLAG_TIMEOUT 1000 /* SW Semaphore flag timeout in ms */ @@ -268,4 +282,6 @@ void e1000_copy_rx_addrs_to_phy_ich8lan(struct e1000_hw *hw); s32 e1000_lv_jumbo_workaround_ich8lan(struct e1000_hw *hw, bool enable); s32 e1000_read_emi_reg_locked(struct e1000_hw *hw, u16 addr, u16 *data); s32 e1000_write_emi_reg_locked(struct e1000_hw *hw, u16 addr, u16 data); +s32 e1000_set_eee_pchlan(struct e1000_hw *hw); +s32 e1000_enable_ulp_lpt_lp(struct e1000_hw *hw, bool to_sx); #endif /* _E1000E_ICH8LAN_H_ */ diff --git a/drivers/net/ethernet/intel/e1000e/mac.c b/drivers/net/ethernet/intel/e1000e/mac.c index 2480c1091873..baa0a466d1d0 100644 --- a/drivers/net/ethernet/intel/e1000e/mac.c +++ b/drivers/net/ethernet/intel/e1000e/mac.c @@ -1,30 +1,23 @@ -/******************************************************************************* - - Intel PRO/1000 Linux driver - Copyright(c) 1999 - 2013 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +/* Intel PRO/1000 Linux driver + * Copyright(c) 1999 - 2014 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + * Contact Information: + * Linux NICS <linux.nics@intel.com> + * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> + * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 + */ #include "e1000.h" diff --git a/drivers/net/ethernet/intel/e1000e/mac.h b/drivers/net/ethernet/intel/e1000e/mac.h index a61fee404ebe..4e81c2825b7a 100644 --- a/drivers/net/ethernet/intel/e1000e/mac.h +++ b/drivers/net/ethernet/intel/e1000e/mac.h @@ -1,30 +1,23 @@ -/******************************************************************************* - - Intel PRO/1000 Linux driver - Copyright(c) 1999 - 2013 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +/* Intel PRO/1000 Linux driver + * Copyright(c) 1999 - 2014 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + * Contact Information: + * Linux NICS <linux.nics@intel.com> + * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> + * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 + */ #ifndef _E1000E_MAC_H_ #define _E1000E_MAC_H_ diff --git a/drivers/net/ethernet/intel/e1000e/manage.c b/drivers/net/ethernet/intel/e1000e/manage.c index e4b0f1ef92f6..cb37ff1f1321 100644 --- a/drivers/net/ethernet/intel/e1000e/manage.c +++ b/drivers/net/ethernet/intel/e1000e/manage.c @@ -1,30 +1,23 @@ -/******************************************************************************* - - Intel PRO/1000 Linux driver - Copyright(c) 1999 - 2013 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +/* Intel PRO/1000 Linux driver + * Copyright(c) 1999 - 2014 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + * Contact Information: + * Linux NICS <linux.nics@intel.com> + * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> + * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 + */ #include "e1000.h" diff --git a/drivers/net/ethernet/intel/e1000e/manage.h b/drivers/net/ethernet/intel/e1000e/manage.h index 326897c29ea8..a8c27f98f7b0 100644 --- a/drivers/net/ethernet/intel/e1000e/manage.h +++ b/drivers/net/ethernet/intel/e1000e/manage.h @@ -1,30 +1,23 @@ -/******************************************************************************* - - Intel PRO/1000 Linux driver - Copyright(c) 1999 - 2013 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +/* Intel PRO/1000 Linux driver + * Copyright(c) 1999 - 2014 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + * Contact Information: + * Linux NICS <linux.nics@intel.com> + * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> + * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 + */ #ifndef _E1000E_MANAGE_H_ #define _E1000E_MANAGE_H_ diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 6d91933c4cdd..5129c4cd14bc 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -1,30 +1,23 @@ -/******************************************************************************* - - Intel PRO/1000 Linux driver - Copyright(c) 1999 - 2013 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +/* Intel PRO/1000 Linux driver + * Copyright(c) 1999 - 2014 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + * Contact Information: + * Linux NICS <linux.nics@intel.com> + * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> + * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 + */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt @@ -1701,7 +1694,7 @@ static void e1000_clean_rx_ring(struct e1000_ring *rx_ring) adapter->flags2 &= ~FLAG2_IS_DISCARDING; writel(0, rx_ring->head); - if (rx_ring->adapter->flags2 & FLAG2_PCIM2PCI_ARBITER_WA) + if (adapter->flags2 & FLAG2_PCIM2PCI_ARBITER_WA) e1000e_update_rdt_wa(rx_ring, 0); else writel(0, rx_ring->tail); @@ -2038,13 +2031,16 @@ void e1000e_set_interrupt_capability(struct e1000_adapter *adapter) msix_entry), GFP_KERNEL); if (adapter->msix_entries) { + struct e1000_adapter *a = adapter; + for (i = 0; i < adapter->num_vectors; i++) adapter->msix_entries[i].entry = i; - err = pci_enable_msix(adapter->pdev, - adapter->msix_entries, - adapter->num_vectors); - if (err == 0) + err = pci_enable_msix_range(a->pdev, + a->msix_entries, + a->num_vectors, + a->num_vectors); + if (err > 0) return; } /* MSI-X failed, so fall through and try MSI */ @@ -2402,7 +2398,7 @@ static void e1000_clean_tx_ring(struct e1000_ring *tx_ring) tx_ring->next_to_clean = 0; writel(0, tx_ring->head); - if (tx_ring->adapter->flags2 & FLAG2_PCIM2PCI_ARBITER_WA) + if (adapter->flags2 & FLAG2_PCIM2PCI_ARBITER_WA) e1000e_update_tdt_wa(tx_ring, 0); else writel(0, tx_ring->tail); @@ -3331,6 +3327,9 @@ static void e1000e_set_rx_mode(struct net_device *netdev) struct e1000_hw *hw = &adapter->hw; u32 rctl; + if (pm_runtime_suspended(netdev->dev.parent)) + return; + /* Check for Promiscuous and All Multicast modes */ rctl = er32(RCTL); @@ -3691,10 +3690,6 @@ void e1000e_power_up_phy(struct e1000_adapter *adapter) */ static void e1000_power_down_phy(struct e1000_adapter *adapter) { - /* WoL is enabled */ - if (adapter->wol) - return; - if (adapter->hw.phy.ops.power_down) adapter->hw.phy.ops.power_down(&adapter->hw); } @@ -3911,10 +3906,8 @@ void e1000e_reset(struct e1000_adapter *adapter) } if (!netif_running(adapter->netdev) && - !test_bit(__E1000_TESTING, &adapter->state)) { + !test_bit(__E1000_TESTING, &adapter->state)) e1000_power_down_phy(adapter); - return; - } e1000_get_phy_info(hw); @@ -3981,7 +3974,12 @@ static void e1000e_flush_descriptors(struct e1000_adapter *adapter) static void e1000e_update_stats(struct e1000_adapter *adapter); -void e1000e_down(struct e1000_adapter *adapter) +/** + * e1000e_down - quiesce the device and optionally reset the hardware + * @adapter: board private structure + * @reset: boolean flag to reset the hardware or not + */ +void e1000e_down(struct e1000_adapter *adapter, bool reset) { struct net_device *netdev = adapter->netdev; struct e1000_hw *hw = &adapter->hw; @@ -4035,12 +4033,8 @@ void e1000e_down(struct e1000_adapter *adapter) e1000_lv_jumbo_workaround_ich8lan(hw, false)) e_dbg("failed to disable jumbo frame workaround mode\n"); - if (!pci_channel_offline(adapter->pdev)) + if (reset && !pci_channel_offline(adapter->pdev)) e1000e_reset(adapter); - - /* TODO: for power management, we could drop the link and - * pci_disable_device here. - */ } void e1000e_reinit_locked(struct e1000_adapter *adapter) @@ -4048,7 +4042,7 @@ void e1000e_reinit_locked(struct e1000_adapter *adapter) might_sleep(); while (test_and_set_bit(__E1000_RESETTING, &adapter->state)) usleep_range(1000, 2000); - e1000e_down(adapter); + e1000e_down(adapter, true); e1000e_up(adapter); clear_bit(__E1000_RESETTING, &adapter->state); } @@ -4326,7 +4320,6 @@ static int e1000_open(struct net_device *netdev) adapter->tx_hang_recheck = false; netif_start_queue(netdev); - adapter->idle_check = true; hw->mac.get_link_status = true; pm_runtime_put(&pdev->dev); @@ -4376,14 +4369,15 @@ static int e1000_close(struct net_device *netdev) pm_runtime_get_sync(&pdev->dev); if (!test_bit(__E1000_DOWN, &adapter->state)) { - e1000e_down(adapter); + e1000e_down(adapter, true); e1000_free_irq(adapter); + + /* Link status message must follow this format */ + pr_info("%s NIC Link is Down\n", adapter->netdev->name); } napi_disable(&adapter->napi); - e1000_power_down_phy(adapter); - e1000e_free_tx_resources(adapter->tx_ring); e1000e_free_rx_resources(adapter->rx_ring); @@ -4460,11 +4454,16 @@ static void e1000e_update_phy_task(struct work_struct *work) struct e1000_adapter *adapter = container_of(work, struct e1000_adapter, update_phy_task); + struct e1000_hw *hw = &adapter->hw; if (test_bit(__E1000_DOWN, &adapter->state)) return; - e1000_get_phy_info(&adapter->hw); + e1000_get_phy_info(hw); + + /* Enable EEE on 82579 after link up */ + if (hw->phy.type == e1000_phy_82579) + e1000_set_eee_pchlan(hw); } /** @@ -5684,8 +5683,11 @@ static int e1000_change_mtu(struct net_device *netdev, int new_mtu) adapter->max_frame_size = max_frame; e_info("changing MTU from %d to %d\n", netdev->mtu, new_mtu); netdev->mtu = new_mtu; + + pm_runtime_get_sync(netdev->dev.parent); + if (netif_running(netdev)) - e1000e_down(adapter); + e1000e_down(adapter, true); /* NOTE: netdev_alloc_skb reserves 16 bytes, and typically NET_IP_ALIGN * means we reserve 2 more, this pushes us to allocate from the next @@ -5711,6 +5713,8 @@ static int e1000_change_mtu(struct net_device *netdev, int new_mtu) else e1000e_reset(adapter); + pm_runtime_put_sync(netdev->dev.parent); + clear_bit(__E1000_RESETTING, &adapter->state); return 0; @@ -5852,7 +5856,7 @@ static int e1000_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) static int e1000_init_phy_wakeup(struct e1000_adapter *adapter, u32 wufc) { struct e1000_hw *hw = &adapter->hw; - u32 i, mac_reg; + u32 i, mac_reg, wuc; u16 phy_reg, wuc_enable; int retval; @@ -5899,13 +5903,18 @@ static int e1000_init_phy_wakeup(struct e1000_adapter *adapter, u32 wufc) phy_reg |= BM_RCTL_RFCE; hw->phy.ops.write_reg_page(&adapter->hw, BM_RCTL, phy_reg); + wuc = E1000_WUC_PME_EN; + if (wufc & (E1000_WUFC_MAG | E1000_WUFC_LNKC)) + wuc |= E1000_WUC_APME; + /* enable PHY wakeup in MAC register */ ew32(WUFC, wufc); - ew32(WUC, E1000_WUC_PHY_WAKE | E1000_WUC_PME_EN); + ew32(WUC, (E1000_WUC_PHY_WAKE | E1000_WUC_APMPME | + E1000_WUC_PME_STATUS | wuc)); /* configure and enable PHY wakeup in PHY registers */ hw->phy.ops.write_reg_page(&adapter->hw, BM_WUFC, wufc); - hw->phy.ops.write_reg_page(&adapter->hw, BM_WUC, E1000_WUC_PME_EN); + hw->phy.ops.write_reg_page(&adapter->hw, BM_WUC, wuc); /* activate PHY wakeup */ wuc_enable |= BM_WUC_ENABLE_BIT | BM_WUC_HOST_WU_BIT; @@ -5918,15 +5927,10 @@ release: return retval; } -static int __e1000_shutdown(struct pci_dev *pdev, bool runtime) +static int e1000e_pm_freeze(struct device *dev) { - struct net_device *netdev = pci_get_drvdata(pdev); + struct net_device *netdev = pci_get_drvdata(to_pci_dev(dev)); struct e1000_adapter *adapter = netdev_priv(netdev); - struct e1000_hw *hw = &adapter->hw; - u32 ctrl, ctrl_ext, rctl, status; - /* Runtime suspend should only enable wakeup for link changes */ - u32 wufc = runtime ? E1000_WUFC_LNKC : adapter->wol; - int retval = 0; netif_device_detach(netdev); @@ -5937,11 +5941,29 @@ static int __e1000_shutdown(struct pci_dev *pdev, bool runtime) usleep_range(10000, 20000); WARN_ON(test_bit(__E1000_RESETTING, &adapter->state)); - e1000e_down(adapter); + + /* Quiesce the device without resetting the hardware */ + e1000e_down(adapter, false); e1000_free_irq(adapter); } e1000e_reset_interrupt_capability(adapter); + /* Allow time for pending master requests to run */ + e1000e_disable_pcie_master(&adapter->hw); + + return 0; +} + +static int __e1000_shutdown(struct pci_dev *pdev, bool runtime) +{ + struct net_device *netdev = pci_get_drvdata(pdev); + struct e1000_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; + u32 ctrl, ctrl_ext, rctl, status; + /* Runtime suspend should only enable wakeup for link changes */ + u32 wufc = runtime ? E1000_WUFC_LNKC : adapter->wol; + int retval = 0; + status = er32(STATUS); if (status & E1000_STATUS_LU) wufc &= ~E1000_WUFC_LNKC; @@ -5972,12 +5994,12 @@ static int __e1000_shutdown(struct pci_dev *pdev, bool runtime) ew32(CTRL_EXT, ctrl_ext); } + if (!runtime) + e1000e_power_up_phy(adapter); + if (adapter->flags & FLAG_IS_ICH) e1000_suspend_workarounds_ich8lan(&adapter->hw); - /* Allow time for pending master requests to run */ - e1000e_disable_pcie_master(&adapter->hw); - if (adapter->flags2 & FLAG2_HAS_PHY_WAKEUP) { /* enable wakeup by the PHY */ retval = e1000_init_phy_wakeup(adapter, wufc); @@ -5991,10 +6013,23 @@ static int __e1000_shutdown(struct pci_dev *pdev, bool runtime) } else { ew32(WUC, 0); ew32(WUFC, 0); + + e1000_power_down_phy(adapter); } - if (adapter->hw.phy.type == e1000_phy_igp_3) + if (adapter->hw.phy.type == e1000_phy_igp_3) { e1000e_igp3_phy_powerdown_workaround_ich8lan(&adapter->hw); + } else if (hw->mac.type == e1000_pch_lpt) { + if (!(wufc & (E1000_WUFC_EX | E1000_WUFC_MC | E1000_WUFC_BC))) + /* ULP does not support wake from unicast, multicast + * or broadcast. + */ + retval = e1000_enable_ulp_lpt_lp(hw, !runtime); + + if (retval) + return retval; + } + /* Release control of h/w to f/w. If f/w is AMT enabled, this * would have already happened in close and is redundant. @@ -6102,18 +6137,12 @@ static void e1000e_disable_aspm(struct pci_dev *pdev, u16 state) } #ifdef CONFIG_PM -static bool e1000e_pm_ready(struct e1000_adapter *adapter) -{ - return !!adapter->tx_ring->buffer_info; -} - static int __e1000_resume(struct pci_dev *pdev) { struct net_device *netdev = pci_get_drvdata(pdev); struct e1000_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; u16 aspm_disable_flag = 0; - u32 err; if (adapter->flags2 & FLAG2_DISABLE_ASPM_L0S) aspm_disable_flag = PCIE_LINK_STATE_L0S; @@ -6124,13 +6153,6 @@ static int __e1000_resume(struct pci_dev *pdev) pci_set_master(pdev); - e1000e_set_interrupt_capability(adapter); - if (netif_running(netdev)) { - err = e1000_request_irq(adapter); - if (err) - return err; - } - if (hw->mac.type >= e1000_pch2lan) e1000_resume_workarounds_pchlan(&adapter->hw); @@ -6169,11 +6191,6 @@ static int __e1000_resume(struct pci_dev *pdev) e1000_init_manageability_pt(adapter); - if (netif_running(netdev)) - e1000e_up(adapter); - - netif_device_attach(netdev); - /* If the controller has AMT, do not set DRV_LOAD until the interface * is up. For all other cases, let the f/w know that the h/w is now * under the control of the driver. @@ -6184,75 +6201,111 @@ static int __e1000_resume(struct pci_dev *pdev) return 0; } +static int e1000e_pm_thaw(struct device *dev) +{ + struct net_device *netdev = pci_get_drvdata(to_pci_dev(dev)); + struct e1000_adapter *adapter = netdev_priv(netdev); + + e1000e_set_interrupt_capability(adapter); + if (netif_running(netdev)) { + u32 err = e1000_request_irq(adapter); + + if (err) + return err; + + e1000e_up(adapter); + } + + netif_device_attach(netdev); + + return 0; +} + #ifdef CONFIG_PM_SLEEP -static int e1000_suspend(struct device *dev) +static int e1000e_pm_suspend(struct device *dev) { struct pci_dev *pdev = to_pci_dev(dev); + e1000e_pm_freeze(dev); + return __e1000_shutdown(pdev, false); } -static int e1000_resume(struct device *dev) +static int e1000e_pm_resume(struct device *dev) { struct pci_dev *pdev = to_pci_dev(dev); - struct net_device *netdev = pci_get_drvdata(pdev); - struct e1000_adapter *adapter = netdev_priv(netdev); + int rc; - if (e1000e_pm_ready(adapter)) - adapter->idle_check = true; + rc = __e1000_resume(pdev); + if (rc) + return rc; - return __e1000_resume(pdev); + return e1000e_pm_thaw(dev); } #endif /* CONFIG_PM_SLEEP */ #ifdef CONFIG_PM_RUNTIME -static int e1000_runtime_suspend(struct device *dev) +static int e1000e_pm_runtime_idle(struct device *dev) { struct pci_dev *pdev = to_pci_dev(dev); struct net_device *netdev = pci_get_drvdata(pdev); struct e1000_adapter *adapter = netdev_priv(netdev); - if (!e1000e_pm_ready(adapter)) - return 0; + if (!e1000e_has_link(adapter)) + pm_schedule_suspend(dev, 5 * MSEC_PER_SEC); - return __e1000_shutdown(pdev, true); + return -EBUSY; } -static int e1000_idle(struct device *dev) +static int e1000e_pm_runtime_resume(struct device *dev) { struct pci_dev *pdev = to_pci_dev(dev); struct net_device *netdev = pci_get_drvdata(pdev); struct e1000_adapter *adapter = netdev_priv(netdev); + int rc; - if (!e1000e_pm_ready(adapter)) - return 0; + rc = __e1000_resume(pdev); + if (rc) + return rc; - if (adapter->idle_check) { - adapter->idle_check = false; - if (!e1000e_has_link(adapter)) - pm_schedule_suspend(dev, MSEC_PER_SEC); - } + if (netdev->flags & IFF_UP) + rc = e1000e_up(adapter); - return -EBUSY; + return rc; } -static int e1000_runtime_resume(struct device *dev) +static int e1000e_pm_runtime_suspend(struct device *dev) { struct pci_dev *pdev = to_pci_dev(dev); struct net_device *netdev = pci_get_drvdata(pdev); struct e1000_adapter *adapter = netdev_priv(netdev); - if (!e1000e_pm_ready(adapter)) - return 0; + if (netdev->flags & IFF_UP) { + int count = E1000_CHECK_RESET_COUNT; + + while (test_bit(__E1000_RESETTING, &adapter->state) && count--) + usleep_range(10000, 20000); + + WARN_ON(test_bit(__E1000_RESETTING, &adapter->state)); + + /* Down the device without resetting the hardware */ + e1000e_down(adapter, false); + } - adapter->idle_check = !dev->power.runtime_auto; - return __e1000_resume(pdev); + if (__e1000_shutdown(pdev, true)) { + e1000e_pm_runtime_resume(dev); + return -EBUSY; + } + + return 0; } #endif /* CONFIG_PM_RUNTIME */ #endif /* CONFIG_PM */ static void e1000_shutdown(struct pci_dev *pdev) { + e1000e_pm_freeze(&pdev->dev); + __e1000_shutdown(pdev, false); } @@ -6338,7 +6391,7 @@ static pci_ers_result_t e1000_io_error_detected(struct pci_dev *pdev, return PCI_ERS_RESULT_DISCONNECT; if (netif_running(netdev)) - e1000e_down(adapter); + e1000e_down(adapter, true); pci_disable_device(pdev); /* Request a slot slot reset. */ @@ -6350,7 +6403,7 @@ static pci_ers_result_t e1000_io_error_detected(struct pci_dev *pdev, * @pdev: Pointer to PCI device * * Restart the card from scratch, as if from a cold-boot. Implementation - * resembles the first-half of the e1000_resume routine. + * resembles the first-half of the e1000e_pm_resume routine. */ static pci_ers_result_t e1000_io_slot_reset(struct pci_dev *pdev) { @@ -6397,7 +6450,7 @@ static pci_ers_result_t e1000_io_slot_reset(struct pci_dev *pdev) * * This callback is called when the error recovery driver tells us that * its OK to resume normal operation. Implementation resembles the - * second-half of the e1000_resume routine. + * second-half of the e1000e_pm_resume routine. */ static void e1000_io_resume(struct pci_dev *pdev) { @@ -6902,9 +6955,6 @@ static void e1000_remove(struct pci_dev *pdev) } } - if (!(netdev->flags & IFF_UP)) - e1000_power_down_phy(adapter); - /* Don't lie to e1000_close() down the road. */ if (!down) clear_bit(__E1000_DOWN, &adapter->state); @@ -7026,9 +7076,14 @@ static DEFINE_PCI_DEVICE_TABLE(e1000_pci_tbl) = { MODULE_DEVICE_TABLE(pci, e1000_pci_tbl); static const struct dev_pm_ops e1000_pm_ops = { - SET_SYSTEM_SLEEP_PM_OPS(e1000_suspend, e1000_resume) - SET_RUNTIME_PM_OPS(e1000_runtime_suspend, e1000_runtime_resume, - e1000_idle) + .suspend = e1000e_pm_suspend, + .resume = e1000e_pm_resume, + .freeze = e1000e_pm_freeze, + .thaw = e1000e_pm_thaw, + .poweroff = e1000e_pm_suspend, + .restore = e1000e_pm_resume, + SET_RUNTIME_PM_OPS(e1000e_pm_runtime_suspend, e1000e_pm_runtime_resume, + e1000e_pm_runtime_idle) }; /* PCI Device API Driver */ @@ -7055,7 +7110,7 @@ static int __init e1000_init_module(void) int ret; pr_info("Intel(R) PRO/1000 Network Driver - %s\n", e1000e_driver_version); - pr_info("Copyright(c) 1999 - 2013 Intel Corporation.\n"); + pr_info("Copyright(c) 1999 - 2014 Intel Corporation.\n"); ret = pci_register_driver(&e1000_driver); return ret; diff --git a/drivers/net/ethernet/intel/e1000e/nvm.c b/drivers/net/ethernet/intel/e1000e/nvm.c index d70a03906ac0..a9a976f04bff 100644 --- a/drivers/net/ethernet/intel/e1000e/nvm.c +++ b/drivers/net/ethernet/intel/e1000e/nvm.c @@ -1,30 +1,23 @@ -/******************************************************************************* - - Intel PRO/1000 Linux driver - Copyright(c) 1999 - 2013 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +/* Intel PRO/1000 Linux driver + * Copyright(c) 1999 - 2014 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + * Contact Information: + * Linux NICS <linux.nics@intel.com> + * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> + * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 + */ #include "e1000.h" diff --git a/drivers/net/ethernet/intel/e1000e/nvm.h b/drivers/net/ethernet/intel/e1000e/nvm.h index 45fc69561627..342bf69efab5 100644 --- a/drivers/net/ethernet/intel/e1000e/nvm.h +++ b/drivers/net/ethernet/intel/e1000e/nvm.h @@ -1,30 +1,23 @@ -/******************************************************************************* - - Intel PRO/1000 Linux driver - Copyright(c) 1999 - 2013 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +/* Intel PRO/1000 Linux driver + * Copyright(c) 1999 - 2014 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + * Contact Information: + * Linux NICS <linux.nics@intel.com> + * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> + * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 + */ #ifndef _E1000E_NVM_H_ #define _E1000E_NVM_H_ diff --git a/drivers/net/ethernet/intel/e1000e/param.c b/drivers/net/ethernet/intel/e1000e/param.c index c16bd75b6caa..d0ac0f3249c8 100644 --- a/drivers/net/ethernet/intel/e1000e/param.c +++ b/drivers/net/ethernet/intel/e1000e/param.c @@ -1,30 +1,23 @@ -/******************************************************************************* - - Intel PRO/1000 Linux driver - Copyright(c) 1999 - 2013 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +/* Intel PRO/1000 Linux driver + * Copyright(c) 1999 - 2014 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + * Contact Information: + * Linux NICS <linux.nics@intel.com> + * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> + * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 + */ #include <linux/netdevice.h> #include <linux/module.h> @@ -381,6 +374,12 @@ void e1000e_check_options(struct e1000_adapter *adapter) "%s set to dynamic mode\n", opt.name); adapter->itr = 20000; break; + case 2: + dev_info(&adapter->pdev->dev, + "%s Invalid mode - setting default\n", + opt.name); + adapter->itr_setting = opt.def; + /* fall-through */ case 3: dev_info(&adapter->pdev->dev, "%s set to dynamic conservative mode\n", diff --git a/drivers/net/ethernet/intel/e1000e/phy.c b/drivers/net/ethernet/intel/e1000e/phy.c index 20e71f4ca426..00b3fc98bf30 100644 --- a/drivers/net/ethernet/intel/e1000e/phy.c +++ b/drivers/net/ethernet/intel/e1000e/phy.c @@ -1,30 +1,23 @@ -/******************************************************************************* - - Intel PRO/1000 Linux driver - Copyright(c) 1999 - 2013 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +/* Intel PRO/1000 Linux driver + * Copyright(c) 1999 - 2014 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + * Contact Information: + * Linux NICS <linux.nics@intel.com> + * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> + * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 + */ #include "e1000.h" diff --git a/drivers/net/ethernet/intel/e1000e/phy.h b/drivers/net/ethernet/intel/e1000e/phy.h index f4f71b9991e3..3841bccf058c 100644 --- a/drivers/net/ethernet/intel/e1000e/phy.h +++ b/drivers/net/ethernet/intel/e1000e/phy.h @@ -1,30 +1,23 @@ -/******************************************************************************* - - Intel PRO/1000 Linux driver - Copyright(c) 1999 - 2013 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +/* Intel PRO/1000 Linux driver + * Copyright(c) 1999 - 2014 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + * Contact Information: + * Linux NICS <linux.nics@intel.com> + * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> + * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 + */ #ifndef _E1000E_PHY_H_ #define _E1000E_PHY_H_ diff --git a/drivers/net/ethernet/intel/e1000e/ptp.c b/drivers/net/ethernet/intel/e1000e/ptp.c index 065f8c80d4f2..3bd79a3ff829 100644 --- a/drivers/net/ethernet/intel/e1000e/ptp.c +++ b/drivers/net/ethernet/intel/e1000e/ptp.c @@ -1,30 +1,23 @@ -/******************************************************************************* - - Intel PRO/1000 Linux driver - Copyright(c) 1999 - 2013 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +/* Intel PRO/1000 Linux driver + * Copyright(c) 1999 - 2014 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + * Contact Information: + * Linux NICS <linux.nics@intel.com> + * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> + * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 + */ /* PTP 1588 Hardware Clock (PHC) * Derived from PTP Hardware Clock driver for Intel 82576 and 82580 (igb) @@ -47,6 +40,7 @@ static int e1000e_phc_adjfreq(struct ptp_clock_info *ptp, s32 delta) ptp_clock_info); struct e1000_hw *hw = &adapter->hw; bool neg_adj = false; + unsigned long flags; u64 adjustment; u32 timinca, incvalue; s32 ret_val; @@ -64,6 +58,8 @@ static int e1000e_phc_adjfreq(struct ptp_clock_info *ptp, s32 delta) if (ret_val) return ret_val; + spin_lock_irqsave(&adapter->systim_lock, flags); + incvalue = timinca & E1000_TIMINCA_INCVALUE_MASK; adjustment = incvalue; @@ -77,6 +73,8 @@ static int e1000e_phc_adjfreq(struct ptp_clock_info *ptp, s32 delta) ew32(TIMINCA, timinca); + spin_unlock_irqrestore(&adapter->systim_lock, flags); + return 0; } diff --git a/drivers/net/ethernet/intel/e1000e/regs.h b/drivers/net/ethernet/intel/e1000e/regs.h index a7e6a3e37257..ea235bbe50d3 100644 --- a/drivers/net/ethernet/intel/e1000e/regs.h +++ b/drivers/net/ethernet/intel/e1000e/regs.h @@ -1,30 +1,23 @@ -/******************************************************************************* - - Intel PRO/1000 Linux driver - Copyright(c) 1999 - 2013 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +/* Intel PRO/1000 Linux driver + * Copyright(c) 1999 - 2014 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * The full GNU General Public License is included in this distribution in + * the file called "COPYING". + * + * Contact Information: + * Linux NICS <linux.nics@intel.com> + * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> + * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 + */ #ifndef _E1000E_REGS_H_ #define _E1000E_REGS_H_ @@ -39,6 +32,7 @@ #define E1000_SCTL 0x00024 /* SerDes Control - RW */ #define E1000_FCAL 0x00028 /* Flow Control Address Low - RW */ #define E1000_FCAH 0x0002C /* Flow Control Address High -RW */ +#define E1000_FEXT 0x0002C /* Future Extended - RW */ #define E1000_FEXTNVM 0x00028 /* Future Extended NVM - RW */ #define E1000_FEXTNVM3 0x0003C /* Future Extended NVM 3 - RW */ #define E1000_FEXTNVM4 0x00024 /* Future Extended NVM 4 - RW */ diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 72dae4d97b43..838b69b74edf 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -86,12 +86,12 @@ #define I40E_NVM_VERSION_LO_SHIFT 0 #define I40E_NVM_VERSION_LO_MASK (0xff << I40E_NVM_VERSION_LO_SHIFT) -#define I40E_NVM_VERSION_HI_SHIFT 8 -#define I40E_NVM_VERSION_HI_MASK (0xff << I40E_NVM_VERSION_HI_SHIFT) +#define I40E_NVM_VERSION_HI_SHIFT 12 +#define I40E_NVM_VERSION_HI_MASK (0xf << I40E_NVM_VERSION_HI_SHIFT) /* The values in here are decimal coded as hex as is the case in the NVM map*/ #define I40E_CURRENT_NVM_VERSION_HI 0x2 -#define I40E_CURRENT_NVM_VERSION_LO 0x30 +#define I40E_CURRENT_NVM_VERSION_LO 0x40 /* magic for getting defines into strings */ #define STRINGIFY(foo) #foo @@ -152,8 +152,18 @@ struct i40e_lump_tracking { }; #define I40E_DEFAULT_ATR_SAMPLE_RATE 20 -#define I40E_FDIR_MAX_RAW_PACKET_LOOKUP 512 -struct i40e_fdir_data { +#define I40E_FDIR_MAX_RAW_PACKET_SIZE 512 +struct i40e_fdir_filter { + struct hlist_node fdir_node; + /* filter ipnut set */ + u8 flow_type; + u8 ip4_proto; + __be32 dst_ip[4]; + __be32 src_ip[4]; + __be16 src_port; + __be16 dst_port; + __be32 sctp_v_tag; + /* filter control */ u16 q_index; u8 flex_off; u8 pctype; @@ -162,7 +172,6 @@ struct i40e_fdir_data { u8 fd_status; u16 cnt_index; u32 fd_id; - u8 *raw_packet; }; #define I40E_ETH_P_LLDP 0x88cc @@ -210,6 +219,9 @@ struct i40e_pf { u8 atr_sample_rate; bool wol_en; + struct hlist_head fdir_filter_list; + u16 fdir_pf_active_filters; + #ifdef CONFIG_I40E_VXLAN __be16 vxlan_ports[I40E_MAX_PF_UDP_OFFLOAD_PORTS]; u16 pending_vxlan_bitmap; @@ -477,10 +489,10 @@ static inline char *i40e_fw_version_str(struct i40e_hw *hw) "f%d.%d a%d.%d n%02x.%02x e%08x", hw->aq.fw_maj_ver, hw->aq.fw_min_ver, hw->aq.api_maj_ver, hw->aq.api_min_ver, - (hw->nvm.version & I40E_NVM_VERSION_HI_MASK) - >> I40E_NVM_VERSION_HI_SHIFT, - (hw->nvm.version & I40E_NVM_VERSION_LO_MASK) - >> I40E_NVM_VERSION_LO_SHIFT, + (hw->nvm.version & I40E_NVM_VERSION_HI_MASK) >> + I40E_NVM_VERSION_HI_SHIFT, + (hw->nvm.version & I40E_NVM_VERSION_LO_MASK) >> + I40E_NVM_VERSION_LO_SHIFT, hw->nvm.eetrack); return buf; @@ -534,9 +546,10 @@ struct rtnl_link_stats64 *i40e_get_vsi_stats_struct(struct i40e_vsi *vsi); int i40e_fetch_switch_configuration(struct i40e_pf *pf, bool printconfig); -int i40e_program_fdir_filter(struct i40e_fdir_data *fdir_data, +int i40e_program_fdir_filter(struct i40e_fdir_filter *fdir_data, u8 *raw_packet, struct i40e_pf *pf, bool add); - +int i40e_add_del_fdir(struct i40e_vsi *vsi, + struct i40e_fdir_filter *input, bool add); void i40e_set_ethtool_ops(struct net_device *netdev); struct i40e_mac_filter *i40e_add_filter(struct i40e_vsi *vsi, u8 *macaddr, s16 vlan, diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq.c b/drivers/net/ethernet/intel/i40e/i40e_adminq.c index a50e6b3479ae..ed3902bf249b 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq.c +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq.c @@ -647,9 +647,8 @@ static u16 i40e_clean_asq(struct i40e_hw *hw) desc_cb = *desc; cb_func(hw, &desc_cb); } - memset((void *)desc, 0, sizeof(struct i40e_aq_desc)); - memset((void *)details, 0, - sizeof(struct i40e_asq_cmd_details)); + memset(desc, 0, sizeof(*desc)); + memset(details, 0, sizeof(*details)); ntc++; if (ntc == asq->count) ntc = 0; diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c index e7f38b57834d..bb948dd92474 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_common.c +++ b/drivers/net/ethernet/intel/i40e/i40e_common.c @@ -162,6 +162,372 @@ i40e_status i40e_aq_queue_shutdown(struct i40e_hw *hw, return status; } +/* The i40e_ptype_lookup table is used to convert from the 8-bit ptype in the + * hardware to a bit-field that can be used by SW to more easily determine the + * packet type. + * + * Macros are used to shorten the table lines and make this table human + * readable. + * + * We store the PTYPE in the top byte of the bit field - this is just so that + * we can check that the table doesn't have a row missing, as the index into + * the table should be the PTYPE. + * + * Typical work flow: + * + * IF NOT i40e_ptype_lookup[ptype].known + * THEN + * Packet is unknown + * ELSE IF i40e_ptype_lookup[ptype].outer_ip == I40E_RX_PTYPE_OUTER_IP + * Use the rest of the fields to look at the tunnels, inner protocols, etc + * ELSE + * Use the enum i40e_rx_l2_ptype to decode the packet type + * ENDIF + */ + +/* macro to make the table lines short */ +#define I40E_PTT(PTYPE, OUTER_IP, OUTER_IP_VER, OUTER_FRAG, T, TE, TEF, I, PL)\ + { PTYPE, \ + 1, \ + I40E_RX_PTYPE_OUTER_##OUTER_IP, \ + I40E_RX_PTYPE_OUTER_##OUTER_IP_VER, \ + I40E_RX_PTYPE_##OUTER_FRAG, \ + I40E_RX_PTYPE_TUNNEL_##T, \ + I40E_RX_PTYPE_TUNNEL_END_##TE, \ + I40E_RX_PTYPE_##TEF, \ + I40E_RX_PTYPE_INNER_PROT_##I, \ + I40E_RX_PTYPE_PAYLOAD_LAYER_##PL } + +#define I40E_PTT_UNUSED_ENTRY(PTYPE) \ + { PTYPE, 0, 0, 0, 0, 0, 0, 0, 0, 0 } + +/* shorter macros makes the table fit but are terse */ +#define I40E_RX_PTYPE_NOF I40E_RX_PTYPE_NOT_FRAG +#define I40E_RX_PTYPE_FRG I40E_RX_PTYPE_FRAG +#define I40E_RX_PTYPE_INNER_PROT_TS I40E_RX_PTYPE_INNER_PROT_TIMESYNC + +/* Lookup table mapping the HW PTYPE to the bit field for decoding */ +struct i40e_rx_ptype_decoded i40e_ptype_lookup[] = { + /* L2 Packet types */ + I40E_PTT_UNUSED_ENTRY(0), + I40E_PTT(1, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2), + I40E_PTT(2, L2, NONE, NOF, NONE, NONE, NOF, TS, PAY2), + I40E_PTT(3, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2), + I40E_PTT_UNUSED_ENTRY(4), + I40E_PTT_UNUSED_ENTRY(5), + I40E_PTT(6, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2), + I40E_PTT(7, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2), + I40E_PTT_UNUSED_ENTRY(8), + I40E_PTT_UNUSED_ENTRY(9), + I40E_PTT(10, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2), + I40E_PTT(11, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE), + I40E_PTT(12, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), + I40E_PTT(13, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), + I40E_PTT(14, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), + I40E_PTT(15, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), + I40E_PTT(16, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), + I40E_PTT(17, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), + I40E_PTT(18, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), + I40E_PTT(19, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), + I40E_PTT(20, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), + I40E_PTT(21, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), + + /* Non Tunneled IPv4 */ + I40E_PTT(22, IP, IPV4, FRG, NONE, NONE, NOF, NONE, PAY3), + I40E_PTT(23, IP, IPV4, NOF, NONE, NONE, NOF, NONE, PAY3), + I40E_PTT(24, IP, IPV4, NOF, NONE, NONE, NOF, UDP, PAY4), + I40E_PTT_UNUSED_ENTRY(25), + I40E_PTT(26, IP, IPV4, NOF, NONE, NONE, NOF, TCP, PAY4), + I40E_PTT(27, IP, IPV4, NOF, NONE, NONE, NOF, SCTP, PAY4), + I40E_PTT(28, IP, IPV4, NOF, NONE, NONE, NOF, ICMP, PAY4), + + /* IPv4 --> IPv4 */ + I40E_PTT(29, IP, IPV4, NOF, IP_IP, IPV4, FRG, NONE, PAY3), + I40E_PTT(30, IP, IPV4, NOF, IP_IP, IPV4, NOF, NONE, PAY3), + I40E_PTT(31, IP, IPV4, NOF, IP_IP, IPV4, NOF, UDP, PAY4), + I40E_PTT_UNUSED_ENTRY(32), + I40E_PTT(33, IP, IPV4, NOF, IP_IP, IPV4, NOF, TCP, PAY4), + I40E_PTT(34, IP, IPV4, NOF, IP_IP, IPV4, NOF, SCTP, PAY4), + I40E_PTT(35, IP, IPV4, NOF, IP_IP, IPV4, NOF, ICMP, PAY4), + + /* IPv4 --> IPv6 */ + I40E_PTT(36, IP, IPV4, NOF, IP_IP, IPV6, FRG, NONE, PAY3), + I40E_PTT(37, IP, IPV4, NOF, IP_IP, IPV6, NOF, NONE, PAY3), + I40E_PTT(38, IP, IPV4, NOF, IP_IP, IPV6, NOF, UDP, PAY4), + I40E_PTT_UNUSED_ENTRY(39), + I40E_PTT(40, IP, IPV4, NOF, IP_IP, IPV6, NOF, TCP, PAY4), + I40E_PTT(41, IP, IPV4, NOF, IP_IP, IPV6, NOF, SCTP, PAY4), + I40E_PTT(42, IP, IPV4, NOF, IP_IP, IPV6, NOF, ICMP, PAY4), + + /* IPv4 --> GRE/NAT */ + I40E_PTT(43, IP, IPV4, NOF, IP_GRENAT, NONE, NOF, NONE, PAY3), + + /* IPv4 --> GRE/NAT --> IPv4 */ + I40E_PTT(44, IP, IPV4, NOF, IP_GRENAT, IPV4, FRG, NONE, PAY3), + I40E_PTT(45, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, NONE, PAY3), + I40E_PTT(46, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, UDP, PAY4), + I40E_PTT_UNUSED_ENTRY(47), + I40E_PTT(48, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, TCP, PAY4), + I40E_PTT(49, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, SCTP, PAY4), + I40E_PTT(50, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, ICMP, PAY4), + + /* IPv4 --> GRE/NAT --> IPv6 */ + I40E_PTT(51, IP, IPV4, NOF, IP_GRENAT, IPV6, FRG, NONE, PAY3), + I40E_PTT(52, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, NONE, PAY3), + I40E_PTT(53, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, UDP, PAY4), + I40E_PTT_UNUSED_ENTRY(54), + I40E_PTT(55, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, TCP, PAY4), + I40E_PTT(56, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, SCTP, PAY4), + I40E_PTT(57, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, ICMP, PAY4), + + /* IPv4 --> GRE/NAT --> MAC */ + I40E_PTT(58, IP, IPV4, NOF, IP_GRENAT_MAC, NONE, NOF, NONE, PAY3), + + /* IPv4 --> GRE/NAT --> MAC --> IPv4 */ + I40E_PTT(59, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, FRG, NONE, PAY3), + I40E_PTT(60, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, NONE, PAY3), + I40E_PTT(61, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, UDP, PAY4), + I40E_PTT_UNUSED_ENTRY(62), + I40E_PTT(63, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, TCP, PAY4), + I40E_PTT(64, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, SCTP, PAY4), + I40E_PTT(65, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, ICMP, PAY4), + + /* IPv4 --> GRE/NAT -> MAC --> IPv6 */ + I40E_PTT(66, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, FRG, NONE, PAY3), + I40E_PTT(67, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, NONE, PAY3), + I40E_PTT(68, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, UDP, PAY4), + I40E_PTT_UNUSED_ENTRY(69), + I40E_PTT(70, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, TCP, PAY4), + I40E_PTT(71, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, SCTP, PAY4), + I40E_PTT(72, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, ICMP, PAY4), + + /* IPv4 --> GRE/NAT --> MAC/VLAN */ + I40E_PTT(73, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, NONE, NOF, NONE, PAY3), + + /* IPv4 ---> GRE/NAT -> MAC/VLAN --> IPv4 */ + I40E_PTT(74, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, FRG, NONE, PAY3), + I40E_PTT(75, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, NONE, PAY3), + I40E_PTT(76, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, UDP, PAY4), + I40E_PTT_UNUSED_ENTRY(77), + I40E_PTT(78, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, TCP, PAY4), + I40E_PTT(79, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, SCTP, PAY4), + I40E_PTT(80, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, ICMP, PAY4), + + /* IPv4 -> GRE/NAT -> MAC/VLAN --> IPv6 */ + I40E_PTT(81, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, FRG, NONE, PAY3), + I40E_PTT(82, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, NONE, PAY3), + I40E_PTT(83, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, UDP, PAY4), + I40E_PTT_UNUSED_ENTRY(84), + I40E_PTT(85, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, TCP, PAY4), + I40E_PTT(86, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, SCTP, PAY4), + I40E_PTT(87, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4), + + /* Non Tunneled IPv6 */ + I40E_PTT(88, IP, IPV6, FRG, NONE, NONE, NOF, NONE, PAY3), + I40E_PTT(89, IP, IPV6, NOF, NONE, NONE, NOF, NONE, PAY3), + I40E_PTT(90, IP, IPV6, NOF, NONE, NONE, NOF, UDP, PAY3), + I40E_PTT_UNUSED_ENTRY(91), + I40E_PTT(92, IP, IPV6, NOF, NONE, NONE, NOF, TCP, PAY4), + I40E_PTT(93, IP, IPV6, NOF, NONE, NONE, NOF, SCTP, PAY4), + I40E_PTT(94, IP, IPV6, NOF, NONE, NONE, NOF, ICMP, PAY4), + + /* IPv6 --> IPv4 */ + I40E_PTT(95, IP, IPV6, NOF, IP_IP, IPV4, FRG, NONE, PAY3), + I40E_PTT(96, IP, IPV6, NOF, IP_IP, IPV4, NOF, NONE, PAY3), + I40E_PTT(97, IP, IPV6, NOF, IP_IP, IPV4, NOF, UDP, PAY4), + I40E_PTT_UNUSED_ENTRY(98), + I40E_PTT(99, IP, IPV6, NOF, IP_IP, IPV4, NOF, TCP, PAY4), + I40E_PTT(100, IP, IPV6, NOF, IP_IP, IPV4, NOF, SCTP, PAY4), + I40E_PTT(101, IP, IPV6, NOF, IP_IP, IPV4, NOF, ICMP, PAY4), + + /* IPv6 --> IPv6 */ + I40E_PTT(102, IP, IPV6, NOF, IP_IP, IPV6, FRG, NONE, PAY3), + I40E_PTT(103, IP, IPV6, NOF, IP_IP, IPV6, NOF, NONE, PAY3), + I40E_PTT(104, IP, IPV6, NOF, IP_IP, IPV6, NOF, UDP, PAY4), + I40E_PTT_UNUSED_ENTRY(105), + I40E_PTT(106, IP, IPV6, NOF, IP_IP, IPV6, NOF, TCP, PAY4), + I40E_PTT(107, IP, IPV6, NOF, IP_IP, IPV6, NOF, SCTP, PAY4), + I40E_PTT(108, IP, IPV6, NOF, IP_IP, IPV6, NOF, ICMP, PAY4), + + /* IPv6 --> GRE/NAT */ + I40E_PTT(109, IP, IPV6, NOF, IP_GRENAT, NONE, NOF, NONE, PAY3), + + /* IPv6 --> GRE/NAT -> IPv4 */ + I40E_PTT(110, IP, IPV6, NOF, IP_GRENAT, IPV4, FRG, NONE, PAY3), + I40E_PTT(111, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, NONE, PAY3), + I40E_PTT(112, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, UDP, PAY4), + I40E_PTT_UNUSED_ENTRY(113), + I40E_PTT(114, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, TCP, PAY4), + I40E_PTT(115, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, SCTP, PAY4), + I40E_PTT(116, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, ICMP, PAY4), + + /* IPv6 --> GRE/NAT -> IPv6 */ + I40E_PTT(117, IP, IPV6, NOF, IP_GRENAT, IPV6, FRG, NONE, PAY3), + I40E_PTT(118, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, NONE, PAY3), + I40E_PTT(119, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, UDP, PAY4), + I40E_PTT_UNUSED_ENTRY(120), + I40E_PTT(121, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, TCP, PAY4), + I40E_PTT(122, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, SCTP, PAY4), + I40E_PTT(123, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, ICMP, PAY4), + + /* IPv6 --> GRE/NAT -> MAC */ + I40E_PTT(124, IP, IPV6, NOF, IP_GRENAT_MAC, NONE, NOF, NONE, PAY3), + + /* IPv6 --> GRE/NAT -> MAC -> IPv4 */ + I40E_PTT(125, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, FRG, NONE, PAY3), + I40E_PTT(126, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, NONE, PAY3), + I40E_PTT(127, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, UDP, PAY4), + I40E_PTT_UNUSED_ENTRY(128), + I40E_PTT(129, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, TCP, PAY4), + I40E_PTT(130, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, SCTP, PAY4), + I40E_PTT(131, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, ICMP, PAY4), + + /* IPv6 --> GRE/NAT -> MAC -> IPv6 */ + I40E_PTT(132, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, FRG, NONE, PAY3), + I40E_PTT(133, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, NONE, PAY3), + I40E_PTT(134, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, UDP, PAY4), + I40E_PTT_UNUSED_ENTRY(135), + I40E_PTT(136, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, TCP, PAY4), + I40E_PTT(137, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, SCTP, PAY4), + I40E_PTT(138, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, ICMP, PAY4), + + /* IPv6 --> GRE/NAT -> MAC/VLAN */ + I40E_PTT(139, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, NONE, NOF, NONE, PAY3), + + /* IPv6 --> GRE/NAT -> MAC/VLAN --> IPv4 */ + I40E_PTT(140, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, FRG, NONE, PAY3), + I40E_PTT(141, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, NONE, PAY3), + I40E_PTT(142, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, UDP, PAY4), + I40E_PTT_UNUSED_ENTRY(143), + I40E_PTT(144, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, TCP, PAY4), + I40E_PTT(145, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, SCTP, PAY4), + I40E_PTT(146, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, ICMP, PAY4), + + /* IPv6 --> GRE/NAT -> MAC/VLAN --> IPv6 */ + I40E_PTT(147, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, FRG, NONE, PAY3), + I40E_PTT(148, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, NONE, PAY3), + I40E_PTT(149, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, UDP, PAY4), + I40E_PTT_UNUSED_ENTRY(150), + I40E_PTT(151, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, TCP, PAY4), + I40E_PTT(152, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, SCTP, PAY4), + I40E_PTT(153, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4), + + /* unused entries */ + I40E_PTT_UNUSED_ENTRY(154), + I40E_PTT_UNUSED_ENTRY(155), + I40E_PTT_UNUSED_ENTRY(156), + I40E_PTT_UNUSED_ENTRY(157), + I40E_PTT_UNUSED_ENTRY(158), + I40E_PTT_UNUSED_ENTRY(159), + + I40E_PTT_UNUSED_ENTRY(160), + I40E_PTT_UNUSED_ENTRY(161), + I40E_PTT_UNUSED_ENTRY(162), + I40E_PTT_UNUSED_ENTRY(163), + I40E_PTT_UNUSED_ENTRY(164), + I40E_PTT_UNUSED_ENTRY(165), + I40E_PTT_UNUSED_ENTRY(166), + I40E_PTT_UNUSED_ENTRY(167), + I40E_PTT_UNUSED_ENTRY(168), + I40E_PTT_UNUSED_ENTRY(169), + + I40E_PTT_UNUSED_ENTRY(170), + I40E_PTT_UNUSED_ENTRY(171), + I40E_PTT_UNUSED_ENTRY(172), + I40E_PTT_UNUSED_ENTRY(173), + I40E_PTT_UNUSED_ENTRY(174), + I40E_PTT_UNUSED_ENTRY(175), + I40E_PTT_UNUSED_ENTRY(176), + I40E_PTT_UNUSED_ENTRY(177), + I40E_PTT_UNUSED_ENTRY(178), + I40E_PTT_UNUSED_ENTRY(179), + + I40E_PTT_UNUSED_ENTRY(180), + I40E_PTT_UNUSED_ENTRY(181), + I40E_PTT_UNUSED_ENTRY(182), + I40E_PTT_UNUSED_ENTRY(183), + I40E_PTT_UNUSED_ENTRY(184), + I40E_PTT_UNUSED_ENTRY(185), + I40E_PTT_UNUSED_ENTRY(186), + I40E_PTT_UNUSED_ENTRY(187), + I40E_PTT_UNUSED_ENTRY(188), + I40E_PTT_UNUSED_ENTRY(189), + + I40E_PTT_UNUSED_ENTRY(190), + I40E_PTT_UNUSED_ENTRY(191), + I40E_PTT_UNUSED_ENTRY(192), + I40E_PTT_UNUSED_ENTRY(193), + I40E_PTT_UNUSED_ENTRY(194), + I40E_PTT_UNUSED_ENTRY(195), + I40E_PTT_UNUSED_ENTRY(196), + I40E_PTT_UNUSED_ENTRY(197), + I40E_PTT_UNUSED_ENTRY(198), + I40E_PTT_UNUSED_ENTRY(199), + + I40E_PTT_UNUSED_ENTRY(200), + I40E_PTT_UNUSED_ENTRY(201), + I40E_PTT_UNUSED_ENTRY(202), + I40E_PTT_UNUSED_ENTRY(203), + I40E_PTT_UNUSED_ENTRY(204), + I40E_PTT_UNUSED_ENTRY(205), + I40E_PTT_UNUSED_ENTRY(206), + I40E_PTT_UNUSED_ENTRY(207), + I40E_PTT_UNUSED_ENTRY(208), + I40E_PTT_UNUSED_ENTRY(209), + + I40E_PTT_UNUSED_ENTRY(210), + I40E_PTT_UNUSED_ENTRY(211), + I40E_PTT_UNUSED_ENTRY(212), + I40E_PTT_UNUSED_ENTRY(213), + I40E_PTT_UNUSED_ENTRY(214), + I40E_PTT_UNUSED_ENTRY(215), + I40E_PTT_UNUSED_ENTRY(216), + I40E_PTT_UNUSED_ENTRY(217), + I40E_PTT_UNUSED_ENTRY(218), + I40E_PTT_UNUSED_ENTRY(219), + + I40E_PTT_UNUSED_ENTRY(220), + I40E_PTT_UNUSED_ENTRY(221), + I40E_PTT_UNUSED_ENTRY(222), + I40E_PTT_UNUSED_ENTRY(223), + I40E_PTT_UNUSED_ENTRY(224), + I40E_PTT_UNUSED_ENTRY(225), + I40E_PTT_UNUSED_ENTRY(226), + I40E_PTT_UNUSED_ENTRY(227), + I40E_PTT_UNUSED_ENTRY(228), + I40E_PTT_UNUSED_ENTRY(229), + + I40E_PTT_UNUSED_ENTRY(230), + I40E_PTT_UNUSED_ENTRY(231), + I40E_PTT_UNUSED_ENTRY(232), + I40E_PTT_UNUSED_ENTRY(233), + I40E_PTT_UNUSED_ENTRY(234), + I40E_PTT_UNUSED_ENTRY(235), + I40E_PTT_UNUSED_ENTRY(236), + I40E_PTT_UNUSED_ENTRY(237), + I40E_PTT_UNUSED_ENTRY(238), + I40E_PTT_UNUSED_ENTRY(239), + + I40E_PTT_UNUSED_ENTRY(240), + I40E_PTT_UNUSED_ENTRY(241), + I40E_PTT_UNUSED_ENTRY(242), + I40E_PTT_UNUSED_ENTRY(243), + I40E_PTT_UNUSED_ENTRY(244), + I40E_PTT_UNUSED_ENTRY(245), + I40E_PTT_UNUSED_ENTRY(246), + I40E_PTT_UNUSED_ENTRY(247), + I40E_PTT_UNUSED_ENTRY(248), + I40E_PTT_UNUSED_ENTRY(249), + + I40E_PTT_UNUSED_ENTRY(250), + I40E_PTT_UNUSED_ENTRY(251), + I40E_PTT_UNUSED_ENTRY(252), + I40E_PTT_UNUSED_ENTRY(253), + I40E_PTT_UNUSED_ENTRY(254), + I40E_PTT_UNUSED_ENTRY(255) +}; + + /** * i40e_init_shared_code - Initialize the shared code * @hw: pointer to hardware structure diff --git a/drivers/net/ethernet/intel/i40e/i40e_dcb.c b/drivers/net/ethernet/intel/i40e/i40e_dcb.c index 50730141bb7b..036570d76176 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_dcb.c +++ b/drivers/net/ethernet/intel/i40e/i40e_dcb.c @@ -332,6 +332,7 @@ i40e_status i40e_lldp_to_dcb_config(u8 *lldpmib, u16 type; u16 length; u16 typelength; + u16 offset = 0; if (!lldpmib || !dcbcfg) return I40E_ERR_PARAM; @@ -339,15 +340,17 @@ i40e_status i40e_lldp_to_dcb_config(u8 *lldpmib, /* set to the start of LLDPDU */ lldpmib += ETH_HLEN; tlv = (struct i40e_lldp_org_tlv *)lldpmib; - while (tlv) { + while (1) { typelength = ntohs(tlv->typelength); type = (u16)((typelength & I40E_LLDP_TLV_TYPE_MASK) >> I40E_LLDP_TLV_TYPE_SHIFT); length = (u16)((typelength & I40E_LLDP_TLV_LEN_MASK) >> I40E_LLDP_TLV_LEN_SHIFT); + offset += sizeof(typelength) + length; - if (type == I40E_TLV_TYPE_END) - break;/* END TLV break out */ + /* END TLV or beyond LLDPDU size */ + if ((type == I40E_TLV_TYPE_END) || (offset > I40E_LLDPDU_SIZE)) + break; switch (type) { case I40E_TLV_TYPE_ORG: diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c index da22c3fa2c00..57fc86496f30 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c +++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c @@ -1663,21 +1663,22 @@ static ssize_t i40e_dbg_command_write(struct file *filp, desc = NULL; } else if ((strncmp(cmd_buf, "add fd_filter", 13) == 0) || (strncmp(cmd_buf, "rem fd_filter", 13) == 0)) { - struct i40e_fdir_data fd_data; + struct i40e_fdir_filter fd_data; u16 packet_len, i, j = 0; char *asc_packet; + u8 *raw_packet; bool add = false; int ret; - asc_packet = kzalloc(I40E_FDIR_MAX_RAW_PACKET_LOOKUP, + asc_packet = kzalloc(I40E_FDIR_MAX_RAW_PACKET_SIZE, GFP_KERNEL); if (!asc_packet) goto command_write_done; - fd_data.raw_packet = kzalloc(I40E_FDIR_MAX_RAW_PACKET_LOOKUP, - GFP_KERNEL); + raw_packet = kzalloc(I40E_FDIR_MAX_RAW_PACKET_SIZE, + GFP_KERNEL); - if (!fd_data.raw_packet) { + if (!raw_packet) { kfree(asc_packet); asc_packet = NULL; goto command_write_done; @@ -1698,36 +1699,36 @@ static ssize_t i40e_dbg_command_write(struct file *filp, cnt); kfree(asc_packet); asc_packet = NULL; - kfree(fd_data.raw_packet); + kfree(raw_packet); goto command_write_done; } /* fix packet length if user entered 0 */ if (packet_len == 0) - packet_len = I40E_FDIR_MAX_RAW_PACKET_LOOKUP; + packet_len = I40E_FDIR_MAX_RAW_PACKET_SIZE; /* make sure to check the max as well */ packet_len = min_t(u16, - packet_len, I40E_FDIR_MAX_RAW_PACKET_LOOKUP); + packet_len, I40E_FDIR_MAX_RAW_PACKET_SIZE); for (i = 0; i < packet_len; i++) { sscanf(&asc_packet[j], "%2hhx ", - &fd_data.raw_packet[i]); + &raw_packet[i]); j += 3; } dev_info(&pf->pdev->dev, "FD raw packet dump\n"); print_hex_dump(KERN_INFO, "FD raw packet: ", DUMP_PREFIX_OFFSET, 16, 1, - fd_data.raw_packet, packet_len, true); - ret = i40e_program_fdir_filter(&fd_data, pf, add); + raw_packet, packet_len, true); + ret = i40e_program_fdir_filter(&fd_data, raw_packet, pf, add); if (!ret) { dev_info(&pf->pdev->dev, "Filter command send Status : Success\n"); } else { dev_info(&pf->pdev->dev, "Filter command send failed %d\n", ret); } - kfree(fd_data.raw_packet); - fd_data.raw_packet = NULL; + kfree(raw_packet); + raw_packet = NULL; kfree(asc_packet); asc_packet = NULL; } else if (strncmp(cmd_buf, "fd-atr off", 10) == 0) { diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index b1d7d8c5cb9b..d34ff31fddd8 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -62,6 +62,9 @@ static const struct i40e_stats i40e_gstrings_net_stats[] = { I40E_NETDEV_STAT(rx_crc_errors), }; +static int i40e_add_del_fdir_ethtool(struct i40e_vsi *vsi, + struct ethtool_rxnfc *cmd, bool add); + /* These PF_STATs might look like duplicates of some NETDEV_STATs, * but they are separate. This device supports Virtualization, and * as such might have several netdevs supporting VMDq and FCoE going @@ -84,6 +87,7 @@ static struct i40e_stats i40e_gstrings_stats[] = { I40E_PF_STAT("illegal_bytes", stats.illegal_bytes), I40E_PF_STAT("mac_local_faults", stats.mac_local_faults), I40E_PF_STAT("mac_remote_faults", stats.mac_remote_faults), + I40E_PF_STAT("tx_timeout", tx_timeout_count), I40E_PF_STAT("rx_length_errors", stats.rx_length_errors), I40E_PF_STAT("link_xon_rx", stats.link_xon_rx), I40E_PF_STAT("link_xoff_rx", stats.link_xoff_rx), @@ -1112,6 +1116,84 @@ static int i40e_get_rss_hash_opts(struct i40e_pf *pf, struct ethtool_rxnfc *cmd) } /** + * i40e_get_ethtool_fdir_all - Populates the rule count of a command + * @pf: Pointer to the physical function struct + * @cmd: The command to get or set Rx flow classification rules + * @rule_locs: Array of used rule locations + * + * This function populates both the total and actual rule count of + * the ethtool flow classification command + * + * Returns 0 on success or -EMSGSIZE if entry not found + **/ +static int i40e_get_ethtool_fdir_all(struct i40e_pf *pf, + struct ethtool_rxnfc *cmd, + u32 *rule_locs) +{ + struct i40e_fdir_filter *rule; + struct hlist_node *node2; + int cnt = 0; + + /* report total rule count */ + cmd->data = pf->hw.fdir_shared_filter_count + + pf->fdir_pf_filter_count; + + hlist_for_each_entry_safe(rule, node2, + &pf->fdir_filter_list, fdir_node) { + if (cnt == cmd->rule_cnt) + return -EMSGSIZE; + + rule_locs[cnt] = rule->fd_id; + cnt++; + } + + cmd->rule_cnt = cnt; + + return 0; +} + +/** + * i40e_get_ethtool_fdir_entry - Look up a filter based on Rx flow + * @pf: Pointer to the physical function struct + * @cmd: The command to get or set Rx flow classification rules + * + * This function looks up a filter based on the Rx flow classification + * command and fills the flow spec info for it if found + * + * Returns 0 on success or -EINVAL if filter not found + **/ +static int i40e_get_ethtool_fdir_entry(struct i40e_pf *pf, + struct ethtool_rxnfc *cmd) +{ + struct ethtool_rx_flow_spec *fsp = + (struct ethtool_rx_flow_spec *)&cmd->fs; + struct i40e_fdir_filter *rule = NULL; + struct hlist_node *node2; + + /* report total rule count */ + cmd->data = pf->hw.fdir_shared_filter_count + + pf->fdir_pf_filter_count; + + hlist_for_each_entry_safe(rule, node2, + &pf->fdir_filter_list, fdir_node) { + if (fsp->location <= rule->fd_id) + break; + } + + if (!rule || fsp->location != rule->fd_id) + return -EINVAL; + + fsp->flow_type = rule->flow_type; + fsp->h_u.tcp_ip4_spec.psrc = rule->src_port; + fsp->h_u.tcp_ip4_spec.pdst = rule->dst_port; + fsp->h_u.tcp_ip4_spec.ip4src = rule->src_ip[0]; + fsp->h_u.tcp_ip4_spec.ip4dst = rule->dst_ip[0]; + fsp->ring_cookie = rule->q_index; + + return 0; +} + +/** * i40e_get_rxnfc - command to get RX flow classification rules * @netdev: network interface device structure * @cmd: ethtool rxnfc command @@ -1135,15 +1217,15 @@ static int i40e_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd, ret = i40e_get_rss_hash_opts(pf, cmd); break; case ETHTOOL_GRXCLSRLCNT: - cmd->rule_cnt = 10; + cmd->rule_cnt = pf->fdir_pf_active_filters; ret = 0; break; case ETHTOOL_GRXCLSRULE: - ret = 0; + ret = i40e_get_ethtool_fdir_entry(pf, cmd); break; case ETHTOOL_GRXCLSRLALL: - cmd->data = 500; - ret = 0; + ret = i40e_get_ethtool_fdir_all(pf, cmd, rule_locs); + break; default: break; } @@ -1274,289 +1356,158 @@ static int i40e_set_rss_hash_opt(struct i40e_pf *pf, struct ethtool_rxnfc *nfc) return 0; } -#define IP_HEADER_OFFSET 14 -#define I40E_UDPIP_DUMMY_PACKET_LEN 42 /** - * i40e_add_del_fdir_udpv4 - Add/Remove UDPv4 Flow Director filters for - * a specific flow spec - * @vsi: pointer to the targeted VSI - * @fd_data: the flow director data required from the FDir descriptor - * @ethtool_rx_flow_spec: the flow spec - * @add: true adds a filter, false removes it + * i40e_update_ethtool_fdir_entry - Updates the fdir filter entry + * @vsi: Pointer to the targeted VSI + * @input: The filter to update or NULL to indicate deletion + * @sw_idx: Software index to the filter + * @cmd: The command to get or set Rx flow classification rules * - * Returns 0 if the filters were successfully added or removed + * This function updates (or deletes) a Flow Director entry from + * the hlist of the corresponding PF + * + * Returns 0 on success **/ -static int i40e_add_del_fdir_udpv4(struct i40e_vsi *vsi, - struct i40e_fdir_data *fd_data, - struct ethtool_rx_flow_spec *fsp, bool add) +static int i40e_update_ethtool_fdir_entry(struct i40e_vsi *vsi, + struct i40e_fdir_filter *input, + u16 sw_idx, + struct ethtool_rxnfc *cmd) { + struct i40e_fdir_filter *rule, *parent; struct i40e_pf *pf = vsi->back; - struct udphdr *udp; - struct iphdr *ip; - bool err = false; - int ret; - int i; - char packet[] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x08, 0, - 0x45, 0, 0, 0x1c, 0, 0, 0x40, 0, 0x40, 0x11, - 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, - 0, 0, 0, 0, 0, 0, 0, 0}; - - memcpy(fd_data->raw_packet, packet, I40E_UDPIP_DUMMY_PACKET_LEN); - - ip = (struct iphdr *)(fd_data->raw_packet + IP_HEADER_OFFSET); - udp = (struct udphdr *)(fd_data->raw_packet + IP_HEADER_OFFSET - + sizeof(struct iphdr)); + struct hlist_node *node2; + int err = -EINVAL; - ip->saddr = fsp->h_u.tcp_ip4_spec.ip4src; - ip->daddr = fsp->h_u.tcp_ip4_spec.ip4dst; - udp->source = fsp->h_u.tcp_ip4_spec.psrc; - udp->dest = fsp->h_u.tcp_ip4_spec.pdst; + parent = NULL; + rule = NULL; - for (i = I40E_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP; - i <= I40E_FILTER_PCTYPE_NONF_IPV4_UDP; i++) { - fd_data->pctype = i; - ret = i40e_program_fdir_filter(fd_data, pf, add); - - if (ret) { - dev_info(&pf->pdev->dev, - "Filter command send failed for PCTYPE %d (ret = %d)\n", - fd_data->pctype, ret); - err = true; - } else { - dev_info(&pf->pdev->dev, - "Filter OK for PCTYPE %d (ret = %d)\n", - fd_data->pctype, ret); - } + hlist_for_each_entry_safe(rule, node2, + &pf->fdir_filter_list, fdir_node) { + /* hash found, or no matching entry */ + if (rule->fd_id >= sw_idx) + break; + parent = rule; } - return err ? -EOPNOTSUPP : 0; -} - -#define I40E_TCPIP_DUMMY_PACKET_LEN 54 -/** - * i40e_add_del_fdir_tcpv4 - Add/Remove TCPv4 Flow Director filters for - * a specific flow spec - * @vsi: pointer to the targeted VSI - * @fd_data: the flow director data required from the FDir descriptor - * @ethtool_rx_flow_spec: the flow spec - * @add: true adds a filter, false removes it - * - * Returns 0 if the filters were successfully added or removed - **/ -static int i40e_add_del_fdir_tcpv4(struct i40e_vsi *vsi, - struct i40e_fdir_data *fd_data, - struct ethtool_rx_flow_spec *fsp, bool add) -{ - struct i40e_pf *pf = vsi->back; - struct tcphdr *tcp; - struct iphdr *ip; - bool err = false; - int ret; - /* Dummy packet */ - char packet[] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x08, 0, - 0x45, 0, 0, 0x28, 0, 0, 0x40, 0, 0x40, 0x6, - 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, - 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, - 0x80, 0x11, 0x0, 0x72, 0, 0, 0, 0}; - - memcpy(fd_data->raw_packet, packet, I40E_TCPIP_DUMMY_PACKET_LEN); - - ip = (struct iphdr *)(fd_data->raw_packet + IP_HEADER_OFFSET); - tcp = (struct tcphdr *)(fd_data->raw_packet + IP_HEADER_OFFSET - + sizeof(struct iphdr)); - - ip->daddr = fsp->h_u.tcp_ip4_spec.ip4dst; - tcp->dest = fsp->h_u.tcp_ip4_spec.pdst; - ip->saddr = fsp->h_u.tcp_ip4_spec.ip4src; - tcp->source = fsp->h_u.tcp_ip4_spec.psrc; - - if (add) { - if (pf->flags & I40E_FLAG_FD_ATR_ENABLED) { - dev_info(&pf->pdev->dev, "Forcing ATR off, sideband rules for TCP/IPv4 flow being applied\n"); - pf->flags &= ~I40E_FLAG_FD_ATR_ENABLED; + /* if there is an old rule occupying our place remove it */ + if (rule && (rule->fd_id == sw_idx)) { + if (!input || (rule->fd_id != input->fd_id)) { + cmd->fs.flow_type = rule->flow_type; + err = i40e_add_del_fdir_ethtool(vsi, cmd, false); } + + hlist_del(&rule->fdir_node); + kfree(rule); + pf->fdir_pf_active_filters--; } - fd_data->pctype = I40E_FILTER_PCTYPE_NONF_IPV4_TCP_SYN; - ret = i40e_program_fdir_filter(fd_data, pf, add); + /* If no input this was a delete, err should be 0 if a rule was + * successfully found and removed from the list else -EINVAL + */ + if (!input) + return err; - if (ret) { - dev_info(&pf->pdev->dev, - "Filter command send failed for PCTYPE %d (ret = %d)\n", - fd_data->pctype, ret); - err = true; - } else { - dev_info(&pf->pdev->dev, "Filter OK for PCTYPE %d (ret = %d)\n", - fd_data->pctype, ret); - } + /* initialize node and set software index */ + INIT_HLIST_NODE(&input->fdir_node); - fd_data->pctype = I40E_FILTER_PCTYPE_NONF_IPV4_TCP; + /* add filter to the list */ + if (parent) + hlist_add_after(&parent->fdir_node, &input->fdir_node); + else + hlist_add_head(&input->fdir_node, + &pf->fdir_filter_list); - ret = i40e_program_fdir_filter(fd_data, pf, add); - if (ret) { - dev_info(&pf->pdev->dev, - "Filter command send failed for PCTYPE %d (ret = %d)\n", - fd_data->pctype, ret); - err = true; - } else { - dev_info(&pf->pdev->dev, "Filter OK for PCTYPE %d (ret = %d)\n", - fd_data->pctype, ret); - } + /* update counts */ + pf->fdir_pf_active_filters++; - return err ? -EOPNOTSUPP : 0; + return 0; } /** - * i40e_add_del_fdir_sctpv4 - Add/Remove SCTPv4 Flow Director filters for - * a specific flow spec - * @vsi: pointer to the targeted VSI - * @fd_data: the flow director data required from the FDir descriptor - * @ethtool_rx_flow_spec: the flow spec - * @add: true adds a filter, false removes it + * i40e_del_fdir_entry - Deletes a Flow Director filter entry + * @vsi: Pointer to the targeted VSI + * @cmd: The command to get or set Rx flow classification rules * - * Returns 0 if the filters were successfully added or removed - **/ -static int i40e_add_del_fdir_sctpv4(struct i40e_vsi *vsi, - struct i40e_fdir_data *fd_data, - struct ethtool_rx_flow_spec *fsp, bool add) -{ - return -EOPNOTSUPP; -} - -#define I40E_IP_DUMMY_PACKET_LEN 34 -/** - * i40e_add_del_fdir_ipv4 - Add/Remove IPv4 Flow Director filters for - * a specific flow spec - * @vsi: pointer to the targeted VSI - * @fd_data: the flow director data required for the FDir descriptor - * @fsp: the ethtool flow spec - * @add: true adds a filter, false removes it + * The function removes a Flow Director filter entry from the + * hlist of the corresponding PF * - * Returns 0 if the filters were successfully added or removed - **/ -static int i40e_add_del_fdir_ipv4(struct i40e_vsi *vsi, - struct i40e_fdir_data *fd_data, - struct ethtool_rx_flow_spec *fsp, bool add) + * Returns 0 on success + */ +static int i40e_del_fdir_entry(struct i40e_vsi *vsi, + struct ethtool_rxnfc *cmd) { + struct ethtool_rx_flow_spec *fsp = + (struct ethtool_rx_flow_spec *)&cmd->fs; struct i40e_pf *pf = vsi->back; - struct iphdr *ip; - bool err = false; - int ret; - int i; - char packet[] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x08, 0, - 0x45, 0, 0, 0x14, 0, 0, 0x40, 0, 0x40, 0x10, - 0, 0, 0, 0, 0, 0, 0, 0, 0, 0}; + int ret = 0; - memcpy(fd_data->raw_packet, packet, I40E_IP_DUMMY_PACKET_LEN); - ip = (struct iphdr *)(fd_data->raw_packet + IP_HEADER_OFFSET); - - ip->saddr = fsp->h_u.usr_ip4_spec.ip4src; - ip->daddr = fsp->h_u.usr_ip4_spec.ip4dst; - ip->protocol = fsp->h_u.usr_ip4_spec.proto; - - for (i = I40E_FILTER_PCTYPE_NONF_IPV4_OTHER; - i <= I40E_FILTER_PCTYPE_FRAG_IPV4; i++) { - fd_data->pctype = i; - ret = i40e_program_fdir_filter(fd_data, pf, add); - - if (ret) { - dev_info(&pf->pdev->dev, - "Filter command send failed for PCTYPE %d (ret = %d)\n", - fd_data->pctype, ret); - err = true; - } else { - dev_info(&pf->pdev->dev, - "Filter OK for PCTYPE %d (ret = %d)\n", - fd_data->pctype, ret); - } - } + ret = i40e_update_ethtool_fdir_entry(vsi, NULL, fsp->location, cmd); - return err ? -EOPNOTSUPP : 0; + return ret; } /** - * i40e_add_del_fdir_ethtool - Add/Remove Flow Director filters for - * a specific flow spec based on their protocol + * i40e_add_del_fdir_ethtool - Add/Remove Flow Director filters * @vsi: pointer to the targeted VSI * @cmd: command to get or set RX flow classification rules * @add: true adds a filter, false removes it * - * Returns 0 if the filters were successfully added or removed + * Add/Remove Flow Director filters for a specific flow spec based on their + * protocol. Returns 0 if the filters were successfully added or removed. **/ static int i40e_add_del_fdir_ethtool(struct i40e_vsi *vsi, - struct ethtool_rxnfc *cmd, bool add) + struct ethtool_rxnfc *cmd, bool add) { - struct i40e_fdir_data fd_data; - int ret = -EINVAL; + struct ethtool_rx_flow_spec *fsp; + struct i40e_fdir_filter *input; struct i40e_pf *pf; - struct ethtool_rx_flow_spec *fsp = - (struct ethtool_rx_flow_spec *)&cmd->fs; + int ret = -EINVAL; if (!vsi) return -EINVAL; + fsp = (struct ethtool_rx_flow_spec *)&cmd->fs; pf = vsi->back; - if ((fsp->ring_cookie != RX_CLS_FLOW_DISC) && - (fsp->ring_cookie >= vsi->num_queue_pairs)) + if (fsp->location >= (pf->hw.func_caps.fd_filters_best_effort + + pf->hw.func_caps.fd_filters_guaranteed)) { return -EINVAL; + } - /* Populate the Flow Director that we have at the moment - * and allocate the raw packet buffer for the calling functions - */ - fd_data.raw_packet = kzalloc(I40E_FDIR_MAX_RAW_PACKET_LOOKUP, - GFP_KERNEL); + if ((fsp->ring_cookie >= vsi->num_queue_pairs) && add) + return -EINVAL; - if (!fd_data.raw_packet) { - dev_info(&pf->pdev->dev, "Could not allocate memory\n"); - return -ENOMEM; - } + input = kzalloc(sizeof(*input), GFP_KERNEL); - fd_data.q_index = fsp->ring_cookie; - fd_data.flex_off = 0; - fd_data.pctype = 0; - fd_data.dest_vsi = vsi->id; - fd_data.dest_ctl = I40E_FILTER_PROGRAM_DESC_DEST_DIRECT_PACKET_QINDEX; - fd_data.fd_status = I40E_FILTER_PROGRAM_DESC_FD_STATUS_FD_ID; - fd_data.cnt_index = 0; - fd_data.fd_id = 0; + if (!input) + return -ENOMEM; - switch (fsp->flow_type & ~FLOW_EXT) { - case TCP_V4_FLOW: - ret = i40e_add_del_fdir_tcpv4(vsi, &fd_data, fsp, add); - break; - case UDP_V4_FLOW: - ret = i40e_add_del_fdir_udpv4(vsi, &fd_data, fsp, add); - break; - case SCTP_V4_FLOW: - ret = i40e_add_del_fdir_sctpv4(vsi, &fd_data, fsp, add); - break; - case IPV4_FLOW: - ret = i40e_add_del_fdir_ipv4(vsi, &fd_data, fsp, add); - break; - case IP_USER_FLOW: - switch (fsp->h_u.usr_ip4_spec.proto) { - case IPPROTO_TCP: - ret = i40e_add_del_fdir_tcpv4(vsi, &fd_data, fsp, add); - break; - case IPPROTO_UDP: - ret = i40e_add_del_fdir_udpv4(vsi, &fd_data, fsp, add); - break; - case IPPROTO_SCTP: - ret = i40e_add_del_fdir_sctpv4(vsi, &fd_data, fsp, add); - break; - default: - ret = i40e_add_del_fdir_ipv4(vsi, &fd_data, fsp, add); - break; - } - break; - default: - dev_info(&pf->pdev->dev, "Could not specify spec type\n"); - ret = -EINVAL; + input->fd_id = fsp->location; + + input->q_index = fsp->ring_cookie; + input->flex_off = 0; + input->pctype = 0; + input->dest_vsi = vsi->id; + input->dest_ctl = I40E_FILTER_PROGRAM_DESC_DEST_DIRECT_PACKET_QINDEX; + input->fd_status = I40E_FILTER_PROGRAM_DESC_FD_STATUS_FD_ID; + input->cnt_index = 0; + input->flow_type = fsp->flow_type; + input->ip4_proto = fsp->h_u.usr_ip4_spec.proto; + input->src_port = fsp->h_u.tcp_ip4_spec.psrc; + input->dst_port = fsp->h_u.tcp_ip4_spec.pdst; + input->src_ip[0] = fsp->h_u.tcp_ip4_spec.ip4src; + input->dst_ip[0] = fsp->h_u.tcp_ip4_spec.ip4dst; + + ret = i40e_add_del_fdir(vsi, input, add); + if (ret) { + kfree(input); + return ret; } - kfree(fd_data.raw_packet); - fd_data.raw_packet = NULL; + if (!ret && add) + i40e_update_ethtool_fdir_entry(vsi, input, fsp->location, NULL); + else + kfree(input); return ret; } @@ -1583,7 +1534,7 @@ static int i40e_set_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd) ret = i40e_add_del_fdir_ethtool(vsi, cmd, true); break; case ETHTOOL_SRXCLSRLDEL: - ret = i40e_add_del_fdir_ethtool(vsi, cmd, false); + ret = i40e_del_fdir_entry(vsi, cmd); break; default: break; diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index b901371ca361..43d391bb65c4 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -38,7 +38,7 @@ static const char i40e_driver_string[] = #define DRV_VERSION_MAJOR 0 #define DRV_VERSION_MINOR 3 -#define DRV_VERSION_BUILD 30 +#define DRV_VERSION_BUILD 34 #define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \ __stringify(DRV_VERSION_MINOR) "." \ __stringify(DRV_VERSION_BUILD) DRV_KERN @@ -305,6 +305,7 @@ static void i40e_tx_timeout(struct net_device *netdev) break; default: netdev_err(netdev, "tx_timeout recovery unsuccessful\n"); + set_bit(__I40E_DOWN, &vsi->state); i40e_down(vsi); break; } @@ -1964,11 +1965,14 @@ static int i40e_vlan_rx_add_vid(struct net_device *netdev, netdev_info(netdev, "adding %pM vid=%d\n", netdev->dev_addr, vid); - /* If the network stack called us with vid = 0, we should - * indicate to i40e_vsi_add_vlan() that we want to receive - * any traffic (i.e. with any vlan tag, or untagged) + /* If the network stack called us with vid = 0 then + * it is asking to receive priority tagged packets with + * vlan id 0. Our HW receives them by default when configured + * to receive untagged packets so there is no need to add an + * extra filter for vlan 0 tagged packets. */ - ret = i40e_vsi_add_vlan(vsi, vid ? vid : I40E_VLAN_ANY); + if (vid) + ret = i40e_vsi_add_vlan(vsi, vid); if (!ret && (vid < VLAN_N_VID)) set_bit(vid, vsi->active_vlans); @@ -2420,6 +2424,25 @@ static void i40e_set_vsi_rx_mode(struct i40e_vsi *vsi) } /** + * i40e_fdir_filter_restore - Restore the Sideband Flow Director filters + * @vsi: Pointer to the targeted VSI + * + * This function replays the hlist on the hw where all the SB Flow Director + * filters were saved. + **/ +static void i40e_fdir_filter_restore(struct i40e_vsi *vsi) +{ + struct i40e_fdir_filter *filter; + struct i40e_pf *pf = vsi->back; + struct hlist_node *node; + + hlist_for_each_entry_safe(filter, node, + &pf->fdir_filter_list, fdir_node) { + i40e_add_del_fdir(vsi, filter, true); + } +} + +/** * i40e_vsi_configure - Set up the VSI for action * @vsi: the VSI being configured **/ @@ -2430,6 +2453,8 @@ static int i40e_vsi_configure(struct i40e_vsi *vsi) i40e_set_vsi_rx_mode(vsi); i40e_restore_vlan(vsi); i40e_vsi_config_dcb_rings(vsi); + if (vsi->type == I40E_VSI_FDIR) + i40e_fdir_filter_restore(vsi); err = i40e_vsi_configure_tx(vsi); if (!err) err = i40e_vsi_configure_rx(vsi); @@ -3107,13 +3132,13 @@ static int i40e_vsi_control_tx(struct i40e_vsi *vsi, bool enable) pf_q = vsi->base_queue; for (i = 0; i < vsi->num_queue_pairs; i++, pf_q++) { - j = 1000; - do { - usleep_range(1000, 2000); + for (j = 0; j < 50; j++) { tx_reg = rd32(hw, I40E_QTX_ENA(pf_q)); - } while (j-- && ((tx_reg >> I40E_QTX_ENA_QENA_REQ_SHIFT) - ^ (tx_reg >> I40E_QTX_ENA_QENA_STAT_SHIFT)) & 1); - + if (((tx_reg >> I40E_QTX_ENA_QENA_REQ_SHIFT) & 1) == + ((tx_reg >> I40E_QTX_ENA_QENA_STAT_SHIFT) & 1)) + break; + usleep_range(1000, 2000); + } /* Skip if the queue is already in the requested state */ if (enable && (tx_reg & I40E_QTX_ENA_QENA_STAT_MASK)) continue; @@ -3123,8 +3148,7 @@ static int i40e_vsi_control_tx(struct i40e_vsi *vsi, bool enable) /* turn on/off the queue */ if (enable) { wr32(hw, I40E_QTX_HEAD(pf_q), 0); - tx_reg |= I40E_QTX_ENA_QENA_REQ_MASK | - I40E_QTX_ENA_QENA_STAT_MASK; + tx_reg |= I40E_QTX_ENA_QENA_REQ_MASK; } else { tx_reg &= ~I40E_QTX_ENA_QENA_REQ_MASK; } @@ -3171,12 +3195,13 @@ static int i40e_vsi_control_rx(struct i40e_vsi *vsi, bool enable) pf_q = vsi->base_queue; for (i = 0; i < vsi->num_queue_pairs; i++, pf_q++) { - j = 1000; - do { - usleep_range(1000, 2000); + for (j = 0; j < 50; j++) { rx_reg = rd32(hw, I40E_QRX_ENA(pf_q)); - } while (j-- && ((rx_reg >> I40E_QRX_ENA_QENA_REQ_SHIFT) - ^ (rx_reg >> I40E_QRX_ENA_QENA_STAT_SHIFT)) & 1); + if (((rx_reg >> I40E_QRX_ENA_QENA_REQ_SHIFT) & 1) == + ((rx_reg >> I40E_QRX_ENA_QENA_STAT_SHIFT) & 1)) + break; + usleep_range(1000, 2000); + } if (enable) { /* is STAT set ? */ @@ -3190,11 +3215,9 @@ static int i40e_vsi_control_rx(struct i40e_vsi *vsi, bool enable) /* turn on/off the queue */ if (enable) - rx_reg |= I40E_QRX_ENA_QENA_REQ_MASK | - I40E_QRX_ENA_QENA_STAT_MASK; + rx_reg |= I40E_QRX_ENA_QENA_REQ_MASK; else - rx_reg &= ~(I40E_QRX_ENA_QENA_REQ_MASK | - I40E_QRX_ENA_QENA_STAT_MASK); + rx_reg &= ~I40E_QRX_ENA_QENA_REQ_MASK; wr32(hw, I40E_QRX_ENA(pf_q), rx_reg); /* wait for the change to finish */ @@ -4269,6 +4292,26 @@ err_setup_tx: } /** + * i40e_fdir_filter_exit - Cleans up the Flow Director accounting + * @pf: Pointer to pf + * + * This function destroys the hlist where all the Flow Director + * filters were saved. + **/ +static void i40e_fdir_filter_exit(struct i40e_pf *pf) +{ + struct i40e_fdir_filter *filter; + struct hlist_node *node2; + + hlist_for_each_entry_safe(filter, node2, + &pf->fdir_filter_list, fdir_node) { + hlist_del(&filter->fdir_node); + kfree(filter); + } + pf->fdir_pf_active_filters = 0; +} + +/** * i40e_close - Disables a network interface * @netdev: network interface device structure * @@ -5053,6 +5096,12 @@ static int i40e_get_capabilities(struct i40e_pf *pf) /* increment MSI-X count because current FW skips one */ pf->hw.func_caps.num_msix_vectors++; + if (((pf->hw.aq.fw_maj_ver == 2) && (pf->hw.aq.fw_min_ver < 22)) || + (pf->hw.aq.fw_maj_ver < 2)) { + pf->hw.func_caps.num_msix_vectors++; + pf->hw.func_caps.num_msix_vectors_vf++; + } + if (pf->hw.debug_mask & I40E_DEBUG_USER) dev_info(&pf->pdev->dev, "pf=%d, num_vfs=%d, msix_pf=%d, msix_vf=%d, fd_g=%d, fd_b=%d, pf_max_q=%d num_vsi=%d\n", @@ -5132,9 +5181,9 @@ static void i40e_fdir_sb_setup(struct i40e_pf *pf) err = i40e_up_complete(vsi); if (err) goto err_up_complete; + clear_bit(__I40E_NEEDS_RESTART, &vsi->state); } - clear_bit(__I40E_NEEDS_RESTART, &vsi->state); return; err_up_complete: @@ -5157,6 +5206,7 @@ static void i40e_fdir_teardown(struct i40e_pf *pf) { int i; + i40e_fdir_filter_exit(pf); for (i = 0; i < pf->hw.func_caps.num_vsis; i++) { if (pf->vsi[i] && pf->vsi[i]->type == I40E_VSI_FDIR) { i40e_vsi_release(pf->vsi[i]); @@ -5331,6 +5381,11 @@ static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit) /* restart the VSIs that were rebuilt and running before the reset */ i40e_pf_unquiesce_all_vsi(pf); + if (pf->num_alloc_vfs) { + for (v = 0; v < pf->num_alloc_vfs; v++) + i40e_reset_vf(&pf->vf[v], true); + } + /* tell the firmware that we're starting */ dv.major_version = DRV_VERSION_MAJOR; dv.minor_version = DRV_VERSION_MINOR; @@ -5850,37 +5905,16 @@ err_out: **/ static int i40e_reserve_msix_vectors(struct i40e_pf *pf, int vectors) { - int err = 0; - - pf->num_msix_entries = 0; - while (vectors >= I40E_MIN_MSIX) { - err = pci_enable_msix(pf->pdev, pf->msix_entries, vectors); - if (err == 0) { - /* good to go */ - pf->num_msix_entries = vectors; - break; - } else if (err < 0) { - /* total failure */ - dev_info(&pf->pdev->dev, - "MSI-X vector reservation failed: %d\n", err); - vectors = 0; - break; - } else { - /* err > 0 is the hint for retry */ - dev_info(&pf->pdev->dev, - "MSI-X vectors wanted %d, retrying with %d\n", - vectors, err); - vectors = err; - } - } - - if (vectors > 0 && vectors < I40E_MIN_MSIX) { + vectors = pci_enable_msix_range(pf->pdev, pf->msix_entries, + I40E_MIN_MSIX, vectors); + if (vectors < 0) { dev_info(&pf->pdev->dev, - "Couldn't get enough vectors, only %d available\n", - vectors); + "MSI-X vector reservation failed: %d\n", vectors); vectors = 0; } + pf->num_msix_entries = vectors; + return vectors; } @@ -5942,7 +5976,7 @@ static int i40e_init_msix(struct i40e_pf *pf) } else if (vec == I40E_MIN_MSIX) { /* Adjust for minimal MSIX use */ - dev_info(&pf->pdev->dev, "Features disabled, not enough MSIX vectors\n"); + dev_info(&pf->pdev->dev, "Features disabled, not enough MSI-X vectors\n"); pf->flags &= ~I40E_FLAG_VMDQ_ENABLED; pf->num_vmdq_vsis = 0; pf->num_vmdq_qps = 0; @@ -6071,7 +6105,7 @@ static void i40e_init_interrupt_scheme(struct i40e_pf *pf) if (!(pf->flags & I40E_FLAG_MSIX_ENABLED) && (pf->flags & I40E_FLAG_MSI_ENABLED)) { - dev_info(&pf->pdev->dev, "MSIX not available, trying MSI\n"); + dev_info(&pf->pdev->dev, "MSI-X not available, trying MSI\n"); err = pci_enable_msi(pf->pdev); if (err) { dev_info(&pf->pdev->dev, "MSI init failed - %d\n", err); @@ -6080,7 +6114,7 @@ static void i40e_init_interrupt_scheme(struct i40e_pf *pf) } if (!(pf->flags & (I40E_FLAG_MSIX_ENABLED | I40E_FLAG_MSI_ENABLED))) - dev_info(&pf->pdev->dev, "MSIX and MSI not available, falling back to Legacy IRQ\n"); + dev_info(&pf->pdev->dev, "MSI-X and MSI not available, falling back to Legacy IRQ\n"); /* track first vector for misc interrupts */ err = i40e_get_lump(pf, pf->irq_pile, 1, I40E_PILE_VALID_BIT-1); @@ -6107,7 +6141,8 @@ static int i40e_setup_misc_vector(struct i40e_pf *pf) i40e_intr, 0, pf->misc_int_name, pf); if (err) { dev_info(&pf->pdev->dev, - "request_irq for msix_misc failed: %d\n", err); + "request_irq for %s failed: %d\n", + pf->misc_int_name, err); return -EFAULT; } } @@ -7946,13 +7981,6 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) err = i40e_init_adminq(hw); dev_info(&pdev->dev, "%s\n", i40e_fw_version_str(hw)); - if (((hw->nvm.version & I40E_NVM_VERSION_HI_MASK) - >> I40E_NVM_VERSION_HI_SHIFT) != I40E_CURRENT_NVM_VERSION_HI) { - dev_info(&pdev->dev, - "warning: NVM version not supported, supported version: %02x.%02x\n", - I40E_CURRENT_NVM_VERSION_HI, - I40E_CURRENT_NVM_VERSION_LO); - } if (err) { dev_info(&pdev->dev, "init_adminq failed: %d expecting API %02x.%02x\n", @@ -8070,6 +8098,16 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) val &= ~I40E_PFGEN_PORTMDIO_NUM_VFLINK_STAT_ENA_MASK; wr32(hw, I40E_PFGEN_PORTMDIO_NUM, val); i40e_flush(hw); + + if (pci_num_vf(pdev)) { + dev_info(&pdev->dev, + "Active VFs found, allocating resources.\n"); + err = i40e_alloc_vfs(pf, pci_num_vf(pdev)); + if (err) + dev_info(&pdev->dev, + "Error %d allocating resources for existing VFs\n", + err); + } } pfs_found++; @@ -8165,16 +8203,16 @@ static void i40e_remove(struct pci_dev *pdev) i40e_ptp_stop(pf); - if (pf->flags & I40E_FLAG_SRIOV_ENABLED) { - i40e_free_vfs(pf); - pf->flags &= ~I40E_FLAG_SRIOV_ENABLED; - } - /* no more scheduling of any task */ set_bit(__I40E_DOWN, &pf->state); del_timer_sync(&pf->service_timer); cancel_work_sync(&pf->service_task); + if (pf->flags & I40E_FLAG_SRIOV_ENABLED) { + i40e_free_vfs(pf); + pf->flags &= ~I40E_FLAG_SRIOV_ENABLED; + } + i40e_fdir_teardown(pf); /* If there is a switch structure or any orphans, remove them. diff --git a/drivers/net/ethernet/intel/i40e/i40e_nvm.c b/drivers/net/ethernet/intel/i40e/i40e_nvm.c index 73f95b081927..262bdf11d221 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_nvm.c +++ b/drivers/net/ethernet/intel/i40e/i40e_nvm.c @@ -27,14 +27,14 @@ #include "i40e_prototype.h" /** - * i40e_init_nvm_ops - Initialize NVM function pointers. - * @hw: pointer to the HW structure. + * i40e_init_nvm_ops - Initialize NVM function pointers + * @hw: pointer to the HW structure * - * Setups the function pointers and the NVM info structure. Should be called - * once per NVM initialization, e.g. inside the i40e_init_shared_code(). - * Please notice that the NVM term is used here (& in all methods covered - * in this file) as an equivalent of the FLASH part mapped into the SR. - * We are accessing FLASH always thru the Shadow RAM. + * Setup the function pointers and the NVM info structure. Should be called + * once per NVM initialization, e.g. inside the i40e_init_shared_code(). + * Please notice that the NVM term is used here (& in all methods covered + * in this file) as an equivalent of the FLASH part mapped into the SR. + * We are accessing FLASH always thru the Shadow RAM. **/ i40e_status i40e_init_nvm(struct i40e_hw *hw) { @@ -49,16 +49,16 @@ i40e_status i40e_init_nvm(struct i40e_hw *hw) gens = rd32(hw, I40E_GLNVM_GENS); sr_size = ((gens & I40E_GLNVM_GENS_SR_SIZE_MASK) >> I40E_GLNVM_GENS_SR_SIZE_SHIFT); - /* Switching to words (sr_size contains power of 2KB). */ + /* Switching to words (sr_size contains power of 2KB) */ nvm->sr_size = (1 << sr_size) * I40E_SR_WORDS_IN_1KB; - /* Check if we are in the normal or blank NVM programming mode. */ + /* Check if we are in the normal or blank NVM programming mode */ fla = rd32(hw, I40E_GLNVM_FLA); - if (fla & I40E_GLNVM_FLA_LOCKED_MASK) { /* Normal programming mode. */ - /* Max NVM timeout. */ + if (fla & I40E_GLNVM_FLA_LOCKED_MASK) { /* Normal programming mode */ + /* Max NVM timeout */ nvm->timeout = I40E_MAX_NVM_TIMEOUT; nvm->blank_nvm_mode = false; - } else { /* Blank programming mode. */ + } else { /* Blank programming mode */ nvm->blank_nvm_mode = true; ret_code = I40E_ERR_NVM_BLANK_MODE; hw_dbg(hw, "NVM init error: unsupported blank mode.\n"); @@ -68,12 +68,12 @@ i40e_status i40e_init_nvm(struct i40e_hw *hw) } /** - * i40e_acquire_nvm - Generic request for acquiring the NVM ownership. - * @hw: pointer to the HW structure. - * @access: NVM access type (read or write). + * i40e_acquire_nvm - Generic request for acquiring the NVM ownership + * @hw: pointer to the HW structure + * @access: NVM access type (read or write) * - * This function will request NVM ownership for reading - * via the proper Admin Command. + * This function will request NVM ownership for reading + * via the proper Admin Command. **/ i40e_status i40e_acquire_nvm(struct i40e_hw *hw, enum i40e_aq_resource_access_type access) @@ -87,20 +87,20 @@ i40e_status i40e_acquire_nvm(struct i40e_hw *hw, ret_code = i40e_aq_request_resource(hw, I40E_NVM_RESOURCE_ID, access, 0, &time, NULL); - /* Reading the Global Device Timer. */ + /* Reading the Global Device Timer */ gtime = rd32(hw, I40E_GLVFGEN_TIMER); - /* Store the timeout. */ + /* Store the timeout */ hw->nvm.hw_semaphore_timeout = I40E_MS_TO_GTIME(time) + gtime; if (ret_code) { - /* Set the polling timeout. */ + /* Set the polling timeout */ if (time > I40E_MAX_NVM_TIMEOUT) timeout = I40E_MS_TO_GTIME(I40E_MAX_NVM_TIMEOUT) + gtime; else timeout = hw->nvm.hw_semaphore_timeout; - /* Poll until the current NVM owner timeouts. */ + /* Poll until the current NVM owner timeouts */ while (gtime < timeout) { usleep_range(10000, 20000); ret_code = i40e_aq_request_resource(hw, @@ -128,10 +128,10 @@ i40e_i40e_acquire_nvm_exit: } /** - * i40e_release_nvm - Generic request for releasing the NVM ownership. - * @hw: pointer to the HW structure. + * i40e_release_nvm - Generic request for releasing the NVM ownership + * @hw: pointer to the HW structure * - * This function will release NVM resource via the proper Admin Command. + * This function will release NVM resource via the proper Admin Command. **/ void i40e_release_nvm(struct i40e_hw *hw) { @@ -140,17 +140,17 @@ void i40e_release_nvm(struct i40e_hw *hw) } /** - * i40e_poll_sr_srctl_done_bit - Polls the GLNVM_SRCTL done bit. - * @hw: pointer to the HW structure. + * i40e_poll_sr_srctl_done_bit - Polls the GLNVM_SRCTL done bit + * @hw: pointer to the HW structure * - * Polls the SRCTL Shadow RAM register done bit. + * Polls the SRCTL Shadow RAM register done bit. **/ static i40e_status i40e_poll_sr_srctl_done_bit(struct i40e_hw *hw) { i40e_status ret_code = I40E_ERR_TIMEOUT; u32 srctl, wait_cnt; - /* Poll the I40E_GLNVM_SRCTL until the done bit is set. */ + /* Poll the I40E_GLNVM_SRCTL until the done bit is set */ for (wait_cnt = 0; wait_cnt < I40E_SRRD_SRCTL_ATTEMPTS; wait_cnt++) { srctl = rd32(hw, I40E_GLNVM_SRCTL); if (srctl & I40E_GLNVM_SRCTL_DONE_MASK) { @@ -165,12 +165,12 @@ static i40e_status i40e_poll_sr_srctl_done_bit(struct i40e_hw *hw) } /** - * i40e_read_nvm_word - Reads Shadow RAM - * @hw: pointer to the HW structure. - * @offset: offset of the Shadow RAM word to read (0x000000 - 0x001FFF). - * @data: word read from the Shadow RAM. + * i40e_read_nvm_word - Reads Shadow RAM + * @hw: pointer to the HW structure + * @offset: offset of the Shadow RAM word to read (0x000000 - 0x001FFF) + * @data: word read from the Shadow RAM * - * Reads 16 bit word from the Shadow RAM using the GLNVM_SRCTL register. + * Reads one 16 bit word from the Shadow RAM using the GLNVM_SRCTL register. **/ i40e_status i40e_read_nvm_word(struct i40e_hw *hw, u16 offset, u16 *data) @@ -184,15 +184,15 @@ i40e_status i40e_read_nvm_word(struct i40e_hw *hw, u16 offset, goto read_nvm_exit; } - /* Poll the done bit first. */ + /* Poll the done bit first */ ret_code = i40e_poll_sr_srctl_done_bit(hw); if (!ret_code) { - /* Write the address and start reading. */ + /* Write the address and start reading */ sr_reg = (u32)(offset << I40E_GLNVM_SRCTL_ADDR_SHIFT) | (1 << I40E_GLNVM_SRCTL_START_SHIFT); wr32(hw, I40E_GLNVM_SRCTL, sr_reg); - /* Poll I40E_GLNVM_SRCTL until the done bit is set. */ + /* Poll I40E_GLNVM_SRCTL until the done bit is set */ ret_code = i40e_poll_sr_srctl_done_bit(hw); if (!ret_code) { sr_reg = rd32(hw, I40E_GLNVM_SRDATA); @@ -210,16 +210,15 @@ read_nvm_exit: } /** - * i40e_read_nvm_buffer - Reads Shadow RAM buffer. - * @hw: pointer to the HW structure. - * @offset: offset of the Shadow RAM word to read (0x000000 - 0x001FFF). - * @words: number of words to read (in) & - * number of words read before the NVM ownership timeout (out). - * @data: words read from the Shadow RAM. + * i40e_read_nvm_buffer - Reads Shadow RAM buffer + * @hw: pointer to the HW structure + * @offset: offset of the Shadow RAM word to read (0x000000 - 0x001FFF). + * @words: (in) number of words to read; (out) number of words actually read + * @data: words read from the Shadow RAM * - * Reads 16 bit words (data buffer) from the SR using the i40e_read_nvm_srrd() - * method. The buffer read is preceded by the NVM ownership take - * and followed by the release. + * Reads 16 bit words (data buffer) from the SR using the i40e_read_nvm_srrd() + * method. The buffer read is preceded by the NVM ownership take + * and followed by the release. **/ i40e_status i40e_read_nvm_buffer(struct i40e_hw *hw, u16 offset, u16 *words, u16 *data) @@ -227,7 +226,7 @@ i40e_status i40e_read_nvm_buffer(struct i40e_hw *hw, u16 offset, i40e_status ret_code = 0; u16 index, word; - /* Loop thru the selected region. */ + /* Loop thru the selected region */ for (word = 0; word < *words; word++) { index = offset + word; ret_code = i40e_read_nvm_word(hw, index, &data[word]); @@ -235,21 +234,21 @@ i40e_status i40e_read_nvm_buffer(struct i40e_hw *hw, u16 offset, break; } - /* Update the number of words read from the Shadow RAM. */ + /* Update the number of words read from the Shadow RAM */ *words = word; return ret_code; } /** - * i40e_calc_nvm_checksum - Calculates and returns the checksum - * @hw: pointer to hardware structure - * @checksum: pointer to the checksum + * i40e_calc_nvm_checksum - Calculates and returns the checksum + * @hw: pointer to hardware structure + * @checksum: pointer to the checksum * - * This function calculate SW Checksum that covers the whole 64kB shadow RAM - * except the VPD and PCIe ALT Auto-load modules. The structure and size of VPD - * is customer specific and unknown. Therefore, this function skips all maximum - * possible size of VPD (1kB). + * This function calculates SW Checksum that covers the whole 64kB shadow RAM + * except the VPD and PCIe ALT Auto-load modules. The structure and size of VPD + * is customer specific and unknown. Therefore, this function skips all maximum + * possible size of VPD (1kB). **/ static i40e_status i40e_calc_nvm_checksum(struct i40e_hw *hw, u16 *checksum) @@ -311,12 +310,12 @@ i40e_calc_nvm_checksum_exit: } /** - * i40e_validate_nvm_checksum - Validate EEPROM checksum - * @hw: pointer to hardware structure - * @checksum: calculated checksum + * i40e_validate_nvm_checksum - Validate EEPROM checksum + * @hw: pointer to hardware structure + * @checksum: calculated checksum * - * Performs checksum calculation and validates the NVM SW checksum. If the - * caller does not need checksum, the value can be NULL. + * Performs checksum calculation and validates the NVM SW checksum. If the + * caller does not need checksum, the value can be NULL. **/ i40e_status i40e_validate_nvm_checksum(struct i40e_hw *hw, u16 *checksum) diff --git a/drivers/net/ethernet/intel/i40e/i40e_prototype.h b/drivers/net/ethernet/intel/i40e/i40e_prototype.h index ed91f93ede2b..9cd57e617959 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_prototype.h +++ b/drivers/net/ethernet/intel/i40e/i40e_prototype.h @@ -231,6 +231,13 @@ i40e_status i40e_validate_nvm_checksum(struct i40e_hw *hw, u16 *checksum); void i40e_set_pci_config_data(struct i40e_hw *hw, u16 link_status); +extern struct i40e_rx_ptype_decoded i40e_ptype_lookup[]; + +static inline struct i40e_rx_ptype_decoded decode_rx_desc_ptype(u8 ptype) +{ + return i40e_ptype_lookup[ptype]; +} + /* prototype for functions used for SW locks */ /* i40e_common for VF drivers*/ diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index d4bb482b1a7f..2081bdb214e5 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -25,6 +25,7 @@ ******************************************************************************/ #include "i40e.h" +#include "i40e_prototype.h" static inline __le64 build_ctob(u32 td_cmd, u32 td_offset, unsigned int size, u32 td_tag) @@ -39,11 +40,12 @@ static inline __le64 build_ctob(u32 td_cmd, u32 td_offset, unsigned int size, #define I40E_TXD_CMD (I40E_TX_DESC_CMD_EOP | I40E_TX_DESC_CMD_RS) /** * i40e_program_fdir_filter - Program a Flow Director filter - * @fdir_input: Packet data that will be filter parameters + * @fdir_data: Packet data that will be filter parameters + * @raw_packet: the pre-allocated packet buffer for FDir * @pf: The pf pointer * @add: True for add/update, False for remove **/ -int i40e_program_fdir_filter(struct i40e_fdir_data *fdir_data, +int i40e_program_fdir_filter(struct i40e_fdir_filter *fdir_data, u8 *raw_packet, struct i40e_pf *pf, bool add) { struct i40e_filter_program_desc *fdir_desc; @@ -68,8 +70,8 @@ int i40e_program_fdir_filter(struct i40e_fdir_data *fdir_data, tx_ring = vsi->tx_rings[0]; dev = tx_ring->dev; - dma = dma_map_single(dev, fdir_data->raw_packet, - I40E_FDIR_MAX_RAW_PACKET_LOOKUP, DMA_TO_DEVICE); + dma = dma_map_single(dev, raw_packet, + I40E_FDIR_MAX_RAW_PACKET_SIZE, DMA_TO_DEVICE); if (dma_mapping_error(dev, dma)) goto dma_fail; @@ -132,14 +134,14 @@ int i40e_program_fdir_filter(struct i40e_fdir_data *fdir_data, tx_ring->next_to_use = (i + 1 < tx_ring->count) ? i + 1 : 0; /* record length, and DMA address */ - dma_unmap_len_set(tx_buf, len, I40E_FDIR_MAX_RAW_PACKET_LOOKUP); + dma_unmap_len_set(tx_buf, len, I40E_FDIR_MAX_RAW_PACKET_SIZE); dma_unmap_addr_set(tx_buf, dma, dma); tx_desc->buffer_addr = cpu_to_le64(dma); td_cmd = I40E_TXD_CMD | I40E_TX_DESC_CMD_DUMMY; tx_desc->cmd_type_offset_bsz = - build_ctob(td_cmd, 0, I40E_FDIR_MAX_RAW_PACKET_LOOKUP, 0); + build_ctob(td_cmd, 0, I40E_FDIR_MAX_RAW_PACKET_SIZE, 0); /* set the timestamp */ tx_buf->time_stamp = jiffies; @@ -161,6 +163,270 @@ dma_fail: return -1; } +#define IP_HEADER_OFFSET 14 +#define I40E_UDPIP_DUMMY_PACKET_LEN 42 +/** + * i40e_add_del_fdir_udpv4 - Add/Remove UDPv4 filters + * @vsi: pointer to the targeted VSI + * @fd_data: the flow director data required for the FDir descriptor + * @raw_packet: the pre-allocated packet buffer for FDir + * @add: true adds a filter, false removes it + * + * Returns 0 if the filters were successfully added or removed + **/ +static int i40e_add_del_fdir_udpv4(struct i40e_vsi *vsi, + struct i40e_fdir_filter *fd_data, + u8 *raw_packet, bool add) +{ + struct i40e_pf *pf = vsi->back; + struct udphdr *udp; + struct iphdr *ip; + bool err = false; + int ret; + int i; + static char packet[] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x08, 0, + 0x45, 0, 0, 0x1c, 0, 0, 0x40, 0, 0x40, 0x11, 0, 0, 0, 0, 0, 0, + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0}; + + memcpy(raw_packet, packet, I40E_UDPIP_DUMMY_PACKET_LEN); + + ip = (struct iphdr *)(raw_packet + IP_HEADER_OFFSET); + udp = (struct udphdr *)(raw_packet + IP_HEADER_OFFSET + + sizeof(struct iphdr)); + + ip->daddr = fd_data->dst_ip[0]; + udp->dest = fd_data->dst_port; + ip->saddr = fd_data->src_ip[0]; + udp->source = fd_data->src_port; + + for (i = I40E_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP; + i <= I40E_FILTER_PCTYPE_NONF_IPV4_UDP; i++) { + fd_data->pctype = i; + ret = i40e_program_fdir_filter(fd_data, raw_packet, pf, add); + + if (ret) { + dev_info(&pf->pdev->dev, + "Filter command send failed for PCTYPE %d (ret = %d)\n", + fd_data->pctype, ret); + err = true; + } else { + dev_info(&pf->pdev->dev, + "Filter OK for PCTYPE %d (ret = %d)\n", + fd_data->pctype, ret); + } + } + + return err ? -EOPNOTSUPP : 0; +} + +#define I40E_TCPIP_DUMMY_PACKET_LEN 54 +/** + * i40e_add_del_fdir_tcpv4 - Add/Remove TCPv4 filters + * @vsi: pointer to the targeted VSI + * @fd_data: the flow director data required for the FDir descriptor + * @raw_packet: the pre-allocated packet buffer for FDir + * @add: true adds a filter, false removes it + * + * Returns 0 if the filters were successfully added or removed + **/ +static int i40e_add_del_fdir_tcpv4(struct i40e_vsi *vsi, + struct i40e_fdir_filter *fd_data, + u8 *raw_packet, bool add) +{ + struct i40e_pf *pf = vsi->back; + struct tcphdr *tcp; + struct iphdr *ip; + bool err = false; + int ret; + /* Dummy packet */ + static char packet[] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x08, 0, + 0x45, 0, 0, 0x28, 0, 0, 0x40, 0, 0x40, 0x6, 0, 0, 0, 0, 0, 0, + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x80, 0x11, + 0x0, 0x72, 0, 0, 0, 0}; + + memcpy(raw_packet, packet, I40E_TCPIP_DUMMY_PACKET_LEN); + + ip = (struct iphdr *)(raw_packet + IP_HEADER_OFFSET); + tcp = (struct tcphdr *)(raw_packet + IP_HEADER_OFFSET + + sizeof(struct iphdr)); + + ip->daddr = fd_data->dst_ip[0]; + tcp->dest = fd_data->dst_port; + ip->saddr = fd_data->src_ip[0]; + tcp->source = fd_data->src_port; + + if (add) { + if (pf->flags & I40E_FLAG_FD_ATR_ENABLED) { + dev_info(&pf->pdev->dev, "Forcing ATR off, sideband rules for TCP/IPv4 flow being applied\n"); + pf->flags &= ~I40E_FLAG_FD_ATR_ENABLED; + } + } + + fd_data->pctype = I40E_FILTER_PCTYPE_NONF_IPV4_TCP_SYN; + ret = i40e_program_fdir_filter(fd_data, raw_packet, pf, add); + + if (ret) { + dev_info(&pf->pdev->dev, + "Filter command send failed for PCTYPE %d (ret = %d)\n", + fd_data->pctype, ret); + err = true; + } else { + dev_info(&pf->pdev->dev, "Filter OK for PCTYPE %d (ret = %d)\n", + fd_data->pctype, ret); + } + + fd_data->pctype = I40E_FILTER_PCTYPE_NONF_IPV4_TCP; + + ret = i40e_program_fdir_filter(fd_data, raw_packet, pf, add); + if (ret) { + dev_info(&pf->pdev->dev, + "Filter command send failed for PCTYPE %d (ret = %d)\n", + fd_data->pctype, ret); + err = true; + } else { + dev_info(&pf->pdev->dev, "Filter OK for PCTYPE %d (ret = %d)\n", + fd_data->pctype, ret); + } + + return err ? -EOPNOTSUPP : 0; +} + +/** + * i40e_add_del_fdir_sctpv4 - Add/Remove SCTPv4 Flow Director filters for + * a specific flow spec + * @vsi: pointer to the targeted VSI + * @fd_data: the flow director data required for the FDir descriptor + * @raw_packet: the pre-allocated packet buffer for FDir + * @add: true adds a filter, false removes it + * + * Returns 0 if the filters were successfully added or removed + **/ +static int i40e_add_del_fdir_sctpv4(struct i40e_vsi *vsi, + struct i40e_fdir_filter *fd_data, + u8 *raw_packet, bool add) +{ + return -EOPNOTSUPP; +} + +#define I40E_IP_DUMMY_PACKET_LEN 34 +/** + * i40e_add_del_fdir_ipv4 - Add/Remove IPv4 Flow Director filters for + * a specific flow spec + * @vsi: pointer to the targeted VSI + * @fd_data: the flow director data required for the FDir descriptor + * @raw_packet: the pre-allocated packet buffer for FDir + * @add: true adds a filter, false removes it + * + * Returns 0 if the filters were successfully added or removed + **/ +static int i40e_add_del_fdir_ipv4(struct i40e_vsi *vsi, + struct i40e_fdir_filter *fd_data, + u8 *raw_packet, bool add) +{ + struct i40e_pf *pf = vsi->back; + struct iphdr *ip; + bool err = false; + int ret; + int i; + static char packet[] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x08, 0, + 0x45, 0, 0, 0x14, 0, 0, 0x40, 0, 0x40, 0x10, 0, 0, 0, 0, 0, 0, + 0, 0, 0, 0}; + + memcpy(raw_packet, packet, I40E_IP_DUMMY_PACKET_LEN); + ip = (struct iphdr *)(raw_packet + IP_HEADER_OFFSET); + + ip->saddr = fd_data->src_ip[0]; + ip->daddr = fd_data->dst_ip[0]; + ip->protocol = 0; + + for (i = I40E_FILTER_PCTYPE_NONF_IPV4_OTHER; + i <= I40E_FILTER_PCTYPE_FRAG_IPV4; i++) { + fd_data->pctype = i; + ret = i40e_program_fdir_filter(fd_data, raw_packet, pf, add); + + if (ret) { + dev_info(&pf->pdev->dev, + "Filter command send failed for PCTYPE %d (ret = %d)\n", + fd_data->pctype, ret); + err = true; + } else { + dev_info(&pf->pdev->dev, + "Filter OK for PCTYPE %d (ret = %d)\n", + fd_data->pctype, ret); + } + } + + return err ? -EOPNOTSUPP : 0; +} + +/** + * i40e_add_del_fdir - Build raw packets to add/del fdir filter + * @vsi: pointer to the targeted VSI + * @cmd: command to get or set RX flow classification rules + * @add: true adds a filter, false removes it + * + **/ +int i40e_add_del_fdir(struct i40e_vsi *vsi, + struct i40e_fdir_filter *input, bool add) +{ + struct i40e_pf *pf = vsi->back; + u8 *raw_packet; + int ret; + + /* Populate the Flow Director that we have at the moment + * and allocate the raw packet buffer for the calling functions + */ + raw_packet = kzalloc(I40E_FDIR_MAX_RAW_PACKET_SIZE, GFP_KERNEL); + if (!raw_packet) + return -ENOMEM; + + switch (input->flow_type & ~FLOW_EXT) { + case TCP_V4_FLOW: + ret = i40e_add_del_fdir_tcpv4(vsi, input, raw_packet, + add); + break; + case UDP_V4_FLOW: + ret = i40e_add_del_fdir_udpv4(vsi, input, raw_packet, + add); + break; + case SCTP_V4_FLOW: + ret = i40e_add_del_fdir_sctpv4(vsi, input, raw_packet, + add); + break; + case IPV4_FLOW: + ret = i40e_add_del_fdir_ipv4(vsi, input, raw_packet, + add); + break; + case IP_USER_FLOW: + switch (input->ip4_proto) { + case IPPROTO_TCP: + ret = i40e_add_del_fdir_tcpv4(vsi, input, + raw_packet, add); + break; + case IPPROTO_UDP: + ret = i40e_add_del_fdir_udpv4(vsi, input, + raw_packet, add); + break; + case IPPROTO_SCTP: + ret = i40e_add_del_fdir_sctpv4(vsi, input, + raw_packet, add); + break; + default: + ret = i40e_add_del_fdir_ipv4(vsi, input, + raw_packet, add); + break; + } + break; + default: + dev_info(&pf->pdev->dev, "Could not specify spec type %d", + input->flow_type); + ret = -EINVAL; + } + + kfree(raw_packet); + return ret; +} + /** * i40e_fd_handle_status - check the Programming Status for FD * @rx_ring: the Rx ring for this descriptor @@ -892,7 +1158,7 @@ static inline void i40e_rx_checksum(struct i40e_vsi *vsi, rx_status & (1 << I40E_RX_DESC_STATUS_L3L4P_SHIFT))) return; - /* likely incorrect csum if alternate IP extention headers found */ + /* likely incorrect csum if alternate IP extension headers found */ if (rx_status & (1 << I40E_RX_DESC_STATUS_IPV6EXADD_SHIFT)) return; @@ -956,6 +1222,29 @@ static inline u32 i40e_rx_hash(struct i40e_ring *ring, } /** + * i40e_ptype_to_hash - get a hash type + * @ptype: the ptype value from the descriptor + * + * Returns a hash type to be used by skb_set_hash + **/ +static inline enum pkt_hash_types i40e_ptype_to_hash(u8 ptype) +{ + struct i40e_rx_ptype_decoded decoded = decode_rx_desc_ptype(ptype); + + if (!decoded.known) + return PKT_HASH_TYPE_NONE; + + if (decoded.outer_ip == I40E_RX_PTYPE_OUTER_IP && + decoded.payload_layer == I40E_RX_PTYPE_PAYLOAD_LAYER_PAY4) + return PKT_HASH_TYPE_L4; + else if (decoded.outer_ip == I40E_RX_PTYPE_OUTER_IP && + decoded.payload_layer == I40E_RX_PTYPE_PAYLOAD_LAYER_PAY3) + return PKT_HASH_TYPE_L3; + else + return PKT_HASH_TYPE_L2; +} + +/** * i40e_clean_rx_irq - Reclaim resources after receive completes * @rx_ring: rx ring to clean * @budget: how many cleans we're allowed @@ -972,8 +1261,8 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) u16 i = rx_ring->next_to_clean; union i40e_rx_desc *rx_desc; u32 rx_error, rx_status; + u8 rx_ptype; u64 qword; - u16 rx_ptype; rx_desc = I40E_RX_DESC(rx_ring, i); qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len); @@ -1087,7 +1376,8 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) goto next_desc; } - skb->rxhash = i40e_rx_hash(rx_ring, rx_desc); + skb_set_hash(skb, i40e_rx_hash(rx_ring, rx_desc), + i40e_ptype_to_hash(rx_ptype)); if (unlikely(rx_status & I40E_RXD_QW1_STATUS_TSYNVALID_MASK)) { i40e_ptp_rx_hwtstamp(vsi->back, skb, (rx_status & I40E_RXD_QW1_STATUS_TSYNINDX_MASK) >> @@ -1812,7 +2102,7 @@ static int i40e_xmit_descriptor_count(struct sk_buff *skb, /* need: 1 descriptor per page * PAGE_SIZE/I40E_MAX_DATA_PER_TXD, * + 1 desc for skb_head_len/I40E_MAX_DATA_PER_TXD, - * + 2 desc gap to keep tail from touching head, + * + 4 desc gap to avoid the cache line where head is, * + 1 desc for context descriptor, * otherwise try next time */ @@ -1823,7 +2113,7 @@ static int i40e_xmit_descriptor_count(struct sk_buff *skb, count += skb_shinfo(skb)->nr_frags; #endif count += TXD_USE_COUNT(skb_headlen(skb)); - if (i40e_maybe_stop_tx(tx_ring, count + 3)) { + if (i40e_maybe_stop_tx(tx_ring, count + 4 + 1)) { tx_ring->tx_stats.tx_busy++; return 0; } diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index b9d1c1c8ca5a..42cc6ba88005 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -408,18 +408,10 @@ static int i40e_alloc_vsi_res(struct i40e_vf *vf, enum i40e_vsi_type type) "Could not allocate VF broadcast filter\n"); } - if (!f) { - dev_err(&pf->pdev->dev, "Unable to add ucast filter\n"); - ret = -ENOMEM; - goto error_alloc_vsi_res; - } - /* program mac filter */ ret = i40e_sync_vsi_filters(vsi); - if (ret) { + if (ret) dev_err(&pf->pdev->dev, "Unable to program ucast filters\n"); - goto error_alloc_vsi_res; - } error_alloc_vsi_res: return ret; @@ -679,9 +671,9 @@ void i40e_reset_vf(struct i40e_vf *vf, bool flr) complete_reset: /* reallocate vf resources to reset the VSI state */ i40e_free_vf_res(vf); - mdelay(10); i40e_alloc_vf_res(vf); i40e_enable_vf_mappings(vf); + set_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states); /* tell the VF the reset is done */ wr32(hw, I40E_VFGEN_RSTAT1(vf->vf_id), I40E_VFR_VFACTIVE); @@ -847,7 +839,7 @@ void i40e_free_vfs(struct i40e_pf *pf) * * allocate vf resources **/ -static int i40e_alloc_vfs(struct i40e_pf *pf, u16 num_alloc_vfs) +int i40e_alloc_vfs(struct i40e_pf *pf, u16 num_alloc_vfs) { struct i40e_vf *vfs; int i, ret = 0; @@ -855,16 +847,18 @@ static int i40e_alloc_vfs(struct i40e_pf *pf, u16 num_alloc_vfs) /* Disable interrupt 0 so we don't try to handle the VFLR. */ i40e_irq_dynamic_disable_icr0(pf); - ret = pci_enable_sriov(pf->pdev, num_alloc_vfs); - if (ret) { - dev_err(&pf->pdev->dev, - "pci_enable_sriov failed with error %d!\n", ret); - pf->num_alloc_vfs = 0; - goto err_iov; + /* Check to see if we're just allocating resources for extant VFs */ + if (pci_num_vf(pf->pdev) != num_alloc_vfs) { + ret = pci_enable_sriov(pf->pdev, num_alloc_vfs); + if (ret) { + dev_err(&pf->pdev->dev, + "Failed to enable SR-IOV, error %d.\n", ret); + pf->num_alloc_vfs = 0; + goto err_iov; + } } - /* allocate memory */ - vfs = kzalloc(num_alloc_vfs * sizeof(struct i40e_vf), GFP_KERNEL); + vfs = kcalloc(num_alloc_vfs, sizeof(struct i40e_vf), GFP_KERNEL); if (!vfs) { ret = -ENOMEM; goto err_alloc; @@ -1873,7 +1867,8 @@ int i40e_vc_process_vflr_event(struct i40e_pf *pf) /* clear the bit in GLGEN_VFLRSTAT */ wr32(hw, I40E_GLGEN_VFLRSTAT(reg_idx), (1 << bit_idx)); - i40e_reset_vf(vf, true); + if (!test_bit(__I40E_DOWN, &pf->state)) + i40e_reset_vf(vf, true); } } diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h index cc1feee36e12..bedf0ba21d74 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h @@ -102,6 +102,7 @@ struct i40e_vf { void i40e_free_vfs(struct i40e_pf *pf); int i40e_pci_sriov_configure(struct pci_dev *dev, int num_vfs); +int i40e_alloc_vfs(struct i40e_pf *pf, u16 num_alloc_vfs); int i40e_vc_process_vf_msg(struct i40e_pf *pf, u16 vf_id, u32 v_opcode, u32 v_retval, u8 *msg, u16 msglen); int i40e_vc_process_vflr_event(struct i40e_pf *pf); diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h index f7cea1bca38d..97662b6bd98a 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h @@ -1229,7 +1229,7 @@ struct i40e_aqc_add_remove_cloud_filters_element_data { #define I40E_AQC_ADD_CLOUD_TNL_TYPE_NGE 2 #define I40E_AQC_ADD_CLOUD_TNL_TYPE_IP 3 - __le32 tenant_id ; + __le32 tenant_id; u8 reserved[4]; __le16 queue_number; #define I40E_AQC_ADD_CLOUD_QUEUE_SHIFT 0 diff --git a/drivers/net/ethernet/intel/i40evf/i40e_common.c b/drivers/net/ethernet/intel/i40evf/i40e_common.c index 7b13953b28c4..78618af271cf 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_common.c +++ b/drivers/net/ethernet/intel/i40evf/i40e_common.c @@ -160,6 +160,372 @@ i40e_status i40evf_aq_queue_shutdown(struct i40e_hw *hw, } +/* The i40e_ptype_lookup table is used to convert from the 8-bit ptype in the + * hardware to a bit-field that can be used by SW to more easily determine the + * packet type. + * + * Macros are used to shorten the table lines and make this table human + * readable. + * + * We store the PTYPE in the top byte of the bit field - this is just so that + * we can check that the table doesn't have a row missing, as the index into + * the table should be the PTYPE. + * + * Typical work flow: + * + * IF NOT i40e_ptype_lookup[ptype].known + * THEN + * Packet is unknown + * ELSE IF i40e_ptype_lookup[ptype].outer_ip == I40E_RX_PTYPE_OUTER_IP + * Use the rest of the fields to look at the tunnels, inner protocols, etc + * ELSE + * Use the enum i40e_rx_l2_ptype to decode the packet type + * ENDIF + */ + +/* macro to make the table lines short */ +#define I40E_PTT(PTYPE, OUTER_IP, OUTER_IP_VER, OUTER_FRAG, T, TE, TEF, I, PL)\ + { PTYPE, \ + 1, \ + I40E_RX_PTYPE_OUTER_##OUTER_IP, \ + I40E_RX_PTYPE_OUTER_##OUTER_IP_VER, \ + I40E_RX_PTYPE_##OUTER_FRAG, \ + I40E_RX_PTYPE_TUNNEL_##T, \ + I40E_RX_PTYPE_TUNNEL_END_##TE, \ + I40E_RX_PTYPE_##TEF, \ + I40E_RX_PTYPE_INNER_PROT_##I, \ + I40E_RX_PTYPE_PAYLOAD_LAYER_##PL } + +#define I40E_PTT_UNUSED_ENTRY(PTYPE) \ + { PTYPE, 0, 0, 0, 0, 0, 0, 0, 0, 0 } + +/* shorter macros makes the table fit but are terse */ +#define I40E_RX_PTYPE_NOF I40E_RX_PTYPE_NOT_FRAG +#define I40E_RX_PTYPE_FRG I40E_RX_PTYPE_FRAG +#define I40E_RX_PTYPE_INNER_PROT_TS I40E_RX_PTYPE_INNER_PROT_TIMESYNC + +/* Lookup table mapping the HW PTYPE to the bit field for decoding */ +struct i40e_rx_ptype_decoded i40e_ptype_lookup[] = { + /* L2 Packet types */ + I40E_PTT_UNUSED_ENTRY(0), + I40E_PTT(1, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2), + I40E_PTT(2, L2, NONE, NOF, NONE, NONE, NOF, TS, PAY2), + I40E_PTT(3, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2), + I40E_PTT_UNUSED_ENTRY(4), + I40E_PTT_UNUSED_ENTRY(5), + I40E_PTT(6, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2), + I40E_PTT(7, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2), + I40E_PTT_UNUSED_ENTRY(8), + I40E_PTT_UNUSED_ENTRY(9), + I40E_PTT(10, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2), + I40E_PTT(11, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE), + I40E_PTT(12, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), + I40E_PTT(13, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), + I40E_PTT(14, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), + I40E_PTT(15, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), + I40E_PTT(16, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), + I40E_PTT(17, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), + I40E_PTT(18, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), + I40E_PTT(19, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), + I40E_PTT(20, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), + I40E_PTT(21, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), + + /* Non Tunneled IPv4 */ + I40E_PTT(22, IP, IPV4, FRG, NONE, NONE, NOF, NONE, PAY3), + I40E_PTT(23, IP, IPV4, NOF, NONE, NONE, NOF, NONE, PAY3), + I40E_PTT(24, IP, IPV4, NOF, NONE, NONE, NOF, UDP, PAY4), + I40E_PTT_UNUSED_ENTRY(25), + I40E_PTT(26, IP, IPV4, NOF, NONE, NONE, NOF, TCP, PAY4), + I40E_PTT(27, IP, IPV4, NOF, NONE, NONE, NOF, SCTP, PAY4), + I40E_PTT(28, IP, IPV4, NOF, NONE, NONE, NOF, ICMP, PAY4), + + /* IPv4 --> IPv4 */ + I40E_PTT(29, IP, IPV4, NOF, IP_IP, IPV4, FRG, NONE, PAY3), + I40E_PTT(30, IP, IPV4, NOF, IP_IP, IPV4, NOF, NONE, PAY3), + I40E_PTT(31, IP, IPV4, NOF, IP_IP, IPV4, NOF, UDP, PAY4), + I40E_PTT_UNUSED_ENTRY(32), + I40E_PTT(33, IP, IPV4, NOF, IP_IP, IPV4, NOF, TCP, PAY4), + I40E_PTT(34, IP, IPV4, NOF, IP_IP, IPV4, NOF, SCTP, PAY4), + I40E_PTT(35, IP, IPV4, NOF, IP_IP, IPV4, NOF, ICMP, PAY4), + + /* IPv4 --> IPv6 */ + I40E_PTT(36, IP, IPV4, NOF, IP_IP, IPV6, FRG, NONE, PAY3), + I40E_PTT(37, IP, IPV4, NOF, IP_IP, IPV6, NOF, NONE, PAY3), + I40E_PTT(38, IP, IPV4, NOF, IP_IP, IPV6, NOF, UDP, PAY4), + I40E_PTT_UNUSED_ENTRY(39), + I40E_PTT(40, IP, IPV4, NOF, IP_IP, IPV6, NOF, TCP, PAY4), + I40E_PTT(41, IP, IPV4, NOF, IP_IP, IPV6, NOF, SCTP, PAY4), + I40E_PTT(42, IP, IPV4, NOF, IP_IP, IPV6, NOF, ICMP, PAY4), + + /* IPv4 --> GRE/NAT */ + I40E_PTT(43, IP, IPV4, NOF, IP_GRENAT, NONE, NOF, NONE, PAY3), + + /* IPv4 --> GRE/NAT --> IPv4 */ + I40E_PTT(44, IP, IPV4, NOF, IP_GRENAT, IPV4, FRG, NONE, PAY3), + I40E_PTT(45, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, NONE, PAY3), + I40E_PTT(46, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, UDP, PAY4), + I40E_PTT_UNUSED_ENTRY(47), + I40E_PTT(48, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, TCP, PAY4), + I40E_PTT(49, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, SCTP, PAY4), + I40E_PTT(50, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, ICMP, PAY4), + + /* IPv4 --> GRE/NAT --> IPv6 */ + I40E_PTT(51, IP, IPV4, NOF, IP_GRENAT, IPV6, FRG, NONE, PAY3), + I40E_PTT(52, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, NONE, PAY3), + I40E_PTT(53, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, UDP, PAY4), + I40E_PTT_UNUSED_ENTRY(54), + I40E_PTT(55, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, TCP, PAY4), + I40E_PTT(56, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, SCTP, PAY4), + I40E_PTT(57, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, ICMP, PAY4), + + /* IPv4 --> GRE/NAT --> MAC */ + I40E_PTT(58, IP, IPV4, NOF, IP_GRENAT_MAC, NONE, NOF, NONE, PAY3), + + /* IPv4 --> GRE/NAT --> MAC --> IPv4 */ + I40E_PTT(59, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, FRG, NONE, PAY3), + I40E_PTT(60, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, NONE, PAY3), + I40E_PTT(61, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, UDP, PAY4), + I40E_PTT_UNUSED_ENTRY(62), + I40E_PTT(63, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, TCP, PAY4), + I40E_PTT(64, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, SCTP, PAY4), + I40E_PTT(65, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, ICMP, PAY4), + + /* IPv4 --> GRE/NAT -> MAC --> IPv6 */ + I40E_PTT(66, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, FRG, NONE, PAY3), + I40E_PTT(67, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, NONE, PAY3), + I40E_PTT(68, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, UDP, PAY4), + I40E_PTT_UNUSED_ENTRY(69), + I40E_PTT(70, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, TCP, PAY4), + I40E_PTT(71, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, SCTP, PAY4), + I40E_PTT(72, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, ICMP, PAY4), + + /* IPv4 --> GRE/NAT --> MAC/VLAN */ + I40E_PTT(73, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, NONE, NOF, NONE, PAY3), + + /* IPv4 ---> GRE/NAT -> MAC/VLAN --> IPv4 */ + I40E_PTT(74, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, FRG, NONE, PAY3), + I40E_PTT(75, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, NONE, PAY3), + I40E_PTT(76, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, UDP, PAY4), + I40E_PTT_UNUSED_ENTRY(77), + I40E_PTT(78, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, TCP, PAY4), + I40E_PTT(79, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, SCTP, PAY4), + I40E_PTT(80, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, ICMP, PAY4), + + /* IPv4 -> GRE/NAT -> MAC/VLAN --> IPv6 */ + I40E_PTT(81, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, FRG, NONE, PAY3), + I40E_PTT(82, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, NONE, PAY3), + I40E_PTT(83, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, UDP, PAY4), + I40E_PTT_UNUSED_ENTRY(84), + I40E_PTT(85, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, TCP, PAY4), + I40E_PTT(86, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, SCTP, PAY4), + I40E_PTT(87, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4), + + /* Non Tunneled IPv6 */ + I40E_PTT(88, IP, IPV6, FRG, NONE, NONE, NOF, NONE, PAY3), + I40E_PTT(89, IP, IPV6, NOF, NONE, NONE, NOF, NONE, PAY3), + I40E_PTT(90, IP, IPV6, NOF, NONE, NONE, NOF, UDP, PAY3), + I40E_PTT_UNUSED_ENTRY(91), + I40E_PTT(92, IP, IPV6, NOF, NONE, NONE, NOF, TCP, PAY4), + I40E_PTT(93, IP, IPV6, NOF, NONE, NONE, NOF, SCTP, PAY4), + I40E_PTT(94, IP, IPV6, NOF, NONE, NONE, NOF, ICMP, PAY4), + + /* IPv6 --> IPv4 */ + I40E_PTT(95, IP, IPV6, NOF, IP_IP, IPV4, FRG, NONE, PAY3), + I40E_PTT(96, IP, IPV6, NOF, IP_IP, IPV4, NOF, NONE, PAY3), + I40E_PTT(97, IP, IPV6, NOF, IP_IP, IPV4, NOF, UDP, PAY4), + I40E_PTT_UNUSED_ENTRY(98), + I40E_PTT(99, IP, IPV6, NOF, IP_IP, IPV4, NOF, TCP, PAY4), + I40E_PTT(100, IP, IPV6, NOF, IP_IP, IPV4, NOF, SCTP, PAY4), + I40E_PTT(101, IP, IPV6, NOF, IP_IP, IPV4, NOF, ICMP, PAY4), + + /* IPv6 --> IPv6 */ + I40E_PTT(102, IP, IPV6, NOF, IP_IP, IPV6, FRG, NONE, PAY3), + I40E_PTT(103, IP, IPV6, NOF, IP_IP, IPV6, NOF, NONE, PAY3), + I40E_PTT(104, IP, IPV6, NOF, IP_IP, IPV6, NOF, UDP, PAY4), + I40E_PTT_UNUSED_ENTRY(105), + I40E_PTT(106, IP, IPV6, NOF, IP_IP, IPV6, NOF, TCP, PAY4), + I40E_PTT(107, IP, IPV6, NOF, IP_IP, IPV6, NOF, SCTP, PAY4), + I40E_PTT(108, IP, IPV6, NOF, IP_IP, IPV6, NOF, ICMP, PAY4), + + /* IPv6 --> GRE/NAT */ + I40E_PTT(109, IP, IPV6, NOF, IP_GRENAT, NONE, NOF, NONE, PAY3), + + /* IPv6 --> GRE/NAT -> IPv4 */ + I40E_PTT(110, IP, IPV6, NOF, IP_GRENAT, IPV4, FRG, NONE, PAY3), + I40E_PTT(111, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, NONE, PAY3), + I40E_PTT(112, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, UDP, PAY4), + I40E_PTT_UNUSED_ENTRY(113), + I40E_PTT(114, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, TCP, PAY4), + I40E_PTT(115, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, SCTP, PAY4), + I40E_PTT(116, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, ICMP, PAY4), + + /* IPv6 --> GRE/NAT -> IPv6 */ + I40E_PTT(117, IP, IPV6, NOF, IP_GRENAT, IPV6, FRG, NONE, PAY3), + I40E_PTT(118, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, NONE, PAY3), + I40E_PTT(119, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, UDP, PAY4), + I40E_PTT_UNUSED_ENTRY(120), + I40E_PTT(121, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, TCP, PAY4), + I40E_PTT(122, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, SCTP, PAY4), + I40E_PTT(123, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, ICMP, PAY4), + + /* IPv6 --> GRE/NAT -> MAC */ + I40E_PTT(124, IP, IPV6, NOF, IP_GRENAT_MAC, NONE, NOF, NONE, PAY3), + + /* IPv6 --> GRE/NAT -> MAC -> IPv4 */ + I40E_PTT(125, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, FRG, NONE, PAY3), + I40E_PTT(126, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, NONE, PAY3), + I40E_PTT(127, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, UDP, PAY4), + I40E_PTT_UNUSED_ENTRY(128), + I40E_PTT(129, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, TCP, PAY4), + I40E_PTT(130, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, SCTP, PAY4), + I40E_PTT(131, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, ICMP, PAY4), + + /* IPv6 --> GRE/NAT -> MAC -> IPv6 */ + I40E_PTT(132, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, FRG, NONE, PAY3), + I40E_PTT(133, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, NONE, PAY3), + I40E_PTT(134, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, UDP, PAY4), + I40E_PTT_UNUSED_ENTRY(135), + I40E_PTT(136, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, TCP, PAY4), + I40E_PTT(137, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, SCTP, PAY4), + I40E_PTT(138, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, ICMP, PAY4), + + /* IPv6 --> GRE/NAT -> MAC/VLAN */ + I40E_PTT(139, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, NONE, NOF, NONE, PAY3), + + /* IPv6 --> GRE/NAT -> MAC/VLAN --> IPv4 */ + I40E_PTT(140, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, FRG, NONE, PAY3), + I40E_PTT(141, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, NONE, PAY3), + I40E_PTT(142, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, UDP, PAY4), + I40E_PTT_UNUSED_ENTRY(143), + I40E_PTT(144, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, TCP, PAY4), + I40E_PTT(145, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, SCTP, PAY4), + I40E_PTT(146, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, ICMP, PAY4), + + /* IPv6 --> GRE/NAT -> MAC/VLAN --> IPv6 */ + I40E_PTT(147, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, FRG, NONE, PAY3), + I40E_PTT(148, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, NONE, PAY3), + I40E_PTT(149, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, UDP, PAY4), + I40E_PTT_UNUSED_ENTRY(150), + I40E_PTT(151, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, TCP, PAY4), + I40E_PTT(152, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, SCTP, PAY4), + I40E_PTT(153, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4), + + /* unused entries */ + I40E_PTT_UNUSED_ENTRY(154), + I40E_PTT_UNUSED_ENTRY(155), + I40E_PTT_UNUSED_ENTRY(156), + I40E_PTT_UNUSED_ENTRY(157), + I40E_PTT_UNUSED_ENTRY(158), + I40E_PTT_UNUSED_ENTRY(159), + + I40E_PTT_UNUSED_ENTRY(160), + I40E_PTT_UNUSED_ENTRY(161), + I40E_PTT_UNUSED_ENTRY(162), + I40E_PTT_UNUSED_ENTRY(163), + I40E_PTT_UNUSED_ENTRY(164), + I40E_PTT_UNUSED_ENTRY(165), + I40E_PTT_UNUSED_ENTRY(166), + I40E_PTT_UNUSED_ENTRY(167), + I40E_PTT_UNUSED_ENTRY(168), + I40E_PTT_UNUSED_ENTRY(169), + + I40E_PTT_UNUSED_ENTRY(170), + I40E_PTT_UNUSED_ENTRY(171), + I40E_PTT_UNUSED_ENTRY(172), + I40E_PTT_UNUSED_ENTRY(173), + I40E_PTT_UNUSED_ENTRY(174), + I40E_PTT_UNUSED_ENTRY(175), + I40E_PTT_UNUSED_ENTRY(176), + I40E_PTT_UNUSED_ENTRY(177), + I40E_PTT_UNUSED_ENTRY(178), + I40E_PTT_UNUSED_ENTRY(179), + + I40E_PTT_UNUSED_ENTRY(180), + I40E_PTT_UNUSED_ENTRY(181), + I40E_PTT_UNUSED_ENTRY(182), + I40E_PTT_UNUSED_ENTRY(183), + I40E_PTT_UNUSED_ENTRY(184), + I40E_PTT_UNUSED_ENTRY(185), + I40E_PTT_UNUSED_ENTRY(186), + I40E_PTT_UNUSED_ENTRY(187), + I40E_PTT_UNUSED_ENTRY(188), + I40E_PTT_UNUSED_ENTRY(189), + + I40E_PTT_UNUSED_ENTRY(190), + I40E_PTT_UNUSED_ENTRY(191), + I40E_PTT_UNUSED_ENTRY(192), + I40E_PTT_UNUSED_ENTRY(193), + I40E_PTT_UNUSED_ENTRY(194), + I40E_PTT_UNUSED_ENTRY(195), + I40E_PTT_UNUSED_ENTRY(196), + I40E_PTT_UNUSED_ENTRY(197), + I40E_PTT_UNUSED_ENTRY(198), + I40E_PTT_UNUSED_ENTRY(199), + + I40E_PTT_UNUSED_ENTRY(200), + I40E_PTT_UNUSED_ENTRY(201), + I40E_PTT_UNUSED_ENTRY(202), + I40E_PTT_UNUSED_ENTRY(203), + I40E_PTT_UNUSED_ENTRY(204), + I40E_PTT_UNUSED_ENTRY(205), + I40E_PTT_UNUSED_ENTRY(206), + I40E_PTT_UNUSED_ENTRY(207), + I40E_PTT_UNUSED_ENTRY(208), + I40E_PTT_UNUSED_ENTRY(209), + + I40E_PTT_UNUSED_ENTRY(210), + I40E_PTT_UNUSED_ENTRY(211), + I40E_PTT_UNUSED_ENTRY(212), + I40E_PTT_UNUSED_ENTRY(213), + I40E_PTT_UNUSED_ENTRY(214), + I40E_PTT_UNUSED_ENTRY(215), + I40E_PTT_UNUSED_ENTRY(216), + I40E_PTT_UNUSED_ENTRY(217), + I40E_PTT_UNUSED_ENTRY(218), + I40E_PTT_UNUSED_ENTRY(219), + + I40E_PTT_UNUSED_ENTRY(220), + I40E_PTT_UNUSED_ENTRY(221), + I40E_PTT_UNUSED_ENTRY(222), + I40E_PTT_UNUSED_ENTRY(223), + I40E_PTT_UNUSED_ENTRY(224), + I40E_PTT_UNUSED_ENTRY(225), + I40E_PTT_UNUSED_ENTRY(226), + I40E_PTT_UNUSED_ENTRY(227), + I40E_PTT_UNUSED_ENTRY(228), + I40E_PTT_UNUSED_ENTRY(229), + + I40E_PTT_UNUSED_ENTRY(230), + I40E_PTT_UNUSED_ENTRY(231), + I40E_PTT_UNUSED_ENTRY(232), + I40E_PTT_UNUSED_ENTRY(233), + I40E_PTT_UNUSED_ENTRY(234), + I40E_PTT_UNUSED_ENTRY(235), + I40E_PTT_UNUSED_ENTRY(236), + I40E_PTT_UNUSED_ENTRY(237), + I40E_PTT_UNUSED_ENTRY(238), + I40E_PTT_UNUSED_ENTRY(239), + + I40E_PTT_UNUSED_ENTRY(240), + I40E_PTT_UNUSED_ENTRY(241), + I40E_PTT_UNUSED_ENTRY(242), + I40E_PTT_UNUSED_ENTRY(243), + I40E_PTT_UNUSED_ENTRY(244), + I40E_PTT_UNUSED_ENTRY(245), + I40E_PTT_UNUSED_ENTRY(246), + I40E_PTT_UNUSED_ENTRY(247), + I40E_PTT_UNUSED_ENTRY(248), + I40E_PTT_UNUSED_ENTRY(249), + + I40E_PTT_UNUSED_ENTRY(250), + I40E_PTT_UNUSED_ENTRY(251), + I40E_PTT_UNUSED_ENTRY(252), + I40E_PTT_UNUSED_ENTRY(253), + I40E_PTT_UNUSED_ENTRY(254), + I40E_PTT_UNUSED_ENTRY(255) +}; + + /** * i40e_aq_send_msg_to_pf * @hw: pointer to the hardware structure diff --git a/drivers/net/ethernet/intel/i40evf/i40e_prototype.h b/drivers/net/ethernet/intel/i40evf/i40e_prototype.h index 7841573a58c9..33c99051cc96 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_prototype.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_prototype.h @@ -63,6 +63,13 @@ i40e_status i40evf_aq_queue_shutdown(struct i40e_hw *hw, i40e_status i40e_set_mac_type(struct i40e_hw *hw); +extern struct i40e_rx_ptype_decoded i40e_ptype_lookup[]; + +static inline struct i40e_rx_ptype_decoded decode_rx_desc_ptype(u8 ptype) +{ + return i40e_ptype_lookup[ptype]; +} + /* prototype for functions used for SW locks */ /* i40e_common for VF drivers*/ diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c index ffdb01d853db..b1d87c6a5c35 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c @@ -1,7 +1,7 @@ /******************************************************************************* * * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver - * Copyright(c) 2013 Intel Corporation. + * Copyright(c) 2013 - 2014 Intel Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, @@ -24,6 +24,7 @@ #include <linux/prefetch.h> #include "i40evf.h" +#include "i40e_prototype.h" static inline __le64 build_ctob(u32 td_cmd, u32 td_offset, unsigned int size, u32 td_tag) @@ -722,7 +723,7 @@ static inline void i40e_rx_checksum(struct i40e_vsi *vsi, rx_status & (1 << I40E_RX_DESC_STATUS_L3L4P_SHIFT))) return; - /* likely incorrect csum if alternate IP extention headers found */ + /* likely incorrect csum if alternate IP extension headers found */ if (rx_status & (1 << I40E_RX_DESC_STATUS_IPV6EXADD_SHIFT)) return; @@ -786,6 +787,29 @@ static inline u32 i40e_rx_hash(struct i40e_ring *ring, } /** + * i40e_ptype_to_hash - get a hash type + * @ptype: the ptype value from the descriptor + * + * Returns a hash type to be used by skb_set_hash + **/ +static inline enum pkt_hash_types i40e_ptype_to_hash(u8 ptype) +{ + struct i40e_rx_ptype_decoded decoded = decode_rx_desc_ptype(ptype); + + if (!decoded.known) + return PKT_HASH_TYPE_NONE; + + if (decoded.outer_ip == I40E_RX_PTYPE_OUTER_IP && + decoded.payload_layer == I40E_RX_PTYPE_PAYLOAD_LAYER_PAY4) + return PKT_HASH_TYPE_L4; + else if (decoded.outer_ip == I40E_RX_PTYPE_OUTER_IP && + decoded.payload_layer == I40E_RX_PTYPE_PAYLOAD_LAYER_PAY3) + return PKT_HASH_TYPE_L3; + else + return PKT_HASH_TYPE_L2; +} + +/** * i40e_clean_rx_irq - Reclaim resources after receive completes * @rx_ring: rx ring to clean * @budget: how many cleans we're allowed @@ -802,13 +826,13 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) u16 i = rx_ring->next_to_clean; union i40e_rx_desc *rx_desc; u32 rx_error, rx_status; + u8 rx_ptype; u64 qword; - u16 rx_ptype; rx_desc = I40E_RX_DESC(rx_ring, i); qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len); - rx_status = (qword & I40E_RXD_QW1_STATUS_MASK) - >> I40E_RXD_QW1_STATUS_SHIFT; + rx_status = (qword & I40E_RXD_QW1_STATUS_MASK) >> + I40E_RXD_QW1_STATUS_SHIFT; while (rx_status & (1 << I40E_RX_DESC_STATUS_DD_SHIFT)) { union i40e_rx_desc *next_rxd; @@ -912,7 +936,8 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) goto next_desc; } - skb->rxhash = i40e_rx_hash(rx_ring, rx_desc); + skb_set_hash(skb, i40e_rx_hash(rx_ring, rx_desc), + i40e_ptype_to_hash(rx_ptype)); /* probably a little skewed due to removing CRC */ total_rx_bytes += skb->len; total_rx_packets++; @@ -1457,7 +1482,7 @@ static int i40e_xmit_descriptor_count(struct sk_buff *skb, /* need: 1 descriptor per page * PAGE_SIZE/I40E_MAX_DATA_PER_TXD, * + 1 desc for skb_head_len/I40E_MAX_DATA_PER_TXD, - * + 2 desc gap to keep tail from touching head, + * + 4 desc gap to avoid the cache line where head is, * + 1 desc for context descriptor, * otherwise try next time */ @@ -1468,7 +1493,7 @@ static int i40e_xmit_descriptor_count(struct sk_buff *skb, count += skb_shinfo(skb)->nr_frags; #endif count += TXD_USE_COUNT(skb_headlen(skb)); - if (i40e_maybe_stop_tx(tx_ring, count + 3)) { + if (i40e_maybe_stop_tx(tx_ring, count + 4 + 1)) { tx_ring->tx_stats.tx_busy++; return 0; } diff --git a/drivers/net/ethernet/intel/i40evf/i40e_type.h b/drivers/net/ethernet/intel/i40evf/i40e_type.h index 3bffac06592f..092aace2a76c 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_type.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_type.h @@ -1,7 +1,7 @@ /******************************************************************************* * * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver - * Copyright(c) 2013 Intel Corporation. + * Copyright(c) 2013 - 2014 Intel Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, @@ -64,8 +64,6 @@ struct i40e_hw; typedef void (*I40E_ADMINQ_CALLBACK)(struct i40e_hw *, struct i40e_aq_desc *); -#define ETH_ALEN 6 - /* Data type manipulation macros. */ #define I40E_DESC_UNUSED(R) \ diff --git a/drivers/net/ethernet/intel/i40evf/i40evf.h b/drivers/net/ethernet/intel/i40evf/i40evf.h index ff6529b288a1..ccb43d343543 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf.h +++ b/drivers/net/ethernet/intel/i40evf/i40evf.h @@ -1,7 +1,7 @@ /******************************************************************************* * * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver - * Copyright(c) 2013 Intel Corporation. + * Copyright(c) 2013 - 2014 Intel Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, @@ -38,8 +38,6 @@ #include <linux/ipv6.h> #include <net/ip6_checksum.h> #include <net/udp.h> -#include <linux/sctp.h> - #include "i40e_type.h" #include "i40e_virtchnl.h" @@ -164,15 +162,14 @@ struct i40evf_vlan_filter { /* Driver state. The order of these is important! */ enum i40evf_state_t { __I40EVF_STARTUP, /* driver loaded, probe complete */ - __I40EVF_FAILED, /* PF communication failed. Fatal. */ __I40EVF_REMOVE, /* driver is being unloaded */ __I40EVF_INIT_VERSION_CHECK, /* aq msg sent, awaiting reply */ __I40EVF_INIT_GET_RESOURCES, /* aq msg sent, awaiting reply */ __I40EVF_INIT_SW, /* got resources, setting up structs */ + __I40EVF_RESETTING, /* in reset */ /* Below here, watchdog is running */ __I40EVF_DOWN, /* ready, can be opened */ __I40EVF_TESTING, /* in ethtool self-test */ - __I40EVF_RESETTING, /* in reset */ __I40EVF_RUNNING, /* opened, working */ }; @@ -185,47 +182,25 @@ enum i40evf_critical_section_t { /* board specific private data structure */ struct i40evf_adapter { struct timer_list watchdog_timer; - struct vlan_group *vlgrp; struct work_struct reset_task; struct work_struct adminq_task; struct delayed_work init_task; struct i40e_q_vector *q_vector[MAX_MSIX_Q_VECTORS]; struct list_head vlan_filter_list; - char name[MAX_MSIX_COUNT][IFNAMSIZ + 9]; - - /* Interrupt Throttle Rate */ - u32 itr_setting; - u16 eitr_low; - u16 eitr_high; + char misc_vector_name[IFNAMSIZ + 9]; /* TX */ struct i40e_ring *tx_rings[I40E_MAX_VSI_QP]; - u64 restart_queue; - u64 hw_csum_tx_good; - u64 lsc_int; - u64 hw_tso_ctxt; - u64 hw_tso6_ctxt; u32 tx_timeout_count; struct list_head mac_filter_list; -#ifdef DEBUG - bool detect_tx_hung; -#endif /* DEBUG */ /* RX */ struct i40e_ring *rx_rings[I40E_MAX_VSI_QP]; - int txd_count; - int rxd_count; u64 hw_csum_rx_error; - u64 hw_rx_no_dma_resources; - u64 hw_csum_rx_good; - u64 non_eop_descs; int num_msix_vectors; struct msix_entry *msix_entries; - u64 rx_hdr_split; - - u32 init_state; - volatile unsigned long flags; + u32 flags; #define I40EVF_FLAG_RX_CSUM_ENABLED (u32)(1) #define I40EVF_FLAG_RX_1BUF_CAPABLE (u32)(1 << 1) #define I40EVF_FLAG_RX_PS_CAPABLE (u32)(1 << 2) @@ -234,6 +209,8 @@ struct i40evf_adapter { #define I40EVF_FLAG_IMIR_ENABLED (u32)(1 << 5) #define I40EVF_FLAG_MQ_CAPABLE (u32)(1 << 6) #define I40EVF_FLAG_NEED_LINK_UPDATE (u32)(1 << 7) +#define I40EVF_FLAG_PF_COMMS_FAILED (u32)(1 << 8) +#define I40EVF_FLAG_RESET_PENDING (u32)(1 << 9) /* duplcates for common code */ #define I40E_FLAG_FDIR_ATR_ENABLED 0 #define I40E_FLAG_DCB_ENABLED 0 @@ -251,21 +228,19 @@ struct i40evf_adapter { #define I40EVF_FLAG_AQ_CONFIGURE_QUEUES (u32)(1 << 6) #define I40EVF_FLAG_AQ_MAP_VECTORS (u32)(1 << 7) #define I40EVF_FLAG_AQ_HANDLE_RESET (u32)(1 << 8) + /* OS defined structs */ struct net_device *netdev; struct pci_dev *pdev; struct net_device_stats net_stats; - /* structs defined in i40e_vf.h */ - struct i40e_hw hw; + struct i40e_hw hw; /* defined in i40e_type.h */ enum i40evf_state_t state; volatile unsigned long crit_section; - u64 tx_busy; struct work_struct watchdog_task; bool netdev_registered; - bool dev_closed; bool link_up; enum i40e_virtchnl_ops current_op; struct i40e_virtchnl_vf_resource *vf_res; /* incl. all VSIs */ @@ -276,11 +251,6 @@ struct i40evf_adapter { u32 aq_wait_count; }; -struct i40evf_info { - enum i40e_mac_type mac; - unsigned int flags; -}; - /* needed by i40evf_ethtool.c */ extern char i40evf_driver_name[]; @@ -315,6 +285,7 @@ void i40evf_add_vlans(struct i40evf_adapter *adapter); void i40evf_del_vlans(struct i40evf_adapter *adapter); void i40evf_set_promiscuous(struct i40evf_adapter *adapter, int flags); void i40evf_request_stats(struct i40evf_adapter *adapter); +void i40evf_request_reset(struct i40evf_adapter *adapter); void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, enum i40e_virtchnl_ops v_opcode, i40e_status v_retval, u8 *msg, u16 msglen); diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c b/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c index b0b1f4bf5ac0..8b0db1ce179c 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c @@ -1,7 +1,7 @@ /******************************************************************************* * * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver - * Copyright(c) 2013 Intel Corporation. + * Copyright(c) 2013 - 2014 Intel Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, @@ -241,6 +241,7 @@ static int i40evf_set_ringparam(struct net_device *netdev, { struct i40evf_adapter *adapter = netdev_priv(netdev); u32 new_rx_count, new_tx_count; + int i; if ((ring->rx_mini_pending) || (ring->rx_jumbo_pending)) return -EINVAL; @@ -256,12 +257,14 @@ static int i40evf_set_ringparam(struct net_device *netdev, new_rx_count = ALIGN(new_rx_count, I40EVF_REQ_DESCRIPTOR_MULTIPLE); /* if nothing to do return success */ - if ((new_tx_count == adapter->txd_count) && - (new_rx_count == adapter->rxd_count)) + if ((new_tx_count == adapter->tx_rings[0]->count) && + (new_rx_count == adapter->rx_rings[0]->count)) return 0; - adapter->txd_count = new_tx_count; - adapter->rxd_count = new_rx_count; + for (i = 0; i < adapter->vsi_res->num_queue_pairs; i++) { + adapter->tx_rings[0]->count = new_tx_count; + adapter->rx_rings[0]->count = new_rx_count; + } if (netif_running(netdev)) i40evf_reinit_locked(adapter); diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c index f5caf4419243..11d0b61510b0 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c @@ -1,7 +1,7 @@ /******************************************************************************* * * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver - * Copyright(c) 2013 Intel Corporation. + * Copyright(c) 2013 - 2014 Intel Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, @@ -31,10 +31,10 @@ char i40evf_driver_name[] = "i40evf"; static const char i40evf_driver_string[] = "Intel(R) XL710 X710 Virtual Function Network Driver"; -#define DRV_VERSION "0.9.11" +#define DRV_VERSION "0.9.14" const char i40evf_driver_version[] = DRV_VERSION; static const char i40evf_copyright[] = - "Copyright (c) 2013 Intel Corporation."; + "Copyright (c) 2013 - 2014 Intel Corporation."; /* i40evf_pci_tbl - PCI Device ID Table * @@ -167,9 +167,13 @@ static void i40evf_tx_timeout(struct net_device *netdev) struct i40evf_adapter *adapter = netdev_priv(netdev); adapter->tx_timeout_count++; - - /* Do the reset outside of interrupt context */ - schedule_work(&adapter->reset_task); + dev_info(&adapter->pdev->dev, "TX timeout detected.\n"); + if (!(adapter->flags & I40EVF_FLAG_RESET_PENDING)) { + dev_info(&adapter->pdev->dev, "Requesting reset from PF\n"); + i40evf_request_reset(adapter); + adapter->flags |= I40EVF_FLAG_RESET_PENDING; + schedule_work(&adapter->reset_task); + } } /** @@ -211,6 +215,9 @@ static void i40evf_irq_disable(struct i40evf_adapter *adapter) int i; struct i40e_hw *hw = &adapter->hw; + if (!adapter->msix_entries) + return; + for (i = 1; i < adapter->num_msix_vectors; i++) { wr32(hw, I40E_VFINT_DYN_CTLN1(i - 1), 0); synchronize_irq(adapter->msix_entries[i].vector); @@ -511,12 +518,14 @@ static int i40evf_request_misc_irq(struct i40evf_adapter *adapter) struct net_device *netdev = adapter->netdev; int err; - sprintf(adapter->name[0], "i40evf:mbx"); + sprintf(adapter->misc_vector_name, "i40evf:mbx"); err = request_irq(adapter->msix_entries[0].vector, - &i40evf_msix_aq, 0, adapter->name[0], netdev); + &i40evf_msix_aq, 0, + adapter->misc_vector_name, netdev); if (err) { dev_err(&adapter->pdev->dev, - "request_irq for msix_aq failed: %d\n", err); + "request_irq for %s failed: %d\n", + adapter->misc_vector_name, err); free_irq(adapter->msix_entries[0].vector, netdev); } return err; @@ -963,16 +972,23 @@ void i40evf_down(struct i40evf_adapter *adapter) struct net_device *netdev = adapter->netdev; struct i40evf_mac_filter *f; - /* remove all MAC filters from the VSI */ + /* remove all MAC filters */ list_for_each_entry(f, &adapter->mac_filter_list, list) { f->remove = true; } - adapter->aq_required |= I40EVF_FLAG_AQ_DEL_MAC_FILTER; - /* disable receives */ - adapter->aq_required |= I40EVF_FLAG_AQ_DISABLE_QUEUES; - mod_timer_pending(&adapter->watchdog_timer, jiffies + 1); - msleep(20); - + /* remove all VLAN filters */ + list_for_each_entry(f, &adapter->vlan_filter_list, list) { + f->remove = true; + } + if (!(adapter->flags & I40EVF_FLAG_PF_COMMS_FAILED) && + adapter->state != __I40EVF_RESETTING) { + adapter->aq_required |= I40EVF_FLAG_AQ_DEL_MAC_FILTER; + adapter->aq_required |= I40EVF_FLAG_AQ_DEL_VLAN_FILTER; + /* disable receives */ + adapter->aq_required |= I40EVF_FLAG_AQ_DISABLE_QUEUES; + mod_timer_pending(&adapter->watchdog_timer, jiffies + 1); + msleep(20); + } netif_tx_disable(netdev); netif_tx_stop_all_queues(netdev); @@ -1291,19 +1307,47 @@ static void i40evf_watchdog_task(struct work_struct *work) watchdog_task); struct i40e_hw *hw = &adapter->hw; - if (adapter->state < __I40EVF_DOWN) + if (test_and_set_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section)) + goto restart_watchdog; + + if (adapter->flags & I40EVF_FLAG_PF_COMMS_FAILED) { + dev_info(&adapter->pdev->dev, "Checking for redemption\n"); + if ((rd32(hw, I40E_VFGEN_RSTAT) & 0x3) == I40E_VFR_VFACTIVE) { + /* A chance for redemption! */ + dev_err(&adapter->pdev->dev, "Hardware came out of reset. Attempting reinit.\n"); + adapter->state = __I40EVF_STARTUP; + adapter->flags &= ~I40EVF_FLAG_PF_COMMS_FAILED; + schedule_delayed_work(&adapter->init_task, 10); + clear_bit(__I40EVF_IN_CRITICAL_TASK, + &adapter->crit_section); + /* Don't reschedule the watchdog, since we've restarted + * the init task. When init_task contacts the PF and + * gets everything set up again, it'll restart the + * watchdog for us. Down, boy. Sit. Stay. Woof. + */ + return; + } + adapter->aq_pending = 0; + adapter->aq_required = 0; + adapter->current_op = I40E_VIRTCHNL_OP_UNKNOWN; goto watchdog_done; + } - if (test_and_set_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section)) + if ((adapter->state < __I40EVF_DOWN) || + (adapter->flags & I40EVF_FLAG_RESET_PENDING)) goto watchdog_done; - /* check for unannounced reset */ - if ((adapter->state != __I40EVF_RESETTING) && + /* check for reset */ + if (!(adapter->flags & I40EVF_FLAG_RESET_PENDING) && (rd32(hw, I40E_VFGEN_RSTAT) & 0x3) != I40E_VFR_VFACTIVE) { adapter->state = __I40EVF_RESETTING; + adapter->flags |= I40EVF_FLAG_RESET_PENDING; + dev_err(&adapter->pdev->dev, "Hardware reset detected.\n"); + dev_info(&adapter->pdev->dev, "Scheduling reset task\n"); schedule_work(&adapter->reset_task); - dev_info(&adapter->pdev->dev, "%s: hardware reset detected\n", - __func__); + adapter->aq_pending = 0; + adapter->aq_required = 0; + adapter->current_op = I40E_VIRTCHNL_OP_UNKNOWN; goto watchdog_done; } @@ -1358,13 +1402,15 @@ static void i40evf_watchdog_task(struct work_struct *work) i40evf_irq_enable(adapter, true); i40evf_fire_sw_int(adapter, 0xFF); + watchdog_done: + clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section); +restart_watchdog: if (adapter->aq_required) mod_timer(&adapter->watchdog_timer, jiffies + msecs_to_jiffies(20)); else mod_timer(&adapter->watchdog_timer, jiffies + (HZ * 2)); - clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section); schedule_work(&adapter->adminq_task); } @@ -1411,6 +1457,8 @@ static void i40evf_configure_rss(struct i40evf_adapter *adapter) i40e_flush(hw); } +#define I40EVF_RESET_WAIT_MS 100 +#define I40EVF_RESET_WAIT_COUNT 200 /** * i40evf_reset_task - Call-back task to handle hardware reset * @work: pointer to work_struct @@ -1421,8 +1469,9 @@ static void i40evf_configure_rss(struct i40evf_adapter *adapter) **/ static void i40evf_reset_task(struct work_struct *work) { - struct i40evf_adapter *adapter = - container_of(work, struct i40evf_adapter, reset_task); + struct i40evf_adapter *adapter = container_of(work, + struct i40evf_adapter, + reset_task); struct i40e_hw *hw = &adapter->hw; int i = 0, err; uint32_t rstat_val; @@ -1430,22 +1479,56 @@ static void i40evf_reset_task(struct work_struct *work) while (test_and_set_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section)) udelay(500); + /* poll until we see the reset actually happen */ + for (i = 0; i < I40EVF_RESET_WAIT_COUNT; i++) { + rstat_val = rd32(hw, I40E_VFGEN_RSTAT) & + I40E_VFGEN_RSTAT_VFR_STATE_MASK; + if (rstat_val != I40E_VFR_VFACTIVE) { + dev_info(&adapter->pdev->dev, "Reset now occurring\n"); + break; + } else { + msleep(I40EVF_RESET_WAIT_MS); + } + } + if (i == I40EVF_RESET_WAIT_COUNT) { + dev_err(&adapter->pdev->dev, "Reset was not detected\n"); + adapter->flags &= ~I40EVF_FLAG_RESET_PENDING; + goto continue_reset; /* act like the reset happened */ + } - /* wait until the reset is complete */ - for (i = 0; i < 20; i++) { + /* wait until the reset is complete and the PF is responding to us */ + for (i = 0; i < I40EVF_RESET_WAIT_COUNT; i++) { rstat_val = rd32(hw, I40E_VFGEN_RSTAT) & I40E_VFGEN_RSTAT_VFR_STATE_MASK; - if (rstat_val == I40E_VFR_COMPLETED) + if (rstat_val == I40E_VFR_VFACTIVE) { + dev_info(&adapter->pdev->dev, "Reset is complete. Reinitializing.\n"); break; - else - mdelay(100); + } else { + msleep(I40EVF_RESET_WAIT_MS); + } } - if (i == 20) { + if (i == I40EVF_RESET_WAIT_COUNT) { /* reset never finished */ - dev_info(&adapter->pdev->dev, "%s: reset never finished: %x\n", - __func__, rstat_val); - /* carry on anyway */ + dev_err(&adapter->pdev->dev, "Reset never finished (%x). PF driver is dead, and so am I.\n", + rstat_val); + adapter->flags |= I40EVF_FLAG_PF_COMMS_FAILED; + + if (netif_running(adapter->netdev)) + i40evf_close(adapter->netdev); + + i40evf_free_misc_irq(adapter); + i40evf_reset_interrupt_capability(adapter); + i40evf_free_queues(adapter); + kfree(adapter->vf_res); + i40evf_shutdown_adminq(hw); + adapter->netdev->flags &= ~IFF_UP; + clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section); + return; /* Do not attempt to reinit. It's dead, Jim. */ } + +continue_reset: + adapter->flags &= ~I40EVF_FLAG_RESET_PENDING; + i40evf_down(adapter); adapter->state = __I40EVF_RESETTING; @@ -1505,6 +1588,9 @@ static void i40evf_adminq_task(struct work_struct *work) i40e_status ret; u16 pending; + if (adapter->flags & I40EVF_FLAG_PF_COMMS_FAILED) + return; + event.msg_size = I40EVF_MAX_AQ_BUF_SIZE; event.msg_buf = kzalloc(event.msg_size, GFP_KERNEL); if (!event.msg_buf) { @@ -1636,6 +1722,10 @@ static int i40evf_open(struct net_device *netdev) struct i40evf_adapter *adapter = netdev_priv(netdev); int err; + if (adapter->flags & I40EVF_FLAG_PF_COMMS_FAILED) { + dev_err(&adapter->pdev->dev, "Unable to open device due to PF driver failure.\n"); + return -EIO; + } if (adapter->state != __I40EVF_DOWN) return -EBUSY; @@ -1690,8 +1780,12 @@ static int i40evf_close(struct net_device *netdev) { struct i40evf_adapter *adapter = netdev_priv(netdev); + if (adapter->state <= __I40EVF_DOWN) + return 0; + /* signal that we are down to the interrupt handler */ adapter->state = __I40EVF_DOWN; + set_bit(__I40E_DOWN, &adapter->vsi.state); i40evf_down(adapter); @@ -1842,16 +1936,18 @@ static void i40evf_init_task(struct work_struct *work) switch (adapter->state) { case __I40EVF_STARTUP: /* driver loaded, probe complete */ + adapter->flags &= ~I40EVF_FLAG_PF_COMMS_FAILED; + adapter->flags &= ~I40EVF_FLAG_RESET_PENDING; err = i40e_set_mac_type(hw); if (err) { - dev_info(&pdev->dev, "%s: set_mac_type failed: %d\n", - __func__, err); + dev_err(&pdev->dev, "Failed to set MAC type (%d)\n", + err); goto err; } err = i40evf_check_reset_complete(hw); if (err) { - dev_info(&pdev->dev, "%s: device is still in reset (%d).\n", - __func__, err); + dev_err(&pdev->dev, "Device is still in reset (%d)\n", + err); goto err; } hw->aq.num_arq_entries = I40EVF_AQ_LEN; @@ -1861,14 +1957,14 @@ static void i40evf_init_task(struct work_struct *work) err = i40evf_init_adminq(hw); if (err) { - dev_info(&pdev->dev, "%s: init_adminq failed: %d\n", - __func__, err); + dev_err(&pdev->dev, "Failed to init Admin Queue (%d)\n", + err); goto err; } err = i40evf_send_api_ver(adapter); if (err) { - dev_info(&pdev->dev, "%s: unable to send to PF (%d)\n", - __func__, err); + dev_err(&pdev->dev, "Unable to send to PF (%d)\n", + err); i40evf_shutdown_adminq(hw); goto err; } @@ -1882,13 +1978,13 @@ static void i40evf_init_task(struct work_struct *work) /* aq msg sent, awaiting reply */ err = i40evf_verify_api_ver(adapter); if (err) { - dev_err(&pdev->dev, "Unable to verify API version, error %d\n", + dev_err(&pdev->dev, "Unable to verify API version (%d)\n", err); goto err; } err = i40evf_send_vf_config_msg(adapter); if (err) { - dev_err(&pdev->dev, "Unable send config request, error %d\n", + dev_err(&pdev->dev, "Unable send config request (%d)\n", err); goto err; } @@ -1902,18 +1998,15 @@ static void i40evf_init_task(struct work_struct *work) (I40E_MAX_VF_VSI * sizeof(struct i40e_virtchnl_vsi_resource)); adapter->vf_res = kzalloc(bufsz, GFP_KERNEL); - if (!adapter->vf_res) { - dev_err(&pdev->dev, "%s: unable to allocate memory\n", - __func__); + if (!adapter->vf_res) goto err; - } } err = i40evf_get_vf_config(adapter); if (err == I40E_ERR_ADMIN_QUEUE_NO_WORK) goto restart; if (err) { - dev_info(&pdev->dev, "%s: unable to get VF config (%d)\n", - __func__, err); + dev_err(&pdev->dev, "Unable to get VF config (%d)\n", + err); goto err_alloc; } adapter->state = __I40EVF_INIT_SW; @@ -1927,25 +2020,23 @@ static void i40evf_init_task(struct work_struct *work) adapter->vsi_res = &adapter->vf_res->vsi_res[i]; } if (!adapter->vsi_res) { - dev_info(&pdev->dev, "%s: no LAN VSI found\n", __func__); + dev_err(&pdev->dev, "No LAN VSI found\n"); goto err_alloc; } adapter->flags |= I40EVF_FLAG_RX_CSUM_ENABLED; - adapter->txd_count = I40EVF_DEFAULT_TXD; - adapter->rxd_count = I40EVF_DEFAULT_RXD; - netdev->netdev_ops = &i40evf_netdev_ops; i40evf_set_ethtool_ops(netdev); netdev->watchdog_timeo = 5 * HZ; - - netdev->features |= NETIF_F_SG | + netdev->features |= NETIF_F_HIGHDMA | + NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_SCTP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_TSO | NETIF_F_TSO6 | + NETIF_F_RXCSUM | NETIF_F_GRO; if (adapter->vf_res->vf_offload_flags @@ -1956,11 +2047,13 @@ static void i40evf_init_task(struct work_struct *work) NETIF_F_HW_VLAN_CTAG_FILTER; } - /* The HW MAC address was set and/or determined in sw_init */ + /* copy netdev features into list of user selectable features */ + netdev->hw_features |= netdev->features; + netdev->hw_features &= ~NETIF_F_RXCSUM; + if (!is_valid_ether_addr(adapter->hw.mac.addr)) { - dev_info(&pdev->dev, - "Invalid MAC address %pMAC, using random\n", - adapter->hw.mac.addr); + dev_info(&pdev->dev, "Invalid MAC address %pMAC, using random\n", + adapter->hw.mac.addr); random_ether_addr(adapter->hw.mac.addr); } memcpy(netdev->dev_addr, adapter->hw.mac.addr, netdev->addr_len); @@ -1994,8 +2087,6 @@ static void i40evf_init_task(struct work_struct *work) netif_carrier_off(netdev); - strcpy(netdev->name, "eth%d"); - adapter->vsi.id = adapter->vsi_res->vsi_id; adapter->vsi.seid = adapter->vsi_res->vsi_id; /* dummy */ adapter->vsi.back = adapter; @@ -2005,9 +2096,11 @@ static void i40evf_init_task(struct work_struct *work) adapter->vsi.tx_itr_setting = I40E_ITR_DYNAMIC; adapter->vsi.netdev = adapter->netdev; - err = register_netdev(netdev); - if (err) - goto err_register; + if (!adapter->netdev_registered) { + err = register_netdev(netdev); + if (err) + goto err_register; + } adapter->netdev_registered = true; @@ -2031,17 +2124,16 @@ err_register: i40evf_free_misc_irq(adapter); err_sw_init: i40evf_reset_interrupt_capability(adapter); - adapter->state = __I40EVF_FAILED; err_alloc: kfree(adapter->vf_res); adapter->vf_res = NULL; err: + if (hw->aq.asq.count) + i40evf_shutdown_adminq(hw); /* ignore error */ /* Things went into the weeds, so try again later */ if (++adapter->aq_wait_count > I40EVF_AQ_MAX_ERR) { dev_err(&pdev->dev, "Failed to communicate with PF; giving up.\n"); - if (hw->aq.asq.count) - i40evf_shutdown_adminq(hw); /* ignore error */ - adapter->state = __I40EVF_FAILED; + adapter->flags |= I40EVF_FLAG_PF_COMMS_FAILED; return; /* do not reschedule */ } schedule_delayed_work(&adapter->init_task, HZ * 3); @@ -2084,20 +2176,18 @@ static int i40evf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) struct net_device *netdev; struct i40evf_adapter *adapter = NULL; struct i40e_hw *hw = NULL; - int err, pci_using_dac; + int err; err = pci_enable_device(pdev); if (err) return err; if (!dma_set_mask(&pdev->dev, DMA_BIT_MASK(64))) { - pci_using_dac = true; /* coherent mask for the same size will always succeed if * dma_set_mask does */ dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(64)); } else if (!dma_set_mask(&pdev->dev, DMA_BIT_MASK(32))) { - pci_using_dac = false; dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32)); } else { dev_err(&pdev->dev, "%s: DMA configuration failed: %d\n", @@ -2128,8 +2218,6 @@ static int i40evf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) pci_set_drvdata(pdev, netdev); adapter = netdev_priv(netdev); - if (pci_using_dac) - netdev->features |= NETIF_F_HIGHDMA; adapter->netdev = netdev; adapter->pdev = pdev; @@ -2271,6 +2359,7 @@ static void i40evf_remove(struct pci_dev *pdev) struct i40e_hw *hw = &adapter->hw; cancel_delayed_work_sync(&adapter->init_task); + cancel_work_sync(&adapter->reset_task); if (adapter->netdev_registered) { unregister_netdev(netdev); @@ -2278,17 +2367,15 @@ static void i40evf_remove(struct pci_dev *pdev) } adapter->state = __I40EVF_REMOVE; - if (adapter->num_msix_vectors) { + if (adapter->msix_entries) { i40evf_misc_irq_disable(adapter); - del_timer_sync(&adapter->watchdog_timer); - - flush_scheduled_work(); - i40evf_free_misc_irq(adapter); - i40evf_reset_interrupt_capability(adapter); } + del_timer_sync(&adapter->watchdog_timer); + flush_scheduled_work(); + if (hw->aq.asq.count) i40evf_shutdown_adminq(hw); diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c index e6978d79e62b..e294f012647d 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c @@ -1,7 +1,7 @@ /******************************************************************************* * * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver - * Copyright(c) 2013 Intel Corporation. + * Copyright(c) 2013 - 2014 Intel Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, @@ -43,6 +43,9 @@ static int i40evf_send_pf_msg(struct i40evf_adapter *adapter, struct i40e_hw *hw = &adapter->hw; i40e_status err; + if (adapter->flags & I40EVF_FLAG_PF_COMMS_FAILED) + return 0; /* nothing to see here, move along */ + err = i40e_aq_send_msg_to_pf(hw, op, 0, msg, len, NULL); if (err) dev_err(&adapter->pdev->dev, "Unable to send opcode %d to PF, error %d, aq status %d\n", @@ -651,6 +654,18 @@ void i40evf_request_stats(struct i40evf_adapter *adapter) /* if the request failed, don't lock out others */ adapter->current_op = I40E_VIRTCHNL_OP_UNKNOWN; } +/** + * i40evf_request_reset + * @adapter: adapter structure + * + * Request that the PF reset this VF. No response is expected. + **/ +void i40evf_request_reset(struct i40evf_adapter *adapter) +{ + /* Don't check CURRENT_OP - this is always higher priority */ + i40evf_send_pf_msg(adapter, I40E_VIRTCHNL_OP_RESET_VF, NULL, 0); + adapter->current_op = I40E_VIRTCHNL_OP_UNKNOWN; +} /** * i40evf_virtchnl_completion @@ -689,10 +704,12 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, } break; case I40E_VIRTCHNL_EVENT_RESET_IMPENDING: - adapter->state = __I40EVF_RESETTING; - schedule_work(&adapter->reset_task); - dev_info(&adapter->pdev->dev, - "%s: hardware reset pending\n", __func__); + dev_info(&adapter->pdev->dev, "PF reset warning received\n"); + if (!(adapter->flags & I40EVF_FLAG_RESET_PENDING)) { + adapter->flags |= I40EVF_FLAG_RESET_PENDING; + dev_info(&adapter->pdev->dev, "Scheduling reset task\n"); + schedule_work(&adapter->reset_task); + } break; default: dev_err(&adapter->pdev->dev, diff --git a/drivers/net/ethernet/intel/igb/Makefile b/drivers/net/ethernet/intel/igb/Makefile index f19700e285bb..5bcb2de75933 100644 --- a/drivers/net/ethernet/intel/igb/Makefile +++ b/drivers/net/ethernet/intel/igb/Makefile @@ -1,7 +1,7 @@ ################################################################################ # # Intel 82575 PCI-Express Ethernet Linux driver -# Copyright(c) 1999 - 2013 Intel Corporation. +# Copyright(c) 1999 - 2014 Intel Corporation. # # This program is free software; you can redistribute it and/or modify it # under the terms and conditions of the GNU General Public License, @@ -13,8 +13,7 @@ # more details. # # You should have received a copy of the GNU General Public License along with -# this program; if not, write to the Free Software Foundation, Inc., -# 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. +# this program; if not, see <http://www.gnu.org/licenses/>. # # The full GNU General Public License is included in this distribution in # the file called "COPYING". diff --git a/drivers/net/ethernet/intel/igb/e1000_82575.c b/drivers/net/ethernet/intel/igb/e1000_82575.c index 06df6928f44c..fa36fe12e775 100644 --- a/drivers/net/ethernet/intel/igb/e1000_82575.c +++ b/drivers/net/ethernet/intel/igb/e1000_82575.c @@ -1,7 +1,7 @@ /******************************************************************************* Intel(R) Gigabit Ethernet Linux driver - Copyright(c) 2007-2013 Intel Corporation. + Copyright(c) 2007-2014 Intel Corporation. This program is free software; you can redistribute it and/or modify it under the terms and conditions of the GNU General Public License, @@ -13,8 +13,7 @@ more details. You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + this program; if not, see <http://www.gnu.org/licenses/>. The full GNU General Public License is included in this distribution in the file called "COPYING". @@ -77,8 +76,6 @@ static s32 igb_update_nvm_checksum_i350(struct e1000_hw *hw); static const u16 e1000_82580_rxpbs_table[] = { 36, 72, 144, 1, 2, 4, 8, 16, 35, 70, 140 }; -#define E1000_82580_RXPBS_TABLE_SIZE \ - (sizeof(e1000_82580_rxpbs_table)/sizeof(u16)) /** * igb_sgmii_uses_mdio_82575 - Determine if I2C pins are for external MDIO @@ -2308,7 +2305,7 @@ u16 igb_rxpbs_adjust_82580(u32 data) { u16 ret_val = 0; - if (data < E1000_82580_RXPBS_TABLE_SIZE) + if (data < ARRAY_SIZE(e1000_82580_rxpbs_table)) ret_val = e1000_82580_rxpbs_table[data]; return ret_val; @@ -2714,13 +2711,14 @@ static const u8 e1000_emc_therm_limit[4] = { E1000_EMC_DIODE3_THERM_LIMIT }; +#ifdef CONFIG_IGB_HWMON /** * igb_get_thermal_sensor_data_generic - Gathers thermal sensor data * @hw: pointer to hardware structure * * Updates the temperatures in mac.thermal_sensor_data **/ -s32 igb_get_thermal_sensor_data_generic(struct e1000_hw *hw) +static s32 igb_get_thermal_sensor_data_generic(struct e1000_hw *hw) { s32 status = E1000_SUCCESS; u16 ets_offset; @@ -2774,7 +2772,7 @@ s32 igb_get_thermal_sensor_data_generic(struct e1000_hw *hw) * Sets the thermal sensor thresholds according to the NVM map * and save off the threshold and location values into mac.thermal_sensor_data **/ -s32 igb_init_thermal_sensor_thresh_generic(struct e1000_hw *hw) +static s32 igb_init_thermal_sensor_thresh_generic(struct e1000_hw *hw) { s32 status = E1000_SUCCESS; u16 ets_offset; @@ -2836,6 +2834,7 @@ s32 igb_init_thermal_sensor_thresh_generic(struct e1000_hw *hw) return status; } +#endif static struct e1000_mac_operations e1000_mac_ops_82575 = { .init_hw = igb_init_hw_82575, .check_for_link = igb_check_for_link_82575, diff --git a/drivers/net/ethernet/intel/igb/e1000_82575.h b/drivers/net/ethernet/intel/igb/e1000_82575.h index 8c2437722aad..f12b086e578d 100644 --- a/drivers/net/ethernet/intel/igb/e1000_82575.h +++ b/drivers/net/ethernet/intel/igb/e1000_82575.h @@ -1,7 +1,7 @@ /******************************************************************************* Intel(R) Gigabit Ethernet Linux driver - Copyright(c) 2007-2013 Intel Corporation. + Copyright(c) 2007-2014 Intel Corporation. This program is free software; you can redistribute it and/or modify it under the terms and conditions of the GNU General Public License, @@ -13,8 +13,7 @@ more details. You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + this program; if not, see <http://www.gnu.org/licenses/>. The full GNU General Public License is included in this distribution in the file called "COPYING". @@ -266,8 +265,6 @@ u16 igb_rxpbs_adjust_82580(u32 data); s32 igb_read_emi_reg(struct e1000_hw *, u16 addr, u16 *data); s32 igb_set_eee_i350(struct e1000_hw *); s32 igb_set_eee_i354(struct e1000_hw *); -s32 igb_init_thermal_sensor_thresh_generic(struct e1000_hw *); -s32 igb_get_thermal_sensor_data_generic(struct e1000_hw *hw); #define E1000_I2C_THERMAL_SENSOR_ADDR 0xF8 #define E1000_EMC_INTERNAL_DATA 0x00 diff --git a/drivers/net/ethernet/intel/igb/e1000_defines.h b/drivers/net/ethernet/intel/igb/e1000_defines.h index 0571b973be80..393c896ac7e7 100644 --- a/drivers/net/ethernet/intel/igb/e1000_defines.h +++ b/drivers/net/ethernet/intel/igb/e1000_defines.h @@ -1,7 +1,7 @@ /******************************************************************************* Intel(R) Gigabit Ethernet Linux driver - Copyright(c) 2007-2013 Intel Corporation. + Copyright(c) 2007-2014 Intel Corporation. This program is free software; you can redistribute it and/or modify it under the terms and conditions of the GNU General Public License, @@ -13,8 +13,7 @@ more details. You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + this program; if not, see <http://www.gnu.org/licenses/>. The full GNU General Public License is included in this distribution in the file called "COPYING". diff --git a/drivers/net/ethernet/intel/igb/e1000_hw.h b/drivers/net/ethernet/intel/igb/e1000_hw.h index ab99e2b582a8..10741d170f2d 100644 --- a/drivers/net/ethernet/intel/igb/e1000_hw.h +++ b/drivers/net/ethernet/intel/igb/e1000_hw.h @@ -1,7 +1,7 @@ /******************************************************************************* Intel(R) Gigabit Ethernet Linux driver - Copyright(c) 2007-2013 Intel Corporation. + Copyright(c) 2007-2014 Intel Corporation. This program is free software; you can redistribute it and/or modify it under the terms and conditions of the GNU General Public License, @@ -13,8 +13,7 @@ more details. You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + this program; if not, see <http://www.gnu.org/licenses/>. The full GNU General Public License is included in this distribution in the file called "COPYING". diff --git a/drivers/net/ethernet/intel/igb/e1000_i210.c b/drivers/net/ethernet/intel/igb/e1000_i210.c index 0c0393316a3a..db963397cc27 100644 --- a/drivers/net/ethernet/intel/igb/e1000_i210.c +++ b/drivers/net/ethernet/intel/igb/e1000_i210.c @@ -1,7 +1,7 @@ /******************************************************************************* Intel(R) Gigabit Ethernet Linux driver - Copyright(c) 2007-2013 Intel Corporation. + Copyright(c) 2007-2014 Intel Corporation. This program is free software; you can redistribute it and/or modify it under the terms and conditions of the GNU General Public License, @@ -13,8 +13,7 @@ more details. You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + this program; if not, see <http://www.gnu.org/licenses/>. The full GNU General Public License is included in this distribution in the file called "COPYING". @@ -35,6 +34,8 @@ #include "e1000_hw.h" #include "e1000_i210.h" +static s32 igb_update_flash_i210(struct e1000_hw *hw); + /** * igb_get_hw_semaphore_i210 - Acquire hardware semaphore * @hw: pointer to the HW structure @@ -111,7 +112,7 @@ static s32 igb_get_hw_semaphore_i210(struct e1000_hw *hw) * Return successful if access grant bit set, else clear the request for * EEPROM access and return -E1000_ERR_NVM (-1). **/ -s32 igb_acquire_nvm_i210(struct e1000_hw *hw) +static s32 igb_acquire_nvm_i210(struct e1000_hw *hw) { return igb_acquire_swfw_sync_i210(hw, E1000_SWFW_EEP_SM); } @@ -123,7 +124,7 @@ s32 igb_acquire_nvm_i210(struct e1000_hw *hw) * Stop any current commands to the EEPROM and clear the EEPROM request bit, * then release the semaphores acquired. **/ -void igb_release_nvm_i210(struct e1000_hw *hw) +static void igb_release_nvm_i210(struct e1000_hw *hw) { igb_release_swfw_sync_i210(hw, E1000_SWFW_EEP_SM); } @@ -206,8 +207,8 @@ void igb_release_swfw_sync_i210(struct e1000_hw *hw, u16 mask) * Reads a 16 bit word from the Shadow Ram using the EERD register. * Uses necessary synchronization semaphores. **/ -s32 igb_read_nvm_srrd_i210(struct e1000_hw *hw, u16 offset, u16 words, - u16 *data) +static s32 igb_read_nvm_srrd_i210(struct e1000_hw *hw, u16 offset, u16 words, + u16 *data) { s32 status = E1000_SUCCESS; u16 i, count; @@ -306,8 +307,8 @@ out: * If error code is returned, data and Shadow RAM may be inconsistent - buffer * partially written. **/ -s32 igb_write_nvm_srwr_i210(struct e1000_hw *hw, u16 offset, u16 words, - u16 *data) +static s32 igb_write_nvm_srwr_i210(struct e1000_hw *hw, u16 offset, u16 words, + u16 *data) { s32 status = E1000_SUCCESS; u16 i, count; @@ -555,7 +556,7 @@ s32 igb_read_invm_version(struct e1000_hw *hw, * Calculates the EEPROM checksum by reading/adding each word of the EEPROM * and then verifies that the sum of the EEPROM is equal to 0xBABA. **/ -s32 igb_validate_nvm_checksum_i210(struct e1000_hw *hw) +static s32 igb_validate_nvm_checksum_i210(struct e1000_hw *hw) { s32 status = E1000_SUCCESS; s32 (*read_op_ptr)(struct e1000_hw *, u16, u16, u16 *); @@ -590,7 +591,7 @@ s32 igb_validate_nvm_checksum_i210(struct e1000_hw *hw) * up to the checksum. Then calculates the EEPROM checksum and writes the * value to the EEPROM. Next commit EEPROM data onto the Flash. **/ -s32 igb_update_nvm_checksum_i210(struct e1000_hw *hw) +static s32 igb_update_nvm_checksum_i210(struct e1000_hw *hw) { s32 ret_val = E1000_SUCCESS; u16 checksum = 0; @@ -684,7 +685,7 @@ bool igb_get_flash_presence_i210(struct e1000_hw *hw) * @hw: pointer to the HW structure * **/ -s32 igb_update_flash_i210(struct e1000_hw *hw) +static s32 igb_update_flash_i210(struct e1000_hw *hw) { s32 ret_val = E1000_SUCCESS; u32 flup; diff --git a/drivers/net/ethernet/intel/igb/e1000_i210.h b/drivers/net/ethernet/intel/igb/e1000_i210.h index 2d913716573a..907fe99a9813 100644 --- a/drivers/net/ethernet/intel/igb/e1000_i210.h +++ b/drivers/net/ethernet/intel/igb/e1000_i210.h @@ -1,7 +1,7 @@ /******************************************************************************* Intel(R) Gigabit Ethernet Linux driver - Copyright(c) 2007-2013 Intel Corporation. + Copyright(c) 2007-2014 Intel Corporation. This program is free software; you can redistribute it and/or modify it under the terms and conditions of the GNU General Public License, @@ -13,8 +13,7 @@ more details. You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + this program; if not, see <http://www.gnu.org/licenses/>. The full GNU General Public License is included in this distribution in the file called "COPYING". @@ -28,17 +27,8 @@ #ifndef _E1000_I210_H_ #define _E1000_I210_H_ -s32 igb_update_flash_i210(struct e1000_hw *hw); -s32 igb_update_nvm_checksum_i210(struct e1000_hw *hw); -s32 igb_validate_nvm_checksum_i210(struct e1000_hw *hw); -s32 igb_write_nvm_srwr_i210(struct e1000_hw *hw, u16 offset, u16 words, - u16 *data); -s32 igb_read_nvm_srrd_i210(struct e1000_hw *hw, u16 offset, u16 words, - u16 *data); s32 igb_acquire_swfw_sync_i210(struct e1000_hw *hw, u16 mask); void igb_release_swfw_sync_i210(struct e1000_hw *hw, u16 mask); -s32 igb_acquire_nvm_i210(struct e1000_hw *hw); -void igb_release_nvm_i210(struct e1000_hw *hw); s32 igb_valid_led_default_i210(struct e1000_hw *hw, u16 *data); s32 igb_read_invm_version(struct e1000_hw *hw, struct e1000_fw_version *invm_ver); diff --git a/drivers/net/ethernet/intel/igb/e1000_mac.c b/drivers/net/ethernet/intel/igb/e1000_mac.c index 298f0ed50670..5910a932ea7c 100644 --- a/drivers/net/ethernet/intel/igb/e1000_mac.c +++ b/drivers/net/ethernet/intel/igb/e1000_mac.c @@ -1,7 +1,7 @@ /******************************************************************************* Intel(R) Gigabit Ethernet Linux driver - Copyright(c) 2007-2013 Intel Corporation. + Copyright(c) 2007-2014 Intel Corporation. This program is free software; you can redistribute it and/or modify it under the terms and conditions of the GNU General Public License, @@ -13,8 +13,7 @@ more details. You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + this program; if not, see <http://www.gnu.org/licenses/>. The full GNU General Public License is included in this distribution in the file called "COPYING". diff --git a/drivers/net/ethernet/intel/igb/e1000_mac.h b/drivers/net/ethernet/intel/igb/e1000_mac.h index e4cbe8ef67b3..99299ba8ee3a 100644 --- a/drivers/net/ethernet/intel/igb/e1000_mac.h +++ b/drivers/net/ethernet/intel/igb/e1000_mac.h @@ -1,7 +1,7 @@ /******************************************************************************* Intel(R) Gigabit Ethernet Linux driver - Copyright(c) 2007-2013 Intel Corporation. + Copyright(c) 2007-2014 Intel Corporation. This program is free software; you can redistribute it and/or modify it under the terms and conditions of the GNU General Public License, @@ -13,8 +13,7 @@ more details. You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + this program; if not, see <http://www.gnu.org/licenses/>. The full GNU General Public License is included in this distribution in the file called "COPYING". diff --git a/drivers/net/ethernet/intel/igb/e1000_mbx.c b/drivers/net/ethernet/intel/igb/e1000_mbx.c index dac1447fabf7..d5b121771c31 100644 --- a/drivers/net/ethernet/intel/igb/e1000_mbx.c +++ b/drivers/net/ethernet/intel/igb/e1000_mbx.c @@ -1,7 +1,7 @@ /******************************************************************************* Intel(R) Gigabit Ethernet Linux driver - Copyright(c) 2007-2013 Intel Corporation. + Copyright(c) 2007-2014 Intel Corporation. This program is free software; you can redistribute it and/or modify it under the terms and conditions of the GNU General Public License, @@ -13,8 +13,7 @@ more details. You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + this program; if not, see <http://www.gnu.org/licenses/>. The full GNU General Public License is included in this distribution in the file called "COPYING". diff --git a/drivers/net/ethernet/intel/igb/e1000_mbx.h b/drivers/net/ethernet/intel/igb/e1000_mbx.h index de9bba41acf3..f52f5515e5a8 100644 --- a/drivers/net/ethernet/intel/igb/e1000_mbx.h +++ b/drivers/net/ethernet/intel/igb/e1000_mbx.h @@ -1,7 +1,7 @@ /******************************************************************************* Intel(R) Gigabit Ethernet Linux driver - Copyright(c) 2007-2013 Intel Corporation. + Copyright(c) 2007-2014 Intel Corporation. This program is free software; you can redistribute it and/or modify it under the terms and conditions of the GNU General Public License, @@ -13,8 +13,7 @@ more details. You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + this program; if not, see <http://www.gnu.org/licenses/>. The full GNU General Public License is included in this distribution in the file called "COPYING". diff --git a/drivers/net/ethernet/intel/igb/e1000_nvm.c b/drivers/net/ethernet/intel/igb/e1000_nvm.c index a7db7f3db914..9abf82919c65 100644 --- a/drivers/net/ethernet/intel/igb/e1000_nvm.c +++ b/drivers/net/ethernet/intel/igb/e1000_nvm.c @@ -1,7 +1,7 @@ /******************************************************************************* Intel(R) Gigabit Ethernet Linux driver - Copyright(c) 2007-2013 Intel Corporation. + Copyright(c) 2007-2014 Intel Corporation. This program is free software; you can redistribute it and/or modify it under the terms and conditions of the GNU General Public License, @@ -13,8 +13,7 @@ more details. You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + this program; if not, see <http://www.gnu.org/licenses/>. The full GNU General Public License is included in this distribution in the file called "COPYING". diff --git a/drivers/net/ethernet/intel/igb/e1000_nvm.h b/drivers/net/ethernet/intel/igb/e1000_nvm.h index 433b7419cb98..5b101170b17e 100644 --- a/drivers/net/ethernet/intel/igb/e1000_nvm.h +++ b/drivers/net/ethernet/intel/igb/e1000_nvm.h @@ -1,7 +1,7 @@ /******************************************************************************* Intel(R) Gigabit Ethernet Linux driver - Copyright(c) 2013 Intel Corporation. + Copyright(c) 2007-2014 Intel Corporation. This program is free software; you can redistribute it and/or modify it under the terms and conditions of the GNU General Public License, @@ -13,8 +13,7 @@ more details. You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + this program; if not, see <http://www.gnu.org/licenses/>. The full GNU General Public License is included in this distribution in the file called "COPYING". diff --git a/drivers/net/ethernet/intel/igb/e1000_phy.c b/drivers/net/ethernet/intel/igb/e1000_phy.c index ad2b74d95138..4009bbab7407 100644 --- a/drivers/net/ethernet/intel/igb/e1000_phy.c +++ b/drivers/net/ethernet/intel/igb/e1000_phy.c @@ -1,7 +1,7 @@ /******************************************************************************* Intel(R) Gigabit Ethernet Linux driver - Copyright(c) 2007-2013 Intel Corporation. + Copyright(c) 2007-2014 Intel Corporation. This program is free software; you can redistribute it and/or modify it under the terms and conditions of the GNU General Public License, @@ -13,8 +13,7 @@ more details. You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + this program; if not, see <http://www.gnu.org/licenses/>. The full GNU General Public License is included in this distribution in the file called "COPYING". @@ -394,77 +393,6 @@ s32 igb_read_sfp_data_byte(struct e1000_hw *hw, u16 offset, u8 *data) } /** - * e1000_write_sfp_data_byte - Writes SFP module data. - * @hw: pointer to the HW structure - * @offset: byte location offset to write to - * @data: data to write - * - * Writes one byte to SFP module data stored - * in SFP resided EEPROM memory or SFP diagnostic area. - * Function should be called with - * E1000_I2CCMD_SFP_DATA_ADDR(<byte offset>) for SFP module database access - * E1000_I2CCMD_SFP_DIAG_ADDR(<byte offset>) for SFP diagnostics parameters - * access - **/ -s32 e1000_write_sfp_data_byte(struct e1000_hw *hw, u16 offset, u8 data) -{ - u32 i = 0; - u32 i2ccmd = 0; - u32 data_local = 0; - - if (offset > E1000_I2CCMD_SFP_DIAG_ADDR(255)) { - hw_dbg("I2CCMD command address exceeds upper limit\n"); - return -E1000_ERR_PHY; - } - /* The programming interface is 16 bits wide - * so we need to read the whole word first - * then update appropriate byte lane and write - * the updated word back. - */ - /* Set up Op-code, EEPROM Address,in the I2CCMD - * register. The MAC will take care of interfacing - * with an EEPROM to write the data given. - */ - i2ccmd = ((offset << E1000_I2CCMD_REG_ADDR_SHIFT) | - E1000_I2CCMD_OPCODE_READ); - /* Set a command to read single word */ - wr32(E1000_I2CCMD, i2ccmd); - for (i = 0; i < E1000_I2CCMD_PHY_TIMEOUT; i++) { - udelay(50); - /* Poll the ready bit to see if lastly - * launched I2C operation completed - */ - i2ccmd = rd32(E1000_I2CCMD); - if (i2ccmd & E1000_I2CCMD_READY) { - /* Check if this is READ or WRITE phase */ - if ((i2ccmd & E1000_I2CCMD_OPCODE_READ) == - E1000_I2CCMD_OPCODE_READ) { - /* Write the selected byte - * lane and update whole word - */ - data_local = i2ccmd & 0xFF00; - data_local |= data; - i2ccmd = ((offset << - E1000_I2CCMD_REG_ADDR_SHIFT) | - E1000_I2CCMD_OPCODE_WRITE | data_local); - wr32(E1000_I2CCMD, i2ccmd); - } else { - break; - } - } - } - if (!(i2ccmd & E1000_I2CCMD_READY)) { - hw_dbg("I2CCMD Write did not complete\n"); - return -E1000_ERR_PHY; - } - if (i2ccmd & E1000_I2CCMD_ERROR) { - hw_dbg("I2CCMD Error bit set\n"); - return -E1000_ERR_PHY; - } - return 0; -} - -/** * igb_read_phy_reg_igp - Read igp PHY register * @hw: pointer to the HW structure * @offset: register offset to be read diff --git a/drivers/net/ethernet/intel/igb/e1000_phy.h b/drivers/net/ethernet/intel/igb/e1000_phy.h index 6a0873f2095a..4c2c36c46a73 100644 --- a/drivers/net/ethernet/intel/igb/e1000_phy.h +++ b/drivers/net/ethernet/intel/igb/e1000_phy.h @@ -1,7 +1,7 @@ /******************************************************************************* Intel(R) Gigabit Ethernet Linux driver - Copyright(c) 2007-2013 Intel Corporation. + Copyright(c) 2007-2014 Intel Corporation. This program is free software; you can redistribute it and/or modify it under the terms and conditions of the GNU General Public License, @@ -13,8 +13,7 @@ more details. You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + this program; if not, see <http://www.gnu.org/licenses/>. The full GNU General Public License is included in this distribution in the file called "COPYING". @@ -70,7 +69,6 @@ s32 igb_write_phy_reg_mdic(struct e1000_hw *hw, u32 offset, u16 data); s32 igb_read_phy_reg_i2c(struct e1000_hw *hw, u32 offset, u16 *data); s32 igb_write_phy_reg_i2c(struct e1000_hw *hw, u32 offset, u16 data); s32 igb_read_sfp_data_byte(struct e1000_hw *hw, u16 offset, u8 *data); -s32 e1000_write_sfp_data_byte(struct e1000_hw *hw, u16 offset, u8 data); s32 igb_copper_link_setup_82580(struct e1000_hw *hw); s32 igb_get_phy_info_82580(struct e1000_hw *hw); s32 igb_phy_force_speed_duplex_82580(struct e1000_hw *hw); diff --git a/drivers/net/ethernet/intel/igb/e1000_regs.h b/drivers/net/ethernet/intel/igb/e1000_regs.h index 82632c6c53af..abdd935a9dad 100644 --- a/drivers/net/ethernet/intel/igb/e1000_regs.h +++ b/drivers/net/ethernet/intel/igb/e1000_regs.h @@ -1,7 +1,7 @@ /******************************************************************************* Intel(R) Gigabit Ethernet Linux driver - Copyright(c) 2007-2013 Intel Corporation. + Copyright(c) 2007-2014 Intel Corporation. This program is free software; you can redistribute it and/or modify it under the terms and conditions of the GNU General Public License, @@ -13,8 +13,7 @@ more details. You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + this program; if not, see <http://www.gnu.org/licenses/>. The full GNU General Public License is included in this distribution in the file called "COPYING". diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h index ccf472f073dd..fc3fc2c6fe40 100644 --- a/drivers/net/ethernet/intel/igb/igb.h +++ b/drivers/net/ethernet/intel/igb/igb.h @@ -1,7 +1,7 @@ /******************************************************************************* Intel(R) Gigabit Ethernet Linux driver - Copyright(c) 2007-2013 Intel Corporation. + Copyright(c) 2007-2014 Intel Corporation. This program is free software; you can redistribute it and/or modify it under the terms and conditions of the GNU General Public License, @@ -13,8 +13,7 @@ more details. You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + this program; if not, see <http://www.gnu.org/licenses/>. The full GNU General Public License is included in this distribution in the file called "COPYING". @@ -525,9 +524,7 @@ void igb_set_fw_version(struct igb_adapter *); void igb_ptp_init(struct igb_adapter *adapter); void igb_ptp_stop(struct igb_adapter *adapter); void igb_ptp_reset(struct igb_adapter *adapter); -void igb_ptp_tx_work(struct work_struct *work); void igb_ptp_rx_hang(struct igb_adapter *adapter); -void igb_ptp_tx_hwtstamp(struct igb_adapter *adapter); void igb_ptp_rx_rgtstamp(struct igb_q_vector *q_vector, struct sk_buff *skb); void igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, unsigned char *va, struct sk_buff *skb); diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c index 1df02378de69..c7f574165298 100644 --- a/drivers/net/ethernet/intel/igb/igb_ethtool.c +++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c @@ -1,7 +1,7 @@ /******************************************************************************* Intel(R) Gigabit Ethernet Linux driver - Copyright(c) 2007-2013 Intel Corporation. + Copyright(c) 2007-2014 Intel Corporation. This program is free software; you can redistribute it and/or modify it under the terms and conditions of the GNU General Public License, @@ -13,8 +13,7 @@ more details. You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + this program; if not, see <http://www.gnu.org/licenses/>. The full GNU General Public License is included in this distribution in the file called "COPYING". diff --git a/drivers/net/ethernet/intel/igb/igb_hwmon.c b/drivers/net/ethernet/intel/igb/igb_hwmon.c index e0af5bc61613..8333f67acf96 100644 --- a/drivers/net/ethernet/intel/igb/igb_hwmon.c +++ b/drivers/net/ethernet/intel/igb/igb_hwmon.c @@ -1,7 +1,7 @@ /******************************************************************************* Intel(R) Gigabit Ethernet Linux driver - Copyright(c) 2007-2013 Intel Corporation. + Copyright(c) 2007-2014 Intel Corporation. This program is free software; you can redistribute it and/or modify it under the terms and conditions of the GNU General Public License, @@ -13,8 +13,7 @@ more details. You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + this program; if not, see <http://www.gnu.org/licenses/>. The full GNU General Public License is included in this distribution in the file called "COPYING". diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 46d31a49f5ea..3384156cf1b5 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -1,7 +1,7 @@ /******************************************************************************* Intel(R) Gigabit Ethernet Linux driver - Copyright(c) 2007-2013 Intel Corporation. + Copyright(c) 2007-2014 Intel Corporation. This program is free software; you can redistribute it and/or modify it under the terms and conditions of the GNU General Public License, @@ -13,8 +13,7 @@ more details. You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + this program; if not, see <http://www.gnu.org/licenses/>. The full GNU General Public License is included in this distribution in the file called "COPYING". @@ -70,7 +69,7 @@ char igb_driver_version[] = DRV_VERSION; static const char igb_driver_string[] = "Intel(R) Gigabit Ethernet Network Driver"; static const char igb_copyright[] = - "Copyright (c) 2007-2013 Intel Corporation."; + "Copyright (c) 2007-2014 Intel Corporation."; static const struct e1000_info *igb_info_tbl[] = { [board_82575] = &e1000_82575_info, @@ -1111,10 +1110,11 @@ static void igb_set_interrupt_capability(struct igb_adapter *adapter, bool msix) for (i = 0; i < numvecs; i++) adapter->msix_entries[i].entry = i; - err = pci_enable_msix(adapter->pdev, - adapter->msix_entries, - numvecs); - if (err == 0) + err = pci_enable_msix_range(adapter->pdev, + adapter->msix_entries, + numvecs, + numvecs); + if (err > 0) return; igb_reset_interrupt_capability(adapter); diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c index 5a54e3dc535d..9c9c141f089a 100644 --- a/drivers/net/ethernet/intel/igb/igb_ptp.c +++ b/drivers/net/ethernet/intel/igb/igb_ptp.c @@ -12,9 +12,8 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. + * You should have received a copy of the GNU General Public License along with + * this program; if not, see <http://www.gnu.org/licenses/>. */ #include <linux/module.h> #include <linux/device.h> @@ -75,6 +74,8 @@ #define INCVALUE_82576 (16 << IGB_82576_TSYNC_SHIFT) #define IGB_NBITS_82580 40 +static void igb_ptp_tx_hwtstamp(struct igb_adapter *adapter); + /* SYSTIM read access for the 82576 */ static cycle_t igb_ptp_read_82576(const struct cyclecounter *cc) { @@ -372,7 +373,7 @@ static int igb_ptp_enable(struct ptp_clock_info *ptp, * This work function polls the TSYNCTXCTL valid bit to determine when a * timestamp has been taken for the current stored skb. **/ -void igb_ptp_tx_work(struct work_struct *work) +static void igb_ptp_tx_work(struct work_struct *work) { struct igb_adapter *adapter = container_of(work, struct igb_adapter, ptp_tx_work); @@ -466,7 +467,7 @@ void igb_ptp_rx_hang(struct igb_adapter *adapter) * available, then it must have been for this skb here because we only * allow only one such packet into the queue. **/ -void igb_ptp_tx_hwtstamp(struct igb_adapter *adapter) +static void igb_ptp_tx_hwtstamp(struct igb_adapter *adapter) { struct e1000_hw *hw = &adapter->hw; struct skb_shared_hwtstamps shhwtstamps; diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c index 675435fc2e53..e2c6d8059b74 100644 --- a/drivers/net/ethernet/intel/igbvf/netdev.c +++ b/drivers/net/ethernet/intel/igbvf/netdev.c @@ -1043,11 +1043,11 @@ static void igbvf_set_interrupt_capability(struct igbvf_adapter *adapter) for (i = 0; i < 3; i++) adapter->msix_entries[i].entry = i; - err = pci_enable_msix(adapter->pdev, - adapter->msix_entries, 3); + err = pci_enable_msix_range(adapter->pdev, + adapter->msix_entries, 3, 3); } - if (err) { + if (err < 0) { /* MSI-X failed */ dev_err(&adapter->pdev->dev, "Failed to initialize MSI-X interrupts.\n"); diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_main.c b/drivers/net/ethernet/intel/ixgb/ixgb_main.c index 57e390cbe6d0..f42c201f727f 100644 --- a/drivers/net/ethernet/intel/ixgb/ixgb_main.c +++ b/drivers/net/ethernet/intel/ixgb/ixgb_main.c @@ -1521,12 +1521,12 @@ ixgb_xmit_frame(struct sk_buff *skb, struct net_device *netdev) int tso; if (test_bit(__IXGB_DOWN, &adapter->flags)) { - dev_kfree_skb(skb); + dev_kfree_skb_any(skb); return NETDEV_TX_OK; } if (skb->len <= 0) { - dev_kfree_skb(skb); + dev_kfree_skb_any(skb); return NETDEV_TX_OK; } @@ -1543,7 +1543,7 @@ ixgb_xmit_frame(struct sk_buff *skb, struct net_device *netdev) tso = ixgb_tso(adapter, skb); if (tso < 0) { - dev_kfree_skb(skb); + dev_kfree_skb_any(skb); return NETDEV_TX_OK; } diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h index 0186ea2969fe..4371ef0ed4a0 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h @@ -765,6 +765,7 @@ struct ixgbe_adapter { struct ptp_clock_info ptp_caps; struct work_struct ptp_tx_work; struct sk_buff *ptp_tx_skb; + struct hwtstamp_config tstamp_config; unsigned long ptp_tx_start; unsigned long last_overflow_check; unsigned long last_rx_ptp_check; @@ -884,7 +885,6 @@ s32 ixgbe_fdir_erase_perfect_filter_82599(struct ixgbe_hw *hw, u16 soft_id); void ixgbe_atr_compute_perfect_hash_82599(union ixgbe_atr_input *input, union ixgbe_atr_input *mask); -bool ixgbe_verify_lesm_fw_enabled_82599(struct ixgbe_hw *hw); void ixgbe_set_rx_mode(struct net_device *netdev); #ifdef CONFIG_IXGBE_DCB void ixgbe_set_rx_drop_en(struct ixgbe_adapter *adapter); @@ -958,8 +958,8 @@ static inline void ixgbe_ptp_rx_hwtstamp(struct ixgbe_ring *rx_ring, rx_ring->last_rx_timestamp = jiffies; } -int ixgbe_ptp_hwtstamp_ioctl(struct ixgbe_adapter *adapter, struct ifreq *ifr, - int cmd); +int ixgbe_ptp_set_ts_config(struct ixgbe_adapter *adapter, struct ifreq *ifr); +int ixgbe_ptp_get_ts_config(struct ixgbe_adapter *adapter, struct ifreq *ifr); void ixgbe_ptp_start_cyclecounter(struct ixgbe_adapter *adapter); void ixgbe_ptp_reset(struct ixgbe_adapter *adapter); void ixgbe_ptp_check_pps_event(struct ixgbe_adapter *adapter, u32 eicr); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c index a26f3fee4f35..15506f0780b2 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c @@ -1,7 +1,7 @@ /******************************************************************************* Intel 10 Gigabit PCI Express Linux driver - Copyright(c) 1999 - 2013 Intel Corporation. + Copyright(c) 1999 - 2014 Intel Corporation. This program is free software; you can redistribute it and/or modify it under the terms and conditions of the GNU General Public License, @@ -61,6 +61,9 @@ static void ixgbe_set_pcie_completion_timeout(struct ixgbe_hw *hw) u32 gcr = IXGBE_READ_REG(hw, IXGBE_GCR); u16 pcie_devctl2; + if (ixgbe_removed(hw->hw_addr)) + return; + /* only take action if timeout value is defaulted to 0 */ if (gcr & IXGBE_GCR_CMPL_TMOUT_MASK) goto out; @@ -79,8 +82,9 @@ static void ixgbe_set_pcie_completion_timeout(struct ixgbe_hw *hw) * directly in order to set the completion timeout value for * 16ms to 55ms */ - pci_read_config_word(adapter->pdev, - IXGBE_PCI_DEVICE_CONTROL2, &pcie_devctl2); + pcie_devctl2 = ixgbe_read_pci_cfg_word(hw, IXGBE_PCI_DEVICE_CONTROL2); + if (ixgbe_removed(hw->hw_addr)) + return; pcie_devctl2 |= IXGBE_PCI_DEVICE_CONTROL2_16ms; pci_write_config_word(adapter->pdev, IXGBE_PCI_DEVICE_CONTROL2, pcie_devctl2); @@ -1316,6 +1320,8 @@ static struct ixgbe_mac_operations mac_ops_82598 = { .get_thermal_sensor_data = NULL, .init_thermal_sensor_thresh = NULL, .mng_fw_enabled = NULL, + .prot_autoc_read = &prot_autoc_read_generic, + .prot_autoc_write = &prot_autoc_write_generic, }; static struct ixgbe_eeprom_operations eeprom_ops_82598 = { diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c index edda6814108c..b96cefd5a2eb 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c @@ -1,7 +1,7 @@ /******************************************************************************* Intel 10 Gigabit PCI Express Linux driver - Copyright(c) 1999 - 2013 Intel Corporation. + Copyright(c) 1999 - 2014 Intel Corporation. This program is free software; you can redistribute it and/or modify it under the terms and conditions of the GNU General Public License, @@ -63,6 +63,8 @@ static s32 ixgbe_read_i2c_byte_82599(struct ixgbe_hw *hw, u8 byte_offset, u8 dev_addr, u8 *data); static s32 ixgbe_write_i2c_byte_82599(struct ixgbe_hw *hw, u8 byte_offset, u8 dev_addr, u8 data); +static s32 ixgbe_reset_pipeline_82599(struct ixgbe_hw *hw); +static bool ixgbe_verify_lesm_fw_enabled_82599(struct ixgbe_hw *hw); static bool ixgbe_mng_enabled(struct ixgbe_hw *hw) { @@ -122,7 +124,6 @@ static s32 ixgbe_setup_sfp_modules_82599(struct ixgbe_hw *hw) { s32 ret_val = 0; u16 list_offset, data_offset, data_value; - bool got_lock = false; if (hw->phy.sfp_type != ixgbe_sfp_type_unknown) { ixgbe_init_mac_link_ops_82599(hw); @@ -160,30 +161,10 @@ static s32 ixgbe_setup_sfp_modules_82599(struct ixgbe_hw *hw) usleep_range(hw->eeprom.semaphore_delay * 1000, hw->eeprom.semaphore_delay * 2000); - /* Need SW/FW semaphore around AUTOC writes if LESM on, - * likewise reset_pipeline requires lock as it also writes - * AUTOC. - */ - if (ixgbe_verify_lesm_fw_enabled_82599(hw)) { - ret_val = hw->mac.ops.acquire_swfw_sync(hw, - IXGBE_GSSR_MAC_CSR_SM); - if (ret_val) - goto setup_sfp_out; - - got_lock = true; - } - /* Restart DSP and set SFI mode */ - IXGBE_WRITE_REG(hw, IXGBE_AUTOC, ((hw->mac.orig_autoc) | - IXGBE_AUTOC_LMS_10G_SERIAL)); - hw->mac.cached_autoc = IXGBE_READ_REG(hw, IXGBE_AUTOC); - ret_val = ixgbe_reset_pipeline_82599(hw); - - if (got_lock) { - hw->mac.ops.release_swfw_sync(hw, - IXGBE_GSSR_MAC_CSR_SM); - got_lock = false; - } + ret_val = hw->mac.ops.prot_autoc_write(hw, + hw->mac.orig_autoc | IXGBE_AUTOC_LMS_10G_SERIAL, + false); if (ret_val) { hw_dbg(hw, " sfp module setup not complete\n"); @@ -207,6 +188,79 @@ setup_sfp_err: return IXGBE_ERR_SFP_SETUP_NOT_COMPLETE; } +/** + * prot_autoc_read_82599 - Hides MAC differences needed for AUTOC read + * @hw: pointer to hardware structure + * @locked: Return the if we locked for this read. + * @reg_val: Value we read from AUTOC + * + * For this part (82599) we need to wrap read-modify-writes with a possible + * FW/SW lock. It is assumed this lock will be freed with the next + * prot_autoc_write_82599(). Note, that locked can only be true in cases + * where this function doesn't return an error. + **/ +static s32 prot_autoc_read_82599(struct ixgbe_hw *hw, bool *locked, + u32 *reg_val) +{ + s32 ret_val; + + *locked = false; + /* If LESM is on then we need to hold the SW/FW semaphore. */ + if (ixgbe_verify_lesm_fw_enabled_82599(hw)) { + ret_val = hw->mac.ops.acquire_swfw_sync(hw, + IXGBE_GSSR_MAC_CSR_SM); + if (!ret_val) + return IXGBE_ERR_SWFW_SYNC; + + *locked = true; + } + + *reg_val = IXGBE_READ_REG(hw, IXGBE_AUTOC); + return 0; +} + +/** + * prot_autoc_write_82599 - Hides MAC differences needed for AUTOC write + * @hw: pointer to hardware structure + * @reg_val: value to write to AUTOC + * @locked: bool to indicate whether the SW/FW lock was already taken by + * previous proc_autoc_read_82599. + * + * This part (82599) may need to hold a the SW/FW lock around all writes to + * AUTOC. Likewise after a write we need to do a pipeline reset. + **/ +static s32 prot_autoc_write_82599(struct ixgbe_hw *hw, u32 autoc, bool locked) +{ + s32 ret_val = 0; + + /* Blocked by MNG FW so bail */ + if (ixgbe_check_reset_blocked(hw)) + goto out; + + /* We only need to get the lock if: + * - We didn't do it already (in the read part of a read-modify-write) + * - LESM is enabled. + */ + if (!locked && ixgbe_verify_lesm_fw_enabled_82599(hw)) { + ret_val = hw->mac.ops.acquire_swfw_sync(hw, + IXGBE_GSSR_MAC_CSR_SM); + if (!ret_val) + return IXGBE_ERR_SWFW_SYNC; + } + + IXGBE_WRITE_REG(hw, IXGBE_AUTOC, autoc); + ret_val = ixgbe_reset_pipeline_82599(hw); + +out: + /* Free the SW/FW semaphore as we either grabbed it here or + * already had it when this function was called. + */ + if (locked) + hw->mac.ops.release_swfw_sync(hw, IXGBE_GSSR_MAC_CSR_SM); + + return ret_val; +} + static s32 ixgbe_get_invariants_82599(struct ixgbe_hw *hw) { struct ixgbe_mac_info *mac = &hw->mac; @@ -542,6 +596,10 @@ static void ixgbe_disable_tx_laser_multispeed_fiber(struct ixgbe_hw *hw) { u32 esdp_reg = IXGBE_READ_REG(hw, IXGBE_ESDP); + /* Blocked by MNG FW so bail */ + if (ixgbe_check_reset_blocked(hw)) + return; + /* Disable tx laser; allow 100us to go dark per spec */ esdp_reg |= IXGBE_ESDP_SDP3; IXGBE_WRITE_REG(hw, IXGBE_ESDP, esdp_reg); @@ -582,6 +640,10 @@ static void ixgbe_enable_tx_laser_multispeed_fiber(struct ixgbe_hw *hw) **/ static void ixgbe_flap_tx_laser_multispeed_fiber(struct ixgbe_hw *hw) { + /* Blocked by MNG FW so bail */ + if (ixgbe_check_reset_blocked(hw)) + return; + if (hw->mac.autotry_restart) { ixgbe_disable_tx_laser_multispeed_fiber(hw); ixgbe_enable_tx_laser_multispeed_fiber(hw); @@ -966,7 +1028,6 @@ static s32 ixgbe_setup_mac_link_82599(struct ixgbe_hw *hw, u32 links_reg; u32 i; ixgbe_link_speed link_capabilities = IXGBE_LINK_SPEED_UNKNOWN; - bool got_lock = false; bool autoneg = false; /* Check to see if speed passed in is supported. */ @@ -989,7 +1050,7 @@ static s32 ixgbe_setup_mac_link_82599(struct ixgbe_hw *hw, autoc = IXGBE_READ_REG(hw, IXGBE_AUTOC); orig_autoc = autoc; - start_autoc = hw->mac.cached_autoc; + start_autoc = IXGBE_READ_REG(hw, IXGBE_AUTOC); link_mode = autoc & IXGBE_AUTOC_LMS_MASK; pma_pmd_1g = autoc & IXGBE_AUTOC_1G_PMA_PMD_MASK; @@ -1030,27 +1091,10 @@ static s32 ixgbe_setup_mac_link_82599(struct ixgbe_hw *hw, } if (autoc != start_autoc) { - /* Need SW/FW semaphore around AUTOC writes if LESM is on, - * likewise reset_pipeline requires us to hold this lock as - * it also writes to AUTOC. - */ - if (ixgbe_verify_lesm_fw_enabled_82599(hw)) { - status = hw->mac.ops.acquire_swfw_sync(hw, - IXGBE_GSSR_MAC_CSR_SM); - if (status != 0) - goto out; - - got_lock = true; - } - /* Restart link */ - IXGBE_WRITE_REG(hw, IXGBE_AUTOC, autoc); - hw->mac.cached_autoc = autoc; - ixgbe_reset_pipeline_82599(hw); - - if (got_lock) - hw->mac.ops.release_swfw_sync(hw, - IXGBE_GSSR_MAC_CSR_SM); + status = hw->mac.ops.prot_autoc_write(hw, autoc, false); + if (!status) + goto out; /* Only poll for autoneg to complete if specified to do so */ if (autoneg_wait_to_complete) { @@ -1117,7 +1161,7 @@ static s32 ixgbe_reset_hw_82599(struct ixgbe_hw *hw) { ixgbe_link_speed link_speed; s32 status; - u32 ctrl, i, autoc2; + u32 ctrl, i, autoc, autoc2; u32 curr_lms; bool link_up = false; @@ -1151,11 +1195,7 @@ static s32 ixgbe_reset_hw_82599(struct ixgbe_hw *hw) hw->phy.ops.reset(hw); /* remember AUTOC from before we reset */ - if (hw->mac.cached_autoc) - curr_lms = hw->mac.cached_autoc & IXGBE_AUTOC_LMS_MASK; - else - curr_lms = IXGBE_READ_REG(hw, IXGBE_AUTOC) & - IXGBE_AUTOC_LMS_MASK; + curr_lms = IXGBE_READ_REG(hw, IXGBE_AUTOC) & IXGBE_AUTOC_LMS_MASK; mac_reset_top: /* @@ -1205,7 +1245,7 @@ mac_reset_top: * stored off yet. Otherwise restore the stored original * values since the reset operation sets back to defaults. */ - hw->mac.cached_autoc = IXGBE_READ_REG(hw, IXGBE_AUTOC); + autoc = IXGBE_READ_REG(hw, IXGBE_AUTOC); autoc2 = IXGBE_READ_REG(hw, IXGBE_AUTOC2); /* Enable link if disabled in NVM */ @@ -1216,7 +1256,7 @@ mac_reset_top: } if (hw->mac.orig_link_settings_stored == false) { - hw->mac.orig_autoc = hw->mac.cached_autoc; + hw->mac.orig_autoc = autoc; hw->mac.orig_autoc2 = autoc2; hw->mac.orig_link_settings_stored = true; } else { @@ -1233,28 +1273,12 @@ mac_reset_top: (hw->mac.orig_autoc & ~IXGBE_AUTOC_LMS_MASK) | curr_lms; - if (hw->mac.cached_autoc != hw->mac.orig_autoc) { - /* Need SW/FW semaphore around AUTOC writes if LESM is - * on, likewise reset_pipeline requires us to hold - * this lock as it also writes to AUTOC. - */ - bool got_lock = false; - if (ixgbe_verify_lesm_fw_enabled_82599(hw)) { - status = hw->mac.ops.acquire_swfw_sync(hw, - IXGBE_GSSR_MAC_CSR_SM); - if (status) - goto reset_hw_out; - - got_lock = true; - } - - IXGBE_WRITE_REG(hw, IXGBE_AUTOC, hw->mac.orig_autoc); - hw->mac.cached_autoc = hw->mac.orig_autoc; - ixgbe_reset_pipeline_82599(hw); - - if (got_lock) - hw->mac.ops.release_swfw_sync(hw, - IXGBE_GSSR_MAC_CSR_SM); + if (autoc != hw->mac.orig_autoc) { + status = hw->mac.ops.prot_autoc_write(hw, + hw->mac.orig_autoc, + false); + if (!status) + goto reset_hw_out; } if ((autoc2 & IXGBE_AUTOC2_UPPER_MASK) != @@ -2260,7 +2284,7 @@ fw_version_err: * Returns true if the LESM FW module is present and enabled. Otherwise * returns false. Smart Speed must be disabled if LESM FW module is enabled. **/ -bool ixgbe_verify_lesm_fw_enabled_82599(struct ixgbe_hw *hw) +static bool ixgbe_verify_lesm_fw_enabled_82599(struct ixgbe_hw *hw) { bool lesm_enabled = false; u16 fw_offset, fw_lesm_param_offset, fw_lesm_state; @@ -2366,7 +2390,7 @@ static s32 ixgbe_read_eeprom_82599(struct ixgbe_hw *hw, * full pipeline reset. Note - We must hold the SW/FW semaphore before writing * to AUTOC, so this function assumes the semaphore is held. **/ -s32 ixgbe_reset_pipeline_82599(struct ixgbe_hw *hw) +static s32 ixgbe_reset_pipeline_82599(struct ixgbe_hw *hw) { s32 ret_val; u32 anlp1_reg = 0; @@ -2380,11 +2404,12 @@ s32 ixgbe_reset_pipeline_82599(struct ixgbe_hw *hw) IXGBE_WRITE_FLUSH(hw); } - autoc_reg = hw->mac.cached_autoc; + autoc_reg = IXGBE_READ_REG(hw, IXGBE_AUTOC); autoc_reg |= IXGBE_AUTOC_AN_RESTART; /* Write AUTOC register with toggled LMS[2] bit and Restart_AN */ - IXGBE_WRITE_REG(hw, IXGBE_AUTOC, autoc_reg ^ IXGBE_AUTOC_LMS_1G_AN); + IXGBE_WRITE_REG(hw, IXGBE_AUTOC, + autoc_reg ^ (0x4 << IXGBE_AUTOC_LMS_SHIFT)); /* Wait for AN to leave state 0 */ for (i = 0; i < 10; i++) { @@ -2566,6 +2591,8 @@ static struct ixgbe_mac_operations mac_ops_82599 = { .get_thermal_sensor_data = &ixgbe_get_thermal_sensor_data_generic, .init_thermal_sensor_thresh = &ixgbe_init_thermal_sensor_thresh_generic, .mng_fw_enabled = &ixgbe_mng_enabled, + .prot_autoc_read = &prot_autoc_read_82599, + .prot_autoc_write = &prot_autoc_write_82599, }; static struct ixgbe_eeprom_operations eeprom_ops_82599 = { diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c index b5c434b617b1..4456c235a44a 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c @@ -1,7 +1,7 @@ /******************************************************************************* Intel 10 Gigabit PCI Express Linux driver - Copyright(c) 1999 - 2013 Intel Corporation. + Copyright(c) 1999 - 2014 Intel Corporation. This program is free software; you can redistribute it and/or modify it under the terms and conditions of the GNU General Public License, @@ -114,7 +114,7 @@ static s32 ixgbe_setup_fc(struct ixgbe_hw *hw) s32 ret_val = 0; u32 reg = 0, reg_bp = 0; u16 reg_cu = 0; - bool got_lock = false; + bool locked = false; /* * Validate the requested mode. Strict IEEE mode does not allow @@ -139,11 +139,17 @@ static s32 ixgbe_setup_fc(struct ixgbe_hw *hw) * we link at 10G, the 1G advertisement is harmless and vice versa. */ switch (hw->phy.media_type) { + case ixgbe_media_type_backplane: + /* some MAC's need RMW protection on AUTOC */ + ret_val = hw->mac.ops.prot_autoc_read(hw, &locked, ®_bp); + if (!ret_val) + goto out; + + /* only backplane uses autoc so fall though */ case ixgbe_media_type_fiber_fixed: case ixgbe_media_type_fiber: - case ixgbe_media_type_backplane: reg = IXGBE_READ_REG(hw, IXGBE_PCS1GANA); - reg_bp = IXGBE_READ_REG(hw, IXGBE_AUTOC); + break; case ixgbe_media_type_copper: hw->phy.ops.read_reg(hw, MDIO_AN_ADVERTISE, @@ -240,27 +246,12 @@ static s32 ixgbe_setup_fc(struct ixgbe_hw *hw) * LESM is on, likewise reset_pipeline requries the lock as * it also writes AUTOC. */ - if ((hw->mac.type == ixgbe_mac_82599EB) && - ixgbe_verify_lesm_fw_enabled_82599(hw)) { - ret_val = hw->mac.ops.acquire_swfw_sync(hw, - IXGBE_GSSR_MAC_CSR_SM); - if (ret_val) - goto out; - - got_lock = true; - } - - IXGBE_WRITE_REG(hw, IXGBE_AUTOC, reg_bp); - - if (hw->mac.type == ixgbe_mac_82599EB) - ixgbe_reset_pipeline_82599(hw); - - if (got_lock) - hw->mac.ops.release_swfw_sync(hw, - IXGBE_GSSR_MAC_CSR_SM); + ret_val = hw->mac.ops.prot_autoc_write(hw, reg_bp, locked); + if (ret_val) + goto out; } else if ((hw->phy.media_type == ixgbe_media_type_copper) && - ixgbe_device_supports_autoneg_fc(hw)) { + ixgbe_device_supports_autoneg_fc(hw)) { hw->phy.ops.write_reg(hw, MDIO_AN_ADVERTISE, MDIO_MMD_AN, reg_cu); } @@ -2437,6 +2428,55 @@ out: } /** + * ixgbe_pcie_timeout_poll - Return number of times to poll for completion + * @hw: pointer to hardware structure + * + * System-wide timeout range is encoded in PCIe Device Control2 register. + * + * Add 10% to specified maximum and return the number of times to poll for + * completion timeout, in units of 100 microsec. Never return less than + * 800 = 80 millisec. + **/ +static u32 ixgbe_pcie_timeout_poll(struct ixgbe_hw *hw) +{ + struct ixgbe_adapter *adapter = hw->back; + s16 devctl2; + u32 pollcnt; + + pci_read_config_word(adapter->pdev, IXGBE_PCI_DEVICE_CONTROL2, + &devctl2); + devctl2 &= IXGBE_PCIDEVCTRL2_TIMEO_MASK; + + switch (devctl2) { + case IXGBE_PCIDEVCTRL2_65_130ms: + pollcnt = 1300; /* 130 millisec */ + break; + case IXGBE_PCIDEVCTRL2_260_520ms: + pollcnt = 5200; /* 520 millisec */ + break; + case IXGBE_PCIDEVCTRL2_1_2s: + pollcnt = 20000; /* 2 sec */ + break; + case IXGBE_PCIDEVCTRL2_4_8s: + pollcnt = 80000; /* 8 sec */ + break; + case IXGBE_PCIDEVCTRL2_17_34s: + pollcnt = 34000; /* 34 sec */ + break; + case IXGBE_PCIDEVCTRL2_50_100us: /* 100 microsecs */ + case IXGBE_PCIDEVCTRL2_1_2ms: /* 2 millisecs */ + case IXGBE_PCIDEVCTRL2_16_32ms: /* 32 millisec */ + case IXGBE_PCIDEVCTRL2_16_32ms_def: /* 32 millisec default */ + default: + pollcnt = 800; /* 80 millisec minimum */ + break; + } + + /* add 10% to spec maximum */ + return (pollcnt * 11) / 10; +} + +/** * ixgbe_disable_pcie_master - Disable PCI-express master access * @hw: pointer to hardware structure * @@ -2447,16 +2487,16 @@ out: **/ static s32 ixgbe_disable_pcie_master(struct ixgbe_hw *hw) { - struct ixgbe_adapter *adapter = hw->back; s32 status = 0; - u32 i; + u32 i, poll; u16 value; /* Always set this bit to ensure any future transactions are blocked */ IXGBE_WRITE_REG(hw, IXGBE_CTRL, IXGBE_CTRL_GIO_DIS); /* Exit if master requests are blocked */ - if (!(IXGBE_READ_REG(hw, IXGBE_STATUS) & IXGBE_STATUS_GIO)) + if (!(IXGBE_READ_REG(hw, IXGBE_STATUS) & IXGBE_STATUS_GIO) || + ixgbe_removed(hw->hw_addr)) goto out; /* Poll for master request bit to clear */ @@ -2481,10 +2521,12 @@ static s32 ixgbe_disable_pcie_master(struct ixgbe_hw *hw) * Before proceeding, make sure that the PCIe block does not have * transactions pending. */ - for (i = 0; i < IXGBE_PCI_MASTER_DISABLE_TIMEOUT; i++) { + poll = ixgbe_pcie_timeout_poll(hw); + for (i = 0; i < poll; i++) { udelay(100); - pci_read_config_word(adapter->pdev, IXGBE_PCI_DEVICE_STATUS, - &value); + value = ixgbe_read_pci_cfg_word(hw, IXGBE_PCI_DEVICE_STATUS); + if (ixgbe_removed(hw->hw_addr)) + goto out; if (!(value & IXGBE_PCI_DEVICE_STATUS_TRANSACTION_PENDING)) goto out; } @@ -2564,6 +2606,35 @@ void ixgbe_release_swfw_sync(struct ixgbe_hw *hw, u16 mask) } /** + * prot_autoc_read_generic - Hides MAC differences needed for AUTOC read + * @hw: pointer to hardware structure + * @reg_val: Value we read from AUTOC + * @locked: bool to indicate whether the SW/FW lock should be taken. Never + * true in this the generic case. + * + * The default case requires no protection so just to the register read. + **/ +s32 prot_autoc_read_generic(struct ixgbe_hw *hw, bool *locked, u32 *reg_val) +{ + *locked = false; + *reg_val = IXGBE_READ_REG(hw, IXGBE_AUTOC); + return 0; +} + +/** + * prot_autoc_write_generic - Hides MAC differences needed for AUTOC write + * @hw: pointer to hardware structure + * @reg_val: value to write to AUTOC + * @locked: bool to indicate whether the SW/FW lock was already taken by + * previous read. + **/ +s32 prot_autoc_write_generic(struct ixgbe_hw *hw, u32 reg_val, bool locked) +{ + IXGBE_WRITE_REG(hw, IXGBE_AUTOC, reg_val); + return 0; +} + +/** * ixgbe_disable_rx_buff_generic - Stops the receive data path * @hw: pointer to hardware structure * @@ -2641,6 +2712,7 @@ s32 ixgbe_blink_led_start_generic(struct ixgbe_hw *hw, u32 index) u32 autoc_reg = IXGBE_READ_REG(hw, IXGBE_AUTOC); u32 led_reg = IXGBE_READ_REG(hw, IXGBE_LEDCTL); s32 ret_val = 0; + bool locked = false; /* * Link must be up to auto-blink the LEDs; @@ -2649,28 +2721,19 @@ s32 ixgbe_blink_led_start_generic(struct ixgbe_hw *hw, u32 index) hw->mac.ops.check_link(hw, &speed, &link_up, false); if (!link_up) { - /* Need the SW/FW semaphore around AUTOC writes if 82599 and - * LESM is on. - */ - bool got_lock = false; - - if ((hw->mac.type == ixgbe_mac_82599EB) && - ixgbe_verify_lesm_fw_enabled_82599(hw)) { - ret_val = hw->mac.ops.acquire_swfw_sync(hw, - IXGBE_GSSR_MAC_CSR_SM); - if (ret_val) - goto out; + ret_val = hw->mac.ops.prot_autoc_read(hw, &locked, &autoc_reg); + if (!ret_val) + goto out; - got_lock = true; - } autoc_reg |= IXGBE_AUTOC_AN_RESTART; autoc_reg |= IXGBE_AUTOC_FLU; - IXGBE_WRITE_REG(hw, IXGBE_AUTOC, autoc_reg); + + ret_val = hw->mac.ops.prot_autoc_write(hw, autoc_reg, locked); + if (!ret_val) + goto out; + IXGBE_WRITE_FLUSH(hw); - if (got_lock) - hw->mac.ops.release_swfw_sync(hw, - IXGBE_GSSR_MAC_CSR_SM); usleep_range(10000, 20000); } @@ -2690,33 +2753,21 @@ out: **/ s32 ixgbe_blink_led_stop_generic(struct ixgbe_hw *hw, u32 index) { - u32 autoc_reg = IXGBE_READ_REG(hw, IXGBE_AUTOC); + u32 autoc_reg = 0; u32 led_reg = IXGBE_READ_REG(hw, IXGBE_LEDCTL); s32 ret_val = 0; - bool got_lock = false; + bool locked = false; - /* Need the SW/FW semaphore around AUTOC writes if 82599 and - * LESM is on. - */ - if ((hw->mac.type == ixgbe_mac_82599EB) && - ixgbe_verify_lesm_fw_enabled_82599(hw)) { - ret_val = hw->mac.ops.acquire_swfw_sync(hw, - IXGBE_GSSR_MAC_CSR_SM); - if (ret_val) - goto out; - - got_lock = true; - } + ret_val = hw->mac.ops.prot_autoc_read(hw, &locked, &autoc_reg); + if (!ret_val) + goto out; autoc_reg &= ~IXGBE_AUTOC_FLU; autoc_reg |= IXGBE_AUTOC_AN_RESTART; - IXGBE_WRITE_REG(hw, IXGBE_AUTOC, autoc_reg); - - if (hw->mac.type == ixgbe_mac_82599EB) - ixgbe_reset_pipeline_82599(hw); - if (got_lock) - hw->mac.ops.release_swfw_sync(hw, IXGBE_GSSR_MAC_CSR_SM); + ret_val = hw->mac.ops.prot_autoc_write(hw, autoc_reg, locked); + if (!ret_val) + goto out; led_reg &= ~IXGBE_LED_MODE_MASK(index); led_reg &= ~IXGBE_LED_BLINK(index); @@ -2817,7 +2868,6 @@ san_mac_addr_clr: **/ u16 ixgbe_get_pcie_msix_count_generic(struct ixgbe_hw *hw) { - struct ixgbe_adapter *adapter = hw->back; u16 msix_count = 1; u16 max_msix_count; u16 pcie_offset; @@ -2836,7 +2886,9 @@ u16 ixgbe_get_pcie_msix_count_generic(struct ixgbe_hw *hw) return msix_count; } - pci_read_config_word(adapter->pdev, pcie_offset, &msix_count); + msix_count = ixgbe_read_pci_cfg_word(hw, pcie_offset); + if (ixgbe_removed(hw->hw_addr)) + msix_count = 0; msix_count &= IXGBE_PCIE_MSIX_TBL_SZ_MASK; /* MSI-X count is zero-based in HW */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h index f2e3919750ec..ef0fd4cef5df 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h @@ -1,7 +1,7 @@ /******************************************************************************* Intel 10 Gigabit PCI Express Linux driver - Copyright(c) 1999 - 2013 Intel Corporation. + Copyright(c) 1999 - 2014 Intel Corporation. This program is free software; you can redistribute it and/or modify it under the terms and conditions of the GNU General Public License, @@ -98,6 +98,10 @@ s32 ixgbe_check_mac_link_generic(struct ixgbe_hw *hw, bool *link_up, bool link_up_wait_to_complete); s32 ixgbe_get_wwn_prefix_generic(struct ixgbe_hw *hw, u16 *wwnn_prefix, u16 *wwpn_prefix); + +s32 prot_autoc_read_generic(struct ixgbe_hw *hw, bool *, u32 *reg_val); +s32 prot_autoc_write_generic(struct ixgbe_hw *hw, u32 reg_val, bool locked); + s32 ixgbe_blink_led_start_generic(struct ixgbe_hw *hw, u32 index); s32 ixgbe_blink_led_stop_generic(struct ixgbe_hw *hw, u32 index); void ixgbe_set_mac_anti_spoofing(struct ixgbe_hw *hw, bool enable, int pf); @@ -109,7 +113,6 @@ void ixgbe_clear_tx_pending(struct ixgbe_hw *hw); void ixgbe_set_rxpba_generic(struct ixgbe_hw *hw, int num_pb, u32 headroom, int strategy); -s32 ixgbe_reset_pipeline_82599(struct ixgbe_hw *hw); #define IXGBE_I2C_THERMAL_SENSOR_ADDR 0xF8 #define IXGBE_EMC_INTERNAL_DATA 0x00 @@ -125,6 +128,10 @@ s32 ixgbe_get_thermal_sensor_data_generic(struct ixgbe_hw *hw); s32 ixgbe_init_thermal_sensor_thresh_generic(struct ixgbe_hw *hw); #define IXGBE_FAILED_READ_REG 0xffffffffU +#define IXGBE_FAILED_READ_CFG_DWORD 0xffffffffU +#define IXGBE_FAILED_READ_CFG_WORD 0xffffU + +u16 ixgbe_read_pci_cfg_word(struct ixgbe_hw *hw, u32 reg); static inline bool ixgbe_removed(void __iomem *addr) { diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c index 043307024c4a..f2d35c04159c 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c @@ -1,7 +1,7 @@ /******************************************************************************* Intel 10 Gigabit PCI Express Linux driver - Copyright(c) 1999 - 2013 Intel Corporation. + Copyright(c) 1999 - 2014 Intel Corporation. This program is free software; you can redistribute it and/or modify it under the terms and conditions of the GNU General Public License, @@ -1247,6 +1247,11 @@ static int ixgbe_link_test(struct ixgbe_adapter *adapter, u64 *data) struct ixgbe_hw *hw = &adapter->hw; bool link_up; u32 link_speed = 0; + + if (ixgbe_removed(hw->hw_addr)) { + *data = 1; + return 1; + } *data = 0; hw->mac.ops.check_link(hw, &link_speed, &link_up, true); @@ -1969,6 +1974,7 @@ static void ixgbe_diag_test(struct net_device *netdev, data[1] = 1; data[2] = 1; data[3] = 1; + data[4] = 1; eth_test->flags |= ETH_TEST_FL_FAILED; return; } @@ -1988,6 +1994,7 @@ static void ixgbe_diag_test(struct net_device *netdev, data[1] = 1; data[2] = 1; data[3] = 1; + data[4] = 1; eth_test->flags |= ETH_TEST_FL_FAILED; clear_bit(__IXGBE_TESTING, &adapter->state); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c index 32e3eaaa160a..0834e1ea44bc 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c @@ -698,7 +698,7 @@ static void ixgbe_set_num_queues(struct ixgbe_adapter *adapter) static void ixgbe_acquire_msix_vectors(struct ixgbe_adapter *adapter, int vectors) { - int err, vector_threshold; + int vector_threshold; /* We'll want at least 2 (vector_threshold): * 1) TxQ[0] + RxQ[0] handler @@ -712,18 +712,10 @@ static void ixgbe_acquire_msix_vectors(struct ixgbe_adapter *adapter, * Right now, we simply care about how many we'll get; we'll * set them up later while requesting irq's. */ - while (vectors >= vector_threshold) { - err = pci_enable_msix(adapter->pdev, adapter->msix_entries, - vectors); - if (!err) /* Success in acquiring all requested vectors. */ - break; - else if (err < 0) - vectors = 0; /* Nasty failure, quit now */ - else /* err == number of vectors we should try again with */ - vectors = err; - } + vectors = pci_enable_msix_range(adapter->pdev, adapter->msix_entries, + vector_threshold, vectors); - if (vectors < vector_threshold) { + if (vectors < 0) { /* Can't allocate enough MSI-X interrupts? Oh well. * This just means we'll go with either a single MSI * vector or fall back to legacy interrupts. diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 6d4ada72dfd0..10b35d82e309 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -1,7 +1,7 @@ /******************************************************************************* Intel 10 Gigabit PCI Express Linux driver - Copyright(c) 1999 - 2013 Intel Corporation. + Copyright(c) 1999 - 2014 Intel Corporation. This program is free software; you can redistribute it and/or modify it under the terms and conditions of the GNU General Public License, @@ -67,7 +67,7 @@ static char ixgbe_default_device_descr[] = #define DRV_VERSION "3.19.1-k" const char ixgbe_driver_version[] = DRV_VERSION; static const char ixgbe_copyright[] = - "Copyright (c) 1999-2013 Intel Corporation."; + "Copyright (c) 1999-2014 Intel Corporation."; static const struct ixgbe_info *ixgbe_info_tbl[] = { [board_82598] = &ixgbe_82598_info, @@ -151,6 +151,8 @@ MODULE_DESCRIPTION("Intel(R) 10 Gigabit PCI Express Network Driver"); MODULE_LICENSE("GPL"); MODULE_VERSION(DRV_VERSION); +static bool ixgbe_check_cfg_remove(struct ixgbe_hw *hw, struct pci_dev *pdev); + static int ixgbe_read_pci_cfg_word_parent(struct ixgbe_adapter *adapter, u32 reg, u16 *value) { @@ -169,6 +171,9 @@ static int ixgbe_read_pci_cfg_word_parent(struct ixgbe_adapter *adapter, return -1; pcie_capability_read_word(parent_dev, reg, value); + if (*value == IXGBE_FAILED_READ_CFG_WORD && + ixgbe_check_cfg_remove(&adapter->hw, parent_dev)) + return -1; return 0; } @@ -313,6 +318,48 @@ void ixgbe_check_remove(struct ixgbe_hw *hw, u32 reg) ixgbe_remove_adapter(hw); } +static bool ixgbe_check_cfg_remove(struct ixgbe_hw *hw, struct pci_dev *pdev) +{ + u16 value; + + pci_read_config_word(pdev, PCI_VENDOR_ID, &value); + if (value == IXGBE_FAILED_READ_CFG_WORD) { + ixgbe_remove_adapter(hw); + return true; + } + return false; +} + +u16 ixgbe_read_pci_cfg_word(struct ixgbe_hw *hw, u32 reg) +{ + struct ixgbe_adapter *adapter = hw->back; + u16 value; + + if (ixgbe_removed(hw->hw_addr)) + return IXGBE_FAILED_READ_CFG_WORD; + pci_read_config_word(adapter->pdev, reg, &value); + if (value == IXGBE_FAILED_READ_CFG_WORD && + ixgbe_check_cfg_remove(hw, adapter->pdev)) + return IXGBE_FAILED_READ_CFG_WORD; + return value; +} + +#ifdef CONFIG_PCI_IOV +static u32 ixgbe_read_pci_cfg_dword(struct ixgbe_hw *hw, u32 reg) +{ + struct ixgbe_adapter *adapter = hw->back; + u32 value; + + if (ixgbe_removed(hw->hw_addr)) + return IXGBE_FAILED_READ_CFG_DWORD; + pci_read_config_dword(adapter->pdev, reg, &value); + if (value == IXGBE_FAILED_READ_CFG_DWORD && + ixgbe_check_cfg_remove(hw, adapter->pdev)) + return IXGBE_FAILED_READ_CFG_DWORD; + return value; +} +#endif /* CONFIG_PCI_IOV */ + static void ixgbe_service_event_complete(struct ixgbe_adapter *adapter) { BUG_ON(!test_bit(__IXGBE_SERVICE_SCHED, &adapter->state)); @@ -2630,9 +2677,12 @@ static irqreturn_t ixgbe_msix_other(int irq, void *data) switch (hw->mac.type) { case ixgbe_mac_82599EB: case ixgbe_mac_X540: - if (eicr & IXGBE_EICR_ECC) - e_info(link, "Received unrecoverable ECC Err, please " - "reboot\n"); + if (eicr & IXGBE_EICR_ECC) { + e_info(link, "Received ECC Err, initiating reset\n"); + adapter->flags2 |= IXGBE_FLAG2_RESET_REQUESTED; + ixgbe_service_event_schedule(adapter); + IXGBE_WRITE_REG(hw, IXGBE_EICR, IXGBE_EICR_ECC); + } /* Handle Flow Director Full threshold interrupt */ if (eicr & IXGBE_EICR_FLOW_DIR) { int reinit_count = 0; @@ -2846,9 +2896,12 @@ static irqreturn_t ixgbe_intr(int irq, void *data) ixgbe_check_sfp_event(adapter, eicr); /* Fall through */ case ixgbe_mac_X540: - if (eicr & IXGBE_EICR_ECC) - e_info(link, "Received unrecoverable ECC err, please " - "reboot\n"); + if (eicr & IXGBE_EICR_ECC) { + e_info(link, "Received ECC Err, initiating reset\n"); + adapter->flags2 |= IXGBE_FLAG2_RESET_REQUESTED; + ixgbe_service_event_schedule(adapter); + IXGBE_WRITE_REG(hw, IXGBE_EICR, IXGBE_EICR_ECC); + } ixgbe_check_overtemp_event(adapter, eicr); break; default: @@ -5502,6 +5555,7 @@ static int ixgbe_resume(struct pci_dev *pdev) struct net_device *netdev = adapter->netdev; u32 err; + adapter->hw.hw_addr = adapter->io_addr; pci_set_power_state(pdev, PCI_D0); pci_restore_state(pdev); /* @@ -6881,7 +6935,7 @@ static inline int ixgbe_maybe_stop_tx(struct ixgbe_ring *tx_ring, u16 size) } static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv) + void *accel_priv, select_queue_fallback_t fallback) { struct ixgbe_fwd_adapter *fwd_adapter = accel_priv; #ifdef IXGBE_FCOE @@ -6907,7 +6961,7 @@ static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb, if (adapter->flags & IXGBE_FLAG_FCOE_ENABLED) break; default: - return __netdev_pick_tx(dev, skb); + return fallback(dev, skb); } f = &adapter->ring_feature[RING_F_FCOE]; @@ -6920,7 +6974,7 @@ static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb, return txq + f->offset; #else - return __netdev_pick_tx(dev, skb); + return fallback(dev, skb); #endif } @@ -7143,7 +7197,9 @@ static int ixgbe_ioctl(struct net_device *netdev, struct ifreq *req, int cmd) switch (cmd) { case SIOCSHWTSTAMP: - return ixgbe_ptp_hwtstamp_ioctl(adapter, req, cmd); + return ixgbe_ptp_set_ts_config(adapter, req); + case SIOCGHWTSTAMP: + return ixgbe_ptp_get_ts_config(adapter, req); default: return mdio_mii_ioctl(&adapter->hw.phy.mdio, if_mii(req), cmd); } @@ -7792,6 +7848,7 @@ int ixgbe_wol_supported(struct ixgbe_adapter *adapter, u16 device_id, case IXGBE_DEV_ID_82599_SFP: /* Only these subdevices could supports WOL */ switch (subdevice_id) { + case IXGBE_SUBDEV_ID_82599_SFP_WOL0: case IXGBE_SUBDEV_ID_82599_560FLR: /* only support first port */ if (hw->bus.func != 0) @@ -8331,6 +8388,7 @@ static pci_ers_result_t ixgbe_io_error_detected(struct pci_dev *pdev, struct net_device *netdev = adapter->netdev; #ifdef CONFIG_PCI_IOV + struct ixgbe_hw *hw = &adapter->hw; struct pci_dev *bdev, *vfdev; u32 dw0, dw1, dw2, dw3; int vf, pos; @@ -8351,10 +8409,12 @@ static pci_ers_result_t ixgbe_io_error_detected(struct pci_dev *pdev, if (!pos) goto skip_bad_vf_detection; - pci_read_config_dword(bdev, pos + PCI_ERR_HEADER_LOG, &dw0); - pci_read_config_dword(bdev, pos + PCI_ERR_HEADER_LOG + 4, &dw1); - pci_read_config_dword(bdev, pos + PCI_ERR_HEADER_LOG + 8, &dw2); - pci_read_config_dword(bdev, pos + PCI_ERR_HEADER_LOG + 12, &dw3); + dw0 = ixgbe_read_pci_cfg_dword(hw, pos + PCI_ERR_HEADER_LOG); + dw1 = ixgbe_read_pci_cfg_dword(hw, pos + PCI_ERR_HEADER_LOG + 4); + dw2 = ixgbe_read_pci_cfg_dword(hw, pos + PCI_ERR_HEADER_LOG + 8); + dw3 = ixgbe_read_pci_cfg_dword(hw, pos + PCI_ERR_HEADER_LOG + 12); + if (ixgbe_removed(hw->hw_addr)) + goto skip_bad_vf_detection; req_id = dw1 >> 16; /* On the 82599 if bit 7 of the requestor ID is set then it's a VF */ @@ -8446,6 +8506,7 @@ static pci_ers_result_t ixgbe_io_slot_reset(struct pci_dev *pdev) e_err(probe, "Cannot re-enable PCI device after reset.\n"); result = PCI_ERS_RESULT_DISCONNECT; } else { + adapter->hw.hw_addr = adapter->io_addr; pci_set_master(pdev); pci_restore_state(pdev); pci_save_state(pdev); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c index 132557c318f8..d2caae4750e0 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c @@ -1,7 +1,7 @@ /******************************************************************************* Intel 10 Gigabit PCI Express Linux driver - Copyright(c) 1999 - 2013 Intel Corporation. + Copyright(c) 1999 - 2014 Intel Corporation. This program is free software; you can redistribute it and/or modify it under the terms and conditions of the GNU General Public License, @@ -98,6 +98,32 @@ s32 ixgbe_identify_phy_generic(struct ixgbe_hw *hw) } /** + * ixgbe_check_reset_blocked - check status of MNG FW veto bit + * @hw: pointer to the hardware structure + * + * This function checks the MMNGC.MNG_VETO bit to see if there are + * any constraints on link from manageability. For MAC's that don't + * have this bit just return false since the link can not be blocked + * via this method. + **/ +s32 ixgbe_check_reset_blocked(struct ixgbe_hw *hw) +{ + u32 mmngc; + + /* If we don't have this bit, it can't be blocking */ + if (hw->mac.type == ixgbe_mac_82598EB) + return false; + + mmngc = IXGBE_READ_REG(hw, IXGBE_MMNGC); + if (mmngc & IXGBE_MMNGC_MNG_VETO) { + hw_dbg(hw, "MNG_VETO bit detected.\n"); + return true; + } + + return false; +} + +/** * ixgbe_get_phy_id - Get the phy type * @hw: pointer to hardware structure * @@ -172,6 +198,10 @@ s32 ixgbe_reset_phy_generic(struct ixgbe_hw *hw) (IXGBE_ERR_OVERTEMP == hw->phy.ops.check_overtemp(hw))) goto out; + /* Blocked by MNG FW so bail */ + if (ixgbe_check_reset_blocked(hw)) + goto out; + /* * Perform soft PHY reset to the PHY_XS. * This will cause a soft reset to the PHY @@ -476,6 +506,10 @@ s32 ixgbe_setup_phy_link_generic(struct ixgbe_hw *hw) autoneg_reg); } + /* Blocked by MNG FW so don't reset PHY */ + if (ixgbe_check_reset_blocked(hw)) + return status; + /* Restart PHY autonegotiation and wait for completion */ hw->phy.ops.read_reg(hw, MDIO_CTRL1, MDIO_MMD_AN, &autoneg_reg); @@ -682,6 +716,10 @@ s32 ixgbe_setup_phy_link_tnx(struct ixgbe_hw *hw) autoneg_reg); } + /* Blocked by MNG FW so don't reset PHY */ + if (ixgbe_check_reset_blocked(hw)) + return status; + /* Restart PHY autonegotiation and wait for completion */ hw->phy.ops.read_reg(hw, MDIO_CTRL1, MDIO_MMD_AN, &autoneg_reg); @@ -759,6 +797,10 @@ s32 ixgbe_reset_phy_nl(struct ixgbe_hw *hw) s32 ret_val = 0; u32 i; + /* Blocked by MNG FW so bail */ + if (ixgbe_check_reset_blocked(hw)) + goto out; + hw->phy.ops.read_reg(hw, MDIO_CTRL1, MDIO_MMD_PHYXS, &phy_data); /* reset the PHY and poll for completion */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h index fffcbdd2bf0e..b4d4323666b8 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h @@ -1,7 +1,7 @@ /******************************************************************************* Intel 10 Gigabit PCI Express Linux driver - Copyright(c) 1999 - 2013 Intel Corporation. + Copyright(c) 1999 - 2014 Intel Corporation. This program is free software; you can redistribute it and/or modify it under the terms and conditions of the GNU General Public License, @@ -131,6 +131,7 @@ s32 ixgbe_setup_phy_link_speed_generic(struct ixgbe_hw *hw, s32 ixgbe_get_copper_link_capabilities_generic(struct ixgbe_hw *hw, ixgbe_link_speed *speed, bool *autoneg); +s32 ixgbe_check_reset_blocked(struct ixgbe_hw *hw); /* PHY specific */ s32 ixgbe_check_phy_link_tnx(struct ixgbe_hw *hw, diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c index 5184e2a1a7d8..9ef730f2916a 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c @@ -576,14 +576,21 @@ void __ixgbe_ptp_rx_hwtstamp(struct ixgbe_q_vector *q_vector, shhwtstamps->hwtstamp = ns_to_ktime(ns); } +int ixgbe_ptp_get_ts_config(struct ixgbe_adapter *adapter, struct ifreq *ifr) +{ + struct hwtstamp_config *config = &adapter->tstamp_config; + + return copy_to_user(ifr->ifr_data, config, + sizeof(*config)) ? -EFAULT : 0; +} + /** - * ixgbe_ptp_hwtstamp_ioctl - control hardware time stamping + * ixgbe_ptp_set_ts_config - control hardware time stamping * @adapter: pointer to adapter struct * @ifreq: ioctl data - * @cmd: particular ioctl requested * * Outgoing time stamping can be enabled and disabled. Play nice and - * disable it when requested, although it shouldn't case any overhead + * disable it when requested, although it shouldn't cause any overhead * when no packet needs it. At most one packet in the queue may be * marked for time stamping, otherwise it would be impossible to tell * for sure to which packet the hardware time stamp belongs. @@ -599,8 +606,7 @@ void __ixgbe_ptp_rx_hwtstamp(struct ixgbe_q_vector *q_vector, * Event mode. This more accurately tells the user what the hardware is going * to do anyways. */ -int ixgbe_ptp_hwtstamp_ioctl(struct ixgbe_adapter *adapter, - struct ifreq *ifr, int cmd) +int ixgbe_ptp_set_ts_config(struct ixgbe_adapter *adapter, struct ifreq *ifr) { struct ixgbe_hw *hw = &adapter->hw; struct hwtstamp_config config; @@ -702,6 +708,10 @@ int ixgbe_ptp_hwtstamp_ioctl(struct ixgbe_adapter *adapter, regval = IXGBE_READ_REG(hw, IXGBE_TXSTMPH); regval = IXGBE_READ_REG(hw, IXGBE_RXSTMPH); + /* save these settings for future reference */ + memcpy(&adapter->tstamp_config, &config, + sizeof(adapter->tstamp_config)); + return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ? -EFAULT : 0; } @@ -809,6 +819,9 @@ void ixgbe_ptp_reset(struct ixgbe_adapter *adapter) IXGBE_WRITE_REG(hw, IXGBE_SYSTIMH, 0x00000000); IXGBE_WRITE_FLUSH(hw); + /* Reset the saved tstamp_config */ + memset(&adapter->tstamp_config, 0, sizeof(adapter->tstamp_config)); + ixgbe_ptp_start_cyclecounter(adapter); spin_lock_irqsave(&adapter->tmreg_lock, flags); @@ -840,7 +853,9 @@ void ixgbe_ptp_init(struct ixgbe_adapter *adapter) switch (adapter->hw.mac.type) { case ixgbe_mac_X540: - snprintf(adapter->ptp_caps.name, 16, "%s", netdev->name); + snprintf(adapter->ptp_caps.name, + sizeof(adapter->ptp_caps.name), + "%s", netdev->name); adapter->ptp_caps.owner = THIS_MODULE; adapter->ptp_caps.max_adj = 250000000; adapter->ptp_caps.n_alarm = 0; @@ -854,7 +869,9 @@ void ixgbe_ptp_init(struct ixgbe_adapter *adapter) adapter->ptp_caps.enable = ixgbe_ptp_enable; break; case ixgbe_mac_82599EB: - snprintf(adapter->ptp_caps.name, 16, "%s", netdev->name); + snprintf(adapter->ptp_caps.name, + sizeof(adapter->ptp_caps.name), + "%s", netdev->name); adapter->ptp_caps.owner = THIS_MODULE; adapter->ptp_caps.max_adj = 250000000; adapter->ptp_caps.n_alarm = 0; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h index 0d39cfc4a3bf..c10382e5aabc 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h @@ -1,7 +1,7 @@ /******************************************************************************* Intel 10 Gigabit PCI Express Linux driver - Copyright(c) 1999 - 2013 Intel Corporation. + Copyright(c) 1999 - 2014 Intel Corporation. This program is free software; you can redistribute it and/or modify it under the terms and conditions of the GNU General Public License, @@ -54,6 +54,7 @@ #define IXGBE_DEV_ID_82599_BACKPLANE_FCOE 0x152a #define IXGBE_DEV_ID_82599_SFP_FCOE 0x1529 #define IXGBE_SUBDEV_ID_82599_SFP 0x11A9 +#define IXGBE_SUBDEV_ID_82599_SFP_WOL0 0x1071 #define IXGBE_SUBDEV_ID_82599_RNDC 0x1F72 #define IXGBE_SUBDEV_ID_82599_560FLR 0x17D0 #define IXGBE_SUBDEV_ID_82599_SP_560FLR 0x211B @@ -1609,6 +1610,9 @@ enum { #define IXGBE_MACC_FS 0x00040000 #define IXGBE_MAC_RX2TX_LPBK 0x00000002 +/* Veto Bit definiton */ +#define IXGBE_MMNGC_MNG_VETO 0x00000001 + /* LINKS Bit Masks */ #define IXGBE_LINKS_KX_AN_COMP 0x80000000 #define IXGBE_LINKS_UP 0x40000000 @@ -1853,8 +1857,19 @@ enum { #define IXGBE_PCI_HEADER_TYPE_MULTIFUNC 0x80 #define IXGBE_PCI_DEVICE_CONTROL2_16ms 0x0005 +#define IXGBE_PCIDEVCTRL2_TIMEO_MASK 0xf +#define IXGBE_PCIDEVCTRL2_16_32ms_def 0x0 +#define IXGBE_PCIDEVCTRL2_50_100us 0x1 +#define IXGBE_PCIDEVCTRL2_1_2ms 0x2 +#define IXGBE_PCIDEVCTRL2_16_32ms 0x5 +#define IXGBE_PCIDEVCTRL2_65_130ms 0x6 +#define IXGBE_PCIDEVCTRL2_260_520ms 0x9 +#define IXGBE_PCIDEVCTRL2_1_2s 0xa +#define IXGBE_PCIDEVCTRL2_4_8s 0xd +#define IXGBE_PCIDEVCTRL2_17_34s 0xe + /* Number of 100 microseconds we wait for PCI Express master disable */ -#define IXGBE_PCI_MASTER_DISABLE_TIMEOUT 800 +#define IXGBE_PCI_MASTER_DISABLE_TIMEOUT 800 /* RAH */ #define IXGBE_RAH_VIND_MASK 0x003C0000 @@ -2858,6 +2873,8 @@ struct ixgbe_mac_operations { s32 (*enable_rx_dma)(struct ixgbe_hw *, u32); s32 (*acquire_swfw_sync)(struct ixgbe_hw *, u16); void (*release_swfw_sync)(struct ixgbe_hw *, u16); + s32 (*prot_autoc_read)(struct ixgbe_hw *, bool *, u32 *); + s32 (*prot_autoc_write)(struct ixgbe_hw *, u32, bool); /* Link */ void (*disable_tx_laser)(struct ixgbe_hw *); @@ -2957,7 +2974,6 @@ struct ixgbe_mac_info { u32 max_tx_queues; u32 max_rx_queues; u32 orig_autoc; - u32 cached_autoc; u32 orig_autoc2; bool orig_link_settings_stored; bool autotry_restart; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c index 24b80a6cfca4..c870f37f15d3 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c @@ -855,6 +855,8 @@ static struct ixgbe_mac_operations mac_ops_X540 = { .get_thermal_sensor_data = NULL, .init_thermal_sensor_thresh = NULL, .mng_fw_enabled = NULL, + .prot_autoc_read = &prot_autoc_read_generic, + .prot_autoc_write = &prot_autoc_write_generic, }; static struct ixgbe_eeprom_operations eeprom_ops_X540 = { diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index 9df28985eba7..6ac5da219150 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -516,7 +516,8 @@ static int ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector, /* Workaround hardware that can't do proper VEPA multicast * source pruning. */ - if ((skb->pkt_type & (PACKET_BROADCAST | PACKET_MULTICAST)) && + if ((skb->pkt_type == PACKET_BROADCAST || + skb->pkt_type == PACKET_MULTICAST) && ether_addr_equal(rx_ring->netdev->dev_addr, eth_hdr(skb)->h_source)) { dev_kfree_skb_irq(skb); @@ -1817,7 +1818,6 @@ void ixgbevf_reset(struct ixgbevf_adapter *adapter) static int ixgbevf_acquire_msix_vectors(struct ixgbevf_adapter *adapter, int vectors) { - int err = 0; int vector_threshold; /* We'll want at least 2 (vector_threshold): @@ -1831,33 +1831,24 @@ static int ixgbevf_acquire_msix_vectors(struct ixgbevf_adapter *adapter, * Right now, we simply care about how many we'll get; we'll * set them up later while requesting irq's. */ - while (vectors >= vector_threshold) { - err = pci_enable_msix(adapter->pdev, adapter->msix_entries, - vectors); - if (!err || err < 0) /* Success or a nasty failure. */ - break; - else /* err == number of vectors we should try again with */ - vectors = err; - } - - if (vectors < vector_threshold) - err = -ENOMEM; + vectors = pci_enable_msix_range(adapter->pdev, adapter->msix_entries, + vector_threshold, vectors); - if (err) { + if (vectors < 0) { dev_err(&adapter->pdev->dev, "Unable to allocate MSI-X interrupts\n"); kfree(adapter->msix_entries); adapter->msix_entries = NULL; - } else { - /* - * Adjust for only the vectors we'll use, which is minimum - * of max_msix_q_vectors + NON_Q_VECTORS, or the number of - * vectors we were allocated. - */ - adapter->num_msix_vectors = vectors; + return vectors; } - return err; + /* Adjust for only the vectors we'll use, which is minimum + * of max_msix_q_vectors + NON_Q_VECTORS, or the number of + * vectors we were allocated. + */ + adapter->num_msix_vectors = vectors; + + return 0; } /** @@ -2787,6 +2778,9 @@ static int ixgbevf_tso(struct ixgbevf_ring *tx_ring, u32 vlan_macip_lens, type_tucmd; u32 mss_l4len_idx, l4len; + if (skb->ip_summed != CHECKSUM_PARTIAL) + return 0; + if (!skb_is_gso(skb)) return 0; @@ -3165,7 +3159,7 @@ static int ixgbevf_xmit_frame(struct sk_buff *skb, struct net_device *netdev) tso = ixgbevf_tso(tx_ring, first, &hdr_len); if (tso < 0) goto out_drop; - else + else if (!tso) ixgbevf_tx_csum(tx_ring, first); ixgbevf_tx_map(tx_ring, first, hdr_len); diff --git a/drivers/net/ethernet/lantiq_etop.c b/drivers/net/ethernet/lantiq_etop.c index 8f9266c64c75..fd4b6aecf6ee 100644 --- a/drivers/net/ethernet/lantiq_etop.c +++ b/drivers/net/ethernet/lantiq_etop.c @@ -619,7 +619,7 @@ ltq_etop_set_multicast_list(struct net_device *dev) static u16 ltq_etop_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv) + void *accel_priv, select_queue_fallback_t fallback) { /* we are currently only using the first queue */ return 0; diff --git a/drivers/net/ethernet/marvell/Kconfig b/drivers/net/ethernet/marvell/Kconfig index 6300fd27f2db..68e6a6613e9a 100644 --- a/drivers/net/ethernet/marvell/Kconfig +++ b/drivers/net/ethernet/marvell/Kconfig @@ -43,12 +43,12 @@ config MVMDIO This driver is used by the MV643XX_ETH and MVNETA drivers. config MVNETA - tristate "Marvell Armada 370/XP network interface support" - depends on MACH_ARMADA_370_XP + tristate "Marvell Armada 370/38x/XP network interface support" + depends on PLAT_ORION select MVMDIO ---help--- This driver supports the network interface units in the - Marvell ARMADA XP and ARMADA 370 SoC family. + Marvell ARMADA XP, ARMADA 370 and ARMADA 38x SoC family. Note that this driver is distinct from the mv643xx_eth driver, which should be used for the older Marvell SoCs diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index f418f4f20f94..12c6a66e54d1 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -2784,7 +2784,6 @@ static int mvneta_probe(struct platform_device *pdev) const char *mac_from; int phy_mode; int err; - int cpu; /* Our multiqueue support is not complete, so for now, only * allow the usage of the first RX queue @@ -2845,18 +2844,12 @@ static int mvneta_probe(struct platform_device *pdev) } /* Alloc per-cpu stats */ - pp->stats = alloc_percpu(struct mvneta_pcpu_stats); + pp->stats = netdev_alloc_pcpu_stats(struct mvneta_pcpu_stats); if (!pp->stats) { err = -ENOMEM; goto err_unmap; } - for_each_possible_cpu(cpu) { - struct mvneta_pcpu_stats *stats; - stats = per_cpu_ptr(pp->stats, cpu); - u64_stats_init(&stats->syncp); - } - dt_mac_addr = of_get_mac_address(dn); if (dt_mac_addr) { mac_from = "device tree"; diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c index 55a37ae11440..2434611d1b4e 100644 --- a/drivers/net/ethernet/marvell/sky2.c +++ b/drivers/net/ethernet/marvell/sky2.c @@ -44,6 +44,8 @@ #include <linux/prefetch.h> #include <linux/debugfs.h> #include <linux/mii.h> +#include <linux/of_device.h> +#include <linux/of_net.h> #include <asm/irq.h> @@ -4748,6 +4750,7 @@ static struct net_device *sky2_init_netdev(struct sky2_hw *hw, unsigned port, { struct sky2_port *sky2; struct net_device *dev = alloc_etherdev(sizeof(*sky2)); + const void *iap; if (!dev) return NULL; @@ -4805,8 +4808,16 @@ static struct net_device *sky2_init_netdev(struct sky2_hw *hw, unsigned port, dev->features |= dev->hw_features; - /* read the mac address */ - memcpy_fromio(dev->dev_addr, hw->regs + B2_MAC_1 + port * 8, ETH_ALEN); + /* try to get mac address in the following order: + * 1) from device tree data + * 2) from internal registers set by bootloader + */ + iap = of_get_mac_address(hw->pdev->dev.of_node); + if (iap) + memcpy(dev->dev_addr, iap, ETH_ALEN); + else + memcpy_fromio(dev->dev_addr, hw->regs + B2_MAC_1 + port * 8, + ETH_ALEN); return dev; } diff --git a/drivers/net/ethernet/mellanox/mlx4/Kconfig b/drivers/net/ethernet/mellanox/mlx4/Kconfig index 563495d8975a..1a6e1887a171 100644 --- a/drivers/net/ethernet/mellanox/mlx4/Kconfig +++ b/drivers/net/ethernet/mellanox/mlx4/Kconfig @@ -3,7 +3,7 @@ # config MLX4_EN - tristate "Mellanox Technologies 10Gbit Ethernet support" + tristate "Mellanox Technologies 1/10/40Gbit Ethernet support" depends on PCI select MLX4_CORE select PTP_1588_CLOCK diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c index 0d02fba94536..2b0b45ece14b 100644 --- a/drivers/net/ethernet/mellanox/mlx4/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c @@ -2289,6 +2289,30 @@ int mlx4_set_vf_vlan(struct mlx4_dev *dev, int port, int vf, u16 vlan, u8 qos) } EXPORT_SYMBOL_GPL(mlx4_set_vf_vlan); + /* mlx4_get_slave_default_vlan - + * return true if VST ( default vlan) + * if VST, will return vlan & qos (if not NULL) + */ +bool mlx4_get_slave_default_vlan(struct mlx4_dev *dev, int port, int slave, + u16 *vlan, u8 *qos) +{ + struct mlx4_vport_oper_state *vp_oper; + struct mlx4_priv *priv; + + priv = mlx4_priv(dev); + vp_oper = &priv->mfunc.master.vf_oper[slave].vport[port]; + + if (MLX4_VGT != vp_oper->state.default_vlan) { + if (vlan) + *vlan = vp_oper->state.default_vlan; + if (qos) + *qos = vp_oper->state.default_qos; + return true; + } + return false; +} +EXPORT_SYMBOL_GPL(mlx4_get_slave_default_vlan); + int mlx4_set_vf_spoofchk(struct mlx4_dev *dev, int port, int vf, bool setting) { struct mlx4_priv *priv = mlx4_priv(dev); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c b/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c index b4881b686159..c95ca252187c 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c @@ -62,7 +62,7 @@ static int mlx4_en_ets_validate(struct mlx4_en_priv *priv, struct ieee_ets *ets) int has_ets_tc = 0; for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) { - if (ets->prio_tc[i] > MLX4_EN_NUM_UP) { + if (ets->prio_tc[i] >= MLX4_EN_NUM_UP) { en_err(priv, "Bad priority in UP <=> TC mapping. TC: %d, UP: %d\n", i, ets->prio_tc[i]); return -EINVAL; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_main.c b/drivers/net/ethernet/mellanox/mlx4/en_main.c index d357bf5a4686..0c59d4fe7e3a 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_main.c @@ -72,6 +72,12 @@ MLX4_EN_PARM_INT(pfctx, 0, "Priority based Flow Control policy on TX[7:0]." MLX4_EN_PARM_INT(pfcrx, 0, "Priority based Flow Control policy on RX[7:0]." " Per priority bit mask"); +MLX4_EN_PARM_INT(inline_thold, MAX_INLINE, + "Threshold for using inline data (range: 17-104, default: 104)"); + +#define MAX_PFC_TX 0xff +#define MAX_PFC_RX 0xff + int en_print(const char *level, const struct mlx4_en_priv *priv, const char *format, ...) { @@ -140,6 +146,7 @@ static int mlx4_en_get_profile(struct mlx4_en_dev *mdev) params->prof[i].tx_ring_num = params->num_tx_rings_p_up * MLX4_EN_NUM_UP; params->prof[i].rss_rings = 0; + params->prof[i].inline_thold = inline_thold; } return 0; @@ -274,19 +281,8 @@ static void *mlx4_en_add(struct mlx4_dev *dev) if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_TS) mlx4_en_init_timestamp(mdev); - mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_ETH) { - if (!dev->caps.comp_pool) { - mdev->profile.prof[i].rx_ring_num = - rounddown_pow_of_two(max_t(int, MIN_RX_RINGS, - min_t(int, - dev->caps.num_comp_vectors, - DEF_RX_RINGS))); - } else { - mdev->profile.prof[i].rx_ring_num = rounddown_pow_of_two( - min_t(int, dev->caps.comp_pool/ - dev->caps.num_ports - 1 , MAX_MSIX_P_PORT - 1)); - } - } + /* Set default number of RX rings*/ + mlx4_en_set_num_rx_rings(mdev); /* Create our own workqueue for reset/multicast tasks * Note: we cannot use the shared workqueue because of deadlocks caused @@ -336,8 +332,31 @@ static struct mlx4_interface mlx4_en_interface = { .protocol = MLX4_PROT_ETH, }; +static void mlx4_en_verify_params(void) +{ + if (pfctx > MAX_PFC_TX) { + pr_warn("mlx4_en: WARNING: illegal module parameter pfctx 0x%x - should be in range 0-0x%x, will be changed to default (0)\n", + pfctx, MAX_PFC_TX); + pfctx = 0; + } + + if (pfcrx > MAX_PFC_RX) { + pr_warn("mlx4_en: WARNING: illegal module parameter pfcrx 0x%x - should be in range 0-0x%x, will be changed to default (0)\n", + pfcrx, MAX_PFC_RX); + pfcrx = 0; + } + + if (inline_thold < MIN_PKT_LEN || inline_thold > MAX_INLINE) { + pr_warn("mlx4_en: WARNING: illegal module parameter inline_thold %d - should be in range %d-%d, will be changed to default (%d)\n", + inline_thold, MIN_PKT_LEN, MAX_INLINE, MAX_INLINE); + inline_thold = MAX_INLINE; + } +} + static int __init mlx4_en_init(void) { + mlx4_en_verify_params(); + return mlx4_register_interface(&mlx4_en_interface); } diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index fad45316200a..3db594614fd3 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -603,7 +603,7 @@ static int mlx4_en_get_qp(struct mlx4_en_priv *priv) int err = 0; u64 reg_id; int *qpn = &priv->base_qpn; - u64 mac = mlx4_en_mac_to_u64(priv->dev->dev_addr); + u64 mac = mlx4_mac_to_u64(priv->dev->dev_addr); en_dbg(DRV, priv, "Registering MAC: %pM for adding\n", priv->dev->dev_addr); @@ -672,7 +672,7 @@ static void mlx4_en_put_qp(struct mlx4_en_priv *priv) u64 mac; if (dev->caps.steering_mode == MLX4_STEERING_MODE_A0) { - mac = mlx4_en_mac_to_u64(priv->dev->dev_addr); + mac = mlx4_mac_to_u64(priv->dev->dev_addr); en_dbg(DRV, priv, "Registering MAC: %pM for deleting\n", priv->dev->dev_addr); mlx4_unregister_mac(dev, priv->port, mac); @@ -685,7 +685,7 @@ static void mlx4_en_put_qp(struct mlx4_en_priv *priv) for (i = 0; i < MLX4_EN_MAC_HASH_SIZE; ++i) { bucket = &priv->mac_hash[i]; hlist_for_each_entry_safe(entry, tmp, bucket, hlist) { - mac = mlx4_en_mac_to_u64(entry->mac); + mac = mlx4_mac_to_u64(entry->mac); en_dbg(DRV, priv, "Registering MAC: %pM for deleting\n", entry->mac); mlx4_en_uc_steer_release(priv, entry->mac, @@ -715,14 +715,14 @@ static int mlx4_en_replace_mac(struct mlx4_en_priv *priv, int qpn, struct mlx4_en_dev *mdev = priv->mdev; struct mlx4_dev *dev = mdev->dev; int err = 0; - u64 new_mac_u64 = mlx4_en_mac_to_u64(new_mac); + u64 new_mac_u64 = mlx4_mac_to_u64(new_mac); if (dev->caps.steering_mode != MLX4_STEERING_MODE_A0) { struct hlist_head *bucket; unsigned int mac_hash; struct mlx4_mac_entry *entry; struct hlist_node *tmp; - u64 prev_mac_u64 = mlx4_en_mac_to_u64(prev_mac); + u64 prev_mac_u64 = mlx4_mac_to_u64(prev_mac); bucket = &priv->mac_hash[prev_mac[MLX4_EN_MAC_HASH_IDX]]; hlist_for_each_entry_safe(entry, tmp, bucket, hlist) { @@ -751,18 +751,6 @@ static int mlx4_en_replace_mac(struct mlx4_en_priv *priv, int qpn, return __mlx4_replace_mac(dev, priv->port, qpn, new_mac_u64); } -u64 mlx4_en_mac_to_u64(u8 *addr) -{ - u64 mac = 0; - int i; - - for (i = 0; i < ETH_ALEN; i++) { - mac <<= 8; - mac |= addr[i]; - } - return mac; -} - static int mlx4_en_do_set_mac(struct mlx4_en_priv *priv) { int err = 0; @@ -1081,7 +1069,7 @@ static void mlx4_en_do_multicast(struct mlx4_en_priv *priv, mlx4_en_cache_mclist(dev); netif_addr_unlock_bh(dev); list_for_each_entry(mclist, &priv->mc_list, list) { - mcast_addr = mlx4_en_mac_to_u64(mclist->addr); + mcast_addr = mlx4_mac_to_u64(mclist->addr); mlx4_SET_MCAST_FLTR(mdev->dev, priv->port, mcast_addr, 0, MLX4_MCAST_CONFIG); } @@ -1173,7 +1161,7 @@ static void mlx4_en_do_uc_filter(struct mlx4_en_priv *priv, found = true; if (!found) { - mac = mlx4_en_mac_to_u64(entry->mac); + mac = mlx4_mac_to_u64(entry->mac); mlx4_en_uc_steer_release(priv, entry->mac, priv->base_qpn, entry->reg_id); @@ -1216,7 +1204,7 @@ static void mlx4_en_do_uc_filter(struct mlx4_en_priv *priv, priv->flags |= MLX4_EN_FLAG_FORCE_PROMISC; break; } - mac = mlx4_en_mac_to_u64(ha->addr); + mac = mlx4_mac_to_u64(ha->addr); memcpy(entry->mac, ha->addr, ETH_ALEN); err = mlx4_register_mac(mdev->dev, priv->port, mac); if (err < 0) { @@ -2206,7 +2194,7 @@ static int mlx4_en_set_vf_mac(struct net_device *dev, int queue, u8 *mac) { struct mlx4_en_priv *en_priv = netdev_priv(dev); struct mlx4_en_dev *mdev = en_priv->mdev; - u64 mac_u64 = mlx4_en_mac_to_u64(mac); + u64 mac_u64 = mlx4_mac_to_u64(mac); if (!is_valid_ether_addr(mac)) return -EINVAL; @@ -2341,7 +2329,7 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, netif_set_real_num_rx_queues(dev, prof->rx_ring_num); SET_NETDEV_DEV(dev, &mdev->dev->pdev->dev); - dev->dev_id = port - 1; + dev->dev_port = port - 1; /* * Initialize driver private data @@ -2407,7 +2395,7 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, if (mlx4_is_slave(priv->mdev->dev)) { eth_hw_addr_random(dev); en_warn(priv, "Assigned random MAC address %pM\n", dev->dev_addr); - mac_u64 = mlx4_en_mac_to_u64(dev->dev_addr); + mac_u64 = mlx4_mac_to_u64(dev->dev_addr); mdev->dev->caps.def_mac[priv->port] = mac_u64; } else { en_err(priv, "Port: %d, invalid mac burned: %pM, quiting\n", diff --git a/drivers/net/ethernet/mellanox/mlx4/en_port.c b/drivers/net/ethernet/mellanox/mlx4/en_port.c index dae1a1f4ae55..c2cfb05e7290 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_port.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_port.c @@ -148,10 +148,16 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset) stats->tx_packets = 0; stats->tx_bytes = 0; priv->port_stats.tx_chksum_offload = 0; + priv->port_stats.queue_stopped = 0; + priv->port_stats.wake_queue = 0; + for (i = 0; i < priv->tx_ring_num; i++) { stats->tx_packets += priv->tx_ring[i]->packets; stats->tx_bytes += priv->tx_ring[i]->bytes; priv->port_stats.tx_chksum_offload += priv->tx_ring[i]->tx_csum; + priv->port_stats.queue_stopped += + priv->tx_ring[i]->queue_stopped; + priv->port_stats.wake_queue += priv->tx_ring[i]->wake_queue; } stats->rx_errors = be64_to_cpu(mlx4_en_stats->PCS) + diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index 890922c1c8ee..8afb72ec957d 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -318,6 +318,31 @@ static void mlx4_en_free_rx_buf(struct mlx4_en_priv *priv, } } +void mlx4_en_set_num_rx_rings(struct mlx4_en_dev *mdev) +{ + int i; + int num_of_eqs; + int num_rx_rings; + struct mlx4_dev *dev = mdev->dev; + + mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_ETH) { + if (!dev->caps.comp_pool) + num_of_eqs = max_t(int, MIN_RX_RINGS, + min_t(int, + dev->caps.num_comp_vectors, + DEF_RX_RINGS)); + else + num_of_eqs = min_t(int, MAX_MSIX_P_PORT, + dev->caps.comp_pool/ + dev->caps.num_ports) - 1; + + num_rx_rings = min_t(int, num_of_eqs, + netif_get_num_default_rss_queues()); + mdev->profile.prof[i].rx_ring_num = + rounddown_pow_of_two(num_rx_rings); + } +} + int mlx4_en_create_rx_ring(struct mlx4_en_priv *priv, struct mlx4_en_rx_ring **pring, u32 size, u16 stride, int node) diff --git a/drivers/net/ethernet/mellanox/mlx4/en_selftest.c b/drivers/net/ethernet/mellanox/mlx4/en_selftest.c index c11d063473e5..03e5f6ac67e7 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_selftest.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_selftest.c @@ -129,8 +129,10 @@ static int mlx4_en_test_speed(struct mlx4_en_priv *priv) if (mlx4_en_QUERY_PORT(priv->mdev, priv->port)) return -ENOMEM; - /* The device currently only supports 10G speed */ - if (priv->port_state.link_speed != SPEED_10000) + /* The device supports 1G, 10G and 40G speeds */ + if (priv->port_state.link_speed != 1000 && + priv->port_state.link_speed != 10000 && + priv->port_state.link_speed != 40000) return priv->port_state.link_speed; return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index 8e8a7eb43a2c..dd1f6d346459 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -44,16 +44,6 @@ #include "mlx4_en.h" -enum { - MAX_INLINE = 104, /* 128 - 16 - 4 - 4 */ - MAX_BF = 256, -}; - -static int inline_thold __read_mostly = MAX_INLINE; - -module_param_named(inline_thold, inline_thold, int, 0444); -MODULE_PARM_DESC(inline_thold, "threshold for using inline data"); - int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv, struct mlx4_en_tx_ring **pring, int qpn, u32 size, u16 stride, int node, int queue_index) @@ -75,8 +65,7 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv, ring->size = size; ring->size_mask = size - 1; ring->stride = stride; - - inline_thold = min(inline_thold, MAX_INLINE); + ring->inline_thold = priv->prof->inline_thold; tmp = size * sizeof(struct mlx4_en_tx_info); ring->tx_info = vmalloc_node(tmp, node); @@ -325,7 +314,7 @@ static u32 mlx4_en_free_tx_desc(struct mlx4_en_priv *priv, } } } - dev_kfree_skb(skb); + dev_kfree_skb_any(skb); return tx_info->nr_txbb; } @@ -456,7 +445,7 @@ static int mlx4_en_process_tx_cq(struct net_device *dev, */ if (netif_tx_queue_stopped(ring->tx_queue) && txbbs_skipped > 0) { netif_tx_wake_queue(ring->tx_queue); - priv->port_stats.wake_queue++; + ring->wake_queue++; } return done; } @@ -520,7 +509,7 @@ static struct mlx4_en_tx_desc *mlx4_en_bounce_to_desc(struct mlx4_en_priv *priv, return ring->buf + index * TXBB_SIZE; } -static int is_inline(struct sk_buff *skb, void **pfrag) +static int is_inline(int inline_thold, struct sk_buff *skb, void **pfrag) { void *ptr; @@ -580,7 +569,7 @@ static int get_real_size(struct sk_buff *skb, struct net_device *dev, } } else { *lso_header_size = 0; - if (!is_inline(skb, NULL)) + if (!is_inline(priv->prof->inline_thold, skb, NULL)) real_size = CTRL_SIZE + (skb_shinfo(skb)->nr_frags + 1) * DS_SIZE; else real_size = inline_size(skb); @@ -596,7 +585,13 @@ static void build_inline_wqe(struct mlx4_en_tx_desc *tx_desc, struct sk_buff *sk int spc = MLX4_INLINE_ALIGN - CTRL_SIZE - sizeof *inl; if (skb->len <= spc) { - inl->byte_count = cpu_to_be32(1 << 31 | skb->len); + if (likely(skb->len >= MIN_PKT_LEN)) { + inl->byte_count = cpu_to_be32(1 << 31 | skb->len); + } else { + inl->byte_count = cpu_to_be32(1 << 31 | MIN_PKT_LEN); + memset(((void *)(inl + 1)) + skb->len, 0, + MIN_PKT_LEN - skb->len); + } skb_copy_from_linear_data(skb, inl + 1, skb_headlen(skb)); if (skb_shinfo(skb)->nr_frags) memcpy(((void *)(inl + 1)) + skb_headlen(skb), fragptr, @@ -629,7 +624,7 @@ static void build_inline_wqe(struct mlx4_en_tx_desc *tx_desc, struct sk_buff *sk } u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv) + void *accel_priv, select_queue_fallback_t fallback) { struct mlx4_en_priv *priv = netdev_priv(dev); u16 rings_p_up = priv->num_tx_rings_p_up; @@ -641,7 +636,7 @@ u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb, if (vlan_tx_tag_present(skb)) up = vlan_tx_tag_get(skb) >> VLAN_PRIO_SHIFT; - return __netdev_pick_tx(dev, skb) % rings_p_up + up * rings_p_up; + return fallback(dev, skb) % rings_p_up + up * rings_p_up; } static void mlx4_bf_copy(void __iomem *dst, unsigned long *src, unsigned bytecnt) @@ -696,7 +691,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev) ring->size - HEADROOM - MAX_DESC_TXBBS)) { /* every full Tx ring stops queue */ netif_tx_stop_queue(ring->tx_queue); - priv->port_stats.queue_stopped++; + ring->queue_stopped++; /* If queue was emptied after the if, and before the * stop_queue - need to wake the queue, or else it will remain @@ -709,7 +704,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev) if (unlikely(((int)(ring->prod - ring->cons)) <= ring->size - HEADROOM - MAX_DESC_TXBBS)) { netif_tx_wake_queue(ring->tx_queue); - priv->port_stats.wake_queue++; + ring->wake_queue++; } else { return NETDEV_TX_BUSY; } @@ -747,11 +742,11 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev) tx_info->data_offset = (void *)data - (void *)tx_desc; tx_info->linear = (lso_header_size < skb_headlen(skb) && - !is_inline(skb, NULL)) ? 1 : 0; + !is_inline(ring->inline_thold, skb, NULL)) ? 1 : 0; data += skb_shinfo(skb)->nr_frags + tx_info->linear - 1; - if (is_inline(skb, &fragptr)) { + if (is_inline(ring->inline_thold, skb, &fragptr)) { tx_info->inl = 1; } else { /* Map fragments */ @@ -881,7 +876,8 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev) skb_tx_timestamp(skb); if (ring->bf_enabled && desc_size <= MAX_BF && !bounce && !vlan_tx_tag_present(skb)) { - *(__be32 *) (&tx_desc->ctrl.vlan_tag) |= cpu_to_be32(ring->doorbell_qpn); + tx_desc->ctrl.bf_qpn |= cpu_to_be32(ring->doorbell_qpn); + op_own |= htonl((bf_index & 0xffff) << 8); /* Ensure new descirptor hits memory * before setting ownership of this descriptor to HW */ diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c index 91b69ff4b4a2..6e1ee2170a39 100644 --- a/drivers/net/ethernet/mellanox/mlx4/fw.c +++ b/drivers/net/ethernet/mellanox/mlx4/fw.c @@ -934,7 +934,10 @@ int mlx4_QUERY_PORT_wrapper(struct mlx4_dev *dev, int slave, MLX4_PUT(outbox->buf, port_type, QUERY_PORT_SUPPORTED_TYPE_OFFSET); - short_field = 1; /* slave max gids */ + if (dev->caps.port_type[vhcr->in_modifier] == MLX4_PORT_TYPE_ETH) + short_field = mlx4_get_slave_num_gids(dev, slave); + else + short_field = 1; /* slave max gids */ MLX4_PUT(outbox->buf, short_field, QUERY_PORT_CUR_MAX_GID_OFFSET); @@ -1890,7 +1893,8 @@ void mlx4_opreq_action(struct work_struct *work) err = EINVAL; break; } - err = mlx4_cmd(dev, 0, ((u32) err | cpu_to_be32(token) << 16), + err = mlx4_cmd(dev, 0, ((u32) err | + (__force u32)cpu_to_be32(token) << 16), 1, MLX4_CMD_GET_OP_REQ, MLX4_CMD_TIME_CLASS_A, MLX4_CMD_NATIVE); if (err) { diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index d711158b0d4b..4c441aa83016 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -41,7 +41,6 @@ #include <linux/slab.h> #include <linux/io-mapping.h> #include <linux/delay.h> -#include <linux/netdevice.h> #include <linux/kmod.h> #include <linux/mlx4/device.h> @@ -1463,7 +1462,11 @@ static void mlx4_parav_master_pf_caps(struct mlx4_dev *dev) int i; for (i = 1; i <= dev->caps.num_ports; i++) { - dev->caps.gid_table_len[i] = 1; + if (dev->caps.port_type[i] == MLX4_PORT_TYPE_ETH) + dev->caps.gid_table_len[i] = + mlx4_get_slave_num_gids(dev, 0); + else + dev->caps.gid_table_len[i] = 1; dev->caps.pkey_table_len[i] = dev->phys_caps.pkey_phys_table_len[i] - 1; } @@ -1974,9 +1977,8 @@ static void mlx4_enable_msi_x(struct mlx4_dev *dev) struct mlx4_priv *priv = mlx4_priv(dev); struct msix_entry *entries; int nreq = min_t(int, dev->caps.num_ports * - min_t(int, netif_get_num_default_rss_queues() + 1, + min_t(int, num_online_cpus() + 1, MAX_MSIX_P_PORT) + MSIX_LEGACY_SZ, MAX_MSIX); - int err; int i; if (msi_x) { @@ -1990,23 +1992,13 @@ static void mlx4_enable_msi_x(struct mlx4_dev *dev) for (i = 0; i < nreq; ++i) entries[i].entry = i; - retry: - err = pci_enable_msix(dev->pdev, entries, nreq); - if (err) { - /* Try again if at least 2 vectors are available */ - if (err > 1) { - mlx4_info(dev, "Requested %d vectors, " - "but only %d MSI-X vectors available, " - "trying again\n", nreq, err); - nreq = err; - goto retry; - } + nreq = pci_enable_msix_range(dev->pdev, entries, 2, nreq); + + if (nreq < 0) { kfree(entries); goto no_msi; - } - - if (nreq < - MSIX_LEGACY_SZ + dev->caps.num_ports * MIN_MSIX_P_PORT) { + } else if (nreq < MSIX_LEGACY_SZ + + dev->caps.num_ports * MIN_MSIX_P_PORT) { /*Working in legacy mode , all EQ's shared*/ dev->caps.comp_pool = 0; dev->caps.num_comp_vectors = nreq - 1; diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h index 6b65f7795215..6ba38c98c492 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h @@ -51,8 +51,8 @@ #define DRV_NAME "mlx4_core" #define PFX DRV_NAME ": " -#define DRV_VERSION "1.1" -#define DRV_RELDATE "Dec, 2011" +#define DRV_VERSION "2.2-1" +#define DRV_RELDATE "Feb, 2014" #define MLX4_FS_UDP_UC_EN (1 << 1) #define MLX4_FS_TCP_UC_EN (1 << 2) @@ -788,6 +788,10 @@ enum { MLX4_USE_RR = 1, }; +struct mlx4_roce_gid_entry { + u8 raw[16]; +}; + struct mlx4_priv { struct mlx4_dev dev; @@ -834,6 +838,7 @@ struct mlx4_priv { int fs_hash_mode; u8 virt2phys_pkey[MLX4_MFUNC_MAX][MLX4_MAX_PORTS][MLX4_MAX_PORT_PKEYS]; __be64 slave_node_guids[MLX4_MFUNC_MAX]; + struct mlx4_roce_gid_entry roce_gids[MLX4_MAX_PORTS][MLX4_ROCE_MAX_GIDS]; atomic_t opreq_count; struct work_struct opreq_task; @@ -1282,4 +1287,7 @@ void mlx4_vf_immed_vlan_work_handler(struct work_struct *_work); void mlx4_init_quotas(struct mlx4_dev *dev); +int mlx4_get_slave_num_gids(struct mlx4_dev *dev, int slave); +int mlx4_get_base_gid_ix(struct mlx4_dev *dev, int slave); + #endif /* MLX4_H */ diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index 3af04c3f42ea..69e1f36858e0 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -57,8 +57,8 @@ #include "en_port.h" #define DRV_NAME "mlx4_en" -#define DRV_VERSION "2.0" -#define DRV_RELDATE "Dec 2011" +#define DRV_VERSION "2.2-1" +#define DRV_RELDATE "Feb 2014" #define MLX4_EN_MSG_LEVEL (NETIF_MSG_LINK | NETIF_MSG_IFDOWN) @@ -187,6 +187,13 @@ enum { #define GET_AVG_PERF_COUNTER(cnt) (0) #endif /* MLX4_EN_PERF_STAT */ +/* Constants for TX flow */ +enum { + MAX_INLINE = 104, /* 128 - 16 - 4 - 4 */ + MAX_BF = 256, + MIN_PKT_LEN = 17, +}; + /* * Configurables */ @@ -267,10 +274,13 @@ struct mlx4_en_tx_ring { unsigned long bytes; unsigned long packets; unsigned long tx_csum; + unsigned long queue_stopped; + unsigned long wake_queue; struct mlx4_bf bf; bool bf_enabled; struct netdev_queue *tx_queue; int hwtstamp_tx_type; + int inline_thold; }; struct mlx4_en_rx_desc { @@ -346,6 +356,7 @@ struct mlx4_en_port_profile { u8 tx_pause; u8 tx_ppp; int rss_rings; + int inline_thold; }; struct mlx4_en_profile { @@ -723,7 +734,7 @@ int mlx4_en_arm_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq); void mlx4_en_tx_irq(struct mlx4_cq *mcq); u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv); + void *accel_priv, select_queue_fallback_t fallback); netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev); int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv, @@ -737,7 +748,7 @@ int mlx4_en_activate_tx_ring(struct mlx4_en_priv *priv, int cq, int user_prio); void mlx4_en_deactivate_tx_ring(struct mlx4_en_priv *priv, struct mlx4_en_tx_ring *ring); - +void mlx4_en_set_num_rx_rings(struct mlx4_en_dev *mdev); int mlx4_en_create_rx_ring(struct mlx4_en_priv *priv, struct mlx4_en_rx_ring **pring, u32 size, u16 stride, int node); @@ -786,7 +797,6 @@ void mlx4_en_cleanup_filters(struct mlx4_en_priv *priv); #define MLX4_EN_NUM_SELF_TEST 5 void mlx4_en_ex_selftest(struct net_device *dev, u32 *flags, u64 *buf); -u64 mlx4_en_mac_to_u64(u8 *addr); void mlx4_en_ptp_overflow_check(struct mlx4_en_dev *mdev); /* diff --git a/drivers/net/ethernet/mellanox/mlx4/port.c b/drivers/net/ethernet/mellanox/mlx4/port.c index a58bcbf1b806..ece328166e94 100644 --- a/drivers/net/ethernet/mellanox/mlx4/port.c +++ b/drivers/net/ethernet/mellanox/mlx4/port.c @@ -505,6 +505,32 @@ int mlx4_get_port_ib_caps(struct mlx4_dev *dev, u8 port, __be32 *caps) mlx4_free_cmd_mailbox(dev, outmailbox); return err; } +static struct mlx4_roce_gid_entry zgid_entry; + +int mlx4_get_slave_num_gids(struct mlx4_dev *dev, int slave) +{ + if (slave == 0) + return MLX4_ROCE_PF_GIDS; + if (slave <= ((MLX4_ROCE_MAX_GIDS - MLX4_ROCE_PF_GIDS) % dev->num_vfs)) + return ((MLX4_ROCE_MAX_GIDS - MLX4_ROCE_PF_GIDS) / dev->num_vfs) + 1; + return (MLX4_ROCE_MAX_GIDS - MLX4_ROCE_PF_GIDS) / dev->num_vfs; +} + +int mlx4_get_base_gid_ix(struct mlx4_dev *dev, int slave) +{ + int gids; + int vfs; + + gids = MLX4_ROCE_MAX_GIDS - MLX4_ROCE_PF_GIDS; + vfs = dev->num_vfs; + + if (slave == 0) + return 0; + if (slave <= gids % vfs) + return MLX4_ROCE_PF_GIDS + ((gids / vfs) + 1) * (slave - 1); + + return MLX4_ROCE_PF_GIDS + (gids % vfs) + ((gids / vfs) * (slave - 1)); +} static int mlx4_common_set_port(struct mlx4_dev *dev, int slave, u32 in_mod, u8 op_mod, struct mlx4_cmd_mailbox *inbox) @@ -515,14 +541,18 @@ static int mlx4_common_set_port(struct mlx4_dev *dev, int slave, u32 in_mod, struct mlx4_slave_state *slave_st = &master->slave_state[slave]; struct mlx4_set_port_rqp_calc_context *qpn_context; struct mlx4_set_port_general_context *gen_context; + struct mlx4_roce_gid_entry *gid_entry_tbl, *gid_entry_mbox, *gid_entry_mb1; int reset_qkey_viols; int port; int is_eth; + int num_gids; + int base; u32 in_modifier; u32 promisc; u16 mtu, prev_mtu; int err; - int i; + int i, j; + int offset; __be32 agg_cap_mask; __be32 slave_cap_mask; __be32 new_cap_mask; @@ -535,7 +565,8 @@ static int mlx4_common_set_port(struct mlx4_dev *dev, int slave, u32 in_mod, /* Slaves cannot perform SET_PORT operations except changing MTU */ if (is_eth) { if (slave != dev->caps.function && - in_modifier != MLX4_SET_PORT_GENERAL) { + in_modifier != MLX4_SET_PORT_GENERAL && + in_modifier != MLX4_SET_PORT_GID_TABLE) { mlx4_warn(dev, "denying SET_PORT for slave:%d\n", slave); return -EINVAL; @@ -581,6 +612,67 @@ static int mlx4_common_set_port(struct mlx4_dev *dev, int slave, u32 in_mod, gen_context->mtu = cpu_to_be16(master->max_mtu[port]); break; + case MLX4_SET_PORT_GID_TABLE: + /* change to MULTIPLE entries: number of guest's gids + * need a FOR-loop here over number of gids the guest has. + * 1. Check no duplicates in gids passed by slave + */ + num_gids = mlx4_get_slave_num_gids(dev, slave); + base = mlx4_get_base_gid_ix(dev, slave); + gid_entry_mbox = (struct mlx4_roce_gid_entry *)(inbox->buf); + for (i = 0; i < num_gids; gid_entry_mbox++, i++) { + if (!memcmp(gid_entry_mbox->raw, zgid_entry.raw, + sizeof(zgid_entry))) + continue; + gid_entry_mb1 = gid_entry_mbox + 1; + for (j = i + 1; j < num_gids; gid_entry_mb1++, j++) { + if (!memcmp(gid_entry_mb1->raw, + zgid_entry.raw, sizeof(zgid_entry))) + continue; + if (!memcmp(gid_entry_mb1->raw, gid_entry_mbox->raw, + sizeof(gid_entry_mbox->raw))) { + /* found duplicate */ + return -EINVAL; + } + } + } + + /* 2. Check that do not have duplicates in OTHER + * entries in the port GID table + */ + for (i = 0; i < MLX4_ROCE_MAX_GIDS; i++) { + if (i >= base && i < base + num_gids) + continue; /* don't compare to slave's current gids */ + gid_entry_tbl = &priv->roce_gids[port - 1][i]; + if (!memcmp(gid_entry_tbl->raw, zgid_entry.raw, sizeof(zgid_entry))) + continue; + gid_entry_mbox = (struct mlx4_roce_gid_entry *)(inbox->buf); + for (j = 0; j < num_gids; gid_entry_mbox++, j++) { + if (!memcmp(gid_entry_mbox->raw, zgid_entry.raw, + sizeof(zgid_entry))) + continue; + if (!memcmp(gid_entry_mbox->raw, gid_entry_tbl->raw, + sizeof(gid_entry_tbl->raw))) { + /* found duplicate */ + mlx4_warn(dev, "requested gid entry for slave:%d " + "is a duplicate of gid at index %d\n", + slave, i); + return -EINVAL; + } + } + } + + /* insert slave GIDs with memcpy, starting at slave's base index */ + gid_entry_mbox = (struct mlx4_roce_gid_entry *)(inbox->buf); + for (i = 0, offset = base; i < num_gids; gid_entry_mbox++, offset++, i++) + memcpy(priv->roce_gids[port - 1][offset].raw, gid_entry_mbox->raw, 16); + + /* Now, copy roce port gids table to current mailbox for passing to FW */ + gid_entry_mbox = (struct mlx4_roce_gid_entry *)(inbox->buf); + for (i = 0; i < MLX4_ROCE_MAX_GIDS; gid_entry_mbox++, i++) + memcpy(gid_entry_mbox->raw, priv->roce_gids[port - 1][i].raw, 16); + + break; } return mlx4_cmd(dev, inbox->dma, in_mod, op_mod, MLX4_CMD_SET_PORT, MLX4_CMD_TIME_CLASS_B, @@ -927,3 +1019,51 @@ void mlx4_set_stats_bitmap(struct mlx4_dev *dev, u64 *stats_bitmap) *stats_bitmap |= MLX4_STATS_ERROR_COUNTERS_MASK; } EXPORT_SYMBOL(mlx4_set_stats_bitmap); + +int mlx4_get_slave_from_roce_gid(struct mlx4_dev *dev, int port, u8 *gid, + int *slave_id) +{ + struct mlx4_priv *priv = mlx4_priv(dev); + int i, found_ix = -1; + int vf_gids = MLX4_ROCE_MAX_GIDS - MLX4_ROCE_PF_GIDS; + + if (!mlx4_is_mfunc(dev)) + return -EINVAL; + + for (i = 0; i < MLX4_ROCE_MAX_GIDS; i++) { + if (!memcmp(priv->roce_gids[port - 1][i].raw, gid, 16)) { + found_ix = i; + break; + } + } + + if (found_ix >= 0) { + if (found_ix < MLX4_ROCE_PF_GIDS) + *slave_id = 0; + else if (found_ix < MLX4_ROCE_PF_GIDS + (vf_gids % dev->num_vfs) * + (vf_gids / dev->num_vfs + 1)) + *slave_id = ((found_ix - MLX4_ROCE_PF_GIDS) / + (vf_gids / dev->num_vfs + 1)) + 1; + else + *slave_id = + ((found_ix - MLX4_ROCE_PF_GIDS - + ((vf_gids % dev->num_vfs) * ((vf_gids / dev->num_vfs + 1)))) / + (vf_gids / dev->num_vfs)) + vf_gids % dev->num_vfs + 1; + } + + return (found_ix >= 0) ? 0 : -EINVAL; +} +EXPORT_SYMBOL(mlx4_get_slave_from_roce_gid); + +int mlx4_get_roce_gid_from_slave(struct mlx4_dev *dev, int port, int slave_id, + u8 *gid) +{ + struct mlx4_priv *priv = mlx4_priv(dev); + + if (!mlx4_is_master(dev)) + return -EINVAL; + + memcpy(gid, priv->roce_gids[port - 1][slave_id].raw, 16); + return 0; +} +EXPORT_SYMBOL(mlx4_get_roce_gid_from_slave); diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c index 57428a0cb9dd..74e490d70184 100644 --- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c +++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c @@ -52,6 +52,8 @@ struct mac_res { struct list_head list; u64 mac; + int ref_count; + u8 smac_index; u8 port; }; @@ -219,6 +221,11 @@ struct res_fs_rule { int qpn; }; +static int mlx4_is_eth(struct mlx4_dev *dev, int port) +{ + return dev->caps.port_mask[port] == MLX4_PORT_TYPE_IB ? 0 : 1; +} + static void *res_tracker_lookup(struct rb_root *root, u64 res_id) { struct rb_node *node = root->rb_node; @@ -600,15 +607,34 @@ static void update_gid(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *inbox, struct mlx4_qp_context *qp_ctx = inbox->buf + 8; enum mlx4_qp_optpar optpar = be32_to_cpu(*(__be32 *) inbox->buf); u32 ts = (be32_to_cpu(qp_ctx->flags) >> 16) & 0xff; + int port; - if (MLX4_QP_ST_UD == ts) - qp_ctx->pri_path.mgid_index = 0x80 | slave; - - if (MLX4_QP_ST_RC == ts || MLX4_QP_ST_UC == ts) { - if (optpar & MLX4_QP_OPTPAR_PRIMARY_ADDR_PATH) - qp_ctx->pri_path.mgid_index = slave & 0x7F; - if (optpar & MLX4_QP_OPTPAR_ALT_ADDR_PATH) - qp_ctx->alt_path.mgid_index = slave & 0x7F; + if (MLX4_QP_ST_UD == ts) { + port = (qp_ctx->pri_path.sched_queue >> 6 & 1) + 1; + if (mlx4_is_eth(dev, port)) + qp_ctx->pri_path.mgid_index = mlx4_get_base_gid_ix(dev, slave) | 0x80; + else + qp_ctx->pri_path.mgid_index = slave | 0x80; + + } else if (MLX4_QP_ST_RC == ts || MLX4_QP_ST_XRC == ts || MLX4_QP_ST_UC == ts) { + if (optpar & MLX4_QP_OPTPAR_PRIMARY_ADDR_PATH) { + port = (qp_ctx->pri_path.sched_queue >> 6 & 1) + 1; + if (mlx4_is_eth(dev, port)) { + qp_ctx->pri_path.mgid_index += mlx4_get_base_gid_ix(dev, slave); + qp_ctx->pri_path.mgid_index &= 0x7f; + } else { + qp_ctx->pri_path.mgid_index = slave & 0x7F; + } + } + if (optpar & MLX4_QP_OPTPAR_ALT_ADDR_PATH) { + port = (qp_ctx->alt_path.sched_queue >> 6 & 1) + 1; + if (mlx4_is_eth(dev, port)) { + qp_ctx->alt_path.mgid_index += mlx4_get_base_gid_ix(dev, slave); + qp_ctx->alt_path.mgid_index &= 0x7f; + } else { + qp_ctx->alt_path.mgid_index = slave & 0x7F; + } + } } } @@ -619,7 +645,6 @@ static int update_vport_qp_param(struct mlx4_dev *dev, struct mlx4_qp_context *qpc = inbox->buf + 8; struct mlx4_vport_oper_state *vp_oper; struct mlx4_priv *priv; - u32 qp_type; int port; port = (qpc->pri_path.sched_queue & 0x40) ? 2 : 1; @@ -627,12 +652,6 @@ static int update_vport_qp_param(struct mlx4_dev *dev, vp_oper = &priv->mfunc.master.vf_oper[slave].vport[port]; if (MLX4_VGT != vp_oper->state.default_vlan) { - qp_type = (be32_to_cpu(qpc->flags) >> 16) & 0xff; - if (MLX4_QP_ST_RC == qp_type || - (MLX4_QP_ST_UD == qp_type && - !mlx4_is_qp_reserved(dev, qpn))) - return -EINVAL; - /* the reserved QPs (special, proxy, tunnel) * do not operate over vlans */ @@ -1659,11 +1678,39 @@ static int srq_alloc_res(struct mlx4_dev *dev, int slave, int op, int cmd, return err; } -static int mac_add_to_slave(struct mlx4_dev *dev, int slave, u64 mac, int port) +static int mac_find_smac_ix_in_slave(struct mlx4_dev *dev, int slave, int port, + u8 smac_index, u64 *mac) { struct mlx4_priv *priv = mlx4_priv(dev); struct mlx4_resource_tracker *tracker = &priv->mfunc.master.res_tracker; - struct mac_res *res; + struct list_head *mac_list = + &tracker->slave_list[slave].res_list[RES_MAC]; + struct mac_res *res, *tmp; + + list_for_each_entry_safe(res, tmp, mac_list, list) { + if (res->smac_index == smac_index && res->port == (u8) port) { + *mac = res->mac; + return 0; + } + } + return -ENOENT; +} + +static int mac_add_to_slave(struct mlx4_dev *dev, int slave, u64 mac, int port, u8 smac_index) +{ + struct mlx4_priv *priv = mlx4_priv(dev); + struct mlx4_resource_tracker *tracker = &priv->mfunc.master.res_tracker; + struct list_head *mac_list = + &tracker->slave_list[slave].res_list[RES_MAC]; + struct mac_res *res, *tmp; + + list_for_each_entry_safe(res, tmp, mac_list, list) { + if (res->mac == mac && res->port == (u8) port) { + /* mac found. update ref count */ + ++res->ref_count; + return 0; + } + } if (mlx4_grant_resource(dev, slave, RES_MAC, 1, port)) return -EINVAL; @@ -1674,6 +1721,8 @@ static int mac_add_to_slave(struct mlx4_dev *dev, int slave, u64 mac, int port) } res->mac = mac; res->port = (u8) port; + res->smac_index = smac_index; + res->ref_count = 1; list_add_tail(&res->list, &tracker->slave_list[slave].res_list[RES_MAC]); return 0; @@ -1690,9 +1739,11 @@ static void mac_del_from_slave(struct mlx4_dev *dev, int slave, u64 mac, list_for_each_entry_safe(res, tmp, mac_list, list) { if (res->mac == mac && res->port == (u8) port) { - list_del(&res->list); - mlx4_release_resource(dev, slave, RES_MAC, 1, port); - kfree(res); + if (!--res->ref_count) { + list_del(&res->list); + mlx4_release_resource(dev, slave, RES_MAC, 1, port); + kfree(res); + } break; } } @@ -1705,10 +1756,13 @@ static void rem_slave_macs(struct mlx4_dev *dev, int slave) struct list_head *mac_list = &tracker->slave_list[slave].res_list[RES_MAC]; struct mac_res *res, *tmp; + int i; list_for_each_entry_safe(res, tmp, mac_list, list) { list_del(&res->list); - __mlx4_unregister_mac(dev, res->port, res->mac); + /* dereference the mac the num times the slave referenced it */ + for (i = 0; i < res->ref_count; i++) + __mlx4_unregister_mac(dev, res->port, res->mac); mlx4_release_resource(dev, slave, RES_MAC, 1, res->port); kfree(res); } @@ -1720,6 +1774,7 @@ static int mac_alloc_res(struct mlx4_dev *dev, int slave, int op, int cmd, int err = -EINVAL; int port; u64 mac; + u8 smac_index; if (op != RES_OP_RESERVE_AND_MAP) return err; @@ -1729,12 +1784,13 @@ static int mac_alloc_res(struct mlx4_dev *dev, int slave, int op, int cmd, err = __mlx4_register_mac(dev, port, mac); if (err >= 0) { + smac_index = err; set_param_l(out_param, err); err = 0; } if (!err) { - err = mac_add_to_slave(dev, slave, mac, port); + err = mac_add_to_slave(dev, slave, mac, port, smac_index); if (err) __mlx4_unregister_mac(dev, port, mac); } @@ -2734,6 +2790,8 @@ static int verify_qp_parameters(struct mlx4_dev *dev, u32 qp_type; struct mlx4_qp_context *qp_ctx; enum mlx4_qp_optpar optpar; + int port; + int num_gids; qp_ctx = inbox->buf + 8; qp_type = (be32_to_cpu(qp_ctx->flags) >> 16) & 0xff; @@ -2741,6 +2799,7 @@ static int verify_qp_parameters(struct mlx4_dev *dev, switch (qp_type) { case MLX4_QP_ST_RC: + case MLX4_QP_ST_XRC: case MLX4_QP_ST_UC: switch (transition) { case QP_TRANS_INIT2RTR: @@ -2749,13 +2808,24 @@ static int verify_qp_parameters(struct mlx4_dev *dev, case QP_TRANS_SQD2SQD: case QP_TRANS_SQD2RTS: if (slave != mlx4_master_func_num(dev)) - /* slaves have only gid index 0 */ - if (optpar & MLX4_QP_OPTPAR_PRIMARY_ADDR_PATH) - if (qp_ctx->pri_path.mgid_index) + if (optpar & MLX4_QP_OPTPAR_PRIMARY_ADDR_PATH) { + port = (qp_ctx->pri_path.sched_queue >> 6 & 1) + 1; + if (dev->caps.port_mask[port] != MLX4_PORT_TYPE_IB) + num_gids = mlx4_get_slave_num_gids(dev, slave); + else + num_gids = 1; + if (qp_ctx->pri_path.mgid_index >= num_gids) return -EINVAL; - if (optpar & MLX4_QP_OPTPAR_ALT_ADDR_PATH) - if (qp_ctx->alt_path.mgid_index) + } + if (optpar & MLX4_QP_OPTPAR_ALT_ADDR_PATH) { + port = (qp_ctx->alt_path.sched_queue >> 6 & 1) + 1; + if (dev->caps.port_mask[port] != MLX4_PORT_TYPE_IB) + num_gids = mlx4_get_slave_num_gids(dev, slave); + else + num_gids = 1; + if (qp_ctx->alt_path.mgid_index >= num_gids) return -EINVAL; + } break; default: break; @@ -3268,6 +3338,25 @@ int mlx4_INIT2INIT_QP_wrapper(struct mlx4_dev *dev, int slave, return mlx4_GEN_QP_wrapper(dev, slave, vhcr, inbox, outbox, cmd); } +static int roce_verify_mac(struct mlx4_dev *dev, int slave, + struct mlx4_qp_context *qpc, + struct mlx4_cmd_mailbox *inbox) +{ + u64 mac; + int port; + u32 ts = (be32_to_cpu(qpc->flags) >> 16) & 0xff; + u8 sched = *(u8 *)(inbox->buf + 64); + u8 smac_ix; + + port = (sched >> 6 & 1) + 1; + if (mlx4_is_eth(dev, port) && (ts != MLX4_QP_ST_MLX)) { + smac_ix = qpc->pri_path.grh_mylmc & 0x7f; + if (mac_find_smac_ix_in_slave(dev, slave, port, smac_ix, &mac)) + return -ENOENT; + } + return 0; +} + int mlx4_INIT2RTR_QP_wrapper(struct mlx4_dev *dev, int slave, struct mlx4_vhcr *vhcr, struct mlx4_cmd_mailbox *inbox, @@ -3290,6 +3379,9 @@ int mlx4_INIT2RTR_QP_wrapper(struct mlx4_dev *dev, int slave, if (err) return err; + if (roce_verify_mac(dev, slave, qpc, inbox)) + return -EINVAL; + update_pkey_index(dev, slave, inbox); update_gid(dev, inbox, (u8)slave); adjust_proxy_tun_qkey(dev, vhcr, qpc); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig index 157fe8df2c3e..8ff57e8e3e91 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig +++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig @@ -4,5 +4,5 @@ config MLX5_CORE tristate - depends on PCI && X86 + depends on PCI default n diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index a064f06e0cb8..77ac95f052da 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -46,8 +46,8 @@ #include "mlx5_core.h" #define DRIVER_NAME "mlx5_core" -#define DRIVER_VERSION "1.0" -#define DRIVER_RELDATE "June 2013" +#define DRIVER_VERSION "2.2-1" +#define DRIVER_RELDATE "Feb 2014" MODULE_AUTHOR("Eli Cohen <eli@mellanox.com>"); MODULE_DESCRIPTION("Mellanox ConnectX-IB HCA core library"); @@ -116,7 +116,6 @@ static int mlx5_enable_msix(struct mlx5_core_dev *dev) struct mlx5_eq_table *table = &dev->priv.eq_table; int num_eqs = 1 << dev->caps.log_max_eq; int nvec; - int err; int i; nvec = dev->caps.num_ports * num_online_cpus() + MLX5_EQ_VEC_COMP_BASE; @@ -131,17 +130,12 @@ static int mlx5_enable_msix(struct mlx5_core_dev *dev) for (i = 0; i < nvec; i++) table->msix_arr[i].entry = i; -retry: - table->num_comp_vectors = nvec - MLX5_EQ_VEC_COMP_BASE; - err = pci_enable_msix(dev->pdev, table->msix_arr, nvec); - if (err <= 0) { - return err; - } else if (err > 2) { - nvec = err; - goto retry; - } + nvec = pci_enable_msix_range(dev->pdev, table->msix_arr, + MLX5_EQ_VEC_COMP_BASE, nvec); + if (nvec < 0) + return nvec; - mlx5_core_dbg(dev, "received %d MSI vectors out of %d requested\n", err, nvec); + table->num_comp_vectors = nvec - MLX5_EQ_VEC_COMP_BASE; return 0; } @@ -537,7 +531,6 @@ static int __init init(void) return 0; - mlx5_health_cleanup(); err_debug: mlx5_unregister_debugfs(); return err; diff --git a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c index 68026f7e8ba3..130f6b204efa 100644 --- a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c +++ b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c @@ -2329,16 +2329,14 @@ static int myri10ge_request_irq(struct myri10ge_priv *mgp) status = 0; if (myri10ge_msi) { if (mgp->num_slices > 1) { - status = - pci_enable_msix(pdev, mgp->msix_vectors, - mgp->num_slices); - if (status == 0) { - mgp->msix_enabled = 1; - } else { + status = pci_enable_msix_range(pdev, mgp->msix_vectors, + mgp->num_slices, mgp->num_slices); + if (status < 0) { dev_err(&pdev->dev, "Error %d setting up MSI-X\n", status); return status; } + mgp->msix_enabled = 1; } if (mgp->msix_enabled == 0) { status = pci_enable_msi(pdev); @@ -3895,32 +3893,34 @@ static void myri10ge_probe_slices(struct myri10ge_priv *mgp) mgp->msix_vectors = kcalloc(mgp->num_slices, sizeof(*mgp->msix_vectors), GFP_KERNEL); if (mgp->msix_vectors == NULL) - goto disable_msix; + goto no_msix; for (i = 0; i < mgp->num_slices; i++) { mgp->msix_vectors[i].entry = i; } while (mgp->num_slices > 1) { - /* make sure it is a power of two */ - while (!is_power_of_2(mgp->num_slices)) - mgp->num_slices--; + mgp->num_slices = rounddown_pow_of_two(mgp->num_slices); if (mgp->num_slices == 1) - goto disable_msix; - status = pci_enable_msix(pdev, mgp->msix_vectors, - mgp->num_slices); - if (status == 0) { - pci_disable_msix(pdev); + goto no_msix; + status = pci_enable_msix_range(pdev, + mgp->msix_vectors, + mgp->num_slices, + mgp->num_slices); + if (status < 0) + goto no_msix; + + pci_disable_msix(pdev); + + if (status == mgp->num_slices) { if (old_allocated) kfree(old_fw); return; - } - if (status > 0) + } else { mgp->num_slices = status; - else - goto disable_msix; + } } -disable_msix: +no_msix: if (mgp->msix_vectors != NULL) { kfree(mgp->msix_vectors); mgp->msix_vectors = NULL; diff --git a/drivers/net/ethernet/neterion/s2io.c b/drivers/net/ethernet/neterion/s2io.c index 9eeddbd0b2c7..56e3a9d42bb2 100644 --- a/drivers/net/ethernet/neterion/s2io.c +++ b/drivers/net/ethernet/neterion/s2io.c @@ -3792,9 +3792,10 @@ static int s2io_enable_msi_x(struct s2io_nic *nic) writeq(rx_mat, &bar0->rx_mat); readq(&bar0->rx_mat); - ret = pci_enable_msix(nic->pdev, nic->entries, nic->num_entries); + ret = pci_enable_msix_range(nic->pdev, nic->entries, + nic->num_entries, nic->num_entries); /* We fail init if error or we get less vectors than min required */ - if (ret) { + if (ret < 0) { DBG_PRINT(ERR_DBG, "Enabling MSI-X failed\n"); kfree(nic->entries); swstats->mem_freed += nic->num_entries * diff --git a/drivers/net/ethernet/neterion/vxge/vxge-main.c b/drivers/net/ethernet/neterion/vxge/vxge-main.c index 1ded50ca1600..c83cedd26dec 100644 --- a/drivers/net/ethernet/neterion/vxge/vxge-main.c +++ b/drivers/net/ethernet/neterion/vxge/vxge-main.c @@ -726,9 +726,6 @@ static int vxge_learn_mac(struct vxgedev *vdev, u8 *mac_header) int vpath_idx = 0; enum vxge_hw_status status = VXGE_HW_OK; struct vxge_vpath *vpath = NULL; - struct __vxge_hw_device *hldev; - - hldev = pci_get_drvdata(vdev->pdev); mac_address = (u8 *)&mac_addr; memcpy(mac_address, mac_header, ETH_ALEN); @@ -2352,12 +2349,18 @@ start: vdev->vxge_entries[j].entry = VXGE_ALARM_MSIX_ID; vdev->vxge_entries[j].in_use = 0; - ret = pci_enable_msix(vdev->pdev, vdev->entries, vdev->intr_cnt); - if (ret > 0) { + ret = pci_enable_msix_range(vdev->pdev, + vdev->entries, 3, vdev->intr_cnt); + if (ret < 0) { + ret = -ENODEV; + goto enable_msix_failed; + } else if (ret < vdev->intr_cnt) { + pci_disable_msix(vdev->pdev); + vxge_debug_init(VXGE_ERR, "%s: MSI-X enable failed for %d vectors, ret: %d", VXGE_DRIVER_NAME, vdev->intr_cnt, ret); - if ((max_config_vpath != VXGE_USE_DEFAULT) || (ret < 3)) { + if (max_config_vpath != VXGE_USE_DEFAULT) { ret = -ENODEV; goto enable_msix_failed; } @@ -2371,9 +2374,6 @@ start: vxge_close_vpaths(vdev, temp); vdev->no_of_vpath = temp; goto start; - } else if (ret < 0) { - ret = -ENODEV; - goto enable_msix_failed; } return 0; @@ -2443,9 +2443,6 @@ static void vxge_rem_msix_isr(struct vxgedev *vdev) static void vxge_rem_isr(struct vxgedev *vdev) { - struct __vxge_hw_device *hldev; - hldev = pci_get_drvdata(vdev->pdev); - #ifdef CONFIG_PCI_MSI if (vdev->config.intr_type == MSI_X) { vxge_rem_msix_isr(vdev); diff --git a/drivers/net/ethernet/nvidia/forcedeth.c b/drivers/net/ethernet/nvidia/forcedeth.c index 70cf97fe67f2..bad3c057ee8a 100644 --- a/drivers/net/ethernet/nvidia/forcedeth.c +++ b/drivers/net/ethernet/nvidia/forcedeth.c @@ -3930,7 +3930,7 @@ static int nv_request_irq(struct net_device *dev, int intr_test) { struct fe_priv *np = get_nvpriv(dev); u8 __iomem *base = get_hwbase(dev); - int ret = 1; + int ret; int i; irqreturn_t (*handler)(int foo, void *data); @@ -3946,14 +3946,18 @@ static int nv_request_irq(struct net_device *dev, int intr_test) if (np->msi_flags & NV_MSI_X_CAPABLE) { for (i = 0; i < (np->msi_flags & NV_MSI_X_VECTORS_MASK); i++) np->msi_x_entry[i].entry = i; - ret = pci_enable_msix(np->pci_dev, np->msi_x_entry, (np->msi_flags & NV_MSI_X_VECTORS_MASK)); - if (ret == 0) { + ret = pci_enable_msix_range(np->pci_dev, + np->msi_x_entry, + np->msi_flags & NV_MSI_X_VECTORS_MASK, + np->msi_flags & NV_MSI_X_VECTORS_MASK); + if (ret > 0) { np->msi_flags |= NV_MSI_X_ENABLED; if (optimization_mode == NV_OPTIMIZATION_MODE_THROUGHPUT && !intr_test) { /* Request irq for rx handling */ sprintf(np->name_rx, "%s-rx", dev->name); - if (request_irq(np->msi_x_entry[NV_MSI_X_VECTOR_RX].vector, - nv_nic_irq_rx, IRQF_SHARED, np->name_rx, dev) != 0) { + ret = request_irq(np->msi_x_entry[NV_MSI_X_VECTOR_RX].vector, + nv_nic_irq_rx, IRQF_SHARED, np->name_rx, dev); + if (ret) { netdev_info(dev, "request_irq failed for rx %d\n", ret); @@ -3963,8 +3967,9 @@ static int nv_request_irq(struct net_device *dev, int intr_test) } /* Request irq for tx handling */ sprintf(np->name_tx, "%s-tx", dev->name); - if (request_irq(np->msi_x_entry[NV_MSI_X_VECTOR_TX].vector, - nv_nic_irq_tx, IRQF_SHARED, np->name_tx, dev) != 0) { + ret = request_irq(np->msi_x_entry[NV_MSI_X_VECTOR_TX].vector, + nv_nic_irq_tx, IRQF_SHARED, np->name_tx, dev); + if (ret) { netdev_info(dev, "request_irq failed for tx %d\n", ret); @@ -3974,8 +3979,9 @@ static int nv_request_irq(struct net_device *dev, int intr_test) } /* Request irq for link and timer handling */ sprintf(np->name_other, "%s-other", dev->name); - if (request_irq(np->msi_x_entry[NV_MSI_X_VECTOR_OTHER].vector, - nv_nic_irq_other, IRQF_SHARED, np->name_other, dev) != 0) { + ret = request_irq(np->msi_x_entry[NV_MSI_X_VECTOR_OTHER].vector, + nv_nic_irq_other, IRQF_SHARED, np->name_other, dev); + if (ret) { netdev_info(dev, "request_irq failed for link %d\n", ret); @@ -3991,7 +3997,9 @@ static int nv_request_irq(struct net_device *dev, int intr_test) set_msix_vector_map(dev, NV_MSI_X_VECTOR_OTHER, NVREG_IRQ_OTHER); } else { /* Request irq for all interrupts */ - if (request_irq(np->msi_x_entry[NV_MSI_X_VECTOR_ALL].vector, handler, IRQF_SHARED, dev->name, dev) != 0) { + ret = request_irq(np->msi_x_entry[NV_MSI_X_VECTOR_ALL].vector, + handler, IRQF_SHARED, dev->name, dev); + if (ret) { netdev_info(dev, "request_irq failed %d\n", ret); @@ -4005,13 +4013,15 @@ static int nv_request_irq(struct net_device *dev, int intr_test) writel(0, base + NvRegMSIXMap1); } netdev_info(dev, "MSI-X enabled\n"); + return 0; } } - if (ret != 0 && np->msi_flags & NV_MSI_CAPABLE) { + if (np->msi_flags & NV_MSI_CAPABLE) { ret = pci_enable_msi(np->pci_dev); if (ret == 0) { np->msi_flags |= NV_MSI_ENABLED; - if (request_irq(np->pci_dev->irq, handler, IRQF_SHARED, dev->name, dev) != 0) { + ret = request_irq(np->pci_dev->irq, handler, IRQF_SHARED, dev->name, dev); + if (ret) { netdev_info(dev, "request_irq failed %d\n", ret); pci_disable_msi(np->pci_dev); @@ -4025,13 +4035,12 @@ static int nv_request_irq(struct net_device *dev, int intr_test) /* enable msi vector 0 */ writel(NVREG_MSI_VECTOR_0_ENABLED, base + NvRegMSIIrqMask); netdev_info(dev, "MSI enabled\n"); + return 0; } } - if (ret != 0) { - if (request_irq(np->pci_dev->irq, handler, IRQF_SHARED, dev->name, dev) != 0) - goto out_err; - } + if (request_irq(np->pci_dev->irq, handler, IRQF_SHARED, dev->name, dev) != 0) + goto out_err; return 0; out_free_tx: diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c index 70849dea32b1..f09c35d669b3 100644 --- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c +++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c @@ -643,8 +643,9 @@ static int netxen_setup_msi_interrupts(struct netxen_adapter *adapter, if (adapter->msix_supported) { netxen_init_msix_entries(adapter, num_msix); - err = pci_enable_msix(pdev, adapter->msix_entries, num_msix); - if (err == 0) { + err = pci_enable_msix_range(pdev, adapter->msix_entries, + num_msix, num_msix); + if (err > 0) { adapter->flags |= NETXEN_NIC_MSIX_ENABLED; netxen_set_msix_bit(pdev, 1); diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h index f19f81cde134..df9daa335292 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h @@ -38,8 +38,8 @@ #define _QLCNIC_LINUX_MAJOR 5 #define _QLCNIC_LINUX_MINOR 3 -#define _QLCNIC_LINUX_SUBVERSION 55 -#define QLCNIC_LINUX_VERSIONID "5.3.55" +#define _QLCNIC_LINUX_SUBVERSION 56 +#define QLCNIC_LINUX_VERSIONID "5.3.56" #define QLCNIC_DRV_IDC_VER 0x01 #define QLCNIC_DRIVER_VERSION ((_QLCNIC_LINUX_MAJOR << 16) |\ (_QLCNIC_LINUX_MINOR << 8) | (_QLCNIC_LINUX_SUBVERSION)) @@ -394,7 +394,7 @@ struct qlcnic_nic_intr_coalesce { u32 timer_out; }; -struct qlcnic_dump_template_hdr { +struct qlcnic_83xx_dump_template_hdr { u32 type; u32 offset; u32 size; @@ -411,15 +411,42 @@ struct qlcnic_dump_template_hdr { u32 rsvd[0]; }; +struct qlcnic_82xx_dump_template_hdr { + u32 type; + u32 offset; + u32 size; + u32 cap_mask; + u32 num_entries; + u32 version; + u32 timestamp; + u32 checksum; + u32 drv_cap_mask; + u32 sys_info[3]; + u32 saved_state[16]; + u32 cap_sizes[8]; + u32 rsvd[7]; + u32 capabilities; + u32 rsvd1[0]; +}; + struct qlcnic_fw_dump { u8 clr; /* flag to indicate if dump is cleared */ bool enable; /* enable/disable dump */ u32 size; /* total size of the dump */ + u32 cap_mask; /* Current capture mask */ void *data; /* dump data area */ - struct qlcnic_dump_template_hdr *tmpl_hdr; + void *tmpl_hdr; dma_addr_t phys_addr; void *dma_buffer; bool use_pex_dma; + /* Read only elements which are common between 82xx and 83xx + * template header. Update these values immediately after we read + * template header from Firmware + */ + u32 tmpl_hdr_size; + u32 version; + u32 num_entries; + u32 offset; }; /* @@ -1769,6 +1796,12 @@ struct qlcnic_hardware_ops { struct qlcnic_host_tx_ring *); void (*disable_tx_intr) (struct qlcnic_adapter *, struct qlcnic_host_tx_ring *); + u32 (*get_saved_state)(void *, u32); + void (*set_saved_state)(void *, u32, u32); + void (*cache_tmpl_hdr_values)(struct qlcnic_fw_dump *); + u32 (*get_cap_size)(void *, int); + void (*set_sys_info)(void *, int, u32); + void (*store_cap_mask)(void *, u32); }; extern struct qlcnic_nic_template qlcnic_vf_ops; @@ -2007,6 +2040,42 @@ static inline void qlcnic_read_phys_port_id(struct qlcnic_adapter *adapter) adapter->ahw->hw_ops->read_phys_port_id(adapter); } +static inline u32 qlcnic_get_saved_state(struct qlcnic_adapter *adapter, + void *t_hdr, u32 index) +{ + return adapter->ahw->hw_ops->get_saved_state(t_hdr, index); +} + +static inline void qlcnic_set_saved_state(struct qlcnic_adapter *adapter, + void *t_hdr, u32 index, u32 value) +{ + adapter->ahw->hw_ops->set_saved_state(t_hdr, index, value); +} + +static inline void qlcnic_cache_tmpl_hdr_values(struct qlcnic_adapter *adapter, + struct qlcnic_fw_dump *fw_dump) +{ + adapter->ahw->hw_ops->cache_tmpl_hdr_values(fw_dump); +} + +static inline u32 qlcnic_get_cap_size(struct qlcnic_adapter *adapter, + void *tmpl_hdr, int index) +{ + return adapter->ahw->hw_ops->get_cap_size(tmpl_hdr, index); +} + +static inline void qlcnic_set_sys_info(struct qlcnic_adapter *adapter, + void *tmpl_hdr, int idx, u32 value) +{ + adapter->ahw->hw_ops->set_sys_info(tmpl_hdr, idx, value); +} + +static inline void qlcnic_store_cap_mask(struct qlcnic_adapter *adapter, + void *tmpl_hdr, u32 mask) +{ + adapter->ahw->hw_ops->store_cap_mask(tmpl_hdr, mask); +} + static inline void qlcnic_dev_request_reset(struct qlcnic_adapter *adapter, u32 key) { diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c index 4146664d4d6a..3b83fbde4975 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c @@ -203,7 +203,12 @@ static struct qlcnic_hardware_ops qlcnic_83xx_hw_ops = { .disable_sds_intr = qlcnic_83xx_disable_sds_intr, .enable_tx_intr = qlcnic_83xx_enable_tx_intr, .disable_tx_intr = qlcnic_83xx_disable_tx_intr, - + .get_saved_state = qlcnic_83xx_get_saved_state, + .set_saved_state = qlcnic_83xx_set_saved_state, + .cache_tmpl_hdr_values = qlcnic_83xx_cache_tmpl_hdr_values, + .get_cap_size = qlcnic_83xx_get_cap_size, + .set_sys_info = qlcnic_83xx_set_sys_info, + .store_cap_mask = qlcnic_83xx_store_cap_mask, }; static struct qlcnic_nic_template qlcnic_83xx_ops = { @@ -340,6 +345,7 @@ int qlcnic_83xx_setup_intr(struct qlcnic_adapter *adapter) if (qlcnic_sriov_vf_check(adapter)) return -EINVAL; num_msix = 1; + adapter->drv_sds_rings = QLCNIC_SINGLE_RING; adapter->drv_tx_rings = QLCNIC_SINGLE_RING; } } diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h index f92485ca21d1..81c1889f6f3e 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h @@ -308,6 +308,8 @@ struct qlc_83xx_reset { #define QLC_83XX_IDC_FLASH_PARAM_ADDR 0x3e8020 struct qlcnic_adapter; +struct qlcnic_fw_dump; + struct qlc_83xx_idc { int (*state_entry) (struct qlcnic_adapter *); u64 sec_counter; @@ -650,4 +652,10 @@ int qlcnic_83xx_check_vnic_state(struct qlcnic_adapter *); void qlcnic_83xx_aer_stop_poll_work(struct qlcnic_adapter *); int qlcnic_83xx_aer_reset(struct qlcnic_adapter *); void qlcnic_83xx_aer_start_poll_work(struct qlcnic_adapter *); +u32 qlcnic_83xx_get_saved_state(void *, u32); +void qlcnic_83xx_set_saved_state(void *, u32, u32); +void qlcnic_83xx_cache_tmpl_hdr_values(struct qlcnic_fw_dump *); +u32 qlcnic_83xx_get_cap_size(void *, int); +void qlcnic_83xx_set_sys_info(void *, int, u32); +void qlcnic_83xx_store_cap_mask(void *, u32); #endif diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_dcb.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_dcb.c index 77f1bce432d2..7d4f54912bad 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_dcb.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_dcb.c @@ -807,7 +807,7 @@ qlcnic_dcb_get_pg_tc_cfg_tx(struct net_device *netdev, int tc, u8 *prio, !type->tc_param_valid) return; - if (tc < 0 || (tc > QLC_DCB_MAX_TC)) + if (tc < 0 || (tc >= QLC_DCB_MAX_TC)) return; tc_cfg = &type->tc_cfg[tc]; @@ -843,7 +843,7 @@ static void qlcnic_dcb_get_pg_bwg_cfg_tx(struct net_device *netdev, int pgid, !type->tc_param_valid) return; - if (pgid < 0 || pgid > QLC_DCB_MAX_PG) + if (pgid < 0 || pgid >= QLC_DCB_MAX_PG) return; pgcfg = &type->pg_cfg[pgid]; diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c index acee1a5d80c6..1960609481ce 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c @@ -1639,14 +1639,14 @@ qlcnic_get_dump_flag(struct net_device *netdev, struct ethtool_dump *dump) } if (fw_dump->clr) - dump->len = fw_dump->tmpl_hdr->size + fw_dump->size; + dump->len = fw_dump->tmpl_hdr_size + fw_dump->size; else dump->len = 0; if (!qlcnic_check_fw_dump_state(adapter)) dump->flag = ETH_FW_DUMP_DISABLE; else - dump->flag = fw_dump->tmpl_hdr->drv_cap_mask; + dump->flag = fw_dump->cap_mask; dump->version = adapter->fw_version; return 0; @@ -1671,9 +1671,10 @@ qlcnic_get_dump_data(struct net_device *netdev, struct ethtool_dump *dump, netdev_info(netdev, "Dump not available\n"); return -EINVAL; } + /* Copy template header first */ - copy_sz = fw_dump->tmpl_hdr->size; - hdr_ptr = (u32 *) fw_dump->tmpl_hdr; + copy_sz = fw_dump->tmpl_hdr_size; + hdr_ptr = (u32 *)fw_dump->tmpl_hdr; data = buffer; for (i = 0; i < copy_sz/sizeof(u32); i++) *data++ = cpu_to_le32(*hdr_ptr++); @@ -1681,7 +1682,7 @@ qlcnic_get_dump_data(struct net_device *netdev, struct ethtool_dump *dump, /* Copy captured dump data */ memcpy(buffer + copy_sz, fw_dump->data, fw_dump->size); dump->len = copy_sz + fw_dump->size; - dump->flag = fw_dump->tmpl_hdr->drv_cap_mask; + dump->flag = fw_dump->cap_mask; /* Free dump area once data has been captured */ vfree(fw_dump->data); @@ -1703,7 +1704,11 @@ static int qlcnic_set_dump_mask(struct qlcnic_adapter *adapter, u32 mask) return -EOPNOTSUPP; } - fw_dump->tmpl_hdr->drv_cap_mask = mask; + fw_dump->cap_mask = mask; + + /* Store new capture mask in template header as well*/ + qlcnic_store_cap_mask(adapter, fw_dump->tmpl_hdr, mask); + netdev_info(netdev, "Driver mask changed to: 0x%x\n", mask); return 0; } diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c index 03d18a0be6ce..9f3adf4e70b5 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c @@ -317,9 +317,7 @@ static void qlcnic_write_window_reg(u32 addr, void __iomem *bar0, u32 data) int qlcnic_pcie_sem_lock(struct qlcnic_adapter *adapter, int sem, u32 id_reg) { - int timeout = 0; - int err = 0; - u32 done = 0; + int timeout = 0, err = 0, done = 0; while (!done) { done = QLCRD32(adapter, QLCNIC_PCIE_REG(PCIE_SEM_LOCK(sem)), @@ -327,10 +325,20 @@ qlcnic_pcie_sem_lock(struct qlcnic_adapter *adapter, int sem, u32 id_reg) if (done == 1) break; if (++timeout >= QLCNIC_PCIE_SEM_TIMEOUT) { - dev_err(&adapter->pdev->dev, - "Failed to acquire sem=%d lock; holdby=%d\n", - sem, - id_reg ? QLCRD32(adapter, id_reg, &err) : -1); + if (id_reg) { + done = QLCRD32(adapter, id_reg, &err); + if (done != -1) + dev_err(&adapter->pdev->dev, + "Failed to acquire sem=%d lock held by=%d\n", + sem, done); + else + dev_err(&adapter->pdev->dev, + "Failed to acquire sem=%d lock", + sem); + } else { + dev_err(&adapter->pdev->dev, + "Failed to acquire sem=%d lock", sem); + } return -EIO; } msleep(1); diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.h index 63d75617d445..576b301b11ef 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.h +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.h @@ -161,6 +161,7 @@ struct qlcnic_host_sds_ring; struct qlcnic_host_tx_ring; struct qlcnic_hardware_context; struct qlcnic_adapter; +struct qlcnic_fw_dump; int qlcnic_82xx_hw_read_wx_2M(struct qlcnic_adapter *adapter, ulong, int *); int qlcnic_82xx_hw_write_wx_2M(struct qlcnic_adapter *, ulong, u32); @@ -213,4 +214,11 @@ int qlcnic_82xx_shutdown(struct pci_dev *); int qlcnic_82xx_resume(struct qlcnic_adapter *); void qlcnic_clr_all_drv_state(struct qlcnic_adapter *adapter, u8 failed); void qlcnic_fw_poll_work(struct work_struct *work); + +u32 qlcnic_82xx_get_saved_state(void *, u32); +void qlcnic_82xx_set_saved_state(void *, u32, u32); +void qlcnic_82xx_cache_tmpl_hdr_values(struct qlcnic_fw_dump *); +u32 qlcnic_82xx_get_cap_size(void *, int); +void qlcnic_82xx_set_sys_info(void *, int, u32); +void qlcnic_82xx_store_cap_mask(void *, u32); #endif /* __QLCNIC_HW_H_ */ diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c index ba78c7481fa3..4b92d9d90267 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c @@ -90,7 +90,6 @@ static void qlcnic_82xx_io_resume(struct pci_dev *); static void qlcnic_82xx_set_mac_filter_count(struct qlcnic_adapter *); static pci_ers_result_t qlcnic_82xx_io_error_detected(struct pci_dev *, pci_channel_state_t); - static u32 qlcnic_vlan_tx_check(struct qlcnic_adapter *adapter) { struct qlcnic_hardware_context *ahw = adapter->ahw; @@ -561,6 +560,12 @@ static struct qlcnic_hardware_ops qlcnic_hw_ops = { .disable_sds_intr = qlcnic_82xx_disable_sds_intr, .enable_tx_intr = qlcnic_82xx_enable_tx_intr, .disable_tx_intr = qlcnic_82xx_disable_tx_intr, + .get_saved_state = qlcnic_82xx_get_saved_state, + .set_saved_state = qlcnic_82xx_set_saved_state, + .cache_tmpl_hdr_values = qlcnic_82xx_cache_tmpl_hdr_values, + .get_cap_size = qlcnic_82xx_get_cap_size, + .set_sys_info = qlcnic_82xx_set_sys_info, + .store_cap_mask = qlcnic_82xx_store_cap_mask, }; static int qlcnic_check_multi_tx_capability(struct qlcnic_adapter *adapter) @@ -684,7 +689,7 @@ restore: int qlcnic_enable_msix(struct qlcnic_adapter *adapter, u32 num_msix) { struct pci_dev *pdev = adapter->pdev; - int err = -1, vector; + int err, vector; if (!adapter->msix_entries) { adapter->msix_entries = kcalloc(num_msix, @@ -701,13 +706,17 @@ enable_msix: for (vector = 0; vector < num_msix; vector++) adapter->msix_entries[vector].entry = vector; - err = pci_enable_msix(pdev, adapter->msix_entries, num_msix); - if (err == 0) { + err = pci_enable_msix_range(pdev, + adapter->msix_entries, 1, num_msix); + + if (err == num_msix) { adapter->flags |= QLCNIC_MSIX_ENABLED; adapter->ahw->num_msix = num_msix; dev_info(&pdev->dev, "using msi-x interrupts\n"); - return err; + return 0; } else if (err > 0) { + pci_disable_msix(pdev); + dev_info(&pdev->dev, "Unable to allocate %d MSI-X vectors, Available vectors %d\n", num_msix, err); @@ -715,12 +724,12 @@ enable_msix: if (qlcnic_82xx_check(adapter)) { num_msix = rounddown_pow_of_two(err); if (err < QLCNIC_82XX_MINIMUM_VECTOR) - return -EIO; + return -ENOSPC; } else { num_msix = rounddown_pow_of_two(err - 1); num_msix += 1; if (err < QLCNIC_83XX_MINIMUM_VECTOR) - return -EIO; + return -ENOSPC; } if (qlcnic_82xx_check(adapter) && @@ -747,7 +756,7 @@ enable_msix: } } - return err; + return -EIO; } static int qlcnic_82xx_calculate_msix_vector(struct qlcnic_adapter *adapter) @@ -816,9 +825,10 @@ static int qlcnic_82xx_setup_intr(struct qlcnic_adapter *adapter) if (!(adapter->flags & QLCNIC_MSIX_ENABLED)) { qlcnic_disable_multi_tx(adapter); + adapter->drv_sds_rings = QLCNIC_SINGLE_RING; err = qlcnic_enable_msi_legacy(adapter); - if (!err) + if (err) return err; } } @@ -2441,8 +2451,8 @@ qlcnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (err) { switch (err) { case -ENOTRECOVERABLE: - dev_err(&pdev->dev, "Adapter initialization failed due to a faulty hardware. Please reboot\n"); - dev_err(&pdev->dev, "If reboot doesn't help, please replace the adapter with new one and return the faulty adapter for repair\n"); + dev_err(&pdev->dev, "Adapter initialization failed due to a faulty hardware\n"); + dev_err(&pdev->dev, "Please replace the adapter with new one and return the faulty adapter for repair\n"); goto err_out_free_hw; case -ENOMEM: dev_err(&pdev->dev, "Adapter initialization failed. Please reboot\n"); @@ -3863,7 +3873,7 @@ int qlcnic_validate_rings(struct qlcnic_adapter *adapter, __u32 ring_cnt, strcpy(buf, "Tx"); } - if (!qlcnic_use_msi_x && !qlcnic_use_msi) { + if (!QLCNIC_IS_MSI_FAMILY(adapter)) { netdev_err(netdev, "No RSS/TSS support in INT-x mode\n"); return -EINVAL; } diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c index 7763962e2ec4..37b979b1266b 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c @@ -211,6 +211,107 @@ enum qlcnic_minidump_opcode { QLCNIC_DUMP_RDEND = 255 }; +inline u32 qlcnic_82xx_get_saved_state(void *t_hdr, u32 index) +{ + struct qlcnic_82xx_dump_template_hdr *hdr = t_hdr; + + return hdr->saved_state[index]; +} + +inline void qlcnic_82xx_set_saved_state(void *t_hdr, u32 index, + u32 value) +{ + struct qlcnic_82xx_dump_template_hdr *hdr = t_hdr; + + hdr->saved_state[index] = value; +} + +void qlcnic_82xx_cache_tmpl_hdr_values(struct qlcnic_fw_dump *fw_dump) +{ + struct qlcnic_82xx_dump_template_hdr *hdr; + + hdr = fw_dump->tmpl_hdr; + fw_dump->tmpl_hdr_size = hdr->size; + fw_dump->version = hdr->version; + fw_dump->num_entries = hdr->num_entries; + fw_dump->offset = hdr->offset; + + hdr->drv_cap_mask = hdr->cap_mask; + fw_dump->cap_mask = hdr->cap_mask; +} + +inline u32 qlcnic_82xx_get_cap_size(void *t_hdr, int index) +{ + struct qlcnic_82xx_dump_template_hdr *hdr = t_hdr; + + return hdr->cap_sizes[index]; +} + +void qlcnic_82xx_set_sys_info(void *t_hdr, int idx, u32 value) +{ + struct qlcnic_82xx_dump_template_hdr *hdr = t_hdr; + + hdr->sys_info[idx] = value; +} + +void qlcnic_82xx_store_cap_mask(void *tmpl_hdr, u32 mask) +{ + struct qlcnic_82xx_dump_template_hdr *hdr = tmpl_hdr; + + hdr->drv_cap_mask = mask; +} + +inline u32 qlcnic_83xx_get_saved_state(void *t_hdr, u32 index) +{ + struct qlcnic_83xx_dump_template_hdr *hdr = t_hdr; + + return hdr->saved_state[index]; +} + +inline void qlcnic_83xx_set_saved_state(void *t_hdr, u32 index, + u32 value) +{ + struct qlcnic_83xx_dump_template_hdr *hdr = t_hdr; + + hdr->saved_state[index] = value; +} + +void qlcnic_83xx_cache_tmpl_hdr_values(struct qlcnic_fw_dump *fw_dump) +{ + struct qlcnic_83xx_dump_template_hdr *hdr; + + hdr = fw_dump->tmpl_hdr; + fw_dump->tmpl_hdr_size = hdr->size; + fw_dump->version = hdr->version; + fw_dump->num_entries = hdr->num_entries; + fw_dump->offset = hdr->offset; + + hdr->drv_cap_mask = hdr->cap_mask; + fw_dump->cap_mask = hdr->cap_mask; +} + +inline u32 qlcnic_83xx_get_cap_size(void *t_hdr, int index) +{ + struct qlcnic_83xx_dump_template_hdr *hdr = t_hdr; + + return hdr->cap_sizes[index]; +} + +void qlcnic_83xx_set_sys_info(void *t_hdr, int idx, u32 value) +{ + struct qlcnic_83xx_dump_template_hdr *hdr = t_hdr; + + hdr->sys_info[idx] = value; +} + +void qlcnic_83xx_store_cap_mask(void *tmpl_hdr, u32 mask) +{ + struct qlcnic_83xx_dump_template_hdr *hdr; + + hdr = tmpl_hdr; + hdr->drv_cap_mask = mask; +} + struct qlcnic_dump_operations { enum qlcnic_minidump_opcode opcode; u32 (*handler)(struct qlcnic_adapter *, struct qlcnic_dump_entry *, @@ -238,11 +339,11 @@ static u32 qlcnic_dump_crb(struct qlcnic_adapter *adapter, static u32 qlcnic_dump_ctrl(struct qlcnic_adapter *adapter, struct qlcnic_dump_entry *entry, __le32 *buffer) { + void *hdr = adapter->ahw->fw_dump.tmpl_hdr; + struct __ctrl *ctr = &entry->region.ctrl; int i, k, timeout = 0; - u32 addr, data; + u32 addr, data, temp; u8 no_ops; - struct __ctrl *ctr = &entry->region.ctrl; - struct qlcnic_dump_template_hdr *t_hdr = adapter->ahw->fw_dump.tmpl_hdr; addr = ctr->addr; no_ops = ctr->no_ops; @@ -285,29 +386,42 @@ static u32 qlcnic_dump_ctrl(struct qlcnic_adapter *adapter, } break; case QLCNIC_DUMP_RD_SAVE: - if (ctr->index_a) - addr = t_hdr->saved_state[ctr->index_a]; + temp = ctr->index_a; + if (temp) + addr = qlcnic_get_saved_state(adapter, + hdr, + temp); data = qlcnic_ind_rd(adapter, addr); - t_hdr->saved_state[ctr->index_v] = data; + qlcnic_set_saved_state(adapter, hdr, + ctr->index_v, data); break; case QLCNIC_DUMP_WRT_SAVED: - if (ctr->index_v) - data = t_hdr->saved_state[ctr->index_v]; + temp = ctr->index_v; + if (temp) + data = qlcnic_get_saved_state(adapter, + hdr, + temp); else data = ctr->val1; - if (ctr->index_a) - addr = t_hdr->saved_state[ctr->index_a]; + + temp = ctr->index_a; + if (temp) + addr = qlcnic_get_saved_state(adapter, + hdr, + temp); qlcnic_ind_wr(adapter, addr, data); break; case QLCNIC_DUMP_MOD_SAVE_ST: - data = t_hdr->saved_state[ctr->index_v]; + data = qlcnic_get_saved_state(adapter, hdr, + ctr->index_v); data <<= ctr->shl_val; data >>= ctr->shr_val; if (ctr->val2) data &= ctr->val2; data |= ctr->val3; data += ctr->val1; - t_hdr->saved_state[ctr->index_v] = data; + qlcnic_set_saved_state(adapter, hdr, + ctr->index_v, data); break; default: dev_info(&adapter->pdev->dev, @@ -544,7 +658,7 @@ out: static int qlcnic_start_pex_dma(struct qlcnic_adapter *adapter, struct __mem *mem) { - struct qlcnic_dump_template_hdr *tmpl_hdr; + struct qlcnic_83xx_dump_template_hdr *tmpl_hdr; struct device *dev = &adapter->pdev->dev; u32 dma_no, dma_base_addr, temp_addr; int i, ret, dma_sts; @@ -596,7 +710,7 @@ static u32 qlcnic_read_memory_pexdma(struct qlcnic_adapter *adapter, struct qlcnic_fw_dump *fw_dump = &adapter->ahw->fw_dump; u32 temp, dma_base_addr, size = 0, read_size = 0; struct qlcnic_pex_dma_descriptor *dma_descr; - struct qlcnic_dump_template_hdr *tmpl_hdr; + struct qlcnic_83xx_dump_template_hdr *tmpl_hdr; struct device *dev = &adapter->pdev->dev; dma_addr_t dma_phys_addr; void *dma_buffer; @@ -938,8 +1052,8 @@ static int qlcnic_fw_flash_get_minidump_temp_size(struct qlcnic_adapter *adapter, struct qlcnic_cmd_args *cmd) { - struct qlcnic_dump_template_hdr tmp_hdr; - u32 size = sizeof(struct qlcnic_dump_template_hdr) / sizeof(u32); + struct qlcnic_83xx_dump_template_hdr tmp_hdr; + u32 size = sizeof(tmp_hdr) / sizeof(u32); int ret = 0; if (qlcnic_82xx_check(adapter)) @@ -1027,17 +1141,19 @@ free_mem: return err; } +#define QLCNIC_TEMPLATE_VERSION (0x20001) + int qlcnic_fw_cmd_get_minidump_temp(struct qlcnic_adapter *adapter) { - int err; - u32 temp_size = 0; - u32 version, csum, *tmp_buf; struct qlcnic_hardware_context *ahw; - struct qlcnic_dump_template_hdr *tmpl_hdr; + struct qlcnic_fw_dump *fw_dump; + u32 version, csum, *tmp_buf; u8 use_flash_temp = 0; + u32 temp_size = 0; + int err; ahw = adapter->ahw; - + fw_dump = &ahw->fw_dump; err = qlcnic_fw_get_minidump_temp_size(adapter, &version, &temp_size, &use_flash_temp); if (err) { @@ -1046,11 +1162,11 @@ int qlcnic_fw_cmd_get_minidump_temp(struct qlcnic_adapter *adapter) return -EIO; } - ahw->fw_dump.tmpl_hdr = vzalloc(temp_size); - if (!ahw->fw_dump.tmpl_hdr) + fw_dump->tmpl_hdr = vzalloc(temp_size); + if (!fw_dump->tmpl_hdr) return -ENOMEM; - tmp_buf = (u32 *)ahw->fw_dump.tmpl_hdr; + tmp_buf = (u32 *)fw_dump->tmpl_hdr; if (use_flash_temp) goto flash_temp; @@ -1065,8 +1181,8 @@ flash_temp: dev_err(&adapter->pdev->dev, "Failed to get minidump template header %d\n", err); - vfree(ahw->fw_dump.tmpl_hdr); - ahw->fw_dump.tmpl_hdr = NULL; + vfree(fw_dump->tmpl_hdr); + fw_dump->tmpl_hdr = NULL; return -EIO; } } @@ -1076,21 +1192,22 @@ flash_temp: if (csum) { dev_err(&adapter->pdev->dev, "Template header checksum validation failed\n"); - vfree(ahw->fw_dump.tmpl_hdr); - ahw->fw_dump.tmpl_hdr = NULL; + vfree(fw_dump->tmpl_hdr); + fw_dump->tmpl_hdr = NULL; return -EIO; } - tmpl_hdr = ahw->fw_dump.tmpl_hdr; - tmpl_hdr->drv_cap_mask = tmpl_hdr->cap_mask; + qlcnic_cache_tmpl_hdr_values(adapter, fw_dump); + dev_info(&adapter->pdev->dev, "Default minidump capture mask 0x%x\n", - tmpl_hdr->cap_mask); + fw_dump->cap_mask); - if ((tmpl_hdr->version & 0xfffff) >= 0x20001) - ahw->fw_dump.use_pex_dma = true; + if (qlcnic_83xx_check(adapter) && + (fw_dump->version & 0xfffff) >= QLCNIC_TEMPLATE_VERSION) + fw_dump->use_pex_dma = true; else - ahw->fw_dump.use_pex_dma = false; + fw_dump->use_pex_dma = false; qlcnic_enable_fw_dump_state(adapter); @@ -1099,21 +1216,22 @@ flash_temp: int qlcnic_dump_fw(struct qlcnic_adapter *adapter) { - __le32 *buffer; - u32 ocm_window; - char mesg[64]; - char *msg[] = {mesg, NULL}; - int i, k, ops_cnt, ops_index, dump_size = 0; - u32 entry_offset, dump, no_entries, buf_offset = 0; - struct qlcnic_dump_entry *entry; struct qlcnic_fw_dump *fw_dump = &adapter->ahw->fw_dump; - struct qlcnic_dump_template_hdr *tmpl_hdr = fw_dump->tmpl_hdr; static const struct qlcnic_dump_operations *fw_dump_ops; + struct qlcnic_83xx_dump_template_hdr *hdr_83xx; + u32 entry_offset, dump, no_entries, buf_offset = 0; + int i, k, ops_cnt, ops_index, dump_size = 0; struct device *dev = &adapter->pdev->dev; struct qlcnic_hardware_context *ahw; - void *temp_buffer; + struct qlcnic_dump_entry *entry; + void *temp_buffer, *tmpl_hdr; + u32 ocm_window; + __le32 *buffer; + char mesg[64]; + char *msg[] = {mesg, NULL}; ahw = adapter->ahw; + tmpl_hdr = fw_dump->tmpl_hdr; /* Return if we don't have firmware dump template header */ if (!tmpl_hdr) @@ -1133,8 +1251,9 @@ int qlcnic_dump_fw(struct qlcnic_adapter *adapter) netif_info(adapter->ahw, drv, adapter->netdev, "Take FW dump\n"); /* Calculate the size for dump data area only */ for (i = 2, k = 1; (i & QLCNIC_DUMP_MASK_MAX); i <<= 1, k++) - if (i & tmpl_hdr->drv_cap_mask) - dump_size += tmpl_hdr->cap_sizes[k]; + if (i & fw_dump->cap_mask) + dump_size += qlcnic_get_cap_size(adapter, tmpl_hdr, k); + if (!dump_size) return -EIO; @@ -1144,10 +1263,10 @@ int qlcnic_dump_fw(struct qlcnic_adapter *adapter) buffer = fw_dump->data; fw_dump->size = dump_size; - no_entries = tmpl_hdr->num_entries; - entry_offset = tmpl_hdr->offset; - tmpl_hdr->sys_info[0] = QLCNIC_DRIVER_VERSION; - tmpl_hdr->sys_info[1] = adapter->fw_version; + no_entries = fw_dump->num_entries; + entry_offset = fw_dump->offset; + qlcnic_set_sys_info(adapter, tmpl_hdr, 0, QLCNIC_DRIVER_VERSION); + qlcnic_set_sys_info(adapter, tmpl_hdr, 1, adapter->fw_version); if (fw_dump->use_pex_dma) { temp_buffer = dma_alloc_coherent(dev, QLC_PEX_DMA_READ_SIZE, @@ -1163,16 +1282,17 @@ int qlcnic_dump_fw(struct qlcnic_adapter *adapter) ops_cnt = ARRAY_SIZE(qlcnic_fw_dump_ops); fw_dump_ops = qlcnic_fw_dump_ops; } else { + hdr_83xx = tmpl_hdr; ops_cnt = ARRAY_SIZE(qlcnic_83xx_fw_dump_ops); fw_dump_ops = qlcnic_83xx_fw_dump_ops; - ocm_window = tmpl_hdr->ocm_wnd_reg[adapter->ahw->pci_func]; - tmpl_hdr->saved_state[QLC_83XX_OCM_INDEX] = ocm_window; - tmpl_hdr->saved_state[QLC_83XX_PCI_INDEX] = ahw->pci_func; + ocm_window = hdr_83xx->ocm_wnd_reg[ahw->pci_func]; + hdr_83xx->saved_state[QLC_83XX_OCM_INDEX] = ocm_window; + hdr_83xx->saved_state[QLC_83XX_PCI_INDEX] = ahw->pci_func; } for (i = 0; i < no_entries; i++) { - entry = (void *)tmpl_hdr + entry_offset; - if (!(entry->hdr.mask & tmpl_hdr->drv_cap_mask)) { + entry = tmpl_hdr + entry_offset; + if (!(entry->hdr.mask & fw_dump->cap_mask)) { entry->hdr.flags |= QLCNIC_DUMP_SKIP; entry_offset += entry->hdr.offset; continue; @@ -1209,8 +1329,9 @@ int qlcnic_dump_fw(struct qlcnic_adapter *adapter) fw_dump->clr = 1; snprintf(mesg, sizeof(mesg), "FW_DUMP=%s", adapter->netdev->name); - dev_info(dev, "%s: Dump data %d bytes captured, template header size %d bytes\n", - adapter->netdev->name, fw_dump->size, tmpl_hdr->size); + netdev_info(adapter->netdev, + "Dump data %d bytes captured, template header size %d bytes\n", + fw_dump->size, fw_dump->tmpl_hdr_size); /* Send a udev event to notify availability of FW dump */ kobject_uevent_env(&dev->kobj, KOBJ_CHANGE, msg); diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c index 09acf15c3a56..14f748cbf0de 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c @@ -13,10 +13,9 @@ #define QLC_VF_MIN_TX_RATE 100 #define QLC_VF_MAX_TX_RATE 9999 #define QLC_MAC_OPCODE_MASK 0x7 -#define QLC_MAC_STAR_ADD 6 -#define QLC_MAC_STAR_DEL 7 #define QLC_VF_FLOOD_BIT BIT_16 #define QLC_FLOOD_MODE 0x5 +#define QLC_SRIOV_ALLOW_VLAN0 BIT_19 static int qlcnic_sriov_pf_get_vport_handle(struct qlcnic_adapter *, u8); @@ -337,8 +336,11 @@ static int qlcnic_sriov_pf_cfg_vlan_filtering(struct qlcnic_adapter *adapter, return err; cmd.req.arg[1] = 0x4; - if (enable) + if (enable) { cmd.req.arg[1] |= BIT_16; + if (qlcnic_84xx_check(adapter)) + cmd.req.arg[1] |= QLC_SRIOV_ALLOW_VLAN0; + } err = qlcnic_issue_cmd(adapter, &cmd); if (err) @@ -1206,13 +1208,6 @@ static int qlcnic_sriov_validate_cfg_macvlan(struct qlcnic_adapter *adapter, struct qlcnic_vport *vp = vf->vp; u8 op, new_op; - if (((cmd->req.arg[1] & QLC_MAC_OPCODE_MASK) == QLC_MAC_STAR_ADD) || - ((cmd->req.arg[1] & QLC_MAC_OPCODE_MASK) == QLC_MAC_STAR_DEL)) { - netdev_err(adapter->netdev, "MAC + any VLAN filter not allowed from VF %d\n", - vf->pci_func); - return -EINVAL; - } - if (!(cmd->req.arg[1] & BIT_8)) return -EINVAL; diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c index 3d64113a35af..448d156c3d08 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c @@ -350,33 +350,15 @@ static ssize_t qlcnic_sysfs_write_mem(struct file *filp, struct kobject *kobj, return size; } -static u32 qlcnic_get_pci_func_count(struct qlcnic_adapter *adapter) -{ - struct qlcnic_hardware_context *ahw = adapter->ahw; - u32 count = 0; - - if (!(adapter->flags & QLCNIC_ESWITCH_ENABLED)) - return ahw->total_nic_func; - - if (ahw->total_pci_func <= QLC_DEFAULT_VNIC_COUNT) - count = QLC_DEFAULT_VNIC_COUNT; - else - count = ahw->max_vnic_func; - - return count; -} - int qlcnic_is_valid_nic_func(struct qlcnic_adapter *adapter, u8 pci_func) { - u32 pci_func_count = qlcnic_get_pci_func_count(adapter); int i; - for (i = 0; i < pci_func_count; i++) { + for (i = 0; i < adapter->ahw->max_vnic_func; i++) { if (adapter->npars[i].pci_func == pci_func) return i; } - - return -1; + return -EINVAL; } static int validate_pm_config(struct qlcnic_adapter *adapter, @@ -464,23 +446,21 @@ static ssize_t qlcnic_sysfs_read_pm_config(struct file *filp, { struct device *dev = container_of(kobj, struct device, kobj); struct qlcnic_adapter *adapter = dev_get_drvdata(dev); - u32 pci_func_count = qlcnic_get_pci_func_count(adapter); struct qlcnic_pm_func_cfg *pm_cfg; - int i, pm_cfg_size; u8 pci_func; + u32 count; + int i; - pm_cfg_size = pci_func_count * sizeof(*pm_cfg); - if (size != pm_cfg_size) - return QL_STATUS_INVALID_PARAM; - - memset(buf, 0, pm_cfg_size); + memset(buf, 0, size); pm_cfg = (struct qlcnic_pm_func_cfg *)buf; - - for (i = 0; i < pci_func_count; i++) { + count = size / sizeof(struct qlcnic_pm_func_cfg); + for (i = 0; i < adapter->ahw->total_nic_func; i++) { pci_func = adapter->npars[i].pci_func; - if (!adapter->npars[i].active) + if (pci_func >= count) { + dev_dbg(dev, "%s: Total nic functions[%d], App sent function count[%d]\n", + __func__, adapter->ahw->total_nic_func, count); continue; - + } if (!adapter->npars[i].eswitch_status) continue; @@ -494,7 +474,6 @@ static ssize_t qlcnic_sysfs_read_pm_config(struct file *filp, static int validate_esw_config(struct qlcnic_adapter *adapter, struct qlcnic_esw_func_cfg *esw_cfg, int count) { - u32 pci_func_count = qlcnic_get_pci_func_count(adapter); struct qlcnic_hardware_context *ahw = adapter->ahw; int i, ret; u32 op_mode; @@ -507,7 +486,7 @@ static int validate_esw_config(struct qlcnic_adapter *adapter, for (i = 0; i < count; i++) { pci_func = esw_cfg[i].pci_func; - if (pci_func >= pci_func_count) + if (pci_func >= ahw->max_vnic_func) return QL_STATUS_INVALID_PARAM; if (adapter->ahw->op_mode == QLCNIC_MGMT_FUNC) @@ -642,23 +621,21 @@ static ssize_t qlcnic_sysfs_read_esw_config(struct file *file, { struct device *dev = container_of(kobj, struct device, kobj); struct qlcnic_adapter *adapter = dev_get_drvdata(dev); - u32 pci_func_count = qlcnic_get_pci_func_count(adapter); struct qlcnic_esw_func_cfg *esw_cfg; - size_t esw_cfg_size; - u8 i, pci_func; - - esw_cfg_size = pci_func_count * sizeof(*esw_cfg); - if (size != esw_cfg_size) - return QL_STATUS_INVALID_PARAM; + u8 pci_func; + u32 count; + int i; - memset(buf, 0, esw_cfg_size); + memset(buf, 0, size); esw_cfg = (struct qlcnic_esw_func_cfg *)buf; - - for (i = 0; i < pci_func_count; i++) { + count = size / sizeof(struct qlcnic_esw_func_cfg); + for (i = 0; i < adapter->ahw->total_nic_func; i++) { pci_func = adapter->npars[i].pci_func; - if (!adapter->npars[i].active) + if (pci_func >= count) { + dev_dbg(dev, "%s: Total nic functions[%d], App sent function count[%d]\n", + __func__, adapter->ahw->total_nic_func, count); continue; - + } if (!adapter->npars[i].eswitch_status) continue; @@ -741,23 +718,24 @@ static ssize_t qlcnic_sysfs_read_npar_config(struct file *file, { struct device *dev = container_of(kobj, struct device, kobj); struct qlcnic_adapter *adapter = dev_get_drvdata(dev); - u32 pci_func_count = qlcnic_get_pci_func_count(adapter); struct qlcnic_npar_func_cfg *np_cfg; struct qlcnic_info nic_info; - size_t np_cfg_size; int i, ret; - - np_cfg_size = pci_func_count * sizeof(*np_cfg); - if (size != np_cfg_size) - return QL_STATUS_INVALID_PARAM; + u32 count; memset(&nic_info, 0, sizeof(struct qlcnic_info)); - memset(buf, 0, np_cfg_size); + memset(buf, 0, size); np_cfg = (struct qlcnic_npar_func_cfg *)buf; - for (i = 0; i < pci_func_count; i++) { + count = size / sizeof(struct qlcnic_npar_func_cfg); + for (i = 0; i < adapter->ahw->total_nic_func; i++) { if (qlcnic_is_valid_nic_func(adapter, i) < 0) continue; + if (adapter->npars[i].pci_func >= count) { + dev_dbg(dev, "%s: Total nic functions[%d], App sent function count[%d]\n", + __func__, adapter->ahw->total_nic_func, count); + continue; + } ret = qlcnic_get_nic_info(adapter, &nic_info, i); if (ret) return ret; @@ -783,7 +761,6 @@ static ssize_t qlcnic_sysfs_get_port_stats(struct file *file, { struct device *dev = container_of(kobj, struct device, kobj); struct qlcnic_adapter *adapter = dev_get_drvdata(dev); - u32 pci_func_count = qlcnic_get_pci_func_count(adapter); struct qlcnic_esw_statistics port_stats; int ret; @@ -793,7 +770,7 @@ static ssize_t qlcnic_sysfs_get_port_stats(struct file *file, if (size != sizeof(struct qlcnic_esw_statistics)) return QL_STATUS_INVALID_PARAM; - if (offset >= pci_func_count) + if (offset >= adapter->ahw->max_vnic_func) return QL_STATUS_INVALID_PARAM; memset(&port_stats, 0, size); @@ -884,13 +861,12 @@ static ssize_t qlcnic_sysfs_clear_port_stats(struct file *file, struct device *dev = container_of(kobj, struct device, kobj); struct qlcnic_adapter *adapter = dev_get_drvdata(dev); - u32 pci_func_count = qlcnic_get_pci_func_count(adapter); int ret; if (qlcnic_83xx_check(adapter)) return QLC_STATUS_UNSUPPORTED_CMD; - if (offset >= pci_func_count) + if (offset >= adapter->ahw->max_vnic_func) return QL_STATUS_INVALID_PARAM; ret = qlcnic_clear_esw_stats(adapter, QLCNIC_STATS_PORT, offset, @@ -914,17 +890,12 @@ static ssize_t qlcnic_sysfs_read_pci_config(struct file *file, { struct device *dev = container_of(kobj, struct device, kobj); struct qlcnic_adapter *adapter = dev_get_drvdata(dev); - u32 pci_func_count = qlcnic_get_pci_func_count(adapter); struct qlcnic_pci_func_cfg *pci_cfg; struct qlcnic_pci_info *pci_info; - size_t pci_cfg_sz; int i, ret; + u32 count; - pci_cfg_sz = pci_func_count * sizeof(*pci_cfg); - if (size != pci_cfg_sz) - return QL_STATUS_INVALID_PARAM; - - pci_info = kcalloc(pci_func_count, sizeof(*pci_info), GFP_KERNEL); + pci_info = kcalloc(size, sizeof(*pci_info), GFP_KERNEL); if (!pci_info) return -ENOMEM; @@ -935,7 +906,8 @@ static ssize_t qlcnic_sysfs_read_pci_config(struct file *file, } pci_cfg = (struct qlcnic_pci_func_cfg *)buf; - for (i = 0; i < pci_func_count; i++) { + count = size / sizeof(struct qlcnic_pci_func_cfg); + for (i = 0; i < count; i++) { pci_cfg[i].pci_func = pci_info[i].id; pci_cfg[i].func_type = pci_info[i].type; pci_cfg[i].func_state = 0; diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_main.c b/drivers/net/ethernet/qlogic/qlge/qlge_main.c index ce2cfddbed50..adf87d26e68f 100644 --- a/drivers/net/ethernet/qlogic/qlge/qlge_main.c +++ b/drivers/net/ethernet/qlogic/qlge/qlge_main.c @@ -3331,24 +3331,16 @@ static void ql_enable_msix(struct ql_adapter *qdev) for (i = 0; i < qdev->intr_count; i++) qdev->msi_x_entry[i].entry = i; - /* Loop to get our vectors. We start with - * what we want and settle for what we get. - */ - do { - err = pci_enable_msix(qdev->pdev, - qdev->msi_x_entry, qdev->intr_count); - if (err > 0) - qdev->intr_count = err; - } while (err > 0); - + err = pci_enable_msix_range(qdev->pdev, qdev->msi_x_entry, + 1, qdev->intr_count); if (err < 0) { kfree(qdev->msi_x_entry); qdev->msi_x_entry = NULL; netif_warn(qdev, ifup, qdev->ndev, "MSI-X Enable failed, trying MSI.\n"); - qdev->intr_count = 1; qlge_irq_type = MSI_IRQ; - } else if (err == 0) { + } else { + qdev->intr_count = err; set_bit(QL_MSIX_ENABLED, &qdev->flags); netif_info(qdev, ifup, qdev->ndev, "MSI-X Enabled, got %d vectors.\n", diff --git a/drivers/net/ethernet/realtek/8139cp.c b/drivers/net/ethernet/realtek/8139cp.c index 737c1a881f78..a3c1daa7ad5c 100644 --- a/drivers/net/ethernet/realtek/8139cp.c +++ b/drivers/net/ethernet/realtek/8139cp.c @@ -899,7 +899,7 @@ out_unlock: return NETDEV_TX_OK; out_dma_error: - kfree_skb(skb); + dev_kfree_skb_any(skb); cp->dev->stats.tx_dropped++; goto out_unlock; } diff --git a/drivers/net/ethernet/realtek/8139too.c b/drivers/net/ethernet/realtek/8139too.c index da5972eefdd2..8cb2f357026e 100644 --- a/drivers/net/ethernet/realtek/8139too.c +++ b/drivers/net/ethernet/realtek/8139too.c @@ -1717,9 +1717,9 @@ static netdev_tx_t rtl8139_start_xmit (struct sk_buff *skb, if (len < ETH_ZLEN) memset(tp->tx_buf[entry], 0, ETH_ZLEN); skb_copy_and_csum_dev(skb, tp->tx_buf[entry]); - dev_kfree_skb(skb); + dev_kfree_skb_any(skb); } else { - dev_kfree_skb(skb); + dev_kfree_skb_any(skb); dev->stats.tx_dropped++; return NETDEV_TX_OK; } diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index 91a67ae8f17b..cf947337e0d6 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -5834,7 +5834,7 @@ static void rtl8169_tx_clear_range(struct rtl8169_private *tp, u32 start, tp->TxDescArray + entry); if (skb) { tp->dev->stats.tx_dropped++; - dev_kfree_skb(skb); + dev_kfree_skb_any(skb); tx_skb->skb = NULL; } } @@ -6059,7 +6059,7 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb, err_dma_1: rtl8169_unmap_tx_skb(d, tp->tx_skb + entry, txd); err_dma_0: - dev_kfree_skb(skb); + dev_kfree_skb_any(skb); err_update_stats: dev->stats.tx_dropped++; return NETDEV_TX_OK; @@ -6142,7 +6142,7 @@ static void rtl_tx(struct net_device *dev, struct rtl8169_private *tp) tp->tx_stats.packets++; tp->tx_stats.bytes += tx_skb->skb->len; u64_stats_update_end(&tp->tx_stats.syncp); - dev_kfree_skb(tx_skb->skb); + dev_kfree_skb_any(tx_skb->skb); tx_skb->skb = NULL; } dirty_tx++; @@ -7118,6 +7118,8 @@ rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) } mutex_init(&tp->wk.mutex); + u64_stats_init(&tp->rx_stats.syncp); + u64_stats_init(&tp->tx_stats.syncp); /* Get MAC address */ for (i = 0; i < ETH_ALEN; i++) diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index 040cb94e8219..b1e6554f44bc 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -1,8 +1,8 @@ /* SuperH Ethernet device driver * * Copyright (C) 2006-2012 Nobuhiro Iwamatsu - * Copyright (C) 2008-2013 Renesas Solutions Corp. - * Copyright (C) 2013 Cogent Embedded, Inc. + * Copyright (C) 2008-2014 Renesas Solutions Corp. + * Copyright (C) 2013-2014 Cogent Embedded, Inc. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, @@ -27,6 +27,10 @@ #include <linux/platform_device.h> #include <linux/mdio-bitbang.h> #include <linux/netdevice.h> +#include <linux/of.h> +#include <linux/of_device.h> +#include <linux/of_irq.h> +#include <linux/of_net.h> #include <linux/phy.h> #include <linux/cache.h> #include <linux/io.h> @@ -2098,8 +2102,8 @@ static int sh_eth_start_xmit(struct sk_buff *skb, struct net_device *ndev) skb->len + 2); txdesc->addr = dma_map_single(&ndev->dev, skb->data, skb->len, DMA_TO_DEVICE); - if (skb->len < ETHERSMALL) - txdesc->buffer_length = ETHERSMALL; + if (skb->len < ETH_ZLEN) + txdesc->buffer_length = ETH_ZLEN; else txdesc->buffer_length = skb->len; @@ -2710,6 +2714,54 @@ static const struct net_device_ops sh_eth_netdev_ops_tsu = { .ndo_change_mtu = eth_change_mtu, }; +#ifdef CONFIG_OF +static struct sh_eth_plat_data *sh_eth_parse_dt(struct device *dev) +{ + struct device_node *np = dev->of_node; + struct sh_eth_plat_data *pdata; + struct device_node *phy; + const char *mac_addr; + + pdata = devm_kzalloc(dev, sizeof(*pdata), GFP_KERNEL); + if (!pdata) + return NULL; + + pdata->phy_interface = of_get_phy_mode(np); + + phy = of_parse_phandle(np, "phy-handle", 0); + if (of_property_read_u32(phy, "reg", &pdata->phy)) + return NULL; + pdata->phy_irq = irq_of_parse_and_map(phy, 0); + + mac_addr = of_get_mac_address(np); + if (mac_addr) + memcpy(pdata->mac_addr, mac_addr, ETH_ALEN); + + pdata->no_ether_link = + of_property_read_bool(np, "renesas,no-ether-link"); + pdata->ether_link_active_low = + of_property_read_bool(np, "renesas,ether-link-active-low"); + + return pdata; +} + +static const struct of_device_id sh_eth_match_table[] = { + { .compatible = "renesas,gether-r8a7740", .data = &r8a7740_data }, + { .compatible = "renesas,ether-r8a7778", .data = &r8a777x_data }, + { .compatible = "renesas,ether-r8a7779", .data = &r8a777x_data }, + { .compatible = "renesas,ether-r8a7790", .data = &r8a779x_data }, + { .compatible = "renesas,ether-r8a7791", .data = &r8a779x_data }, + { .compatible = "renesas,ether-r7s72100", .data = &r7s72100_data }, + { } +}; +MODULE_DEVICE_TABLE(of, sh_eth_match_table); +#else +static inline struct sh_eth_plat_data *sh_eth_parse_dt(struct device *dev) +{ + return NULL; +} +#endif + static int sh_eth_drv_probe(struct platform_device *pdev) { int ret, devno = 0; @@ -2763,6 +2815,8 @@ static int sh_eth_drv_probe(struct platform_device *pdev) pm_runtime_enable(&pdev->dev); pm_runtime_resume(&pdev->dev); + if (pdev->dev.of_node) + pd = sh_eth_parse_dt(&pdev->dev); if (!pd) { dev_err(&pdev->dev, "no platform data\n"); ret = -EINVAL; @@ -2778,7 +2832,15 @@ static int sh_eth_drv_probe(struct platform_device *pdev) mdp->ether_link_active_low = pd->ether_link_active_low; /* set cpu data */ - mdp->cd = (struct sh_eth_cpu_data *)id->driver_data; + if (id) { + mdp->cd = (struct sh_eth_cpu_data *)id->driver_data; + } else { + const struct of_device_id *match; + + match = of_match_device(of_match_ptr(sh_eth_match_table), + &pdev->dev); + mdp->cd = (struct sh_eth_cpu_data *)match->data; + } mdp->reg_offset = sh_eth_get_register_offset(mdp->cd->register_type); sh_eth_set_default_cpu_data(mdp->cd); @@ -2920,6 +2982,7 @@ static struct platform_driver sh_eth_driver = { .driver = { .name = CARDNAME, .pm = SH_ETH_PM_OPS, + .of_match_table = of_match_ptr(sh_eth_match_table), }, }; diff --git a/drivers/net/ethernet/renesas/sh_eth.h b/drivers/net/ethernet/renesas/sh_eth.h index 6075915b88ec..d55e37cd5fec 100644 --- a/drivers/net/ethernet/renesas/sh_eth.h +++ b/drivers/net/ethernet/renesas/sh_eth.h @@ -27,8 +27,7 @@ #define RX_RING_MIN 64 #define TX_RING_MAX 1024 #define RX_RING_MAX 1024 -#define ETHERSMALL 60 -#define PKT_BUF_SZ 1538 +#define PKT_BUF_SZ 1538 #define SH_ETH_TSU_TIMEOUT_MS 500 #define SH_ETH_TSU_CAM_ENTRIES 32 diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c index 174a92f5fe51..eb75675f6e32 100644 --- a/drivers/net/ethernet/sfc/ef10.c +++ b/drivers/net/ethernet/sfc/ef10.c @@ -162,8 +162,8 @@ static int efx_ef10_get_mac_address(struct efx_nic *efx, u8 *mac_address) if (outlen < MC_CMD_GET_MAC_ADDRESSES_OUT_LEN) return -EIO; - memcpy(mac_address, - MCDI_PTR(outbuf, GET_MAC_ADDRESSES_OUT_MAC_ADDR_BASE), ETH_ALEN); + ether_addr_copy(mac_address, + MCDI_PTR(outbuf, GET_MAC_ADDRESSES_OUT_MAC_ADDR_BASE)); return 0; } @@ -172,8 +172,8 @@ static int efx_ef10_probe(struct efx_nic *efx) struct efx_ef10_nic_data *nic_data; int i, rc; - /* We can have one VI for each 8K region. However we need - * multiple TX queues per channel. + /* We can have one VI for each 8K region. However, until we + * use TX option descriptors we need two TX queues per channel. */ efx->max_channels = min_t(unsigned int, @@ -3145,12 +3145,10 @@ static void efx_ef10_filter_sync_rx_mode(struct efx_nic *efx) table->dev_uc_count = -1; } else { table->dev_uc_count = 1 + netdev_uc_count(net_dev); - memcpy(table->dev_uc_list[0].addr, net_dev->dev_addr, - ETH_ALEN); + ether_addr_copy(table->dev_uc_list[0].addr, net_dev->dev_addr); i = 1; netdev_for_each_uc_addr(uc, net_dev) { - memcpy(table->dev_uc_list[i].addr, - uc->addr, ETH_ALEN); + ether_addr_copy(table->dev_uc_list[i].addr, uc->addr); i++; } } @@ -3162,8 +3160,7 @@ static void efx_ef10_filter_sync_rx_mode(struct efx_nic *efx) eth_broadcast_addr(table->dev_mc_list[0].addr); i = 1; netdev_for_each_mc_addr(mc, net_dev) { - memcpy(table->dev_mc_list[i].addr, - mc->addr, ETH_ALEN); + ether_addr_copy(table->dev_mc_list[i].addr, mc->addr); i++; } } diff --git a/drivers/net/ethernet/sfc/ef10_regs.h b/drivers/net/ethernet/sfc/ef10_regs.h index 207ac9a1e3de..62a55dde61d5 100644 --- a/drivers/net/ethernet/sfc/ef10_regs.h +++ b/drivers/net/ethernet/sfc/ef10_regs.h @@ -227,36 +227,6 @@ #define ESF_DZ_RX_KER_BUF_ADDR_LBN 0 #define ESF_DZ_RX_KER_BUF_ADDR_WIDTH 48 -/* RX_USER_DESC */ -#define ESF_DZ_RX_USR_RESERVED_LBN 62 -#define ESF_DZ_RX_USR_RESERVED_WIDTH 2 -#define ESF_DZ_RX_USR_BYTE_CNT_LBN 48 -#define ESF_DZ_RX_USR_BYTE_CNT_WIDTH 14 -#define ESF_DZ_RX_USR_BUF_PAGE_SIZE_LBN 44 -#define ESF_DZ_RX_USR_BUF_PAGE_SIZE_WIDTH 4 -#define ESE_DZ_USR_BUF_PAGE_SZ_4MB 10 -#define ESE_DZ_USR_BUF_PAGE_SZ_1MB 8 -#define ESE_DZ_USR_BUF_PAGE_SZ_64KB 4 -#define ESE_DZ_USR_BUF_PAGE_SZ_4KB 0 -#define ESF_DZ_RX_USR_BUF_ID_OFFSET_LBN 0 -#define ESF_DZ_RX_USR_BUF_ID_OFFSET_WIDTH 44 -#define ESF_DZ_RX_USR_4KBPS_BUF_ID_LBN 12 -#define ESF_DZ_RX_USR_4KBPS_BUF_ID_WIDTH 32 -#define ESF_DZ_RX_USR_64KBPS_BUF_ID_LBN 16 -#define ESF_DZ_RX_USR_64KBPS_BUF_ID_WIDTH 28 -#define ESF_DZ_RX_USR_1MBPS_BUF_ID_LBN 20 -#define ESF_DZ_RX_USR_1MBPS_BUF_ID_WIDTH 24 -#define ESF_DZ_RX_USR_4MBPS_BUF_ID_LBN 22 -#define ESF_DZ_RX_USR_4MBPS_BUF_ID_WIDTH 22 -#define ESF_DZ_RX_USR_4MBPS_BYTE_OFFSET_LBN 0 -#define ESF_DZ_RX_USR_4MBPS_BYTE_OFFSET_WIDTH 22 -#define ESF_DZ_RX_USR_1MBPS_BYTE_OFFSET_LBN 0 -#define ESF_DZ_RX_USR_1MBPS_BYTE_OFFSET_WIDTH 20 -#define ESF_DZ_RX_USR_64KBPS_BYTE_OFFSET_LBN 0 -#define ESF_DZ_RX_USR_64KBPS_BYTE_OFFSET_WIDTH 16 -#define ESF_DZ_RX_USR_4KBPS_BYTE_OFFSET_LBN 0 -#define ESF_DZ_RX_USR_4KBPS_BYTE_OFFSET_WIDTH 12 - /* TX_CSUM_TSTAMP_DESC */ #define ESF_DZ_TX_DESC_IS_OPT_LBN 63 #define ESF_DZ_TX_DESC_IS_OPT_WIDTH 1 @@ -338,37 +308,6 @@ #define ESF_DZ_TX_TSO_TCP_SEQNO_LBN 0 #define ESF_DZ_TX_TSO_TCP_SEQNO_WIDTH 32 -/* TX_USER_DESC */ -#define ESF_DZ_TX_USR_TYPE_LBN 63 -#define ESF_DZ_TX_USR_TYPE_WIDTH 1 -#define ESF_DZ_TX_USR_CONT_LBN 62 -#define ESF_DZ_TX_USR_CONT_WIDTH 1 -#define ESF_DZ_TX_USR_BYTE_CNT_LBN 48 -#define ESF_DZ_TX_USR_BYTE_CNT_WIDTH 14 -#define ESF_DZ_TX_USR_BUF_PAGE_SIZE_LBN 44 -#define ESF_DZ_TX_USR_BUF_PAGE_SIZE_WIDTH 4 -#define ESE_DZ_USR_BUF_PAGE_SZ_4MB 10 -#define ESE_DZ_USR_BUF_PAGE_SZ_1MB 8 -#define ESE_DZ_USR_BUF_PAGE_SZ_64KB 4 -#define ESE_DZ_USR_BUF_PAGE_SZ_4KB 0 -#define ESF_DZ_TX_USR_BUF_ID_OFFSET_LBN 0 -#define ESF_DZ_TX_USR_BUF_ID_OFFSET_WIDTH 44 -#define ESF_DZ_TX_USR_4KBPS_BUF_ID_LBN 12 -#define ESF_DZ_TX_USR_4KBPS_BUF_ID_WIDTH 32 -#define ESF_DZ_TX_USR_64KBPS_BUF_ID_LBN 16 -#define ESF_DZ_TX_USR_64KBPS_BUF_ID_WIDTH 28 -#define ESF_DZ_TX_USR_1MBPS_BUF_ID_LBN 20 -#define ESF_DZ_TX_USR_1MBPS_BUF_ID_WIDTH 24 -#define ESF_DZ_TX_USR_4MBPS_BUF_ID_LBN 22 -#define ESF_DZ_TX_USR_4MBPS_BUF_ID_WIDTH 22 -#define ESF_DZ_TX_USR_4MBPS_BYTE_OFFSET_LBN 0 -#define ESF_DZ_TX_USR_4MBPS_BYTE_OFFSET_WIDTH 22 -#define ESF_DZ_TX_USR_1MBPS_BYTE_OFFSET_LBN 0 -#define ESF_DZ_TX_USR_1MBPS_BYTE_OFFSET_WIDTH 20 -#define ESF_DZ_TX_USR_64KBPS_BYTE_OFFSET_LBN 0 -#define ESF_DZ_TX_USR_64KBPS_BYTE_OFFSET_WIDTH 16 -#define ESF_DZ_TX_USR_4KBPS_BYTE_OFFSET_LBN 0 -#define ESF_DZ_TX_USR_4KBPS_BYTE_OFFSET_WIDTH 12 /*************************************************************************/ /* TX_DESC_UPD_REG: Transmit descriptor update register. diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index 83d464347021..52589f6a8beb 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -503,8 +503,6 @@ static int efx_probe_channel(struct efx_channel *channel) goto fail; } - channel->n_rx_frm_trunc = 0; - return 0; fail: @@ -1014,7 +1012,7 @@ static int efx_probe_port(struct efx_nic *efx) return rc; /* Initialise MAC address to permanent address */ - memcpy(efx->net_dev->dev_addr, efx->net_dev->perm_addr, ETH_ALEN); + ether_addr_copy(efx->net_dev->dev_addr, efx->net_dev->perm_addr); return 0; } @@ -1346,20 +1344,23 @@ static int efx_probe_interrupts(struct efx_nic *efx) for (i = 0; i < n_channels; i++) xentries[i].entry = i; - rc = pci_enable_msix(efx->pci_dev, xentries, n_channels); - if (rc > 0) { + rc = pci_enable_msix_range(efx->pci_dev, + xentries, 1, n_channels); + if (rc < 0) { + /* Fall back to single channel MSI */ + efx->interrupt_mode = EFX_INT_MODE_MSI; + netif_err(efx, drv, efx->net_dev, + "could not enable MSI-X\n"); + } else if (rc < n_channels) { netif_err(efx, drv, efx->net_dev, "WARNING: Insufficient MSI-X vectors" " available (%d < %u).\n", rc, n_channels); netif_err(efx, drv, efx->net_dev, "WARNING: Performance may be reduced.\n"); - EFX_BUG_ON_PARANOID(rc >= n_channels); n_channels = rc; - rc = pci_enable_msix(efx->pci_dev, xentries, - n_channels); } - if (rc == 0) { + if (rc > 0) { efx->n_channels = n_channels; if (n_channels > extra_channels) n_channels -= extra_channels; @@ -1375,11 +1376,6 @@ static int efx_probe_interrupts(struct efx_nic *efx) for (i = 0; i < efx->n_channels; i++) efx_get_channel(efx, i)->irq = xentries[i].vector; - } else { - /* Fall back to single channel MSI */ - efx->interrupt_mode = EFX_INT_MODE_MSI; - netif_err(efx, drv, efx->net_dev, - "could not enable MSI-X\n"); } } @@ -2115,7 +2111,7 @@ static int efx_set_mac_address(struct net_device *net_dev, void *data) { struct efx_nic *efx = netdev_priv(net_dev); struct sockaddr *addr = data; - char *new_addr = addr->sa_data; + u8 *new_addr = addr->sa_data; if (!is_valid_ether_addr(new_addr)) { netif_err(efx, drv, efx->net_dev, @@ -2124,7 +2120,7 @@ static int efx_set_mac_address(struct net_device *net_dev, void *data) return -EADDRNOTAVAIL; } - memcpy(net_dev->dev_addr, new_addr, net_dev->addr_len); + ether_addr_copy(net_dev->dev_addr, new_addr); efx_sriov_mac_address_changed(efx); /* Reconfigure the MAC */ @@ -3273,6 +3269,6 @@ module_exit(efx_exit_module); MODULE_AUTHOR("Solarflare Communications and " "Michael Brown <mbrown@fensystems.co.uk>"); -MODULE_DESCRIPTION("Solarflare Communications network driver"); +MODULE_DESCRIPTION("Solarflare network driver"); MODULE_LICENSE("GPL"); MODULE_DEVICE_TABLE(pci, efx_pci_table); diff --git a/drivers/net/ethernet/sfc/efx.h b/drivers/net/ethernet/sfc/efx.h index dbd7b78fe01c..99032581336f 100644 --- a/drivers/net/ethernet/sfc/efx.h +++ b/drivers/net/ethernet/sfc/efx.h @@ -14,7 +14,7 @@ #include "net_driver.h" #include "filter.h" -/* Solarstorm controllers use BAR 0 for I/O space and BAR 2(&3) for memory */ +/* All controllers use BAR 0 for I/O space and BAR 2(&3) for memory */ #define EFX_MEM_BAR 2 /* TX */ diff --git a/drivers/net/ethernet/sfc/ethtool.c b/drivers/net/ethernet/sfc/ethtool.c index 229428915aa8..0de8b07c24c2 100644 --- a/drivers/net/ethernet/sfc/ethtool.c +++ b/drivers/net/ethernet/sfc/ethtool.c @@ -251,6 +251,9 @@ static void efx_fill_test(unsigned int test_index, u8 *strings, u64 *data, * @test_index: Starting index of the test * @strings: Ethtool strings, or %NULL * @data: Ethtool test results, or %NULL + * + * Fill in a block of loopback self-test entries. Return new test + * index. */ static int efx_fill_loopback_test(struct efx_nic *efx, struct efx_loopback_self_tests *lb_tests, @@ -290,6 +293,12 @@ static int efx_fill_loopback_test(struct efx_nic *efx, * @tests: Efx self-test results structure, or %NULL * @strings: Ethtool strings, or %NULL * @data: Ethtool test results, or %NULL + * + * Get self-test number of strings, strings, and/or test results. + * Return number of strings (== number of test results). + * + * The reason for merging these three functions is to make sure that + * they can never be inconsistent. */ static int efx_ethtool_fill_self_tests(struct efx_nic *efx, struct efx_self_tests *tests, @@ -444,7 +453,7 @@ static void efx_ethtool_self_test(struct net_device *net_dev, { struct efx_nic *efx = netdev_priv(net_dev); struct efx_self_tests *efx_tests; - int already_up; + bool already_up; int rc = -ENOMEM; efx_tests = kzalloc(sizeof(*efx_tests), GFP_KERNEL); @@ -452,8 +461,8 @@ static void efx_ethtool_self_test(struct net_device *net_dev, goto fail; if (efx->state != STATE_READY) { - rc = -EIO; - goto fail1; + rc = -EBUSY; + goto out; } netif_info(efx, drv, efx->net_dev, "starting %sline testing\n", @@ -466,7 +475,7 @@ static void efx_ethtool_self_test(struct net_device *net_dev, if (rc) { netif_err(efx, drv, efx->net_dev, "failed opening device.\n"); - goto fail1; + goto out; } } @@ -479,8 +488,7 @@ static void efx_ethtool_self_test(struct net_device *net_dev, rc == 0 ? "passed" : "failed", (test->flags & ETH_TEST_FL_OFFLINE) ? "off" : "on"); -fail1: - /* Fill ethtool results structures */ +out: efx_ethtool_fill_self_tests(efx, efx_tests, NULL, data); kfree(efx_tests); fail: @@ -691,7 +699,6 @@ static void efx_ethtool_get_pauseparam(struct net_device *net_dev, pause->autoneg = !!(efx->wanted_fc & EFX_FC_AUTO); } - static void efx_ethtool_get_wol(struct net_device *net_dev, struct ethtool_wolinfo *wol) { @@ -720,7 +727,7 @@ static int efx_ethtool_reset(struct net_device *net_dev, u32 *flags) } /* MAC address mask including only I/G bit */ -static const u8 mac_addr_ig_mask[ETH_ALEN] = { 0x01, 0, 0, 0, 0, 0 }; +static const u8 mac_addr_ig_mask[ETH_ALEN] __aligned(2) = {0x01, 0, 0, 0, 0, 0}; #define IP4_ADDR_FULL_MASK ((__force __be32)~0) #define PORT_FULL_MASK ((__force __be16)~0) @@ -780,16 +787,16 @@ static int efx_ethtool_get_class_rule(struct efx_nic *efx, rule->flow_type = ETHER_FLOW; if (spec.match_flags & (EFX_FILTER_MATCH_LOC_MAC | EFX_FILTER_MATCH_LOC_MAC_IG)) { - memcpy(mac_entry->h_dest, spec.loc_mac, ETH_ALEN); + ether_addr_copy(mac_entry->h_dest, spec.loc_mac); if (spec.match_flags & EFX_FILTER_MATCH_LOC_MAC) - memset(mac_mask->h_dest, ~0, ETH_ALEN); + eth_broadcast_addr(mac_mask->h_dest); else - memcpy(mac_mask->h_dest, mac_addr_ig_mask, - ETH_ALEN); + ether_addr_copy(mac_mask->h_dest, + mac_addr_ig_mask); } if (spec.match_flags & EFX_FILTER_MATCH_REM_MAC) { - memcpy(mac_entry->h_source, spec.rem_mac, ETH_ALEN); - memset(mac_mask->h_source, ~0, ETH_ALEN); + ether_addr_copy(mac_entry->h_source, spec.rem_mac); + eth_broadcast_addr(mac_mask->h_source); } if (spec.match_flags & EFX_FILTER_MATCH_ETHER_TYPE) { mac_entry->h_proto = spec.ether_type; @@ -961,13 +968,13 @@ static int efx_ethtool_set_class_rule(struct efx_nic *efx, spec.match_flags |= EFX_FILTER_MATCH_LOC_MAC; else return -EINVAL; - memcpy(spec.loc_mac, mac_entry->h_dest, ETH_ALEN); + ether_addr_copy(spec.loc_mac, mac_entry->h_dest); } if (!is_zero_ether_addr(mac_mask->h_source)) { if (!is_broadcast_ether_addr(mac_mask->h_source)) return -EINVAL; spec.match_flags |= EFX_FILTER_MATCH_REM_MAC; - memcpy(spec.rem_mac, mac_entry->h_source, ETH_ALEN); + ether_addr_copy(spec.rem_mac, mac_entry->h_source); } if (mac_mask->h_proto) { if (mac_mask->h_proto != ETHER_TYPE_FULL_MASK) diff --git a/drivers/net/ethernet/sfc/falcon.c b/drivers/net/ethernet/sfc/falcon.c index 18d6f761f4d0..8ec20b713cc6 100644 --- a/drivers/net/ethernet/sfc/falcon.c +++ b/drivers/net/ethernet/sfc/falcon.c @@ -422,7 +422,6 @@ static inline void falcon_irq_ack_a1(struct efx_nic *efx) efx_readd(efx, ®, FR_AA_WORK_AROUND_BROKEN_PCI_READS); } - static irqreturn_t falcon_legacy_interrupt_a1(int irq, void *dev_id) { struct efx_nic *efx = dev_id; @@ -467,6 +466,7 @@ static irqreturn_t falcon_legacy_interrupt_a1(int irq, void *dev_id) efx_schedule_channel_irq(efx_get_channel(efx, 1)); return IRQ_HANDLED; } + /************************************************************************** * * RSS @@ -1358,6 +1358,7 @@ static void falcon_reconfigure_mac_wrapper(struct efx_nic *efx) case 100: link_speed = 1; break; default: link_speed = 0; break; } + /* MAC_LINK_STATUS controls MAC backpressure but doesn't work * as advertised. Disable to ensure packets are not * indefinitely held and TX queue can be flushed at any point @@ -2182,7 +2183,7 @@ static int falcon_probe_nvconfig(struct efx_nic *efx) } /* Read the MAC addresses */ - memcpy(efx->net_dev->perm_addr, nvconfig->mac_address[0], ETH_ALEN); + ether_addr_copy(efx->net_dev->perm_addr, nvconfig->mac_address[0]); netif_dbg(efx, probe, efx->net_dev, "PHY is %d phy_id %d\n", efx->phy_type, efx->mdio.prtad); @@ -2868,4 +2869,3 @@ const struct efx_nic_type falcon_b0_nic_type = { .mcdi_max_ver = -1, .max_rx_ip_filters = FR_BZ_RX_FILTER_TBL0_ROWS, }; - diff --git a/drivers/net/ethernet/sfc/farch.c b/drivers/net/ethernet/sfc/farch.c index f72489a105ca..aa1b169f45ec 100644 --- a/drivers/net/ethernet/sfc/farch.c +++ b/drivers/net/ethernet/sfc/farch.c @@ -311,7 +311,6 @@ static inline void efx_farch_push_tx_desc(struct efx_tx_queue *tx_queue, */ void efx_farch_tx_write(struct efx_tx_queue *tx_queue) { - struct efx_tx_buffer *buffer; efx_qword_t *txd; unsigned write_ptr; @@ -1609,7 +1608,6 @@ irqreturn_t efx_farch_msi_interrupt(int irq, void *dev_id) return IRQ_HANDLED; } - /* Setup RSS indirection table. * This maps from the hash value of the packet to RXQ */ diff --git a/drivers/net/ethernet/sfc/filter.h b/drivers/net/ethernet/sfc/filter.h index 3ef298d3c47e..d0ed7f71ea7e 100644 --- a/drivers/net/ethernet/sfc/filter.h +++ b/drivers/net/ethernet/sfc/filter.h @@ -243,7 +243,7 @@ static inline int efx_filter_set_eth_local(struct efx_filter_spec *spec, } if (addr != NULL) { spec->match_flags |= EFX_FILTER_MATCH_LOC_MAC; - memcpy(spec->loc_mac, addr, ETH_ALEN); + ether_addr_copy(spec->loc_mac, addr); } return 0; } diff --git a/drivers/net/ethernet/sfc/mcdi.c b/drivers/net/ethernet/sfc/mcdi.c index eb59abb57e85..7bd4b14bf3b3 100644 --- a/drivers/net/ethernet/sfc/mcdi.c +++ b/drivers/net/ethernet/sfc/mcdi.c @@ -1187,6 +1187,9 @@ int efx_mcdi_get_board_cfg(struct efx_nic *efx, u8 *mac_address, int rc; BUILD_BUG_ON(MC_CMD_GET_BOARD_CFG_IN_LEN != 0); + /* we need __aligned(2) for ether_addr_copy */ + BUILD_BUG_ON(MC_CMD_GET_BOARD_CFG_OUT_MAC_ADDR_BASE_PORT0_OFST & 1); + BUILD_BUG_ON(MC_CMD_GET_BOARD_CFG_OUT_MAC_ADDR_BASE_PORT1_OFST & 1); rc = efx_mcdi_rpc(efx, MC_CMD_GET_BOARD_CFG, NULL, 0, outbuf, sizeof(outbuf), &outlen); @@ -1199,11 +1202,10 @@ int efx_mcdi_get_board_cfg(struct efx_nic *efx, u8 *mac_address, } if (mac_address) - memcpy(mac_address, - port_num ? - MCDI_PTR(outbuf, GET_BOARD_CFG_OUT_MAC_ADDR_BASE_PORT1) : - MCDI_PTR(outbuf, GET_BOARD_CFG_OUT_MAC_ADDR_BASE_PORT0), - ETH_ALEN); + ether_addr_copy(mac_address, + port_num ? + MCDI_PTR(outbuf, GET_BOARD_CFG_OUT_MAC_ADDR_BASE_PORT1) : + MCDI_PTR(outbuf, GET_BOARD_CFG_OUT_MAC_ADDR_BASE_PORT0)); if (fw_subtype_list) { for (i = 0; i < MCDI_VAR_ARRAY_LEN(outlen, @@ -1532,7 +1534,7 @@ static int efx_mcdi_wol_filter_set(struct efx_nic *efx, u32 type, MCDI_SET_DWORD(inbuf, WOL_FILTER_SET_IN_WOL_TYPE, type); MCDI_SET_DWORD(inbuf, WOL_FILTER_SET_IN_FILTER_MODE, MC_CMD_FILTER_MODE_SIMPLE); - memcpy(MCDI_PTR(inbuf, WOL_FILTER_SET_IN_MAGIC_MAC), mac, ETH_ALEN); + ether_addr_copy(MCDI_PTR(inbuf, WOL_FILTER_SET_IN_MAGIC_MAC), mac); rc = efx_mcdi_rpc(efx, MC_CMD_WOL_FILTER_SET, inbuf, sizeof(inbuf), outbuf, sizeof(outbuf), &outlen); diff --git a/drivers/net/ethernet/sfc/mcdi_port.c b/drivers/net/ethernet/sfc/mcdi_port.c index 91d23252f8fa..e5fc4e1574b5 100644 --- a/drivers/net/ethernet/sfc/mcdi_port.c +++ b/drivers/net/ethernet/sfc/mcdi_port.c @@ -854,8 +854,8 @@ int efx_mcdi_set_mac(struct efx_nic *efx) BUILD_BUG_ON(MC_CMD_SET_MAC_OUT_LEN != 0); - memcpy(MCDI_PTR(cmdbytes, SET_MAC_IN_ADDR), - efx->net_dev->dev_addr, ETH_ALEN); + ether_addr_copy(MCDI_PTR(cmdbytes, SET_MAC_IN_ADDR), + efx->net_dev->dev_addr); MCDI_SET_DWORD(cmdbytes, SET_MAC_IN_MTU, EFX_MAX_FRAME_LEN(efx->net_dev->mtu)); diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h index af2b8c59a903..8a400a0595eb 100644 --- a/drivers/net/ethernet/sfc/net_driver.h +++ b/drivers/net/ethernet/sfc/net_driver.h @@ -1323,7 +1323,6 @@ static inline struct efx_rx_buffer *efx_rx_buffer(struct efx_rx_queue *rx_queue, return &rx_queue->buffer[index]; } - /** * EFX_MAX_FRAME_LEN - calculate maximum frame length * diff --git a/drivers/net/ethernet/sfc/nic.c b/drivers/net/ethernet/sfc/nic.c index 79226b19e3c4..32d969e857f7 100644 --- a/drivers/net/ethernet/sfc/nic.c +++ b/drivers/net/ethernet/sfc/nic.c @@ -530,4 +530,3 @@ void efx_nic_fix_nodesc_drop_stat(struct efx_nic *efx, u64 *rx_nodesc_drops) efx->rx_nodesc_drops_prev_state = !!(efx->net_dev->flags & IFF_UP); *rx_nodesc_drops -= efx->rx_nodesc_drops_while_down; } - diff --git a/drivers/net/ethernet/sfc/ptp.c b/drivers/net/ethernet/sfc/ptp.c index eb75fbd11a01..722344fcd155 100644 --- a/drivers/net/ethernet/sfc/ptp.c +++ b/drivers/net/ethernet/sfc/ptp.c @@ -223,7 +223,6 @@ struct efx_ptp_timeset { * @evt_list: List of MC receive events awaiting packets * @evt_free_list: List of free events * @evt_lock: Lock for manipulating evt_list and evt_free_list - * @evt_overflow: Boolean indicating that event list has overflowed * @rx_evts: Instantiated events (on evt_list and evt_free_list) * @workwq: Work queue for processing pending PTP operations * @work: Work task @@ -275,7 +274,6 @@ struct efx_ptp_data { struct list_head evt_list; struct list_head evt_free_list; spinlock_t evt_lock; - bool evt_overflow; struct efx_ptp_event_rx rx_evts[MAX_RECEIVE_EVENTS]; struct workqueue_struct *workwq; struct work_struct work; @@ -768,37 +766,36 @@ efx_ptp_process_times(struct efx_nic *efx, MCDI_DECLARE_STRUCT_PTR(synch_buf), return -EAGAIN; } - /* Convert the NIC time into kernel time. No correction is required- - * this time is the output of a firmware process. - */ - mc_time = ptp->nic_to_kernel_time(ptp->timeset[last_good].major, - ptp->timeset[last_good].minor, 0); - - /* Calculate delay from actual PPS to last_time */ - delta = ktime_to_timespec(mc_time); - delta.tv_nsec += - last_time->ts_real.tv_nsec - - (ptp->timeset[last_good].host_start & MC_NANOSECOND_MASK); - - /* It is possible that the seconds rolled over between taking + /* Calculate delay from last good sync (host time) to last_time. + * It is possible that the seconds rolled over between taking * the start reading and the last value written by the host. The * timescales are such that a gap of more than one second is never - * expected. + * expected. delta is *not* normalised. */ start_sec = ptp->timeset[last_good].host_start >> MC_NANOSECOND_BITS; last_sec = last_time->ts_real.tv_sec & MC_SECOND_MASK; - if (start_sec != last_sec) { - if (((start_sec + 1) & MC_SECOND_MASK) != last_sec) { - netif_warn(efx, hw, efx->net_dev, - "PTP bad synchronisation seconds\n"); - return -EAGAIN; - } else { - delta.tv_sec = 1; - } - } else { - delta.tv_sec = 0; + if (start_sec != last_sec && + ((start_sec + 1) & MC_SECOND_MASK) != last_sec) { + netif_warn(efx, hw, efx->net_dev, + "PTP bad synchronisation seconds\n"); + return -EAGAIN; } + delta.tv_sec = (last_sec - start_sec) & 1; + delta.tv_nsec = + last_time->ts_real.tv_nsec - + (ptp->timeset[last_good].host_start & MC_NANOSECOND_MASK); + + /* Convert the NIC time at last good sync into kernel time. + * No correction is required - this time is the output of a + * firmware process. + */ + mc_time = ptp->nic_to_kernel_time(ptp->timeset[last_good].major, + ptp->timeset[last_good].minor, 0); + + /* Calculate delay from NIC top of second to last_time */ + delta.tv_nsec += ktime_to_timespec(mc_time).tv_nsec; + /* Set PPS timestamp to match NIC top of second */ ptp->host_time_pps = *last_time; pps_sub_ts(&ptp->host_time_pps, delta); @@ -941,11 +938,6 @@ static void efx_ptp_drop_time_expired_events(struct efx_nic *efx) } } } - /* If the event overflow flag is set and the event list is now empty - * clear the flag to re-enable the overflow warning message. - */ - if (ptp->evt_overflow && list_empty(&ptp->evt_list)) - ptp->evt_overflow = false; spin_unlock_bh(&ptp->evt_lock); } @@ -989,11 +981,6 @@ static enum ptp_packet_state efx_ptp_match_rx(struct efx_nic *efx, break; } } - /* If the event overflow flag is set and the event list is now empty - * clear the flag to re-enable the overflow warning message. - */ - if (ptp->evt_overflow && list_empty(&ptp->evt_list)) - ptp->evt_overflow = false; spin_unlock_bh(&ptp->evt_lock); return rc; @@ -1147,7 +1134,6 @@ static int efx_ptp_stop(struct efx_nic *efx) list_for_each_safe(cursor, next, &efx->ptp_data->evt_list) { list_move(cursor, &efx->ptp_data->evt_free_list); } - ptp->evt_overflow = false; spin_unlock_bh(&efx->ptp_data->evt_lock); return rc; @@ -1253,7 +1239,6 @@ int efx_ptp_probe(struct efx_nic *efx, struct efx_channel *channel) spin_lock_init(&ptp->evt_lock); for (pos = 0; pos < MAX_RECEIVE_EVENTS; pos++) list_add(&ptp->rx_evts[pos].link, &ptp->evt_free_list); - ptp->evt_overflow = false; /* Get the NIC PTP attributes and set up time conversions */ rc = efx_ptp_get_attributes(efx); @@ -1380,6 +1365,7 @@ static bool efx_ptp_rx(struct efx_channel *channel, struct sk_buff *skb) struct efx_ptp_match *match = (struct efx_ptp_match *)skb->cb; u8 *match_data_012, *match_data_345; unsigned int version; + u8 *data; match->expiry = jiffies + msecs_to_jiffies(PKT_EVENT_LIFETIME_MS); @@ -1388,7 +1374,8 @@ static bool efx_ptp_rx(struct efx_channel *channel, struct sk_buff *skb) if (!pskb_may_pull(skb, PTP_V1_MIN_LENGTH)) { return false; } - version = ntohs(*(__be16 *)&skb->data[PTP_V1_VERSION_OFFSET]); + data = skb->data; + version = ntohs(*(__be16 *)&data[PTP_V1_VERSION_OFFSET]); if (version != PTP_VERSION_V1) { return false; } @@ -1396,13 +1383,14 @@ static bool efx_ptp_rx(struct efx_channel *channel, struct sk_buff *skb) /* PTP V1 uses all six bytes of the UUID to match the packet * to the timestamp */ - match_data_012 = skb->data + PTP_V1_UUID_OFFSET; - match_data_345 = skb->data + PTP_V1_UUID_OFFSET + 3; + match_data_012 = data + PTP_V1_UUID_OFFSET; + match_data_345 = data + PTP_V1_UUID_OFFSET + 3; } else { if (!pskb_may_pull(skb, PTP_V2_MIN_LENGTH)) { return false; } - version = skb->data[PTP_V2_VERSION_OFFSET]; + data = skb->data; + version = data[PTP_V2_VERSION_OFFSET]; if ((version & PTP_VERSION_V2_MASK) != PTP_VERSION_V2) { return false; } @@ -1414,17 +1402,17 @@ static bool efx_ptp_rx(struct efx_channel *channel, struct sk_buff *skb) * enhanced mode fixes this issue and uses bytes 0-2 * and byte 5-7 of the UUID. */ - match_data_345 = skb->data + PTP_V2_UUID_OFFSET + 5; + match_data_345 = data + PTP_V2_UUID_OFFSET + 5; if (ptp->mode == MC_CMD_PTP_MODE_V2) { - match_data_012 = skb->data + PTP_V2_UUID_OFFSET + 2; + match_data_012 = data + PTP_V2_UUID_OFFSET + 2; } else { - match_data_012 = skb->data + PTP_V2_UUID_OFFSET + 0; + match_data_012 = data + PTP_V2_UUID_OFFSET + 0; BUG_ON(ptp->mode != MC_CMD_PTP_MODE_V2_ENHANCED); } } /* Does this packet require timestamping? */ - if (ntohs(*(__be16 *)&skb->data[PTP_DPORT_OFFSET]) == PTP_EVENT_PORT) { + if (ntohs(*(__be16 *)&data[PTP_DPORT_OFFSET]) == PTP_EVENT_PORT) { match->state = PTP_PACKET_STATE_UNMATCHED; /* We expect the sequence number to be in the same position in @@ -1440,8 +1428,8 @@ static bool efx_ptp_rx(struct efx_channel *channel, struct sk_buff *skb) (match_data_345[0] << 24)); match->words[1] = (match_data_345[1] | (match_data_345[2] << 8) | - (skb->data[PTP_V1_SEQUENCE_OFFSET + - PTP_V1_SEQUENCE_LENGTH - 1] << + (data[PTP_V1_SEQUENCE_OFFSET + + PTP_V1_SEQUENCE_LENGTH - 1] << 16)); } else { match->state = PTP_PACKET_STATE_MATCH_UNWANTED; @@ -1635,13 +1623,9 @@ static void ptp_event_rx(struct efx_nic *efx, struct efx_ptp_data *ptp) list_add_tail(&evt->link, &ptp->evt_list); queue_work(ptp->workwq, &ptp->work); - } else if (!ptp->evt_overflow) { - /* Log a warning message and set the event overflow flag. - * The message won't be logged again until the event queue - * becomes empty. - */ + } else if (net_ratelimit()) { + /* Log a rate-limited warning message. */ netif_err(efx, rx_err, efx->net_dev, "PTP event queue overflow\n"); - ptp->evt_overflow = true; } spin_unlock_bh(&ptp->evt_lock); } @@ -1668,6 +1652,13 @@ void efx_ptp_event(struct efx_nic *efx, efx_qword_t *ev) struct efx_ptp_data *ptp = efx->ptp_data; int code = EFX_QWORD_FIELD(*ev, MCDI_EVENT_CODE); + if (!ptp) { + if (net_ratelimit()) + netif_warn(efx, drv, efx->net_dev, + "Received PTP event but PTP not set up\n"); + return; + } + if (!ptp->enabled) return; diff --git a/drivers/net/ethernet/sfc/selftest.c b/drivers/net/ethernet/sfc/selftest.c index 26641817a9c7..0fc5baef45b1 100644 --- a/drivers/net/ethernet/sfc/selftest.c +++ b/drivers/net/ethernet/sfc/selftest.c @@ -50,7 +50,7 @@ struct efx_loopback_payload { } __packed; /* Loopback test source MAC address */ -static const unsigned char payload_source[ETH_ALEN] = { +static const u8 payload_source[ETH_ALEN] __aligned(2) = { 0x00, 0x0f, 0x53, 0x1b, 0x1b, 0x1b, }; @@ -366,8 +366,8 @@ static void efx_iterate_state(struct efx_nic *efx) struct efx_loopback_payload *payload = &state->payload; /* Initialise the layerII header */ - memcpy(&payload->header.h_dest, net_dev->dev_addr, ETH_ALEN); - memcpy(&payload->header.h_source, &payload_source, ETH_ALEN); + ether_addr_copy((u8 *)&payload->header.h_dest, net_dev->dev_addr); + ether_addr_copy((u8 *)&payload->header.h_source, payload_source); payload->header.h_proto = htons(ETH_P_IP); /* saddr set later and used as incrementing count */ diff --git a/drivers/net/ethernet/sfc/siena_sriov.c b/drivers/net/ethernet/sfc/siena_sriov.c index 0c38f926871e..9a9205e77896 100644 --- a/drivers/net/ethernet/sfc/siena_sriov.c +++ b/drivers/net/ethernet/sfc/siena_sriov.c @@ -1095,7 +1095,7 @@ static void efx_sriov_peer_work(struct work_struct *data) /* Fill the remaining addresses */ list_for_each_entry(local_addr, &efx->local_addr_list, link) { - memcpy(peer->mac_addr, local_addr->addr, ETH_ALEN); + ether_addr_copy(peer->mac_addr, local_addr->addr); peer->tci = 0; ++peer; ++peer_count; @@ -1303,8 +1303,7 @@ int efx_sriov_init(struct efx_nic *efx) goto fail_vfs; rtnl_lock(); - memcpy(vfdi_status->peers[0].mac_addr, - net_dev->dev_addr, ETH_ALEN); + ether_addr_copy(vfdi_status->peers[0].mac_addr, net_dev->dev_addr); efx->vf_init_count = efx->vf_count; rtnl_unlock(); @@ -1452,8 +1451,8 @@ void efx_sriov_mac_address_changed(struct efx_nic *efx) if (!efx->vf_init_count) return; - memcpy(vfdi_status->peers[0].mac_addr, - efx->net_dev->dev_addr, ETH_ALEN); + ether_addr_copy(vfdi_status->peers[0].mac_addr, + efx->net_dev->dev_addr); queue_work(vfdi_workqueue, &efx->peer_work); } @@ -1570,7 +1569,7 @@ int efx_sriov_set_vf_mac(struct net_device *net_dev, int vf_i, u8 *mac) vf = efx->vf + vf_i; mutex_lock(&vf->status_lock); - memcpy(vf->addr.mac_addr, mac, ETH_ALEN); + ether_addr_copy(vf->addr.mac_addr, mac); __efx_sriov_update_vf_addr(vf); mutex_unlock(&vf->status_lock); @@ -1633,7 +1632,7 @@ int efx_sriov_get_vf_config(struct net_device *net_dev, int vf_i, vf = efx->vf + vf_i; ivi->vf = vf_i; - memcpy(ivi->mac, vf->addr.mac_addr, ETH_ALEN); + ether_addr_copy(ivi->mac, vf->addr.mac_addr); ivi->tx_rate = 0; tci = ntohs(vf->addr.tci); ivi->vlan = tci & VLAN_VID_MASK; diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c index c49d1fb16965..fa9475300411 100644 --- a/drivers/net/ethernet/sfc/tx.c +++ b/drivers/net/ethernet/sfc/tx.c @@ -429,7 +429,9 @@ netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb) } /* Transfer ownership of the skb to the final buffer */ +#ifdef EFX_USE_PIO finish_packet: +#endif buffer->skb = skb; buffer->flags = EFX_TX_BUF_SKB | dma_flags; @@ -785,15 +787,6 @@ void efx_remove_tx_queue(struct efx_tx_queue *tx_queue) * Requires TX checksum offload support. */ -/* Number of bytes inserted at the start of a TSO header buffer, - * similar to NET_IP_ALIGN. - */ -#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS -#define TSOH_OFFSET 0 -#else -#define TSOH_OFFSET NET_IP_ALIGN -#endif - #define PTR_DIFF(p1, p2) ((u8 *)(p1) - (u8 *)(p2)) /** @@ -880,13 +873,13 @@ static u8 *efx_tsoh_get_buffer(struct efx_tx_queue *tx_queue, EFX_BUG_ON_PARANOID(buffer->flags); EFX_BUG_ON_PARANOID(buffer->unmap_len); - if (likely(len <= TSOH_STD_SIZE - TSOH_OFFSET)) { + if (likely(len <= TSOH_STD_SIZE - NET_IP_ALIGN)) { unsigned index = (tx_queue->insert_count & tx_queue->ptr_mask) / 2; struct efx_buffer *page_buf = &tx_queue->tsoh_page[index / TSOH_PER_PAGE]; unsigned offset = - TSOH_STD_SIZE * (index % TSOH_PER_PAGE) + TSOH_OFFSET; + TSOH_STD_SIZE * (index % TSOH_PER_PAGE) + NET_IP_ALIGN; if (unlikely(!page_buf->addr) && efx_nic_alloc_buffer(tx_queue->efx, page_buf, PAGE_SIZE, @@ -899,10 +892,10 @@ static u8 *efx_tsoh_get_buffer(struct efx_tx_queue *tx_queue, } else { tx_queue->tso_long_headers++; - buffer->heap_buf = kmalloc(TSOH_OFFSET + len, GFP_ATOMIC); + buffer->heap_buf = kmalloc(NET_IP_ALIGN + len, GFP_ATOMIC); if (unlikely(!buffer->heap_buf)) return NULL; - result = (u8 *)buffer->heap_buf + TSOH_OFFSET; + result = (u8 *)buffer->heap_buf + NET_IP_ALIGN; buffer->flags = EFX_TX_BUF_CONT | EFX_TX_BUF_HEAP; } @@ -1009,7 +1002,7 @@ static void efx_enqueue_unwind(struct efx_tx_queue *tx_queue) static int tso_start(struct tso_state *st, struct efx_nic *efx, const struct sk_buff *skb) { - bool use_options = efx_nic_rev(efx) >= EFX_REV_HUNT_A0; + bool use_opt_desc = efx_nic_rev(efx) >= EFX_REV_HUNT_A0; struct device *dma_dev = &efx->pci_dev->dev; unsigned int header_len, in_len; dma_addr_t dma_addr; @@ -1035,7 +1028,7 @@ static int tso_start(struct tso_state *st, struct efx_nic *efx, st->out_len = skb->len - header_len; - if (!use_options) { + if (!use_opt_desc) { st->header_unmap_len = 0; if (likely(in_len == 0)) { diff --git a/drivers/net/ethernet/stmicro/stmmac/Kconfig b/drivers/net/ethernet/stmicro/stmmac/Kconfig index e2f202e3932f..f2d7c702c77f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/Kconfig +++ b/drivers/net/ethernet/stmicro/stmmac/Kconfig @@ -37,6 +37,17 @@ config DWMAC_SUNXI stmmac device driver. This driver is used for A20/A31 GMAC ethernet controller. +config DWMAC_STI + bool "STi GMAC support" + depends on STMMAC_PLATFORM && ARCH_STI + default y + ---help--- + Support for ethernet controller on STi SOCs. + + This selects STi SoC glue layer support for the stmmac + device driver. This driver is used on for the STi series + SOCs GMAC ethernet controller. + config STMMAC_PCI bool "STMMAC PCI bus support" depends on STMMAC_ETH && PCI diff --git a/drivers/net/ethernet/stmicro/stmmac/Makefile b/drivers/net/ethernet/stmicro/stmmac/Makefile index ecadecea79b2..dcef28775dad 100644 --- a/drivers/net/ethernet/stmicro/stmmac/Makefile +++ b/drivers/net/ethernet/stmicro/stmmac/Makefile @@ -2,6 +2,7 @@ obj-$(CONFIG_STMMAC_ETH) += stmmac.o stmmac-$(CONFIG_STMMAC_PLATFORM) += stmmac_platform.o stmmac-$(CONFIG_STMMAC_PCI) += stmmac_pci.o stmmac-$(CONFIG_DWMAC_SUNXI) += dwmac-sunxi.o +stmmac-$(CONFIG_DWMAC_STI) += dwmac-sti.o stmmac-objs:= stmmac_main.o stmmac_ethtool.o stmmac_mdio.o ring_mode.o \ chain_mode.o dwmac_lib.o dwmac1000_core.o dwmac1000_dma.o \ dwmac100_core.o dwmac100_dma.o enh_desc.o norm_desc.o \ diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c new file mode 100644 index 000000000000..552bbc17863c --- /dev/null +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c @@ -0,0 +1,330 @@ +/** + * dwmac-sti.c - STMicroelectronics DWMAC Specific Glue layer + * + * Copyright (C) 2003-2014 STMicroelectronics (R&D) Limited + * Author: Srinivas Kandagatla <srinivas.kandagatla@st.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 <linux/kernel.h> +#include <linux/slab.h> +#include <linux/platform_device.h> +#include <linux/stmmac.h> +#include <linux/phy.h> +#include <linux/mfd/syscon.h> +#include <linux/regmap.h> +#include <linux/clk.h> +#include <linux/of.h> +#include <linux/of_net.h> + +/** + * STi GMAC glue logic. + * -------------------- + * + * _ + * | \ + * --------|0 \ ETH_SEL_INTERNAL_NOTEXT_PHYCLK + * phyclk | |___________________________________________ + * | | | (phyclk-in) + * --------|1 / | + * int-clk |_ / | + * | _ + * | | \ + * |_______|1 \ ETH_SEL_TX_RETIME_CLK + * | |___________________________ + * | | (tx-retime-clk) + * _______|0 / + * | |_ / + * _ | + * | \ | + * --------|0 \ | + * clk_125 | |__| + * | | ETH_SEL_TXCLK_NOT_CLK125 + * --------|1 / + * txclk |_ / + * + * + * ETH_SEL_INTERNAL_NOTEXT_PHYCLK is valid only for RMII where PHY can + * generate 50MHz clock or MAC can generate it. + * This bit is configured by "st,ext-phyclk" property. + * + * ETH_SEL_TXCLK_NOT_CLK125 is only valid for gigabit modes, where the 125Mhz + * clock either comes from clk-125 pin or txclk pin. This configuration is + * totally driven by the board wiring. This bit is configured by + * "st,tx-retime-src" property. + * + * TXCLK configuration is different for different phy interface modes + * and changes according to link speed in modes like RGMII. + * + * Below table summarizes the clock requirement and clock sources for + * supported phy interface modes with link speeds. + * ________________________________________________ + *| PHY_MODE | 1000 Mbit Link | 100 Mbit Link | + * ------------------------------------------------ + *| MII | n/a | 25Mhz | + *| | | txclk | + * ------------------------------------------------ + *| GMII | 125Mhz | 25Mhz | + *| | clk-125/txclk | txclk | + * ------------------------------------------------ + *| RGMII | 125Mhz | 25Mhz | + *| | clk-125/txclk | clkgen | + * ------------------------------------------------ + *| RMII | n/a | 25Mhz | + *| | |clkgen/phyclk-in | + * ------------------------------------------------ + * + * TX lines are always retimed with a clk, which can vary depending + * on the board configuration. Below is the table of these bits + * in eth configuration register depending on source of retime clk. + * + *--------------------------------------------------------------- + * src | tx_rt_clk | int_not_ext_phyclk | txclk_n_clk125| + *--------------------------------------------------------------- + * txclk | 0 | n/a | 1 | + *--------------------------------------------------------------- + * ck_125| 0 | n/a | 0 | + *--------------------------------------------------------------- + * phyclk| 1 | 0 | n/a | + *--------------------------------------------------------------- + * clkgen| 1 | 1 | n/a | + *--------------------------------------------------------------- + */ + + /* Register definition */ + + /* 3 bits [8:6] + * [6:6] ETH_SEL_TXCLK_NOT_CLK125 + * [7:7] ETH_SEL_INTERNAL_NOTEXT_PHYCLK + * [8:8] ETH_SEL_TX_RETIME_CLK + * + */ + +#define TX_RETIME_SRC_MASK GENMASK(8, 6) +#define ETH_SEL_TX_RETIME_CLK BIT(8) +#define ETH_SEL_INTERNAL_NOTEXT_PHYCLK BIT(7) +#define ETH_SEL_TXCLK_NOT_CLK125 BIT(6) + +#define ENMII_MASK GENMASK(5, 5) +#define ENMII BIT(5) + +/** + * 3 bits [4:2] + * 000-GMII/MII + * 001-RGMII + * 010-SGMII + * 100-RMII +*/ +#define MII_PHY_SEL_MASK GENMASK(4, 2) +#define ETH_PHY_SEL_RMII BIT(4) +#define ETH_PHY_SEL_SGMII BIT(3) +#define ETH_PHY_SEL_RGMII BIT(2) +#define ETH_PHY_SEL_GMII 0x0 +#define ETH_PHY_SEL_MII 0x0 + +#define IS_PHY_IF_MODE_RGMII(iface) (iface == PHY_INTERFACE_MODE_RGMII || \ + iface == PHY_INTERFACE_MODE_RGMII_ID || \ + iface == PHY_INTERFACE_MODE_RGMII_RXID || \ + iface == PHY_INTERFACE_MODE_RGMII_TXID) + +#define IS_PHY_IF_MODE_GBIT(iface) (IS_PHY_IF_MODE_RGMII(iface) || \ + iface == PHY_INTERFACE_MODE_GMII) + +struct sti_dwmac { + int interface; + bool ext_phyclk; + bool is_tx_retime_src_clk_125; + struct clk *clk; + int reg; + struct device *dev; + struct regmap *regmap; +}; + +static u32 phy_intf_sels[] = { + [PHY_INTERFACE_MODE_MII] = ETH_PHY_SEL_MII, + [PHY_INTERFACE_MODE_GMII] = ETH_PHY_SEL_GMII, + [PHY_INTERFACE_MODE_RGMII] = ETH_PHY_SEL_RGMII, + [PHY_INTERFACE_MODE_RGMII_ID] = ETH_PHY_SEL_RGMII, + [PHY_INTERFACE_MODE_SGMII] = ETH_PHY_SEL_SGMII, + [PHY_INTERFACE_MODE_RMII] = ETH_PHY_SEL_RMII, +}; + +enum { + TX_RETIME_SRC_NA = 0, + TX_RETIME_SRC_TXCLK = 1, + TX_RETIME_SRC_CLK_125, + TX_RETIME_SRC_PHYCLK, + TX_RETIME_SRC_CLKGEN, +}; + +static const char *const tx_retime_srcs[] = { + [TX_RETIME_SRC_NA] = "", + [TX_RETIME_SRC_TXCLK] = "txclk", + [TX_RETIME_SRC_CLK_125] = "clk_125", + [TX_RETIME_SRC_PHYCLK] = "phyclk", + [TX_RETIME_SRC_CLKGEN] = "clkgen", +}; + +static u32 tx_retime_val[] = { + [TX_RETIME_SRC_TXCLK] = ETH_SEL_TXCLK_NOT_CLK125, + [TX_RETIME_SRC_CLK_125] = 0x0, + [TX_RETIME_SRC_PHYCLK] = ETH_SEL_TX_RETIME_CLK, + [TX_RETIME_SRC_CLKGEN] = ETH_SEL_TX_RETIME_CLK | + ETH_SEL_INTERNAL_NOTEXT_PHYCLK, +}; + +static void setup_retime_src(struct sti_dwmac *dwmac, u32 spd) +{ + u32 src = 0, freq = 0; + + if (spd == SPEED_100) { + if (dwmac->interface == PHY_INTERFACE_MODE_MII || + dwmac->interface == PHY_INTERFACE_MODE_GMII) { + src = TX_RETIME_SRC_TXCLK; + } else if (dwmac->interface == PHY_INTERFACE_MODE_RMII) { + if (dwmac->ext_phyclk) { + src = TX_RETIME_SRC_PHYCLK; + } else { + src = TX_RETIME_SRC_CLKGEN; + freq = 50000000; + } + + } else if (IS_PHY_IF_MODE_RGMII(dwmac->interface)) { + src = TX_RETIME_SRC_CLKGEN; + freq = 25000000; + } + + if (src == TX_RETIME_SRC_CLKGEN && dwmac->clk) + clk_set_rate(dwmac->clk, freq); + + } else if (spd == SPEED_1000) { + if (dwmac->is_tx_retime_src_clk_125) + src = TX_RETIME_SRC_CLK_125; + else + src = TX_RETIME_SRC_TXCLK; + } + + regmap_update_bits(dwmac->regmap, dwmac->reg, + TX_RETIME_SRC_MASK, tx_retime_val[src]); +} + +static void sti_dwmac_exit(struct platform_device *pdev, void *priv) +{ + struct sti_dwmac *dwmac = priv; + + if (dwmac->clk) + clk_disable_unprepare(dwmac->clk); +} + +static void sti_fix_mac_speed(void *priv, unsigned int spd) +{ + struct sti_dwmac *dwmac = priv; + + setup_retime_src(dwmac, spd); + + return; +} + +static int sti_dwmac_parse_data(struct sti_dwmac *dwmac, + struct platform_device *pdev) +{ + struct resource *res; + struct device *dev = &pdev->dev; + struct device_node *np = dev->of_node; + struct regmap *regmap; + int err; + + if (!np) + return -EINVAL; + + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "sti-ethconf"); + if (!res) + return -ENODATA; + + regmap = syscon_regmap_lookup_by_phandle(np, "st,syscon"); + if (IS_ERR(regmap)) + return PTR_ERR(regmap); + + dwmac->dev = dev; + dwmac->interface = of_get_phy_mode(np); + dwmac->regmap = regmap; + dwmac->reg = res->start; + dwmac->ext_phyclk = of_property_read_bool(np, "st,ext-phyclk"); + dwmac->is_tx_retime_src_clk_125 = false; + + if (IS_PHY_IF_MODE_GBIT(dwmac->interface)) { + const char *rs; + + err = of_property_read_string(np, "st,tx-retime-src", &rs); + if (err < 0) { + dev_err(dev, "st,tx-retime-src not specified\n"); + return err; + } + + if (!strcasecmp(rs, "clk_125")) + dwmac->is_tx_retime_src_clk_125 = true; + } + + dwmac->clk = devm_clk_get(dev, "sti-ethclk"); + + if (IS_ERR(dwmac->clk)) + dwmac->clk = NULL; + + return 0; +} + +static int sti_dwmac_init(struct platform_device *pdev, void *priv) +{ + struct sti_dwmac *dwmac = priv; + struct regmap *regmap = dwmac->regmap; + int iface = dwmac->interface; + u32 reg = dwmac->reg; + u32 val, spd; + + if (dwmac->clk) + clk_prepare_enable(dwmac->clk); + + regmap_update_bits(regmap, reg, MII_PHY_SEL_MASK, phy_intf_sels[iface]); + + val = (iface == PHY_INTERFACE_MODE_REVMII) ? 0 : ENMII; + regmap_update_bits(regmap, reg, ENMII_MASK, val); + + if (IS_PHY_IF_MODE_GBIT(iface)) + spd = SPEED_1000; + else + spd = SPEED_100; + + setup_retime_src(dwmac, spd); + + return 0; +} + +static void *sti_dwmac_setup(struct platform_device *pdev) +{ + struct sti_dwmac *dwmac; + int ret; + + dwmac = devm_kzalloc(&pdev->dev, sizeof(*dwmac), GFP_KERNEL); + if (!dwmac) + return ERR_PTR(-ENOMEM); + + ret = sti_dwmac_parse_data(dwmac, pdev); + if (ret) { + dev_err(&pdev->dev, "Unable to parse OF data\n"); + return ERR_PTR(ret); + } + + return dwmac; +} + +const struct stmmac_of_data sti_gmac_data = { + .fix_mac_speed = sti_fix_mac_speed, + .setup = sti_dwmac_setup, + .init = sti_dwmac_init, + .exit = sti_dwmac_exit, +}; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h index d9af26ed58ee..f9e60d7918c4 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h @@ -133,6 +133,9 @@ bool stmmac_eee_init(struct stmmac_priv *priv); #ifdef CONFIG_DWMAC_SUNXI extern const struct stmmac_of_data sun7i_gmac_data; #endif +#ifdef CONFIG_DWMAC_STI +extern const struct stmmac_of_data sti_gmac_data; +#endif extern struct platform_driver stmmac_pltfr_driver; static inline int stmmac_register_platform(void) { diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index a2e7d2c96e36..078ad0ec8593 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1705,7 +1705,7 @@ static int stmmac_open(struct net_device *dev) priv->dma_rx_size = STMMAC_ALIGN(dma_rxsize); priv->dma_buf_sz = STMMAC_ALIGN(buf_sz); - alloc_dma_desc_resources(priv); + ret = alloc_dma_desc_resources(priv); if (ret < 0) { pr_err("%s: DMA descriptors allocation failed\n", __func__); goto dma_desc_error; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 5884a7d2063b..c61bc72b8e90 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -33,6 +33,11 @@ static const struct of_device_id stmmac_dt_ids[] = { #ifdef CONFIG_DWMAC_SUNXI { .compatible = "allwinner,sun7i-a20-gmac", .data = &sun7i_gmac_data}, #endif +#ifdef CONFIG_DWMAC_STI + { .compatible = "st,stih415-dwmac", .data = &sti_gmac_data}, + { .compatible = "st,stih416-dwmac", .data = &sti_gmac_data}, + { .compatible = "st,stih127-dwmac", .data = &sti_gmac_data}, +#endif /* SoC specific glue layers should come before generic bindings */ { .compatible = "st,spear600-gmac"}, { .compatible = "snps,dwmac-3.610"}, diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c index 8e2266e1f260..79606f47a08e 100644 --- a/drivers/net/ethernet/sun/niu.c +++ b/drivers/net/ethernet/sun/niu.c @@ -9041,7 +9041,7 @@ static void niu_try_msix(struct niu *np, u8 *ldg_num_map) struct msix_entry msi_vec[NIU_NUM_LDG]; struct niu_parent *parent = np->parent; struct pci_dev *pdev = np->pdev; - int i, num_irqs, err; + int i, num_irqs; u8 first_ldg; first_ldg = (NIU_NUM_LDG / parent->num_ports) * np->port; @@ -9053,21 +9053,16 @@ static void niu_try_msix(struct niu *np, u8 *ldg_num_map) (np->port == 0 ? 3 : 1)); BUG_ON(num_irqs > (NIU_NUM_LDG / parent->num_ports)); -retry: for (i = 0; i < num_irqs; i++) { msi_vec[i].vector = 0; msi_vec[i].entry = i; } - err = pci_enable_msix(pdev, msi_vec, num_irqs); - if (err < 0) { + num_irqs = pci_enable_msix_range(pdev, msi_vec, 1, num_irqs); + if (num_irqs < 0) { np->flags &= ~NIU_FLAGS_MSIX; return; } - if (err > 0) { - num_irqs = err; - goto retry; - } np->flags |= NIU_FLAGS_MSIX; for (i = 0; i < num_irqs; i++) diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index bde63e3af96f..543a0813c9e0 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -378,7 +378,6 @@ struct cpsw_priv { u32 version; u32 coal_intvl; u32 bus_freq_mhz; - struct net_device_stats stats; int rx_packet_max; int host_port; struct clk *clk; @@ -554,7 +553,7 @@ static void cpsw_set_promiscious(struct net_device *ndev, bool enable) * common for both the interface as the interface shares * the same hardware resource. */ - for (i = 0; i <= priv->data.slaves; i++) + for (i = 0; i < priv->data.slaves; i++) if (priv->slaves[i].ndev->flags & IFF_PROMISC) flag = true; @@ -578,7 +577,7 @@ static void cpsw_set_promiscious(struct net_device *ndev, bool enable) unsigned long timeout = jiffies + HZ; /* Disable Learn for all ports */ - for (i = 0; i <= priv->data.slaves; i++) { + for (i = 0; i < priv->data.slaves; i++) { cpsw_ale_control_set(ale, i, ALE_PORT_NOLEARN, 1); cpsw_ale_control_set(ale, i, @@ -606,7 +605,7 @@ static void cpsw_set_promiscious(struct net_device *ndev, bool enable) cpsw_ale_control_set(ale, 0, ALE_P0_UNI_FLOOD, 0); /* Enable Learn for all ports */ - for (i = 0; i <= priv->data.slaves; i++) { + for (i = 0; i < priv->data.slaves; i++) { cpsw_ale_control_set(ale, i, ALE_PORT_NOLEARN, 0); cpsw_ale_control_set(ale, i, @@ -673,8 +672,8 @@ static void cpsw_tx_handler(void *token, int len, int status) if (unlikely(netif_queue_stopped(ndev))) netif_wake_queue(ndev); cpts_tx_timestamp(priv->cpts, skb); - priv->stats.tx_packets++; - priv->stats.tx_bytes += len; + ndev->stats.tx_packets++; + ndev->stats.tx_bytes += len; dev_kfree_skb_any(skb); } @@ -700,10 +699,10 @@ static void cpsw_rx_handler(void *token, int len, int status) cpts_rx_timestamp(priv->cpts, skb); skb->protocol = eth_type_trans(skb, ndev); netif_receive_skb(skb); - priv->stats.rx_bytes += len; - priv->stats.rx_packets++; + ndev->stats.rx_bytes += len; + ndev->stats.rx_packets++; } else { - priv->stats.rx_dropped++; + ndev->stats.rx_dropped++; new_skb = skb; } @@ -1164,11 +1163,17 @@ static void cpsw_init_host_port(struct cpsw_priv *priv) static void cpsw_slave_stop(struct cpsw_slave *slave, struct cpsw_priv *priv) { + u32 slave_port; + + slave_port = cpsw_get_slave_port(priv, slave->slave_num); + if (!slave->phy) return; phy_stop(slave->phy); phy_disconnect(slave->phy); slave->phy = NULL; + cpsw_ale_control_set(priv->ale, slave_port, + ALE_PORT_STATE, ALE_PORT_STATE_DISABLE); } static int cpsw_ndo_open(struct net_device *ndev) @@ -1307,7 +1312,7 @@ static netdev_tx_t cpsw_ndo_start_xmit(struct sk_buff *skb, if (skb_padto(skb, CPSW_MIN_PACKET_SIZE)) { cpsw_err(priv, tx_err, "packet pad failed\n"); - priv->stats.tx_dropped++; + ndev->stats.tx_dropped++; return NETDEV_TX_OK; } @@ -1331,7 +1336,7 @@ static netdev_tx_t cpsw_ndo_start_xmit(struct sk_buff *skb, return NETDEV_TX_OK; fail: - priv->stats.tx_dropped++; + ndev->stats.tx_dropped++; netif_stop_queue(ndev); return NETDEV_TX_BUSY; } @@ -1471,7 +1476,6 @@ static int cpsw_hwtstamp_get(struct net_device *dev, struct ifreq *ifr) static int cpsw_ndo_ioctl(struct net_device *dev, struct ifreq *req, int cmd) { struct cpsw_priv *priv = netdev_priv(dev); - struct mii_ioctl_data *data = if_mii(req); int slave_no = cpsw_slave_index(priv); if (!netif_running(dev)) @@ -1484,14 +1488,11 @@ static int cpsw_ndo_ioctl(struct net_device *dev, struct ifreq *req, int cmd) case SIOCGHWTSTAMP: return cpsw_hwtstamp_get(dev, req); #endif - case SIOCGMIIPHY: - data->phy_id = priv->slaves[slave_no].phy->addr; - break; - default: - return -ENOTSUPP; } - return 0; + if (!priv->slaves[slave_no].phy) + return -EOPNOTSUPP; + return phy_mii_ioctl(priv->slaves[slave_no].phy, req, cmd); } static void cpsw_ndo_tx_timeout(struct net_device *ndev) @@ -1499,7 +1500,7 @@ static void cpsw_ndo_tx_timeout(struct net_device *ndev) struct cpsw_priv *priv = netdev_priv(ndev); cpsw_err(priv, tx_err, "transmit timeout, restarting dma\n"); - priv->stats.tx_errors++; + ndev->stats.tx_errors++; cpsw_intr_disable(priv); cpdma_ctlr_int_ctrl(priv->dma, false); cpdma_chan_stop(priv->txch); @@ -1538,12 +1539,6 @@ static int cpsw_ndo_set_mac_address(struct net_device *ndev, void *p) return 0; } -static struct net_device_stats *cpsw_ndo_get_stats(struct net_device *ndev) -{ - struct cpsw_priv *priv = netdev_priv(ndev); - return &priv->stats; -} - #ifdef CONFIG_NET_POLL_CONTROLLER static void cpsw_ndo_poll_controller(struct net_device *ndev) { @@ -1636,7 +1631,6 @@ static const struct net_device_ops cpsw_netdev_ops = { .ndo_validate_addr = eth_validate_addr, .ndo_change_mtu = eth_change_mtu, .ndo_tx_timeout = cpsw_ndo_tx_timeout, - .ndo_get_stats = cpsw_ndo_get_stats, .ndo_set_rx_mode = cpsw_ndo_set_rx_mode, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = cpsw_ndo_poll_controller, @@ -1878,14 +1872,29 @@ static int cpsw_probe_dt(struct cpsw_platform_data *data, mdio_node = of_find_node_by_phandle(be32_to_cpup(parp)); phyid = be32_to_cpup(parp+1); mdio = of_find_device_by_node(mdio_node); - snprintf(slave_data->phy_id, sizeof(slave_data->phy_id), - PHY_ID_FMT, mdio->name, phyid); + + if (strncmp(mdio->name, "gpio", 4) == 0) { + /* GPIO bitbang MDIO driver attached */ + struct mii_bus *bus = dev_get_drvdata(&mdio->dev); + + snprintf(slave_data->phy_id, sizeof(slave_data->phy_id), + PHY_ID_FMT, bus->id, phyid); + } else { + /* davinci MDIO driver attached */ + snprintf(slave_data->phy_id, sizeof(slave_data->phy_id), + PHY_ID_FMT, mdio->name, phyid); + } mac_addr = of_get_mac_address(slave_node); if (mac_addr) memcpy(slave_data->mac_addr, mac_addr, ETH_ALEN); slave_data->phy_if = of_get_phy_mode(slave_node); + if (slave_data->phy_if < 0) { + pr_err("Missing or malformed slave[%d] phy-mode property\n", + i); + return slave_data->phy_if; + } if (data->dual_emac) { if (of_property_read_u32(slave_node, "dual_emac_res_vlan", diff --git a/drivers/net/ethernet/tile/tilegx.c b/drivers/net/ethernet/tile/tilegx.c index 023237a65720..17503da9f7a5 100644 --- a/drivers/net/ethernet/tile/tilegx.c +++ b/drivers/net/ethernet/tile/tilegx.c @@ -2071,7 +2071,7 @@ static int tile_net_tx(struct sk_buff *skb, struct net_device *dev) /* Return subqueue id on this core (one per core). */ static u16 tile_net_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv) + void *accel_priv, select_queue_fallback_t fallback) { return smp_processor_id(); } diff --git a/drivers/net/ethernet/wiznet/w5100.c b/drivers/net/ethernet/wiznet/w5100.c index 0df36c6ec7f4..104d46f37969 100644 --- a/drivers/net/ethernet/wiznet/w5100.c +++ b/drivers/net/ethernet/wiznet/w5100.c @@ -641,11 +641,10 @@ static int w5100_hw_probe(struct platform_device *pdev) if (!mem) return -ENXIO; mem_size = resource_size(mem); - if (!devm_request_mem_region(&pdev->dev, mem->start, mem_size, name)) - return -EBUSY; - priv->base = devm_ioremap(&pdev->dev, mem->start, mem_size); - if (!priv->base) - return -EBUSY; + + priv->base = devm_ioremap_resource(&pdev->dev, mem); + if (IS_ERR(priv->base)) + return PTR_ERR(priv->base); spin_lock_init(&priv->reg_lock); priv->indirect = mem_size < W5100_BUS_DIRECT_SIZE; diff --git a/drivers/net/ethernet/wiznet/w5300.c b/drivers/net/ethernet/wiznet/w5300.c index 71c27b3292f1..1f33c4c86c20 100644 --- a/drivers/net/ethernet/wiznet/w5300.c +++ b/drivers/net/ethernet/wiznet/w5300.c @@ -561,11 +561,10 @@ static int w5300_hw_probe(struct platform_device *pdev) if (!mem) return -ENXIO; mem_size = resource_size(mem); - if (!devm_request_mem_region(&pdev->dev, mem->start, mem_size, name)) - return -EBUSY; - priv->base = devm_ioremap(&pdev->dev, mem->start, mem_size); - if (!priv->base) - return -EBUSY; + + priv->base = devm_ioremap_resource(&pdev->dev, mem); + if (IS_ERR(priv->base)) + return PTR_ERR(priv->base); spin_lock_init(&priv->reg_lock); priv->indirect = mem_size < W5300_BUS_DIRECT_SIZE; diff --git a/drivers/net/ethernet/xilinx/ll_temac_main.c b/drivers/net/ethernet/xilinx/ll_temac_main.c index a4347508031c..fa193c4688da 100644 --- a/drivers/net/ethernet/xilinx/ll_temac_main.c +++ b/drivers/net/ethernet/xilinx/ll_temac_main.c @@ -771,8 +771,8 @@ static void ll_temac_recv(struct net_device *ndev) /* if we're doing rx csum offload, set it up */ if (((lp->temac_features & TEMAC_FEATURE_RX_CSUM) != 0) && - (skb->protocol == __constant_htons(ETH_P_IP)) && - (skb->len > 64)) { + (skb->protocol == htons(ETH_P_IP)) && + (skb->len > 64)) { skb->csum = cur_p->app3 & 0xFFFF; skb->ip_summed = CHECKSUM_COMPLETE; diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index 1ec65feebb9e..7b0a73556264 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -26,6 +26,7 @@ #include <linux/netdevice.h> #include <linux/of_mdio.h> #include <linux/of_platform.h> +#include <linux/of_irq.h> #include <linux/of_address.h> #include <linux/skbuff.h> #include <linux/spinlock.h> @@ -600,7 +601,8 @@ static void axienet_start_xmit_done(struct net_device *ndev) size += status & XAXIDMA_BD_STS_ACTUAL_LEN_MASK; packets++; - lp->tx_bd_ci = ++lp->tx_bd_ci % TX_BD_NUM; + ++lp->tx_bd_ci; + lp->tx_bd_ci %= TX_BD_NUM; cur_p = &lp->tx_bd_v[lp->tx_bd_ci]; status = cur_p->status; } @@ -686,7 +688,8 @@ static int axienet_start_xmit(struct sk_buff *skb, struct net_device *ndev) skb_headlen(skb), DMA_TO_DEVICE); for (ii = 0; ii < num_frag; ii++) { - lp->tx_bd_tail = ++lp->tx_bd_tail % TX_BD_NUM; + ++lp->tx_bd_tail; + lp->tx_bd_tail %= TX_BD_NUM; cur_p = &lp->tx_bd_v[lp->tx_bd_tail]; frag = &skb_shinfo(skb)->frags[ii]; cur_p->phys = dma_map_single(ndev->dev.parent, @@ -702,7 +705,8 @@ static int axienet_start_xmit(struct sk_buff *skb, struct net_device *ndev) tail_p = lp->tx_bd_p + sizeof(*lp->tx_bd_v) * lp->tx_bd_tail; /* Start the transfer */ axienet_dma_out32(lp, XAXIDMA_TX_TDESC_OFFSET, tail_p); - lp->tx_bd_tail = ++lp->tx_bd_tail % TX_BD_NUM; + ++lp->tx_bd_tail; + lp->tx_bd_tail %= TX_BD_NUM; return NETDEV_TX_OK; } @@ -752,7 +756,7 @@ static void axienet_recv(struct net_device *ndev) skb->ip_summed = CHECKSUM_UNNECESSARY; } } else if ((lp->features & XAE_FEATURE_PARTIAL_RX_CSUM) != 0 && - skb->protocol == __constant_htons(ETH_P_IP) && + skb->protocol == htons(ETH_P_IP) && skb->len > 64) { skb->csum = be32_to_cpu(cur_p->app3 & 0xFFFF); skb->ip_summed = CHECKSUM_COMPLETE; @@ -774,7 +778,8 @@ static void axienet_recv(struct net_device *ndev) cur_p->status = 0; cur_p->sw_id_offset = (u32) new_skb; - lp->rx_bd_ci = ++lp->rx_bd_ci % RX_BD_NUM; + ++lp->rx_bd_ci; + lp->rx_bd_ci %= RX_BD_NUM; cur_p = &lp->rx_bd_v[lp->rx_bd_ci]; } diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h index 7b594ce3f21d..13010b4dae5b 100644 --- a/drivers/net/hyperv/hyperv_net.h +++ b/drivers/net/hyperv/hyperv_net.h @@ -30,6 +30,7 @@ /* Fwd declaration */ struct hv_netvsc_packet; +struct ndis_tcp_ip_checksum_info; /* Represent the xfer page packet which contains 1 or more netvsc packet */ struct xferpage_packet { @@ -73,7 +74,7 @@ struct hv_netvsc_packet { } completion; /* This points to the memory after page_buf */ - void *extension; + struct rndis_message *rndis_msg; u32 total_data_buflen; /* Points to the send/receive buffer where the ethernet frame is */ @@ -117,7 +118,8 @@ int netvsc_send(struct hv_device *device, void netvsc_linkstatus_callback(struct hv_device *device_obj, unsigned int status); int netvsc_recv_callback(struct hv_device *device_obj, - struct hv_netvsc_packet *packet); + struct hv_netvsc_packet *packet, + struct ndis_tcp_ip_checksum_info *csum_info); int rndis_filter_open(struct hv_device *dev); int rndis_filter_close(struct hv_device *dev); int rndis_filter_device_add(struct hv_device *dev, @@ -126,11 +128,6 @@ void rndis_filter_device_remove(struct hv_device *dev); int rndis_filter_receive(struct hv_device *dev, struct hv_netvsc_packet *pkt); - - -int rndis_filter_send(struct hv_device *dev, - struct hv_netvsc_packet *pkt); - int rndis_filter_set_packet_filter(struct rndis_device *dev, u32 new_filter); int rndis_filter_set_device_mac(struct hv_device *hdev, char *mac); @@ -139,6 +136,8 @@ int rndis_filter_set_device_mac(struct hv_device *hdev, char *mac); #define NVSP_PROTOCOL_VERSION_1 2 #define NVSP_PROTOCOL_VERSION_2 0x30002 +#define NVSP_PROTOCOL_VERSION_4 0x40000 +#define NVSP_PROTOCOL_VERSION_5 0x50000 enum { NVSP_MSG_TYPE_NONE = 0, @@ -193,6 +192,23 @@ enum { NVSP_MSG2_TYPE_ALLOC_CHIMNEY_HANDLE, NVSP_MSG2_TYPE_ALLOC_CHIMNEY_HANDLE_COMP, + + NVSP_MSG2_MAX = NVSP_MSG2_TYPE_ALLOC_CHIMNEY_HANDLE_COMP, + + /* Version 4 messages */ + NVSP_MSG4_TYPE_SEND_VF_ASSOCIATION, + NVSP_MSG4_TYPE_SWITCH_DATA_PATH, + NVSP_MSG4_TYPE_UPLINK_CONNECT_STATE_DEPRECATED, + + NVSP_MSG4_MAX = NVSP_MSG4_TYPE_UPLINK_CONNECT_STATE_DEPRECATED, + + /* Version 5 messages */ + NVSP_MSG5_TYPE_OID_QUERY_EX, + NVSP_MSG5_TYPE_OID_QUERY_EX_COMP, + NVSP_MSG5_TYPE_SUBCHANNEL, + NVSP_MSG5_TYPE_SEND_INDIRECTION_TABLE, + + NVSP_MSG5_MAX = NVSP_MSG5_TYPE_SEND_INDIRECTION_TABLE, }; enum { @@ -447,10 +463,44 @@ union nvsp_2_message_uber { struct nvsp_2_free_rxbuf free_rxbuf; } __packed; +enum nvsp_subchannel_operation { + NVSP_SUBCHANNEL_NONE = 0, + NVSP_SUBCHANNEL_ALLOCATE, + NVSP_SUBCHANNEL_MAX +}; + +struct nvsp_5_subchannel_request { + u32 op; + u32 num_subchannels; +} __packed; + +struct nvsp_5_subchannel_complete { + u32 status; + u32 num_subchannels; /* Actual number of subchannels allocated */ +} __packed; + +struct nvsp_5_send_indirect_table { + /* The number of entries in the send indirection table */ + u32 count; + + /* The offset of the send indireciton table from top of this struct. + * The send indirection table tells which channel to put the send + * traffic on. Each entry is a channel number. + */ + u32 offset; +} __packed; + +union nvsp_5_message_uber { + struct nvsp_5_subchannel_request subchn_req; + struct nvsp_5_subchannel_complete subchn_comp; + struct nvsp_5_send_indirect_table send_table; +} __packed; + union nvsp_all_messages { union nvsp_message_init_uber init_msg; union nvsp_1_message_uber v1_msg; union nvsp_2_message_uber v2_msg; + union nvsp_5_message_uber v5_msg; } __packed; /* ALL Messages */ @@ -463,6 +513,7 @@ struct nvsp_message { #define NETVSC_MTU 65536 #define NETVSC_RECEIVE_BUFFER_SIZE (1024*1024*16) /* 16MB */ +#define NETVSC_RECEIVE_BUFFER_SIZE_LEGACY (1024*1024*15) /* 15MB */ #define NETVSC_RECEIVE_BUFFER_ID 0xcafe @@ -506,6 +557,8 @@ struct netvsc_device { /* Holds rndis device info */ void *extension; + /* The recive buffer for this device */ + unsigned char cb_buffer[NETVSC_PACKET_SIZE]; }; /* NdisInitialize message */ @@ -671,9 +724,133 @@ struct ndis_pkt_8021q_info { }; }; +struct ndis_oject_header { + u8 type; + u8 revision; + u16 size; +}; + +#define NDIS_OBJECT_TYPE_DEFAULT 0x80 +#define NDIS_OFFLOAD_PARAMETERS_REVISION_3 3 +#define NDIS_OFFLOAD_PARAMETERS_NO_CHANGE 0 +#define NDIS_OFFLOAD_PARAMETERS_LSOV2_DISABLED 1 +#define NDIS_OFFLOAD_PARAMETERS_LSOV2_ENABLED 2 +#define NDIS_OFFLOAD_PARAMETERS_LSOV1_ENABLED 2 +#define NDIS_OFFLOAD_PARAMETERS_RSC_DISABLED 1 +#define NDIS_OFFLOAD_PARAMETERS_RSC_ENABLED 2 +#define NDIS_OFFLOAD_PARAMETERS_TX_RX_DISABLED 1 +#define NDIS_OFFLOAD_PARAMETERS_TX_ENABLED_RX_DISABLED 2 +#define NDIS_OFFLOAD_PARAMETERS_RX_ENABLED_TX_DISABLED 3 +#define NDIS_OFFLOAD_PARAMETERS_TX_RX_ENABLED 4 + +#define NDIS_TCP_LARGE_SEND_OFFLOAD_V2_TYPE 1 +#define NDIS_TCP_LARGE_SEND_OFFLOAD_IPV4 0 +#define NDIS_TCP_LARGE_SEND_OFFLOAD_IPV6 1 + +/* + * New offload OIDs for NDIS 6 + */ +#define OID_TCP_OFFLOAD_CURRENT_CONFIG 0xFC01020B /* query only */ +#define OID_TCP_OFFLOAD_PARAMETERS 0xFC01020C /* set only */ +#define OID_TCP_OFFLOAD_HARDWARE_CAPABILITIES 0xFC01020D/* query only */ +#define OID_TCP_CONNECTION_OFFLOAD_CURRENT_CONFIG 0xFC01020E /* query only */ +#define OID_TCP_CONNECTION_OFFLOAD_HARDWARE_CAPABILITIES 0xFC01020F /* query */ +#define OID_OFFLOAD_ENCAPSULATION 0x0101010A /* set/query */ + +struct ndis_offload_params { + struct ndis_oject_header header; + u8 ip_v4_csum; + u8 tcp_ip_v4_csum; + u8 udp_ip_v4_csum; + u8 tcp_ip_v6_csum; + u8 udp_ip_v6_csum; + u8 lso_v1; + u8 ip_sec_v1; + u8 lso_v2_ipv4; + u8 lso_v2_ipv6; + u8 tcp_connection_ip_v4; + u8 tcp_connection_ip_v6; + u32 flags; + u8 ip_sec_v2; + u8 ip_sec_v2_ip_v4; + struct { + u8 rsc_ip_v4; + u8 rsc_ip_v6; + }; + struct { + u8 encapsulated_packet_task_offload; + u8 encapsulation_types; + }; +}; + +struct ndis_tcp_ip_checksum_info { + union { + struct { + u32 is_ipv4:1; + u32 is_ipv6:1; + u32 tcp_checksum:1; + u32 udp_checksum:1; + u32 ip_header_checksum:1; + u32 reserved:11; + u32 tcp_header_offset:10; + } transmit; + struct { + u32 tcp_checksum_failed:1; + u32 udp_checksum_failed:1; + u32 ip_checksum_failed:1; + u32 tcp_checksum_succeeded:1; + u32 udp_checksum_succeeded:1; + u32 ip_checksum_succeeded:1; + u32 loopback:1; + u32 tcp_checksum_value_invalid:1; + u32 ip_checksum_value_invalid:1; + } receive; + u32 value; + }; +}; + +struct ndis_tcp_lso_info { + union { + struct { + u32 unused:30; + u32 type:1; + u32 reserved2:1; + } transmit; + struct { + u32 mss:20; + u32 tcp_header_offset:10; + u32 type:1; + u32 reserved2:1; + } lso_v1_transmit; + struct { + u32 tcp_payload:30; + u32 type:1; + u32 reserved2:1; + } lso_v1_transmit_complete; + struct { + u32 mss:20; + u32 tcp_header_offset:10; + u32 type:1; + u32 ip_version:1; + } lso_v2_transmit; + struct { + u32 reserved:30; + u32 type:1; + u32 reserved2:1; + } lso_v2_transmit_complete; + u32 value; + }; +}; + #define NDIS_VLAN_PPI_SIZE (sizeof(struct rndis_per_packet_info) + \ sizeof(struct ndis_pkt_8021q_info)) +#define NDIS_CSUM_PPI_SIZE (sizeof(struct rndis_per_packet_info) + \ + sizeof(struct ndis_tcp_ip_checksum_info)) + +#define NDIS_LSO_PPI_SIZE (sizeof(struct rndis_per_packet_info) + \ + sizeof(struct ndis_tcp_lso_info)) + /* Format of Information buffer passed in a SetRequest for the OID */ /* OID_GEN_RNDIS_CONFIG_PARAMETER. */ struct rndis_config_parameter_info { @@ -846,12 +1023,6 @@ struct rndis_message { }; -struct rndis_filter_packet { - void *completion_ctx; - void (*completion)(void *context); - struct rndis_message msg; -}; - /* Handy macros */ /* get the size of an RNDIS message. Pass in the message type, */ @@ -905,6 +1076,16 @@ struct rndis_filter_packet { #define NDIS_PACKET_TYPE_FUNCTIONAL 0x00000400 #define NDIS_PACKET_TYPE_MAC_FRAME 0x00000800 +#define INFO_IPV4 2 +#define INFO_IPV6 4 +#define INFO_TCP 2 +#define INFO_UDP 4 + +#define TRANSPORT_INFO_NOT_IP 0 +#define TRANSPORT_INFO_IPV4_TCP ((INFO_IPV4 << 16) | INFO_TCP) +#define TRANSPORT_INFO_IPV4_UDP ((INFO_IPV4 << 16) | INFO_UDP) +#define TRANSPORT_INFO_IPV6_TCP ((INFO_IPV6 << 16) | INFO_TCP) +#define TRANSPORT_INFO_IPV6_UDP ((INFO_IPV6 << 16) | INFO_UDP) #endif /* _HYPERV_NET_H */ diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index 03a2c6e17158..daddea2654ce 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -290,7 +290,7 @@ static int negotiate_nvsp_ver(struct hv_device *device, NVSP_STAT_SUCCESS) return -EINVAL; - if (nvsp_ver != NVSP_PROTOCOL_VERSION_2) + if (nvsp_ver == NVSP_PROTOCOL_VERSION_1) return 0; /* NVSPv2 only: Send NDIS config */ @@ -314,6 +314,9 @@ static int netvsc_connect_vsp(struct hv_device *device) struct nvsp_message *init_packet; int ndis_version; struct net_device *ndev; + u32 ver_list[] = { NVSP_PROTOCOL_VERSION_1, NVSP_PROTOCOL_VERSION_2, + NVSP_PROTOCOL_VERSION_4, NVSP_PROTOCOL_VERSION_5 }; + int i, num_ver = 4; /* number of different NVSP versions */ net_device = get_outbound_net_device(device); if (!net_device) @@ -323,13 +326,14 @@ static int netvsc_connect_vsp(struct hv_device *device) init_packet = &net_device->channel_init_pkt; /* Negotiate the latest NVSP protocol supported */ - if (negotiate_nvsp_ver(device, net_device, init_packet, - NVSP_PROTOCOL_VERSION_2) == 0) { - net_device->nvsp_version = NVSP_PROTOCOL_VERSION_2; - } else if (negotiate_nvsp_ver(device, net_device, init_packet, - NVSP_PROTOCOL_VERSION_1) == 0) { - net_device->nvsp_version = NVSP_PROTOCOL_VERSION_1; - } else { + for (i = num_ver - 1; i >= 0; i--) + if (negotiate_nvsp_ver(device, net_device, init_packet, + ver_list[i]) == 0) { + net_device->nvsp_version = ver_list[i]; + break; + } + + if (i < 0) { ret = -EPROTO; goto cleanup; } @@ -339,7 +343,10 @@ static int netvsc_connect_vsp(struct hv_device *device) /* Send the ndis version */ memset(init_packet, 0, sizeof(struct nvsp_message)); - ndis_version = 0x00050001; + if (net_device->nvsp_version <= NVSP_PROTOCOL_VERSION_4) + ndis_version = 0x00050001; + else + ndis_version = 0x0006001e; init_packet->hdr.msg_type = NVSP_MSG1_TYPE_SEND_NDIS_VER; init_packet->msg.v1_msg. @@ -358,6 +365,11 @@ static int netvsc_connect_vsp(struct hv_device *device) goto cleanup; /* Post the big receive buffer to NetVSP */ + if (net_device->nvsp_version <= NVSP_PROTOCOL_VERSION_2) + net_device->recv_buf_size = NETVSC_RECEIVE_BUFFER_SIZE_LEGACY; + else + net_device->recv_buf_size = NETVSC_RECEIVE_BUFFER_SIZE; + ret = netvsc_init_recv_buf(device); cleanup: @@ -432,17 +444,14 @@ static inline u32 hv_ringbuf_avail_percent( return avail_write * 100 / ring_info->ring_datasize; } -static void netvsc_send_completion(struct hv_device *device, +static void netvsc_send_completion(struct netvsc_device *net_device, + struct hv_device *device, struct vmpacket_descriptor *packet) { - struct netvsc_device *net_device; struct nvsp_message *nvsp_packet; struct hv_netvsc_packet *nvsc_packet; struct net_device *ndev; - net_device = get_inbound_net_device(device); - if (!net_device) - return; ndev = net_device->ndev; nvsp_packet = (struct nvsp_message *)((unsigned long)packet + @@ -561,13 +570,13 @@ int netvsc_send(struct hv_device *device, } static void netvsc_send_recv_completion(struct hv_device *device, + struct netvsc_device *net_device, u64 transaction_id, u32 status) { struct nvsp_message recvcompMessage; int retries = 0; int ret; struct net_device *ndev; - struct netvsc_device *net_device = hv_get_drvdata(device); ndev = net_device->ndev; @@ -653,14 +662,15 @@ static void netvsc_receive_completion(void *context) /* Send a receive completion for the xfer page packet */ if (fsend_receive_comp) - netvsc_send_recv_completion(device, transaction_id, status); + netvsc_send_recv_completion(device, net_device, transaction_id, + status); } -static void netvsc_receive(struct hv_device *device, - struct vmpacket_descriptor *packet) +static void netvsc_receive(struct netvsc_device *net_device, + struct hv_device *device, + struct vmpacket_descriptor *packet) { - struct netvsc_device *net_device; struct vmtransfer_page_packet_header *vmxferpage_packet; struct nvsp_message *nvsp_packet; struct hv_netvsc_packet *netvsc_packet = NULL; @@ -673,9 +683,6 @@ static void netvsc_receive(struct hv_device *device, LIST_HEAD(listHead); - net_device = get_inbound_net_device(device); - if (!net_device) - return; ndev = net_device->ndev; /* @@ -741,7 +748,7 @@ static void netvsc_receive(struct hv_device *device, spin_unlock_irqrestore(&net_device->recv_pkt_list_lock, flags); - netvsc_send_recv_completion(device, + netvsc_send_recv_completion(device, net_device, vmxferpage_packet->d.trans_id, NVSP_STAT_FAIL); @@ -800,22 +807,16 @@ static void netvsc_channel_cb(void *context) struct netvsc_device *net_device; u32 bytes_recvd; u64 request_id; - unsigned char *packet; struct vmpacket_descriptor *desc; unsigned char *buffer; int bufferlen = NETVSC_PACKET_SIZE; struct net_device *ndev; - packet = kzalloc(NETVSC_PACKET_SIZE * sizeof(unsigned char), - GFP_ATOMIC); - if (!packet) - return; - buffer = packet; - net_device = get_inbound_net_device(device); if (!net_device) - goto out; + return; ndev = net_device->ndev; + buffer = net_device->cb_buffer; do { ret = vmbus_recvpacket_raw(device->channel, buffer, bufferlen, @@ -825,11 +826,13 @@ static void netvsc_channel_cb(void *context) desc = (struct vmpacket_descriptor *)buffer; switch (desc->type) { case VM_PKT_COMP: - netvsc_send_completion(device, desc); + netvsc_send_completion(net_device, + device, desc); break; case VM_PKT_DATA_USING_XFER_PAGES: - netvsc_receive(device, desc); + netvsc_receive(net_device, + device, desc); break; default: @@ -841,23 +844,16 @@ static void netvsc_channel_cb(void *context) break; } - /* reset */ - if (bufferlen > NETVSC_PACKET_SIZE) { - kfree(buffer); - buffer = packet; - bufferlen = NETVSC_PACKET_SIZE; - } } else { - /* reset */ - if (bufferlen > NETVSC_PACKET_SIZE) { - kfree(buffer); - buffer = packet; - bufferlen = NETVSC_PACKET_SIZE; - } - + /* + * We are done for this pass. + */ break; } + } else if (ret == -ENOBUFS) { + if (bufferlen > NETVSC_PACKET_SIZE) + kfree(buffer); /* Handle large packet */ buffer = kmalloc(bytes_recvd, GFP_ATOMIC); if (buffer == NULL) { @@ -872,8 +868,8 @@ static void netvsc_channel_cb(void *context) } } while (1); -out: - kfree(buffer); + if (bufferlen > NETVSC_PACKET_SIZE) + kfree(buffer); return; } @@ -907,7 +903,6 @@ int netvsc_device_add(struct hv_device *device, void *additional_info) ndev = net_device->ndev; /* Initialize the NetVSC channel extension */ - net_device->recv_buf_size = NETVSC_RECEIVE_BUFFER_SIZE; spin_lock_init(&net_device->recv_pkt_list_lock); INIT_LIST_HEAD(&net_device->recv_pkt_list); diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 7756118c2f0a..3d069901e6d9 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -88,8 +88,12 @@ static int netvsc_open(struct net_device *net) { struct net_device_context *net_device_ctx = netdev_priv(net); struct hv_device *device_obj = net_device_ctx->device_ctx; + struct netvsc_device *nvdev; + struct rndis_device *rdev; int ret = 0; + netif_carrier_off(net); + /* Open up the device */ ret = rndis_filter_open(device_obj); if (ret != 0) { @@ -99,6 +103,11 @@ static int netvsc_open(struct net_device *net) netif_start_queue(net); + nvdev = hv_get_drvdata(device_obj); + rdev = nvdev->extension; + if (!rdev->link_state) + netif_carrier_on(net); + return ret; } @@ -119,6 +128,27 @@ static int netvsc_close(struct net_device *net) return ret; } +static void *init_ppi_data(struct rndis_message *msg, u32 ppi_size, + int pkt_type) +{ + struct rndis_packet *rndis_pkt; + struct rndis_per_packet_info *ppi; + + rndis_pkt = &msg->msg.pkt; + rndis_pkt->data_offset += ppi_size; + + ppi = (struct rndis_per_packet_info *)((void *)rndis_pkt + + rndis_pkt->per_pkt_info_offset + rndis_pkt->per_pkt_info_len); + + ppi->size = ppi_size; + ppi->type = pkt_type; + ppi->ppi_offset = sizeof(struct rndis_per_packet_info); + + rndis_pkt->per_pkt_info_len += ppi_size; + + return ppi; +} + static void netvsc_xmit_completion(void *context) { struct hv_netvsc_packet *packet = (struct hv_netvsc_packet *)context; @@ -131,22 +161,164 @@ static void netvsc_xmit_completion(void *context) dev_kfree_skb_any(skb); } +static u32 fill_pg_buf(struct page *page, u32 offset, u32 len, + struct hv_page_buffer *pb) +{ + int j = 0; + + /* Deal with compund pages by ignoring unused part + * of the page. + */ + page += (offset >> PAGE_SHIFT); + offset &= ~PAGE_MASK; + + while (len > 0) { + unsigned long bytes; + + bytes = PAGE_SIZE - offset; + if (bytes > len) + bytes = len; + pb[j].pfn = page_to_pfn(page); + pb[j].offset = offset; + pb[j].len = bytes; + + offset += bytes; + len -= bytes; + + if (offset == PAGE_SIZE && len) { + page++; + offset = 0; + j++; + } + } + + return j + 1; +} + +static u32 init_page_array(void *hdr, u32 len, struct sk_buff *skb, + struct hv_page_buffer *pb) +{ + u32 slots_used = 0; + char *data = skb->data; + int frags = skb_shinfo(skb)->nr_frags; + int i; + + /* The packet is laid out thus: + * 1. hdr + * 2. skb linear data + * 3. skb fragment data + */ + if (hdr != NULL) + slots_used += fill_pg_buf(virt_to_page(hdr), + offset_in_page(hdr), + len, &pb[slots_used]); + + slots_used += fill_pg_buf(virt_to_page(data), + offset_in_page(data), + skb_headlen(skb), &pb[slots_used]); + + for (i = 0; i < frags; i++) { + skb_frag_t *frag = skb_shinfo(skb)->frags + i; + + slots_used += fill_pg_buf(skb_frag_page(frag), + frag->page_offset, + skb_frag_size(frag), &pb[slots_used]); + } + return slots_used; +} + +static int count_skb_frag_slots(struct sk_buff *skb) +{ + int i, frags = skb_shinfo(skb)->nr_frags; + int pages = 0; + + for (i = 0; i < frags; i++) { + skb_frag_t *frag = skb_shinfo(skb)->frags + i; + unsigned long size = skb_frag_size(frag); + unsigned long offset = frag->page_offset; + + /* Skip unused frames from start of page */ + offset &= ~PAGE_MASK; + pages += PFN_UP(offset + size); + } + return pages; +} + +static int netvsc_get_slots(struct sk_buff *skb) +{ + char *data = skb->data; + unsigned int offset = offset_in_page(data); + unsigned int len = skb_headlen(skb); + int slots; + int frag_slots; + + slots = DIV_ROUND_UP(offset + len, PAGE_SIZE); + frag_slots = count_skb_frag_slots(skb); + return slots + frag_slots; +} + +static u32 get_net_transport_info(struct sk_buff *skb, u32 *trans_off) +{ + u32 ret_val = TRANSPORT_INFO_NOT_IP; + + if ((eth_hdr(skb)->h_proto != htons(ETH_P_IP)) && + (eth_hdr(skb)->h_proto != htons(ETH_P_IPV6))) { + goto not_ip; + } + + *trans_off = skb_transport_offset(skb); + + if ((eth_hdr(skb)->h_proto == htons(ETH_P_IP))) { + struct iphdr *iphdr = ip_hdr(skb); + + if (iphdr->protocol == IPPROTO_TCP) + ret_val = TRANSPORT_INFO_IPV4_TCP; + else if (iphdr->protocol == IPPROTO_UDP) + ret_val = TRANSPORT_INFO_IPV4_UDP; + } else { + if (ipv6_hdr(skb)->nexthdr == IPPROTO_TCP) + ret_val = TRANSPORT_INFO_IPV6_TCP; + else if (ipv6_hdr(skb)->nexthdr == IPPROTO_UDP) + ret_val = TRANSPORT_INFO_IPV6_UDP; + } + +not_ip: + return ret_val; +} + static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net) { struct net_device_context *net_device_ctx = netdev_priv(net); struct hv_netvsc_packet *packet; int ret; - unsigned int i, num_pages, npg_data; - - /* Add multipages for skb->data and additional 2 for RNDIS */ - npg_data = (((unsigned long)skb->data + skb_headlen(skb) - 1) - >> PAGE_SHIFT) - ((unsigned long)skb->data >> PAGE_SHIFT) + 1; - num_pages = skb_shinfo(skb)->nr_frags + npg_data + 2; + unsigned int num_data_pgs; + struct rndis_message *rndis_msg; + struct rndis_packet *rndis_pkt; + u32 rndis_msg_size; + bool isvlan; + struct rndis_per_packet_info *ppi; + struct ndis_tcp_ip_checksum_info *csum_info; + struct ndis_tcp_lso_info *lso_info; + int hdr_offset; + u32 net_trans_info; + + + /* We will atmost need two pages to describe the rndis + * header. We can only transmit MAX_PAGE_BUFFER_COUNT number + * of pages in a single packet. + */ + num_data_pgs = netvsc_get_slots(skb) + 2; + if (num_data_pgs > MAX_PAGE_BUFFER_COUNT) { + netdev_err(net, "Packet too big: %u\n", skb->len); + dev_kfree_skb(skb); + net->stats.tx_dropped++; + return NETDEV_TX_OK; + } /* Allocate a netvsc packet based on # of frags. */ packet = kzalloc(sizeof(struct hv_netvsc_packet) + - (num_pages * sizeof(struct hv_page_buffer)) + - sizeof(struct rndis_filter_packet) + + (num_data_pgs * sizeof(struct hv_page_buffer)) + + sizeof(struct rndis_message) + NDIS_VLAN_PPI_SIZE, GFP_ATOMIC); if (!packet) { /* out of memory, drop packet */ @@ -159,53 +331,111 @@ static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net) packet->vlan_tci = skb->vlan_tci; - packet->extension = (void *)(unsigned long)packet + + packet->is_data_pkt = true; + packet->total_data_buflen = skb->len; + + packet->rndis_msg = (struct rndis_message *)((unsigned long)packet + sizeof(struct hv_netvsc_packet) + - (num_pages * sizeof(struct hv_page_buffer)); + (num_data_pgs * sizeof(struct hv_page_buffer))); - /* If the rndis msg goes beyond 1 page, we will add 1 later */ - packet->page_buf_cnt = num_pages - 1; + /* Set the completion routine */ + packet->completion.send.send_completion = netvsc_xmit_completion; + packet->completion.send.send_completion_ctx = packet; + packet->completion.send.send_completion_tid = (unsigned long)skb; - /* Initialize it from the skb */ - packet->total_data_buflen = skb->len; + isvlan = packet->vlan_tci & VLAN_TAG_PRESENT; + + /* Add the rndis header */ + rndis_msg = packet->rndis_msg; + rndis_msg->ndis_msg_type = RNDIS_MSG_PACKET; + rndis_msg->msg_len = packet->total_data_buflen; + rndis_pkt = &rndis_msg->msg.pkt; + rndis_pkt->data_offset = sizeof(struct rndis_packet); + rndis_pkt->data_len = packet->total_data_buflen; + rndis_pkt->per_pkt_info_offset = sizeof(struct rndis_packet); + + rndis_msg_size = RNDIS_MESSAGE_SIZE(struct rndis_packet); + + if (isvlan) { + struct ndis_pkt_8021q_info *vlan; + + rndis_msg_size += NDIS_VLAN_PPI_SIZE; + ppi = init_ppi_data(rndis_msg, NDIS_VLAN_PPI_SIZE, + IEEE_8021Q_INFO); + vlan = (struct ndis_pkt_8021q_info *)((void *)ppi + + ppi->ppi_offset); + vlan->vlanid = packet->vlan_tci & VLAN_VID_MASK; + vlan->pri = (packet->vlan_tci & VLAN_PRIO_MASK) >> + VLAN_PRIO_SHIFT; + } + + net_trans_info = get_net_transport_info(skb, &hdr_offset); + if (net_trans_info == TRANSPORT_INFO_NOT_IP) + goto do_send; + + /* + * Setup the sendside checksum offload only if this is not a + * GSO packet. + */ + if (skb_is_gso(skb)) + goto do_lso; - /* Start filling in the page buffers starting after RNDIS buffer. */ - packet->page_buf[1].pfn = virt_to_phys(skb->data) >> PAGE_SHIFT; - packet->page_buf[1].offset - = (unsigned long)skb->data & (PAGE_SIZE - 1); - if (npg_data == 1) - packet->page_buf[1].len = skb_headlen(skb); + rndis_msg_size += NDIS_CSUM_PPI_SIZE; + ppi = init_ppi_data(rndis_msg, NDIS_CSUM_PPI_SIZE, + TCPIP_CHKSUM_PKTINFO); + + csum_info = (struct ndis_tcp_ip_checksum_info *)((void *)ppi + + ppi->ppi_offset); + + if (net_trans_info & (INFO_IPV4 << 16)) + csum_info->transmit.is_ipv4 = 1; else - packet->page_buf[1].len = PAGE_SIZE - - packet->page_buf[1].offset; - - for (i = 2; i <= npg_data; i++) { - packet->page_buf[i].pfn = virt_to_phys(skb->data - + PAGE_SIZE * (i-1)) >> PAGE_SHIFT; - packet->page_buf[i].offset = 0; - packet->page_buf[i].len = PAGE_SIZE; + csum_info->transmit.is_ipv6 = 1; + + if (net_trans_info & INFO_TCP) { + csum_info->transmit.tcp_checksum = 1; + csum_info->transmit.tcp_header_offset = hdr_offset; + } else if (net_trans_info & INFO_UDP) { + csum_info->transmit.udp_checksum = 1; } - if (npg_data > 1) - packet->page_buf[npg_data].len = (((unsigned long)skb->data - + skb_headlen(skb) - 1) & (PAGE_SIZE - 1)) + 1; - - /* Additional fragments are after SKB data */ - for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { - const skb_frag_t *f = &skb_shinfo(skb)->frags[i]; - - packet->page_buf[i+npg_data+1].pfn = - page_to_pfn(skb_frag_page(f)); - packet->page_buf[i+npg_data+1].offset = f->page_offset; - packet->page_buf[i+npg_data+1].len = skb_frag_size(f); + goto do_send; + +do_lso: + rndis_msg_size += NDIS_LSO_PPI_SIZE; + ppi = init_ppi_data(rndis_msg, NDIS_LSO_PPI_SIZE, + TCP_LARGESEND_PKTINFO); + + lso_info = (struct ndis_tcp_lso_info *)((void *)ppi + + ppi->ppi_offset); + + lso_info->lso_v2_transmit.type = NDIS_TCP_LARGE_SEND_OFFLOAD_V2_TYPE; + if (net_trans_info & (INFO_IPV4 << 16)) { + lso_info->lso_v2_transmit.ip_version = + NDIS_TCP_LARGE_SEND_OFFLOAD_IPV4; + ip_hdr(skb)->tot_len = 0; + ip_hdr(skb)->check = 0; + tcp_hdr(skb)->check = + ~csum_tcpudp_magic(ip_hdr(skb)->saddr, + ip_hdr(skb)->daddr, 0, IPPROTO_TCP, 0); + } else { + lso_info->lso_v2_transmit.ip_version = + NDIS_TCP_LARGE_SEND_OFFLOAD_IPV6; + ipv6_hdr(skb)->payload_len = 0; + tcp_hdr(skb)->check = + ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr, + &ipv6_hdr(skb)->daddr, 0, IPPROTO_TCP, 0); } + lso_info->lso_v2_transmit.tcp_header_offset = hdr_offset; + lso_info->lso_v2_transmit.mss = skb_shinfo(skb)->gso_size; - /* Set the completion routine */ - packet->completion.send.send_completion = netvsc_xmit_completion; - packet->completion.send.send_completion_ctx = packet; - packet->completion.send.send_completion_tid = (unsigned long)skb; +do_send: + /* Start filling in the page buffers with the rndis hdr */ + rndis_msg->msg_len += rndis_msg_size; + packet->page_buf_cnt = init_page_array(rndis_msg, rndis_msg_size, + skb, &packet->page_buf[0]); + + ret = netvsc_send(net_device_ctx->device_ctx, packet); - ret = rndis_filter_send(net_device_ctx->device_ctx, - packet); if (ret == 0) { net->stats.tx_bytes += skb->len; net->stats.tx_packets++; @@ -229,23 +459,24 @@ void netvsc_linkstatus_callback(struct hv_device *device_obj, struct net_device *net; struct net_device_context *ndev_ctx; struct netvsc_device *net_device; + struct rndis_device *rdev; net_device = hv_get_drvdata(device_obj); + rdev = net_device->extension; + + rdev->link_state = status != 1; + net = net_device->ndev; - if (!net) { - netdev_err(net, "got link status but net device " - "not initialized yet\n"); + if (!net || net->reg_state != NETREG_REGISTERED) return; - } + ndev_ctx = netdev_priv(net); if (status == 1) { - netif_carrier_on(net); - ndev_ctx = netdev_priv(net); schedule_delayed_work(&ndev_ctx->dwork, 0); schedule_delayed_work(&ndev_ctx->dwork, msecs_to_jiffies(20)); } else { - netif_carrier_off(net); + schedule_delayed_work(&ndev_ctx->dwork, 0); } } @@ -254,7 +485,8 @@ void netvsc_linkstatus_callback(struct hv_device *device_obj, * "wire" on the specified device. */ int netvsc_recv_callback(struct hv_device *device_obj, - struct hv_netvsc_packet *packet) + struct hv_netvsc_packet *packet, + struct ndis_tcp_ip_checksum_info *csum_info) { struct net_device *net; struct sk_buff *skb; @@ -281,7 +513,17 @@ int netvsc_recv_callback(struct hv_device *device_obj, packet->total_data_buflen); skb->protocol = eth_type_trans(skb, net); - skb->ip_summed = CHECKSUM_NONE; + if (csum_info) { + /* We only look at the IP checksum here. + * Should we be dropping the packet if checksum + * failed? How do we deal with other checksums - TCP/UDP? + */ + if (csum_info->receive.ip_checksum_succeeded) + skb->ip_summed = CHECKSUM_UNNECESSARY; + else + skb->ip_summed = CHECKSUM_NONE; + } + if (packet->vlan_tci & VLAN_TAG_PRESENT) __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), packet->vlan_tci); @@ -317,7 +559,7 @@ static int netvsc_change_mtu(struct net_device *ndev, int mtu) if (nvdev == NULL || nvdev->destroy) return -ENODEV; - if (nvdev->nvsp_version == NVSP_PROTOCOL_VERSION_2) + if (nvdev->nvsp_version >= NVSP_PROTOCOL_VERSION_2) limit = NETVSC_MTU; if (mtu < 68 || mtu > limit) @@ -388,17 +630,35 @@ static const struct net_device_ops device_ops = { * current context when receiving RNDIS_STATUS_MEDIA_CONNECT event. So, add * another netif_notify_peers() into a delayed work, otherwise GARP packet * will not be sent after quick migration, and cause network disconnection. + * Also, we update the carrier status here. */ -static void netvsc_send_garp(struct work_struct *w) +static void netvsc_link_change(struct work_struct *w) { struct net_device_context *ndev_ctx; struct net_device *net; struct netvsc_device *net_device; + struct rndis_device *rdev; + bool notify; + + rtnl_lock(); ndev_ctx = container_of(w, struct net_device_context, dwork.work); net_device = hv_get_drvdata(ndev_ctx->device_ctx); + rdev = net_device->extension; net = net_device->ndev; - netdev_notify_peers(net); + + if (rdev->link_state) { + netif_carrier_off(net); + notify = false; + } else { + netif_carrier_on(net); + notify = true; + } + + rtnl_unlock(); + + if (notify) + netdev_notify_peers(net); } @@ -414,20 +674,18 @@ static int netvsc_probe(struct hv_device *dev, if (!net) return -ENOMEM; - /* Set initial state */ - netif_carrier_off(net); - net_device_ctx = netdev_priv(net); net_device_ctx->device_ctx = dev; hv_set_drvdata(dev, net); - INIT_DELAYED_WORK(&net_device_ctx->dwork, netvsc_send_garp); + INIT_DELAYED_WORK(&net_device_ctx->dwork, netvsc_link_change); INIT_WORK(&net_device_ctx->work, do_set_multicast); net->netdev_ops = &device_ops; - /* TODO: Add GSO and Checksum offload */ - net->hw_features = 0; - net->features = NETIF_F_HW_VLAN_CTAG_TX; + net->hw_features = NETIF_F_RXCSUM | NETIF_F_SG | NETIF_F_IP_CSUM | + NETIF_F_TSO; + net->features = NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_SG | NETIF_F_RXCSUM | + NETIF_F_IP_CSUM | NETIF_F_TSO; SET_ETHTOOL_OPS(net, ðtool_ops); SET_NETDEV_DEV(net, &dev->device); @@ -443,8 +701,6 @@ static int netvsc_probe(struct hv_device *dev, } memcpy(net->dev_addr, device_info.mac_adr, ETH_ALEN); - netif_carrier_on(net); - ret = register_netdev(net); if (ret != 0) { pr_err("Unable to register netdev.\n"); diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c index 1084e5de3ceb..54553df74cd2 100644 --- a/drivers/net/hyperv/rndis_filter.c +++ b/drivers/net/hyperv/rndis_filter.c @@ -58,9 +58,6 @@ struct rndis_request { u8 request_ext[RNDIS_EXT_LEN]; }; -static void rndis_filter_send_completion(void *ctx); - - static struct rndis_device *get_rndis_device(void) { struct rndis_device *device; @@ -277,7 +274,7 @@ static void rndis_filter_receive_response(struct rndis_device *dev, "rndis response buffer overflow " "detected (size %u max %zu)\n", resp->msg_len, - sizeof(struct rndis_filter_packet)); + sizeof(struct rndis_message)); if (resp->ndis_msg_type == RNDIS_MSG_RESET_C) { @@ -353,6 +350,7 @@ static void rndis_filter_receive_data(struct rndis_device *dev, struct rndis_packet *rndis_pkt; u32 data_offset; struct ndis_pkt_8021q_info *vlan; + struct ndis_tcp_ip_checksum_info *csum_info; rndis_pkt = &msg->msg.pkt; @@ -391,7 +389,8 @@ static void rndis_filter_receive_data(struct rndis_device *dev, pkt->vlan_tci = 0; } - netvsc_recv_callback(dev->net_dev->dev, pkt); + csum_info = rndis_get_ppi(rndis_pkt, TCPIP_CHKSUM_PKTINFO); + netvsc_recv_callback(dev->net_dev->dev, pkt, csum_info); } int rndis_filter_receive(struct hv_device *dev, @@ -610,6 +609,61 @@ cleanup: return ret; } +int rndis_filter_set_offload_params(struct hv_device *hdev, + struct ndis_offload_params *req_offloads) +{ + struct netvsc_device *nvdev = hv_get_drvdata(hdev); + struct rndis_device *rdev = nvdev->extension; + struct net_device *ndev = nvdev->ndev; + struct rndis_request *request; + struct rndis_set_request *set; + struct ndis_offload_params *offload_params; + struct rndis_set_complete *set_complete; + u32 extlen = sizeof(struct ndis_offload_params); + int ret, t; + + request = get_rndis_request(rdev, RNDIS_MSG_SET, + RNDIS_MESSAGE_SIZE(struct rndis_set_request) + extlen); + if (!request) + return -ENOMEM; + + set = &request->request_msg.msg.set_req; + set->oid = OID_TCP_OFFLOAD_PARAMETERS; + set->info_buflen = extlen; + set->info_buf_offset = sizeof(struct rndis_set_request); + set->dev_vc_handle = 0; + + offload_params = (struct ndis_offload_params *)((ulong)set + + set->info_buf_offset); + *offload_params = *req_offloads; + offload_params->header.type = NDIS_OBJECT_TYPE_DEFAULT; + offload_params->header.revision = NDIS_OFFLOAD_PARAMETERS_REVISION_3; + offload_params->header.size = extlen; + + ret = rndis_filter_send_request(rdev, request); + if (ret != 0) + goto cleanup; + + t = wait_for_completion_timeout(&request->wait_event, 5*HZ); + if (t == 0) { + netdev_err(ndev, "timeout before we got aOFFLOAD set response...\n"); + /* can't put_rndis_request, since we may still receive a + * send-completion. + */ + return -EBUSY; + } else { + set_complete = &request->response_msg.msg.set_complete; + if (set_complete->status != RNDIS_STATUS_SUCCESS) { + netdev_err(ndev, "Fail to set MAC on host side:0x%x\n", + set_complete->status); + ret = -EINVAL; + } + } + +cleanup: + put_rndis_request(rdev, request); + return ret; +} static int rndis_filter_query_device_link_status(struct rndis_device *dev) { @@ -810,6 +864,7 @@ int rndis_filter_device_add(struct hv_device *dev, struct netvsc_device *net_device; struct rndis_device *rndis_device; struct netvsc_device_info *device_info = additional_info; + struct ndis_offload_params offloads; rndis_device = get_rndis_device(); if (!rndis_device) @@ -849,6 +904,26 @@ int rndis_filter_device_add(struct hv_device *dev, memcpy(device_info->mac_adr, rndis_device->hw_mac_adr, ETH_ALEN); + /* Turn on the offloads; the host supports all of the relevant + * offloads. + */ + memset(&offloads, 0, sizeof(struct ndis_offload_params)); + /* A value of zero means "no change"; now turn on what we + * want. + */ + offloads.ip_v4_csum = NDIS_OFFLOAD_PARAMETERS_TX_RX_ENABLED; + offloads.tcp_ip_v4_csum = NDIS_OFFLOAD_PARAMETERS_TX_RX_ENABLED; + offloads.udp_ip_v4_csum = NDIS_OFFLOAD_PARAMETERS_TX_RX_ENABLED; + offloads.tcp_ip_v6_csum = NDIS_OFFLOAD_PARAMETERS_TX_RX_ENABLED; + offloads.udp_ip_v6_csum = NDIS_OFFLOAD_PARAMETERS_TX_RX_ENABLED; + offloads.lso_v2_ipv4 = NDIS_OFFLOAD_PARAMETERS_LSOV2_ENABLED; + + + ret = rndis_filter_set_offload_params(dev, &offloads); + if (ret) + goto err_dev_remv; + + rndis_filter_query_device_link_status(rndis_device); device_info->link_state = rndis_device->link_state; @@ -858,6 +933,10 @@ int rndis_filter_device_add(struct hv_device *dev, device_info->link_state ? "down" : "up"); return ret; + +err_dev_remv: + rndis_filter_device_remove(dev); + return ret; } void rndis_filter_device_remove(struct hv_device *dev) @@ -894,101 +973,3 @@ int rndis_filter_close(struct hv_device *dev) return rndis_filter_close_device(nvdev->extension); } - -int rndis_filter_send(struct hv_device *dev, - struct hv_netvsc_packet *pkt) -{ - int ret; - struct rndis_filter_packet *filter_pkt; - struct rndis_message *rndis_msg; - struct rndis_packet *rndis_pkt; - u32 rndis_msg_size; - bool isvlan = pkt->vlan_tci & VLAN_TAG_PRESENT; - - /* Add the rndis header */ - filter_pkt = (struct rndis_filter_packet *)pkt->extension; - - rndis_msg = &filter_pkt->msg; - rndis_msg_size = RNDIS_MESSAGE_SIZE(struct rndis_packet); - if (isvlan) - rndis_msg_size += NDIS_VLAN_PPI_SIZE; - - rndis_msg->ndis_msg_type = RNDIS_MSG_PACKET; - rndis_msg->msg_len = pkt->total_data_buflen + - rndis_msg_size; - - rndis_pkt = &rndis_msg->msg.pkt; - rndis_pkt->data_offset = sizeof(struct rndis_packet); - if (isvlan) - rndis_pkt->data_offset += NDIS_VLAN_PPI_SIZE; - rndis_pkt->data_len = pkt->total_data_buflen; - - if (isvlan) { - struct rndis_per_packet_info *ppi; - struct ndis_pkt_8021q_info *vlan; - - rndis_pkt->per_pkt_info_offset = sizeof(struct rndis_packet); - rndis_pkt->per_pkt_info_len = NDIS_VLAN_PPI_SIZE; - - ppi = (struct rndis_per_packet_info *)((ulong)rndis_pkt + - rndis_pkt->per_pkt_info_offset); - ppi->size = NDIS_VLAN_PPI_SIZE; - ppi->type = IEEE_8021Q_INFO; - ppi->ppi_offset = sizeof(struct rndis_per_packet_info); - - vlan = (struct ndis_pkt_8021q_info *)((ulong)ppi + - ppi->ppi_offset); - vlan->vlanid = pkt->vlan_tci & VLAN_VID_MASK; - vlan->pri = (pkt->vlan_tci & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT; - } - - pkt->is_data_pkt = true; - pkt->page_buf[0].pfn = virt_to_phys(rndis_msg) >> PAGE_SHIFT; - pkt->page_buf[0].offset = - (unsigned long)rndis_msg & (PAGE_SIZE-1); - pkt->page_buf[0].len = rndis_msg_size; - - /* Add one page_buf if the rndis msg goes beyond page boundary */ - if (pkt->page_buf[0].offset + rndis_msg_size > PAGE_SIZE) { - int i; - for (i = pkt->page_buf_cnt; i > 1; i--) - pkt->page_buf[i] = pkt->page_buf[i-1]; - pkt->page_buf_cnt++; - pkt->page_buf[0].len = PAGE_SIZE - pkt->page_buf[0].offset; - pkt->page_buf[1].pfn = virt_to_phys((void *)((ulong) - rndis_msg + pkt->page_buf[0].len)) >> PAGE_SHIFT; - pkt->page_buf[1].offset = 0; - pkt->page_buf[1].len = rndis_msg_size - pkt->page_buf[0].len; - } - - /* Save the packet send completion and context */ - filter_pkt->completion = pkt->completion.send.send_completion; - filter_pkt->completion_ctx = - pkt->completion.send.send_completion_ctx; - - /* Use ours */ - pkt->completion.send.send_completion = rndis_filter_send_completion; - pkt->completion.send.send_completion_ctx = filter_pkt; - - ret = netvsc_send(dev, pkt); - if (ret != 0) { - /* - * Reset the completion to originals to allow retries from - * above - */ - pkt->completion.send.send_completion = - filter_pkt->completion; - pkt->completion.send.send_completion_ctx = - filter_pkt->completion_ctx; - } - - return ret; -} - -static void rndis_filter_send_completion(void *ctx) -{ - struct rndis_filter_packet *filter_pkt = ctx; - - /* Pass it back to the original handler */ - filter_pkt->completion(filter_pkt->completion_ctx); -} diff --git a/drivers/net/ieee802154/Kconfig b/drivers/net/ieee802154/Kconfig index 08ae4655423a..3e89beab64fd 100644 --- a/drivers/net/ieee802154/Kconfig +++ b/drivers/net/ieee802154/Kconfig @@ -15,9 +15,9 @@ config IEEE802154_FAKEHARD depends on IEEE802154_DRIVERS ---help--- Say Y here to enable the fake driver that serves as an example - of HardMAC device driver. + of HardMAC device driver. - This driver can also be built as a module. To do so say M here. + This driver can also be built as a module. To do so say M here. The module will be called 'fakehard'. config IEEE802154_FAKELB @@ -31,17 +31,23 @@ config IEEE802154_FAKELB The module will be called 'fakelb'. config IEEE802154_AT86RF230 - depends on IEEE802154_DRIVERS && MAC802154 - tristate "AT86RF230/231 transceiver driver" - depends on SPI + depends on IEEE802154_DRIVERS && MAC802154 + tristate "AT86RF230/231/233/212 transceiver driver" + depends on SPI + ---help--- + Say Y here to enable the at86rf230/231/233/212 SPI 802.15.4 wireless + controller. + + This driver can also be built as a module. To do so, say M here. + the module will be called 'at86rf230'. config IEEE802154_MRF24J40 - tristate "Microchip MRF24J40 transceiver driver" - depends on IEEE802154_DRIVERS && MAC802154 - depends on SPI - ---help--- - Say Y here to enable the MRF24J20 SPI 802.15.4 wireless - controller. - - This driver can also be built as a module. To do so, say M here. - the module will be called 'mrf24j40'. + tristate "Microchip MRF24J40 transceiver driver" + depends on IEEE802154_DRIVERS && MAC802154 + depends on SPI + ---help--- + Say Y here to enable the MRF24J20 SPI 802.15.4 wireless + controller. + + This driver can also be built as a module. To do so, say M here. + the module will be called 'mrf24j40'. diff --git a/drivers/net/ieee802154/at86rf230.c b/drivers/net/ieee802154/at86rf230.c index ab31544bc254..b8e732121a85 100644 --- a/drivers/net/ieee802154/at86rf230.c +++ b/drivers/net/ieee802154/at86rf230.c @@ -37,7 +37,6 @@ struct at86rf230_local { struct spi_device *spi; - int rstn, slp_tr, dig2; u8 part; u8 vers; @@ -53,8 +52,16 @@ struct at86rf230_local { spinlock_t lock; bool irq_busy; bool is_tx; + bool tx_aret; + + int rssi_base_val; }; +static bool is_rf212(struct at86rf230_local *local) +{ + return local->part == 7; +} + #define RG_TRX_STATUS (0x01) #define SR_TRX_STATUS 0x01, 0x1f, 0 #define SR_RESERVED_01_3 0x01, 0x20, 5 @@ -100,7 +107,10 @@ struct at86rf230_local { #define SR_SFD_VALUE 0x0b, 0xff, 0 #define RG_TRX_CTRL_2 (0x0c) #define SR_OQPSK_DATA_RATE 0x0c, 0x03, 0 -#define SR_RESERVED_0c_2 0x0c, 0x7c, 2 +#define SR_SUB_MODE 0x0c, 0x04, 2 +#define SR_BPSK_QPSK 0x0c, 0x08, 3 +#define SR_OQPSK_SUB1_RC_EN 0x0c, 0x10, 4 +#define SR_RESERVED_0c_5 0x0c, 0x60, 5 #define SR_RX_SAFE_MODE 0x0c, 0x80, 7 #define RG_ANT_DIV (0x0d) #define SR_ANT_CTRL 0x0d, 0x03, 0 @@ -145,7 +155,7 @@ struct at86rf230_local { #define SR_RESERVED_17_5 0x17, 0x08, 3 #define SR_AACK_UPLD_RES_FT 0x17, 0x10, 4 #define SR_AACK_FLTR_RES_FT 0x17, 0x20, 5 -#define SR_RESERVED_17_2 0x17, 0x40, 6 +#define SR_CSMA_LBT_MODE 0x17, 0x40, 6 #define SR_RESERVED_17_1 0x17, 0x80, 7 #define RG_FTN_CTRL (0x18) #define SR_RESERVED_18_2 0x18, 0x7f, 0 @@ -234,6 +244,7 @@ struct at86rf230_local { #define STATE_TX_ON 0x09 /* 0x0a - 0x0e */ /* 0x0a - UNSUPPORTED_ATTRIBUTE */ #define STATE_SLEEP 0x0F +#define STATE_PREP_DEEP_SLEEP 0x10 #define STATE_BUSY_RX_AACK 0x11 #define STATE_BUSY_TX_ARET 0x12 #define STATE_RX_AACK_ON 0x16 @@ -244,6 +255,57 @@ struct at86rf230_local { #define STATE_TRANSITION_IN_PROGRESS 0x1F static int +__at86rf230_detect_device(struct spi_device *spi, u16 *man_id, u8 *part, + u8 *version) +{ + u8 data[4]; + u8 *buf = kmalloc(2, GFP_KERNEL); + int status; + struct spi_message msg; + struct spi_transfer xfer = { + .len = 2, + .tx_buf = buf, + .rx_buf = buf, + }; + u8 reg; + + if (!buf) + return -ENOMEM; + + for (reg = RG_PART_NUM; reg <= RG_MAN_ID_1; reg++) { + buf[0] = (reg & CMD_REG_MASK) | CMD_REG; + buf[1] = 0xff; + dev_vdbg(&spi->dev, "buf[0] = %02x\n", buf[0]); + spi_message_init(&msg); + spi_message_add_tail(&xfer, &msg); + + status = spi_sync(spi, &msg); + dev_vdbg(&spi->dev, "status = %d\n", status); + if (msg.status) + status = msg.status; + + dev_vdbg(&spi->dev, "status = %d\n", status); + dev_vdbg(&spi->dev, "buf[0] = %02x\n", buf[0]); + dev_vdbg(&spi->dev, "buf[1] = %02x\n", buf[1]); + + if (status == 0) + data[reg - RG_PART_NUM] = buf[1]; + else + break; + } + + if (status == 0) { + *part = data[0]; + *version = data[1]; + *man_id = (data[3] << 8) | data[2]; + } + + kfree(buf); + + return status; +} + +static int __at86rf230_write(struct at86rf230_local *lp, u8 addr, u8 data) { u8 *buf = lp->buf; @@ -489,7 +551,9 @@ at86rf230_state(struct ieee802154_dev *dev, int state) } while (val == STATE_TRANSITION_IN_PROGRESS); - if (val == desired_status) + if (val == desired_status || + (desired_status == STATE_RX_ON && val == STATE_BUSY_RX) || + (desired_status == STATE_RX_AACK_ON && val == STATE_BUSY_RX_AACK)) return 0; pr_err("unexpected state change: %d, asked for %d\n", val, state); @@ -510,7 +574,11 @@ at86rf230_start(struct ieee802154_dev *dev) if (rc) return rc; - return at86rf230_state(dev, STATE_RX_ON); + rc = at86rf230_state(dev, STATE_FORCE_TX_ON); + if (rc) + return rc; + + return at86rf230_state(dev, STATE_RX_AACK_ON); } static void @@ -520,6 +588,39 @@ at86rf230_stop(struct ieee802154_dev *dev) } static int +at86rf230_set_channel(struct at86rf230_local *lp, int page, int channel) +{ + lp->rssi_base_val = -91; + + return at86rf230_write_subreg(lp, SR_CHANNEL, channel); +} + +static int +at86rf212_set_channel(struct at86rf230_local *lp, int page, int channel) +{ + int rc; + + if (channel == 0) + rc = at86rf230_write_subreg(lp, SR_SUB_MODE, 0); + else + rc = at86rf230_write_subreg(lp, SR_SUB_MODE, 1); + if (rc < 0) + return rc; + + if (page == 0) { + rc = at86rf230_write_subreg(lp, SR_BPSK_QPSK, 0); + lp->rssi_base_val = -100; + } else { + rc = at86rf230_write_subreg(lp, SR_BPSK_QPSK, 1); + lp->rssi_base_val = -98; + } + if (rc < 0) + return rc; + + return at86rf230_write_subreg(lp, SR_CHANNEL, channel); +} + +static int at86rf230_channel(struct ieee802154_dev *dev, int page, int channel) { struct at86rf230_local *lp = dev->priv; @@ -527,14 +628,22 @@ at86rf230_channel(struct ieee802154_dev *dev, int page, int channel) might_sleep(); - if (page != 0 || channel < 11 || channel > 26) { + if (page < 0 || page > 31 || + !(lp->dev->phy->channels_supported[page] & BIT(channel))) { WARN_ON(1); return -EINVAL; } - rc = at86rf230_write_subreg(lp, SR_CHANNEL, channel); + if (is_rf212(lp)) + rc = at86rf212_set_channel(lp, page, channel); + else + rc = at86rf230_set_channel(lp, page, channel); + if (rc < 0) + return rc; + msleep(1); /* Wait for PLL */ dev->phy->current_channel = channel; + dev->phy->current_page = page; return 0; } @@ -568,6 +677,12 @@ at86rf230_xmit(struct ieee802154_dev *dev, struct sk_buff *skb) if (rc) goto err_rx; + if (lp->tx_aret) { + rc = at86rf230_write_subreg(lp, SR_TRX_CMD, STATE_TX_ARET_ON); + if (rc) + goto err_rx; + } + rc = at86rf230_write_subreg(lp, SR_TRX_CMD, STATE_BUSY_TX); if (rc) goto err_rx; @@ -668,6 +783,93 @@ at86rf230_set_hw_addr_filt(struct ieee802154_dev *dev, return 0; } +static int +at86rf212_set_txpower(struct ieee802154_dev *dev, int db) +{ + struct at86rf230_local *lp = dev->priv; + + /* typical maximum output is 5dBm with RG_PHY_TX_PWR 0x60, lower five + * bits decrease power in 1dB steps. 0x60 represents extra PA gain of + * 0dB. + * thus, supported values for db range from -26 to 5, for 31dB of + * reduction to 0dB of reduction. + */ + if (db > 5 || db < -26) + return -EINVAL; + + db = -(db - 5); + + return __at86rf230_write(lp, RG_PHY_TX_PWR, 0x60 | db); +} + +static int +at86rf212_set_lbt(struct ieee802154_dev *dev, bool on) +{ + struct at86rf230_local *lp = dev->priv; + + return at86rf230_write_subreg(lp, SR_CSMA_LBT_MODE, on); +} + +static int +at86rf212_set_cca_mode(struct ieee802154_dev *dev, u8 mode) +{ + struct at86rf230_local *lp = dev->priv; + + return at86rf230_write_subreg(lp, SR_CCA_MODE, mode); +} + +static int +at86rf212_set_cca_ed_level(struct ieee802154_dev *dev, s32 level) +{ + struct at86rf230_local *lp = dev->priv; + int desens_steps; + + if (level < lp->rssi_base_val || level > 30) + return -EINVAL; + + desens_steps = (level - lp->rssi_base_val) * 100 / 207; + + return at86rf230_write_subreg(lp, SR_CCA_ED_THRES, desens_steps); +} + +static int +at86rf212_set_csma_params(struct ieee802154_dev *dev, u8 min_be, u8 max_be, + u8 retries) +{ + struct at86rf230_local *lp = dev->priv; + int rc; + + if (min_be > max_be || max_be > 8 || retries > 5) + return -EINVAL; + + rc = at86rf230_write_subreg(lp, SR_MIN_BE, min_be); + if (rc) + return rc; + + rc = at86rf230_write_subreg(lp, SR_MAX_BE, max_be); + if (rc) + return rc; + + return at86rf230_write_subreg(lp, SR_MAX_CSMA_RETRIES, max_be); +} + +static int +at86rf212_set_frame_retries(struct ieee802154_dev *dev, s8 retries) +{ + struct at86rf230_local *lp = dev->priv; + int rc = 0; + + if (retries < -1 || retries > 15) + return -EINVAL; + + lp->tx_aret = retries >= 0; + + if (retries >= 0) + rc = at86rf230_write_subreg(lp, SR_MAX_FRAME_RETRIES, retries); + + return rc; +} + static struct ieee802154_ops at86rf230_ops = { .owner = THIS_MODULE, .xmit = at86rf230_xmit, @@ -678,6 +880,22 @@ static struct ieee802154_ops at86rf230_ops = { .set_hw_addr_filt = at86rf230_set_hw_addr_filt, }; +static struct ieee802154_ops at86rf212_ops = { + .owner = THIS_MODULE, + .xmit = at86rf230_xmit, + .ed = at86rf230_ed, + .set_channel = at86rf230_channel, + .start = at86rf230_start, + .stop = at86rf230_stop, + .set_hw_addr_filt = at86rf230_set_hw_addr_filt, + .set_txpower = at86rf212_set_txpower, + .set_lbt = at86rf212_set_lbt, + .set_cca_mode = at86rf212_set_cca_mode, + .set_cca_ed_level = at86rf212_set_cca_ed_level, + .set_csma_params = at86rf212_set_csma_params, + .set_frame_retries = at86rf212_set_frame_retries, +}; + static void at86rf230_irqwork(struct work_struct *work) { struct at86rf230_local *lp = @@ -752,22 +970,15 @@ static int at86rf230_hw_init(struct at86rf230_local *lp) struct at86rf230_platform_data *pdata = lp->spi->dev.platform_data; int rc, irq_pol; u8 status; + u8 csma_seed[2]; rc = at86rf230_read_subreg(lp, SR_TRX_STATUS, &status); if (rc) return rc; - dev_info(&lp->spi->dev, "Status: %02x\n", status); - if (status == STATE_P_ON) { - rc = at86rf230_write_subreg(lp, SR_TRX_CMD, STATE_TRX_OFF); - if (rc) - return rc; - msleep(1); - rc = at86rf230_read_subreg(lp, SR_TRX_STATUS, &status); - if (rc) - return rc; - dev_info(&lp->spi->dev, "Status: %02x\n", status); - } + rc = at86rf230_write_subreg(lp, SR_TRX_CMD, STATE_FORCE_TRX_OFF); + if (rc) + return rc; /* configure irq polarity, defaults to high active */ if (pdata->irq_type & (IRQF_TRIGGER_FALLING | IRQF_TRIGGER_LOW)) @@ -783,6 +994,14 @@ static int at86rf230_hw_init(struct at86rf230_local *lp) if (rc) return rc; + get_random_bytes(csma_seed, ARRAY_SIZE(csma_seed)); + rc = at86rf230_write_subreg(lp, SR_CSMA_SEED_0, csma_seed[0]); + if (rc) + return rc; + rc = at86rf230_write_subreg(lp, SR_CSMA_SEED_1, csma_seed[1]); + if (rc) + return rc; + /* CLKM changes are applied immediately */ rc = at86rf230_write_subreg(lp, SR_CLKM_SHA_SEL, 0x00); if (rc) @@ -795,16 +1014,6 @@ static int at86rf230_hw_init(struct at86rf230_local *lp) /* Wait the next SLEEP cycle */ msleep(100); - rc = at86rf230_write_subreg(lp, SR_TRX_CMD, STATE_TX_ON); - if (rc) - return rc; - msleep(1); - - rc = at86rf230_read_subreg(lp, SR_TRX_STATUS, &status); - if (rc) - return rc; - dev_info(&lp->spi->dev, "Status: %02x\n", status); - rc = at86rf230_read_subreg(lp, SR_DVDD_OK, &status); if (rc) return rc; @@ -824,26 +1033,18 @@ static int at86rf230_hw_init(struct at86rf230_local *lp) return 0; } -static void at86rf230_fill_data(struct spi_device *spi) -{ - struct at86rf230_local *lp = spi_get_drvdata(spi); - struct at86rf230_platform_data *pdata = spi->dev.platform_data; - - lp->rstn = pdata->rstn; - lp->slp_tr = pdata->slp_tr; - lp->dig2 = pdata->dig2; -} - static int at86rf230_probe(struct spi_device *spi) { struct at86rf230_platform_data *pdata; struct ieee802154_dev *dev; struct at86rf230_local *lp; - u8 man_id_0, man_id_1, status; + u16 man_id = 0; + u8 part = 0, version = 0, status; irq_handler_t irq_handler; work_func_t irq_worker; - int rc, supported = 0; + int rc; const char *chip; + struct ieee802154_ops *ops = NULL; if (!spi->irq) { dev_err(&spi->dev, "no IRQ specified\n"); @@ -856,116 +1057,121 @@ static int at86rf230_probe(struct spi_device *spi) return -EINVAL; } - dev = ieee802154_alloc_device(sizeof(*lp), &at86rf230_ops); - if (!dev) - return -ENOMEM; - - lp = dev->priv; - lp->dev = dev; - - lp->spi = spi; - - dev->parent = &spi->dev; - dev->extra_tx_headroom = 0; - /* We do support only 2.4 Ghz */ - dev->phy->channels_supported[0] = 0x7FFF800; - dev->flags = IEEE802154_HW_OMIT_CKSUM; - - if (pdata->irq_type & (IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING)) { - irq_worker = at86rf230_irqwork; - irq_handler = at86rf230_isr; - } else { - irq_worker = at86rf230_irqwork_level; - irq_handler = at86rf230_isr_level; - } - - mutex_init(&lp->bmux); - INIT_WORK(&lp->irqwork, irq_worker); - spin_lock_init(&lp->lock); - init_completion(&lp->tx_complete); - - spi_set_drvdata(spi, lp); - - at86rf230_fill_data(spi); - - rc = gpio_request(lp->rstn, "rstn"); + rc = gpio_request(pdata->rstn, "rstn"); if (rc) - goto err_rstn; + return rc; - if (gpio_is_valid(lp->slp_tr)) { - rc = gpio_request(lp->slp_tr, "slp_tr"); + if (gpio_is_valid(pdata->slp_tr)) { + rc = gpio_request(pdata->slp_tr, "slp_tr"); if (rc) goto err_slp_tr; } - rc = gpio_direction_output(lp->rstn, 1); + rc = gpio_direction_output(pdata->rstn, 1); if (rc) goto err_gpio_dir; - if (gpio_is_valid(lp->slp_tr)) { - rc = gpio_direction_output(lp->slp_tr, 0); + if (gpio_is_valid(pdata->slp_tr)) { + rc = gpio_direction_output(pdata->slp_tr, 0); if (rc) goto err_gpio_dir; } /* Reset */ msleep(1); - gpio_set_value(lp->rstn, 0); + gpio_set_value(pdata->rstn, 0); msleep(1); - gpio_set_value(lp->rstn, 1); + gpio_set_value(pdata->rstn, 1); msleep(1); - rc = at86rf230_read_subreg(lp, SR_MAN_ID_0, &man_id_0); - if (rc) - goto err_gpio_dir; - rc = at86rf230_read_subreg(lp, SR_MAN_ID_1, &man_id_1); - if (rc) + rc = __at86rf230_detect_device(spi, &man_id, &part, &version); + if (rc < 0) goto err_gpio_dir; - if (man_id_1 != 0x00 || man_id_0 != 0x1f) { + if (man_id != 0x001f) { dev_err(&spi->dev, "Non-Atmel dev found (MAN_ID %02x %02x)\n", - man_id_1, man_id_0); + man_id >> 8, man_id & 0xFF); rc = -EINVAL; goto err_gpio_dir; } - rc = at86rf230_read_subreg(lp, SR_PART_NUM, &lp->part); - if (rc) - goto err_gpio_dir; - - rc = at86rf230_read_subreg(lp, SR_VERSION_NUM, &lp->vers); - if (rc) - goto err_gpio_dir; - - switch (lp->part) { + switch (part) { case 2: chip = "at86rf230"; - /* supported = 1; FIXME: should be easy to support; */ + /* FIXME: should be easy to support; */ break; case 3: chip = "at86rf231"; - supported = 1; + ops = &at86rf230_ops; + break; + case 7: + chip = "at86rf212"; + if (version == 1) + ops = &at86rf212_ops; + break; + case 11: + chip = "at86rf233"; + ops = &at86rf230_ops; break; default: chip = "UNKNOWN"; break; } - dev_info(&spi->dev, "Detected %s chip version %d\n", chip, lp->vers); - if (!supported) { + dev_info(&spi->dev, "Detected %s chip version %d\n", chip, version); + if (!ops) { rc = -ENOTSUPP; goto err_gpio_dir; } + dev = ieee802154_alloc_device(sizeof(*lp), ops); + if (!dev) { + rc = -ENOMEM; + goto err_gpio_dir; + } + + lp = dev->priv; + lp->dev = dev; + lp->part = part; + lp->vers = version; + + lp->spi = spi; + + dev->parent = &spi->dev; + dev->extra_tx_headroom = 0; + dev->flags = IEEE802154_HW_OMIT_CKSUM | IEEE802154_HW_AACK; + + if (pdata->irq_type & (IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING)) { + irq_worker = at86rf230_irqwork; + irq_handler = at86rf230_isr; + } else { + irq_worker = at86rf230_irqwork_level; + irq_handler = at86rf230_isr_level; + } + + mutex_init(&lp->bmux); + INIT_WORK(&lp->irqwork, irq_worker); + spin_lock_init(&lp->lock); + init_completion(&lp->tx_complete); + + spi_set_drvdata(spi, lp); + + if (is_rf212(lp)) { + dev->phy->channels_supported[0] = 0x00007FF; + dev->phy->channels_supported[2] = 0x00007FF; + } else { + dev->phy->channels_supported[0] = 0x7FFF800; + } + rc = at86rf230_hw_init(lp); if (rc) - goto err_gpio_dir; + goto err_hw_init; rc = request_irq(spi->irq, irq_handler, IRQF_SHARED | pdata->irq_type, dev_name(&spi->dev), lp); if (rc) - goto err_gpio_dir; + goto err_hw_init; /* Read irq status register to reset irq line */ rc = at86rf230_read_subreg(lp, RG_IRQ_STATUS, 0xff, 0, &status); @@ -980,30 +1186,33 @@ static int at86rf230_probe(struct spi_device *spi) err_irq: free_irq(spi->irq, lp); +err_hw_init: flush_work(&lp->irqwork); -err_gpio_dir: - if (gpio_is_valid(lp->slp_tr)) - gpio_free(lp->slp_tr); -err_slp_tr: - gpio_free(lp->rstn); -err_rstn: + spi_set_drvdata(spi, NULL); mutex_destroy(&lp->bmux); ieee802154_free_device(lp->dev); + +err_gpio_dir: + if (gpio_is_valid(pdata->slp_tr)) + gpio_free(pdata->slp_tr); +err_slp_tr: + gpio_free(pdata->rstn); return rc; } static int at86rf230_remove(struct spi_device *spi) { struct at86rf230_local *lp = spi_get_drvdata(spi); + struct at86rf230_platform_data *pdata = spi->dev.platform_data; ieee802154_unregister_device(lp->dev); free_irq(spi->irq, lp); flush_work(&lp->irqwork); - if (gpio_is_valid(lp->slp_tr)) - gpio_free(lp->slp_tr); - gpio_free(lp->rstn); + if (gpio_is_valid(pdata->slp_tr)) + gpio_free(pdata->slp_tr); + gpio_free(pdata->rstn); mutex_destroy(&lp->bmux); ieee802154_free_device(lp->dev); diff --git a/drivers/net/irda/Kconfig b/drivers/net/irda/Kconfig index 2dc82f1d2e70..3da44d5d9149 100644 --- a/drivers/net/irda/Kconfig +++ b/drivers/net/irda/Kconfig @@ -210,13 +210,6 @@ config KINGSUN_DONGLE To compile it as a module, choose M here: the module will be called kingsun-sir. -config EP7211_DONGLE - tristate "Cirrus Logic clps711x I/R support" - depends on IRTTY_SIR && ARCH_CLPS711X && IRDA - help - Say Y here if you want to build support for the Cirrus logic - EP7211 chipset's infrared module. - config KSDAZZLE_DONGLE tristate "KingSun Dazzle IrDA-USB dongle" depends on IRDA && USB diff --git a/drivers/net/irda/Makefile b/drivers/net/irda/Makefile index dfc64537f62f..be8ab5b9a4a2 100644 --- a/drivers/net/irda/Makefile +++ b/drivers/net/irda/Makefile @@ -35,7 +35,6 @@ obj-$(CONFIG_MCP2120_DONGLE) += mcp2120-sir.o obj-$(CONFIG_ACT200L_DONGLE) += act200l-sir.o obj-$(CONFIG_MA600_DONGLE) += ma600-sir.o obj-$(CONFIG_TOIM3232_DONGLE) += toim3232-sir.o -obj-$(CONFIG_EP7211_DONGLE) += ep7211-sir.o obj-$(CONFIG_KINGSUN_DONGLE) += kingsun-sir.o obj-$(CONFIG_KSDAZZLE_DONGLE) += ksdazzle-sir.o obj-$(CONFIG_KS959_DONGLE) += ks959-sir.o diff --git a/drivers/net/irda/ep7211-sir.c b/drivers/net/irda/ep7211-sir.c deleted file mode 100644 index 5fe1f4dd3369..000000000000 --- a/drivers/net/irda/ep7211-sir.c +++ /dev/null @@ -1,70 +0,0 @@ -/* - * IR port driver for the Cirrus Logic CLPS711X processors - * - * Copyright 2001, Blue Mug Inc. All rights reserved. - * Copyright 2007, Samuel Ortiz <samuel@sortiz.org> - */ - -#include <linux/module.h> -#include <linux/platform_device.h> - -#include <mach/hardware.h> - -#include "sir-dev.h" - -static int clps711x_dongle_open(struct sir_dev *dev) -{ - unsigned int syscon; - - /* Turn on the SIR encoder. */ - syscon = clps_readl(SYSCON1); - syscon |= SYSCON1_SIREN; - clps_writel(syscon, SYSCON1); - - return 0; -} - -static int clps711x_dongle_close(struct sir_dev *dev) -{ - unsigned int syscon; - - /* Turn off the SIR encoder. */ - syscon = clps_readl(SYSCON1); - syscon &= ~SYSCON1_SIREN; - clps_writel(syscon, SYSCON1); - - return 0; -} - -static struct dongle_driver clps711x_dongle = { - .owner = THIS_MODULE, - .driver_name = "EP7211 IR driver", - .type = IRDA_EP7211_DONGLE, - .open = clps711x_dongle_open, - .close = clps711x_dongle_close, -}; - -static int clps711x_sir_probe(struct platform_device *pdev) -{ - return irda_register_dongle(&clps711x_dongle); -} - -static int clps711x_sir_remove(struct platform_device *pdev) -{ - return irda_unregister_dongle(&clps711x_dongle); -} - -static struct platform_driver clps711x_sir_driver = { - .driver = { - .name = "sir-clps711x", - .owner = THIS_MODULE, - }, - .probe = clps711x_sir_probe, - .remove = clps711x_sir_remove, -}; -module_platform_driver(clps711x_sir_driver); - -MODULE_AUTHOR("Samuel Ortiz <samuel@sortiz.org>"); -MODULE_DESCRIPTION("EP7211 IR dongle driver"); -MODULE_LICENSE("GPL"); -MODULE_ALIAS("irda-dongle-13"); /* IRDA_EP7211_DONGLE */ diff --git a/drivers/net/irda/irtty-sir.c b/drivers/net/irda/irtty-sir.c index 177441afeb96..24b6dddd7f2f 100644 --- a/drivers/net/irda/irtty-sir.c +++ b/drivers/net/irda/irtty-sir.c @@ -522,7 +522,6 @@ static void irtty_close(struct tty_struct *tty) sirdev_put_instance(priv->dev); /* Stop tty */ - irtty_stop_receiver(tty, TRUE); clear_bit(TTY_DO_WRITE_WAKEUP, &tty->flags); if (tty->ops->stop) tty->ops->stop(tty); diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c index c5011e078e1b..282effee7e1c 100644 --- a/drivers/net/loopback.c +++ b/drivers/net/loopback.c @@ -136,16 +136,9 @@ static const struct ethtool_ops loopback_ethtool_ops = { static int loopback_dev_init(struct net_device *dev) { - int i; - dev->lstats = alloc_percpu(struct pcpu_lstats); + dev->lstats = netdev_alloc_pcpu_stats(struct pcpu_lstats); if (!dev->lstats) return -ENOMEM; - - for_each_possible_cpu(i) { - struct pcpu_lstats *lb_stats; - lb_stats = per_cpu_ptr(dev->lstats, i); - u64_stats_init(&lb_stats->syncp); - } return 0; } @@ -160,6 +153,7 @@ static const struct net_device_ops loopback_ops = { .ndo_init = loopback_dev_init, .ndo_start_xmit= loopback_xmit, .ndo_get_stats64 = loopback_get_stats64, + .ndo_set_mac_address = eth_mac_addr, }; /* @@ -174,6 +168,7 @@ static void loopback_setup(struct net_device *dev) dev->tx_queue_len = 0; dev->type = ARPHRD_LOOPBACK; /* 0x0001*/ dev->flags = IFF_LOOPBACK; + dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; dev->hw_features = NETIF_F_ALL_TSO | NETIF_F_UFO; dev->features = NETIF_F_SG | NETIF_F_FRAGLIST @@ -181,6 +176,7 @@ static void loopback_setup(struct net_device *dev) | NETIF_F_UFO | NETIF_F_HW_CSUM | NETIF_F_RXCSUM + | NETIF_F_SCTP_CSUM | NETIF_F_HIGHDMA | NETIF_F_LLTX | NETIF_F_NETNS_LOCAL diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 8433de4509c7..c683ac2c8c94 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -506,6 +506,9 @@ static int macvlan_change_mtu(struct net_device *dev, int new_mtu) static struct lock_class_key macvlan_netdev_xmit_lock_key; static struct lock_class_key macvlan_netdev_addr_lock_key; +#define ALWAYS_ON_FEATURES \ + (NETIF_F_SG | NETIF_F_GEN_CSUM | NETIF_F_GSO_SOFTWARE | NETIF_F_LLTX) + #define MACVLAN_FEATURES \ (NETIF_F_SG | NETIF_F_ALL_CSUM | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | \ NETIF_F_GSO | NETIF_F_TSO | NETIF_F_UFO | NETIF_F_GSO_ROBUST | \ @@ -534,28 +537,21 @@ static int macvlan_init(struct net_device *dev) { struct macvlan_dev *vlan = netdev_priv(dev); const struct net_device *lowerdev = vlan->lowerdev; - int i; dev->state = (dev->state & ~MACVLAN_STATE_MASK) | (lowerdev->state & MACVLAN_STATE_MASK); dev->features = lowerdev->features & MACVLAN_FEATURES; - dev->features |= NETIF_F_LLTX; + dev->features |= ALWAYS_ON_FEATURES; dev->gso_max_size = lowerdev->gso_max_size; dev->iflink = lowerdev->ifindex; dev->hard_header_len = lowerdev->hard_header_len; macvlan_set_lockdep_class(dev); - vlan->pcpu_stats = alloc_percpu(struct vlan_pcpu_stats); + vlan->pcpu_stats = netdev_alloc_pcpu_stats(struct vlan_pcpu_stats); if (!vlan->pcpu_stats) return -ENOMEM; - for_each_possible_cpu(i) { - struct vlan_pcpu_stats *mvlstats; - mvlstats = per_cpu_ptr(vlan->pcpu_stats, i); - u64_stats_init(&mvlstats->syncp); - } - return 0; } @@ -699,7 +695,7 @@ static netdev_features_t macvlan_fix_features(struct net_device *dev, features = netdev_increment_features(vlan->lowerdev->features, features, mask); - features |= NETIF_F_LLTX; + features |= ALWAYS_ON_FEATURES; return features; } @@ -879,14 +875,15 @@ int macvlan_common_newlink(struct net *src_net, struct net_device *dev, dev->priv_flags |= IFF_MACVLAN; err = netdev_upper_dev_link(lowerdev, dev); if (err) - goto destroy_port; - + goto unregister_netdev; list_add_tail_rcu(&vlan->list, &port->vlans); netif_stacked_transfer_operstate(lowerdev, dev); return 0; +unregister_netdev: + unregister_netdevice(dev); destroy_port: port->count -= 1; if (!port->count) diff --git a/drivers/net/nlmon.c b/drivers/net/nlmon.c index d2bb12bfabd5..14ce7de6a933 100644 --- a/drivers/net/nlmon.c +++ b/drivers/net/nlmon.c @@ -47,16 +47,7 @@ static int nlmon_change_mtu(struct net_device *dev, int new_mtu) static int nlmon_dev_init(struct net_device *dev) { - int i; - - dev->lstats = alloc_percpu(struct pcpu_lstats); - - for_each_possible_cpu(i) { - struct pcpu_lstats *nlmstats; - nlmstats = per_cpu_ptr(dev->lstats, i); - u64_stats_init(&nlmstats->syncp); - } - + dev->lstats = netdev_alloc_pcpu_stats(struct pcpu_lstats); return dev->lstats == NULL ? -ENOMEM : 0; } diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig index 9b5d46c03eed..6a17f92153b3 100644 --- a/drivers/net/phy/Kconfig +++ b/drivers/net/phy/Kconfig @@ -71,6 +71,12 @@ config BCM63XX_PHY ---help--- Currently supports the 6348 and 6358 PHYs. +config BCM7XXX_PHY + tristate "Drivers for Broadcom 7xxx SOCs internal PHYs" + ---help--- + Currently supports the BCM7366, BCM7439, BCM7445, and + 40nm and 65nm generation of BCM7xxx Set Top Box SoCs. + config BCM87XX_PHY tristate "Driver for Broadcom BCM8706 and BCM8727 PHYs" help diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile index 9013dfa12aa3..07d24024863e 100644 --- a/drivers/net/phy/Makefile +++ b/drivers/net/phy/Makefile @@ -12,6 +12,7 @@ obj-$(CONFIG_SMSC_PHY) += smsc.o obj-$(CONFIG_VITESSE_PHY) += vitesse.o obj-$(CONFIG_BROADCOM_PHY) += broadcom.o obj-$(CONFIG_BCM63XX_PHY) += bcm63xx.o +obj-$(CONFIG_BCM7XXX_PHY) += bcm7xxx.o obj-$(CONFIG_BCM87XX_PHY) += bcm87xx.o obj-$(CONFIG_ICPLUS_PHY) += icplus.o obj-$(CONFIG_REALTEK_PHY) += realtek.o diff --git a/drivers/net/phy/bcm7xxx.c b/drivers/net/phy/bcm7xxx.c new file mode 100644 index 000000000000..697337220016 --- /dev/null +++ b/drivers/net/phy/bcm7xxx.c @@ -0,0 +1,343 @@ +/* + * Broadcom BCM7xxx internal transceivers support. + * + * Copyright (C) 2014, Broadcom Corporation + * + * 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 <linux/module.h> +#include <linux/phy.h> +#include <linux/delay.h> +#include <linux/bitops.h> +#include <linux/brcmphy.h> + +/* Broadcom BCM7xxx internal PHY registers */ +#define MII_BCM7XXX_CHANNEL_WIDTH 0x2000 + +/* 40nm only register definitions */ +#define MII_BCM7XXX_100TX_AUX_CTL 0x10 +#define MII_BCM7XXX_100TX_FALSE_CAR 0x13 +#define MII_BCM7XXX_100TX_DISC 0x14 +#define MII_BCM7XXX_AUX_MODE 0x1d +#define MII_BCM7XX_64CLK_MDIO BIT(12) +#define MII_BCM7XXX_CORE_BASE1E 0x1e +#define MII_BCM7XXX_TEST 0x1f +#define MII_BCM7XXX_SHD_MODE_2 BIT(2) + +static int bcm7445_config_init(struct phy_device *phydev) +{ + int ret; + const struct bcm7445_regs { + int reg; + u16 value; + } bcm7445_regs_cfg[] = { + /* increases ADC latency by 24ns */ + { MII_BCM54XX_EXP_SEL, 0x0038 }, + { MII_BCM54XX_EXP_DATA, 0xAB95 }, + /* increases internal 1V LDO voltage by 5% */ + { MII_BCM54XX_EXP_SEL, 0x2038 }, + { MII_BCM54XX_EXP_DATA, 0xBB22 }, + /* reduce RX low pass filter corner frequency */ + { MII_BCM54XX_EXP_SEL, 0x6038 }, + { MII_BCM54XX_EXP_DATA, 0xFFC5 }, + /* reduce RX high pass filter corner frequency */ + { MII_BCM54XX_EXP_SEL, 0x003a }, + { MII_BCM54XX_EXP_DATA, 0x2002 }, + }; + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(bcm7445_regs_cfg); i++) { + ret = phy_write(phydev, + bcm7445_regs_cfg[i].reg, + bcm7445_regs_cfg[i].value); + if (ret) + return ret; + } + + return 0; +} + +static void phy_write_exp(struct phy_device *phydev, + u16 reg, u16 value) +{ + phy_write(phydev, MII_BCM54XX_EXP_SEL, MII_BCM54XX_EXP_SEL_ER | reg); + phy_write(phydev, MII_BCM54XX_EXP_DATA, value); +} + +static void phy_write_misc(struct phy_device *phydev, + u16 reg, u16 chl, u16 value) +{ + int tmp; + + phy_write(phydev, MII_BCM54XX_AUX_CTL, MII_BCM54XX_AUXCTL_SHDWSEL_MISC); + + tmp = phy_read(phydev, MII_BCM54XX_AUX_CTL); + tmp |= MII_BCM54XX_AUXCTL_ACTL_SMDSP_ENA; + phy_write(phydev, MII_BCM54XX_AUX_CTL, tmp); + + tmp = (chl * MII_BCM7XXX_CHANNEL_WIDTH) | reg; + phy_write(phydev, MII_BCM54XX_EXP_SEL, tmp); + + phy_write(phydev, MII_BCM54XX_EXP_DATA, value); +} + +static int bcm7xxx_28nm_afe_config_init(struct phy_device *phydev) +{ + /* write AFE_RXCONFIG_0 */ + phy_write_misc(phydev, 0x38, 0x0000, 0xeb19); + + /* write AFE_RXCONFIG_1 */ + phy_write_misc(phydev, 0x38, 0x0001, 0x9a3f); + + /* write AFE_RX_LP_COUNTER */ + phy_write_misc(phydev, 0x38, 0x0003, 0x7fc7); + + /* write AFE_HPF_TRIM_OTHERS */ + phy_write_misc(phydev, 0x3A, 0x0000, 0x000b); + + /* write AFTE_TX_CONFIG */ + phy_write_misc(phydev, 0x39, 0x0000, 0x0800); + + /* Increase VCO range to prevent unlocking problem of PLL at low + * temp + */ + phy_write_misc(phydev, 0x0032, 0x0001, 0x0048); + + /* Change Ki to 011 */ + phy_write_misc(phydev, 0x0032, 0x0002, 0x021b); + + /* Disable loading of TVCO buffer to bandgap, set bandgap trim + * to 111 + */ + phy_write_misc(phydev, 0x0033, 0x0000, 0x0e20); + + /* Adjust bias current trim by -3 */ + phy_write_misc(phydev, 0x000a, 0x0000, 0x690b); + + /* Switch to CORE_BASE1E */ + phy_write(phydev, MII_BCM7XXX_CORE_BASE1E, 0xd); + + /* Reset R_CAL/RC_CAL Engine */ + phy_write_exp(phydev, 0x00b0, 0x0010); + + /* Disable Reset R_CAL/RC_CAL Engine */ + phy_write_exp(phydev, 0x00b0, 0x0000); + + return 0; +} + +static int bcm7xxx_28nm_config_init(struct phy_device *phydev) +{ + int ret; + + ret = bcm7445_config_init(phydev); + if (ret) + return ret; + + return bcm7xxx_28nm_afe_config_init(phydev); +} + +static int phy_set_clr_bits(struct phy_device *dev, int location, + int set_mask, int clr_mask) +{ + int v, ret; + + v = phy_read(dev, location); + if (v < 0) + return v; + + v &= ~clr_mask; + v |= set_mask; + + ret = phy_write(dev, location, v); + if (ret < 0) + return ret; + + return v; +} + +static int bcm7xxx_config_init(struct phy_device *phydev) +{ + int ret; + + /* Enable 64 clock MDIO */ + phy_write(phydev, MII_BCM7XXX_AUX_MODE, MII_BCM7XX_64CLK_MDIO); + phy_read(phydev, MII_BCM7XXX_AUX_MODE); + + /* Workaround only required for 100Mbits/sec */ + if (!(phydev->dev_flags & PHY_BRCM_100MBPS_WAR)) + return 0; + + /* set shadow mode 2 */ + ret = phy_set_clr_bits(phydev, MII_BCM7XXX_TEST, + MII_BCM7XXX_SHD_MODE_2, MII_BCM7XXX_SHD_MODE_2); + if (ret < 0) + return ret; + + /* set iddq_clkbias */ + phy_write(phydev, MII_BCM7XXX_100TX_DISC, 0x0F00); + udelay(10); + + /* reset iddq_clkbias */ + phy_write(phydev, MII_BCM7XXX_100TX_DISC, 0x0C00); + + phy_write(phydev, MII_BCM7XXX_100TX_FALSE_CAR, 0x7555); + + /* reset shadow mode 2 */ + ret = phy_set_clr_bits(phydev, MII_BCM7XXX_TEST, MII_BCM7XXX_SHD_MODE_2, 0); + if (ret < 0) + return ret; + + return 0; +} + +/* Workaround for putting the PHY in IDDQ mode, required + * for all BCM7XXX PHYs + */ +static int bcm7xxx_suspend(struct phy_device *phydev) +{ + int ret; + const struct bcm7xxx_regs { + int reg; + u16 value; + } bcm7xxx_suspend_cfg[] = { + { MII_BCM7XXX_TEST, 0x008b }, + { MII_BCM7XXX_100TX_AUX_CTL, 0x01c0 }, + { MII_BCM7XXX_100TX_DISC, 0x7000 }, + { MII_BCM7XXX_TEST, 0x000f }, + { MII_BCM7XXX_100TX_AUX_CTL, 0x20d0 }, + { MII_BCM7XXX_TEST, 0x000b }, + }; + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(bcm7xxx_suspend_cfg); i++) { + ret = phy_write(phydev, + bcm7xxx_suspend_cfg[i].reg, + bcm7xxx_suspend_cfg[i].value); + if (ret) + return ret; + } + + return 0; +} + +static int bcm7xxx_dummy_config_init(struct phy_device *phydev) +{ + return 0; +} + +static struct phy_driver bcm7xxx_driver[] = { +{ + .phy_id = PHY_ID_BCM7366, + .phy_id_mask = 0xfffffff0, + .name = "Broadcom BCM7366", + .features = PHY_GBIT_FEATURES | + SUPPORTED_Pause | SUPPORTED_Asym_Pause, + .flags = PHY_IS_INTERNAL, + .config_init = bcm7xxx_28nm_afe_config_init, + .config_aneg = genphy_config_aneg, + .read_status = genphy_read_status, + .suspend = bcm7xxx_suspend, + .resume = bcm7xxx_28nm_afe_config_init, + .driver = { .owner = THIS_MODULE }, +}, { + .phy_id = PHY_ID_BCM7439, + .phy_id_mask = 0xfffffff0, + .name = "Broadcom BCM7439", + .features = PHY_GBIT_FEATURES | + SUPPORTED_Pause | SUPPORTED_Asym_Pause, + .flags = PHY_IS_INTERNAL, + .config_init = bcm7xxx_28nm_afe_config_init, + .config_aneg = genphy_config_aneg, + .read_status = genphy_read_status, + .suspend = bcm7xxx_suspend, + .resume = bcm7xxx_28nm_afe_config_init, + .driver = { .owner = THIS_MODULE }, +}, { + .phy_id = PHY_ID_BCM7445, + .phy_id_mask = 0xfffffff0, + .name = "Broadcom BCM7445", + .features = PHY_GBIT_FEATURES | + SUPPORTED_Pause | SUPPORTED_Asym_Pause, + .flags = PHY_IS_INTERNAL, + .config_init = bcm7xxx_28nm_config_init, + .config_aneg = genphy_config_aneg, + .read_status = genphy_read_status, + .suspend = bcm7xxx_suspend, + .resume = bcm7xxx_28nm_config_init, + .driver = { .owner = THIS_MODULE }, +}, { + .name = "Broadcom BCM7XXX 28nm", + .phy_id = PHY_ID_BCM7XXX_28, + .phy_id_mask = PHY_BCM_OUI_MASK, + .features = PHY_GBIT_FEATURES | + SUPPORTED_Pause | SUPPORTED_Asym_Pause, + .flags = PHY_IS_INTERNAL, + .config_init = bcm7xxx_28nm_config_init, + .config_aneg = genphy_config_aneg, + .read_status = genphy_read_status, + .suspend = bcm7xxx_suspend, + .resume = bcm7xxx_28nm_config_init, + .driver = { .owner = THIS_MODULE }, +}, { + .phy_id = PHY_BCM_OUI_4, + .phy_id_mask = 0xffff0000, + .name = "Broadcom BCM7XXX 40nm", + .features = PHY_GBIT_FEATURES | + SUPPORTED_Pause | SUPPORTED_Asym_Pause, + .flags = PHY_IS_INTERNAL, + .config_init = bcm7xxx_config_init, + .config_aneg = genphy_config_aneg, + .read_status = genphy_read_status, + .suspend = bcm7xxx_suspend, + .resume = bcm7xxx_config_init, + .driver = { .owner = THIS_MODULE }, +}, { + .phy_id = PHY_BCM_OUI_5, + .phy_id_mask = 0xffffff00, + .name = "Broadcom BCM7XXX 65nm", + .features = PHY_BASIC_FEATURES | + SUPPORTED_Pause | SUPPORTED_Asym_Pause, + .flags = PHY_IS_INTERNAL, + .config_init = bcm7xxx_dummy_config_init, + .config_aneg = genphy_config_aneg, + .read_status = genphy_read_status, + .suspend = bcm7xxx_suspend, + .resume = bcm7xxx_config_init, + .driver = { .owner = THIS_MODULE }, +} }; + +static struct mdio_device_id __maybe_unused bcm7xxx_tbl[] = { + { PHY_ID_BCM7366, 0xfffffff0, }, + { PHY_ID_BCM7439, 0xfffffff0, }, + { PHY_ID_BCM7445, 0xfffffff0, }, + { PHY_ID_BCM7XXX_28, 0xfffffc00 }, + { PHY_BCM_OUI_4, 0xffff0000 }, + { PHY_BCM_OUI_5, 0xffffff00 }, + { } +}; + +static int __init bcm7xxx_phy_init(void) +{ + return phy_drivers_register(bcm7xxx_driver, + ARRAY_SIZE(bcm7xxx_driver)); +} + +static void __exit bcm7xxx_phy_exit(void) +{ + phy_drivers_unregister(bcm7xxx_driver, + ARRAY_SIZE(bcm7xxx_driver)); +} + +module_init(bcm7xxx_phy_init); +module_exit(bcm7xxx_phy_exit); + +MODULE_DEVICE_TABLE(mdio, bcm7xxx_tbl); + +MODULE_DESCRIPTION("Broadcom BCM7xxx internal PHY driver"); +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Broadcom Corporation"); diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c index f8c90ea75108..34088d60da74 100644 --- a/drivers/net/phy/broadcom.c +++ b/drivers/net/phy/broadcom.c @@ -25,58 +25,6 @@ #define BRCM_PHY_REV(phydev) \ ((phydev)->drv->phy_id & ~((phydev)->drv->phy_id_mask)) - -#define MII_BCM54XX_ECR 0x10 /* BCM54xx extended control register */ -#define MII_BCM54XX_ECR_IM 0x1000 /* Interrupt mask */ -#define MII_BCM54XX_ECR_IF 0x0800 /* Interrupt force */ - -#define MII_BCM54XX_ESR 0x11 /* BCM54xx extended status register */ -#define MII_BCM54XX_ESR_IS 0x1000 /* Interrupt status */ - -#define MII_BCM54XX_EXP_DATA 0x15 /* Expansion register data */ -#define MII_BCM54XX_EXP_SEL 0x17 /* Expansion register select */ -#define MII_BCM54XX_EXP_SEL_SSD 0x0e00 /* Secondary SerDes select */ -#define MII_BCM54XX_EXP_SEL_ER 0x0f00 /* Expansion register select */ - -#define MII_BCM54XX_AUX_CTL 0x18 /* Auxiliary control register */ -#define MII_BCM54XX_ISR 0x1a /* BCM54xx interrupt status register */ -#define MII_BCM54XX_IMR 0x1b /* BCM54xx interrupt mask register */ -#define MII_BCM54XX_INT_CRCERR 0x0001 /* CRC error */ -#define MII_BCM54XX_INT_LINK 0x0002 /* Link status changed */ -#define MII_BCM54XX_INT_SPEED 0x0004 /* Link speed change */ -#define MII_BCM54XX_INT_DUPLEX 0x0008 /* Duplex mode changed */ -#define MII_BCM54XX_INT_LRS 0x0010 /* Local receiver status changed */ -#define MII_BCM54XX_INT_RRS 0x0020 /* Remote receiver status changed */ -#define MII_BCM54XX_INT_SSERR 0x0040 /* Scrambler synchronization error */ -#define MII_BCM54XX_INT_UHCD 0x0080 /* Unsupported HCD negotiated */ -#define MII_BCM54XX_INT_NHCD 0x0100 /* No HCD */ -#define MII_BCM54XX_INT_NHCDL 0x0200 /* No HCD link */ -#define MII_BCM54XX_INT_ANPR 0x0400 /* Auto-negotiation page received */ -#define MII_BCM54XX_INT_LC 0x0800 /* All counters below 128 */ -#define MII_BCM54XX_INT_HC 0x1000 /* Counter above 32768 */ -#define MII_BCM54XX_INT_MDIX 0x2000 /* MDIX status change */ -#define MII_BCM54XX_INT_PSERR 0x4000 /* Pair swap error */ - -#define MII_BCM54XX_SHD 0x1c /* 0x1c shadow registers */ -#define MII_BCM54XX_SHD_WRITE 0x8000 -#define MII_BCM54XX_SHD_VAL(x) ((x & 0x1f) << 10) -#define MII_BCM54XX_SHD_DATA(x) ((x & 0x3ff) << 0) - -/* - * AUXILIARY CONTROL SHADOW ACCESS REGISTERS. (PHY REG 0x18) - */ -#define MII_BCM54XX_AUXCTL_SHDWSEL_AUXCTL 0x0000 -#define MII_BCM54XX_AUXCTL_ACTL_TX_6DB 0x0400 -#define MII_BCM54XX_AUXCTL_ACTL_SMDSP_ENA 0x0800 - -#define MII_BCM54XX_AUXCTL_MISC_WREN 0x8000 -#define MII_BCM54XX_AUXCTL_MISC_FORCE_AMDIX 0x0200 -#define MII_BCM54XX_AUXCTL_MISC_RDSEL_MISC 0x7000 -#define MII_BCM54XX_AUXCTL_SHDWSEL_MISC 0x0007 - -#define MII_BCM54XX_AUXCTL_SHDWSEL_AUXCTL 0x0000 - - /* * Broadcom LED source encodings. These are used in BCM5461, BCM5481, * BCM5482, and possibly some others. diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c index 547725fa8671..98e7cbf720a5 100644 --- a/drivers/net/phy/dp83640.c +++ b/drivers/net/phy/dp83640.c @@ -437,7 +437,10 @@ static int ptp_dp83640_enable(struct ptp_clock_info *ptp, if (on) { gpio_num = gpio_tab[EXTTS0_GPIO + index]; evnt |= (gpio_num & EVNT_GPIO_MASK) << EVNT_GPIO_SHIFT; - evnt |= EVNT_RISE; + if (rq->extts.flags & PTP_FALLING_EDGE) + evnt |= EVNT_FALL; + else + evnt |= EVNT_RISE; } ext_write(0, phydev, PAGE5, PTP_EVNT, evnt); return 0; @@ -1003,11 +1006,6 @@ static int dp83640_probe(struct phy_device *phydev) } else list_add_tail(&dp83640->list, &clock->phylist); - if (clock->chosen && !list_empty(&clock->phylist)) - recalibrate(clock); - else - enable_broadcast(dp83640->phydev, clock->page, 1); - dp83640_clock_put(clock); return 0; @@ -1058,6 +1056,21 @@ static void dp83640_remove(struct phy_device *phydev) kfree(dp83640); } +static int dp83640_config_init(struct phy_device *phydev) +{ + struct dp83640_private *dp83640 = phydev->priv; + struct dp83640_clock *clock = dp83640->clock; + + if (clock->chosen && !list_empty(&clock->phylist)) + recalibrate(clock); + else + enable_broadcast(phydev, clock->page, 1); + + enable_status_frames(phydev, true); + ext_write(0, phydev, PAGE4, PTP_CTL, PTP_ENABLE); + return 0; +} + static int dp83640_ack_interrupt(struct phy_device *phydev) { int err = phy_read(phydev, MII_DP83640_MISR); @@ -1195,11 +1208,6 @@ static int dp83640_hwtstamp(struct phy_device *phydev, struct ifreq *ifr) mutex_lock(&dp83640->clock->extreg_lock); - if (dp83640->hwts_tx_en || dp83640->hwts_rx_en) { - enable_status_frames(phydev, true); - ext_write(0, phydev, PAGE4, PTP_CTL, PTP_ENABLE); - } - ext_write(0, phydev, PAGE5, PTP_TXCFG0, txcfg0); ext_write(0, phydev, PAGE5, PTP_RXCFG0, rxcfg0); @@ -1281,6 +1289,7 @@ static void dp83640_txtstamp(struct phy_device *phydev, } /* fall through */ case HWTSTAMP_TX_ON: + skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; skb_queue_tail(&dp83640->tx_queue, skb); schedule_work(&dp83640->ts_work); break; @@ -1330,6 +1339,7 @@ static struct phy_driver dp83640_driver = { .flags = PHY_HAS_INTERRUPT, .probe = dp83640_probe, .remove = dp83640_remove, + .config_init = dp83640_config_init, .config_aneg = genphy_config_aneg, .read_status = genphy_read_status, .ack_interrupt = dp83640_ack_interrupt, diff --git a/drivers/net/phy/mdio-sun4i.c b/drivers/net/phy/mdio-sun4i.c index bb88bc7d81fb..9367acc84fbb 100644 --- a/drivers/net/phy/mdio-sun4i.c +++ b/drivers/net/phy/mdio-sun4i.c @@ -170,6 +170,9 @@ static int sun4i_mdio_remove(struct platform_device *pdev) } static const struct of_device_id sun4i_mdio_dt_ids[] = { + { .compatible = "allwinner,sun4i-a10-mdio" }, + + /* Deprecated */ { .compatible = "allwinner,sun4i-mdio" }, { } }; diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c index 71e49000fbf3..76f54b32a120 100644 --- a/drivers/net/phy/mdio_bus.c +++ b/drivers/net/phy/mdio_bus.c @@ -432,8 +432,28 @@ phy_id_show(struct device *dev, struct device_attribute *attr, char *buf) } static DEVICE_ATTR_RO(phy_id); +static ssize_t +phy_interface_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct phy_device *phydev = to_phy_device(dev); + + return sprintf(buf, "%s\n", phy_modes(phydev->interface)); +} +static DEVICE_ATTR_RO(phy_interface); + +static ssize_t +phy_has_fixups_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct phy_device *phydev = to_phy_device(dev); + + return sprintf(buf, "%d\n", phydev->has_fixups); +} +static DEVICE_ATTR_RO(phy_has_fixups); + static struct attribute *mdio_dev_attrs[] = { &dev_attr_phy_id.attr, + &dev_attr_phy_interface.attr, + &dev_attr_phy_has_fixups.attr, NULL, }; ATTRIBUTE_GROUPS(mdio_dev); diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 5a8993b0cafc..0c9e4342f11d 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -148,15 +148,52 @@ static int ks8737_config_intr(struct phy_device *phydev) return rc < 0 ? rc : 0; } +static int kszphy_setup_led(struct phy_device *phydev, + unsigned int reg, unsigned int shift) +{ + + struct device *dev = &phydev->dev; + struct device_node *of_node = dev->of_node; + int rc, temp; + u32 val; + + if (!of_node && dev->parent->of_node) + of_node = dev->parent->of_node; + + if (of_property_read_u32(of_node, "micrel,led-mode", &val)) + return 0; + + temp = phy_read(phydev, reg); + if (temp < 0) + return temp; + + temp &= 3 << shift; + temp |= val << shift; + rc = phy_write(phydev, reg, temp); + + return rc < 0 ? rc : 0; +} + static int kszphy_config_init(struct phy_device *phydev) { return 0; } +static int kszphy_config_init_led8041(struct phy_device *phydev) +{ + /* single led control, register 0x1e bits 15..14 */ + return kszphy_setup_led(phydev, 0x1e, 14); +} + static int ksz8021_config_init(struct phy_device *phydev) { - int rc; const u16 val = KSZPHY_OMSO_B_CAST_OFF | KSZPHY_OMSO_RMII_OVERRIDE; + int rc; + + rc = kszphy_setup_led(phydev, 0x1f, 4); + if (rc) + dev_err(&phydev->dev, "failed to set led mode\n"); + phy_write(phydev, MII_KSZPHY_OMSO, val); rc = ksz_config_flags(phydev); return rc < 0 ? rc : 0; @@ -166,6 +203,10 @@ static int ks8051_config_init(struct phy_device *phydev) { int rc; + rc = kszphy_setup_led(phydev, 0x1f, 4); + if (rc) + dev_err(&phydev->dev, "failed to set led mode\n"); + rc = ksz_config_flags(phydev); return rc < 0 ? rc : 0; } @@ -327,7 +368,7 @@ static struct phy_driver ksphy_driver[] = { .features = (PHY_BASIC_FEATURES | SUPPORTED_Pause | SUPPORTED_Asym_Pause), .flags = PHY_HAS_MAGICANEG | PHY_HAS_INTERRUPT, - .config_init = kszphy_config_init, + .config_init = kszphy_config_init_led8041, .config_aneg = genphy_config_aneg, .read_status = genphy_read_status, .ack_interrupt = kszphy_ack_interrupt, @@ -342,7 +383,7 @@ static struct phy_driver ksphy_driver[] = { .features = PHY_BASIC_FEATURES | SUPPORTED_Pause | SUPPORTED_Asym_Pause, .flags = PHY_HAS_MAGICANEG | PHY_HAS_INTERRUPT, - .config_init = kszphy_config_init, + .config_init = kszphy_config_init_led8041, .config_aneg = genphy_config_aneg, .read_status = genphy_read_status, .ack_interrupt = kszphy_ack_interrupt, @@ -371,7 +412,7 @@ static struct phy_driver ksphy_driver[] = { .phy_id_mask = 0x00ffffff, .features = (PHY_BASIC_FEATURES | SUPPORTED_Pause), .flags = PHY_HAS_MAGICANEG | PHY_HAS_INTERRUPT, - .config_init = kszphy_config_init, + .config_init = kszphy_config_init_led8041, .config_aneg = genphy_config_aneg, .read_status = genphy_read_status, .ack_interrupt = kszphy_ack_interrupt, diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 19c9eca0ef26..643b5d665f41 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -38,6 +38,26 @@ #include <asm/irq.h> +static const char *phy_speed_to_str(int speed) +{ + switch (speed) { + case SPEED_10: + return "10Mbps"; + case SPEED_100: + return "100Mbps"; + case SPEED_1000: + return "1Gbps"; + case SPEED_2500: + return "2.5Gbps"; + case SPEED_10000: + return "10Gbps"; + case SPEED_UNKNOWN: + return "Unknown"; + default: + return "Unsupported (update phy.c)"; + } +} + /** * phy_print_status - Convenience function to print out the current phy status * @phydev: the phy_device struct @@ -45,12 +65,13 @@ void phy_print_status(struct phy_device *phydev) { if (phydev->link) { - pr_info("%s - Link is Up - %d/%s\n", - dev_name(&phydev->dev), - phydev->speed, - DUPLEX_FULL == phydev->duplex ? "Full" : "Half"); + netdev_info(phydev->attached_dev, + "Link is Up - %s/%s - flow control %s\n", + phy_speed_to_str(phydev->speed), + DUPLEX_FULL == phydev->duplex ? "Full" : "Half", + phydev->pause ? "rx/tx" : "off"); } else { - pr_info("%s - Link is Down\n", dev_name(&phydev->dev)); + netdev_info(phydev->attached_dev, "Link is Down\n"); } } EXPORT_SYMBOL(phy_print_status); @@ -62,7 +83,7 @@ EXPORT_SYMBOL(phy_print_status); * If the @phydev driver has an ack_interrupt function, call it to * ack and clear the phy device's interrupt. * - * Returns 0 on success on < 0 on error. + * Returns 0 on success or < 0 on error. */ static int phy_clear_interrupt(struct phy_device *phydev) { @@ -77,7 +98,7 @@ static int phy_clear_interrupt(struct phy_device *phydev) * @phydev: the phy_device struct * @interrupts: interrupt flags to configure for this @phydev * - * Returns 0 on success on < 0 on error. + * Returns 0 on success or < 0 on error. */ static int phy_config_interrupt(struct phy_device *phydev, u32 interrupts) { @@ -93,15 +114,16 @@ static int phy_config_interrupt(struct phy_device *phydev, u32 interrupts) * phy_aneg_done - return auto-negotiation status * @phydev: target phy_device struct * - * Description: Reads the status register and returns 0 either if - * auto-negotiation is incomplete, or if there was an error. - * Returns BMSR_ANEGCOMPLETE if auto-negotiation is done. + * Description: Return the auto-negotiation status from this @phydev + * Returns > 0 on success or < 0 on error. 0 means that auto-negotiation + * is still pending. */ static inline int phy_aneg_done(struct phy_device *phydev) { - int retval = phy_read(phydev, MII_BMSR); + if (phydev->drv->aneg_done) + return phydev->drv->aneg_done(phydev); - return (retval < 0) ? retval : (retval & BMSR_ANEGCOMPLETE); + return genphy_aneg_done(phydev); } /* A structure for mapping a particular speed and duplex @@ -283,7 +305,10 @@ int phy_ethtool_gset(struct phy_device *phydev, struct ethtool_cmd *cmd) ethtool_cmd_speed_set(cmd, phydev->speed); cmd->duplex = phydev->duplex; - cmd->port = PORT_MII; + if (phydev->interface == PHY_INTERFACE_MODE_MOCA) + cmd->port = PORT_BNC; + else + cmd->port = PORT_MII; cmd->phy_address = phydev->addr; cmd->transceiver = phy_is_internal(phydev) ? XCVR_INTERNAL : XCVR_EXTERNAL; diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 4b03e63639b7..a2fbb3e1db9a 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -139,6 +139,7 @@ static int phy_scan_fixups(struct phy_device *phydev) mutex_unlock(&phy_fixup_lock); return err; } + phydev->has_fixups = true; } } mutex_unlock(&phy_fixup_lock); @@ -534,16 +535,16 @@ static int phy_poll_reset(struct phy_device *phydev) int phy_init_hw(struct phy_device *phydev) { - int ret; + int ret = 0; if (!phydev->drv || !phydev->drv->config_init) return 0; - ret = phy_write(phydev, MII_BMCR, BMCR_RESET); - if (ret < 0) - return ret; + if (phydev->drv->soft_reset) + ret = phydev->drv->soft_reset(phydev); + else + ret = genphy_soft_reset(phydev); - ret = phy_poll_reset(phydev); if (ret < 0) return ret; @@ -719,7 +720,7 @@ int phy_resume(struct phy_device *phydev) static int genphy_config_advert(struct phy_device *phydev) { u32 advertise; - int oldadv, adv; + int oldadv, adv, bmsr; int err, changed = 0; /* Only allow advertising what this PHY supports */ @@ -744,26 +745,36 @@ static int genphy_config_advert(struct phy_device *phydev) changed = 1; } + bmsr = phy_read(phydev, MII_BMSR); + if (bmsr < 0) + return bmsr; + + /* Per 802.3-2008, Section 22.2.4.2.16 Extended status all + * 1000Mbits/sec capable PHYs shall have the BMSR_ESTATEN bit set to a + * logical 1. + */ + if (!(bmsr & BMSR_ESTATEN)) + return changed; + /* Configure gigabit if it's supported */ + adv = phy_read(phydev, MII_CTRL1000); + if (adv < 0) + return adv; + + oldadv = adv; + adv &= ~(ADVERTISE_1000FULL | ADVERTISE_1000HALF); + if (phydev->supported & (SUPPORTED_1000baseT_Half | SUPPORTED_1000baseT_Full)) { - adv = phy_read(phydev, MII_CTRL1000); - if (adv < 0) - return adv; - - oldadv = adv; - adv &= ~(ADVERTISE_1000FULL | ADVERTISE_1000HALF); adv |= ethtool_adv_to_mii_ctrl1000_t(advertise); - - if (adv != oldadv) { - err = phy_write(phydev, MII_CTRL1000, adv); - - if (err < 0) - return err; + if (adv != oldadv) changed = 1; - } } + err = phy_write(phydev, MII_CTRL1000, adv); + if (err < 0) + return err; + return changed; } @@ -855,6 +866,22 @@ int genphy_config_aneg(struct phy_device *phydev) } EXPORT_SYMBOL(genphy_config_aneg); +/** + * genphy_aneg_done - return auto-negotiation status + * @phydev: target phy_device struct + * + * Description: Reads the status register and returns 0 either if + * auto-negotiation is incomplete, or if there was an error. + * Returns BMSR_ANEGCOMPLETE if auto-negotiation is done. + */ +int genphy_aneg_done(struct phy_device *phydev) +{ + int retval = phy_read(phydev, MII_BMSR); + + return (retval < 0) ? retval : (retval & BMSR_ANEGCOMPLETE); +} +EXPORT_SYMBOL(genphy_aneg_done); + static int gen10g_config_aneg(struct phy_device *phydev) { return 0; @@ -906,6 +933,8 @@ int genphy_read_status(struct phy_device *phydev) int err; int lpa; int lpagb = 0; + int common_adv; + int common_adv_gb = 0; /* Update the link, but return if there was an error */ err = genphy_update_link(phydev); @@ -927,7 +956,7 @@ int genphy_read_status(struct phy_device *phydev) phydev->lp_advertising = mii_stat1000_to_ethtool_lpa_t(lpagb); - lpagb &= adv << 2; + common_adv_gb = lpagb & adv << 2; } lpa = phy_read(phydev, MII_LPA); @@ -940,25 +969,25 @@ int genphy_read_status(struct phy_device *phydev) if (adv < 0) return adv; - lpa &= adv; + common_adv = lpa & adv; phydev->speed = SPEED_10; phydev->duplex = DUPLEX_HALF; phydev->pause = 0; phydev->asym_pause = 0; - if (lpagb & (LPA_1000FULL | LPA_1000HALF)) { + if (common_adv_gb & (LPA_1000FULL | LPA_1000HALF)) { phydev->speed = SPEED_1000; - if (lpagb & LPA_1000FULL) + if (common_adv_gb & LPA_1000FULL) phydev->duplex = DUPLEX_FULL; - } else if (lpa & (LPA_100FULL | LPA_100HALF)) { + } else if (common_adv & (LPA_100FULL | LPA_100HALF)) { phydev->speed = SPEED_100; - if (lpa & LPA_100FULL) + if (common_adv & LPA_100FULL) phydev->duplex = DUPLEX_FULL; } else - if (lpa & LPA_10FULL) + if (common_adv & LPA_10FULL) phydev->duplex = DUPLEX_FULL; if (phydev->duplex == DUPLEX_FULL) { @@ -1018,6 +1047,27 @@ static int gen10g_read_status(struct phy_device *phydev) return 0; } +/** + * genphy_soft_reset - software reset the PHY via BMCR_RESET bit + * @phydev: target phy_device struct + * + * Description: Perform a software PHY reset using the standard + * BMCR_RESET bit and poll for the reset bit to be cleared. + * + * Returns: 0 on success, < 0 on failure + */ +int genphy_soft_reset(struct phy_device *phydev) +{ + int ret; + + ret = phy_write(phydev, MII_BMCR, BMCR_RESET); + if (ret < 0) + return ret; + + return phy_poll_reset(phydev); +} +EXPORT_SYMBOL(genphy_soft_reset); + static int genphy_config_init(struct phy_device *phydev) { int val; @@ -1064,6 +1114,12 @@ static int genphy_config_init(struct phy_device *phydev) return 0; } +static int gen10g_soft_reset(struct phy_device *phydev) +{ + /* Do nothing for now */ + return 0; +} + static int gen10g_config_init(struct phy_device *phydev) { /* Temporarily just say we support everything */ @@ -1238,9 +1294,11 @@ static struct phy_driver genphy_driver[] = { .phy_id = 0xffffffff, .phy_id_mask = 0xffffffff, .name = "Generic PHY", + .soft_reset = genphy_soft_reset, .config_init = genphy_config_init, .features = 0, .config_aneg = genphy_config_aneg, + .aneg_done = genphy_aneg_done, .read_status = genphy_read_status, .suspend = genphy_suspend, .resume = genphy_resume, @@ -1249,6 +1307,7 @@ static struct phy_driver genphy_driver[] = { .phy_id = 0xffffffff, .phy_id_mask = 0xffffffff, .name = "Generic 10G PHY", + .soft_reset = gen10g_soft_reset, .config_init = gen10g_config_init, .features = 0, .config_aneg = gen10g_config_aneg, diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index 28407426fd6f..aea92f02401b 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -1540,16 +1540,10 @@ static int team_init(struct net_device *dev) mutex_init(&team->lock); team_set_no_mode(team); - team->pcpu_stats = alloc_percpu(struct team_pcpu_stats); + team->pcpu_stats = netdev_alloc_pcpu_stats(struct team_pcpu_stats); if (!team->pcpu_stats) return -ENOMEM; - for_each_possible_cpu(i) { - struct team_pcpu_stats *team_stats; - team_stats = per_cpu_ptr(team->pcpu_stats, i); - u64_stats_init(&team_stats->syncp); - } - for (i = 0; i < TEAM_PORT_HASHENTRIES; i++) INIT_HLIST_HEAD(&team->en_port_hlist[i]); INIT_LIST_HEAD(&team->port_list); @@ -1648,7 +1642,7 @@ static netdev_tx_t team_xmit(struct sk_buff *skb, struct net_device *dev) } static u16 team_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv) + void *accel_priv, select_queue_fallback_t fallback) { /* * This helper function exists to help dev_pick_tx get the correct diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 44c4db8450f0..26f8635b027d 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -366,7 +366,7 @@ static inline void tun_flow_save_rps_rxhash(struct tun_flow_entry *e, u32 hash) * hope the rxq no. may help here. */ static u16 tun_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv) + void *accel_priv, select_queue_fallback_t fallback) { struct tun_struct *tun = netdev_priv(dev); struct tun_flow_entry *e; @@ -1686,7 +1686,9 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr) TUN_USER_FEATURES | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX; dev->features = dev->hw_features; - dev->vlan_features = dev->features; + dev->vlan_features = dev->features & + ~(NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_STAG_TX); INIT_LIST_HEAD(&tun->disabled); err = tun_attach(tun, file, false); diff --git a/drivers/net/usb/Kconfig b/drivers/net/usb/Kconfig index 6b638a066c1d..7e7269fd3707 100644 --- a/drivers/net/usb/Kconfig +++ b/drivers/net/usb/Kconfig @@ -292,6 +292,21 @@ config USB_NET_SR9700 This option adds support for CoreChip-sz SR9700 based USB 1.1 10/100 Ethernet adapters. +config USB_NET_SR9800 + tristate "CoreChip-sz SR9800 based USB 2.0 10/100 ethernet devices" + depends on USB_USBNET + select CRC32 + ---help--- + Say Y if you want to use one of the following 100Mbps USB Ethernet + device based on the CoreChip-sz SR9800 chip. + + This driver makes the adapter appear as a normal Ethernet interface, + typically on eth0, if it is the only ethernet device, or perhaps on + eth1, if you have a PCI or ISA ethernet card installed. + + To compile this driver as a module, choose M here: the + module will be called sr9800. + config USB_NET_SMSC75XX tristate "SMSC LAN75XX based USB 2.0 gigabit ethernet devices" depends on USB_USBNET diff --git a/drivers/net/usb/Makefile b/drivers/net/usb/Makefile index b17b5e88bbaf..433f0a00c683 100644 --- a/drivers/net/usb/Makefile +++ b/drivers/net/usb/Makefile @@ -15,6 +15,7 @@ obj-$(CONFIG_USB_NET_CDCETHER) += cdc_ether.o r815x.o obj-$(CONFIG_USB_NET_CDC_EEM) += cdc_eem.o obj-$(CONFIG_USB_NET_DM9601) += dm9601.o obj-$(CONFIG_USB_NET_SR9700) += sr9700.o +obj-$(CONFIG_USB_NET_SR9800) += sr9800.o obj-$(CONFIG_USB_NET_SMSC75XX) += smsc75xx.o obj-$(CONFIG_USB_NET_SMSC95XX) += smsc95xx.o obj-$(CONFIG_USB_NET_GL620A) += gl620a.o diff --git a/drivers/net/usb/asix_devices.c b/drivers/net/usb/asix_devices.c index 9765a7d4766d..5d194093f3e1 100644 --- a/drivers/net/usb/asix_devices.c +++ b/drivers/net/usb/asix_devices.c @@ -917,7 +917,8 @@ static const struct driver_info ax88178_info = { .status = asix_status, .link_reset = ax88178_link_reset, .reset = ax88178_reset, - .flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_LINK_INTR, + .flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_LINK_INTR | + FLAG_MULTI_PACKET, .rx_fixup = asix_rx_fixup_common, .tx_fixup = asix_tx_fixup, }; diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c index d6f64dad05bc..d2e6fdb25e28 100644 --- a/drivers/net/usb/ax88179_178a.c +++ b/drivers/net/usb/ax88179_178a.c @@ -1118,6 +1118,10 @@ static int ax88179_rx_fixup(struct usbnet *dev, struct sk_buff *skb) u16 hdr_off; u32 *pkt_hdr; + /* This check is no longer done by usbnet */ + if (skb->len < dev->net->hard_header_len) + return 0; + skb_trim(skb, skb->len - 4); memcpy(&rx_hdr, skb_tail_pointer(skb), 4); le32_to_cpus(&rx_hdr); @@ -1391,6 +1395,19 @@ static const struct driver_info ax88178a_info = { .tx_fixup = ax88179_tx_fixup, }; +static const struct driver_info dlink_dub1312_info = { + .description = "D-Link DUB-1312 USB 3.0 to Gigabit Ethernet Adapter", + .bind = ax88179_bind, + .unbind = ax88179_unbind, + .status = ax88179_status, + .link_reset = ax88179_link_reset, + .reset = ax88179_reset, + .stop = ax88179_stop, + .flags = FLAG_ETHER | FLAG_FRAMING_AX, + .rx_fixup = ax88179_rx_fixup, + .tx_fixup = ax88179_tx_fixup, +}; + static const struct driver_info sitecom_info = { .description = "Sitecom USB 3.0 to Gigabit Adapter", .bind = ax88179_bind, @@ -1417,6 +1434,19 @@ static const struct driver_info samsung_info = { .tx_fixup = ax88179_tx_fixup, }; +static const struct driver_info lenovo_info = { + .description = "Lenovo OneLinkDock Gigabit LAN", + .bind = ax88179_bind, + .unbind = ax88179_unbind, + .status = ax88179_status, + .link_reset = ax88179_link_reset, + .reset = ax88179_reset, + .stop = ax88179_stop, + .flags = FLAG_ETHER | FLAG_FRAMING_AX, + .rx_fixup = ax88179_rx_fixup, + .tx_fixup = ax88179_tx_fixup, +}; + static const struct usb_device_id products[] = { { /* ASIX AX88179 10/100/1000 */ @@ -1427,6 +1457,10 @@ static const struct usb_device_id products[] = { USB_DEVICE(0x0b95, 0x178a), .driver_info = (unsigned long)&ax88178a_info, }, { + /* D-Link DUB-1312 USB 3.0 to Gigabit Ethernet Adapter */ + USB_DEVICE(0x2001, 0x4a00), + .driver_info = (unsigned long)&dlink_dub1312_info, +}, { /* Sitecom USB 3.0 to Gigabit Adapter */ USB_DEVICE(0x0df6, 0x0072), .driver_info = (unsigned long)&sitecom_info, @@ -1434,6 +1468,10 @@ static const struct usb_device_id products[] = { /* Samsung USB Ethernet Adapter */ USB_DEVICE(0x04e8, 0xa100), .driver_info = (unsigned long)&samsung_info, +}, { + /* Lenovo OneLinkDock Gigabit LAN */ + USB_DEVICE(0x17ef, 0x304b), + .driver_info = (unsigned long)&lenovo_info, }, { }, }; diff --git a/drivers/net/usb/gl620a.c b/drivers/net/usb/gl620a.c index e4a8a93fbaf7..1cc24e6f23e2 100644 --- a/drivers/net/usb/gl620a.c +++ b/drivers/net/usb/gl620a.c @@ -84,6 +84,10 @@ static int genelink_rx_fixup(struct usbnet *dev, struct sk_buff *skb) u32 size; u32 count; + /* This check is no longer done by usbnet */ + if (skb->len < dev->net->hard_header_len) + return 0; + header = (struct gl_header *) skb->data; // get the packet count of the received skb diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c index 1a482344b3f5..660bd5ea9fc0 100644 --- a/drivers/net/usb/hso.c +++ b/drivers/net/usb/hso.c @@ -1201,16 +1201,18 @@ static void hso_std_serial_read_bulk_callback(struct urb *urb) struct hso_serial *serial = urb->context; int status = urb->status; + D4("\n--- Got serial_read_bulk callback %02x ---", status); + /* sanity check */ if (!serial) { D1("serial == NULL"); return; - } else if (status) { + } + if (status) { handle_usb_error(status, __func__, serial->parent); return; } - D4("\n--- Got serial_read_bulk callback %02x ---", status); D1("Actual length = %d\n", urb->actual_length); DUMP1(urb->transfer_buffer, urb->actual_length); @@ -1218,25 +1220,13 @@ static void hso_std_serial_read_bulk_callback(struct urb *urb) if (serial->port.count == 0) return; - if (status == 0) { - if (serial->parent->port_spec & HSO_INFO_CRC_BUG) - fix_crc_bug(urb, serial->in_endp->wMaxPacketSize); - /* Valid data, handle RX data */ - spin_lock(&serial->serial_lock); - serial->rx_urb_filled[hso_urb_to_index(serial, urb)] = 1; - put_rxbuf_data_and_resubmit_bulk_urb(serial); - spin_unlock(&serial->serial_lock); - } else if (status == -ENOENT || status == -ECONNRESET) { - /* Unlinked - check for throttled port. */ - D2("Port %d, successfully unlinked urb", serial->minor); - spin_lock(&serial->serial_lock); - serial->rx_urb_filled[hso_urb_to_index(serial, urb)] = 0; - hso_resubmit_rx_bulk_urb(serial, urb); - spin_unlock(&serial->serial_lock); - } else { - D2("Port %d, status = %d for read urb", serial->minor, status); - return; - } + if (serial->parent->port_spec & HSO_INFO_CRC_BUG) + fix_crc_bug(urb, serial->in_endp->wMaxPacketSize); + /* Valid data, handle RX data */ + spin_lock(&serial->serial_lock); + serial->rx_urb_filled[hso_urb_to_index(serial, urb)] = 1; + put_rxbuf_data_and_resubmit_bulk_urb(serial); + spin_unlock(&serial->serial_lock); } /* diff --git a/drivers/net/usb/lg-vl600.c b/drivers/net/usb/lg-vl600.c index acfcc32b323d..8f37efd2d2fb 100644 --- a/drivers/net/usb/lg-vl600.c +++ b/drivers/net/usb/lg-vl600.c @@ -210,7 +210,7 @@ static int vl600_rx_fixup(struct usbnet *dev, struct sk_buff *skb) * (0x86dd) so Linux can understand it. */ if ((buf->data[sizeof(*ethhdr)] & 0xf0) == 0x60) - ethhdr->h_proto = __constant_htons(ETH_P_IPV6); + ethhdr->h_proto = htons(ETH_P_IPV6); } if (count) { diff --git a/drivers/net/usb/mcs7830.c b/drivers/net/usb/mcs7830.c index a305a7b2dae6..82d844a8ebd0 100644 --- a/drivers/net/usb/mcs7830.c +++ b/drivers/net/usb/mcs7830.c @@ -526,8 +526,9 @@ static int mcs7830_rx_fixup(struct usbnet *dev, struct sk_buff *skb) { u8 status; - if (skb->len == 0) { - dev_err(&dev->udev->dev, "unexpected empty rx frame\n"); + /* This check is no longer done by usbnet */ + if (skb->len < dev->net->hard_header_len) { + dev_err(&dev->udev->dev, "unexpected tiny rx frame\n"); return 0; } diff --git a/drivers/net/usb/net1080.c b/drivers/net/usb/net1080.c index 0a85d9227775..4cbdb1307f3e 100644 --- a/drivers/net/usb/net1080.c +++ b/drivers/net/usb/net1080.c @@ -364,6 +364,10 @@ static int net1080_rx_fixup(struct usbnet *dev, struct sk_buff *skb) struct nc_trailer *trailer; u16 hdr_len, packet_len; + /* This check is no longer done by usbnet */ + if (skb->len < dev->net->hard_header_len) + return 0; + if (!(skb->len & 0x01)) { netdev_dbg(dev->net, "rx framesize %d range %d..%d mtu %d\n", skb->len, dev->net->hard_header_len, dev->hard_mtu, diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 23bdd5b9274d..313cb6cd4848 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -80,10 +80,10 @@ static int qmi_wwan_rx_fixup(struct usbnet *dev, struct sk_buff *skb) { __be16 proto; - /* usbnet rx_complete guarantees that skb->len is at least - * hard_header_len, so we can inspect the dest address without - * checking skb->len - */ + /* This check is no longer done by usbnet */ + if (skb->len < dev->net->hard_header_len) + return 0; + switch (skb->data[0] & 0xf0) { case 0x40: proto = htons(ETH_P_IP); @@ -712,6 +712,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x19d2, 0x1255, 3)}, {QMI_FIXED_INTF(0x19d2, 0x1255, 4)}, {QMI_FIXED_INTF(0x19d2, 0x1256, 4)}, + {QMI_FIXED_INTF(0x19d2, 0x1270, 5)}, /* ZTE MF667 */ {QMI_FIXED_INTF(0x19d2, 0x1401, 2)}, {QMI_FIXED_INTF(0x19d2, 0x1402, 2)}, /* ZTE MF60 */ {QMI_FIXED_INTF(0x19d2, 0x1424, 2)}, @@ -723,6 +724,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x1199, 0x68a2, 8)}, /* Sierra Wireless MC7710 in QMI mode */ {QMI_FIXED_INTF(0x1199, 0x68a2, 19)}, /* Sierra Wireless MC7710 in QMI mode */ {QMI_FIXED_INTF(0x1199, 0x901c, 8)}, /* Sierra Wireless EM7700 */ + {QMI_FIXED_INTF(0x1199, 0x9051, 8)}, /* Netgear AirCard 340U */ {QMI_FIXED_INTF(0x1bbb, 0x011e, 4)}, /* Telekom Speedstick LTE II (Alcatel One Touch L100V LTE) */ {QMI_FIXED_INTF(0x2357, 0x0201, 4)}, /* TP-LINK HSUPA Modem MA180 */ {QMI_FIXED_INTF(0x2357, 0x9000, 4)}, /* TP-LINK MA260 */ @@ -730,6 +732,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x1bc7, 0x1201, 2)}, /* Telit LE920 */ {QMI_FIXED_INTF(0x0b3c, 0xc005, 6)}, /* Olivetti Olicard 200 */ {QMI_FIXED_INTF(0x1e2d, 0x0060, 4)}, /* Cinterion PLxx */ + {QMI_FIXED_INTF(0x1e2d, 0x0053, 4)}, /* Cinterion PHxx,PXxx */ /* 4. Gobi 1000 devices */ {QMI_GOBI1K_DEVICE(0x05c6, 0x9212)}, /* Acer Gobi Modem Device */ diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index e8fac732c6f1..aa1d5b2e9c30 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -21,9 +21,10 @@ #include <linux/list.h> #include <linux/ip.h> #include <linux/ipv6.h> +#include <net/ip6_checksum.h> /* Version Information */ -#define DRIVER_VERSION "v1.04.0 (2014/01/15)" +#define DRIVER_VERSION "v1.06.0 (2014/03/03)" #define DRIVER_AUTHOR "Realtek linux nic maintainers <nic_swsd@realtek.com>" #define DRIVER_DESC "Realtek RTL8152/RTL8153 Based USB Ethernet Adapters" #define MODULENAME "r8152" @@ -59,9 +60,11 @@ #define PLA_TCR0 0xe610 #define PLA_TCR1 0xe612 #define PLA_TXFIFO_CTRL 0xe618 -#define PLA_RSTTELLY 0xe800 +#define PLA_RSTTALLY 0xe800 #define PLA_CR 0xe813 #define PLA_CRWECR 0xe81c +#define PLA_CONFIG12 0xe81e /* CONFIG1, CONFIG2 */ +#define PLA_CONFIG34 0xe820 /* CONFIG3, CONFIG4 */ #define PLA_CONFIG5 0xe822 #define PLA_PHY_PWR 0xe84c #define PLA_OOB_CTRL 0xe84f @@ -69,7 +72,7 @@ #define PLA_MISC_0 0xe858 #define PLA_MISC_1 0xe85a #define PLA_OCP_GPHY_BASE 0xe86c -#define PLA_TELLYCNT 0xe890 +#define PLA_TALLYCNT 0xe890 #define PLA_SFF_STS_7 0xe8de #define PLA_PHYSTATUS 0xe908 #define PLA_BP_BA 0xfc26 @@ -177,6 +180,9 @@ /* PLA_TCR1 */ #define VERSION_MASK 0x7cf0 +/* PLA_RSTTALLY */ +#define TALLY_RESET 0x0001 + /* PLA_CR */ #define CR_RST 0x10 #define CR_RE 0x08 @@ -216,7 +222,14 @@ /* PAL_BDC_CR */ #define ALDPS_PROXY_MODE 0x0001 +/* PLA_CONFIG34 */ +#define LINK_ON_WAKE_EN 0x0010 +#define LINK_OFF_WAKE_EN 0x0008 + /* PLA_CONFIG5 */ +#define BWF_EN 0x0040 +#define MWF_EN 0x0020 +#define UWF_EN 0x0010 #define LAN_WAKE_EN 0x0002 /* PLA_LED_FEATURE */ @@ -436,6 +449,9 @@ enum rtl8152_flags { RTL8152_SET_RX_MODE, WORK_ENABLE, RTL8152_LINK_CHG, + SELECTIVE_SUSPEND, + PHY_RESET, + SCHEDULE_TASKLET, }; /* Define these values to match your device */ @@ -452,11 +468,37 @@ enum rtl8152_flags { #define REALTEK_USB_DEVICE(vend, prod) \ USB_DEVICE_INTERFACE_CLASS(vend, prod, USB_CLASS_VENDOR_SPEC) +struct tally_counter { + __le64 tx_packets; + __le64 rx_packets; + __le64 tx_errors; + __le32 rx_errors; + __le16 rx_missed; + __le16 align_errors; + __le32 tx_one_collision; + __le32 tx_multi_collision; + __le64 rx_unicast; + __le64 rx_broadcast; + __le32 rx_multicast; + __le16 tx_aborted; + __le16 tx_underun; +}; + struct rx_desc { __le32 opts1; #define RX_LEN_MASK 0x7fff + __le32 opts2; +#define RD_UDP_CS (1 << 23) +#define RD_TCP_CS (1 << 22) +#define RD_IPV6_CS (1 << 20) +#define RD_IPV4_CS (1 << 19) + __le32 opts3; +#define IPF (1 << 23) /* IP checksum fail */ +#define UDPF (1 << 22) /* UDP checksum fail */ +#define TCPF (1 << 21) /* TCP checksum fail */ + __le32 opts4; __le32 opts5; __le32 opts6; @@ -466,13 +508,21 @@ struct tx_desc { __le32 opts1; #define TX_FS (1 << 31) /* First segment of a packet */ #define TX_LS (1 << 30) /* Final segment of a packet */ -#define TX_LEN_MASK 0x3ffff +#define GTSENDV4 (1 << 28) +#define GTSENDV6 (1 << 27) +#define GTTCPHO_SHIFT 18 +#define GTTCPHO_MAX 0x7fU +#define TX_LEN_MAX 0x3ffffU __le32 opts2; #define UDP_CS (1 << 31) /* Calculate UDP/IP checksum */ #define TCP_CS (1 << 30) /* Calculate TCP/IP checksum */ #define IPV4_CS (1 << 29) /* Calculate IPv4 checksum */ #define IPV6_CS (1 << 28) /* Calculate IPv6 checksum */ +#define MSS_SHIFT 17 +#define MSS_MAX 0x7ffU +#define TCPHO_SHIFT 17 +#define TCPHO_MAX 0x7ffU }; struct r8152; @@ -514,11 +564,13 @@ struct r8152 { void (*init)(struct r8152 *); int (*enable)(struct r8152 *); void (*disable)(struct r8152 *); + void (*up)(struct r8152 *); void (*down)(struct r8152 *); void (*unload)(struct r8152 *); } rtl_ops; int intr_interval; + u32 saved_wolopts; u32 msg_enable; u32 tx_qlen; u16 ocp_base; @@ -537,12 +589,21 @@ enum rtl_version { RTL_VER_MAX }; +enum tx_csum_stat { + TX_CSUM_SUCCESS = 0, + TX_CSUM_TSO, + TX_CSUM_NONE +}; + /* Maximum number of multicast addresses to filter (vs. Rx-all-multicast). * The RTL chips use a 64 element hash table based on the Ethernet CRC. */ static const int multicast_filter_limit = 32; static unsigned int rx_buf_sz = 16384; +#define RTL_LIMITED_TSO_SIZE (rx_buf_sz - sizeof(struct tx_desc) - \ + VLAN_ETH_HLEN - VLAN_HLEN) + static int get_registers(struct r8152 *tp, u16 value, u16 index, u16 size, void *data) { @@ -580,6 +641,7 @@ int set_registers(struct r8152 *tp, u16 value, u16 index, u16 size, void *data) value, index, tmp, size, 500); kfree(tmp); + return ret; } @@ -865,11 +927,21 @@ static u16 sram_read(struct r8152 *tp, u16 addr) static int read_mii_word(struct net_device *netdev, int phy_id, int reg) { struct r8152 *tp = netdev_priv(netdev); + int ret; if (phy_id != R8152_PHY_ID) return -EINVAL; - return r8152_mdio_read(tp, reg); + ret = usb_autopm_get_interface(tp->intf); + if (ret < 0) + goto out; + + ret = r8152_mdio_read(tp, reg); + + usb_autopm_put_interface(tp->intf); + +out: + return ret; } static @@ -880,7 +952,12 @@ void write_mii_word(struct net_device *netdev, int phy_id, int reg, int val) if (phy_id != R8152_PHY_ID) return; + if (usb_autopm_get_interface(tp->intf) < 0) + return; + r8152_mdio_write(tp, reg, val); + + usb_autopm_put_interface(tp->intf); } static @@ -889,11 +966,26 @@ int r8152_submit_rx(struct r8152 *tp, struct rx_agg *agg, gfp_t mem_flags); static inline void set_ethernet_addr(struct r8152 *tp) { struct net_device *dev = tp->netdev; + int ret; u8 node_id[8] = {0}; - if (pla_ocp_read(tp, PLA_IDR, sizeof(node_id), node_id) < 0) + if (tp->version == RTL_VER_01) + ret = pla_ocp_read(tp, PLA_IDR, sizeof(node_id), node_id); + else + ret = pla_ocp_read(tp, PLA_BACKUP, sizeof(node_id), node_id); + + if (ret < 0) { netif_notice(tp, probe, dev, "inet addr fail\n"); - else { + } else { + if (tp->version != RTL_VER_01) { + ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CRWECR, + CRWECR_CONFIG); + pla_ocp_write(tp, PLA_IDR, BYTE_EN_SIX_BYTES, + sizeof(node_id), node_id); + ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CRWECR, + CRWECR_NORAML); + } + memcpy(dev->dev_addr, node_id, dev->addr_len); memcpy(dev->perm_addr, dev->dev_addr, dev->addr_len); } @@ -916,15 +1008,9 @@ static int rtl8152_set_mac_address(struct net_device *netdev, void *p) return 0; } -static struct net_device_stats *rtl8152_get_stats(struct net_device *dev) -{ - return &dev->stats; -} - static void read_bulk_callback(struct urb *urb) { struct net_device *netdev; - unsigned long flags; int status = urb->status; struct rx_agg *agg; struct r8152 *tp; @@ -951,14 +1037,16 @@ static void read_bulk_callback(struct urb *urb) if (!netif_carrier_ok(netdev)) return; + usb_mark_last_busy(tp->udev); + switch (status) { case 0: if (urb->actual_length < ETH_ZLEN) break; - spin_lock_irqsave(&tp->rx_lock, flags); + spin_lock(&tp->rx_lock); list_add_tail(&agg->list, &tp->rx_done); - spin_unlock_irqrestore(&tp->rx_lock, flags); + spin_unlock(&tp->rx_lock); tasklet_schedule(&tp->tl); return; case -ESHUTDOWN: @@ -981,9 +1069,9 @@ static void read_bulk_callback(struct urb *urb) if (result == -ENODEV) { netif_device_detach(tp->netdev); } else if (result) { - spin_lock_irqsave(&tp->rx_lock, flags); + spin_lock(&tp->rx_lock); list_add_tail(&agg->list, &tp->rx_done); - spin_unlock_irqrestore(&tp->rx_lock, flags); + spin_unlock(&tp->rx_lock); tasklet_schedule(&tp->tl); } } @@ -991,7 +1079,7 @@ static void read_bulk_callback(struct urb *urb) static void write_bulk_callback(struct urb *urb) { struct net_device_stats *stats; - unsigned long flags; + struct net_device *netdev; struct tx_agg *agg; struct r8152 *tp; int status = urb->status; @@ -1004,21 +1092,24 @@ static void write_bulk_callback(struct urb *urb) if (!tp) return; - stats = rtl8152_get_stats(tp->netdev); + netdev = tp->netdev; + stats = &netdev->stats; if (status) { if (net_ratelimit()) - netdev_warn(tp->netdev, "Tx status %d\n", status); + netdev_warn(netdev, "Tx status %d\n", status); stats->tx_errors += agg->skb_num; } else { stats->tx_packets += agg->skb_num; stats->tx_bytes += agg->skb_len; } - spin_lock_irqsave(&tp->tx_lock, flags); + spin_lock(&tp->tx_lock); list_add_tail(&agg->list, &tp->tx_free); - spin_unlock_irqrestore(&tp->tx_lock, flags); + spin_unlock(&tp->tx_lock); - if (!netif_carrier_ok(tp->netdev)) + usb_autopm_put_interface_async(tp->intf); + + if (!netif_carrier_ok(netdev)) return; if (!test_bit(WORK_ENABLE, &tp->flags)) @@ -1223,6 +1314,9 @@ static struct tx_agg *r8152_get_tx_agg(struct r8152 *tp) struct tx_agg *agg = NULL; unsigned long flags; + if (list_empty(&tp->tx_free)) + return NULL; + spin_lock_irqsave(&tp->tx_lock, flags); if (!list_empty(&tp->tx_free)) { struct list_head *cursor; @@ -1236,24 +1330,138 @@ static struct tx_agg *r8152_get_tx_agg(struct r8152 *tp) return agg; } -static void -r8152_tx_csum(struct r8152 *tp, struct tx_desc *desc, struct sk_buff *skb) +static inline __be16 get_protocol(struct sk_buff *skb) +{ + __be16 protocol; + + if (skb->protocol == htons(ETH_P_8021Q)) + protocol = vlan_eth_hdr(skb)->h_vlan_encapsulated_proto; + else + protocol = skb->protocol; + + return protocol; +} + +/* + * r8152_csum_workaround() + * The hw limites the value the transport offset. When the offset is out of the + * range, calculate the checksum by sw. + */ +static void r8152_csum_workaround(struct r8152 *tp, struct sk_buff *skb, + struct sk_buff_head *list) +{ + if (skb_shinfo(skb)->gso_size) { + netdev_features_t features = tp->netdev->features; + struct sk_buff_head seg_list; + struct sk_buff *segs, *nskb; + + features &= ~(NETIF_F_IP_CSUM | NETIF_F_SG | NETIF_F_TSO); + segs = skb_gso_segment(skb, features); + if (IS_ERR(segs) || !segs) + goto drop; + + __skb_queue_head_init(&seg_list); + + do { + nskb = segs; + segs = segs->next; + nskb->next = NULL; + __skb_queue_tail(&seg_list, nskb); + } while (segs); + + skb_queue_splice(&seg_list, list); + dev_kfree_skb(skb); + } else if (skb->ip_summed == CHECKSUM_PARTIAL) { + if (skb_checksum_help(skb) < 0) + goto drop; + + __skb_queue_head(list, skb); + } else { + struct net_device_stats *stats; + +drop: + stats = &tp->netdev->stats; + stats->tx_dropped++; + dev_kfree_skb(skb); + } +} + +/* + * msdn_giant_send_check() + * According to the document of microsoft, the TCP Pseudo Header excludes the + * packet length for IPv6 TCP large packets. + */ +static int msdn_giant_send_check(struct sk_buff *skb) { - memset(desc, 0, sizeof(*desc)); + const struct ipv6hdr *ipv6h; + struct tcphdr *th; + int ret; - desc->opts1 = cpu_to_le32((skb->len & TX_LEN_MASK) | TX_FS | TX_LS); + ret = skb_cow_head(skb, 0); + if (ret) + return ret; - if (skb->ip_summed == CHECKSUM_PARTIAL) { - __be16 protocol; + ipv6h = ipv6_hdr(skb); + th = tcp_hdr(skb); + + th->check = 0; + th->check = ~tcp_v6_check(0, &ipv6h->saddr, &ipv6h->daddr, 0); + + return ret; +} + +static int r8152_tx_csum(struct r8152 *tp, struct tx_desc *desc, + struct sk_buff *skb, u32 len, u32 transport_offset) +{ + u32 mss = skb_shinfo(skb)->gso_size; + u32 opts1, opts2 = 0; + int ret = TX_CSUM_SUCCESS; + + WARN_ON_ONCE(len > TX_LEN_MAX); + + opts1 = len | TX_FS | TX_LS; + + if (mss) { + if (transport_offset > GTTCPHO_MAX) { + netif_warn(tp, tx_err, tp->netdev, + "Invalid transport offset 0x%x for TSO\n", + transport_offset); + ret = TX_CSUM_TSO; + goto unavailable; + } + + switch (get_protocol(skb)) { + case htons(ETH_P_IP): + opts1 |= GTSENDV4; + break; + + case htons(ETH_P_IPV6): + if (msdn_giant_send_check(skb)) { + ret = TX_CSUM_TSO; + goto unavailable; + } + opts1 |= GTSENDV6; + break; + + default: + WARN_ON_ONCE(1); + break; + } + + opts1 |= transport_offset << GTTCPHO_SHIFT; + opts2 |= min(mss, MSS_MAX) << MSS_SHIFT; + } else if (skb->ip_summed == CHECKSUM_PARTIAL) { u8 ip_protocol; - u32 opts2 = 0; - if (skb->protocol == htons(ETH_P_8021Q)) - protocol = vlan_eth_hdr(skb)->h_vlan_encapsulated_proto; - else - protocol = skb->protocol; + if (transport_offset > TCPHO_MAX) { + netif_warn(tp, tx_err, tp->netdev, + "Invalid transport offset 0x%x\n", + transport_offset); + ret = TX_CSUM_NONE; + goto unavailable; + } - switch (protocol) { + switch (get_protocol(skb)) { case htons(ETH_P_IP): opts2 |= IPV4_CS; ip_protocol = ip_hdr(skb)->protocol; @@ -1269,24 +1477,34 @@ r8152_tx_csum(struct r8152 *tp, struct tx_desc *desc, struct sk_buff *skb) break; } - if (ip_protocol == IPPROTO_TCP) { + if (ip_protocol == IPPROTO_TCP) opts2 |= TCP_CS; - opts2 |= (skb_transport_offset(skb) & 0x7fff) << 17; - } else if (ip_protocol == IPPROTO_UDP) { + else if (ip_protocol == IPPROTO_UDP) opts2 |= UDP_CS; - } else { + else WARN_ON_ONCE(1); - } - desc->opts2 = cpu_to_le32(opts2); + opts2 |= transport_offset << TCPHO_SHIFT; } + + desc->opts2 = cpu_to_le32(opts2); + desc->opts1 = cpu_to_le32(opts1); + +unavailable: + return ret; } static int r8152_tx_agg_fill(struct r8152 *tp, struct tx_agg *agg) { - int remain; + struct sk_buff_head skb_head, *tx_queue = &tp->tx_queue; + int remain, ret; u8 *tx_data; + __skb_queue_head_init(&skb_head); + spin_lock(&tx_queue->lock); + skb_queue_splice_init(tx_queue, &skb_head); + spin_unlock(&tx_queue->lock); + tx_data = agg->head; agg->skb_num = agg->skb_len = 0; remain = rx_buf_sz; @@ -1295,32 +1513,56 @@ static int r8152_tx_agg_fill(struct r8152 *tp, struct tx_agg *agg) struct tx_desc *tx_desc; struct sk_buff *skb; unsigned int len; + u32 offset; - skb = skb_dequeue(&tp->tx_queue); + skb = __skb_dequeue(&skb_head); if (!skb) break; - remain -= sizeof(*tx_desc); - len = skb->len; - if (remain < len) { - skb_queue_head(&tp->tx_queue, skb); + len = skb->len + sizeof(*tx_desc); + + if (len > remain) { + __skb_queue_head(&skb_head, skb); break; } tx_data = tx_agg_align(tx_data); tx_desc = (struct tx_desc *)tx_data; + + offset = (u32)skb_transport_offset(skb); + + if (r8152_tx_csum(tp, tx_desc, skb, skb->len, offset)) { + r8152_csum_workaround(tp, skb, &skb_head); + continue; + } + tx_data += sizeof(*tx_desc); - r8152_tx_csum(tp, tx_desc, skb); - memcpy(tx_data, skb->data, len); - agg->skb_num++; + len = skb->len; + if (skb_copy_bits(skb, 0, tx_data, len) < 0) { + struct net_device_stats *stats = &tp->netdev->stats; + + stats->tx_dropped++; + dev_kfree_skb_any(skb); + tx_data -= sizeof(*tx_desc); + continue; + } + + tx_data += len; agg->skb_len += len; + agg->skb_num++; + dev_kfree_skb_any(skb); - tx_data += len; remain = rx_buf_sz - (int)(tx_agg_align(tx_data) - agg->head); } + if (!skb_queue_empty(&skb_head)) { + spin_lock(&tx_queue->lock); + skb_queue_splice(&skb_head, tx_queue); + spin_unlock(&tx_queue->lock); + } + netif_tx_lock(tp->netdev); if (netif_queue_stopped(tp->netdev) && @@ -1329,20 +1571,67 @@ static int r8152_tx_agg_fill(struct r8152 *tp, struct tx_agg *agg) netif_tx_unlock(tp->netdev); + ret = usb_autopm_get_interface_async(tp->intf); + if (ret < 0) + goto out_tx_fill; + usb_fill_bulk_urb(agg->urb, tp->udev, usb_sndbulkpipe(tp->udev, 2), agg->head, (int)(tx_data - (u8 *)agg->head), (usb_complete_t)write_bulk_callback, agg); - return usb_submit_urb(agg->urb, GFP_ATOMIC); + ret = usb_submit_urb(agg->urb, GFP_ATOMIC); + if (ret < 0) + usb_autopm_put_interface_async(tp->intf); + +out_tx_fill: + return ret; +} + +static u8 r8152_rx_csum(struct r8152 *tp, struct rx_desc *rx_desc) +{ + u8 checksum = CHECKSUM_NONE; + u32 opts2, opts3; + + if (tp->version == RTL_VER_01) + goto return_result; + + opts2 = le32_to_cpu(rx_desc->opts2); + opts3 = le32_to_cpu(rx_desc->opts3); + + if (opts2 & RD_IPV4_CS) { + if (opts3 & IPF) + checksum = CHECKSUM_NONE; + else if ((opts2 & RD_UDP_CS) && (opts3 & UDPF)) + checksum = CHECKSUM_NONE; + else if ((opts2 & RD_TCP_CS) && (opts3 & TCPF)) + checksum = CHECKSUM_NONE; + else + checksum = CHECKSUM_UNNECESSARY; + } else if (RD_IPV6_CS) { + if ((opts2 & RD_UDP_CS) && !(opts3 & UDPF)) + checksum = CHECKSUM_UNNECESSARY; + else if ((opts2 & RD_TCP_CS) && !(opts3 & TCPF)) + checksum = CHECKSUM_UNNECESSARY; + } + +return_result: + return checksum; } static void rx_bottom(struct r8152 *tp) { unsigned long flags; - struct list_head *cursor, *next; + struct list_head *cursor, *next, rx_queue; + if (list_empty(&tp->rx_done)) + return; + + INIT_LIST_HEAD(&rx_queue); spin_lock_irqsave(&tp->rx_lock, flags); - list_for_each_safe(cursor, next, &tp->rx_done) { + list_splice_init(&tp->rx_done, &rx_queue); + spin_unlock_irqrestore(&tp->rx_lock, flags); + + list_for_each_safe(cursor, next, &rx_queue) { struct rx_desc *rx_desc; struct rx_agg *agg; int len_used = 0; @@ -1351,7 +1640,6 @@ static void rx_bottom(struct r8152 *tp) int ret; list_del_init(cursor); - spin_unlock_irqrestore(&tp->rx_lock, flags); agg = list_entry(cursor, struct rx_agg, list); urb = agg->urb; @@ -1364,7 +1652,7 @@ static void rx_bottom(struct r8152 *tp) while (urb->actual_length > len_used) { struct net_device *netdev = tp->netdev; - struct net_device_stats *stats; + struct net_device_stats *stats = &netdev->stats; unsigned int pkt_len; struct sk_buff *skb; @@ -1376,23 +1664,24 @@ static void rx_bottom(struct r8152 *tp) if (urb->actual_length < len_used) break; - stats = rtl8152_get_stats(netdev); - pkt_len -= CRC_SIZE; rx_data += sizeof(struct rx_desc); skb = netdev_alloc_skb_ip_align(netdev, pkt_len); if (!skb) { stats->rx_dropped++; - break; + goto find_next_rx; } + + skb->ip_summed = r8152_rx_csum(tp, rx_desc); memcpy(skb->data, rx_data, pkt_len); skb_put(skb, pkt_len); skb->protocol = eth_type_trans(skb, netdev); - netif_rx(skb); + netif_receive_skb(skb); stats->rx_packets++; stats->rx_bytes += pkt_len; +find_next_rx: rx_data = rx_agg_align(rx_data + pkt_len + CRC_SIZE); rx_desc = (struct rx_desc *)rx_data; len_used = (int)(rx_data - (u8 *)agg->head); @@ -1401,13 +1690,13 @@ static void rx_bottom(struct r8152 *tp) submit: ret = r8152_submit_rx(tp, agg, GFP_ATOMIC); - spin_lock_irqsave(&tp->rx_lock, flags); if (ret && ret != -ENODEV) { - list_add_tail(&agg->list, next); + spin_lock_irqsave(&tp->rx_lock, flags); + list_add_tail(&agg->list, &tp->rx_done); + spin_unlock_irqrestore(&tp->rx_lock, flags); tasklet_schedule(&tp->tl); } } - spin_unlock_irqrestore(&tp->rx_lock, flags); } static void tx_bottom(struct r8152 *tp) @@ -1426,19 +1715,18 @@ static void tx_bottom(struct r8152 *tp) res = r8152_tx_agg_fill(tp, agg); if (res) { - struct net_device_stats *stats; - struct net_device *netdev; - unsigned long flags; - - netdev = tp->netdev; - stats = rtl8152_get_stats(netdev); + struct net_device *netdev = tp->netdev; if (res == -ENODEV) { netif_device_detach(netdev); } else { + struct net_device_stats *stats = &netdev->stats; + unsigned long flags; + netif_warn(tp, tx_err, netdev, "failed tx_urb %d\n", res); stats->tx_dropped += agg->skb_num; + spin_lock_irqsave(&tp->tx_lock, flags); list_add_tail(&agg->list, &tp->tx_free); spin_unlock_irqrestore(&tp->tx_lock, flags); @@ -1478,6 +1766,26 @@ int r8152_submit_rx(struct r8152 *tp, struct rx_agg *agg, gfp_t mem_flags) return usb_submit_urb(agg->urb, mem_flags); } +static void rtl_drop_queued_tx(struct r8152 *tp) +{ + struct net_device_stats *stats = &tp->netdev->stats; + struct sk_buff_head skb_head, *tx_queue = &tp->tx_queue; + struct sk_buff *skb; + + if (skb_queue_empty(tx_queue)) + return; + + __skb_queue_head_init(&skb_head); + spin_lock_bh(&tx_queue->lock); + skb_queue_splice_init(tx_queue, &skb_head); + spin_unlock_bh(&tx_queue->lock); + + while ((skb = __skb_dequeue(&skb_head))) { + dev_kfree_skb(skb); + stats->tx_dropped++; + } +} + static void rtl8152_tx_timeout(struct net_device *netdev) { struct r8152 *tp = netdev_priv(netdev); @@ -1541,7 +1849,7 @@ static void _rtl8152_set_rx_mode(struct net_device *netdev) } static netdev_tx_t rtl8152_start_xmit(struct sk_buff *skb, - struct net_device *netdev) + struct net_device *netdev) { struct r8152 *tp = netdev_priv(netdev); @@ -1549,13 +1857,17 @@ static netdev_tx_t rtl8152_start_xmit(struct sk_buff *skb, skb_queue_tail(&tp->tx_queue, skb); - if (list_empty(&tp->tx_free) && - skb_queue_len(&tp->tx_queue) > tp->tx_qlen) + if (!list_empty(&tp->tx_free)) { + if (test_bit(SELECTIVE_SUSPEND, &tp->flags)) { + set_bit(SCHEDULE_TASKLET, &tp->flags); + schedule_delayed_work(&tp->schedule, 0); + } else { + usb_mark_last_busy(tp->udev); + tasklet_schedule(&tp->tl); + } + } else if (skb_queue_len(&tp->tx_queue) > tp->tx_qlen) netif_stop_queue(netdev); - if (!list_empty(&tp->tx_free)) - tasklet_schedule(&tp->tl); - return NETDEV_TX_OK; } @@ -1613,6 +1925,18 @@ static void rtl_set_eee_plus(struct r8152 *tp) } } +static void rxdy_gated_en(struct r8152 *tp, bool enable) +{ + u32 ocp_data; + + ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_MISC_1); + if (enable) + ocp_data |= RXDY_GATED_EN; + else + ocp_data &= ~RXDY_GATED_EN; + ocp_write_word(tp, MCU_TYPE_PLA, PLA_MISC_1, ocp_data); +} + static int rtl_enable(struct r8152 *tp) { u32 ocp_data; @@ -1624,9 +1948,7 @@ static int rtl_enable(struct r8152 *tp) ocp_data |= CR_RE | CR_TE; ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CR, ocp_data); - ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_MISC_1); - ocp_data &= ~RXDY_GATED_EN; - ocp_write_word(tp, MCU_TYPE_PLA, PLA_MISC_1, ocp_data); + rxdy_gated_en(tp, false); INIT_LIST_HEAD(&tp->rx_done); ret = 0; @@ -1681,8 +2003,6 @@ static int rtl8153_enable(struct r8152 *tp) static void rtl8152_disable(struct r8152 *tp) { - struct net_device_stats *stats = rtl8152_get_stats(tp->netdev); - struct sk_buff *skb; u32 ocp_data; int i; @@ -1690,17 +2010,12 @@ static void rtl8152_disable(struct r8152 *tp) ocp_data &= ~RCR_ACPT_ALL; ocp_write_dword(tp, MCU_TYPE_PLA, PLA_RCR, ocp_data); - while ((skb = skb_dequeue(&tp->tx_queue))) { - dev_kfree_skb(skb); - stats->tx_dropped++; - } + rtl_drop_queued_tx(tp); for (i = 0; i < RTL8152_MAX_TX; i++) usb_kill_urb(tp->tx_info[i].urb); - ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_MISC_1); - ocp_data |= RXDY_GATED_EN; - ocp_write_word(tp, MCU_TYPE_PLA, PLA_MISC_1, ocp_data); + rxdy_gated_en(tp, true); for (i = 0; i < 1000; i++) { ocp_data = ocp_read_byte(tp, MCU_TYPE_PLA, PLA_OOB_CTRL); @@ -1721,18 +2036,209 @@ static void rtl8152_disable(struct r8152 *tp) rtl8152_nic_reset(tp); } +static void r8152_power_cut_en(struct r8152 *tp, bool enable) +{ + u32 ocp_data; + + ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_UPS_CTRL); + if (enable) + ocp_data |= POWER_CUT; + else + ocp_data &= ~POWER_CUT; + ocp_write_word(tp, MCU_TYPE_USB, USB_UPS_CTRL, ocp_data); + + ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_PM_CTRL_STATUS); + ocp_data &= ~RESUME_INDICATE; + ocp_write_word(tp, MCU_TYPE_USB, USB_PM_CTRL_STATUS, ocp_data); +} + +#define WAKE_ANY (WAKE_PHY | WAKE_MAGIC | WAKE_UCAST | WAKE_BCAST | WAKE_MCAST) + +static u32 __rtl_get_wol(struct r8152 *tp) +{ + u32 ocp_data; + u32 wolopts = 0; + + ocp_data = ocp_read_byte(tp, MCU_TYPE_PLA, PLA_CONFIG5); + if (!(ocp_data & LAN_WAKE_EN)) + return 0; + + ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_CONFIG34); + if (ocp_data & LINK_ON_WAKE_EN) + wolopts |= WAKE_PHY; + + ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_CONFIG5); + if (ocp_data & UWF_EN) + wolopts |= WAKE_UCAST; + if (ocp_data & BWF_EN) + wolopts |= WAKE_BCAST; + if (ocp_data & MWF_EN) + wolopts |= WAKE_MCAST; + + ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_CFG_WOL); + if (ocp_data & MAGIC_EN) + wolopts |= WAKE_MAGIC; + + return wolopts; +} + +static void __rtl_set_wol(struct r8152 *tp, u32 wolopts) +{ + u32 ocp_data; + + ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CRWECR, CRWECR_CONFIG); + + ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_CONFIG34); + ocp_data &= ~LINK_ON_WAKE_EN; + if (wolopts & WAKE_PHY) + ocp_data |= LINK_ON_WAKE_EN; + ocp_write_word(tp, MCU_TYPE_PLA, PLA_CONFIG34, ocp_data); + + ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_CONFIG5); + ocp_data &= ~(UWF_EN | BWF_EN | MWF_EN | LAN_WAKE_EN); + if (wolopts & WAKE_UCAST) + ocp_data |= UWF_EN; + if (wolopts & WAKE_BCAST) + ocp_data |= BWF_EN; + if (wolopts & WAKE_MCAST) + ocp_data |= MWF_EN; + if (wolopts & WAKE_ANY) + ocp_data |= LAN_WAKE_EN; + ocp_write_word(tp, MCU_TYPE_PLA, PLA_CONFIG5, ocp_data); + + ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CRWECR, CRWECR_NORAML); + + ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_CFG_WOL); + ocp_data &= ~MAGIC_EN; + if (wolopts & WAKE_MAGIC) + ocp_data |= MAGIC_EN; + ocp_write_word(tp, MCU_TYPE_PLA, PLA_CFG_WOL, ocp_data); + + if (wolopts & WAKE_ANY) + device_set_wakeup_enable(&tp->udev->dev, true); + else + device_set_wakeup_enable(&tp->udev->dev, false); +} + +static void rtl_runtime_suspend_enable(struct r8152 *tp, bool enable) +{ + if (enable) { + u32 ocp_data; + + __rtl_set_wol(tp, WAKE_ANY); + + ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CRWECR, CRWECR_CONFIG); + + ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_CONFIG34); + ocp_data |= LINK_OFF_WAKE_EN; + ocp_write_word(tp, MCU_TYPE_PLA, PLA_CONFIG34, ocp_data); + + ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CRWECR, CRWECR_NORAML); + } else { + __rtl_set_wol(tp, tp->saved_wolopts); + } +} + +static void rtl_phy_reset(struct r8152 *tp) +{ + u16 data; + int i; + + clear_bit(PHY_RESET, &tp->flags); + + data = r8152_mdio_read(tp, MII_BMCR); + + /* don't reset again before the previous one complete */ + if (data & BMCR_RESET) + return; + + data |= BMCR_RESET; + r8152_mdio_write(tp, MII_BMCR, data); + + for (i = 0; i < 50; i++) { + msleep(20); + if ((r8152_mdio_read(tp, MII_BMCR) & BMCR_RESET) == 0) + break; + } +} + +static void rtl_clear_bp(struct r8152 *tp) +{ + ocp_write_dword(tp, MCU_TYPE_PLA, PLA_BP_0, 0); + ocp_write_dword(tp, MCU_TYPE_PLA, PLA_BP_2, 0); + ocp_write_dword(tp, MCU_TYPE_PLA, PLA_BP_4, 0); + ocp_write_dword(tp, MCU_TYPE_PLA, PLA_BP_6, 0); + ocp_write_dword(tp, MCU_TYPE_USB, USB_BP_0, 0); + ocp_write_dword(tp, MCU_TYPE_USB, USB_BP_2, 0); + ocp_write_dword(tp, MCU_TYPE_USB, USB_BP_4, 0); + ocp_write_dword(tp, MCU_TYPE_USB, USB_BP_6, 0); + mdelay(3); + ocp_write_word(tp, MCU_TYPE_PLA, PLA_BP_BA, 0); + ocp_write_word(tp, MCU_TYPE_USB, USB_BP_BA, 0); +} + +static void r8153_clear_bp(struct r8152 *tp) +{ + ocp_write_byte(tp, MCU_TYPE_PLA, PLA_BP_EN, 0); + ocp_write_byte(tp, MCU_TYPE_USB, USB_BP_EN, 0); + rtl_clear_bp(tp); +} + +static void r8153_teredo_off(struct r8152 *tp) +{ + u32 ocp_data; + + ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_TEREDO_CFG); + ocp_data &= ~(TEREDO_SEL | TEREDO_RS_EVENT_MASK | OOB_TEREDO_EN); + ocp_write_word(tp, MCU_TYPE_PLA, PLA_TEREDO_CFG, ocp_data); + + ocp_write_word(tp, MCU_TYPE_PLA, PLA_WDT6_CTRL, WDT6_SET_MODE); + ocp_write_word(tp, MCU_TYPE_PLA, PLA_REALWOW_TIMER, 0); + ocp_write_dword(tp, MCU_TYPE_PLA, PLA_TEREDO_TIMER, 0); +} + +static void r8152b_disable_aldps(struct r8152 *tp) +{ + ocp_reg_write(tp, OCP_ALDPS_CONFIG, ENPDNPS | LINKENA | DIS_SDSAVE); + msleep(20); +} + +static inline void r8152b_enable_aldps(struct r8152 *tp) +{ + ocp_reg_write(tp, OCP_ALDPS_CONFIG, ENPWRSAVE | ENPDNPS | + LINKENA | DIS_SDSAVE); +} + +static void r8152b_hw_phy_cfg(struct r8152 *tp) +{ + u16 data; + + data = r8152_mdio_read(tp, MII_BMCR); + if (data & BMCR_PDOWN) { + data &= ~BMCR_PDOWN; + r8152_mdio_write(tp, MII_BMCR, data); + } + + r8152b_disable_aldps(tp); + + rtl_clear_bp(tp); + + r8152b_enable_aldps(tp); + set_bit(PHY_RESET, &tp->flags); +} + static void r8152b_exit_oob(struct r8152 *tp) { - u32 ocp_data; - int i; + u32 ocp_data; + int i; ocp_data = ocp_read_dword(tp, MCU_TYPE_PLA, PLA_RCR); ocp_data &= ~RCR_ACPT_ALL; ocp_write_dword(tp, MCU_TYPE_PLA, PLA_RCR, ocp_data); - ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_MISC_1); - ocp_data |= RXDY_GATED_EN; - ocp_write_word(tp, MCU_TYPE_PLA, PLA_MISC_1, ocp_data); + rxdy_gated_en(tp, true); + r8153_teredo_off(tp); + r8152b_hw_phy_cfg(tp); ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CRWECR, CRWECR_NORAML); ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CR, 0x00); @@ -1838,10 +2344,6 @@ static void r8152b_enter_oob(struct r8152 *tp) ocp_write_word(tp, MCU_TYPE_PLA, PLA_RMS, RTL8152_RMS); - ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_CFG_WOL); - ocp_data |= MAGIC_EN; - ocp_write_word(tp, MCU_TYPE_PLA, PLA_CFG_WOL, ocp_data); - ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_CPCR); ocp_data |= CPCR_RX_VLAN; ocp_write_word(tp, MCU_TYPE_PLA, PLA_CPCR, ocp_data); @@ -1854,36 +2356,26 @@ static void r8152b_enter_oob(struct r8152 *tp) ocp_data |= NOW_IS_OOB | DIS_MCU_CLROOB; ocp_write_byte(tp, MCU_TYPE_PLA, PLA_OOB_CTRL, ocp_data); - ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CONFIG5, LAN_WAKE_EN); - - ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_MISC_1); - ocp_data &= ~RXDY_GATED_EN; - ocp_write_word(tp, MCU_TYPE_PLA, PLA_MISC_1, ocp_data); + rxdy_gated_en(tp, false); ocp_data = ocp_read_dword(tp, MCU_TYPE_PLA, PLA_RCR); ocp_data |= RCR_APM | RCR_AM | RCR_AB; ocp_write_dword(tp, MCU_TYPE_PLA, PLA_RCR, ocp_data); } -static void r8152b_disable_aldps(struct r8152 *tp) -{ - ocp_reg_write(tp, OCP_ALDPS_CONFIG, ENPDNPS | LINKENA | DIS_SDSAVE); - msleep(20); -} - -static inline void r8152b_enable_aldps(struct r8152 *tp) -{ - ocp_reg_write(tp, OCP_ALDPS_CONFIG, ENPWRSAVE | ENPDNPS | - LINKENA | DIS_SDSAVE); -} - static void r8153_hw_phy_cfg(struct r8152 *tp) { u32 ocp_data; u16 data; ocp_reg_write(tp, OCP_ADC_CFG, CKADSEL_L | ADC_EN | EN_EMI_L); - r8152_mdio_write(tp, MII_BMCR, BMCR_ANENABLE); + data = r8152_mdio_read(tp, MII_BMCR); + if (data & BMCR_PDOWN) { + data &= ~BMCR_PDOWN; + r8152_mdio_write(tp, MII_BMCR, data); + } + + r8153_clear_bp(tp); if (tp->version == RTL_VER_03) { data = ocp_reg_read(tp, OCP_EEE_CFG); @@ -1919,9 +2411,11 @@ static void r8153_hw_phy_cfg(struct r8152 *tp) data = sram_read(tp, SRAM_10M_AMP2); data |= AMP_DN; sram_write(tp, SRAM_10M_AMP2, data); + + set_bit(PHY_RESET, &tp->flags); } -static void r8153_u1u2en(struct r8152 *tp, int enable) +static void r8153_u1u2en(struct r8152 *tp, bool enable) { u8 u1u2[8]; @@ -1933,7 +2427,7 @@ static void r8153_u1u2en(struct r8152 *tp, int enable) usb_ocp_write(tp, USB_TOLERANCE, BYTE_EN_SIX_BYTES, sizeof(u1u2), u1u2); } -static void r8153_u2p3en(struct r8152 *tp, int enable) +static void r8153_u2p3en(struct r8152 *tp, bool enable) { u32 ocp_data; @@ -1945,7 +2439,7 @@ static void r8153_u2p3en(struct r8152 *tp, int enable) ocp_write_word(tp, MCU_TYPE_USB, USB_U2P3_CTRL, ocp_data); } -static void r8153_power_cut_en(struct r8152 *tp, int enable) +static void r8153_power_cut_en(struct r8152 *tp, bool enable) { u32 ocp_data; @@ -1961,28 +2455,12 @@ static void r8153_power_cut_en(struct r8152 *tp, int enable) ocp_write_word(tp, MCU_TYPE_USB, USB_MISC_0, ocp_data); } -static void r8153_teredo_off(struct r8152 *tp) -{ - u32 ocp_data; - - ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_TEREDO_CFG); - ocp_data &= ~(TEREDO_SEL | TEREDO_RS_EVENT_MASK | OOB_TEREDO_EN); - ocp_write_word(tp, MCU_TYPE_PLA, PLA_TEREDO_CFG, ocp_data); - - ocp_write_word(tp, MCU_TYPE_PLA, PLA_WDT6_CTRL, WDT6_SET_MODE); - ocp_write_word(tp, MCU_TYPE_PLA, PLA_REALWOW_TIMER, 0); - ocp_write_dword(tp, MCU_TYPE_PLA, PLA_TEREDO_TIMER, 0); -} - static void r8153_first_init(struct r8152 *tp) { u32 ocp_data; int i; - ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_MISC_1); - ocp_data |= RXDY_GATED_EN; - ocp_write_word(tp, MCU_TYPE_PLA, PLA_MISC_1, ocp_data); - + rxdy_gated_en(tp, true); r8153_teredo_off(tp); ocp_data = ocp_read_dword(tp, MCU_TYPE_PLA, PLA_RCR); @@ -2075,10 +2553,6 @@ static void r8153_enter_oob(struct r8152 *tp) ocp_write_word(tp, MCU_TYPE_PLA, PLA_RMS, RTL8152_RMS); - ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_CFG_WOL); - ocp_data |= MAGIC_EN; - ocp_write_word(tp, MCU_TYPE_PLA, PLA_CFG_WOL, ocp_data); - ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_TEREDO_CFG); ocp_data &= ~TEREDO_WAKE_MASK; ocp_write_word(tp, MCU_TYPE_PLA, PLA_TEREDO_CFG, ocp_data); @@ -2095,11 +2569,7 @@ static void r8153_enter_oob(struct r8152 *tp) ocp_data |= NOW_IS_OOB | DIS_MCU_CLROOB; ocp_write_byte(tp, MCU_TYPE_PLA, PLA_OOB_CTRL, ocp_data); - ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CONFIG5, LAN_WAKE_EN); - - ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_MISC_1); - ocp_data &= ~RXDY_GATED_EN; - ocp_write_word(tp, MCU_TYPE_PLA, PLA_MISC_1, ocp_data); + rxdy_gated_en(tp, false); ocp_data = ocp_read_dword(tp, MCU_TYPE_PLA, PLA_RCR); ocp_data |= RCR_APM | RCR_AM | RCR_AB; @@ -2190,12 +2660,26 @@ static int rtl8152_set_speed(struct r8152 *tp, u8 autoneg, u16 speed, u8 duplex) bmcr = BMCR_ANENABLE | BMCR_ANRESTART; } + if (test_bit(PHY_RESET, &tp->flags)) + bmcr |= BMCR_RESET; + if (tp->mii.supports_gmii) r8152_mdio_write(tp, MII_CTRL1000, gbcr); r8152_mdio_write(tp, MII_ADVERTISE, anar); r8152_mdio_write(tp, MII_BMCR, bmcr); + if (test_bit(PHY_RESET, &tp->flags)) { + int i; + + clear_bit(PHY_RESET, &tp->flags); + for (i = 0; i < 50; i++) { + msleep(20); + if ((r8152_mdio_read(tp, MII_BMCR) & BMCR_RESET) == 0) + break; + } + } + out: return ret; @@ -2203,12 +2687,7 @@ out: static void rtl8152_down(struct r8152 *tp) { - u32 ocp_data; - - ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_UPS_CTRL); - ocp_data &= ~POWER_CUT; - ocp_write_word(tp, MCU_TYPE_USB, USB_UPS_CTRL, ocp_data); - + r8152_power_cut_en(tp, false); r8152b_disable_aldps(tp); r8152b_enter_oob(tp); r8152b_enable_aldps(tp); @@ -2216,8 +2695,8 @@ static void rtl8152_down(struct r8152 *tp) static void rtl8153_down(struct r8152 *tp) { - r8153_u1u2en(tp, 0); - r8153_power_cut_en(tp, 0); + r8153_u1u2en(tp, false); + r8153_power_cut_en(tp, false); r8153_disable_aldps(tp); r8153_enter_oob(tp); r8153_enable_aldps(tp); @@ -2252,6 +2731,9 @@ static void rtl_work_func_t(struct work_struct *work) { struct r8152 *tp = container_of(work, struct r8152, schedule.work); + if (usb_autopm_get_interface(tp->intf) < 0) + return; + if (!test_bit(WORK_ENABLE, &tp->flags)) goto out1; @@ -2264,8 +2746,17 @@ static void rtl_work_func_t(struct work_struct *work) if (test_bit(RTL8152_SET_RX_MODE, &tp->flags)) _rtl8152_set_rx_mode(tp->netdev); + if (test_bit(SCHEDULE_TASKLET, &tp->flags) && + (tp->speed & LINK_STATUS)) { + clear_bit(SCHEDULE_TASKLET, &tp->flags); + tasklet_schedule(&tp->tl); + } + + if (test_bit(PHY_RESET, &tp->flags)) + rtl_phy_reset(tp); + out1: - return; + usb_autopm_put_interface(tp->intf); } static int rtl8152_open(struct net_device *netdev) @@ -2273,15 +2764,27 @@ static int rtl8152_open(struct net_device *netdev) struct r8152 *tp = netdev_priv(netdev); int res = 0; - res = usb_submit_urb(tp->intr_urb, GFP_KERNEL); - if (res) { - if (res == -ENODEV) - netif_device_detach(tp->netdev); - netif_warn(tp, ifup, netdev, "intr_urb submit failed: %d\n", - res); - return res; + res = alloc_all_mem(tp); + if (res) + goto out; + + res = usb_autopm_get_interface(tp->intf); + if (res < 0) { + free_all_mem(tp); + goto out; } + /* The WORK_ENABLE may be set when autoresume occurs */ + if (test_bit(WORK_ENABLE, &tp->flags)) { + clear_bit(WORK_ENABLE, &tp->flags); + usb_kill_urb(tp->intr_urb); + cancel_delayed_work_sync(&tp->schedule); + if (tp->speed & LINK_STATUS) + tp->rtl_ops.disable(tp); + } + + tp->rtl_ops.up(tp); + rtl8152_set_speed(tp, AUTONEG_ENABLE, tp->mii.supports_gmii ? SPEED_1000 : SPEED_100, DUPLEX_FULL); @@ -2290,6 +2793,18 @@ static int rtl8152_open(struct net_device *netdev) netif_start_queue(netdev); set_bit(WORK_ENABLE, &tp->flags); + res = usb_submit_urb(tp->intr_urb, GFP_KERNEL); + if (res) { + if (res == -ENODEV) + netif_device_detach(tp->netdev); + netif_warn(tp, ifup, netdev, "intr_urb submit failed: %d\n", + res); + free_all_mem(tp); + } + + usb_autopm_put_interface(tp->intf); + +out: return res; } @@ -2298,37 +2813,34 @@ static int rtl8152_close(struct net_device *netdev) struct r8152 *tp = netdev_priv(netdev); int res = 0; - usb_kill_urb(tp->intr_urb); clear_bit(WORK_ENABLE, &tp->flags); + usb_kill_urb(tp->intr_urb); cancel_delayed_work_sync(&tp->schedule); netif_stop_queue(netdev); - tasklet_disable(&tp->tl); - tp->rtl_ops.disable(tp); - tasklet_enable(&tp->tl); - return res; -} + res = usb_autopm_get_interface(tp->intf); + if (res < 0) { + rtl_drop_queued_tx(tp); + } else { + /* + * The autosuspend may have been enabled and wouldn't + * be disable when autoresume occurs, because the + * netif_running() would be false. + */ + if (test_bit(SELECTIVE_SUSPEND, &tp->flags)) { + rtl_runtime_suspend_enable(tp, false); + clear_bit(SELECTIVE_SUSPEND, &tp->flags); + } -static void rtl_clear_bp(struct r8152 *tp) -{ - ocp_write_dword(tp, MCU_TYPE_PLA, PLA_BP_0, 0); - ocp_write_dword(tp, MCU_TYPE_PLA, PLA_BP_2, 0); - ocp_write_dword(tp, MCU_TYPE_PLA, PLA_BP_4, 0); - ocp_write_dword(tp, MCU_TYPE_PLA, PLA_BP_6, 0); - ocp_write_dword(tp, MCU_TYPE_USB, USB_BP_0, 0); - ocp_write_dword(tp, MCU_TYPE_USB, USB_BP_2, 0); - ocp_write_dword(tp, MCU_TYPE_USB, USB_BP_4, 0); - ocp_write_dword(tp, MCU_TYPE_USB, USB_BP_6, 0); - mdelay(3); - ocp_write_word(tp, MCU_TYPE_PLA, PLA_BP_BA, 0); - ocp_write_word(tp, MCU_TYPE_USB, USB_BP_BA, 0); -} + tasklet_disable(&tp->tl); + tp->rtl_ops.down(tp); + tasklet_enable(&tp->tl); + usb_autopm_put_interface(tp->intf); + } -static void r8153_clear_bp(struct r8152 *tp) -{ - ocp_write_byte(tp, MCU_TYPE_PLA, PLA_BP_EN, 0); - ocp_write_byte(tp, MCU_TYPE_USB, USB_BP_EN, 0); - rtl_clear_bp(tp); + free_all_mem(tp); + + return res; } static void r8152b_enable_eee(struct r8152 *tp) @@ -2379,18 +2891,18 @@ static void r8152b_enable_fc(struct r8152 *tp) r8152_mdio_write(tp, MII_ADVERTISE, anar); } -static void r8152b_hw_phy_cfg(struct r8152 *tp) +static void rtl_tally_reset(struct r8152 *tp) { - r8152_mdio_write(tp, MII_BMCR, BMCR_ANENABLE); - r8152b_disable_aldps(tp); + u32 ocp_data; + + ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_RSTTALLY); + ocp_data |= TALLY_RESET; + ocp_write_word(tp, MCU_TYPE_PLA, PLA_RSTTALLY, ocp_data); } static void r8152b_init(struct r8152 *tp) { u32 ocp_data; - int i; - - rtl_clear_bp(tp); if (tp->version == RTL_VER_01) { ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_LED_FEATURE); @@ -2398,17 +2910,7 @@ static void r8152b_init(struct r8152 *tp) ocp_write_word(tp, MCU_TYPE_PLA, PLA_LED_FEATURE, ocp_data); } - r8152b_hw_phy_cfg(tp); - - ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_UPS_CTRL); - ocp_data &= ~POWER_CUT; - ocp_write_word(tp, MCU_TYPE_USB, USB_UPS_CTRL, ocp_data); - - ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_PM_CTRL_STATUS); - ocp_data &= ~RESUME_INDICATE; - ocp_write_word(tp, MCU_TYPE_USB, USB_PM_CTRL_STATUS, ocp_data); - - r8152b_exit_oob(tp); + r8152_power_cut_en(tp, false); ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_PHY_PWR); ocp_data |= TX_10M_IDLE_EN | PFM_PWM_SWITCH; @@ -2424,14 +2926,7 @@ static void r8152b_init(struct r8152 *tp) r8152b_enable_eee(tp); r8152b_enable_aldps(tp); r8152b_enable_fc(tp); - - r8152_mdio_write(tp, MII_BMCR, BMCR_RESET | BMCR_ANENABLE | - BMCR_ANRESTART); - for (i = 0; i < 100; i++) { - udelay(100); - if (!(r8152_mdio_read(tp, MII_BMCR) & BMCR_RESET)) - break; - } + rtl_tally_reset(tp); /* enable rx aggregation */ ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_USB_CTRL); @@ -2444,7 +2939,7 @@ static void r8153_init(struct r8152 *tp) u32 ocp_data; int i; - r8153_u1u2en(tp, 0); + r8153_u1u2en(tp, false); for (i = 0; i < 500; i++) { if (ocp_read_word(tp, MCU_TYPE_PLA, PLA_BOOT_CTRL) & @@ -2460,14 +2955,12 @@ static void r8153_init(struct r8152 *tp) msleep(20); } - r8153_u2p3en(tp, 0); + r8153_u2p3en(tp, false); ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_WDT11_CTRL); ocp_data &= ~TIMER11_EN; ocp_write_word(tp, MCU_TYPE_USB, USB_WDT11_CTRL, ocp_data); - r8153_clear_bp(tp); - ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_LED_FEATURE); ocp_data &= ~LED_MODE_MASK; ocp_write_word(tp, MCU_TYPE_PLA, PLA_LED_FEATURE, ocp_data); @@ -2485,10 +2978,8 @@ static void r8153_init(struct r8152 *tp) ocp_data |= SEN_VAL_NORMAL | SEL_RXIDLE; ocp_write_word(tp, MCU_TYPE_USB, USB_AFE_CTRL2, ocp_data); - r8153_power_cut_en(tp, 0); - r8153_u1u2en(tp, 1); - - r8153_first_init(tp); + r8153_power_cut_en(tp, false); + r8153_u1u2en(tp, true); ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL, ALDPS_SPDWN_RATIO); ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL2, EEE_SPDWN_RATIO); @@ -2503,26 +2994,31 @@ static void r8153_init(struct r8152 *tp) r8153_enable_eee(tp); r8153_enable_aldps(tp); r8152b_enable_fc(tp); - - r8152_mdio_write(tp, MII_BMCR, BMCR_RESET | BMCR_ANENABLE | - BMCR_ANRESTART); + rtl_tally_reset(tp); } static int rtl8152_suspend(struct usb_interface *intf, pm_message_t message) { struct r8152 *tp = usb_get_intfdata(intf); - netif_device_detach(tp->netdev); + if (PMSG_IS_AUTO(message)) + set_bit(SELECTIVE_SUSPEND, &tp->flags); + else + netif_device_detach(tp->netdev); if (netif_running(tp->netdev)) { clear_bit(WORK_ENABLE, &tp->flags); usb_kill_urb(tp->intr_urb); cancel_delayed_work_sync(&tp->schedule); - tasklet_disable(&tp->tl); + if (test_bit(SELECTIVE_SUSPEND, &tp->flags)) { + rtl_runtime_suspend_enable(tp, true); + } else { + tasklet_disable(&tp->tl); + tp->rtl_ops.down(tp); + tasklet_enable(&tp->tl); + } } - tp->rtl_ops.down(tp); - return 0; } @@ -2530,22 +3026,77 @@ static int rtl8152_resume(struct usb_interface *intf) { struct r8152 *tp = usb_get_intfdata(intf); - tp->rtl_ops.init(tp); - netif_device_attach(tp->netdev); + if (!test_bit(SELECTIVE_SUSPEND, &tp->flags)) { + tp->rtl_ops.init(tp); + netif_device_attach(tp->netdev); + } + if (netif_running(tp->netdev)) { - rtl8152_set_speed(tp, AUTONEG_ENABLE, + if (test_bit(SELECTIVE_SUSPEND, &tp->flags)) { + rtl_runtime_suspend_enable(tp, false); + clear_bit(SELECTIVE_SUSPEND, &tp->flags); + if (tp->speed & LINK_STATUS) + tp->rtl_ops.disable(tp); + } else { + tp->rtl_ops.up(tp); + rtl8152_set_speed(tp, AUTONEG_ENABLE, tp->mii.supports_gmii ? SPEED_1000 : SPEED_100, DUPLEX_FULL); + } tp->speed = 0; netif_carrier_off(tp->netdev); set_bit(WORK_ENABLE, &tp->flags); usb_submit_urb(tp->intr_urb, GFP_KERNEL); - tasklet_enable(&tp->tl); } return 0; } +static void rtl8152_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol) +{ + struct r8152 *tp = netdev_priv(dev); + + if (usb_autopm_get_interface(tp->intf) < 0) + return; + + wol->supported = WAKE_ANY; + wol->wolopts = __rtl_get_wol(tp); + + usb_autopm_put_interface(tp->intf); +} + +static int rtl8152_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol) +{ + struct r8152 *tp = netdev_priv(dev); + int ret; + + ret = usb_autopm_get_interface(tp->intf); + if (ret < 0) + goto out_set_wol; + + __rtl_set_wol(tp, wol->wolopts); + tp->saved_wolopts = wol->wolopts & WAKE_ANY; + + usb_autopm_put_interface(tp->intf); + +out_set_wol: + return ret; +} + +static u32 rtl8152_get_msglevel(struct net_device *dev) +{ + struct r8152 *tp = netdev_priv(dev); + + return tp->msg_enable; +} + +static void rtl8152_set_msglevel(struct net_device *dev, u32 value) +{ + struct r8152 *tp = netdev_priv(dev); + + tp->msg_enable = value; +} + static void rtl8152_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *info) { @@ -2570,8 +3121,76 @@ int rtl8152_get_settings(struct net_device *netdev, struct ethtool_cmd *cmd) static int rtl8152_set_settings(struct net_device *dev, struct ethtool_cmd *cmd) { struct r8152 *tp = netdev_priv(dev); + int ret; - return rtl8152_set_speed(tp, cmd->autoneg, cmd->speed, cmd->duplex); + ret = usb_autopm_get_interface(tp->intf); + if (ret < 0) + goto out; + + ret = rtl8152_set_speed(tp, cmd->autoneg, cmd->speed, cmd->duplex); + + usb_autopm_put_interface(tp->intf); + +out: + return ret; +} + +static const char rtl8152_gstrings[][ETH_GSTRING_LEN] = { + "tx_packets", + "rx_packets", + "tx_errors", + "rx_errors", + "rx_missed", + "align_errors", + "tx_single_collisions", + "tx_multi_collisions", + "rx_unicast", + "rx_broadcast", + "rx_multicast", + "tx_aborted", + "tx_underrun", +}; + +static int rtl8152_get_sset_count(struct net_device *dev, int sset) +{ + switch (sset) { + case ETH_SS_STATS: + return ARRAY_SIZE(rtl8152_gstrings); + default: + return -EOPNOTSUPP; + } +} + +static void rtl8152_get_ethtool_stats(struct net_device *dev, + struct ethtool_stats *stats, u64 *data) +{ + struct r8152 *tp = netdev_priv(dev); + struct tally_counter tally; + + generic_ocp_read(tp, PLA_TALLYCNT, sizeof(tally), &tally, MCU_TYPE_PLA); + + data[0] = le64_to_cpu(tally.tx_packets); + data[1] = le64_to_cpu(tally.rx_packets); + data[2] = le64_to_cpu(tally.tx_errors); + data[3] = le32_to_cpu(tally.rx_errors); + data[4] = le16_to_cpu(tally.rx_missed); + data[5] = le16_to_cpu(tally.align_errors); + data[6] = le32_to_cpu(tally.tx_one_collision); + data[7] = le32_to_cpu(tally.tx_multi_collision); + data[8] = le64_to_cpu(tally.rx_unicast); + data[9] = le64_to_cpu(tally.rx_broadcast); + data[10] = le32_to_cpu(tally.rx_multicast); + data[11] = le16_to_cpu(tally.tx_aborted); + data[12] = le16_to_cpu(tally.tx_underun); +} + +static void rtl8152_get_strings(struct net_device *dev, u32 stringset, u8 *data) +{ + switch (stringset) { + case ETH_SS_STATS: + memcpy(data, *rtl8152_gstrings, sizeof(rtl8152_gstrings)); + break; + } } static struct ethtool_ops ops = { @@ -2579,13 +3198,24 @@ static struct ethtool_ops ops = { .get_settings = rtl8152_get_settings, .set_settings = rtl8152_set_settings, .get_link = ethtool_op_get_link, + .get_msglevel = rtl8152_get_msglevel, + .set_msglevel = rtl8152_set_msglevel, + .get_wol = rtl8152_get_wol, + .set_wol = rtl8152_set_wol, + .get_strings = rtl8152_get_strings, + .get_sset_count = rtl8152_get_sset_count, + .get_ethtool_stats = rtl8152_get_ethtool_stats, }; static int rtl8152_ioctl(struct net_device *netdev, struct ifreq *rq, int cmd) { struct r8152 *tp = netdev_priv(netdev); struct mii_ioctl_data *data = if_mii(rq); - int res = 0; + int res; + + res = usb_autopm_get_interface(tp->intf); + if (res < 0) + goto out; switch (cmd) { case SIOCGMIIPHY: @@ -2608,6 +3238,9 @@ static int rtl8152_ioctl(struct net_device *netdev, struct ifreq *rq, int cmd) res = -EOPNOTSUPP; } + usb_autopm_put_interface(tp->intf); + +out: return res; } @@ -2660,22 +3293,13 @@ static void r8152b_get_version(struct r8152 *tp) static void rtl8152_unload(struct r8152 *tp) { - u32 ocp_data; - - if (tp->version != RTL_VER_01) { - ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_UPS_CTRL); - ocp_data |= POWER_CUT; - ocp_write_word(tp, MCU_TYPE_USB, USB_UPS_CTRL, ocp_data); - } - - ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_PM_CTRL_STATUS); - ocp_data &= ~RESUME_INDICATE; - ocp_write_word(tp, MCU_TYPE_USB, USB_PM_CTRL_STATUS, ocp_data); + if (tp->version != RTL_VER_01) + r8152_power_cut_en(tp, true); } static void rtl8153_unload(struct r8152 *tp) { - r8153_power_cut_en(tp, 1); + r8153_power_cut_en(tp, true); } static int rtl_ops_init(struct r8152 *tp, const struct usb_device_id *id) @@ -2690,6 +3314,7 @@ static int rtl_ops_init(struct r8152 *tp, const struct usb_device_id *id) ops->init = r8152b_init; ops->enable = rtl8152_enable; ops->disable = rtl8152_disable; + ops->up = r8152b_exit_oob; ops->down = rtl8152_down; ops->unload = rtl8152_unload; ret = 0; @@ -2698,6 +3323,7 @@ static int rtl_ops_init(struct r8152 *tp, const struct usb_device_id *id) ops->init = r8153_init; ops->enable = rtl8153_enable; ops->disable = rtl8152_disable; + ops->up = r8153_first_init; ops->down = rtl8153_down; ops->unload = rtl8153_unload; ret = 0; @@ -2713,6 +3339,7 @@ static int rtl_ops_init(struct r8152 *tp, const struct usb_device_id *id) ops->init = r8153_init; ops->enable = rtl8153_enable; ops->disable = rtl8152_disable; + ops->up = r8153_first_init; ops->down = rtl8153_down; ops->unload = rtl8153_unload; ret = 0; @@ -2764,9 +3391,15 @@ static int rtl8152_probe(struct usb_interface *intf, netdev->netdev_ops = &rtl8152_netdev_ops; netdev->watchdog_timeo = RTL8152_TX_TIMEOUT; - netdev->features |= NETIF_F_IP_CSUM; - netdev->hw_features = NETIF_F_IP_CSUM; + netdev->features |= NETIF_F_RXCSUM | NETIF_F_IP_CSUM | NETIF_F_SG | + NETIF_F_TSO | NETIF_F_FRAGLIST | NETIF_F_IPV6_CSUM | + NETIF_F_TSO6; + netdev->hw_features = NETIF_F_RXCSUM | NETIF_F_IP_CSUM | NETIF_F_SG | + NETIF_F_TSO | NETIF_F_FRAGLIST | + NETIF_F_IPV6_CSUM | NETIF_F_TSO6; + SET_ETHTOOL_OPS(netdev, &ops); + netif_set_gso_max_size(netdev, RTL_LIMITED_TSO_SIZE); tp->mii.dev = netdev; tp->mii.mdio_read = read_mii_word; @@ -2776,14 +3409,12 @@ static int rtl8152_probe(struct usb_interface *intf, tp->mii.phy_id = R8152_PHY_ID; tp->mii.supports_gmii = 0; + intf->needs_remote_wakeup = 1; + r8152b_get_version(tp); tp->rtl_ops.init(tp); set_ethernet_addr(tp); - ret = alloc_all_mem(tp); - if (ret) - goto out; - usb_set_intfdata(intf, tp); ret = register_netdev(netdev); @@ -2792,6 +3423,12 @@ static int rtl8152_probe(struct usb_interface *intf, goto out1; } + tp->saved_wolopts = __rtl_get_wol(tp); + if (tp->saved_wolopts) + device_set_wakeup_enable(&udev->dev, true); + else + device_set_wakeup_enable(&udev->dev, false); + netif_info(tp, probe, netdev, "%s\n", DRIVER_VERSION); return 0; @@ -2813,7 +3450,6 @@ static void rtl8152_disconnect(struct usb_interface *intf) tasklet_kill(&tp->tl); unregister_netdev(tp->netdev); tp->rtl_ops.unload(tp); - free_all_mem(tp); free_netdev(tp->netdev); } } @@ -2836,6 +3472,8 @@ static struct usb_driver rtl8152_driver = { .suspend = rtl8152_suspend, .resume = rtl8152_resume, .reset_resume = rtl8152_resume, + .supports_autosuspend = 1, + .disable_hub_initiated_lpm = 1, }; module_usb_driver(rtl8152_driver); diff --git a/drivers/net/usb/rndis_host.c b/drivers/net/usb/rndis_host.c index a48bc0f20c1a..524a47a28120 100644 --- a/drivers/net/usb/rndis_host.c +++ b/drivers/net/usb/rndis_host.c @@ -492,6 +492,10 @@ EXPORT_SYMBOL_GPL(rndis_unbind); */ int rndis_rx_fixup(struct usbnet *dev, struct sk_buff *skb) { + /* This check is no longer done by usbnet */ + if (skb->len < dev->net->hard_header_len) + return 0; + /* peripheral may have batched packets to us... */ while (likely(skb->len)) { struct rndis_data_hdr *hdr = (void *)skb->data; diff --git a/drivers/net/usb/smsc75xx.c b/drivers/net/usb/smsc75xx.c index f17b9e02dd34..d9e7892262fa 100644 --- a/drivers/net/usb/smsc75xx.c +++ b/drivers/net/usb/smsc75xx.c @@ -2106,6 +2106,10 @@ static void smsc75xx_rx_csum_offload(struct usbnet *dev, struct sk_buff *skb, static int smsc75xx_rx_fixup(struct usbnet *dev, struct sk_buff *skb) { + /* This check is no longer done by usbnet */ + if (skb->len < dev->net->hard_header_len) + return 0; + while (skb->len > 0) { u32 rx_cmd_a, rx_cmd_b, align_count, size; struct sk_buff *ax_skb; diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c index 8dd54a0f7b29..424db65e4396 100644 --- a/drivers/net/usb/smsc95xx.c +++ b/drivers/net/usb/smsc95xx.c @@ -1723,6 +1723,10 @@ static void smsc95xx_rx_csum_offload(struct sk_buff *skb) static int smsc95xx_rx_fixup(struct usbnet *dev, struct sk_buff *skb) { + /* This check is no longer done by usbnet */ + if (skb->len < dev->net->hard_header_len) + return 0; + while (skb->len > 0) { u32 header, align_count; struct sk_buff *ax_skb; diff --git a/drivers/net/usb/sr9800.c b/drivers/net/usb/sr9800.c new file mode 100644 index 000000000000..b94a0fbb8b3b --- /dev/null +++ b/drivers/net/usb/sr9800.c @@ -0,0 +1,874 @@ +/* CoreChip-sz SR9800 one chip USB 2.0 Ethernet Devices + * + * Author : Liu Junliang <liujunliang_ljl@163.com> + * + * Based on asix_common.c, asix_devices.c + * + * This file is licensed under the terms of the GNU General Public License + * version 2. This program is licensed "as is" without any warranty of any + * kind, whether express or implied.* + */ + +#include <linux/module.h> +#include <linux/kmod.h> +#include <linux/init.h> +#include <linux/netdevice.h> +#include <linux/etherdevice.h> +#include <linux/ethtool.h> +#include <linux/workqueue.h> +#include <linux/mii.h> +#include <linux/usb.h> +#include <linux/crc32.h> +#include <linux/usb/usbnet.h> +#include <linux/slab.h> +#include <linux/if_vlan.h> + +#include "sr9800.h" + +static int sr_read_cmd(struct usbnet *dev, u8 cmd, u16 value, u16 index, + u16 size, void *data) +{ + int err; + + err = usbnet_read_cmd(dev, cmd, SR_REQ_RD_REG, value, index, + data, size); + if ((err != size) && (err >= 0)) + err = -EINVAL; + + return err; +} + +static int sr_write_cmd(struct usbnet *dev, u8 cmd, u16 value, u16 index, + u16 size, void *data) +{ + int err; + + err = usbnet_write_cmd(dev, cmd, SR_REQ_WR_REG, value, index, + data, size); + if ((err != size) && (err >= 0)) + err = -EINVAL; + + return err; +} + +static void +sr_write_cmd_async(struct usbnet *dev, u8 cmd, u16 value, u16 index, + u16 size, void *data) +{ + usbnet_write_cmd_async(dev, cmd, SR_REQ_WR_REG, value, index, data, + size); +} + +static int sr_rx_fixup(struct usbnet *dev, struct sk_buff *skb) +{ + int offset = 0; + + /* This check is no longer done by usbnet */ + if (skb->len < dev->net->hard_header_len) + return 0; + + while (offset + sizeof(u32) < skb->len) { + struct sk_buff *sr_skb; + u16 size; + u32 header = get_unaligned_le32(skb->data + offset); + + offset += sizeof(u32); + /* get the packet length */ + size = (u16) (header & 0x7ff); + if (size != ((~header >> 16) & 0x07ff)) { + netdev_err(dev->net, "%s : Bad Header Length\n", + __func__); + return 0; + } + + if ((size > dev->net->mtu + ETH_HLEN + VLAN_HLEN) || + (size + offset > skb->len)) { + netdev_err(dev->net, "%s : Bad RX Length %d\n", + __func__, size); + return 0; + } + sr_skb = netdev_alloc_skb_ip_align(dev->net, size); + if (!sr_skb) + return 0; + + skb_put(sr_skb, size); + memcpy(sr_skb->data, skb->data + offset, size); + usbnet_skb_return(dev, sr_skb); + + offset += (size + 1) & 0xfffe; + } + + if (skb->len != offset) { + netdev_err(dev->net, "%s : Bad SKB Length %d\n", __func__, + skb->len); + return 0; + } + + return 1; +} + +static struct sk_buff *sr_tx_fixup(struct usbnet *dev, struct sk_buff *skb, + gfp_t flags) +{ + int headroom = skb_headroom(skb); + int tailroom = skb_tailroom(skb); + u32 padbytes = 0xffff0000; + u32 packet_len; + int padlen; + + padlen = ((skb->len + 4) % (dev->maxpacket - 1)) ? 0 : 4; + + if ((!skb_cloned(skb)) && ((headroom + tailroom) >= (4 + padlen))) { + if ((headroom < 4) || (tailroom < padlen)) { + skb->data = memmove(skb->head + 4, skb->data, + skb->len); + skb_set_tail_pointer(skb, skb->len); + } + } else { + struct sk_buff *skb2; + skb2 = skb_copy_expand(skb, 4, padlen, flags); + dev_kfree_skb_any(skb); + skb = skb2; + if (!skb) + return NULL; + } + + skb_push(skb, 4); + packet_len = (((skb->len - 4) ^ 0x0000ffff) << 16) + (skb->len - 4); + cpu_to_le32s(&packet_len); + skb_copy_to_linear_data(skb, &packet_len, sizeof(packet_len)); + + if (padlen) { + cpu_to_le32s(&padbytes); + memcpy(skb_tail_pointer(skb), &padbytes, sizeof(padbytes)); + skb_put(skb, sizeof(padbytes)); + } + + return skb; +} + +static void sr_status(struct usbnet *dev, struct urb *urb) +{ + struct sr9800_int_data *event; + int link; + + if (urb->actual_length < 8) + return; + + event = urb->transfer_buffer; + link = event->link & 0x01; + if (netif_carrier_ok(dev->net) != link) { + usbnet_link_change(dev, link, 1); + netdev_dbg(dev->net, "Link Status is: %d\n", link); + } + + return; +} + +static inline int sr_set_sw_mii(struct usbnet *dev) +{ + int ret; + + ret = sr_write_cmd(dev, SR_CMD_SET_SW_MII, 0x0000, 0, 0, NULL); + if (ret < 0) + netdev_err(dev->net, "Failed to enable software MII access\n"); + return ret; +} + +static inline int sr_set_hw_mii(struct usbnet *dev) +{ + int ret; + + ret = sr_write_cmd(dev, SR_CMD_SET_HW_MII, 0x0000, 0, 0, NULL); + if (ret < 0) + netdev_err(dev->net, "Failed to enable hardware MII access\n"); + return ret; +} + +static inline int sr_get_phy_addr(struct usbnet *dev) +{ + u8 buf[2]; + int ret; + + ret = sr_read_cmd(dev, SR_CMD_READ_PHY_ID, 0, 0, 2, buf); + if (ret < 0) { + netdev_err(dev->net, "%s : Error reading PHYID register:%02x\n", + __func__, ret); + goto out; + } + netdev_dbg(dev->net, "%s : returning 0x%04x\n", __func__, + *((__le16 *)buf)); + + ret = buf[1]; + +out: + return ret; +} + +static int sr_sw_reset(struct usbnet *dev, u8 flags) +{ + int ret; + + ret = sr_write_cmd(dev, SR_CMD_SW_RESET, flags, 0, 0, NULL); + if (ret < 0) + netdev_err(dev->net, "Failed to send software reset:%02x\n", + ret); + + return ret; +} + +static u16 sr_read_rx_ctl(struct usbnet *dev) +{ + __le16 v; + int ret; + + ret = sr_read_cmd(dev, SR_CMD_READ_RX_CTL, 0, 0, 2, &v); + if (ret < 0) { + netdev_err(dev->net, "Error reading RX_CTL register:%02x\n", + ret); + goto out; + } + + ret = le16_to_cpu(v); +out: + return ret; +} + +static int sr_write_rx_ctl(struct usbnet *dev, u16 mode) +{ + int ret; + + netdev_dbg(dev->net, "%s : mode = 0x%04x\n", __func__, mode); + ret = sr_write_cmd(dev, SR_CMD_WRITE_RX_CTL, mode, 0, 0, NULL); + if (ret < 0) + netdev_err(dev->net, + "Failed to write RX_CTL mode to 0x%04x:%02x\n", + mode, ret); + + return ret; +} + +static u16 sr_read_medium_status(struct usbnet *dev) +{ + __le16 v; + int ret; + + ret = sr_read_cmd(dev, SR_CMD_READ_MEDIUM_STATUS, 0, 0, 2, &v); + if (ret < 0) { + netdev_err(dev->net, + "Error reading Medium Status register:%02x\n", ret); + return ret; /* TODO: callers not checking for error ret */ + } + + return le16_to_cpu(v); +} + +static int sr_write_medium_mode(struct usbnet *dev, u16 mode) +{ + int ret; + + netdev_dbg(dev->net, "%s : mode = 0x%04x\n", __func__, mode); + ret = sr_write_cmd(dev, SR_CMD_WRITE_MEDIUM_MODE, mode, 0, 0, NULL); + if (ret < 0) + netdev_err(dev->net, + "Failed to write Medium Mode mode to 0x%04x:%02x\n", + mode, ret); + return ret; +} + +static int sr_write_gpio(struct usbnet *dev, u16 value, int sleep) +{ + int ret; + + netdev_dbg(dev->net, "%s : value = 0x%04x\n", __func__, value); + ret = sr_write_cmd(dev, SR_CMD_WRITE_GPIOS, value, 0, 0, NULL); + if (ret < 0) + netdev_err(dev->net, "Failed to write GPIO value 0x%04x:%02x\n", + value, ret); + if (sleep) + msleep(sleep); + + return ret; +} + +/* SR9800 have a 16-bit RX_CTL value */ +static void sr_set_multicast(struct net_device *net) +{ + struct usbnet *dev = netdev_priv(net); + struct sr_data *data = (struct sr_data *)&dev->data; + u16 rx_ctl = SR_DEFAULT_RX_CTL; + + if (net->flags & IFF_PROMISC) { + rx_ctl |= SR_RX_CTL_PRO; + } else if (net->flags & IFF_ALLMULTI || + netdev_mc_count(net) > SR_MAX_MCAST) { + rx_ctl |= SR_RX_CTL_AMALL; + } else if (netdev_mc_empty(net)) { + /* just broadcast and directed */ + } else { + /* We use the 20 byte dev->data + * for our 8 byte filter buffer + * to avoid allocating memory that + * is tricky to free later + */ + struct netdev_hw_addr *ha; + u32 crc_bits; + + memset(data->multi_filter, 0, SR_MCAST_FILTER_SIZE); + + /* Build the multicast hash filter. */ + netdev_for_each_mc_addr(ha, net) { + crc_bits = ether_crc(ETH_ALEN, ha->addr) >> 26; + data->multi_filter[crc_bits >> 3] |= + 1 << (crc_bits & 7); + } + + sr_write_cmd_async(dev, SR_CMD_WRITE_MULTI_FILTER, 0, 0, + SR_MCAST_FILTER_SIZE, data->multi_filter); + + rx_ctl |= SR_RX_CTL_AM; + } + + sr_write_cmd_async(dev, SR_CMD_WRITE_RX_CTL, rx_ctl, 0, 0, NULL); +} + +static int sr_mdio_read(struct net_device *net, int phy_id, int loc) +{ + struct usbnet *dev = netdev_priv(net); + __le16 res; + + mutex_lock(&dev->phy_mutex); + sr_set_sw_mii(dev); + sr_read_cmd(dev, SR_CMD_READ_MII_REG, phy_id, (__u16)loc, 2, &res); + sr_set_hw_mii(dev); + mutex_unlock(&dev->phy_mutex); + + netdev_dbg(dev->net, + "%s : phy_id=0x%02x, loc=0x%02x, returns=0x%04x\n", __func__, + phy_id, loc, le16_to_cpu(res)); + + return le16_to_cpu(res); +} + +static void +sr_mdio_write(struct net_device *net, int phy_id, int loc, int val) +{ + struct usbnet *dev = netdev_priv(net); + __le16 res = cpu_to_le16(val); + + netdev_dbg(dev->net, + "%s : phy_id=0x%02x, loc=0x%02x, val=0x%04x\n", __func__, + phy_id, loc, val); + mutex_lock(&dev->phy_mutex); + sr_set_sw_mii(dev); + sr_write_cmd(dev, SR_CMD_WRITE_MII_REG, phy_id, (__u16)loc, 2, &res); + sr_set_hw_mii(dev); + mutex_unlock(&dev->phy_mutex); +} + +/* Get the PHY Identifier from the PHYSID1 & PHYSID2 MII registers */ +static u32 sr_get_phyid(struct usbnet *dev) +{ + int phy_reg; + u32 phy_id; + int i; + + /* Poll for the rare case the FW or phy isn't ready yet. */ + for (i = 0; i < 100; i++) { + phy_reg = sr_mdio_read(dev->net, dev->mii.phy_id, MII_PHYSID1); + if (phy_reg != 0 && phy_reg != 0xFFFF) + break; + mdelay(1); + } + + if (phy_reg <= 0 || phy_reg == 0xFFFF) + return 0; + + phy_id = (phy_reg & 0xffff) << 16; + + phy_reg = sr_mdio_read(dev->net, dev->mii.phy_id, MII_PHYSID2); + if (phy_reg < 0) + return 0; + + phy_id |= (phy_reg & 0xffff); + + return phy_id; +} + +static void +sr_get_wol(struct net_device *net, struct ethtool_wolinfo *wolinfo) +{ + struct usbnet *dev = netdev_priv(net); + u8 opt; + + if (sr_read_cmd(dev, SR_CMD_READ_MONITOR_MODE, 0, 0, 1, &opt) < 0) { + wolinfo->supported = 0; + wolinfo->wolopts = 0; + return; + } + wolinfo->supported = WAKE_PHY | WAKE_MAGIC; + wolinfo->wolopts = 0; + if (opt & SR_MONITOR_LINK) + wolinfo->wolopts |= WAKE_PHY; + if (opt & SR_MONITOR_MAGIC) + wolinfo->wolopts |= WAKE_MAGIC; +} + +static int +sr_set_wol(struct net_device *net, struct ethtool_wolinfo *wolinfo) +{ + struct usbnet *dev = netdev_priv(net); + u8 opt = 0; + + if (wolinfo->wolopts & WAKE_PHY) + opt |= SR_MONITOR_LINK; + if (wolinfo->wolopts & WAKE_MAGIC) + opt |= SR_MONITOR_MAGIC; + + if (sr_write_cmd(dev, SR_CMD_WRITE_MONITOR_MODE, + opt, 0, 0, NULL) < 0) + return -EINVAL; + + return 0; +} + +static int sr_get_eeprom_len(struct net_device *net) +{ + struct usbnet *dev = netdev_priv(net); + struct sr_data *data = (struct sr_data *)&dev->data; + + return data->eeprom_len; +} + +static int sr_get_eeprom(struct net_device *net, + struct ethtool_eeprom *eeprom, u8 *data) +{ + struct usbnet *dev = netdev_priv(net); + __le16 *ebuf = (__le16 *)data; + int ret; + int i; + + /* Crude hack to ensure that we don't overwrite memory + * if an odd length is supplied + */ + if (eeprom->len % 2) + return -EINVAL; + + eeprom->magic = SR_EEPROM_MAGIC; + + /* sr9800 returns 2 bytes from eeprom on read */ + for (i = 0; i < eeprom->len / 2; i++) { + ret = sr_read_cmd(dev, SR_CMD_READ_EEPROM, eeprom->offset + i, + 0, 2, &ebuf[i]); + if (ret < 0) + return -EINVAL; + } + return 0; +} + +static void sr_get_drvinfo(struct net_device *net, + struct ethtool_drvinfo *info) +{ + struct usbnet *dev = netdev_priv(net); + struct sr_data *data = (struct sr_data *)&dev->data; + + /* Inherit standard device info */ + usbnet_get_drvinfo(net, info); + strncpy(info->driver, DRIVER_NAME, sizeof(info->driver)); + strncpy(info->version, DRIVER_VERSION, sizeof(info->version)); + info->eedump_len = data->eeprom_len; +} + +static u32 sr_get_link(struct net_device *net) +{ + struct usbnet *dev = netdev_priv(net); + + return mii_link_ok(&dev->mii); +} + +static int sr_ioctl(struct net_device *net, struct ifreq *rq, int cmd) +{ + struct usbnet *dev = netdev_priv(net); + + return generic_mii_ioctl(&dev->mii, if_mii(rq), cmd, NULL); +} + +static int sr_set_mac_address(struct net_device *net, void *p) +{ + struct usbnet *dev = netdev_priv(net); + struct sr_data *data = (struct sr_data *)&dev->data; + struct sockaddr *addr = p; + + if (netif_running(net)) + return -EBUSY; + if (!is_valid_ether_addr(addr->sa_data)) + return -EADDRNOTAVAIL; + + memcpy(net->dev_addr, addr->sa_data, ETH_ALEN); + + /* We use the 20 byte dev->data + * for our 6 byte mac buffer + * to avoid allocating memory that + * is tricky to free later + */ + memcpy(data->mac_addr, addr->sa_data, ETH_ALEN); + sr_write_cmd_async(dev, SR_CMD_WRITE_NODE_ID, 0, 0, ETH_ALEN, + data->mac_addr); + + return 0; +} + +static const struct ethtool_ops sr9800_ethtool_ops = { + .get_drvinfo = sr_get_drvinfo, + .get_link = sr_get_link, + .get_msglevel = usbnet_get_msglevel, + .set_msglevel = usbnet_set_msglevel, + .get_wol = sr_get_wol, + .set_wol = sr_set_wol, + .get_eeprom_len = sr_get_eeprom_len, + .get_eeprom = sr_get_eeprom, + .get_settings = usbnet_get_settings, + .set_settings = usbnet_set_settings, + .nway_reset = usbnet_nway_reset, +}; + +static int sr9800_link_reset(struct usbnet *dev) +{ + struct ethtool_cmd ecmd = { .cmd = ETHTOOL_GSET }; + u16 mode; + + mii_check_media(&dev->mii, 1, 1); + mii_ethtool_gset(&dev->mii, &ecmd); + mode = SR9800_MEDIUM_DEFAULT; + + if (ethtool_cmd_speed(&ecmd) != SPEED_100) + mode &= ~SR_MEDIUM_PS; + + if (ecmd.duplex != DUPLEX_FULL) + mode &= ~SR_MEDIUM_FD; + + netdev_dbg(dev->net, "%s : speed: %u duplex: %d mode: 0x%04x\n", + __func__, ethtool_cmd_speed(&ecmd), ecmd.duplex, mode); + + sr_write_medium_mode(dev, mode); + + return 0; +} + + +static int sr9800_set_default_mode(struct usbnet *dev) +{ + u16 rx_ctl; + int ret; + + sr_mdio_write(dev->net, dev->mii.phy_id, MII_BMCR, BMCR_RESET); + sr_mdio_write(dev->net, dev->mii.phy_id, MII_ADVERTISE, + ADVERTISE_ALL | ADVERTISE_CSMA); + mii_nway_restart(&dev->mii); + + ret = sr_write_medium_mode(dev, SR9800_MEDIUM_DEFAULT); + if (ret < 0) + goto out; + + ret = sr_write_cmd(dev, SR_CMD_WRITE_IPG012, + SR9800_IPG0_DEFAULT | SR9800_IPG1_DEFAULT, + SR9800_IPG2_DEFAULT, 0, NULL); + if (ret < 0) { + netdev_dbg(dev->net, "Write IPG,IPG1,IPG2 failed: %d\n", ret); + goto out; + } + + /* Set RX_CTL to default values with 2k buffer, and enable cactus */ + ret = sr_write_rx_ctl(dev, SR_DEFAULT_RX_CTL); + if (ret < 0) + goto out; + + rx_ctl = sr_read_rx_ctl(dev); + netdev_dbg(dev->net, "RX_CTL is 0x%04x after all initializations\n", + rx_ctl); + + rx_ctl = sr_read_medium_status(dev); + netdev_dbg(dev->net, "Medium Status:0x%04x after all initializations\n", + rx_ctl); + + return 0; +out: + return ret; +} + +static int sr9800_reset(struct usbnet *dev) +{ + struct sr_data *data = (struct sr_data *)&dev->data; + int ret, embd_phy; + u16 rx_ctl; + + ret = sr_write_gpio(dev, + SR_GPIO_RSE | SR_GPIO_GPO_2 | SR_GPIO_GPO2EN, 5); + if (ret < 0) + goto out; + + embd_phy = ((sr_get_phy_addr(dev) & 0x1f) == 0x10 ? 1 : 0); + + ret = sr_write_cmd(dev, SR_CMD_SW_PHY_SELECT, embd_phy, 0, 0, NULL); + if (ret < 0) { + netdev_dbg(dev->net, "Select PHY #1 failed: %d\n", ret); + goto out; + } + + ret = sr_sw_reset(dev, SR_SWRESET_IPPD | SR_SWRESET_PRL); + if (ret < 0) + goto out; + + msleep(150); + + ret = sr_sw_reset(dev, SR_SWRESET_CLEAR); + if (ret < 0) + goto out; + + msleep(150); + + if (embd_phy) { + ret = sr_sw_reset(dev, SR_SWRESET_IPRL); + if (ret < 0) + goto out; + } else { + ret = sr_sw_reset(dev, SR_SWRESET_PRTE); + if (ret < 0) + goto out; + } + + msleep(150); + rx_ctl = sr_read_rx_ctl(dev); + netdev_dbg(dev->net, "RX_CTL is 0x%04x after software reset\n", rx_ctl); + ret = sr_write_rx_ctl(dev, 0x0000); + if (ret < 0) + goto out; + + rx_ctl = sr_read_rx_ctl(dev); + netdev_dbg(dev->net, "RX_CTL is 0x%04x setting to 0x0000\n", rx_ctl); + + ret = sr_sw_reset(dev, SR_SWRESET_PRL); + if (ret < 0) + goto out; + + msleep(150); + + ret = sr_sw_reset(dev, SR_SWRESET_IPRL | SR_SWRESET_PRL); + if (ret < 0) + goto out; + + msleep(150); + + ret = sr9800_set_default_mode(dev); + if (ret < 0) + goto out; + + /* Rewrite MAC address */ + memcpy(data->mac_addr, dev->net->dev_addr, ETH_ALEN); + ret = sr_write_cmd(dev, SR_CMD_WRITE_NODE_ID, 0, 0, ETH_ALEN, + data->mac_addr); + if (ret < 0) + goto out; + + return 0; + +out: + return ret; +} + +static const struct net_device_ops sr9800_netdev_ops = { + .ndo_open = usbnet_open, + .ndo_stop = usbnet_stop, + .ndo_start_xmit = usbnet_start_xmit, + .ndo_tx_timeout = usbnet_tx_timeout, + .ndo_change_mtu = usbnet_change_mtu, + .ndo_set_mac_address = sr_set_mac_address, + .ndo_validate_addr = eth_validate_addr, + .ndo_do_ioctl = sr_ioctl, + .ndo_set_rx_mode = sr_set_multicast, +}; + +static int sr9800_phy_powerup(struct usbnet *dev) +{ + int ret; + + /* set the embedded Ethernet PHY in power-down state */ + ret = sr_sw_reset(dev, SR_SWRESET_IPPD | SR_SWRESET_IPRL); + if (ret < 0) { + netdev_err(dev->net, "Failed to power down PHY : %d\n", ret); + return ret; + } + msleep(20); + + /* set the embedded Ethernet PHY in power-up state */ + ret = sr_sw_reset(dev, SR_SWRESET_IPRL); + if (ret < 0) { + netdev_err(dev->net, "Failed to reset PHY: %d\n", ret); + return ret; + } + msleep(600); + + /* set the embedded Ethernet PHY in reset state */ + ret = sr_sw_reset(dev, SR_SWRESET_CLEAR); + if (ret < 0) { + netdev_err(dev->net, "Failed to power up PHY: %d\n", ret); + return ret; + } + msleep(20); + + /* set the embedded Ethernet PHY in power-up state */ + ret = sr_sw_reset(dev, SR_SWRESET_IPRL); + if (ret < 0) { + netdev_err(dev->net, "Failed to reset PHY: %d\n", ret); + return ret; + } + + return 0; +} + +static int sr9800_bind(struct usbnet *dev, struct usb_interface *intf) +{ + struct sr_data *data = (struct sr_data *)&dev->data; + u16 led01_mux, led23_mux; + int ret, embd_phy; + u32 phyid; + u16 rx_ctl; + + data->eeprom_len = SR9800_EEPROM_LEN; + + usbnet_get_endpoints(dev, intf); + + /* LED Setting Rule : + * AABB:CCDD + * AA : MFA0(LED0) + * BB : MFA1(LED1) + * CC : MFA2(LED2), Reserved for SR9800 + * DD : MFA3(LED3), Reserved for SR9800 + */ + led01_mux = (SR_LED_MUX_LINK_ACTIVE << 8) | SR_LED_MUX_LINK; + led23_mux = (SR_LED_MUX_LINK_ACTIVE << 8) | SR_LED_MUX_TX_ACTIVE; + ret = sr_write_cmd(dev, SR_CMD_LED_MUX, led01_mux, led23_mux, 0, NULL); + if (ret < 0) { + netdev_err(dev->net, "set LINK LED failed : %d\n", ret); + goto out; + } + + /* Get the MAC address */ + ret = sr_read_cmd(dev, SR_CMD_READ_NODE_ID, 0, 0, ETH_ALEN, + dev->net->dev_addr); + if (ret < 0) { + netdev_dbg(dev->net, "Failed to read MAC address: %d\n", ret); + return ret; + } + netdev_dbg(dev->net, "mac addr : %pM\n", dev->net->dev_addr); + + /* Initialize MII structure */ + dev->mii.dev = dev->net; + dev->mii.mdio_read = sr_mdio_read; + dev->mii.mdio_write = sr_mdio_write; + dev->mii.phy_id_mask = 0x1f; + dev->mii.reg_num_mask = 0x1f; + dev->mii.phy_id = sr_get_phy_addr(dev); + + dev->net->netdev_ops = &sr9800_netdev_ops; + dev->net->ethtool_ops = &sr9800_ethtool_ops; + + embd_phy = ((dev->mii.phy_id & 0x1f) == 0x10 ? 1 : 0); + /* Reset the PHY to normal operation mode */ + ret = sr_write_cmd(dev, SR_CMD_SW_PHY_SELECT, embd_phy, 0, 0, NULL); + if (ret < 0) { + netdev_dbg(dev->net, "Select PHY #1 failed: %d\n", ret); + return ret; + } + + /* Init PHY routine */ + ret = sr9800_phy_powerup(dev); + if (ret < 0) + goto out; + + rx_ctl = sr_read_rx_ctl(dev); + netdev_dbg(dev->net, "RX_CTL is 0x%04x after software reset\n", rx_ctl); + ret = sr_write_rx_ctl(dev, 0x0000); + if (ret < 0) + goto out; + + rx_ctl = sr_read_rx_ctl(dev); + netdev_dbg(dev->net, "RX_CTL is 0x%04x setting to 0x0000\n", rx_ctl); + + /* Read PHYID register *AFTER* the PHY was reset properly */ + phyid = sr_get_phyid(dev); + netdev_dbg(dev->net, "PHYID=0x%08x\n", phyid); + + /* medium mode setting */ + ret = sr9800_set_default_mode(dev); + if (ret < 0) + goto out; + + if (dev->udev->speed == USB_SPEED_HIGH) { + ret = sr_write_cmd(dev, SR_CMD_BULKIN_SIZE, + SR9800_BULKIN_SIZE[SR9800_MAX_BULKIN_4K].byte_cnt, + SR9800_BULKIN_SIZE[SR9800_MAX_BULKIN_4K].threshold, + 0, NULL); + if (ret < 0) { + netdev_err(dev->net, "Reset RX_CTL failed: %d\n", ret); + goto out; + } + dev->rx_urb_size = + SR9800_BULKIN_SIZE[SR9800_MAX_BULKIN_4K].size; + } else { + ret = sr_write_cmd(dev, SR_CMD_BULKIN_SIZE, + SR9800_BULKIN_SIZE[SR9800_MAX_BULKIN_2K].byte_cnt, + SR9800_BULKIN_SIZE[SR9800_MAX_BULKIN_2K].threshold, + 0, NULL); + if (ret < 0) { + netdev_err(dev->net, "Reset RX_CTL failed: %d\n", ret); + goto out; + } + dev->rx_urb_size = + SR9800_BULKIN_SIZE[SR9800_MAX_BULKIN_2K].size; + } + netdev_dbg(dev->net, "%s : setting rx_urb_size with : %zu\n", __func__, + dev->rx_urb_size); + return 0; + +out: + return ret; +} + +static const struct driver_info sr9800_driver_info = { + .description = "CoreChip SR9800 USB 2.0 Ethernet", + .bind = sr9800_bind, + .status = sr_status, + .link_reset = sr9800_link_reset, + .reset = sr9800_reset, + .flags = DRIVER_FLAG, + .rx_fixup = sr_rx_fixup, + .tx_fixup = sr_tx_fixup, +}; + +static const struct usb_device_id products[] = { + { + USB_DEVICE(0x0fe6, 0x9800), /* SR9800 Device */ + .driver_info = (unsigned long) &sr9800_driver_info, + }, + {}, /* END */ +}; + +MODULE_DEVICE_TABLE(usb, products); + +static struct usb_driver sr_driver = { + .name = DRIVER_NAME, + .id_table = products, + .probe = usbnet_probe, + .suspend = usbnet_suspend, + .resume = usbnet_resume, + .disconnect = usbnet_disconnect, + .supports_autosuspend = 1, +}; + +module_usb_driver(sr_driver); + +MODULE_AUTHOR("Liu Junliang <liujunliang_ljl@163.com"); +MODULE_VERSION(DRIVER_VERSION); +MODULE_DESCRIPTION("SR9800 USB 2.0 USB2NET Dev : http://www.corechip-sz.com"); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/usb/sr9800.h b/drivers/net/usb/sr9800.h new file mode 100644 index 000000000000..18f670251275 --- /dev/null +++ b/drivers/net/usb/sr9800.h @@ -0,0 +1,202 @@ +/* CoreChip-sz SR9800 one chip USB 2.0 Ethernet Devices + * + * Author : Liu Junliang <liujunliang_ljl@163.com> + * + * This file is licensed under the terms of the GNU General Public License + * version 2. This program is licensed "as is" without any warranty of any + * kind, whether express or implied. + */ + +#ifndef _SR9800_H +#define _SR9800_H + +/* SR9800 spec. command table on Linux Platform */ + +/* command : Software Station Management Control Reg */ +#define SR_CMD_SET_SW_MII 0x06 +/* command : PHY Read Reg */ +#define SR_CMD_READ_MII_REG 0x07 +/* command : PHY Write Reg */ +#define SR_CMD_WRITE_MII_REG 0x08 +/* command : Hardware Station Management Control Reg */ +#define SR_CMD_SET_HW_MII 0x0a +/* command : SROM Read Reg */ +#define SR_CMD_READ_EEPROM 0x0b +/* command : SROM Write Reg */ +#define SR_CMD_WRITE_EEPROM 0x0c +/* command : SROM Write Enable Reg */ +#define SR_CMD_WRITE_ENABLE 0x0d +/* command : SROM Write Disable Reg */ +#define SR_CMD_WRITE_DISABLE 0x0e +/* command : RX Control Read Reg */ +#define SR_CMD_READ_RX_CTL 0x0f +#define SR_RX_CTL_PRO (1 << 0) +#define SR_RX_CTL_AMALL (1 << 1) +#define SR_RX_CTL_SEP (1 << 2) +#define SR_RX_CTL_AB (1 << 3) +#define SR_RX_CTL_AM (1 << 4) +#define SR_RX_CTL_AP (1 << 5) +#define SR_RX_CTL_ARP (1 << 6) +#define SR_RX_CTL_SO (1 << 7) +#define SR_RX_CTL_RH1M (1 << 8) +#define SR_RX_CTL_RH2M (1 << 9) +#define SR_RX_CTL_RH3M (1 << 10) +/* command : RX Control Write Reg */ +#define SR_CMD_WRITE_RX_CTL 0x10 +/* command : IPG0/IPG1/IPG2 Control Read Reg */ +#define SR_CMD_READ_IPG012 0x11 +/* command : IPG0/IPG1/IPG2 Control Write Reg */ +#define SR_CMD_WRITE_IPG012 0x12 +/* command : Node ID Read Reg */ +#define SR_CMD_READ_NODE_ID 0x13 +/* command : Node ID Write Reg */ +#define SR_CMD_WRITE_NODE_ID 0x14 +/* command : Multicast Filter Array Read Reg */ +#define SR_CMD_READ_MULTI_FILTER 0x15 +/* command : Multicast Filter Array Write Reg */ +#define SR_CMD_WRITE_MULTI_FILTER 0x16 +/* command : Eth/HomePNA PHY Address Reg */ +#define SR_CMD_READ_PHY_ID 0x19 +/* command : Medium Status Read Reg */ +#define SR_CMD_READ_MEDIUM_STATUS 0x1a +#define SR_MONITOR_LINK (1 << 1) +#define SR_MONITOR_MAGIC (1 << 2) +#define SR_MONITOR_HSFS (1 << 4) +/* command : Medium Status Write Reg */ +#define SR_CMD_WRITE_MEDIUM_MODE 0x1b +#define SR_MEDIUM_GM (1 << 0) +#define SR_MEDIUM_FD (1 << 1) +#define SR_MEDIUM_AC (1 << 2) +#define SR_MEDIUM_ENCK (1 << 3) +#define SR_MEDIUM_RFC (1 << 4) +#define SR_MEDIUM_TFC (1 << 5) +#define SR_MEDIUM_JFE (1 << 6) +#define SR_MEDIUM_PF (1 << 7) +#define SR_MEDIUM_RE (1 << 8) +#define SR_MEDIUM_PS (1 << 9) +#define SR_MEDIUM_RSV (1 << 10) +#define SR_MEDIUM_SBP (1 << 11) +#define SR_MEDIUM_SM (1 << 12) +/* command : Monitor Mode Status Read Reg */ +#define SR_CMD_READ_MONITOR_MODE 0x1c +/* command : Monitor Mode Status Write Reg */ +#define SR_CMD_WRITE_MONITOR_MODE 0x1d +/* command : GPIO Status Read Reg */ +#define SR_CMD_READ_GPIOS 0x1e +#define SR_GPIO_GPO0EN (1 << 0) /* GPIO0 Output enable */ +#define SR_GPIO_GPO_0 (1 << 1) /* GPIO0 Output value */ +#define SR_GPIO_GPO1EN (1 << 2) /* GPIO1 Output enable */ +#define SR_GPIO_GPO_1 (1 << 3) /* GPIO1 Output value */ +#define SR_GPIO_GPO2EN (1 << 4) /* GPIO2 Output enable */ +#define SR_GPIO_GPO_2 (1 << 5) /* GPIO2 Output value */ +#define SR_GPIO_RESERVED (1 << 6) /* Reserved */ +#define SR_GPIO_RSE (1 << 7) /* Reload serial EEPROM */ +/* command : GPIO Status Write Reg */ +#define SR_CMD_WRITE_GPIOS 0x1f +/* command : Eth PHY Power and Reset Control Reg */ +#define SR_CMD_SW_RESET 0x20 +#define SR_SWRESET_CLEAR 0x00 +#define SR_SWRESET_RR (1 << 0) +#define SR_SWRESET_RT (1 << 1) +#define SR_SWRESET_PRTE (1 << 2) +#define SR_SWRESET_PRL (1 << 3) +#define SR_SWRESET_BZ (1 << 4) +#define SR_SWRESET_IPRL (1 << 5) +#define SR_SWRESET_IPPD (1 << 6) +/* command : Software Interface Selection Status Read Reg */ +#define SR_CMD_SW_PHY_STATUS 0x21 +/* command : Software Interface Selection Status Write Reg */ +#define SR_CMD_SW_PHY_SELECT 0x22 +/* command : BULK in Buffer Size Reg */ +#define SR_CMD_BULKIN_SIZE 0x2A +/* command : LED_MUX Control Reg */ +#define SR_CMD_LED_MUX 0x70 +#define SR_LED_MUX_TX_ACTIVE (1 << 0) +#define SR_LED_MUX_RX_ACTIVE (1 << 1) +#define SR_LED_MUX_COLLISION (1 << 2) +#define SR_LED_MUX_DUP_COL (1 << 3) +#define SR_LED_MUX_DUP (1 << 4) +#define SR_LED_MUX_SPEED (1 << 5) +#define SR_LED_MUX_LINK_ACTIVE (1 << 6) +#define SR_LED_MUX_LINK (1 << 7) + +/* Register Access Flags */ +#define SR_REQ_RD_REG (USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_DEVICE) +#define SR_REQ_WR_REG (USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_DEVICE) + +/* Multicast Filter Array size & Max Number */ +#define SR_MCAST_FILTER_SIZE 8 +#define SR_MAX_MCAST 64 + +/* IPG0/1/2 Default Value */ +#define SR9800_IPG0_DEFAULT 0x15 +#define SR9800_IPG1_DEFAULT 0x0c +#define SR9800_IPG2_DEFAULT 0x12 + +/* Medium Status Default Mode */ +#define SR9800_MEDIUM_DEFAULT \ + (SR_MEDIUM_FD | SR_MEDIUM_RFC | \ + SR_MEDIUM_TFC | SR_MEDIUM_PS | \ + SR_MEDIUM_AC | SR_MEDIUM_RE) + +/* RX Control Default Setting */ +#define SR_DEFAULT_RX_CTL \ + (SR_RX_CTL_SO | SR_RX_CTL_AB | SR_RX_CTL_RH1M) + +/* EEPROM Magic Number & EEPROM Size */ +#define SR_EEPROM_MAGIC 0xdeadbeef +#define SR9800_EEPROM_LEN 0xff + +/* SR9800 Driver Version and Driver Name */ +#define DRIVER_VERSION "11-Nov-2013" +#define DRIVER_NAME "CoreChips" +#define DRIVER_FLAG \ + (FLAG_ETHER | FLAG_FRAMING_AX | FLAG_LINK_INTR | FLAG_MULTI_PACKET) + +/* SR9800 BULKIN Buffer Size */ +#define SR9800_MAX_BULKIN_2K 0 +#define SR9800_MAX_BULKIN_4K 1 +#define SR9800_MAX_BULKIN_6K 2 +#define SR9800_MAX_BULKIN_8K 3 +#define SR9800_MAX_BULKIN_16K 4 +#define SR9800_MAX_BULKIN_20K 5 +#define SR9800_MAX_BULKIN_24K 6 +#define SR9800_MAX_BULKIN_32K 7 + +struct {unsigned short size, byte_cnt, threshold; } SR9800_BULKIN_SIZE[] = { + /* 2k */ + {2048, 0x8000, 0x8001}, + /* 4k */ + {4096, 0x8100, 0x8147}, + /* 6k */ + {6144, 0x8200, 0x81EB}, + /* 8k */ + {8192, 0x8300, 0x83D7}, + /* 16 */ + {16384, 0x8400, 0x851E}, + /* 20k */ + {20480, 0x8500, 0x8666}, + /* 24k */ + {24576, 0x8600, 0x87AE}, + /* 32k */ + {32768, 0x8700, 0x8A3D}, +}; + +/* This structure cannot exceed sizeof(unsigned long [5]) AKA 20 bytes */ +struct sr_data { + u8 multi_filter[SR_MCAST_FILTER_SIZE]; + u8 mac_addr[ETH_ALEN]; + u8 phymode; + u8 ledmode; + u8 eeprom_len; +}; + +struct sr9800_int_data { + __le16 res1; + u8 link; + __le16 res2; + u8 status; + __le16 res3; +} __packed; + +#endif /* _SR9800_H */ diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index 4671da755e7b..dd10d5817d2a 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -542,17 +542,19 @@ static inline void rx_process (struct usbnet *dev, struct sk_buff *skb) } // else network stack removes extra byte if we forced a short packet - if (skb->len) { - /* all data was already cloned from skb inside the driver */ - if (dev->driver_info->flags & FLAG_MULTI_PACKET) - dev_kfree_skb_any(skb); - else - usbnet_skb_return(dev, skb); + /* all data was already cloned from skb inside the driver */ + if (dev->driver_info->flags & FLAG_MULTI_PACKET) + goto done; + + if (skb->len < ETH_HLEN) { + dev->net->stats.rx_errors++; + dev->net->stats.rx_length_errors++; + netif_dbg(dev, rx_err, dev->net, "rx length %d\n", skb->len); + } else { + usbnet_skb_return(dev, skb); return; } - netif_dbg(dev, rx_err, dev->net, "drop\n"); - dev->net->stats.rx_errors++; done: skb_queue_tail(&dev->done, skb); } @@ -574,13 +576,6 @@ static void rx_complete (struct urb *urb) switch (urb_status) { /* success */ case 0: - if (skb->len < dev->net->hard_header_len) { - state = rx_cleanup; - dev->net->stats.rx_errors++; - dev->net->stats.rx_length_errors++; - netif_dbg(dev, rx_err, dev->net, - "rx length %d\n", skb->len); - } break; /* stalls need manual reset. this is rare ... except that diff --git a/drivers/net/veth.c b/drivers/net/veth.c index 2ec2041b62d4..3aca92e80e1e 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -14,6 +14,7 @@ #include <linux/etherdevice.h> #include <linux/u64_stats_sync.h> +#include <net/rtnetlink.h> #include <net/dst.h> #include <net/xfrm.h> #include <linux/veth.h> @@ -235,18 +236,9 @@ static int veth_change_mtu(struct net_device *dev, int new_mtu) static int veth_dev_init(struct net_device *dev) { - int i; - - dev->vstats = alloc_percpu(struct pcpu_vstats); + dev->vstats = netdev_alloc_pcpu_stats(struct pcpu_vstats); if (!dev->vstats) return -ENOMEM; - - for_each_possible_cpu(i) { - struct pcpu_vstats *veth_stats; - veth_stats = per_cpu_ptr(dev->vstats, i); - u64_stats_init(&veth_stats->syncp); - } - return 0; } @@ -285,7 +277,8 @@ static void veth_setup(struct net_device *dev) dev->ethtool_ops = &veth_ethtool_ops; dev->features |= NETIF_F_LLTX; dev->features |= VETH_FEATURES; - dev->vlan_features = dev->features; + dev->vlan_features = dev->features & + ~(NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX); dev->destructor = veth_dev_free; dev->hw_features = VETH_FEATURES; @@ -332,10 +325,9 @@ static int veth_newlink(struct net *src_net, struct net_device *dev, nla_peer = data[VETH_INFO_PEER]; ifmp = nla_data(nla_peer); - err = nla_parse(peer_tb, IFLA_MAX, - nla_data(nla_peer) + sizeof(struct ifinfomsg), - nla_len(nla_peer) - sizeof(struct ifinfomsg), - ifla_policy); + err = rtnl_nla_parse_ifla(peer_tb, + nla_data(nla_peer) + sizeof(struct ifinfomsg), + nla_len(nla_peer) - sizeof(struct ifinfomsg)); if (err < 0) return err; diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index d75f8edf4fb3..5632a99cbbd2 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -1711,7 +1711,8 @@ static int virtnet_probe(struct virtio_device *vdev) /* If we can receive ANY GSO packets, we must allocate large ones. */ if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO4) || virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO6) || - virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_ECN)) + virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_ECN) || + virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_UFO)) vi->big_packets = true; if (virtio_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF)) diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c index 3be786faaaec..9275c8c423b1 100644 --- a/drivers/net/vmxnet3/vmxnet3_drv.c +++ b/drivers/net/vmxnet3/vmxnet3_drv.c @@ -2729,47 +2729,35 @@ vmxnet3_read_mac_addr(struct vmxnet3_adapter *adapter, u8 *mac) /* * Enable MSIx vectors. * Returns : - * 0 on successful enabling of required vectors, * VMXNET3_LINUX_MIN_MSIX_VECT when only minimum number of vectors required - * could be enabled. - * number of vectors which can be enabled otherwise (this number is smaller + * were enabled. + * number of vectors which were enabled otherwise (this number is greater * than VMXNET3_LINUX_MIN_MSIX_VECT) */ static int -vmxnet3_acquire_msix_vectors(struct vmxnet3_adapter *adapter, - int vectors) -{ - int err = 0, vector_threshold; - vector_threshold = VMXNET3_LINUX_MIN_MSIX_VECT; - - while (vectors >= vector_threshold) { - err = pci_enable_msix(adapter->pdev, adapter->intr.msix_entries, - vectors); - if (!err) { - adapter->intr.num_intrs = vectors; - return 0; - } else if (err < 0) { - dev_err(&adapter->netdev->dev, - "Failed to enable MSI-X, error: %d\n", err); - vectors = 0; - } else if (err < vector_threshold) { - break; - } else { - /* If fails to enable required number of MSI-x vectors - * try enabling minimum number of vectors required. - */ - dev_err(&adapter->netdev->dev, - "Failed to enable %d MSI-X, trying %d instead\n", - vectors, vector_threshold); - vectors = vector_threshold; - } +vmxnet3_acquire_msix_vectors(struct vmxnet3_adapter *adapter, int nvec) +{ + int ret = pci_enable_msix_range(adapter->pdev, + adapter->intr.msix_entries, nvec, nvec); + + if (ret == -ENOSPC && nvec > VMXNET3_LINUX_MIN_MSIX_VECT) { + dev_err(&adapter->netdev->dev, + "Failed to enable %d MSI-X, trying %d\n", + nvec, VMXNET3_LINUX_MIN_MSIX_VECT); + + ret = pci_enable_msix_range(adapter->pdev, + adapter->intr.msix_entries, + VMXNET3_LINUX_MIN_MSIX_VECT, + VMXNET3_LINUX_MIN_MSIX_VECT); } - dev_info(&adapter->pdev->dev, - "Number of MSI-X interrupts which can be allocated " - "is lower than min threshold required.\n"); - return err; + if (ret < 0) { + dev_err(&adapter->netdev->dev, + "Failed to enable MSI-X, error: %d\n", ret); + } + + return ret; } @@ -2796,56 +2784,50 @@ vmxnet3_alloc_intr_resources(struct vmxnet3_adapter *adapter) #ifdef CONFIG_PCI_MSI if (adapter->intr.type == VMXNET3_IT_MSIX) { - int vector, err = 0; - - adapter->intr.num_intrs = (adapter->share_intr == - VMXNET3_INTR_TXSHARE) ? 1 : - adapter->num_tx_queues; - adapter->intr.num_intrs += (adapter->share_intr == - VMXNET3_INTR_BUDDYSHARE) ? 0 : - adapter->num_rx_queues; - adapter->intr.num_intrs += 1; /* for link event */ - - adapter->intr.num_intrs = (adapter->intr.num_intrs > - VMXNET3_LINUX_MIN_MSIX_VECT - ? adapter->intr.num_intrs : - VMXNET3_LINUX_MIN_MSIX_VECT); - - for (vector = 0; vector < adapter->intr.num_intrs; vector++) - adapter->intr.msix_entries[vector].entry = vector; - - err = vmxnet3_acquire_msix_vectors(adapter, - adapter->intr.num_intrs); + int i, nvec; + + nvec = adapter->share_intr == VMXNET3_INTR_TXSHARE ? + 1 : adapter->num_tx_queues; + nvec += adapter->share_intr == VMXNET3_INTR_BUDDYSHARE ? + 0 : adapter->num_rx_queues; + nvec += 1; /* for link event */ + nvec = nvec > VMXNET3_LINUX_MIN_MSIX_VECT ? + nvec : VMXNET3_LINUX_MIN_MSIX_VECT; + + for (i = 0; i < nvec; i++) + adapter->intr.msix_entries[i].entry = i; + + nvec = vmxnet3_acquire_msix_vectors(adapter, nvec); + if (nvec < 0) + goto msix_err; + /* If we cannot allocate one MSIx vector per queue * then limit the number of rx queues to 1 */ - if (err == VMXNET3_LINUX_MIN_MSIX_VECT) { + if (nvec == VMXNET3_LINUX_MIN_MSIX_VECT) { if (adapter->share_intr != VMXNET3_INTR_BUDDYSHARE || adapter->num_rx_queues != 1) { adapter->share_intr = VMXNET3_INTR_TXSHARE; netdev_err(adapter->netdev, "Number of rx queues : 1\n"); adapter->num_rx_queues = 1; - adapter->intr.num_intrs = - VMXNET3_LINUX_MIN_MSIX_VECT; } - return; } - if (!err) - return; + adapter->intr.num_intrs = nvec; + return; + +msix_err: /* If we cannot allocate MSIx vectors use only one rx queue */ dev_info(&adapter->pdev->dev, "Failed to enable MSI-X, error %d. " - "Limiting #rx queues to 1, try MSI.\n", err); + "Limiting #rx queues to 1, try MSI.\n", nvec); adapter->intr.type = VMXNET3_IT_MSI; } if (adapter->intr.type == VMXNET3_IT_MSI) { - int err; - err = pci_enable_msi(adapter->pdev); - if (!err) { + if (!pci_enable_msi(adapter->pdev)) { adapter->num_rx_queues = 1; adapter->intr.num_intrs = 1; return; diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 026a313c2d2d..eb59b14d5ee0 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -469,7 +469,6 @@ static inline struct hlist_head *vxlan_fdb_head(struct vxlan_dev *vxlan, /* Look up Ethernet address in forwarding table */ static struct vxlan_fdb *__vxlan_find_mac(struct vxlan_dev *vxlan, const u8 *mac) - { struct hlist_head *head = vxlan_fdb_head(vxlan, mac); struct vxlan_fdb *f; @@ -596,10 +595,8 @@ static struct sk_buff **vxlan_gro_receive(struct sk_buff **head, struct sk_buff NAPI_GRO_CB(p)->same_flow = 0; continue; } - goto found; } -found: type = eh->h_proto; rcu_read_lock(); @@ -1135,7 +1132,6 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb) { struct vxlan_sock *vs; struct vxlanhdr *vxh; - __be16 port; /* Need Vxlan and inner Ethernet header to be present */ if (!pskb_may_pull(skb, VXLAN_HLEN)) @@ -1153,8 +1149,6 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb) if (iptunnel_pull_header(skb, VXLAN_HLEN, htons(ETH_P_TEB))) goto drop; - port = inet_sk(sk)->inet_sport; - vs = rcu_dereference_sk_user_data(sk); if (!vs) goto drop; @@ -1981,19 +1975,11 @@ static int vxlan_init(struct net_device *dev) struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_net *vn = net_generic(dev_net(dev), vxlan_net_id); struct vxlan_sock *vs; - int i; - dev->tstats = alloc_percpu(struct pcpu_sw_netstats); + dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); if (!dev->tstats) return -ENOMEM; - for_each_possible_cpu(i) { - struct pcpu_sw_netstats *vxlan_stats; - vxlan_stats = per_cpu_ptr(dev->tstats, i); - u64_stats_init(&vxlan_stats->syncp); - } - - spin_lock(&vn->sock_lock); vs = vxlan_find_sock(dev_net(dev), vxlan->dst_port); if (vs) { diff --git a/drivers/net/wan/dlci.c b/drivers/net/wan/dlci.c index 0d1c7592efa0..19f7cb2cdef3 100644 --- a/drivers/net/wan/dlci.c +++ b/drivers/net/wan/dlci.c @@ -71,12 +71,9 @@ static int dlci_header(struct sk_buff *skb, struct net_device *dev, const void *saddr, unsigned len) { struct frhdr hdr; - struct dlci_local *dlp; unsigned int hlen; char *dest; - dlp = netdev_priv(dev); - hdr.control = FRAD_I_UI; switch (type) { @@ -107,11 +104,9 @@ static int dlci_header(struct sk_buff *skb, struct net_device *dev, static void dlci_receive(struct sk_buff *skb, struct net_device *dev) { - struct dlci_local *dlp; struct frhdr *hdr; int process, header; - dlp = netdev_priv(dev); if (!pskb_may_pull(skb, sizeof(*hdr))) { netdev_notice(dev, "invalid data no header\n"); dev->stats.rx_errors++; diff --git a/drivers/net/wireless/ath/wil6210/pcie_bus.c b/drivers/net/wireless/ath/wil6210/pcie_bus.c index eeceab39cda2..e1c8cc4a4b92 100644 --- a/drivers/net/wireless/ath/wil6210/pcie_bus.c +++ b/drivers/net/wireless/ath/wil6210/pcie_bus.c @@ -41,30 +41,28 @@ static int wil_if_pcie_enable(struct wil6210_priv *wil) switch (use_msi) { case 3: case 1: + wil_dbg_misc(wil, "Setup %d MSI interrupts\n", use_msi); + break; case 0: + wil_dbg_misc(wil, "MSI interrupts disabled, use INTx\n"); break; default: - wil_err(wil, "Invalid use_msi=%d, default to 1\n", - use_msi); + wil_err(wil, "Invalid use_msi=%d, default to 1\n", use_msi); use_msi = 1; } - wil->n_msi = use_msi; - if (wil->n_msi) { - wil_dbg_misc(wil, "Setup %d MSI interrupts\n", use_msi); - rc = pci_enable_msi_block(pdev, wil->n_msi); - if (rc && (wil->n_msi == 3)) { - wil_err(wil, "3 MSI mode failed, try 1 MSI\n"); - wil->n_msi = 1; - rc = pci_enable_msi_block(pdev, wil->n_msi); - } - if (rc) { - wil_err(wil, "pci_enable_msi failed, use INTx\n"); - wil->n_msi = 0; - } - } else { - wil_dbg_misc(wil, "MSI interrupts disabled, use INTx\n"); + + if (use_msi == 3 && pci_enable_msi_range(pdev, 3, 3) < 0) { + wil_err(wil, "3 MSI mode failed, try 1 MSI\n"); + use_msi = 1; + } + + if (use_msi == 1 && pci_enable_msi(pdev)) { + wil_err(wil, "pci_enable_msi failed, use INTx\n"); + use_msi = 0; } + wil->n_msi = use_msi; + rc = wil6210_init_irq(wil, pdev->irq); if (rc) goto stop_master; diff --git a/drivers/net/wireless/mwifiex/main.c b/drivers/net/wireless/mwifiex/main.c index 5397ee0ad652..7b4502fefec3 100644 --- a/drivers/net/wireless/mwifiex/main.c +++ b/drivers/net/wireless/mwifiex/main.c @@ -748,7 +748,7 @@ static struct net_device_stats *mwifiex_get_stats(struct net_device *dev) static u16 mwifiex_netdev_select_wmm_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv) + void *accel_priv, select_queue_fallback_t fallback) { skb->priority = cfg80211_classify8021d(skb, NULL); return mwifiex_1d_to_wmm_queue[skb->priority]; diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h index 4c76bcb9a879..bef37be402b8 100644 --- a/drivers/net/xen-netback/common.h +++ b/drivers/net/xen-netback/common.h @@ -48,37 +48,19 @@ typedef unsigned int pending_ring_idx_t; #define INVALID_PENDING_RING_IDX (~0U) -/* For the head field in pending_tx_info: it is used to indicate - * whether this tx info is the head of one or more coalesced requests. - * - * When head != INVALID_PENDING_RING_IDX, it means the start of a new - * tx requests queue and the end of previous queue. - * - * An example sequence of head fields (I = INVALID_PENDING_RING_IDX): - * - * ...|0 I I I|5 I|9 I I I|... - * -->|<-INUSE---------------- - * - * After consuming the first slot(s) we have: - * - * ...|V V V V|5 I|9 I I I|... - * -----FREE->|<-INUSE-------- - * - * where V stands for "valid pending ring index". Any number other - * than INVALID_PENDING_RING_IDX is OK. These entries are considered - * free and can contain any number other than - * INVALID_PENDING_RING_IDX. In practice we use 0. - * - * The in use non-INVALID_PENDING_RING_IDX (say 0, 5 and 9 in the - * above example) number is the index into pending_tx_info and - * mmap_pages arrays. - */ struct pending_tx_info { - struct xen_netif_tx_request req; /* coalesced tx request */ - pending_ring_idx_t head; /* head != INVALID_PENDING_RING_IDX - * if it is head of one or more tx - * reqs - */ + struct xen_netif_tx_request req; /* tx request */ + /* Callback data for released SKBs. The callback is always + * xenvif_zerocopy_callback, desc contains the pending_idx, which is + * also an index in pending_tx_info array. It is initialized in + * xenvif_alloc and it never changes. + * skb_shinfo(skb)->destructor_arg points to the first mapped slot's + * callback_struct in this array of struct pending_tx_info's, then ctx + * to the next, or NULL if there is no more slot for this skb. + * ubuf_to_vif is a helper which finds the struct xenvif from a pointer + * to this field. + */ + struct ubuf_info callback_struct; }; #define XEN_NETIF_TX_RING_SIZE __CONST_RING_SIZE(xen_netif_tx, PAGE_SIZE) @@ -108,6 +90,15 @@ struct xenvif_rx_meta { */ #define MAX_GRANT_COPY_OPS (MAX_SKB_FRAGS * XEN_NETIF_RX_RING_SIZE) +#define NETBACK_INVALID_HANDLE -1 + +/* To avoid confusion, we define XEN_NETBK_LEGACY_SLOTS_MAX indicating + * the maximum slots a valid packet can use. Now this value is defined + * to be XEN_NETIF_NR_SLOTS_MIN, which is supposed to be supported by + * all backend. + */ +#define XEN_NETBK_LEGACY_SLOTS_MAX XEN_NETIF_NR_SLOTS_MIN + struct xenvif { /* Unique identifier for this interface. */ domid_t domid; @@ -126,13 +117,28 @@ struct xenvif { pending_ring_idx_t pending_cons; u16 pending_ring[MAX_PENDING_REQS]; struct pending_tx_info pending_tx_info[MAX_PENDING_REQS]; - - /* Coalescing tx requests before copying makes number of grant - * copy ops greater or equal to number of slots required. In - * worst case a tx request consumes 2 gnttab_copy. + grant_handle_t grant_tx_handle[MAX_PENDING_REQS]; + + struct gnttab_map_grant_ref tx_map_ops[MAX_PENDING_REQS]; + struct gnttab_unmap_grant_ref tx_unmap_ops[MAX_PENDING_REQS]; + /* passed to gnttab_[un]map_refs with pages under (un)mapping */ + struct page *pages_to_map[MAX_PENDING_REQS]; + struct page *pages_to_unmap[MAX_PENDING_REQS]; + + /* This prevents zerocopy callbacks to race over dealloc_ring */ + spinlock_t callback_lock; + /* This prevents dealloc thread and NAPI instance to race over response + * creation and pending_ring in xenvif_idx_release. In xenvif_tx_err + * it only protect response creation */ - struct gnttab_copy tx_copy_ops[2*MAX_PENDING_REQS]; - + spinlock_t response_lock; + pending_ring_idx_t dealloc_prod; + pending_ring_idx_t dealloc_cons; + u16 dealloc_ring[MAX_PENDING_REQS]; + struct task_struct *dealloc_task; + wait_queue_head_t dealloc_wq; + struct timer_list dealloc_delay; + bool dealloc_delay_timed_out; /* Use kthread for guest RX */ struct task_struct *task; @@ -143,11 +149,10 @@ struct xenvif { char rx_irq_name[IFNAMSIZ+4]; /* DEVNAME-rx */ struct xen_netif_rx_back_ring rx; struct sk_buff_head rx_queue; - bool rx_queue_stopped; - /* Set when the RX interrupt is triggered by the frontend. - * The worker thread may need to wake the queue. - */ - bool rx_event; + RING_IDX rx_last_skb_slots; + bool rx_queue_purge; + + struct timer_list wake_queue; /* This array is allocated seperately as it is large */ struct gnttab_copy *grant_copy_op; @@ -179,6 +184,10 @@ struct xenvif { /* Statistics */ unsigned long rx_gso_checksum_fixup; + unsigned long tx_zerocopy_sent; + unsigned long tx_zerocopy_success; + unsigned long tx_zerocopy_fail; + unsigned long tx_frag_overflow; /* Miscellaneous private stuff. */ struct net_device *dev; @@ -220,9 +229,11 @@ void xenvif_carrier_off(struct xenvif *vif); int xenvif_tx_action(struct xenvif *vif, int budget); -int xenvif_kthread(void *data); +int xenvif_kthread_guest_rx(void *data); void xenvif_kick_thread(struct xenvif *vif); +int xenvif_dealloc_kthread(void *data); + /* Determine whether the needed number of slots (req) are available, * and set req_event if not. */ @@ -230,6 +241,30 @@ bool xenvif_rx_ring_slots_available(struct xenvif *vif, int needed); void xenvif_stop_queue(struct xenvif *vif); +/* Callback from stack when TX packet can be released */ +void xenvif_zerocopy_callback(struct ubuf_info *ubuf, bool zerocopy_success); + +/* Unmap a pending page and release it back to the guest */ +void xenvif_idx_unmap(struct xenvif *vif, u16 pending_idx); + +static inline pending_ring_idx_t nr_pending_reqs(struct xenvif *vif) +{ + return MAX_PENDING_REQS - + vif->pending_prod + vif->pending_cons; +} + +static inline bool xenvif_tx_pending_slots_available(struct xenvif *vif) +{ + return nr_pending_reqs(vif) + XEN_NETBK_LEGACY_SLOTS_MAX + < MAX_PENDING_REQS; +} + +/* Callback from stack when TX packet can be released */ +void xenvif_zerocopy_callback(struct ubuf_info *ubuf, bool zerocopy_success); + extern bool separate_tx_rx_irq; +extern unsigned int rx_drain_timeout_msecs; +extern unsigned int rx_drain_timeout_jiffies; + #endif /* __XEN_NETBACK__COMMON_H__ */ diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c index b9de31ea7fc4..83a71ac5b93a 100644 --- a/drivers/net/xen-netback/interface.c +++ b/drivers/net/xen-netback/interface.c @@ -38,6 +38,7 @@ #include <xen/events.h> #include <asm/xen/hypercall.h> +#include <xen/balloon.h> #define XENVIF_QUEUE_LENGTH 32 #define XENVIF_NAPI_WEIGHT 64 @@ -87,7 +88,8 @@ static int xenvif_poll(struct napi_struct *napi, int budget) local_irq_save(flags); RING_FINAL_CHECK_FOR_REQUESTS(&vif->tx, more_to_do); - if (!more_to_do) + if (!(more_to_do && + xenvif_tx_pending_slots_available(vif))) __napi_complete(napi); local_irq_restore(flags); @@ -100,7 +102,6 @@ static irqreturn_t xenvif_rx_interrupt(int irq, void *dev_id) { struct xenvif *vif = dev_id; - vif->rx_event = true; xenvif_kick_thread(vif); return IRQ_HANDLED; @@ -114,6 +115,18 @@ static irqreturn_t xenvif_interrupt(int irq, void *dev_id) return IRQ_HANDLED; } +static void xenvif_wake_queue(unsigned long data) +{ + struct xenvif *vif = (struct xenvif *)data; + + if (netif_queue_stopped(vif->dev)) { + netdev_err(vif->dev, "draining TX queue\n"); + vif->rx_queue_purge = true; + xenvif_kick_thread(vif); + netif_wake_queue(vif->dev); + } +} + static int xenvif_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct xenvif *vif = netdev_priv(dev); @@ -122,7 +135,9 @@ static int xenvif_start_xmit(struct sk_buff *skb, struct net_device *dev) BUG_ON(skb->dev != dev); /* Drop the packet if vif is not ready */ - if (vif->task == NULL || !xenvif_schedulable(vif)) + if (vif->task == NULL || + vif->dealloc_task == NULL || + !xenvif_schedulable(vif)) goto drop; /* At best we'll need one slot for the header and one for each @@ -141,8 +156,13 @@ static int xenvif_start_xmit(struct sk_buff *skb, struct net_device *dev) * then turn off the queue to give the ring a chance to * drain. */ - if (!xenvif_rx_ring_slots_available(vif, min_slots_needed)) + if (!xenvif_rx_ring_slots_available(vif, min_slots_needed)) { + vif->wake_queue.function = xenvif_wake_queue; + vif->wake_queue.data = (unsigned long)vif; xenvif_stop_queue(vif); + mod_timer(&vif->wake_queue, + jiffies + rx_drain_timeout_jiffies); + } skb_queue_tail(&vif->rx_queue, skb); xenvif_kick_thread(vif); @@ -235,6 +255,28 @@ static const struct xenvif_stat { "rx_gso_checksum_fixup", offsetof(struct xenvif, rx_gso_checksum_fixup) }, + /* If (sent != success + fail), there are probably packets never + * freed up properly! + */ + { + "tx_zerocopy_sent", + offsetof(struct xenvif, tx_zerocopy_sent), + }, + { + "tx_zerocopy_success", + offsetof(struct xenvif, tx_zerocopy_success), + }, + { + "tx_zerocopy_fail", + offsetof(struct xenvif, tx_zerocopy_fail) + }, + /* Number of packets exceeding MAX_SKB_FRAG slots. You should use + * a guest with the same MAX_SKB_FRAG + */ + { + "tx_frag_overflow", + offsetof(struct xenvif, tx_frag_overflow) + }, }; static int xenvif_get_sset_count(struct net_device *dev, int string_set) @@ -328,6 +370,8 @@ struct xenvif *xenvif_alloc(struct device *parent, domid_t domid, init_timer(&vif->credit_timeout); vif->credit_window_start = get_jiffies_64(); + init_timer(&vif->wake_queue); + dev->netdev_ops = &xenvif_netdev_ops; dev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | @@ -344,8 +388,27 @@ struct xenvif *xenvif_alloc(struct device *parent, domid_t domid, vif->pending_prod = MAX_PENDING_REQS; for (i = 0; i < MAX_PENDING_REQS; i++) vif->pending_ring[i] = i; - for (i = 0; i < MAX_PENDING_REQS; i++) - vif->mmap_pages[i] = NULL; + spin_lock_init(&vif->callback_lock); + spin_lock_init(&vif->response_lock); + /* If ballooning is disabled, this will consume real memory, so you + * better enable it. The long term solution would be to use just a + * bunch of valid page descriptors, without dependency on ballooning + */ + err = alloc_xenballooned_pages(MAX_PENDING_REQS, + vif->mmap_pages, + false); + if (err) { + netdev_err(dev, "Could not reserve mmap_pages\n"); + return ERR_PTR(-ENOMEM); + } + for (i = 0; i < MAX_PENDING_REQS; i++) { + vif->pending_tx_info[i].callback_struct = (struct ubuf_info) + { .callback = xenvif_zerocopy_callback, + .ctx = NULL, + .desc = i }; + vif->grant_tx_handle[i] = NETBACK_INVALID_HANDLE; + } + init_timer(&vif->dealloc_delay); /* * Initialise a dummy MAC address. We choose the numerically @@ -383,12 +446,14 @@ int xenvif_connect(struct xenvif *vif, unsigned long tx_ring_ref, BUG_ON(vif->tx_irq); BUG_ON(vif->task); + BUG_ON(vif->dealloc_task); err = xenvif_map_frontend_rings(vif, tx_ring_ref, rx_ring_ref); if (err < 0) goto err; init_waitqueue_head(&vif->wq); + init_waitqueue_head(&vif->dealloc_wq); if (tx_evtchn == rx_evtchn) { /* feature-split-event-channels == 0 */ @@ -422,8 +487,8 @@ int xenvif_connect(struct xenvif *vif, unsigned long tx_ring_ref, disable_irq(vif->rx_irq); } - task = kthread_create(xenvif_kthread, - (void *)vif, "%s", vif->dev->name); + task = kthread_create(xenvif_kthread_guest_rx, + (void *)vif, "%s-guest-rx", vif->dev->name); if (IS_ERR(task)) { pr_warn("Could not allocate kthread for %s\n", vif->dev->name); err = PTR_ERR(task); @@ -432,6 +497,16 @@ int xenvif_connect(struct xenvif *vif, unsigned long tx_ring_ref, vif->task = task; + task = kthread_create(xenvif_dealloc_kthread, + (void *)vif, "%s-dealloc", vif->dev->name); + if (IS_ERR(task)) { + pr_warn("Could not allocate kthread for %s\n", vif->dev->name); + err = PTR_ERR(task); + goto err_rx_unbind; + } + + vif->dealloc_task = task; + rtnl_lock(); if (!vif->can_sg && vif->dev->mtu > ETH_DATA_LEN) dev_set_mtu(vif->dev, ETH_DATA_LEN); @@ -442,6 +517,7 @@ int xenvif_connect(struct xenvif *vif, unsigned long tx_ring_ref, rtnl_unlock(); wake_up_process(vif->task); + wake_up_process(vif->dealloc_task); return 0; @@ -475,10 +551,17 @@ void xenvif_disconnect(struct xenvif *vif) xenvif_carrier_off(vif); if (vif->task) { + del_timer_sync(&vif->wake_queue); kthread_stop(vif->task); vif->task = NULL; } + if (vif->dealloc_task) { + del_timer_sync(&vif->dealloc_delay); + kthread_stop(vif->dealloc_task); + vif->dealloc_task = NULL; + } + if (vif->tx_irq) { if (vif->tx_irq == vif->rx_irq) unbind_from_irqhandler(vif->tx_irq, vif); @@ -494,6 +577,36 @@ void xenvif_disconnect(struct xenvif *vif) void xenvif_free(struct xenvif *vif) { + int i, unmap_timeout = 0; + /* Here we want to avoid timeout messages if an skb can be legitimatly + * stucked somewhere else. Realisticly this could be an another vif's + * internal or QDisc queue. That another vif also has this + * rx_drain_timeout_msecs timeout, but the timer only ditches the + * internal queue. After that, the QDisc queue can put in worst case + * XEN_NETIF_RX_RING_SIZE / MAX_SKB_FRAGS skbs into that another vif's + * internal queue, so we need several rounds of such timeouts until we + * can be sure that no another vif should have skb's from us. We are + * not sending more skb's, so newly stucked packets are not interesting + * for us here. + */ + unsigned int worst_case_skb_lifetime = (rx_drain_timeout_msecs/1000) * + DIV_ROUND_UP(XENVIF_QUEUE_LENGTH, (XEN_NETIF_RX_RING_SIZE / MAX_SKB_FRAGS)); + + for (i = 0; i < MAX_PENDING_REQS; ++i) { + if (vif->grant_tx_handle[i] != NETBACK_INVALID_HANDLE) { + unmap_timeout++; + schedule_timeout(msecs_to_jiffies(1000)); + if (unmap_timeout > worst_case_skb_lifetime && + net_ratelimit()) + netdev_err(vif->dev, + "Page still granted! Index: %x\n", + i); + i = -1; + } + } + + free_xenballooned_pages(MAX_PENDING_REQS, vif->mmap_pages); + netif_napi_del(&vif->napi); unregister_netdev(vif->dev); diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index 6b62c3eb8e18..bc943205a691 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -37,6 +37,7 @@ #include <linux/kthread.h> #include <linux/if_vlan.h> #include <linux/udp.h> +#include <linux/highmem.h> #include <net/tcp.h> @@ -54,6 +55,13 @@ bool separate_tx_rx_irq = 1; module_param(separate_tx_rx_irq, bool, 0644); +/* When guest ring is filled up, qdisc queues the packets for us, but we have + * to timeout them, otherwise other guests' packets can get stucked there + */ +unsigned int rx_drain_timeout_msecs = 10000; +module_param(rx_drain_timeout_msecs, uint, 0444); +unsigned int rx_drain_timeout_jiffies; + /* * This is the maximum slots a skb can have. If a guest sends a skb * which exceeds this limit it is considered malicious. @@ -62,24 +70,6 @@ module_param(separate_tx_rx_irq, bool, 0644); static unsigned int fatal_skb_slots = FATAL_SKB_SLOTS_DEFAULT; module_param(fatal_skb_slots, uint, 0444); -/* - * To avoid confusion, we define XEN_NETBK_LEGACY_SLOTS_MAX indicating - * the maximum slots a valid packet can use. Now this value is defined - * to be XEN_NETIF_NR_SLOTS_MIN, which is supposed to be supported by - * all backend. - */ -#define XEN_NETBK_LEGACY_SLOTS_MAX XEN_NETIF_NR_SLOTS_MIN - -/* - * If head != INVALID_PENDING_RING_IDX, it means this tx request is head of - * one or more merged tx requests, otherwise it is the continuation of - * previous tx request. - */ -static inline int pending_tx_is_head(struct xenvif *vif, RING_IDX idx) -{ - return vif->pending_tx_info[idx].head != INVALID_PENDING_RING_IDX; -} - static void xenvif_idx_release(struct xenvif *vif, u16 pending_idx, u8 status); @@ -109,6 +99,18 @@ static inline unsigned long idx_to_kaddr(struct xenvif *vif, return (unsigned long)pfn_to_kaddr(idx_to_pfn(vif, idx)); } +/* Find the containing VIF's structure from a pointer in pending_tx_info array + */ +static inline struct xenvif* ubuf_to_vif(struct ubuf_info *ubuf) +{ + u16 pending_idx = ubuf->desc; + struct pending_tx_info *temp = + container_of(ubuf, struct pending_tx_info, callback_struct); + return container_of(temp - pending_idx, + struct xenvif, + pending_tx_info[0]); +} + /* This is a miniumum size for the linear area to avoid lots of * calls to __pskb_pull_tail() as we set up checksum offsets. The * value 128 was chosen as it covers all IPv4 and most likely @@ -131,10 +133,9 @@ static inline pending_ring_idx_t pending_index(unsigned i) return i & (MAX_PENDING_REQS-1); } -static inline pending_ring_idx_t nr_pending_reqs(struct xenvif *vif) +static inline pending_ring_idx_t nr_free_slots(struct xen_netif_tx_back_ring *ring) { - return MAX_PENDING_REQS - - vif->pending_prod + vif->pending_cons; + return ring->nr_ents - (ring->sring->req_prod - ring->rsp_prod_pvt); } bool xenvif_rx_ring_slots_available(struct xenvif *vif, int needed) @@ -235,7 +236,9 @@ static struct xenvif_rx_meta *get_next_rx_buffer(struct xenvif *vif, static void xenvif_gop_frag_copy(struct xenvif *vif, struct sk_buff *skb, struct netrx_pending_operations *npo, struct page *page, unsigned long size, - unsigned long offset, int *head) + unsigned long offset, int *head, + struct xenvif *foreign_vif, + grant_ref_t foreign_gref) { struct gnttab_copy *copy_gop; struct xenvif_rx_meta *meta; @@ -277,8 +280,15 @@ static void xenvif_gop_frag_copy(struct xenvif *vif, struct sk_buff *skb, copy_gop->flags = GNTCOPY_dest_gref; copy_gop->len = bytes; - copy_gop->source.domid = DOMID_SELF; - copy_gop->source.u.gmfn = virt_to_mfn(page_address(page)); + if (foreign_vif) { + copy_gop->source.domid = foreign_vif->domid; + copy_gop->source.u.ref = foreign_gref; + copy_gop->flags |= GNTCOPY_source_gref; + } else { + copy_gop->source.domid = DOMID_SELF; + copy_gop->source.u.gmfn = + virt_to_mfn(page_address(page)); + } copy_gop->source.offset = offset; copy_gop->dest.domid = vif->domid; @@ -339,6 +349,9 @@ static int xenvif_gop_skb(struct sk_buff *skb, int old_meta_prod; int gso_type; int gso_size; + struct ubuf_info *ubuf = skb_shinfo(skb)->destructor_arg; + grant_ref_t foreign_grefs[MAX_SKB_FRAGS]; + struct xenvif *foreign_vif = NULL; old_meta_prod = npo->meta_prod; @@ -379,6 +392,19 @@ static int xenvif_gop_skb(struct sk_buff *skb, npo->copy_off = 0; npo->copy_gref = req->gref; + if ((skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) && + (ubuf->callback == &xenvif_zerocopy_callback)) { + int i = 0; + foreign_vif = ubuf_to_vif(ubuf); + + do { + u16 pending_idx = ubuf->desc; + foreign_grefs[i++] = + foreign_vif->pending_tx_info[pending_idx].req.gref; + ubuf = (struct ubuf_info *) ubuf->ctx; + } while (ubuf); + } + data = skb->data; while (data < skb_tail_pointer(skb)) { unsigned int offset = offset_in_page(data); @@ -388,7 +414,9 @@ static int xenvif_gop_skb(struct sk_buff *skb, len = skb_tail_pointer(skb) - data; xenvif_gop_frag_copy(vif, skb, npo, - virt_to_page(data), len, offset, &head); + virt_to_page(data), len, offset, &head, + NULL, + 0); data += len; } @@ -397,7 +425,9 @@ static int xenvif_gop_skb(struct sk_buff *skb, skb_frag_page(&skb_shinfo(skb)->frags[i]), skb_frag_size(&skb_shinfo(skb)->frags[i]), skb_shinfo(skb)->frags[i].page_offset, - &head); + &head, + foreign_vif, + foreign_grefs[i]); } return npo->meta_prod - old_meta_prod; @@ -455,10 +485,12 @@ static void xenvif_add_frag_responses(struct xenvif *vif, int status, } } -struct skb_cb_overlay { +struct xenvif_rx_cb { int meta_slots_used; }; +#define XENVIF_RX_CB(skb) ((struct xenvif_rx_cb *)(skb)->cb) + void xenvif_kick_thread(struct xenvif *vif) { wake_up(&vif->wq); @@ -474,9 +506,7 @@ static void xenvif_rx_action(struct xenvif *vif) LIST_HEAD(notify); int ret; unsigned long offset; - struct skb_cb_overlay *sco; bool need_to_notify = false; - bool ring_full = false; struct netrx_pending_operations npo = { .copy = vif->grant_copy_op, @@ -486,7 +516,7 @@ static void xenvif_rx_action(struct xenvif *vif) skb_queue_head_init(&rxq); while ((skb = skb_dequeue(&vif->rx_queue)) != NULL) { - int max_slots_needed; + RING_IDX max_slots_needed; int i; /* We need a cheap worse case estimate for the number of @@ -509,21 +539,19 @@ static void xenvif_rx_action(struct xenvif *vif) if (!xenvif_rx_ring_slots_available(vif, max_slots_needed)) { skb_queue_head(&vif->rx_queue, skb); need_to_notify = true; - ring_full = true; + vif->rx_last_skb_slots = max_slots_needed; break; - } + } else + vif->rx_last_skb_slots = 0; - sco = (struct skb_cb_overlay *)skb->cb; - sco->meta_slots_used = xenvif_gop_skb(skb, &npo); - BUG_ON(sco->meta_slots_used > max_slots_needed); + XENVIF_RX_CB(skb)->meta_slots_used = xenvif_gop_skb(skb, &npo); + BUG_ON(XENVIF_RX_CB(skb)->meta_slots_used > max_slots_needed); __skb_queue_tail(&rxq, skb); } BUG_ON(npo.meta_prod > ARRAY_SIZE(vif->meta)); - vif->rx_queue_stopped = !npo.copy_prod && ring_full; - if (!npo.copy_prod) goto done; @@ -531,7 +559,6 @@ static void xenvif_rx_action(struct xenvif *vif) gnttab_batch_copy(vif->grant_copy_op, npo.copy_prod); while ((skb = __skb_dequeue(&rxq)) != NULL) { - sco = (struct skb_cb_overlay *)skb->cb; if ((1 << vif->meta[npo.meta_cons].gso_type) & vif->gso_prefix_mask) { @@ -542,19 +569,21 @@ static void xenvif_rx_action(struct xenvif *vif) resp->offset = vif->meta[npo.meta_cons].gso_size; resp->id = vif->meta[npo.meta_cons].id; - resp->status = sco->meta_slots_used; + resp->status = XENVIF_RX_CB(skb)->meta_slots_used; npo.meta_cons++; - sco->meta_slots_used--; + XENVIF_RX_CB(skb)->meta_slots_used--; } vif->dev->stats.tx_bytes += skb->len; vif->dev->stats.tx_packets++; - status = xenvif_check_gop(vif, sco->meta_slots_used, &npo); + status = xenvif_check_gop(vif, + XENVIF_RX_CB(skb)->meta_slots_used, + &npo); - if (sco->meta_slots_used == 1) + if (XENVIF_RX_CB(skb)->meta_slots_used == 1) flags = 0; else flags = XEN_NETRXF_more_data; @@ -591,13 +620,13 @@ static void xenvif_rx_action(struct xenvif *vif) xenvif_add_frag_responses(vif, status, vif->meta + npo.meta_cons + 1, - sco->meta_slots_used); + XENVIF_RX_CB(skb)->meta_slots_used); RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&vif->rx, ret); need_to_notify |= !!ret; - npo.meta_cons += sco->meta_slots_used; + npo.meta_cons += XENVIF_RX_CB(skb)->meta_slots_used; dev_kfree_skb(skb); } @@ -647,9 +676,12 @@ static void xenvif_tx_err(struct xenvif *vif, struct xen_netif_tx_request *txp, RING_IDX end) { RING_IDX cons = vif->tx.req_cons; + unsigned long flags; do { + spin_lock_irqsave(&vif->response_lock, flags); make_tx_response(vif, txp, XEN_NETIF_RSP_ERROR); + spin_unlock_irqrestore(&vif->response_lock, flags); if (cons == end) break; txp = RING_GET_REQUEST(&vif->tx, cons++); @@ -761,180 +793,168 @@ static int xenvif_count_requests(struct xenvif *vif, return slots; } -static struct page *xenvif_alloc_page(struct xenvif *vif, - u16 pending_idx) + +struct xenvif_tx_cb { + u16 pending_idx; +}; + +#define XENVIF_TX_CB(skb) ((struct xenvif_tx_cb *)(skb)->cb) + +static inline void xenvif_tx_create_gop(struct xenvif *vif, + u16 pending_idx, + struct xen_netif_tx_request *txp, + struct gnttab_map_grant_ref *gop) { - struct page *page; + vif->pages_to_map[gop-vif->tx_map_ops] = vif->mmap_pages[pending_idx]; + gnttab_set_map_op(gop, idx_to_kaddr(vif, pending_idx), + GNTMAP_host_map | GNTMAP_readonly, + txp->gref, vif->domid); + + memcpy(&vif->pending_tx_info[pending_idx].req, txp, + sizeof(*txp)); +} - page = alloc_page(GFP_ATOMIC|__GFP_COLD); - if (!page) +static inline struct sk_buff *xenvif_alloc_skb(unsigned int size) +{ + struct sk_buff *skb = + alloc_skb(size + NET_SKB_PAD + NET_IP_ALIGN, + GFP_ATOMIC | __GFP_NOWARN); + if (unlikely(skb == NULL)) return NULL; - vif->mmap_pages[pending_idx] = page; - return page; + /* Packets passed to netif_rx() must have some headroom. */ + skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN); + + /* Initialize it here to avoid later surprises */ + skb_shinfo(skb)->destructor_arg = NULL; + + return skb; } -static struct gnttab_copy *xenvif_get_requests(struct xenvif *vif, - struct sk_buff *skb, - struct xen_netif_tx_request *txp, - struct gnttab_copy *gop) +static struct gnttab_map_grant_ref *xenvif_get_requests(struct xenvif *vif, + struct sk_buff *skb, + struct xen_netif_tx_request *txp, + struct gnttab_map_grant_ref *gop) { struct skb_shared_info *shinfo = skb_shinfo(skb); skb_frag_t *frags = shinfo->frags; - u16 pending_idx = *((u16 *)skb->data); - u16 head_idx = 0; - int slot, start; - struct page *page; - pending_ring_idx_t index, start_idx = 0; - uint16_t dst_offset; - unsigned int nr_slots; - struct pending_tx_info *first = NULL; + u16 pending_idx = XENVIF_TX_CB(skb)->pending_idx; + int start; + pending_ring_idx_t index; + unsigned int nr_slots, frag_overflow = 0; /* At this point shinfo->nr_frags is in fact the number of * slots, which can be as large as XEN_NETBK_LEGACY_SLOTS_MAX. */ + if (shinfo->nr_frags > MAX_SKB_FRAGS) { + frag_overflow = shinfo->nr_frags - MAX_SKB_FRAGS; + BUG_ON(frag_overflow > MAX_SKB_FRAGS); + shinfo->nr_frags = MAX_SKB_FRAGS; + } nr_slots = shinfo->nr_frags; /* Skip first skb fragment if it is on same page as header fragment. */ start = (frag_get_pending_idx(&shinfo->frags[0]) == pending_idx); - /* Coalesce tx requests, at this point the packet passed in - * should be <= 64K. Any packets larger than 64K have been - * handled in xenvif_count_requests(). - */ - for (shinfo->nr_frags = slot = start; slot < nr_slots; - shinfo->nr_frags++) { - struct pending_tx_info *pending_tx_info = - vif->pending_tx_info; + for (shinfo->nr_frags = start; shinfo->nr_frags < nr_slots; + shinfo->nr_frags++, txp++, gop++) { + index = pending_index(vif->pending_cons++); + pending_idx = vif->pending_ring[index]; + xenvif_tx_create_gop(vif, pending_idx, txp, gop); + frag_set_pending_idx(&frags[shinfo->nr_frags], pending_idx); + } - page = alloc_page(GFP_ATOMIC|__GFP_COLD); - if (!page) - goto err; - - dst_offset = 0; - first = NULL; - while (dst_offset < PAGE_SIZE && slot < nr_slots) { - gop->flags = GNTCOPY_source_gref; - - gop->source.u.ref = txp->gref; - gop->source.domid = vif->domid; - gop->source.offset = txp->offset; - - gop->dest.domid = DOMID_SELF; - - gop->dest.offset = dst_offset; - gop->dest.u.gmfn = virt_to_mfn(page_address(page)); - - if (dst_offset + txp->size > PAGE_SIZE) { - /* This page can only merge a portion - * of tx request. Do not increment any - * pointer / counter here. The txp - * will be dealt with in future - * rounds, eventually hitting the - * `else` branch. - */ - gop->len = PAGE_SIZE - dst_offset; - txp->offset += gop->len; - txp->size -= gop->len; - dst_offset += gop->len; /* quit loop */ - } else { - /* This tx request can be merged in the page */ - gop->len = txp->size; - dst_offset += gop->len; - - index = pending_index(vif->pending_cons++); - - pending_idx = vif->pending_ring[index]; - - memcpy(&pending_tx_info[pending_idx].req, txp, - sizeof(*txp)); - - /* Poison these fields, corresponding - * fields for head tx req will be set - * to correct values after the loop. - */ - vif->mmap_pages[pending_idx] = (void *)(~0UL); - pending_tx_info[pending_idx].head = - INVALID_PENDING_RING_IDX; - - if (!first) { - first = &pending_tx_info[pending_idx]; - start_idx = index; - head_idx = pending_idx; - } - - txp++; - slot++; - } + if (frag_overflow) { + struct sk_buff *nskb = xenvif_alloc_skb(0); + if (unlikely(nskb == NULL)) { + if (net_ratelimit()) + netdev_err(vif->dev, + "Can't allocate the frag_list skb.\n"); + return NULL; + } + + shinfo = skb_shinfo(nskb); + frags = shinfo->frags; - gop++; + for (shinfo->nr_frags = 0; shinfo->nr_frags < frag_overflow; + shinfo->nr_frags++, txp++, gop++) { + index = pending_index(vif->pending_cons++); + pending_idx = vif->pending_ring[index]; + xenvif_tx_create_gop(vif, pending_idx, txp, gop); + frag_set_pending_idx(&frags[shinfo->nr_frags], + pending_idx); } - first->req.offset = 0; - first->req.size = dst_offset; - first->head = start_idx; - vif->mmap_pages[head_idx] = page; - frag_set_pending_idx(&frags[shinfo->nr_frags], head_idx); + skb_shinfo(skb)->frag_list = nskb; } - BUG_ON(shinfo->nr_frags > MAX_SKB_FRAGS); - return gop; -err: - /* Unwind, freeing all pages and sending error responses. */ - while (shinfo->nr_frags-- > start) { - xenvif_idx_release(vif, - frag_get_pending_idx(&frags[shinfo->nr_frags]), - XEN_NETIF_RSP_ERROR); +} + +static inline void xenvif_grant_handle_set(struct xenvif *vif, + u16 pending_idx, + grant_handle_t handle) +{ + if (unlikely(vif->grant_tx_handle[pending_idx] != + NETBACK_INVALID_HANDLE)) { + netdev_err(vif->dev, + "Trying to overwrite active handle! pending_idx: %x\n", + pending_idx); + BUG(); } - /* The head too, if necessary. */ - if (start) - xenvif_idx_release(vif, pending_idx, XEN_NETIF_RSP_ERROR); + vif->grant_tx_handle[pending_idx] = handle; +} - return NULL; +static inline void xenvif_grant_handle_reset(struct xenvif *vif, + u16 pending_idx) +{ + if (unlikely(vif->grant_tx_handle[pending_idx] == + NETBACK_INVALID_HANDLE)) { + netdev_err(vif->dev, + "Trying to unmap invalid handle! pending_idx: %x\n", + pending_idx); + BUG(); + } + vif->grant_tx_handle[pending_idx] = NETBACK_INVALID_HANDLE; } static int xenvif_tx_check_gop(struct xenvif *vif, struct sk_buff *skb, - struct gnttab_copy **gopp) + struct gnttab_map_grant_ref **gopp) { - struct gnttab_copy *gop = *gopp; - u16 pending_idx = *((u16 *)skb->data); + struct gnttab_map_grant_ref *gop = *gopp; + u16 pending_idx = XENVIF_TX_CB(skb)->pending_idx; struct skb_shared_info *shinfo = skb_shinfo(skb); struct pending_tx_info *tx_info; int nr_frags = shinfo->nr_frags; int i, err, start; - u16 peek; /* peek into next tx request */ + struct sk_buff *first_skb = NULL; /* Check status of header. */ err = gop->status; if (unlikely(err)) xenvif_idx_release(vif, pending_idx, XEN_NETIF_RSP_ERROR); + else + xenvif_grant_handle_set(vif, pending_idx , gop->handle); /* Skip first skb fragment if it is on same page as header fragment. */ start = (frag_get_pending_idx(&shinfo->frags[0]) == pending_idx); +check_frags: for (i = start; i < nr_frags; i++) { int j, newerr; - pending_ring_idx_t head; pending_idx = frag_get_pending_idx(&shinfo->frags[i]); tx_info = &vif->pending_tx_info[pending_idx]; - head = tx_info->head; /* Check error status: if okay then remember grant handle. */ - do { - newerr = (++gop)->status; - if (newerr) - break; - peek = vif->pending_ring[pending_index(++head)]; - } while (!pending_tx_is_head(vif, peek)); + newerr = (++gop)->status; if (likely(!newerr)) { + xenvif_grant_handle_set(vif, pending_idx , gop->handle); /* Had a previous error? Invalidate this fragment. */ if (unlikely(err)) - xenvif_idx_release(vif, pending_idx, - XEN_NETIF_RSP_OKAY); + xenvif_idx_unmap(vif, pending_idx); continue; } @@ -944,20 +964,45 @@ static int xenvif_tx_check_gop(struct xenvif *vif, /* Not the first error? Preceding frags already invalidated. */ if (err) continue; - /* First error: invalidate header and preceding fragments. */ - pending_idx = *((u16 *)skb->data); - xenvif_idx_release(vif, pending_idx, XEN_NETIF_RSP_OKAY); + if (!first_skb) + pending_idx = XENVIF_TX_CB(skb)->pending_idx; + else + pending_idx = XENVIF_TX_CB(skb)->pending_idx; + xenvif_idx_unmap(vif, pending_idx); for (j = start; j < i; j++) { pending_idx = frag_get_pending_idx(&shinfo->frags[j]); - xenvif_idx_release(vif, pending_idx, - XEN_NETIF_RSP_OKAY); + xenvif_idx_unmap(vif, pending_idx); } /* Remember the error: invalidate all subsequent fragments. */ err = newerr; } + if (skb_has_frag_list(skb)) { + first_skb = skb; + skb = shinfo->frag_list; + shinfo = skb_shinfo(skb); + nr_frags = shinfo->nr_frags; + start = 0; + + goto check_frags; + } + + /* There was a mapping error in the frag_list skb. We have to unmap + * the first skb's frags + */ + if (first_skb && err) { + int j; + shinfo = skb_shinfo(first_skb); + pending_idx = XENVIF_TX_CB(skb)->pending_idx; + start = (frag_get_pending_idx(&shinfo->frags[0]) == pending_idx); + for (j = start; j < shinfo->nr_frags; j++) { + pending_idx = frag_get_pending_idx(&shinfo->frags[j]); + xenvif_idx_unmap(vif, pending_idx); + } + } + *gopp = gop + 1; return err; } @@ -967,6 +1012,10 @@ static void xenvif_fill_frags(struct xenvif *vif, struct sk_buff *skb) struct skb_shared_info *shinfo = skb_shinfo(skb); int nr_frags = shinfo->nr_frags; int i; + u16 prev_pending_idx = INVALID_PENDING_IDX; + + if (skb_shinfo(skb)->destructor_arg) + prev_pending_idx = XENVIF_TX_CB(skb)->pending_idx; for (i = 0; i < nr_frags; i++) { skb_frag_t *frag = shinfo->frags + i; @@ -976,6 +1025,17 @@ static void xenvif_fill_frags(struct xenvif *vif, struct sk_buff *skb) pending_idx = frag_get_pending_idx(frag); + /* If this is not the first frag, chain it to the previous*/ + if (unlikely(prev_pending_idx == INVALID_PENDING_IDX)) + skb_shinfo(skb)->destructor_arg = + &vif->pending_tx_info[pending_idx].callback_struct; + else if (likely(pending_idx != prev_pending_idx)) + vif->pending_tx_info[prev_pending_idx].callback_struct.ctx = + &(vif->pending_tx_info[pending_idx].callback_struct); + + vif->pending_tx_info[pending_idx].callback_struct.ctx = NULL; + prev_pending_idx = pending_idx; + txp = &vif->pending_tx_info[pending_idx].req; page = virt_to_page(idx_to_kaddr(vif, pending_idx)); __skb_fill_page_desc(skb, i, page, txp->offset, txp->size); @@ -983,10 +1043,15 @@ static void xenvif_fill_frags(struct xenvif *vif, struct sk_buff *skb) skb->data_len += txp->size; skb->truesize += txp->size; - /* Take an extra reference to offset xenvif_idx_release */ + /* Take an extra reference to offset network stack's put_page */ get_page(vif->mmap_pages[pending_idx]); - xenvif_idx_release(vif, pending_idx, XEN_NETIF_RSP_OKAY); } + /* FIXME: __skb_fill_page_desc set this to true because page->pfmemalloc + * overlaps with "index", and "mapping" is not set. I think mapping + * should be set. If delivered to local stack, it would drop this + * skb in sk_filter unless the socket has the right to use it. + */ + skb->pfmemalloc = false; } static int xenvif_get_extras(struct xenvif *vif, @@ -1106,16 +1171,14 @@ static bool tx_credit_exceeded(struct xenvif *vif, unsigned size) static unsigned xenvif_tx_build_gops(struct xenvif *vif, int budget) { - struct gnttab_copy *gop = vif->tx_copy_ops, *request_gop; + struct gnttab_map_grant_ref *gop = vif->tx_map_ops, *request_gop; struct sk_buff *skb; int ret; - while ((nr_pending_reqs(vif) + XEN_NETBK_LEGACY_SLOTS_MAX - < MAX_PENDING_REQS) && + while (xenvif_tx_pending_slots_available(vif) && (skb_queue_len(&vif->tx_queue) < budget)) { struct xen_netif_tx_request txreq; struct xen_netif_tx_request txfrags[XEN_NETBK_LEGACY_SLOTS_MAX]; - struct page *page; struct xen_netif_extra_info extras[XEN_NETIF_EXTRA_TYPE_MAX-1]; u16 pending_idx; RING_IDX idx; @@ -1191,8 +1254,7 @@ static unsigned xenvif_tx_build_gops(struct xenvif *vif, int budget) ret < XEN_NETBK_LEGACY_SLOTS_MAX) ? PKT_PROT_LEN : txreq.size; - skb = alloc_skb(data_len + NET_SKB_PAD + NET_IP_ALIGN, - GFP_ATOMIC | __GFP_NOWARN); + skb = xenvif_alloc_skb(data_len); if (unlikely(skb == NULL)) { netdev_dbg(vif->dev, "Can't allocate a skb in start_xmit.\n"); @@ -1200,9 +1262,6 @@ static unsigned xenvif_tx_build_gops(struct xenvif *vif, int budget) break; } - /* Packets passed to netif_rx() must have some headroom. */ - skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN); - if (extras[XEN_NETIF_EXTRA_TYPE_GSO - 1].type) { struct xen_netif_extra_info *gso; gso = &extras[XEN_NETIF_EXTRA_TYPE_GSO - 1]; @@ -1214,31 +1273,11 @@ static unsigned xenvif_tx_build_gops(struct xenvif *vif, int budget) } } - /* XXX could copy straight to head */ - page = xenvif_alloc_page(vif, pending_idx); - if (!page) { - kfree_skb(skb); - xenvif_tx_err(vif, &txreq, idx); - break; - } - - gop->source.u.ref = txreq.gref; - gop->source.domid = vif->domid; - gop->source.offset = txreq.offset; - - gop->dest.u.gmfn = virt_to_mfn(page_address(page)); - gop->dest.domid = DOMID_SELF; - gop->dest.offset = txreq.offset; - - gop->len = txreq.size; - gop->flags = GNTCOPY_source_gref; + xenvif_tx_create_gop(vif, pending_idx, &txreq, gop); gop++; - memcpy(&vif->pending_tx_info[pending_idx].req, - &txreq, sizeof(txreq)); - vif->pending_tx_info[pending_idx].head = index; - *((u16 *)skb->data) = pending_idx; + XENVIF_TX_CB(skb)->pending_idx = pending_idx; __skb_put(skb, data_len); @@ -1266,17 +1305,82 @@ static unsigned xenvif_tx_build_gops(struct xenvif *vif, int budget) vif->tx.req_cons = idx; - if ((gop-vif->tx_copy_ops) >= ARRAY_SIZE(vif->tx_copy_ops)) + if ((gop-vif->tx_map_ops) >= ARRAY_SIZE(vif->tx_map_ops)) break; } - return gop - vif->tx_copy_ops; + return gop - vif->tx_map_ops; } +/* Consolidate skb with a frag_list into a brand new one with local pages on + * frags. Returns 0 or -ENOMEM if can't allocate new pages. + */ +static int xenvif_handle_frag_list(struct xenvif *vif, struct sk_buff *skb) +{ + unsigned int offset = skb_headlen(skb); + skb_frag_t frags[MAX_SKB_FRAGS]; + int i; + struct ubuf_info *uarg; + struct sk_buff *nskb = skb_shinfo(skb)->frag_list; + + vif->tx_zerocopy_sent += 2; + vif->tx_frag_overflow++; + + xenvif_fill_frags(vif, nskb); + /* Subtract frags size, we will correct it later */ + skb->truesize -= skb->data_len; + skb->len += nskb->len; + skb->data_len += nskb->len; + + /* create a brand new frags array and coalesce there */ + for (i = 0; offset < skb->len; i++) { + struct page *page; + unsigned int len; + + BUG_ON(i >= MAX_SKB_FRAGS); + page = alloc_page(GFP_ATOMIC|__GFP_COLD); + if (!page) { + int j; + skb->truesize += skb->data_len; + for (j = 0; j < i; j++) + put_page(frags[j].page.p); + return -ENOMEM; + } + + if (offset + PAGE_SIZE < skb->len) + len = PAGE_SIZE; + else + len = skb->len - offset; + if (skb_copy_bits(skb, offset, page_address(page), len)) + BUG(); + + offset += len; + frags[i].page.p = page; + frags[i].page_offset = 0; + skb_frag_size_set(&frags[i], len); + } + /* swap out with old one */ + memcpy(skb_shinfo(skb)->frags, + frags, + i * sizeof(skb_frag_t)); + skb_shinfo(skb)->nr_frags = i; + skb->truesize += i * PAGE_SIZE; + + /* remove traces of mapped pages and frag_list */ + skb_frag_list_init(skb); + uarg = skb_shinfo(skb)->destructor_arg; + uarg->callback(uarg, true); + skb_shinfo(skb)->destructor_arg = NULL; + + skb_shinfo(nskb)->tx_flags |= SKBTX_DEV_ZEROCOPY; + kfree_skb(nskb); + + return 0; +} static int xenvif_tx_submit(struct xenvif *vif) { - struct gnttab_copy *gop = vif->tx_copy_ops; + struct gnttab_map_grant_ref *gop = vif->tx_map_ops; struct sk_buff *skb; int work_done = 0; @@ -1285,7 +1389,7 @@ static int xenvif_tx_submit(struct xenvif *vif) u16 pending_idx; unsigned data_len; - pending_idx = *((u16 *)skb->data); + pending_idx = XENVIF_TX_CB(skb)->pending_idx; txp = &vif->pending_tx_info[pending_idx].req; /* Check the remap error code. */ @@ -1300,14 +1404,16 @@ static int xenvif_tx_submit(struct xenvif *vif) memcpy(skb->data, (void *)(idx_to_kaddr(vif, pending_idx)|txp->offset), data_len); + vif->pending_tx_info[pending_idx].callback_struct.ctx = NULL; if (data_len < txp->size) { /* Append the packet payload as a fragment. */ txp->offset += data_len; txp->size -= data_len; + skb_shinfo(skb)->destructor_arg = + &vif->pending_tx_info[pending_idx].callback_struct; } else { /* Schedule a response immediately. */ - xenvif_idx_release(vif, pending_idx, - XEN_NETIF_RSP_OKAY); + xenvif_idx_unmap(vif, pending_idx); } if (txp->flags & XEN_NETTXF_csum_blank) @@ -1317,6 +1423,17 @@ static int xenvif_tx_submit(struct xenvif *vif) xenvif_fill_frags(vif, skb); + if (unlikely(skb_has_frag_list(skb))) { + if (xenvif_handle_frag_list(vif, skb)) { + if (net_ratelimit()) + netdev_err(vif->dev, + "Not enough memory to consolidate frag_list!\n"); + skb_shinfo(skb)->tx_flags |= SKBTX_DEV_ZEROCOPY; + kfree_skb(skb); + continue; + } + } + if (skb_is_nonlinear(skb) && skb_headlen(skb) < PKT_PROT_LEN) { int target = min_t(int, skb->len, PKT_PROT_LEN); __pskb_pull_tail(skb, target - skb_headlen(skb)); @@ -1329,6 +1446,9 @@ static int xenvif_tx_submit(struct xenvif *vif) if (checksum_setup(vif, skb)) { netdev_dbg(vif->dev, "Can't setup checksum in net_tx_action\n"); + /* We have to set this flag to trigger the callback */ + if (skb_shinfo(skb)->destructor_arg) + skb_shinfo(skb)->tx_flags |= SKBTX_DEV_ZEROCOPY; kfree_skb(skb); continue; } @@ -1354,17 +1474,134 @@ static int xenvif_tx_submit(struct xenvif *vif) work_done++; + /* Set this flag right before netif_receive_skb, otherwise + * someone might think this packet already left netback, and + * do a skb_copy_ubufs while we are still in control of the + * skb. E.g. the __pskb_pull_tail earlier can do such thing. + */ + if (skb_shinfo(skb)->destructor_arg) { + skb_shinfo(skb)->tx_flags |= SKBTX_DEV_ZEROCOPY; + vif->tx_zerocopy_sent++; + } + netif_receive_skb(skb); } return work_done; } +void xenvif_zerocopy_callback(struct ubuf_info *ubuf, bool zerocopy_success) +{ + unsigned long flags; + pending_ring_idx_t index; + struct xenvif *vif = ubuf_to_vif(ubuf); + + /* This is the only place where we grab this lock, to protect callbacks + * from each other. + */ + spin_lock_irqsave(&vif->callback_lock, flags); + do { + u16 pending_idx = ubuf->desc; + ubuf = (struct ubuf_info *) ubuf->ctx; + BUG_ON(vif->dealloc_prod - vif->dealloc_cons >= + MAX_PENDING_REQS); + index = pending_index(vif->dealloc_prod); + vif->dealloc_ring[index] = pending_idx; + /* Sync with xenvif_tx_dealloc_action: + * insert idx then incr producer. + */ + smp_wmb(); + vif->dealloc_prod++; + } while (ubuf); + wake_up(&vif->dealloc_wq); + spin_unlock_irqrestore(&vif->callback_lock, flags); + + if (RING_HAS_UNCONSUMED_REQUESTS(&vif->tx) && + xenvif_tx_pending_slots_available(vif)) { + local_bh_disable(); + napi_schedule(&vif->napi); + local_bh_enable(); + } + + if (likely(zerocopy_success)) + vif->tx_zerocopy_success++; + else + vif->tx_zerocopy_fail++; +} + +static inline void xenvif_tx_dealloc_action(struct xenvif *vif) +{ + struct gnttab_unmap_grant_ref *gop; + pending_ring_idx_t dc, dp; + u16 pending_idx, pending_idx_release[MAX_PENDING_REQS]; + unsigned int i = 0; + + dc = vif->dealloc_cons; + gop = vif->tx_unmap_ops; + + /* Free up any grants we have finished using */ + do { + dp = vif->dealloc_prod; + + /* Ensure we see all indices enqueued by all + * xenvif_zerocopy_callback(). + */ + smp_rmb(); + + while (dc != dp) { + BUG_ON(gop - vif->tx_unmap_ops > MAX_PENDING_REQS); + pending_idx = + vif->dealloc_ring[pending_index(dc++)]; + + pending_idx_release[gop-vif->tx_unmap_ops] = + pending_idx; + vif->pages_to_unmap[gop-vif->tx_unmap_ops] = + vif->mmap_pages[pending_idx]; + gnttab_set_unmap_op(gop, + idx_to_kaddr(vif, pending_idx), + GNTMAP_host_map, + vif->grant_tx_handle[pending_idx]); + /* Btw. already unmapped? */ + xenvif_grant_handle_reset(vif, pending_idx); + ++gop; + } + + } while (dp != vif->dealloc_prod); + + vif->dealloc_cons = dc; + + if (gop - vif->tx_unmap_ops > 0) { + int ret; + ret = gnttab_unmap_refs(vif->tx_unmap_ops, + NULL, + vif->pages_to_unmap, + gop - vif->tx_unmap_ops); + if (ret) { + netdev_err(vif->dev, "Unmap fail: nr_ops %x ret %d\n", + gop - vif->tx_unmap_ops, ret); + for (i = 0; i < gop - vif->tx_unmap_ops; ++i) { + if (gop[i].status != GNTST_okay) + netdev_err(vif->dev, + " host_addr: %llx handle: %x status: %d\n", + gop[i].host_addr, + gop[i].handle, + gop[i].status); + } + BUG(); + } + } + + for (i = 0; i < gop - vif->tx_unmap_ops; ++i) + xenvif_idx_release(vif, pending_idx_release[i], + XEN_NETIF_RSP_OKAY); +} + + /* Called after netfront has transmitted */ int xenvif_tx_action(struct xenvif *vif, int budget) { unsigned nr_gops; - int work_done; + int work_done, ret; if (unlikely(!tx_work_todo(vif))) return 0; @@ -1374,7 +1611,11 @@ int xenvif_tx_action(struct xenvif *vif, int budget) if (nr_gops == 0) return 0; - gnttab_batch_copy(vif->tx_copy_ops, nr_gops); + ret = gnttab_map_refs(vif->tx_map_ops, + NULL, + vif->pages_to_map, + nr_gops); + BUG_ON(ret); work_done = xenvif_tx_submit(vif); @@ -1385,45 +1626,18 @@ static void xenvif_idx_release(struct xenvif *vif, u16 pending_idx, u8 status) { struct pending_tx_info *pending_tx_info; - pending_ring_idx_t head; - u16 peek; /* peek into next tx request */ - - BUG_ON(vif->mmap_pages[pending_idx] == (void *)(~0UL)); - - /* Already complete? */ - if (vif->mmap_pages[pending_idx] == NULL) - return; + pending_ring_idx_t index; + unsigned long flags; pending_tx_info = &vif->pending_tx_info[pending_idx]; - - head = pending_tx_info->head; - - BUG_ON(!pending_tx_is_head(vif, head)); - BUG_ON(vif->pending_ring[pending_index(head)] != pending_idx); - - do { - pending_ring_idx_t index; - pending_ring_idx_t idx = pending_index(head); - u16 info_idx = vif->pending_ring[idx]; - - pending_tx_info = &vif->pending_tx_info[info_idx]; - make_tx_response(vif, &pending_tx_info->req, status); - - /* Setting any number other than - * INVALID_PENDING_RING_IDX indicates this slot is - * starting a new packet / ending a previous packet. - */ - pending_tx_info->head = 0; - - index = pending_index(vif->pending_prod++); - vif->pending_ring[index] = vif->pending_ring[info_idx]; - - peek = vif->pending_ring[pending_index(++head)]; - - } while (!pending_tx_is_head(vif, peek)); - - put_page(vif->mmap_pages[pending_idx]); - vif->mmap_pages[pending_idx] = NULL; + spin_lock_irqsave(&vif->response_lock, flags); + make_tx_response(vif, &pending_tx_info->req, status); + index = pending_index(vif->pending_prod); + vif->pending_ring[index] = pending_idx; + /* TX shouldn't use the index before we give it back here */ + mb(); + vif->pending_prod++; + spin_unlock_irqrestore(&vif->response_lock, flags); } @@ -1471,23 +1685,74 @@ static struct xen_netif_rx_response *make_rx_response(struct xenvif *vif, return resp; } +void xenvif_idx_unmap(struct xenvif *vif, u16 pending_idx) +{ + int ret; + struct gnttab_unmap_grant_ref tx_unmap_op; + + gnttab_set_unmap_op(&tx_unmap_op, + idx_to_kaddr(vif, pending_idx), + GNTMAP_host_map, + vif->grant_tx_handle[pending_idx]); + /* Btw. already unmapped? */ + xenvif_grant_handle_reset(vif, pending_idx); + + ret = gnttab_unmap_refs(&tx_unmap_op, NULL, + &vif->mmap_pages[pending_idx], 1); + BUG_ON(ret); + + xenvif_idx_release(vif, pending_idx, XEN_NETIF_RSP_OKAY); +} + static inline int rx_work_todo(struct xenvif *vif) { - return (!skb_queue_empty(&vif->rx_queue) && !vif->rx_queue_stopped) || - vif->rx_event; + return (!skb_queue_empty(&vif->rx_queue) && + xenvif_rx_ring_slots_available(vif, vif->rx_last_skb_slots)) || + vif->rx_queue_purge; } static inline int tx_work_todo(struct xenvif *vif) { if (likely(RING_HAS_UNCONSUMED_REQUESTS(&vif->tx)) && - (nr_pending_reqs(vif) + XEN_NETBK_LEGACY_SLOTS_MAX - < MAX_PENDING_REQS)) + xenvif_tx_pending_slots_available(vif)) return 1; return 0; } +static void xenvif_dealloc_delay(unsigned long data) +{ + struct xenvif *vif = (struct xenvif *)data; + + vif->dealloc_delay_timed_out = true; + wake_up(&vif->dealloc_wq); +} + +static inline bool tx_dealloc_work_todo(struct xenvif *vif) +{ + if (vif->dealloc_cons != vif->dealloc_prod) { + if ((nr_free_slots(&vif->tx) > 2 * XEN_NETBK_LEGACY_SLOTS_MAX) && + (vif->dealloc_prod - vif->dealloc_cons < MAX_PENDING_REQS / 4) && + !vif->dealloc_delay_timed_out) { + if (!timer_pending(&vif->dealloc_delay)) { + vif->dealloc_delay.function = + xenvif_dealloc_delay; + vif->dealloc_delay.data = (unsigned long)vif; + mod_timer(&vif->dealloc_delay, + jiffies + msecs_to_jiffies(1)); + + } + return false; + } + del_timer_sync(&vif->dealloc_delay); + vif->dealloc_delay_timed_out = false; + return true; + } + + return false; +} + void xenvif_unmap_frontend_rings(struct xenvif *vif) { if (vif->tx.sring) @@ -1545,7 +1810,7 @@ static void xenvif_start_queue(struct xenvif *vif) netif_wake_queue(vif->dev); } -int xenvif_kthread(void *data) +int xenvif_kthread_guest_rx(void *data) { struct xenvif *vif = data; struct sk_buff *skb; @@ -1557,14 +1822,19 @@ int xenvif_kthread(void *data) if (kthread_should_stop()) break; + if (vif->rx_queue_purge) { + skb_queue_purge(&vif->rx_queue); + vif->rx_queue_purge = false; + } + if (!skb_queue_empty(&vif->rx_queue)) xenvif_rx_action(vif); - vif->rx_event = false; - if (skb_queue_empty(&vif->rx_queue) && - netif_queue_stopped(vif->dev)) + netif_queue_stopped(vif->dev)) { + del_timer_sync(&vif->wake_queue); xenvif_start_queue(vif); + } cond_resched(); } @@ -1576,6 +1846,28 @@ int xenvif_kthread(void *data) return 0; } +int xenvif_dealloc_kthread(void *data) +{ + struct xenvif *vif = data; + + while (!kthread_should_stop()) { + wait_event_interruptible(vif->dealloc_wq, + tx_dealloc_work_todo(vif) || + kthread_should_stop()); + if (kthread_should_stop()) + break; + + xenvif_tx_dealloc_action(vif); + cond_resched(); + } + + /* Unmap anything remaining*/ + if (tx_dealloc_work_todo(vif)) + xenvif_tx_dealloc_action(vif); + + return 0; +} + static int __init netback_init(void) { int rc = 0; @@ -1593,6 +1885,8 @@ static int __init netback_init(void) if (rc) goto failed_init; + rx_drain_timeout_jiffies = msecs_to_jiffies(rx_drain_timeout_msecs); + return 0; failed_init: diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index ff04d4f95baa..a38f03ded5a4 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -907,6 +907,7 @@ static int handle_incoming_queue(struct net_device *dev, /* Ethernet work: Delayed to here as it peeks the header. */ skb->protocol = eth_type_trans(skb, dev); + skb_reset_network_header(skb); if (checksum_setup(dev, skb)) { kfree_skb(skb); @@ -1281,16 +1282,10 @@ static struct net_device *xennet_create_dev(struct xenbus_device *dev) np->rx_refill_timer.function = rx_refill_timeout; err = -ENOMEM; - np->stats = alloc_percpu(struct netfront_stats); + np->stats = netdev_alloc_pcpu_stats(struct netfront_stats); if (np->stats == NULL) goto exit; - for_each_possible_cpu(i) { - struct netfront_stats *xen_nf_stats; - xen_nf_stats = per_cpu_ptr(np->stats, i); - u64_stats_init(&xen_nf_stats->syncp); - } - /* Initialise tx_skbs as a free chain containing every entry. */ np->tx_skb_freelist = 0; for (i = 0; i < NET_TX_RING_SIZE; i++) { @@ -1832,7 +1827,6 @@ static void netback_changed(struct xenbus_device *dev, case XenbusStateReconfiguring: case XenbusStateReconfigured: case XenbusStateUnknown: - case XenbusStateClosed: break; case XenbusStateInitWait: @@ -1847,6 +1841,10 @@ static void netback_changed(struct xenbus_device *dev, netdev_notify_peers(netdev); break; + case XenbusStateClosed: + if (dev->state == XenbusStateClosed) + break; + /* Missed the backend's CLOSING state -- fallthrough */ case XenbusStateClosing: xenbus_frontend_closed(dev); break; diff --git a/drivers/of/address.c b/drivers/of/address.c index d3dd41c840f1..1a54f1ffaadb 100644 --- a/drivers/of/address.c +++ b/drivers/of/address.c @@ -99,11 +99,12 @@ static unsigned int of_bus_default_get_flags(const __be32 *addr) static int of_bus_pci_match(struct device_node *np) { /* + * "pciex" is PCI Express * "vci" is for the /chaos bridge on 1st-gen PCI powermacs * "ht" is hypertransport */ - return !strcmp(np->type, "pci") || !strcmp(np->type, "vci") || - !strcmp(np->type, "ht"); + return !strcmp(np->type, "pci") || !strcmp(np->type, "pciex") || + !strcmp(np->type, "vci") || !strcmp(np->type, "ht"); } static void of_bus_pci_count_cells(struct device_node *np, diff --git a/drivers/of/base.c b/drivers/of/base.c index ff85450d5683..89e888a78899 100644 --- a/drivers/of/base.c +++ b/drivers/of/base.c @@ -342,27 +342,72 @@ struct device_node *of_get_cpu_node(int cpu, unsigned int *thread) } EXPORT_SYMBOL(of_get_cpu_node); -/** Checks if the given "compat" string matches one of the strings in - * the device's "compatible" property +/** + * __of_device_is_compatible() - Check if the node matches given constraints + * @device: pointer to node + * @compat: required compatible string, NULL or "" for any match + * @type: required device_type value, NULL or "" for any match + * @name: required node name, NULL or "" for any match + * + * Checks if the given @compat, @type and @name strings match the + * properties of the given @device. A constraints can be skipped by + * passing NULL or an empty string as the constraint. + * + * Returns 0 for no match, and a positive integer on match. The return + * value is a relative score with larger values indicating better + * matches. The score is weighted for the most specific compatible value + * to get the highest score. Matching type is next, followed by matching + * name. Practically speaking, this results in the following priority + * order for matches: + * + * 1. specific compatible && type && name + * 2. specific compatible && type + * 3. specific compatible && name + * 4. specific compatible + * 5. general compatible && type && name + * 6. general compatible && type + * 7. general compatible && name + * 8. general compatible + * 9. type && name + * 10. type + * 11. name */ static int __of_device_is_compatible(const struct device_node *device, - const char *compat) + const char *compat, const char *type, const char *name) { - const char* cp; - int cplen, l; + struct property *prop; + const char *cp; + int index = 0, score = 0; + + /* Compatible match has highest priority */ + if (compat && compat[0]) { + prop = __of_find_property(device, "compatible", NULL); + for (cp = of_prop_next_string(prop, NULL); cp; + cp = of_prop_next_string(prop, cp), index++) { + if (of_compat_cmp(cp, compat, strlen(compat)) == 0) { + score = INT_MAX/2 - (index << 2); + break; + } + } + if (!score) + return 0; + } - cp = __of_get_property(device, "compatible", &cplen); - if (cp == NULL) - return 0; - while (cplen > 0) { - if (of_compat_cmp(cp, compat, strlen(compat)) == 0) - return 1; - l = strlen(cp) + 1; - cp += l; - cplen -= l; + /* Matching type is better than matching name */ + if (type && type[0]) { + if (!device->type || of_node_cmp(type, device->type)) + return 0; + score += 2; } - return 0; + /* Matching name is a bit better than not */ + if (name && name[0]) { + if (!device->name || of_node_cmp(name, device->name)) + return 0; + score++; + } + + return score; } /** Checks if the given "compat" string matches one of the strings in @@ -375,7 +420,7 @@ int of_device_is_compatible(const struct device_node *device, int res; raw_spin_lock_irqsave(&devtree_lock, flags); - res = __of_device_is_compatible(device, compat); + res = __of_device_is_compatible(device, compat, NULL, NULL); raw_spin_unlock_irqrestore(&devtree_lock, flags); return res; } @@ -681,10 +726,7 @@ struct device_node *of_find_compatible_node(struct device_node *from, raw_spin_lock_irqsave(&devtree_lock, flags); np = from ? from->allnext : of_allnodes; for (; np; np = np->allnext) { - if (type - && !(np->type && (of_node_cmp(np->type, type) == 0))) - continue; - if (__of_device_is_compatible(np, compatible) && + if (__of_device_is_compatible(np, compatible, type, NULL) && of_node_get(np)) break; } @@ -734,43 +776,22 @@ static const struct of_device_id *__of_match_node(const struct of_device_id *matches, const struct device_node *node) { - const char *cp; - int cplen, l; + const struct of_device_id *best_match = NULL; + int score, best_score = 0; if (!matches) return NULL; - cp = __of_get_property(node, "compatible", &cplen); - do { - const struct of_device_id *m = matches; - - /* Check against matches with current compatible string */ - while (m->name[0] || m->type[0] || m->compatible[0]) { - int match = 1; - if (m->name[0]) - match &= node->name - && !strcmp(m->name, node->name); - if (m->type[0]) - match &= node->type - && !strcmp(m->type, node->type); - if (m->compatible[0]) - match &= cp - && !of_compat_cmp(m->compatible, cp, - strlen(m->compatible)); - if (match) - return m; - m++; - } - - /* Get node's next compatible string */ - if (cp) { - l = strlen(cp) + 1; - cp += l; - cplen -= l; + for (; matches->name[0] || matches->type[0] || matches->compatible[0]; matches++) { + score = __of_device_is_compatible(node, matches->compatible, + matches->type, matches->name); + if (score > best_score) { + best_match = matches; + best_score = score; } - } while (cp && (cplen > 0)); + } - return NULL; + return best_match; } /** @@ -778,10 +799,7 @@ const struct of_device_id *__of_match_node(const struct of_device_id *matches, * @matches: array of of device match structures to search in * @node: the of device structure to match against * - * Low level utility function used by device matching. Matching order - * is to compare each of the node's compatibles with all given matches - * first. This implies node's compatible is sorted from specific to - * generic while matches can be in any order. + * Low level utility function used by device matching. */ const struct of_device_id *of_match_node(const struct of_device_id *matches, const struct device_node *node) diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c index 875b7b6f0d2a..5b3c24f3cde5 100644 --- a/drivers/of/of_mdio.c +++ b/drivers/of/of_mdio.c @@ -24,7 +24,11 @@ MODULE_LICENSE("GPL"); static void of_set_phy_supported(struct phy_device *phydev, u32 max_speed) { - phydev->supported |= PHY_DEFAULT_FEATURES; + /* The default values for phydev->supported are provided by the PHY + * driver "features" member, we want to reset to sane defaults fist + * before supporting higher speeds. + */ + phydev->supported &= PHY_DEFAULT_FEATURES; switch (max_speed) { default: @@ -44,7 +48,7 @@ static int of_mdiobus_register_phy(struct mii_bus *mdio, struct device_node *chi { struct phy_device *phy; bool is_c45; - int rc, prev_irq; + int rc; u32 max_speed = 0; is_c45 = of_device_is_compatible(child, @@ -54,12 +58,14 @@ static int of_mdiobus_register_phy(struct mii_bus *mdio, struct device_node *chi if (!phy || IS_ERR(phy)) return 1; - if (mdio->irq) { - prev_irq = mdio->irq[addr]; - mdio->irq[addr] = - irq_of_parse_and_map(child, 0); - if (!mdio->irq[addr]) - mdio->irq[addr] = prev_irq; + rc = irq_of_parse_and_map(child, 0); + if (rc > 0) { + phy->irq = rc; + if (mdio->irq) + mdio->irq[addr] = rc; + } else { + if (mdio->irq) + phy->irq = mdio->irq[addr]; } /* Associate the OF node with the device structure so it diff --git a/drivers/of/of_net.c b/drivers/of/of_net.c index a208a457558c..84215c1929c4 100644 --- a/drivers/of/of_net.c +++ b/drivers/of/of_net.c @@ -12,28 +12,6 @@ #include <linux/export.h> /** - * It maps 'enum phy_interface_t' found in include/linux/phy.h - * into the device tree binding of 'phy-mode', so that Ethernet - * device driver can get phy interface from device tree. - */ -static const char *phy_modes[] = { - [PHY_INTERFACE_MODE_NA] = "", - [PHY_INTERFACE_MODE_MII] = "mii", - [PHY_INTERFACE_MODE_GMII] = "gmii", - [PHY_INTERFACE_MODE_SGMII] = "sgmii", - [PHY_INTERFACE_MODE_TBI] = "tbi", - [PHY_INTERFACE_MODE_REVMII] = "rev-mii", - [PHY_INTERFACE_MODE_RMII] = "rmii", - [PHY_INTERFACE_MODE_RGMII] = "rgmii", - [PHY_INTERFACE_MODE_RGMII_ID] = "rgmii-id", - [PHY_INTERFACE_MODE_RGMII_RXID] = "rgmii-rxid", - [PHY_INTERFACE_MODE_RGMII_TXID] = "rgmii-txid", - [PHY_INTERFACE_MODE_RTBI] = "rtbi", - [PHY_INTERFACE_MODE_SMII] = "smii", - [PHY_INTERFACE_MODE_XGMII] = "xgmii", -}; - -/** * of_get_phy_mode - Get phy mode for given device_node * @np: Pointer to the given device_node * @@ -49,8 +27,8 @@ int of_get_phy_mode(struct device_node *np) if (err < 0) return err; - for (i = 0; i < ARRAY_SIZE(phy_modes); i++) - if (!strcasecmp(pm, phy_modes[i])) + for (i = 0; i < PHY_INTERFACE_MODE_MAX; i++) + if (!strcasecmp(pm, phy_modes(i))) return i; return -ENODEV; diff --git a/drivers/of/selftest.c b/drivers/of/selftest.c index e21012bde639..6643d1920985 100644 --- a/drivers/of/selftest.c +++ b/drivers/of/selftest.c @@ -300,6 +300,72 @@ static void __init of_selftest_parse_interrupts_extended(void) of_node_put(np); } +static struct of_device_id match_node_table[] = { + { .data = "A", .name = "name0", }, /* Name alone is lowest priority */ + { .data = "B", .type = "type1", }, /* followed by type alone */ + + { .data = "Ca", .name = "name2", .type = "type1", }, /* followed by both together */ + { .data = "Cb", .name = "name2", }, /* Only match when type doesn't match */ + { .data = "Cc", .name = "name2", .type = "type2", }, + + { .data = "E", .compatible = "compat3" }, + { .data = "G", .compatible = "compat2", }, + { .data = "H", .compatible = "compat2", .name = "name5", }, + { .data = "I", .compatible = "compat2", .type = "type1", }, + { .data = "J", .compatible = "compat2", .type = "type1", .name = "name8", }, + { .data = "K", .compatible = "compat2", .name = "name9", }, + {} +}; + +static struct { + const char *path; + const char *data; +} match_node_tests[] = { + { .path = "/testcase-data/match-node/name0", .data = "A", }, + { .path = "/testcase-data/match-node/name1", .data = "B", }, + { .path = "/testcase-data/match-node/a/name2", .data = "Ca", }, + { .path = "/testcase-data/match-node/b/name2", .data = "Cb", }, + { .path = "/testcase-data/match-node/c/name2", .data = "Cc", }, + { .path = "/testcase-data/match-node/name3", .data = "E", }, + { .path = "/testcase-data/match-node/name4", .data = "G", }, + { .path = "/testcase-data/match-node/name5", .data = "H", }, + { .path = "/testcase-data/match-node/name6", .data = "G", }, + { .path = "/testcase-data/match-node/name7", .data = "I", }, + { .path = "/testcase-data/match-node/name8", .data = "J", }, + { .path = "/testcase-data/match-node/name9", .data = "K", }, +}; + +static void __init of_selftest_match_node(void) +{ + struct device_node *np; + const struct of_device_id *match; + int i; + + for (i = 0; i < ARRAY_SIZE(match_node_tests); i++) { + np = of_find_node_by_path(match_node_tests[i].path); + if (!np) { + selftest(0, "missing testcase node %s\n", + match_node_tests[i].path); + continue; + } + + match = of_match_node(match_node_table, np); + if (!match) { + selftest(0, "%s didn't match anything\n", + match_node_tests[i].path); + continue; + } + + if (strcmp(match->data, match_node_tests[i].data) != 0) { + selftest(0, "%s got wrong match. expected %s, got %s\n", + match_node_tests[i].path, match_node_tests[i].data, + (const char *)match->data); + continue; + } + selftest(1, "passed"); + } +} + static int __init of_selftest(void) { struct device_node *np; @@ -316,6 +382,7 @@ static int __init of_selftest(void) of_selftest_property_match_string(); of_selftest_parse_interrupts(); of_selftest_parse_interrupts_extended(); + of_selftest_match_node(); pr_info("end of selftest - %i passed, %i failed\n", selftest_results.passed, selftest_results.failed); return 0; diff --git a/drivers/of/testcase-data/testcases.dtsi b/drivers/of/testcase-data/testcases.dtsi new file mode 100644 index 000000000000..3a5b75a8e4d7 --- /dev/null +++ b/drivers/of/testcase-data/testcases.dtsi @@ -0,0 +1,3 @@ +#include "tests-phandle.dtsi" +#include "tests-interrupts.dtsi" +#include "tests-match.dtsi" diff --git a/arch/arm/boot/dts/testcases/tests-interrupts.dtsi b/drivers/of/testcase-data/tests-interrupts.dtsi index c843720bd3e5..c843720bd3e5 100644 --- a/arch/arm/boot/dts/testcases/tests-interrupts.dtsi +++ b/drivers/of/testcase-data/tests-interrupts.dtsi diff --git a/drivers/of/testcase-data/tests-match.dtsi b/drivers/of/testcase-data/tests-match.dtsi new file mode 100644 index 000000000000..c9e541129534 --- /dev/null +++ b/drivers/of/testcase-data/tests-match.dtsi @@ -0,0 +1,19 @@ + +/ { + testcase-data { + match-node { + name0 { }; + name1 { device_type = "type1"; }; + a { name2 { device_type = "type1"; }; }; + b { name2 { }; }; + c { name2 { device_type = "type2"; }; }; + name3 { compatible = "compat3"; }; + name4 { compatible = "compat2", "compat3"; }; + name5 { compatible = "compat2", "compat3"; }; + name6 { compatible = "compat1", "compat2", "compat3"; }; + name7 { compatible = "compat2"; device_type = "type1"; }; + name8 { compatible = "compat2"; device_type = "type1"; }; + name9 { compatible = "compat2"; }; + }; + }; +}; diff --git a/arch/arm/boot/dts/testcases/tests-phandle.dtsi b/drivers/of/testcase-data/tests-phandle.dtsi index 0007d3cd7dc2..0007d3cd7dc2 100644 --- a/arch/arm/boot/dts/testcases/tests-phandle.dtsi +++ b/drivers/of/testcase-data/tests-phandle.dtsi diff --git a/drivers/pci/host/pci-mvebu.c b/drivers/pci/host/pci-mvebu.c index 13478ecd4113..0e79665afd44 100644 --- a/drivers/pci/host/pci-mvebu.c +++ b/drivers/pci/host/pci-mvebu.c @@ -60,14 +60,6 @@ #define PCIE_DEBUG_CTRL 0x1a60 #define PCIE_DEBUG_SOFT_RESET BIT(20) -/* - * This product ID is registered by Marvell, and used when the Marvell - * SoC is not the root complex, but an endpoint on the PCIe bus. It is - * therefore safe to re-use this PCI ID for our emulated PCI-to-PCI - * bridge. - */ -#define MARVELL_EMULATED_PCI_PCI_BRIDGE_ID 0x7846 - /* PCI configuration space of a PCI-to-PCI bridge */ struct mvebu_sw_pci_bridge { u16 vendor; @@ -388,7 +380,8 @@ static void mvebu_sw_pci_bridge_init(struct mvebu_pcie_port *port) bridge->class = PCI_CLASS_BRIDGE_PCI; bridge->vendor = PCI_VENDOR_ID_MARVELL; - bridge->device = MARVELL_EMULATED_PCI_PCI_BRIDGE_ID; + bridge->device = mvebu_readl(port, PCIE_DEV_ID_OFF) >> 16; + bridge->revision = mvebu_readl(port, PCIE_DEV_REV_OFF) & 0xff; bridge->header_type = PCI_HEADER_TYPE_BRIDGE; bridge->cache_line_size = 0x10; diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c index e2a783fdb98f..7c7a388c85ab 100644 --- a/drivers/pci/hotplug/acpiphp_glue.c +++ b/drivers/pci/hotplug/acpiphp_glue.c @@ -730,6 +730,17 @@ static unsigned int get_slot_status(struct acpiphp_slot *slot) return (unsigned int)sta; } +static inline bool device_status_valid(unsigned int sta) +{ + /* + * ACPI spec says that _STA may return bit 0 clear with bit 3 set + * if the device is valid but does not require a device driver to be + * loaded (Section 6.3.7 of ACPI 5.0A). + */ + unsigned int mask = ACPI_STA_DEVICE_ENABLED | ACPI_STA_DEVICE_FUNCTIONING; + return (sta & mask) == mask; +} + /** * trim_stale_devices - remove PCI devices that are not responding. * @dev: PCI device to start walking the hierarchy from. @@ -745,7 +756,7 @@ static void trim_stale_devices(struct pci_dev *dev) unsigned long long sta; status = acpi_evaluate_integer(handle, "_STA", NULL, &sta); - alive = (ACPI_SUCCESS(status) && sta == ACPI_STA_ALL) + alive = (ACPI_SUCCESS(status) && device_status_valid(sta)) || acpiphp_no_hotplug(handle); } if (!alive) { @@ -792,7 +803,7 @@ static void acpiphp_check_bridge(struct acpiphp_bridge *bridge) mutex_lock(&slot->crit_sect); if (slot_no_hotplug(slot)) { ; /* do nothing */ - } else if (get_slot_status(slot) == ACPI_STA_ALL) { + } else if (device_status_valid(get_slot_status(slot))) { /* remove stale devices if any */ list_for_each_entry_safe_reverse(dev, tmp, &bus->devices, bus_list) diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index 7a0fec6ce571..955ab7990c5b 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -545,9 +545,15 @@ static int populate_msi_sysfs(struct pci_dev *pdev) return -ENOMEM; list_for_each_entry(entry, &pdev->msi_list, list) { char *name = kmalloc(20, GFP_KERNEL); + if (!name) + goto error_attrs; + msi_dev_attr = kzalloc(sizeof(*msi_dev_attr), GFP_KERNEL); - if (!msi_dev_attr) + if (!msi_dev_attr) { + kfree(name); goto error_attrs; + } + sprintf(name, "%d", entry->irq); sysfs_attr_init(&msi_dev_attr->attr); msi_dev_attr->attr.name = name; @@ -589,6 +595,7 @@ error_attrs: ++count; msi_attr = msi_attrs[count]; } + kfree(msi_attrs); return ret; } @@ -959,7 +966,6 @@ EXPORT_SYMBOL(pci_disable_msi); /** * pci_msix_vec_count - return the number of device's MSI-X table entries * @dev: pointer to the pci_dev data structure of MSI-X device function - * This function returns the number of device's MSI-X table entries and * therefore the number of MSI-X vectors device is capable of sending. * It returns a negative errno if the device is not capable of sending MSI-X diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 1febe90831b4..6b05f6134b68 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -1181,6 +1181,8 @@ EXPORT_SYMBOL_GPL(pci_load_and_free_saved_state); static int do_pci_enable_device(struct pci_dev *dev, int bars) { int err; + u16 cmd; + u8 pin; err = pci_set_power_state(dev, PCI_D0); if (err < 0 && err != -EIO) @@ -1190,6 +1192,14 @@ static int do_pci_enable_device(struct pci_dev *dev, int bars) return err; pci_fixup_device(pci_fixup_enable, dev); + pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &pin); + if (pin) { + pci_read_config_word(dev, PCI_COMMAND, &cmd); + if (cmd & PCI_COMMAND_INTX_DISABLE) + pci_write_config_word(dev, PCI_COMMAND, + cmd & ~PCI_COMMAND_INTX_DISABLE); + } + return 0; } diff --git a/drivers/phy/Kconfig b/drivers/phy/Kconfig index afa2354f6600..c7a551c2d5f1 100644 --- a/drivers/phy/Kconfig +++ b/drivers/phy/Kconfig @@ -5,7 +5,7 @@ menu "PHY Subsystem" config GENERIC_PHY - tristate "PHY Core" + bool "PHY Core" help Generic PHY support. @@ -61,6 +61,7 @@ config PHY_EXYNOS_DP_VIDEO config BCM_KONA_USB2_PHY tristate "Broadcom Kona USB2 PHY Driver" depends on GENERIC_PHY + depends on HAS_IOMEM help Enable this to support the Broadcom Kona USB 2.0 PHY. diff --git a/drivers/phy/phy-core.c b/drivers/phy/phy-core.c index 645c867c1257..6c738376daff 100644 --- a/drivers/phy/phy-core.c +++ b/drivers/phy/phy-core.c @@ -162,6 +162,9 @@ int phy_init(struct phy *phy) { int ret; + if (!phy) + return 0; + ret = phy_pm_runtime_get_sync(phy); if (ret < 0 && ret != -ENOTSUPP) return ret; @@ -173,6 +176,8 @@ 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; @@ -187,6 +192,9 @@ int phy_exit(struct phy *phy) { int ret; + if (!phy) + return 0; + ret = phy_pm_runtime_get_sync(phy); if (ret < 0 && ret != -ENOTSUPP) return ret; @@ -212,6 +220,9 @@ int phy_power_on(struct phy *phy) { int ret; + if (!phy) + return 0; + ret = phy_pm_runtime_get_sync(phy); if (ret < 0 && ret != -ENOTSUPP) return ret; @@ -223,6 +234,8 @@ 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); @@ -240,6 +253,9 @@ int phy_power_off(struct phy *phy) { int ret; + if (!phy) + return 0; + mutex_lock(&phy->mutex); if (phy->power_count == 1 && phy->ops->power_off) { ret = phy->ops->power_off(phy); @@ -308,7 +324,7 @@ err0: */ void phy_put(struct phy *phy) { - if (IS_ERR(phy)) + if (!phy || IS_ERR(phy)) return; module_put(phy->ops->owner); @@ -328,6 +344,9 @@ void devm_phy_put(struct device *dev, struct phy *phy) { int r; + if (!phy) + return; + r = devres_destroy(dev, devm_phy_release, devm_phy_match, phy); dev_WARN_ONCE(dev, r, "couldn't find PHY resource\n"); } @@ -389,17 +408,11 @@ struct phy *phy_get(struct device *dev, const char *string) index = of_property_match_string(dev->of_node, "phy-names", string); phy = of_phy_get(dev, index); - if (IS_ERR(phy)) { - dev_err(dev, "unable to find phy\n"); - return phy; - } } else { phy = phy_lookup(dev, string); - if (IS_ERR(phy)) { - dev_err(dev, "unable to find phy\n"); - return phy; - } } + if (IS_ERR(phy)) + return phy; if (!try_module_get(phy->ops->owner)) return ERR_PTR(-EPROBE_DEFER); @@ -411,6 +424,27 @@ struct phy *phy_get(struct device *dev, const char *string) EXPORT_SYMBOL_GPL(phy_get); /** + * phy_optional_get() - lookup and obtain a reference to an optional phy. + * @dev: device that requests this phy + * @string: the phy name as given in the dt data or the name of the controller + * port for non-dt case + * + * Returns the phy driver, after getting a refcount to it; or + * NULL if there is no such phy. The caller is responsible for + * calling phy_put() to release that count. + */ +struct phy *phy_optional_get(struct device *dev, const char *string) +{ + struct phy *phy = phy_get(dev, string); + + if (PTR_ERR(phy) == -ENODEV) + phy = NULL; + + return phy; +} +EXPORT_SYMBOL_GPL(phy_optional_get); + +/** * devm_phy_get() - lookup and obtain a reference to a phy. * @dev: device that requests this phy * @string: the phy name as given in the dt data or phy device name @@ -441,6 +475,30 @@ struct phy *devm_phy_get(struct device *dev, const char *string) EXPORT_SYMBOL_GPL(devm_phy_get); /** + * devm_phy_optional_get() - lookup and obtain a reference to an optional phy. + * @dev: device that requests this phy + * @string: the phy name as given in the dt data or phy device name + * for non-dt case + * + * Gets the phy using phy_get(), and associates a device with it using + * devres. On driver detach, release function is invoked on the devres + * data, then, devres data is freed. This differs to devm_phy_get() in + * that if the phy does not exist, it is not considered an error and + * -ENODEV will not be returned. Instead the NULL phy is returned, + * which can be passed to all other phy consumer calls. + */ +struct phy *devm_phy_optional_get(struct device *dev, const char *string) +{ + struct phy *phy = devm_phy_get(dev, string); + + if (PTR_ERR(phy) == -ENODEV) + phy = NULL; + + return phy; +} +EXPORT_SYMBOL_GPL(devm_phy_optional_get); + +/** * phy_create() - create a new phy * @dev: device that is creating the new phy * @ops: function pointers for performing phy operations diff --git a/drivers/phy/phy-exynos-dp-video.c b/drivers/phy/phy-exynos-dp-video.c index 1dbe6ce7b2ce..0786fef842e7 100644 --- a/drivers/phy/phy-exynos-dp-video.c +++ b/drivers/phy/phy-exynos-dp-video.c @@ -76,10 +76,6 @@ static int exynos_dp_video_phy_probe(struct platform_device *pdev) if (IS_ERR(state->regs)) return PTR_ERR(state->regs); - phy_provider = devm_of_phy_provider_register(dev, of_phy_simple_xlate); - if (IS_ERR(phy_provider)) - return PTR_ERR(phy_provider); - phy = devm_phy_create(dev, &exynos_dp_video_phy_ops, NULL); if (IS_ERR(phy)) { dev_err(dev, "failed to create Display Port PHY\n"); @@ -87,6 +83,10 @@ static int exynos_dp_video_phy_probe(struct platform_device *pdev) } phy_set_drvdata(phy, state); + phy_provider = devm_of_phy_provider_register(dev, of_phy_simple_xlate); + if (IS_ERR(phy_provider)) + return PTR_ERR(phy_provider); + return 0; } diff --git a/drivers/phy/phy-exynos-mipi-video.c b/drivers/phy/phy-exynos-mipi-video.c index 0c5efab11af1..7f139326a642 100644 --- a/drivers/phy/phy-exynos-mipi-video.c +++ b/drivers/phy/phy-exynos-mipi-video.c @@ -134,11 +134,6 @@ static int exynos_mipi_video_phy_probe(struct platform_device *pdev) dev_set_drvdata(dev, state); spin_lock_init(&state->slock); - phy_provider = devm_of_phy_provider_register(dev, - exynos_mipi_video_phy_xlate); - if (IS_ERR(phy_provider)) - return PTR_ERR(phy_provider); - for (i = 0; i < EXYNOS_MIPI_PHYS_NUM; i++) { struct phy *phy = devm_phy_create(dev, &exynos_mipi_video_phy_ops, NULL); @@ -152,6 +147,11 @@ static int exynos_mipi_video_phy_probe(struct platform_device *pdev) phy_set_drvdata(phy, &state->phys[i]); } + phy_provider = devm_of_phy_provider_register(dev, + exynos_mipi_video_phy_xlate); + if (IS_ERR(phy_provider)) + return PTR_ERR(phy_provider); + return 0; } diff --git a/drivers/phy/phy-mvebu-sata.c b/drivers/phy/phy-mvebu-sata.c index d43786f62437..d70ecd6a1b3f 100644 --- a/drivers/phy/phy-mvebu-sata.c +++ b/drivers/phy/phy-mvebu-sata.c @@ -99,17 +99,17 @@ static int phy_mvebu_sata_probe(struct platform_device *pdev) if (IS_ERR(priv->clk)) return PTR_ERR(priv->clk); - phy_provider = devm_of_phy_provider_register(&pdev->dev, - of_phy_simple_xlate); - if (IS_ERR(phy_provider)) - return PTR_ERR(phy_provider); - phy = devm_phy_create(&pdev->dev, &phy_mvebu_sata_ops, NULL); if (IS_ERR(phy)) return PTR_ERR(phy); phy_set_drvdata(phy, priv); + phy_provider = devm_of_phy_provider_register(&pdev->dev, + of_phy_simple_xlate); + if (IS_ERR(phy_provider)) + return PTR_ERR(phy_provider); + /* The boot loader may of left it on. Turn it off. */ phy_mvebu_sata_power_off(phy); diff --git a/drivers/phy/phy-omap-usb2.c b/drivers/phy/phy-omap-usb2.c index bfc5c337f99a..7699752fba11 100644 --- a/drivers/phy/phy-omap-usb2.c +++ b/drivers/phy/phy-omap-usb2.c @@ -177,11 +177,6 @@ static int omap_usb2_probe(struct platform_device *pdev) phy->phy.otg = otg; phy->phy.type = USB_PHY_TYPE_USB2; - phy_provider = devm_of_phy_provider_register(phy->dev, - of_phy_simple_xlate); - if (IS_ERR(phy_provider)) - return PTR_ERR(phy_provider); - control_node = of_parse_phandle(node, "ctrl-module", 0); if (!control_node) { dev_err(&pdev->dev, "Failed to get control device phandle\n"); @@ -214,6 +209,11 @@ static int omap_usb2_probe(struct platform_device *pdev) phy_set_drvdata(generic_phy, phy); + phy_provider = devm_of_phy_provider_register(phy->dev, + of_phy_simple_xlate); + if (IS_ERR(phy_provider)) + return PTR_ERR(phy_provider); + phy->wkupclk = devm_clk_get(phy->dev, "usb_phy_cm_clk32k"); if (IS_ERR(phy->wkupclk)) { dev_err(&pdev->dev, "unable to get usb_phy_cm_clk32k\n"); diff --git a/drivers/phy/phy-twl4030-usb.c b/drivers/phy/phy-twl4030-usb.c index daf65e68aaab..c3ace1db8136 100644 --- a/drivers/phy/phy-twl4030-usb.c +++ b/drivers/phy/phy-twl4030-usb.c @@ -695,11 +695,6 @@ static int twl4030_usb_probe(struct platform_device *pdev) otg->set_host = twl4030_set_host; otg->set_peripheral = twl4030_set_peripheral; - phy_provider = devm_of_phy_provider_register(twl->dev, - of_phy_simple_xlate); - if (IS_ERR(phy_provider)) - return PTR_ERR(phy_provider); - phy = devm_phy_create(twl->dev, &ops, init_data); if (IS_ERR(phy)) { dev_dbg(&pdev->dev, "Failed to create PHY\n"); @@ -708,6 +703,11 @@ static int twl4030_usb_probe(struct platform_device *pdev) phy_set_drvdata(phy, twl); + phy_provider = devm_of_phy_provider_register(twl->dev, + of_phy_simple_xlate); + if (IS_ERR(phy_provider)) + return PTR_ERR(phy_provider); + /* init spinlock for workqueue */ spin_lock_init(&twl->lock); diff --git a/drivers/power/ds2782_battery.c b/drivers/power/ds2782_battery.c index 563174891c90..041f9b638d28 100644 --- a/drivers/power/ds2782_battery.c +++ b/drivers/power/ds2782_battery.c @@ -192,7 +192,7 @@ static int ds2786_get_voltage(struct ds278x_info *info, int *voltage_uV) /* * Voltage is measured in units of 1.22mV. The voltage is stored as - * a 10-bit number plus sign, in the upper bits of a 16-bit register + * a 12-bit number plus sign, in the upper bits of a 16-bit register */ err = ds278x_read_reg16(info, DS278x_REG_VOLT_MSB, &raw); if (err) diff --git a/drivers/power/isp1704_charger.c b/drivers/power/isp1704_charger.c index 80edb7d8cb54..0b4cf9d63291 100644 --- a/drivers/power/isp1704_charger.c +++ b/drivers/power/isp1704_charger.c @@ -444,8 +444,6 @@ static int isp1704_charger_probe(struct platform_device *pdev) ret = PTR_ERR(isp->phy); goto fail0; } - if (!isp->phy) - goto fail0; isp->dev = &pdev->dev; platform_set_drvdata(pdev, isp); diff --git a/drivers/power/max17040_battery.c b/drivers/power/max17040_battery.c index c7ff6d67f158..0fbac861080d 100644 --- a/drivers/power/max17040_battery.c +++ b/drivers/power/max17040_battery.c @@ -148,7 +148,7 @@ static void max17040_get_online(struct i2c_client *client) { struct max17040_chip *chip = i2c_get_clientdata(client); - if (chip->pdata->battery_online) + if (chip->pdata && chip->pdata->battery_online) chip->online = chip->pdata->battery_online(); else chip->online = 1; @@ -158,7 +158,8 @@ static void max17040_get_status(struct i2c_client *client) { struct max17040_chip *chip = i2c_get_clientdata(client); - if (!chip->pdata->charger_online || !chip->pdata->charger_enable) { + if (!chip->pdata || !chip->pdata->charger_online + || !chip->pdata->charger_enable) { chip->status = POWER_SUPPLY_STATUS_UNKNOWN; return; } diff --git a/drivers/pwm/pwm-lp3943.c b/drivers/pwm/pwm-lp3943.c index 8a843a04c224..a40b9c34e9ff 100644 --- a/drivers/pwm/pwm-lp3943.c +++ b/drivers/pwm/pwm-lp3943.c @@ -52,8 +52,10 @@ lp3943_pwm_request_map(struct lp3943_pwm *lp3943_pwm, int hwpwm) offset = pwm_map->output[i]; /* Return an error if the pin is already assigned */ - if (test_and_set_bit(offset, &lp3943->pin_used)) + if (test_and_set_bit(offset, &lp3943->pin_used)) { + kfree(pwm_map); return ERR_PTR(-EBUSY); + } } return pwm_map; diff --git a/drivers/rapidio/devices/tsi721.h b/drivers/rapidio/devices/tsi721.h index b4b0d83f9ef6..7061ac0ad428 100644 --- a/drivers/rapidio/devices/tsi721.h +++ b/drivers/rapidio/devices/tsi721.h @@ -678,6 +678,7 @@ struct tsi721_bdma_chan { struct list_head free_list; dma_cookie_t completed_cookie; struct tasklet_struct tasklet; + bool active; }; #endif /* CONFIG_RAPIDIO_DMA_ENGINE */ diff --git a/drivers/rapidio/devices/tsi721_dma.c b/drivers/rapidio/devices/tsi721_dma.c index 502663f5f7c6..91245f5dbe81 100644 --- a/drivers/rapidio/devices/tsi721_dma.c +++ b/drivers/rapidio/devices/tsi721_dma.c @@ -206,8 +206,8 @@ void tsi721_bdma_handler(struct tsi721_bdma_chan *bdma_chan) { /* Disable BDMA channel interrupts */ iowrite32(0, bdma_chan->regs + TSI721_DMAC_INTE); - - tasklet_schedule(&bdma_chan->tasklet); + if (bdma_chan->active) + tasklet_schedule(&bdma_chan->tasklet); } #ifdef CONFIG_PCI_MSI @@ -562,7 +562,7 @@ static int tsi721_alloc_chan_resources(struct dma_chan *dchan) } #endif /* CONFIG_PCI_MSI */ - tasklet_enable(&bdma_chan->tasklet); + bdma_chan->active = true; tsi721_bdma_interrupt_enable(bdma_chan, 1); return bdma_chan->bd_num - 1; @@ -576,9 +576,7 @@ err_out: static void tsi721_free_chan_resources(struct dma_chan *dchan) { struct tsi721_bdma_chan *bdma_chan = to_tsi721_chan(dchan); -#ifdef CONFIG_PCI_MSI struct tsi721_device *priv = to_tsi721(dchan->device); -#endif LIST_HEAD(list); dev_dbg(dchan->device->dev, "%s: Entry\n", __func__); @@ -589,14 +587,25 @@ static void tsi721_free_chan_resources(struct dma_chan *dchan) BUG_ON(!list_empty(&bdma_chan->active_list)); BUG_ON(!list_empty(&bdma_chan->queue)); - tasklet_disable(&bdma_chan->tasklet); + tsi721_bdma_interrupt_enable(bdma_chan, 0); + bdma_chan->active = false; + +#ifdef CONFIG_PCI_MSI + if (priv->flags & TSI721_USING_MSIX) { + synchronize_irq(priv->msix[TSI721_VECT_DMA0_DONE + + bdma_chan->id].vector); + synchronize_irq(priv->msix[TSI721_VECT_DMA0_INT + + bdma_chan->id].vector); + } else +#endif + synchronize_irq(priv->pdev->irq); + + tasklet_kill(&bdma_chan->tasklet); spin_lock_bh(&bdma_chan->lock); list_splice_init(&bdma_chan->free_list, &list); spin_unlock_bh(&bdma_chan->lock); - tsi721_bdma_interrupt_enable(bdma_chan, 0); - #ifdef CONFIG_PCI_MSI if (priv->flags & TSI721_USING_MSIX) { free_irq(priv->msix[TSI721_VECT_DMA0_DONE + @@ -790,6 +799,7 @@ int tsi721_register_dma(struct tsi721_device *priv) bdma_chan->dchan.cookie = 1; bdma_chan->dchan.chan_id = i; bdma_chan->id = i; + bdma_chan->active = false; spin_lock_init(&bdma_chan->lock); @@ -799,7 +809,6 @@ int tsi721_register_dma(struct tsi721_device *priv) tasklet_init(&bdma_chan->tasklet, tsi721_dma_tasklet, (unsigned long)bdma_chan); - tasklet_disable(&bdma_chan->tasklet); list_add_tail(&bdma_chan->dchan.device_node, &mport->dma.channels); } diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index 16a309e5c024..afca1bc24f26 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -953,6 +953,8 @@ static int machine_constraints_current(struct regulator_dev *rdev, return 0; } +static int _regulator_do_enable(struct regulator_dev *rdev); + /** * set_machine_constraints - sets regulator constraints * @rdev: regulator source @@ -1013,10 +1015,9 @@ static int set_machine_constraints(struct regulator_dev *rdev, /* If the constraints say the regulator should be on at this point * and we have control then make sure it is enabled. */ - if ((rdev->constraints->always_on || rdev->constraints->boot_on) && - ops->enable) { - ret = ops->enable(rdev); - if (ret < 0) { + if (rdev->constraints->always_on || rdev->constraints->boot_on) { + ret = _regulator_do_enable(rdev); + if (ret < 0 && ret != -EINVAL) { rdev_err(rdev, "failed to enable\n"); goto out; } @@ -1359,7 +1360,7 @@ static struct regulator *_regulator_get(struct device *dev, const char *id, goto found; /* Don't log an error when called from regulator_get_optional() */ } else if (!have_full_constraints() || exclusive) { - dev_err(dev, "dummy supplies not allowed\n"); + dev_warn(dev, "dummy supplies not allowed\n"); } mutex_unlock(®ulator_list_mutex); @@ -1907,8 +1908,6 @@ static int _regulator_do_disable(struct regulator_dev *rdev) trace_regulator_disable_complete(rdev_get_name(rdev)); - _notifier_call_chain(rdev, REGULATOR_EVENT_DISABLE, - NULL); return 0; } @@ -1932,6 +1931,8 @@ static int _regulator_disable(struct regulator_dev *rdev) rdev_err(rdev, "failed to disable\n"); return ret; } + _notifier_call_chain(rdev, REGULATOR_EVENT_DISABLE, + NULL); } rdev->use_count = 0; @@ -1984,20 +1985,16 @@ static int _regulator_force_disable(struct regulator_dev *rdev) { int ret = 0; - /* force disable */ - if (rdev->desc->ops->disable) { - /* ah well, who wants to live forever... */ - ret = rdev->desc->ops->disable(rdev); - if (ret < 0) { - rdev_err(rdev, "failed to force disable\n"); - return ret; - } - /* notify other consumers that power has been forced off */ - _notifier_call_chain(rdev, REGULATOR_EVENT_FORCE_DISABLE | - REGULATOR_EVENT_DISABLE, NULL); + ret = _regulator_do_disable(rdev); + if (ret < 0) { + rdev_err(rdev, "failed to force disable\n"); + return ret; } - return ret; + _notifier_call_chain(rdev, REGULATOR_EVENT_FORCE_DISABLE | + REGULATOR_EVENT_DISABLE, NULL); + + return 0; } /** @@ -3630,23 +3627,18 @@ int regulator_suspend_finish(void) mutex_lock(®ulator_list_mutex); list_for_each_entry(rdev, ®ulator_list, list) { - struct regulator_ops *ops = rdev->desc->ops; - mutex_lock(&rdev->mutex); - if ((rdev->use_count > 0 || rdev->constraints->always_on) && - ops->enable) { - error = ops->enable(rdev); + if (rdev->use_count > 0 || rdev->constraints->always_on) { + error = _regulator_do_enable(rdev); if (error) ret = error; } else { if (!have_full_constraints()) goto unlock; - if (!ops->disable) - goto unlock; if (!_regulator_is_enabled(rdev)) goto unlock; - error = ops->disable(rdev); + error = _regulator_do_disable(rdev); if (error) ret = error; } @@ -3820,7 +3812,7 @@ static int __init regulator_init_complete(void) ops = rdev->desc->ops; c = rdev->constraints; - if (!ops->disable || (c && c->always_on)) + if (c && c->always_on) continue; mutex_lock(&rdev->mutex); @@ -3841,7 +3833,7 @@ static int __init regulator_init_complete(void) /* We log since this may kill the system if it * goes wrong. */ rdev_info(rdev, "disabling\n"); - ret = ops->disable(rdev); + ret = _regulator_do_disable(rdev); if (ret != 0) rdev_err(rdev, "couldn't disable: %d\n", ret); } else { diff --git a/drivers/regulator/da9055-regulator.c b/drivers/regulator/da9055-regulator.c index 7f340206d329..b14ebdad5dd2 100644 --- a/drivers/regulator/da9055-regulator.c +++ b/drivers/regulator/da9055-regulator.c @@ -576,7 +576,9 @@ static int da9055_regulator_probe(struct platform_device *pdev) /* Only LDO 5 and 6 has got the over current interrupt */ if (pdev->id == DA9055_ID_LDO5 || pdev->id == DA9055_ID_LDO6) { irq = platform_get_irq_byname(pdev, "REGULATOR"); - irq = regmap_irq_get_virq(da9055->irq_data, irq); + if (irq < 0) + return irq; + ret = devm_request_threaded_irq(&pdev->dev, irq, NULL, da9055_ldo5_6_oc_irq, IRQF_TRIGGER_HIGH | diff --git a/drivers/regulator/da9063-regulator.c b/drivers/regulator/da9063-regulator.c index 56727eb745df..91e99a2c8dc1 100644 --- a/drivers/regulator/da9063-regulator.c +++ b/drivers/regulator/da9063-regulator.c @@ -1,3 +1,4 @@ + /* * Regulator driver for DA9063 PMIC series * @@ -60,7 +61,8 @@ struct da9063_regulator_info { .desc.ops = &da9063_ldo_ops, \ .desc.min_uV = (min_mV) * 1000, \ .desc.uV_step = (step_mV) * 1000, \ - .desc.n_voltages = (((max_mV) - (min_mV))/(step_mV) + 1), \ + .desc.n_voltages = (((max_mV) - (min_mV))/(step_mV) + 1 \ + + (DA9063_V##regl_name##_BIAS)), \ .desc.enable_reg = DA9063_REG_##regl_name##_CONT, \ .desc.enable_mask = DA9063_LDO_EN, \ .desc.vsel_reg = DA9063_REG_V##regl_name##_A, \ diff --git a/drivers/regulator/max14577.c b/drivers/regulator/max14577.c index b1078ba3f393..e0619526708c 100644 --- a/drivers/regulator/max14577.c +++ b/drivers/regulator/max14577.c @@ -166,12 +166,14 @@ static int max14577_regulator_dt_parse_pdata(struct platform_device *pdev) ret = of_regulator_match(&pdev->dev, np, max14577_regulator_matches, MAX14577_REG_MAX); - if (ret < 0) { + if (ret < 0) dev_err(&pdev->dev, "Error parsing regulator init data: %d\n", ret); - return ret; - } + else + ret = 0; - return 0; + of_node_put(np); + + return ret; } static inline struct regulator_init_data *match_init_data(int index) diff --git a/drivers/regulator/s5m8767.c b/drivers/regulator/s5m8767.c index d7164bb75d3e..d958dfa05125 100644 --- a/drivers/regulator/s5m8767.c +++ b/drivers/regulator/s5m8767.c @@ -535,7 +535,7 @@ static int s5m8767_pmic_dt_parse_pdata(struct platform_device *pdev, return -ENODEV; } - regulators_np = of_find_node_by_name(pmic_np, "regulators"); + regulators_np = of_get_child_by_name(pmic_np, "regulators"); if (!regulators_np) { dev_err(iodev->dev, "could not find regulators sub-node\n"); return -EINVAL; @@ -591,6 +591,8 @@ static int s5m8767_pmic_dt_parse_pdata(struct platform_device *pdev, rmode++; } + of_node_put(regulators_np); + if (of_get_property(pmic_np, "s5m8767,pmic-buck2-uses-gpio-dvs", NULL)) { pdata->buck2_gpiodvs = true; diff --git a/drivers/rtc/rtc-s3c.c b/drivers/rtc/rtc-s3c.c index 7afd373b9595..c4cde9c08f1f 100644 --- a/drivers/rtc/rtc-s3c.c +++ b/drivers/rtc/rtc-s3c.c @@ -580,10 +580,12 @@ static int s3c_rtc_suspend(struct device *dev) clk_enable(rtc_clk); /* save TICNT for anyone using periodic interrupts */ - ticnt_save = readb(s3c_rtc_base + S3C2410_TICNT); if (s3c_rtc_cpu_type == TYPE_S3C64XX) { ticnt_en_save = readw(s3c_rtc_base + S3C2410_RTCCON); ticnt_en_save &= S3C64XX_RTCCON_TICEN; + ticnt_save = readl(s3c_rtc_base + S3C2410_TICNT); + } else { + ticnt_save = readb(s3c_rtc_base + S3C2410_TICNT); } s3c_rtc_enable(pdev, 0); @@ -605,10 +607,15 @@ static int s3c_rtc_resume(struct device *dev) clk_enable(rtc_clk); s3c_rtc_enable(pdev, 1); - writeb(ticnt_save, s3c_rtc_base + S3C2410_TICNT); - if (s3c_rtc_cpu_type == TYPE_S3C64XX && ticnt_en_save) { - tmp = readw(s3c_rtc_base + S3C2410_RTCCON); - writew(tmp | ticnt_en_save, s3c_rtc_base + S3C2410_RTCCON); + if (s3c_rtc_cpu_type == TYPE_S3C64XX) { + writel(ticnt_save, s3c_rtc_base + S3C2410_TICNT); + if (ticnt_en_save) { + tmp = readw(s3c_rtc_base + S3C2410_RTCCON); + writew(tmp | ticnt_en_save, + s3c_rtc_base + S3C2410_RTCCON); + } + } else { + writeb(ticnt_save, s3c_rtc_base + S3C2410_TICNT); } if (device_may_wakeup(dev) && wake_en) { diff --git a/drivers/s390/cio/chsc.c b/drivers/s390/cio/chsc.c index f6b9188c5af5..9f0ea6cb6922 100644 --- a/drivers/s390/cio/chsc.c +++ b/drivers/s390/cio/chsc.c @@ -610,6 +610,7 @@ void chsc_chp_online(struct chp_id chpid) css_wait_for_slow_path(); for_each_subchannel_staged(__s390_process_res_acc, NULL, &link); + css_schedule_reprobe(); } } diff --git a/drivers/s390/cio/cio.c b/drivers/s390/cio/cio.c index 88e35d85d205..8ee88c4ebd83 100644 --- a/drivers/s390/cio/cio.c +++ b/drivers/s390/cio/cio.c @@ -342,8 +342,9 @@ static int cio_check_config(struct subchannel *sch, struct schib *schib) */ int cio_commit_config(struct subchannel *sch) { - struct schib schib; int ccode, retry, ret = 0; + struct schib schib; + struct irb irb; if (stsch_err(sch->schid, &schib) || !css_sch_is_valid(&schib)) return -ENODEV; @@ -367,7 +368,10 @@ int cio_commit_config(struct subchannel *sch) ret = -EAGAIN; break; case 1: /* status pending */ - return -EBUSY; + ret = -EBUSY; + if (tsch(sch->schid, &irb)) + return ret; + break; case 2: /* busy */ udelay(100); /* allow for recovery */ ret = -EBUSY; @@ -403,7 +407,6 @@ EXPORT_SYMBOL_GPL(cio_update_schib); */ int cio_enable_subchannel(struct subchannel *sch, u32 intparm) { - int retry; int ret; CIO_TRACE_EVENT(2, "ensch"); @@ -418,20 +421,14 @@ int cio_enable_subchannel(struct subchannel *sch, u32 intparm) sch->config.isc = sch->isc; sch->config.intparm = intparm; - for (retry = 0; retry < 3; retry++) { + ret = cio_commit_config(sch); + if (ret == -EIO) { + /* + * Got a program check in msch. Try without + * the concurrent sense bit the next time. + */ + sch->config.csense = 0; ret = cio_commit_config(sch); - if (ret == -EIO) { - /* - * Got a program check in msch. Try without - * the concurrent sense bit the next time. - */ - sch->config.csense = 0; - } else if (ret == -EBUSY) { - struct irb irb; - if (tsch(sch->schid, &irb) != 0) - break; - } else - break; } CIO_HEX_EVENT(2, &ret, sizeof(ret)); return ret; @@ -444,7 +441,6 @@ EXPORT_SYMBOL_GPL(cio_enable_subchannel); */ int cio_disable_subchannel(struct subchannel *sch) { - int retry; int ret; CIO_TRACE_EVENT(2, "dissch"); @@ -456,16 +452,8 @@ int cio_disable_subchannel(struct subchannel *sch) return -ENODEV; sch->config.ena = 0; + ret = cio_commit_config(sch); - for (retry = 0; retry < 3; retry++) { - ret = cio_commit_config(sch); - if (ret == -EBUSY) { - struct irb irb; - if (tsch(sch->schid, &irb) != 0) - break; - } else - break; - } CIO_HEX_EVENT(2, &ret, sizeof(ret)); return ret; } diff --git a/drivers/s390/cio/qdio.h b/drivers/s390/cio/qdio.h index 8acaae18bd11..a563e4c00590 100644 --- a/drivers/s390/cio/qdio.h +++ b/drivers/s390/cio/qdio.h @@ -359,14 +359,12 @@ static inline int multicast_outbound(struct qdio_q *q) #define need_siga_sync_out_after_pci(q) \ (unlikely(q->irq_ptr->siga_flag.sync_out_after_pci)) -#define for_each_input_queue(irq_ptr, q, i) \ - for (i = 0, q = irq_ptr->input_qs[0]; \ - i < irq_ptr->nr_input_qs; \ - q = irq_ptr->input_qs[++i]) -#define for_each_output_queue(irq_ptr, q, i) \ - for (i = 0, q = irq_ptr->output_qs[0]; \ - i < irq_ptr->nr_output_qs; \ - q = irq_ptr->output_qs[++i]) +#define for_each_input_queue(irq_ptr, q, i) \ + for (i = 0; i < irq_ptr->nr_input_qs && \ + ({ q = irq_ptr->input_qs[i]; 1; }); i++) +#define for_each_output_queue(irq_ptr, q, i) \ + for (i = 0; i < irq_ptr->nr_output_qs && \ + ({ q = irq_ptr->output_qs[i]; 1; }); i++) #define prev_buf(bufnr) \ ((bufnr + QDIO_MAX_BUFFERS_MASK) & QDIO_MAX_BUFFERS_MASK) diff --git a/drivers/s390/cio/qdio_main.c b/drivers/s390/cio/qdio_main.c index c883a085c059..77466c4faabb 100644 --- a/drivers/s390/cio/qdio_main.c +++ b/drivers/s390/cio/qdio_main.c @@ -996,7 +996,7 @@ static void qdio_int_handler_pci(struct qdio_irq *irq_ptr) } } - if (!pci_out_supported(q)) + if (!(irq_ptr->qib.ac & QIB_AC_OUTBOUND_PCI_SUPPORTED)) return; for_each_output_queue(irq_ptr, q, i) { diff --git a/drivers/s390/crypto/zcrypt_msgtype6.c b/drivers/s390/crypto/zcrypt_msgtype6.c index dc542e0a3055..0bc91e46395a 100644 --- a/drivers/s390/crypto/zcrypt_msgtype6.c +++ b/drivers/s390/crypto/zcrypt_msgtype6.c @@ -311,7 +311,7 @@ static int XCRB_msg_to_type6CPRB_msgX(struct zcrypt_device *zdev, } __packed * msg = ap_msg->message; int rcblen = CEIL4(xcRB->request_control_blk_length); - int replylen; + int replylen, req_sumlen, resp_sumlen; char *req_data = ap_msg->message + sizeof(struct type6_hdr) + rcblen; char *function_code; @@ -321,12 +321,34 @@ static int XCRB_msg_to_type6CPRB_msgX(struct zcrypt_device *zdev, xcRB->request_data_length; if (ap_msg->length > MSGTYPE06_MAX_MSG_SIZE) return -EINVAL; + + /* Overflow check + sum must be greater (or equal) than the largest operand */ + req_sumlen = CEIL4(xcRB->request_control_blk_length) + + xcRB->request_data_length; + if ((CEIL4(xcRB->request_control_blk_length) <= + xcRB->request_data_length) ? + (req_sumlen < xcRB->request_data_length) : + (req_sumlen < CEIL4(xcRB->request_control_blk_length))) { + return -EINVAL; + } + replylen = sizeof(struct type86_fmt2_msg) + CEIL4(xcRB->reply_control_blk_length) + xcRB->reply_data_length; if (replylen > MSGTYPE06_MAX_MSG_SIZE) return -EINVAL; + /* Overflow check + sum must be greater (or equal) than the largest operand */ + resp_sumlen = CEIL4(xcRB->reply_control_blk_length) + + xcRB->reply_data_length; + if ((CEIL4(xcRB->reply_control_blk_length) <= xcRB->reply_data_length) ? + (resp_sumlen < xcRB->reply_data_length) : + (resp_sumlen < CEIL4(xcRB->reply_control_blk_length))) { + return -EINVAL; + } + /* prepare type6 header */ msg->hdr = static_type6_hdrX; memcpy(msg->hdr.agent_id , &(xcRB->agent_ID), sizeof(xcRB->agent_ID)); diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index c3a83df07894..795ed61a5496 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -1660,7 +1660,6 @@ int qeth_qdio_clear_card(struct qeth_card *card, int use_halt) QDIO_FLAG_CLEANUP_USING_CLEAR); if (rc) QETH_CARD_TEXT_(card, 3, "1err%d", rc); - qdio_free(CARD_DDEV(card)); atomic_set(&card->qdio.state, QETH_QDIO_ALLOCATED); break; case QETH_QDIO_CLEANING: @@ -2605,6 +2604,7 @@ static int qeth_mpc_initialize(struct qeth_card *card) return 0; out_qdio: qeth_qdio_clear_card(card, card->info.type != QETH_CARD_TYPE_IQD); + qdio_free(CARD_DDEV(card)); return rc; } @@ -4906,9 +4906,11 @@ retry: if (retries < 3) QETH_DBF_MESSAGE(2, "%s Retrying to do IDX activates.\n", dev_name(&card->gdev->dev)); + rc = qeth_qdio_clear_card(card, card->info.type != QETH_CARD_TYPE_IQD); ccw_device_set_offline(CARD_DDEV(card)); ccw_device_set_offline(CARD_WDEV(card)); ccw_device_set_offline(CARD_RDEV(card)); + qdio_free(CARD_DDEV(card)); rc = ccw_device_set_online(CARD_RDEV(card)); if (rc) goto retriable; @@ -4918,7 +4920,6 @@ retry: rc = ccw_device_set_online(CARD_DDEV(card)); if (rc) goto retriable; - rc = qeth_qdio_clear_card(card, card->info.type != QETH_CARD_TYPE_IQD); retriable: if (rc == -ERESTARTSYS) { QETH_DBF_TEXT(SETUP, 2, "break1"); diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index 0710550093ce..908d82529ee9 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -1091,6 +1091,7 @@ out_remove: ccw_device_set_offline(CARD_DDEV(card)); ccw_device_set_offline(CARD_WDEV(card)); ccw_device_set_offline(CARD_RDEV(card)); + qdio_free(CARD_DDEV(card)); if (recover_flag == CARD_STATE_RECOVER) card->state = CARD_STATE_RECOVER; else @@ -1132,6 +1133,7 @@ static int __qeth_l2_set_offline(struct ccwgroup_device *cgdev, rc = (rc2) ? rc2 : rc3; if (rc) QETH_DBF_TEXT_(SETUP, 2, "1err%d", rc); + qdio_free(CARD_DDEV(card)); if (recover_flag == CARD_STATE_UP) card->state = CARD_STATE_RECOVER; /* let user_space know that device is offline */ @@ -1194,6 +1196,7 @@ static void qeth_l2_shutdown(struct ccwgroup_device *gdev) qeth_hw_trap(card, QETH_DIAGS_TRAP_DISARM); qeth_qdio_clear_card(card, 0); qeth_clear_qdio_buffers(card); + qdio_free(CARD_DDEV(card)); } static int qeth_l2_pm_suspend(struct ccwgroup_device *gdev) diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index 0f430424c3b8..3524d34ff694 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -3447,6 +3447,7 @@ out_remove: ccw_device_set_offline(CARD_DDEV(card)); ccw_device_set_offline(CARD_WDEV(card)); ccw_device_set_offline(CARD_RDEV(card)); + qdio_free(CARD_DDEV(card)); if (recover_flag == CARD_STATE_RECOVER) card->state = CARD_STATE_RECOVER; else @@ -3493,6 +3494,7 @@ static int __qeth_l3_set_offline(struct ccwgroup_device *cgdev, rc = (rc2) ? rc2 : rc3; if (rc) QETH_DBF_TEXT_(SETUP, 2, "1err%d", rc); + qdio_free(CARD_DDEV(card)); if (recover_flag == CARD_STATE_UP) card->state = CARD_STATE_RECOVER; /* let user_space know that device is offline */ @@ -3545,6 +3547,7 @@ static void qeth_l3_shutdown(struct ccwgroup_device *gdev) qeth_hw_trap(card, QETH_DIAGS_TRAP_DISARM); qeth_qdio_clear_card(card, 0); qeth_clear_qdio_buffers(card); + qdio_free(CARD_DDEV(card)); } static int qeth_l3_pm_suspend(struct ccwgroup_device *gdev) diff --git a/drivers/sbus/char/jsflash.c b/drivers/sbus/char/jsflash.c index 6b4678a7900a..4ccb5d869389 100644 --- a/drivers/sbus/char/jsflash.c +++ b/drivers/sbus/char/jsflash.c @@ -507,7 +507,6 @@ static int jsflash_init(void) } /* Let us be really paranoid for modifications to probing code. */ - /* extern enum sparc_cpu sparc_cpu_model; */ /* in <asm/system.h> */ if (sparc_cpu_model != sun4m) { /* We must be on sun4m because we use MMU Bypass ASI. */ return -ENXIO; diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index 9e80d61e5a3a..0cb73074c199 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -790,17 +790,32 @@ static inline int test_tgt_sess_count(struct qla_tgt *tgt) } /* Called by tcm_qla2xxx configfs code */ -void qlt_stop_phase1(struct qla_tgt *tgt) +int qlt_stop_phase1(struct qla_tgt *tgt) { struct scsi_qla_host *vha = tgt->vha; struct qla_hw_data *ha = tgt->ha; unsigned long flags; + mutex_lock(&qla_tgt_mutex); + if (!vha->fc_vport) { + struct Scsi_Host *sh = vha->host; + struct fc_host_attrs *fc_host = shost_to_fc_host(sh); + bool npiv_vports; + + spin_lock_irqsave(sh->host_lock, flags); + npiv_vports = (fc_host->npiv_vports_inuse); + spin_unlock_irqrestore(sh->host_lock, flags); + + if (npiv_vports) { + mutex_unlock(&qla_tgt_mutex); + return -EPERM; + } + } if (tgt->tgt_stop || tgt->tgt_stopped) { ql_dbg(ql_dbg_tgt_mgt, vha, 0xf04e, "Already in tgt->tgt_stop or tgt_stopped state\n"); - dump_stack(); - return; + mutex_unlock(&qla_tgt_mutex); + return -EPERM; } ql_dbg(ql_dbg_tgt, vha, 0xe003, "Stopping target for host %ld(%p)\n", @@ -815,6 +830,7 @@ void qlt_stop_phase1(struct qla_tgt *tgt) qlt_clear_tgt_db(tgt, true); spin_unlock_irqrestore(&ha->hardware_lock, flags); mutex_unlock(&vha->vha_tgt.tgt_mutex); + mutex_unlock(&qla_tgt_mutex); flush_delayed_work(&tgt->sess_del_work); @@ -841,6 +857,7 @@ void qlt_stop_phase1(struct qla_tgt *tgt) /* Wait for sessions to clear out (just in case) */ wait_event(tgt->waitQ, test_tgt_sess_count(tgt)); + return 0; } EXPORT_SYMBOL(qlt_stop_phase1); @@ -2595,8 +2612,6 @@ static int qlt_handle_cmd_for_atio(struct scsi_qla_host *vha, return -ENOMEM; } - INIT_LIST_HEAD(&cmd->cmd_list); - memcpy(&cmd->atio, atio, sizeof(*atio)); cmd->state = QLA_TGT_STATE_NEW; cmd->tgt = vha->vha_tgt.qla_tgt; @@ -3187,7 +3202,8 @@ restart: ql_dbg(ql_dbg_tgt_mgt, vha, 0xf02c, "SRR cmd %p (se_cmd %p, tag %d, op %x), " "sg_cnt=%d, offset=%d", cmd, &cmd->se_cmd, cmd->tag, - se_cmd->t_task_cdb[0], cmd->sg_cnt, cmd->offset); + se_cmd->t_task_cdb ? se_cmd->t_task_cdb[0] : 0, + cmd->sg_cnt, cmd->offset); qlt_handle_srr(vha, sctio, imm); @@ -4183,6 +4199,9 @@ int qlt_add_target(struct qla_hw_data *ha, struct scsi_qla_host *base_vha) tgt->datasegs_per_cmd = QLA_TGT_DATASEGS_PER_CMD_24XX; tgt->datasegs_per_cont = QLA_TGT_DATASEGS_PER_CONT_24XX; + if (base_vha->fc_vport) + return 0; + mutex_lock(&qla_tgt_mutex); list_add_tail(&tgt->tgt_list_entry, &qla_tgt_glist); mutex_unlock(&qla_tgt_mutex); @@ -4196,6 +4215,10 @@ int qlt_remove_target(struct qla_hw_data *ha, struct scsi_qla_host *vha) if (!vha->vha_tgt.qla_tgt) return 0; + if (vha->fc_vport) { + qlt_release(vha->vha_tgt.qla_tgt); + return 0; + } mutex_lock(&qla_tgt_mutex); list_del(&vha->vha_tgt.qla_tgt->tgt_list_entry); mutex_unlock(&qla_tgt_mutex); @@ -4267,6 +4290,12 @@ int qlt_lport_register(void *target_lport_ptr, u64 phys_wwpn, spin_unlock_irqrestore(&ha->hardware_lock, flags); continue; } + if (tgt->tgt_stop) { + pr_debug("MODE_TARGET in shutdown on qla2xxx(%d)\n", + host->host_no); + spin_unlock_irqrestore(&ha->hardware_lock, flags); + continue; + } spin_unlock_irqrestore(&ha->hardware_lock, flags); if (!scsi_host_get(host)) { @@ -4281,12 +4310,11 @@ int qlt_lport_register(void *target_lport_ptr, u64 phys_wwpn, scsi_host_put(host); continue; } - mutex_unlock(&qla_tgt_mutex); - rc = (*callback)(vha, target_lport_ptr, npiv_wwpn, npiv_wwnn); if (rc != 0) scsi_host_put(host); + mutex_unlock(&qla_tgt_mutex); return rc; } mutex_unlock(&qla_tgt_mutex); diff --git a/drivers/scsi/qla2xxx/qla_target.h b/drivers/scsi/qla2xxx/qla_target.h index 1d10eecad499..ce33d8c26406 100644 --- a/drivers/scsi/qla2xxx/qla_target.h +++ b/drivers/scsi/qla2xxx/qla_target.h @@ -855,7 +855,6 @@ struct qla_tgt_cmd { uint16_t loop_id; /* to save extra sess dereferences */ struct qla_tgt *tgt; /* to save extra sess dereferences */ struct scsi_qla_host *vha; - struct list_head cmd_list; struct atio_from_isp atio; }; @@ -1002,7 +1001,7 @@ extern void qlt_modify_vp_config(struct scsi_qla_host *, extern void qlt_probe_one_stage1(struct scsi_qla_host *, struct qla_hw_data *); extern int qlt_mem_alloc(struct qla_hw_data *); extern void qlt_mem_free(struct qla_hw_data *); -extern void qlt_stop_phase1(struct qla_tgt *); +extern int qlt_stop_phase1(struct qla_tgt *); extern void qlt_stop_phase2(struct qla_tgt *); extern irqreturn_t qla83xx_msix_atio_q(int, void *); extern void qlt_83xx_iospace_config(struct qla_hw_data *); diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c index 75a141bbe74d..788c4fe2b0c9 100644 --- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c +++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c @@ -182,20 +182,6 @@ static int tcm_qla2xxx_npiv_parse_wwn( return 0; } -static ssize_t tcm_qla2xxx_npiv_format_wwn(char *buf, size_t len, - u64 wwpn, u64 wwnn) -{ - u8 b[8], b2[8]; - - put_unaligned_be64(wwpn, b); - put_unaligned_be64(wwnn, b2); - return snprintf(buf, len, - "%2.2x:%2.2x:%2.2x:%2.2x:%2.2x:%2.2x:%2.2x:%2.2x," - "%2.2x:%2.2x:%2.2x:%2.2x:%2.2x:%2.2x:%2.2x:%2.2x", - b[0], b[1], b[2], b[3], b[4], b[5], b[6], b[7], - b2[0], b2[1], b2[2], b2[3], b2[4], b2[5], b2[6], b2[7]); -} - static char *tcm_qla2xxx_npiv_get_fabric_name(void) { return "qla2xxx_npiv"; @@ -227,15 +213,6 @@ static char *tcm_qla2xxx_get_fabric_wwn(struct se_portal_group *se_tpg) return lport->lport_naa_name; } -static char *tcm_qla2xxx_npiv_get_fabric_wwn(struct se_portal_group *se_tpg) -{ - struct tcm_qla2xxx_tpg *tpg = container_of(se_tpg, - struct tcm_qla2xxx_tpg, se_tpg); - struct tcm_qla2xxx_lport *lport = tpg->lport; - - return &lport->lport_npiv_name[0]; -} - static u16 tcm_qla2xxx_get_tag(struct se_portal_group *se_tpg) { struct tcm_qla2xxx_tpg *tpg = container_of(se_tpg, @@ -941,15 +918,41 @@ static ssize_t tcm_qla2xxx_tpg_show_enable( atomic_read(&tpg->lport_tpg_enabled)); } +static void tcm_qla2xxx_depend_tpg(struct work_struct *work) +{ + struct tcm_qla2xxx_tpg *base_tpg = container_of(work, + struct tcm_qla2xxx_tpg, tpg_base_work); + struct se_portal_group *se_tpg = &base_tpg->se_tpg; + struct scsi_qla_host *base_vha = base_tpg->lport->qla_vha; + + if (!configfs_depend_item(se_tpg->se_tpg_tfo->tf_subsys, + &se_tpg->tpg_group.cg_item)) { + atomic_set(&base_tpg->lport_tpg_enabled, 1); + qlt_enable_vha(base_vha); + } + complete(&base_tpg->tpg_base_comp); +} + +static void tcm_qla2xxx_undepend_tpg(struct work_struct *work) +{ + struct tcm_qla2xxx_tpg *base_tpg = container_of(work, + struct tcm_qla2xxx_tpg, tpg_base_work); + struct se_portal_group *se_tpg = &base_tpg->se_tpg; + struct scsi_qla_host *base_vha = base_tpg->lport->qla_vha; + + if (!qlt_stop_phase1(base_vha->vha_tgt.qla_tgt)) { + atomic_set(&base_tpg->lport_tpg_enabled, 0); + configfs_undepend_item(se_tpg->se_tpg_tfo->tf_subsys, + &se_tpg->tpg_group.cg_item); + } + complete(&base_tpg->tpg_base_comp); +} + static ssize_t tcm_qla2xxx_tpg_store_enable( struct se_portal_group *se_tpg, const char *page, size_t count) { - struct se_wwn *se_wwn = se_tpg->se_tpg_wwn; - struct tcm_qla2xxx_lport *lport = container_of(se_wwn, - struct tcm_qla2xxx_lport, lport_wwn); - struct scsi_qla_host *vha = lport->qla_vha; struct tcm_qla2xxx_tpg *tpg = container_of(se_tpg, struct tcm_qla2xxx_tpg, se_tpg); unsigned long op; @@ -964,19 +967,28 @@ static ssize_t tcm_qla2xxx_tpg_store_enable( pr_err("Illegal value for tpg_enable: %lu\n", op); return -EINVAL; } - if (op) { - atomic_set(&tpg->lport_tpg_enabled, 1); - qlt_enable_vha(vha); + if (atomic_read(&tpg->lport_tpg_enabled)) + return -EEXIST; + + INIT_WORK(&tpg->tpg_base_work, tcm_qla2xxx_depend_tpg); } else { - if (!vha->vha_tgt.qla_tgt) { - pr_err("struct qla_hw_data *vha->vha_tgt.qla_tgt is NULL\n"); - return -ENODEV; - } - atomic_set(&tpg->lport_tpg_enabled, 0); - qlt_stop_phase1(vha->vha_tgt.qla_tgt); + if (!atomic_read(&tpg->lport_tpg_enabled)) + return count; + + INIT_WORK(&tpg->tpg_base_work, tcm_qla2xxx_undepend_tpg); } + init_completion(&tpg->tpg_base_comp); + schedule_work(&tpg->tpg_base_work); + wait_for_completion(&tpg->tpg_base_comp); + if (op) { + if (!atomic_read(&tpg->lport_tpg_enabled)) + return -ENODEV; + } else { + if (atomic_read(&tpg->lport_tpg_enabled)) + return -EPERM; + } return count; } @@ -1053,11 +1065,64 @@ static void tcm_qla2xxx_drop_tpg(struct se_portal_group *se_tpg) /* * Clear local TPG=1 pointer for non NPIV mode. */ - lport->tpg_1 = NULL; - + lport->tpg_1 = NULL; kfree(tpg); } +static ssize_t tcm_qla2xxx_npiv_tpg_show_enable( + struct se_portal_group *se_tpg, + char *page) +{ + return tcm_qla2xxx_tpg_show_enable(se_tpg, page); +} + +static ssize_t tcm_qla2xxx_npiv_tpg_store_enable( + struct se_portal_group *se_tpg, + const char *page, + size_t count) +{ + struct se_wwn *se_wwn = se_tpg->se_tpg_wwn; + struct tcm_qla2xxx_lport *lport = container_of(se_wwn, + struct tcm_qla2xxx_lport, lport_wwn); + struct scsi_qla_host *vha = lport->qla_vha; + struct tcm_qla2xxx_tpg *tpg = container_of(se_tpg, + struct tcm_qla2xxx_tpg, se_tpg); + unsigned long op; + int rc; + + rc = kstrtoul(page, 0, &op); + if (rc < 0) { + pr_err("kstrtoul() returned %d\n", rc); + return -EINVAL; + } + if ((op != 1) && (op != 0)) { + pr_err("Illegal value for tpg_enable: %lu\n", op); + return -EINVAL; + } + if (op) { + if (atomic_read(&tpg->lport_tpg_enabled)) + return -EEXIST; + + atomic_set(&tpg->lport_tpg_enabled, 1); + qlt_enable_vha(vha); + } else { + if (!atomic_read(&tpg->lport_tpg_enabled)) + return count; + + atomic_set(&tpg->lport_tpg_enabled, 0); + qlt_stop_phase1(vha->vha_tgt.qla_tgt); + } + + return count; +} + +TF_TPG_BASE_ATTR(tcm_qla2xxx_npiv, enable, S_IRUGO | S_IWUSR); + +static struct configfs_attribute *tcm_qla2xxx_npiv_tpg_attrs[] = { + &tcm_qla2xxx_npiv_tpg_enable.attr, + NULL, +}; + static struct se_portal_group *tcm_qla2xxx_npiv_make_tpg( struct se_wwn *wwn, struct config_group *group, @@ -1650,6 +1715,9 @@ static int tcm_qla2xxx_lport_register_npiv_cb(struct scsi_qla_host *base_vha, struct scsi_qla_host *npiv_vha; struct tcm_qla2xxx_lport *lport = (struct tcm_qla2xxx_lport *)target_lport_ptr; + struct tcm_qla2xxx_lport *base_lport = + (struct tcm_qla2xxx_lport *)base_vha->vha_tgt.target_lport_ptr; + struct tcm_qla2xxx_tpg *base_tpg; struct fc_vport_identifiers vport_id; if (!qla_tgt_mode_enabled(base_vha)) { @@ -1657,6 +1725,13 @@ static int tcm_qla2xxx_lport_register_npiv_cb(struct scsi_qla_host *base_vha, return -EPERM; } + if (!base_lport || !base_lport->tpg_1 || + !atomic_read(&base_lport->tpg_1->lport_tpg_enabled)) { + pr_err("qla2xxx base_lport or tpg_1 not available\n"); + return -EPERM; + } + base_tpg = base_lport->tpg_1; + memset(&vport_id, 0, sizeof(vport_id)); vport_id.port_name = npiv_wwpn; vport_id.node_name = npiv_wwnn; @@ -1675,7 +1750,6 @@ static int tcm_qla2xxx_lport_register_npiv_cb(struct scsi_qla_host *base_vha, npiv_vha = (struct scsi_qla_host *)vport->dd_data; npiv_vha->vha_tgt.target_lport_ptr = target_lport_ptr; lport->qla_vha = npiv_vha; - scsi_host_get(npiv_vha->host); return 0; } @@ -1714,8 +1788,6 @@ static struct se_wwn *tcm_qla2xxx_npiv_make_lport( } lport->lport_npiv_wwpn = npiv_wwpn; lport->lport_npiv_wwnn = npiv_wwnn; - tcm_qla2xxx_npiv_format_wwn(&lport->lport_npiv_name[0], - TCM_QLA2XXX_NAMELEN, npiv_wwpn, npiv_wwnn); sprintf(lport->lport_naa_name, "naa.%016llx", (unsigned long long) npiv_wwpn); ret = tcm_qla2xxx_init_lport(lport); @@ -1824,7 +1896,7 @@ static struct target_core_fabric_ops tcm_qla2xxx_ops = { static struct target_core_fabric_ops tcm_qla2xxx_npiv_ops = { .get_fabric_name = tcm_qla2xxx_npiv_get_fabric_name, .get_fabric_proto_ident = tcm_qla2xxx_get_fabric_proto_ident, - .tpg_get_wwn = tcm_qla2xxx_npiv_get_fabric_wwn, + .tpg_get_wwn = tcm_qla2xxx_get_fabric_wwn, .tpg_get_tag = tcm_qla2xxx_get_tag, .tpg_get_default_depth = tcm_qla2xxx_get_default_depth, .tpg_get_pr_transport_id = tcm_qla2xxx_get_pr_transport_id, @@ -1935,7 +2007,7 @@ static int tcm_qla2xxx_register_configfs(void) */ npiv_fabric->tf_cit_tmpl.tfc_wwn_cit.ct_attrs = tcm_qla2xxx_wwn_attrs; npiv_fabric->tf_cit_tmpl.tfc_tpg_base_cit.ct_attrs = - tcm_qla2xxx_tpg_attrs; + tcm_qla2xxx_npiv_tpg_attrs; npiv_fabric->tf_cit_tmpl.tfc_tpg_attrib_cit.ct_attrs = NULL; npiv_fabric->tf_cit_tmpl.tfc_tpg_param_cit.ct_attrs = NULL; npiv_fabric->tf_cit_tmpl.tfc_tpg_np_base_cit.ct_attrs = NULL; diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.h b/drivers/scsi/qla2xxx/tcm_qla2xxx.h index 275d8b9a7a34..33aaac8c7d59 100644 --- a/drivers/scsi/qla2xxx/tcm_qla2xxx.h +++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.h @@ -4,8 +4,6 @@ #define TCM_QLA2XXX_VERSION "v0.1" /* length of ASCII WWPNs including pad */ #define TCM_QLA2XXX_NAMELEN 32 -/* lenth of ASCII NPIV 'WWPN+WWNN' including pad */ -#define TCM_QLA2XXX_NPIV_NAMELEN 66 #include "qla_target.h" @@ -43,6 +41,9 @@ struct tcm_qla2xxx_tpg { struct tcm_qla2xxx_tpg_attrib tpg_attrib; /* Returned by tcm_qla2xxx_make_tpg() */ struct se_portal_group se_tpg; + /* Items for dealing with configfs_depend_item */ + struct completion tpg_base_comp; + struct work_struct tpg_base_work; }; struct tcm_qla2xxx_fc_loopid { @@ -62,8 +63,6 @@ struct tcm_qla2xxx_lport { char lport_name[TCM_QLA2XXX_NAMELEN]; /* ASCII formatted naa WWPN for VPD page 83 etc */ char lport_naa_name[TCM_QLA2XXX_NAMELEN]; - /* ASCII formatted WWPN+WWNN for NPIV FC Target Lport */ - char lport_npiv_name[TCM_QLA2XXX_NPIV_NAMELEN]; /* map for fc_port pointers in 24-bit FC Port ID space */ struct btree_head32 lport_fcport_map; /* vmalloc-ed memory for fc_port pointers for 16-bit FC loop ID */ diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 7bd7f0d5f050..62ec84b42e31 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -1684,7 +1684,7 @@ u64 scsi_calculate_bounce_limit(struct Scsi_Host *shost) host_dev = scsi_get_device(shost); if (host_dev && host_dev->dma_mask) - bounce_limit = dma_max_pfn(host_dev) << PAGE_SHIFT; + bounce_limit = (u64)dma_max_pfn(host_dev) << PAGE_SHIFT; return bounce_limit; } diff --git a/drivers/spi/Kconfig b/drivers/spi/Kconfig index ba9310bc9acb..581ee2a8856b 100644 --- a/drivers/spi/Kconfig +++ b/drivers/spi/Kconfig @@ -376,10 +376,10 @@ config SPI_PXA2XX_PCI def_tristate SPI_PXA2XX && PCI config SPI_RSPI - tristate "Renesas RSPI controller" + tristate "Renesas RSPI/QSPI controller" depends on (SUPERH && SH_DMAE_BASE) || ARCH_SHMOBILE help - SPI driver for Renesas RSPI blocks. + SPI driver for Renesas RSPI and QSPI blocks. config SPI_S3C24XX tristate "Samsung S3C24XX series SPI" diff --git a/drivers/spi/spi-nuc900.c b/drivers/spi/spi-nuc900.c index 50406306bc20..bae97ffec4b9 100644 --- a/drivers/spi/spi-nuc900.c +++ b/drivers/spi/spi-nuc900.c @@ -361,6 +361,8 @@ static int nuc900_spi_probe(struct platform_device *pdev) init_completion(&hw->done); master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH; + if (hw->pdata->lsb) + master->mode_bits |= SPI_LSB_FIRST; master->num_chipselect = hw->pdata->num_cs; master->bus_num = hw->pdata->bus_num; hw->bitbang.master = hw->master; diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index 23756b0f9036..d0b28bba38be 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -755,9 +755,7 @@ static void spi_pump_messages(struct kthread_work *work) ret = master->transfer_one_message(master, master->cur_msg); if (ret) { dev_err(&master->dev, - "failed to transfer one message from queue: %d\n", ret); - master->cur_msg->status = ret; - spi_finalize_current_message(master); + "failed to transfer one message from queue\n"); return; } } diff --git a/drivers/staging/android/ashmem.c b/drivers/staging/android/ashmem.c index 23948f167012..713a97226787 100644 --- a/drivers/staging/android/ashmem.c +++ b/drivers/staging/android/ashmem.c @@ -295,21 +295,29 @@ static ssize_t ashmem_read(struct file *file, char __user *buf, /* If size is not set, or set to 0, always return EOF. */ if (asma->size == 0) - goto out; + goto out_unlock; if (!asma->file) { ret = -EBADF; - goto out; + goto out_unlock; } - ret = asma->file->f_op->read(asma->file, buf, len, pos); - if (ret < 0) - goto out; + mutex_unlock(&ashmem_mutex); - /** Update backing file pos, since f_ops->read() doesn't */ - asma->file->f_pos = *pos; + /* + * asma and asma->file are used outside the lock here. We assume + * once asma->file is set it will never be changed, and will not + * be destroyed until all references to the file are dropped and + * ashmem_release is called. + */ + ret = asma->file->f_op->read(asma->file, buf, len, pos); + if (ret >= 0) { + /** Update backing file pos, since f_ops->read() doesn't */ + asma->file->f_pos = *pos; + } + return ret; -out: +out_unlock: mutex_unlock(&ashmem_mutex); return ret; } @@ -498,6 +506,7 @@ out: static int set_name(struct ashmem_area *asma, void __user *name) { + int len; int ret = 0; char local_name[ASHMEM_NAME_LEN]; @@ -510,21 +519,19 @@ static int set_name(struct ashmem_area *asma, void __user *name) * variable that does not need protection and later copy the local * variable to the structure member with lock held. */ - if (copy_from_user(local_name, name, ASHMEM_NAME_LEN)) - return -EFAULT; - + len = strncpy_from_user(local_name, name, ASHMEM_NAME_LEN); + if (len < 0) + return len; + if (len == ASHMEM_NAME_LEN) + local_name[ASHMEM_NAME_LEN - 1] = '\0'; mutex_lock(&ashmem_mutex); /* cannot change an existing mapping's name */ - if (unlikely(asma->file)) { + if (unlikely(asma->file)) ret = -EINVAL; - goto out; - } - memcpy(asma->name + ASHMEM_NAME_PREFIX_LEN, - local_name, ASHMEM_NAME_LEN); - asma->name[ASHMEM_FULL_NAME_LEN-1] = '\0'; -out: - mutex_unlock(&ashmem_mutex); + else + strcpy(asma->name + ASHMEM_NAME_PREFIX_LEN, local_name); + mutex_unlock(&ashmem_mutex); return ret; } diff --git a/drivers/staging/android/binder.c b/drivers/staging/android/binder.c index eaec1dab7fe4..1432d956769c 100644 --- a/drivers/staging/android/binder.c +++ b/drivers/staging/android/binder.c @@ -2904,7 +2904,7 @@ static int binder_node_release(struct binder_node *node, int refs) refs++; if (!ref->death) - goto out; + continue; death++; @@ -2917,7 +2917,6 @@ static int binder_node_release(struct binder_node *node, int refs) BUG(); } -out: binder_debug(BINDER_DEBUG_DEAD_BINDER, "node %d now dead, refs %d, death %d\n", node->debug_id, refs, death); diff --git a/drivers/staging/android/ion/compat_ion.c b/drivers/staging/android/ion/compat_ion.c index af6cd370b30f..ee3a7380e53b 100644 --- a/drivers/staging/android/ion/compat_ion.c +++ b/drivers/staging/android/ion/compat_ion.c @@ -35,9 +35,14 @@ struct compat_ion_custom_data { compat_ulong_t arg; }; +struct compat_ion_handle_data { + compat_int_t handle; +}; + #define COMPAT_ION_IOC_ALLOC _IOWR(ION_IOC_MAGIC, 0, \ struct compat_ion_allocation_data) -#define COMPAT_ION_IOC_FREE _IOWR(ION_IOC_MAGIC, 1, struct ion_handle_data) +#define COMPAT_ION_IOC_FREE _IOWR(ION_IOC_MAGIC, 1, \ + struct compat_ion_handle_data) #define COMPAT_ION_IOC_CUSTOM _IOWR(ION_IOC_MAGIC, 6, \ struct compat_ion_custom_data) @@ -64,6 +69,19 @@ static int compat_get_ion_allocation_data( return err; } +static int compat_get_ion_handle_data( + struct compat_ion_handle_data __user *data32, + struct ion_handle_data __user *data) +{ + compat_int_t i; + int err; + + err = get_user(i, &data32->handle); + err |= put_user(i, &data->handle); + + return err; +} + static int compat_put_ion_allocation_data( struct compat_ion_allocation_data __user *data32, struct ion_allocation_data __user *data) @@ -132,8 +150,8 @@ long compat_ion_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) } case COMPAT_ION_IOC_FREE: { - struct compat_ion_allocation_data __user *data32; - struct ion_allocation_data __user *data; + struct compat_ion_handle_data __user *data32; + struct ion_handle_data __user *data; int err; data32 = compat_ptr(arg); @@ -141,7 +159,7 @@ long compat_ion_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) if (data == NULL) return -EFAULT; - err = compat_get_ion_allocation_data(data32, data); + err = compat_get_ion_handle_data(data32, data); if (err) return err; diff --git a/drivers/staging/android/ion/ion_dummy_driver.c b/drivers/staging/android/ion/ion_dummy_driver.c index 55b2002753f2..01cdc8aee898 100644 --- a/drivers/staging/android/ion/ion_dummy_driver.c +++ b/drivers/staging/android/ion/ion_dummy_driver.c @@ -17,9 +17,11 @@ #include <linux/err.h> #include <linux/platform_device.h> #include <linux/slab.h> +#include <linux/init.h> #include <linux/bootmem.h> #include <linux/memblock.h> #include <linux/sizes.h> +#include <linux/io.h> #include "ion.h" #include "ion_priv.h" @@ -57,7 +59,7 @@ struct ion_platform_heap dummy_heaps[] = { }; struct ion_platform_data dummy_ion_pdata = { - .nr = 4, + .nr = ARRAY_SIZE(dummy_heaps), .heaps = dummy_heaps, }; @@ -69,7 +71,7 @@ static int __init ion_dummy_init(void) heaps = kzalloc(sizeof(struct ion_heap *) * dummy_ion_pdata.nr, GFP_KERNEL); if (!heaps) - return PTR_ERR(heaps); + return -ENOMEM; /* Allocate a dummy carveout heap */ @@ -128,6 +130,7 @@ err: } return err; } +device_initcall(ion_dummy_init); static void __exit ion_dummy_exit(void) { @@ -152,7 +155,4 @@ static void __exit ion_dummy_exit(void) return; } - -module_init(ion_dummy_init); -module_exit(ion_dummy_exit); - +__exitcall(ion_dummy_exit); diff --git a/drivers/staging/android/ion/ion_heap.c b/drivers/staging/android/ion/ion_heap.c index 296c74f98dc0..37e64d51394c 100644 --- a/drivers/staging/android/ion/ion_heap.c +++ b/drivers/staging/android/ion/ion_heap.c @@ -243,12 +243,12 @@ int ion_heap_init_deferred_free(struct ion_heap *heap) init_waitqueue_head(&heap->waitqueue); heap->task = kthread_run(ion_heap_deferred_free, heap, "%s", heap->name); - sched_setscheduler(heap->task, SCHED_IDLE, ¶m); if (IS_ERR(heap->task)) { pr_err("%s: creating thread for deferred free failed\n", __func__); return PTR_RET(heap->task); } + sched_setscheduler(heap->task, SCHED_IDLE, ¶m); return 0; } diff --git a/drivers/staging/android/ion/ion_priv.h b/drivers/staging/android/ion/ion_priv.h index d98673981cc4..fc2e4fccf69d 100644 --- a/drivers/staging/android/ion/ion_priv.h +++ b/drivers/staging/android/ion/ion_priv.h @@ -17,6 +17,7 @@ #ifndef _ION_PRIV_H #define _ION_PRIV_H +#include <linux/device.h> #include <linux/dma-direction.h> #include <linux/kref.h> #include <linux/mm_types.h> diff --git a/drivers/staging/android/ion/ion_system_heap.c b/drivers/staging/android/ion/ion_system_heap.c index 7f0729130d65..9849f3963e75 100644 --- a/drivers/staging/android/ion/ion_system_heap.c +++ b/drivers/staging/android/ion/ion_system_heap.c @@ -124,6 +124,7 @@ static struct page_info *alloc_largest_available(struct ion_system_heap *heap, info->page = page; info->order = orders[i]; + INIT_LIST_HEAD(&info->list); return info; } kfree(info); @@ -145,12 +146,15 @@ static int ion_system_heap_allocate(struct ion_heap *heap, struct list_head pages; struct page_info *info, *tmp_info; int i = 0; - long size_remaining = PAGE_ALIGN(size); + unsigned long size_remaining = PAGE_ALIGN(size); unsigned int max_order = orders[0]; if (align > PAGE_SIZE) return -EINVAL; + if (size / PAGE_SIZE > totalram_pages / 2) + return -ENOMEM; + INIT_LIST_HEAD(&pages); while (size_remaining > 0) { info = alloc_largest_available(sys_heap, buffer, size_remaining, diff --git a/drivers/staging/android/sw_sync.h b/drivers/staging/android/sw_sync.h index 585040be5f18..5aaf71d6974b 100644 --- a/drivers/staging/android/sw_sync.h +++ b/drivers/staging/android/sw_sync.h @@ -35,10 +35,27 @@ struct sw_sync_pt { u32 value; }; +#if IS_ENABLED(CONFIG_SW_SYNC) struct sw_sync_timeline *sw_sync_timeline_create(const char *name); void sw_sync_timeline_inc(struct sw_sync_timeline *obj, u32 inc); struct sync_pt *sw_sync_pt_create(struct sw_sync_timeline *obj, u32 value); +#else +static inline struct sw_sync_timeline *sw_sync_timeline_create(const char *name) +{ + return NULL; +} + +static inline void sw_sync_timeline_inc(struct sw_sync_timeline *obj, u32 inc) +{ +} + +static inline struct sync_pt *sw_sync_pt_create(struct sw_sync_timeline *obj, + u32 value) +{ + return NULL; +} +#endif /* IS_ENABLED(CONFIG_SW_SYNC) */ #endif /* __KERNEL __ */ diff --git a/drivers/staging/android/sync.c b/drivers/staging/android/sync.c index 38e5d3b5ed9b..3d05f662110b 100644 --- a/drivers/staging/android/sync.c +++ b/drivers/staging/android/sync.c @@ -79,27 +79,27 @@ static void sync_timeline_free(struct kref *kref) container_of(kref, struct sync_timeline, kref); unsigned long flags; - if (obj->ops->release_obj) - obj->ops->release_obj(obj); - spin_lock_irqsave(&sync_timeline_list_lock, flags); list_del(&obj->sync_timeline_list); spin_unlock_irqrestore(&sync_timeline_list_lock, flags); + if (obj->ops->release_obj) + obj->ops->release_obj(obj); + kfree(obj); } void sync_timeline_destroy(struct sync_timeline *obj) { obj->destroyed = true; + smp_wmb(); /* - * If this is not the last reference, signal any children - * that their parent is going away. + * signal any children that their parent is going away. */ + sync_timeline_signal(obj); - if (!kref_put(&obj->kref, sync_timeline_free)) - sync_timeline_signal(obj); + kref_put(&obj->kref, sync_timeline_free); } EXPORT_SYMBOL(sync_timeline_destroy); diff --git a/drivers/staging/bcm/Bcmnet.c b/drivers/staging/bcm/Bcmnet.c index 8dfdd2732bdc..95a2358267ba 100644 --- a/drivers/staging/bcm/Bcmnet.c +++ b/drivers/staging/bcm/Bcmnet.c @@ -40,7 +40,7 @@ static INT bcm_close(struct net_device *dev) } static u16 bcm_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv) + void *accel_priv, select_queue_fallback_t fallback) { return ClassifyPacket(netdev_priv(dev), skb); } diff --git a/drivers/staging/comedi/drivers.c b/drivers/staging/comedi/drivers.c index 246080316c90..5b15033a94bf 100644 --- a/drivers/staging/comedi/drivers.c +++ b/drivers/staging/comedi/drivers.c @@ -616,8 +616,6 @@ int comedi_auto_config(struct device *hardware_device, ret = driver->auto_attach(dev, context); if (ret >= 0) ret = comedi_device_postconfig(dev); - if (ret < 0) - comedi_device_detach(dev); mutex_unlock(&dev->mutex); if (ret < 0) { diff --git a/drivers/staging/comedi/drivers/adv_pci1710.c b/drivers/staging/comedi/drivers/adv_pci1710.c index 593676cf706a..d9ad2c0fdda2 100644 --- a/drivers/staging/comedi/drivers/adv_pci1710.c +++ b/drivers/staging/comedi/drivers/adv_pci1710.c @@ -494,6 +494,7 @@ static int pci171x_insn_write_ao(struct comedi_device *dev, struct comedi_insn *insn, unsigned int *data) { struct pci1710_private *devpriv = dev->private; + unsigned int val; int n, chan, range, ofs; chan = CR_CHAN(insn->chanspec); @@ -509,11 +510,14 @@ static int pci171x_insn_write_ao(struct comedi_device *dev, outw(devpriv->da_ranges, dev->iobase + PCI171x_DAREF); ofs = PCI171x_DA1; } + val = devpriv->ao_data[chan]; - for (n = 0; n < insn->n; n++) - outw(data[n], dev->iobase + ofs); + for (n = 0; n < insn->n; n++) { + val = data[n]; + outw(val, dev->iobase + ofs); + } - devpriv->ao_data[chan] = data[n]; + devpriv->ao_data[chan] = val; return n; @@ -679,6 +683,7 @@ static int pci1720_insn_write_ao(struct comedi_device *dev, struct comedi_insn *insn, unsigned int *data) { struct pci1710_private *devpriv = dev->private; + unsigned int val; int n, rangereg, chan; chan = CR_CHAN(insn->chanspec); @@ -688,13 +693,15 @@ static int pci1720_insn_write_ao(struct comedi_device *dev, outb(rangereg, dev->iobase + PCI1720_RANGE); devpriv->da_ranges = rangereg; } + val = devpriv->ao_data[chan]; for (n = 0; n < insn->n; n++) { - outw(data[n], dev->iobase + PCI1720_DA0 + (chan << 1)); + val = data[n]; + outw(val, dev->iobase + PCI1720_DA0 + (chan << 1)); outb(0, dev->iobase + PCI1720_SYNCOUT); /* update outputs */ } - devpriv->ao_data[chan] = data[n]; + devpriv->ao_data[chan] = val; return n; } diff --git a/drivers/staging/comedi/drivers/usbduxsigma.c b/drivers/staging/comedi/drivers/usbduxsigma.c index 3beeb1254152..88c60b6020c4 100644 --- a/drivers/staging/comedi/drivers/usbduxsigma.c +++ b/drivers/staging/comedi/drivers/usbduxsigma.c @@ -48,6 +48,7 @@ #include <linux/usb.h> #include <linux/fcntl.h> #include <linux/compiler.h> +#include <asm/unaligned.h> #include "comedi_fc.h" #include "../comedidev.h" @@ -792,7 +793,8 @@ static int usbduxsigma_ai_insn_read(struct comedi_device *dev, } /* 32 bits big endian from the A/D converter */ - val = be32_to_cpu(*((uint32_t *)((devpriv->insn_buf) + 1))); + val = be32_to_cpu(get_unaligned((uint32_t + *)(devpriv->insn_buf + 1))); val &= 0x00ffffff; /* strip status byte */ val ^= 0x00800000; /* convert to unsigned */ @@ -1357,7 +1359,7 @@ static int usbduxsigma_getstatusinfo(struct comedi_device *dev, int chan) return ret; /* 32 bits big endian from the A/D converter */ - val = be32_to_cpu(*((uint32_t *)((devpriv->insn_buf)+1))); + val = be32_to_cpu(get_unaligned((uint32_t *)(devpriv->insn_buf + 1))); val &= 0x00ffffff; /* strip status byte */ val ^= 0x00800000; /* convert to unsigned */ diff --git a/drivers/staging/dgrp/dgrp_net_ops.c b/drivers/staging/dgrp/dgrp_net_ops.c index 1f61b89eca44..33ac7fb88cbd 100644 --- a/drivers/staging/dgrp/dgrp_net_ops.c +++ b/drivers/staging/dgrp/dgrp_net_ops.c @@ -2232,177 +2232,6 @@ done: return rtn; } -/* - * Common Packet Handling code - */ - -static void handle_data_in_packet(struct nd_struct *nd, struct ch_struct *ch, - long dlen, long plen, int n1, u8 *dbuf) -{ - char *error; - long n; - long remain; - u8 *buf; - u8 *b; - - remain = nd->nd_remain; - nd->nd_tx_work = 1; - - /* - * Otherwise data should appear only when we are - * in the CS_READY state. - */ - - if (ch->ch_state < CS_READY) { - error = "Data received before RWIN established"; - nd->nd_remain = 0; - nd->nd_state = NS_SEND_ERROR; - nd->nd_error = error; - } - - /* - * Assure that the data received is within the - * allowable window. - */ - - n = (ch->ch_s_rwin - ch->ch_s_rin) & 0xffff; - - if (dlen > n) { - error = "Receive data overrun"; - nd->nd_remain = 0; - nd->nd_state = NS_SEND_ERROR; - nd->nd_error = error; - } - - /* - * If we received 3 or less characters, - * assume it is a human typing, and set RTIME - * to 10 milliseconds. - * - * If we receive 10 or more characters, - * assume its not a human typing, and set RTIME - * to 100 milliseconds. - */ - - if (ch->ch_edelay != DGRP_RTIME) { - if (ch->ch_rtime != ch->ch_edelay) { - ch->ch_rtime = ch->ch_edelay; - ch->ch_flag |= CH_PARAM; - } - } else if (dlen <= 3) { - if (ch->ch_rtime != 10) { - ch->ch_rtime = 10; - ch->ch_flag |= CH_PARAM; - } - } else { - if (ch->ch_rtime != DGRP_RTIME) { - ch->ch_rtime = DGRP_RTIME; - ch->ch_flag |= CH_PARAM; - } - } - - /* - * If a portion of the packet is outside the - * buffer, shorten the effective length of the - * data packet to be the amount of data received. - */ - - if (remain < plen) - dlen -= plen - remain; - - /* - * Detect if receive flush is now complete. - */ - - if ((ch->ch_flag & CH_RX_FLUSH) != 0 && - ((ch->ch_flush_seq - nd->nd_seq_out) & SEQ_MASK) >= - ((nd->nd_seq_in - nd->nd_seq_out) & SEQ_MASK)) { - ch->ch_flag &= ~CH_RX_FLUSH; - } - - /* - * If we are ready to receive, move the data into - * the receive buffer. - */ - - ch->ch_s_rin = (ch->ch_s_rin + dlen) & 0xffff; - - if (ch->ch_state == CS_READY && - (ch->ch_tun.un_open_count != 0) && - (ch->ch_tun.un_flag & UN_CLOSING) == 0 && - (ch->ch_cflag & CF_CREAD) != 0 && - (ch->ch_flag & (CH_BAUD0 | CH_RX_FLUSH)) == 0 && - (ch->ch_send & RR_RX_FLUSH) == 0) { - - if (ch->ch_rin + dlen >= RBUF_MAX) { - n = RBUF_MAX - ch->ch_rin; - - memcpy(ch->ch_rbuf + ch->ch_rin, dbuf, n); - - ch->ch_rin = 0; - dbuf += n; - dlen -= n; - } - - memcpy(ch->ch_rbuf + ch->ch_rin, dbuf, dlen); - - ch->ch_rin += dlen; - - - /* - * If we are not in fastcook mode, or - * if there is a fastcook thread - * waiting for data, send the data to - * the line discipline. - */ - - if ((ch->ch_flag & CH_FAST_READ) == 0 || - ch->ch_inwait != 0) { - dgrp_input(ch); - } - - /* - * If there is a read thread waiting - * in select, and we are in fastcook - * mode, wake him up. - */ - - if (waitqueue_active(&ch->ch_tun.un_tty->read_wait) && - (ch->ch_flag & CH_FAST_READ) != 0) - wake_up_interruptible(&ch->ch_tun.un_tty->read_wait); - - /* - * Wake any thread waiting in the - * fastcook loop. - */ - - if ((ch->ch_flag & CH_INPUT) != 0) { - ch->ch_flag &= ~CH_INPUT; - wake_up_interruptible(&ch->ch_flag_wait); - } - } - - /* - * Fabricate and insert a data packet header to - * preced the remaining data when it comes in. - */ - - if (remain < plen) { - dlen = plen - remain; - b = buf; - - b[0] = 0x90 + n1; - put_unaligned_be16(dlen, b + 1); - - remain = 3; - if (remain > 0 && b != buf) - memcpy(buf, b, remain); - - nd->nd_remain = remain; - return; - } -} - /** * dgrp_receive() -- decode data packets received from the remote PortServer. * @nd: pointer to a node structure @@ -2477,8 +2306,7 @@ static void dgrp_receive(struct nd_struct *nd) plen = dlen + 1; dbuf = b + 1; - handle_data_in_packet(nd, ch, dlen, plen, n1, dbuf); - break; + goto data; /* * Process 2-byte header data packet. @@ -2492,8 +2320,7 @@ static void dgrp_receive(struct nd_struct *nd) plen = dlen + 2; dbuf = b + 2; - handle_data_in_packet(nd, ch, dlen, plen, n1, dbuf); - break; + goto data; /* * Process 3-byte header data packet. @@ -2508,6 +2335,159 @@ static void dgrp_receive(struct nd_struct *nd) dbuf = b + 3; + /* + * Common packet handling code. + */ + +data: + nd->nd_tx_work = 1; + + /* + * Otherwise data should appear only when we are + * in the CS_READY state. + */ + + if (ch->ch_state < CS_READY) { + error = "Data received before RWIN established"; + goto prot_error; + } + + /* + * Assure that the data received is within the + * allowable window. + */ + + n = (ch->ch_s_rwin - ch->ch_s_rin) & 0xffff; + + if (dlen > n) { + error = "Receive data overrun"; + goto prot_error; + } + + /* + * If we received 3 or less characters, + * assume it is a human typing, and set RTIME + * to 10 milliseconds. + * + * If we receive 10 or more characters, + * assume its not a human typing, and set RTIME + * to 100 milliseconds. + */ + + if (ch->ch_edelay != DGRP_RTIME) { + if (ch->ch_rtime != ch->ch_edelay) { + ch->ch_rtime = ch->ch_edelay; + ch->ch_flag |= CH_PARAM; + } + } else if (dlen <= 3) { + if (ch->ch_rtime != 10) { + ch->ch_rtime = 10; + ch->ch_flag |= CH_PARAM; + } + } else { + if (ch->ch_rtime != DGRP_RTIME) { + ch->ch_rtime = DGRP_RTIME; + ch->ch_flag |= CH_PARAM; + } + } + + /* + * If a portion of the packet is outside the + * buffer, shorten the effective length of the + * data packet to be the amount of data received. + */ + + if (remain < plen) + dlen -= plen - remain; + + /* + * Detect if receive flush is now complete. + */ + + if ((ch->ch_flag & CH_RX_FLUSH) != 0 && + ((ch->ch_flush_seq - nd->nd_seq_out) & SEQ_MASK) >= + ((nd->nd_seq_in - nd->nd_seq_out) & SEQ_MASK)) { + ch->ch_flag &= ~CH_RX_FLUSH; + } + + /* + * If we are ready to receive, move the data into + * the receive buffer. + */ + + ch->ch_s_rin = (ch->ch_s_rin + dlen) & 0xffff; + + if (ch->ch_state == CS_READY && + (ch->ch_tun.un_open_count != 0) && + (ch->ch_tun.un_flag & UN_CLOSING) == 0 && + (ch->ch_cflag & CF_CREAD) != 0 && + (ch->ch_flag & (CH_BAUD0 | CH_RX_FLUSH)) == 0 && + (ch->ch_send & RR_RX_FLUSH) == 0) { + + if (ch->ch_rin + dlen >= RBUF_MAX) { + n = RBUF_MAX - ch->ch_rin; + + memcpy(ch->ch_rbuf + ch->ch_rin, dbuf, n); + + ch->ch_rin = 0; + dbuf += n; + dlen -= n; + } + + memcpy(ch->ch_rbuf + ch->ch_rin, dbuf, dlen); + + ch->ch_rin += dlen; + + + /* + * If we are not in fastcook mode, or + * if there is a fastcook thread + * waiting for data, send the data to + * the line discipline. + */ + + if ((ch->ch_flag & CH_FAST_READ) == 0 || + ch->ch_inwait != 0) { + dgrp_input(ch); + } + + /* + * If there is a read thread waiting + * in select, and we are in fastcook + * mode, wake him up. + */ + + if (waitqueue_active(&ch->ch_tun.un_tty->read_wait) && + (ch->ch_flag & CH_FAST_READ) != 0) + wake_up_interruptible(&ch->ch_tun.un_tty->read_wait); + + /* + * Wake any thread waiting in the + * fastcook loop. + */ + + if ((ch->ch_flag & CH_INPUT) != 0) { + ch->ch_flag &= ~CH_INPUT; + + wake_up_interruptible(&ch->ch_flag_wait); + } + } + + /* + * Fabricate and insert a data packet header to + * preced the remaining data when it comes in. + */ + + if (remain < plen) { + dlen = plen - remain; + b = buf; + + b[0] = 0x90 + n1; + put_unaligned_be16(dlen, b + 1); + + remain = 3; + goto done; + } break; /* diff --git a/drivers/staging/gdm72xx/gdm_usb.c b/drivers/staging/gdm72xx/gdm_usb.c index f8788bf0a7d3..cdeffe75496b 100644 --- a/drivers/staging/gdm72xx/gdm_usb.c +++ b/drivers/staging/gdm72xx/gdm_usb.c @@ -635,11 +635,14 @@ static int gdm_usb_probe(struct usb_interface *intf, #endif /* CONFIG_WIMAX_GDM72XX_USB_PM */ ret = register_wimax_device(phy_dev, &intf->dev); + if (ret) + release_usb(udev); out: if (ret) { kfree(phy_dev); kfree(udev); + usb_put_dev(usbdev); } else { usb_set_intfdata(intf, phy_dev); } diff --git a/drivers/staging/iio/Documentation/iio_utils.h b/drivers/staging/iio/Documentation/iio_utils.h index 35154d60faf6..c9fedb79e3a2 100644 --- a/drivers/staging/iio/Documentation/iio_utils.h +++ b/drivers/staging/iio/Documentation/iio_utils.h @@ -77,7 +77,6 @@ struct iio_channel_info { uint64_t mask; unsigned be; unsigned is_signed; - unsigned enabled; unsigned location; }; @@ -335,6 +334,7 @@ inline int build_channel_array(const char *device_dir, while (ent = readdir(dp), ent != NULL) { if (strcmp(ent->d_name + strlen(ent->d_name) - strlen("_en"), "_en") == 0) { + int current_enabled = 0; current = &(*ci_array)[count++]; ret = asprintf(&filename, "%s/%s", scan_el_dir, ent->d_name); @@ -350,10 +350,10 @@ inline int build_channel_array(const char *device_dir, ret = -errno; goto error_cleanup_array; } - fscanf(sysfsfp, "%u", ¤t->enabled); + fscanf(sysfsfp, "%u", ¤t_enabled); fclose(sysfsfp); - if (!current->enabled) { + if (!current_enabled) { free(filename); count--; continue; diff --git a/drivers/staging/iio/adc/ad799x_core.c b/drivers/staging/iio/adc/ad799x_core.c index 5ea36410f716..5708ffc62aec 100644 --- a/drivers/staging/iio/adc/ad799x_core.c +++ b/drivers/staging/iio/adc/ad799x_core.c @@ -393,7 +393,7 @@ static const struct iio_event_spec ad799x_events[] = { }, { .type = IIO_EV_TYPE_THRESH, .dir = IIO_EV_DIR_FALLING, - .mask_separate = BIT(IIO_EV_INFO_VALUE), + .mask_separate = BIT(IIO_EV_INFO_VALUE) | BIT(IIO_EV_INFO_ENABLE), }, { .type = IIO_EV_TYPE_THRESH, @@ -409,7 +409,13 @@ static const struct iio_event_spec ad799x_events[] = { .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), \ .info_mask_shared_by_type = BIT(IIO_CHAN_INFO_SCALE), \ .scan_index = (_index), \ - .scan_type = IIO_ST('u', _realbits, 16, 12 - (_realbits)), \ + .scan_type = { \ + .sign = 'u', \ + .realbits = (_realbits), \ + .storagebits = 16, \ + .shift = 12 - (_realbits), \ + .endianness = IIO_BE, \ + }, \ .event_spec = _ev_spec, \ .num_event_specs = _num_ev_spec, \ } @@ -588,7 +594,8 @@ static int ad799x_probe(struct i2c_client *client, return 0; error_free_irq: - free_irq(client->irq, indio_dev); + if (client->irq > 0) + free_irq(client->irq, indio_dev); error_cleanup_ring: ad799x_ring_cleanup(indio_dev); error_disable_reg: diff --git a/drivers/staging/iio/adc/mxs-lradc.c b/drivers/staging/iio/adc/mxs-lradc.c index df71669bb60e..514844efac75 100644 --- a/drivers/staging/iio/adc/mxs-lradc.c +++ b/drivers/staging/iio/adc/mxs-lradc.c @@ -757,6 +757,7 @@ static void mxs_lradc_finish_touch_event(struct mxs_lradc *lradc, bool valid) } /* if it is released, wait for the next touch via IRQ */ + lradc->cur_plate = LRADC_TOUCH; mxs_lradc_reg_clear(lradc, LRADC_CTRL1_TOUCH_DETECT_IRQ, LRADC_CTRL1); mxs_lradc_reg_set(lradc, LRADC_CTRL1_TOUCH_DETECT_IRQ_EN, LRADC_CTRL1); } @@ -1035,8 +1036,6 @@ SHOW_SCALE_AVAILABLE_ATTR(4); SHOW_SCALE_AVAILABLE_ATTR(5); SHOW_SCALE_AVAILABLE_ATTR(6); SHOW_SCALE_AVAILABLE_ATTR(7); -SHOW_SCALE_AVAILABLE_ATTR(8); -SHOW_SCALE_AVAILABLE_ATTR(9); SHOW_SCALE_AVAILABLE_ATTR(10); SHOW_SCALE_AVAILABLE_ATTR(11); SHOW_SCALE_AVAILABLE_ATTR(12); @@ -1053,8 +1052,6 @@ static struct attribute *mxs_lradc_attributes[] = { &iio_dev_attr_in_voltage5_scale_available.dev_attr.attr, &iio_dev_attr_in_voltage6_scale_available.dev_attr.attr, &iio_dev_attr_in_voltage7_scale_available.dev_attr.attr, - &iio_dev_attr_in_voltage8_scale_available.dev_attr.attr, - &iio_dev_attr_in_voltage9_scale_available.dev_attr.attr, &iio_dev_attr_in_voltage10_scale_available.dev_attr.attr, &iio_dev_attr_in_voltage11_scale_available.dev_attr.attr, &iio_dev_attr_in_voltage12_scale_available.dev_attr.attr, @@ -1613,7 +1610,7 @@ static int mxs_lradc_probe(struct platform_device *pdev) * of the array. */ scale_uv = ((u64)lradc->vref_mv[i] * 100000000) >> - (iio->channels[i].scan_type.realbits - s); + (LRADC_RESOLUTION - s); lradc->scale_avail[i][s].nano = do_div(scale_uv, 100000000) * 10; lradc->scale_avail[i][s].integer = scale_uv; diff --git a/drivers/staging/iio/impedance-analyzer/ad5933.c b/drivers/staging/iio/impedance-analyzer/ad5933.c index 0a4298b744e6..2b96665da8a2 100644 --- a/drivers/staging/iio/impedance-analyzer/ad5933.c +++ b/drivers/staging/iio/impedance-analyzer/ad5933.c @@ -629,7 +629,7 @@ static int ad5933_register_ring_funcs_and_init(struct iio_dev *indio_dev) struct iio_buffer *buffer; buffer = iio_kfifo_allocate(indio_dev); - if (buffer) + if (!buffer) return -ENOMEM; iio_device_attach_buffer(indio_dev, buffer); diff --git a/drivers/staging/imx-drm/imx-drm-core.c b/drivers/staging/imx-drm/imx-drm-core.c index 09ef5fb8bae6..236ed66f116a 100644 --- a/drivers/staging/imx-drm/imx-drm-core.c +++ b/drivers/staging/imx-drm/imx-drm-core.c @@ -88,9 +88,9 @@ static int imx_drm_driver_unload(struct drm_device *drm) imx_drm_device_put(); - drm_vblank_cleanup(imxdrm->drm); - drm_kms_helper_poll_fini(imxdrm->drm); - drm_mode_config_cleanup(imxdrm->drm); + drm_vblank_cleanup(drm); + drm_kms_helper_poll_fini(drm); + drm_mode_config_cleanup(drm); return 0; } @@ -142,19 +142,19 @@ EXPORT_SYMBOL_GPL(imx_drm_crtc_panel_format); int imx_drm_crtc_vblank_get(struct imx_drm_crtc *imx_drm_crtc) { - return drm_vblank_get(imx_drm_crtc->imxdrm->drm, imx_drm_crtc->pipe); + return drm_vblank_get(imx_drm_crtc->crtc->dev, imx_drm_crtc->pipe); } EXPORT_SYMBOL_GPL(imx_drm_crtc_vblank_get); void imx_drm_crtc_vblank_put(struct imx_drm_crtc *imx_drm_crtc) { - drm_vblank_put(imx_drm_crtc->imxdrm->drm, imx_drm_crtc->pipe); + drm_vblank_put(imx_drm_crtc->crtc->dev, imx_drm_crtc->pipe); } EXPORT_SYMBOL_GPL(imx_drm_crtc_vblank_put); void imx_drm_handle_vblank(struct imx_drm_crtc *imx_drm_crtc) { - drm_handle_vblank(imx_drm_crtc->imxdrm->drm, imx_drm_crtc->pipe); + drm_handle_vblank(imx_drm_crtc->crtc->dev, imx_drm_crtc->pipe); } EXPORT_SYMBOL_GPL(imx_drm_handle_vblank); @@ -370,29 +370,6 @@ static void imx_drm_connector_unregister( } /* - * register a crtc to the drm core - */ -static int imx_drm_crtc_register(struct imx_drm_crtc *imx_drm_crtc) -{ - struct imx_drm_device *imxdrm = __imx_drm_device(); - int ret; - - ret = drm_mode_crtc_set_gamma_size(imx_drm_crtc->crtc, 256); - if (ret) - return ret; - - drm_crtc_helper_add(imx_drm_crtc->crtc, - imx_drm_crtc->imx_drm_helper_funcs.crtc_helper_funcs); - - drm_crtc_init(imxdrm->drm, imx_drm_crtc->crtc, - imx_drm_crtc->imx_drm_helper_funcs.crtc_funcs); - - drm_mode_group_reinit(imxdrm->drm); - - return 0; -} - -/* * Called by the CRTC driver when all CRTCs are registered. This * puts all the pieces together and initializes the driver. * Once this is called no more CRTCs can be registered since @@ -424,15 +401,15 @@ static int imx_drm_driver_load(struct drm_device *drm, unsigned long flags) mutex_lock(&imxdrm->mutex); - drm_kms_helper_poll_init(imxdrm->drm); + drm_kms_helper_poll_init(drm); /* setup the grouping for the legacy output */ - ret = drm_mode_group_init_legacy_group(imxdrm->drm, - &imxdrm->drm->primary->mode_group); + ret = drm_mode_group_init_legacy_group(drm, + &drm->primary->mode_group); if (ret) goto err_kms; - ret = drm_vblank_init(imxdrm->drm, MAX_CRTC); + ret = drm_vblank_init(drm, MAX_CRTC); if (ret) goto err_kms; @@ -441,7 +418,7 @@ static int imx_drm_driver_load(struct drm_device *drm, unsigned long flags) * by drm timer once a current process gives up ownership of * vblank event.(after drm_vblank_put function is called) */ - imxdrm->drm->vblank_disable_allowed = true; + drm->vblank_disable_allowed = true; if (!imx_drm_device_get()) { ret = -EINVAL; @@ -536,10 +513,18 @@ int imx_drm_add_crtc(struct drm_crtc *crtc, *new_crtc = imx_drm_crtc; - ret = imx_drm_crtc_register(imx_drm_crtc); + ret = drm_mode_crtc_set_gamma_size(imx_drm_crtc->crtc, 256); if (ret) goto err_register; + drm_crtc_helper_add(crtc, + imx_drm_crtc->imx_drm_helper_funcs.crtc_helper_funcs); + + drm_crtc_init(imxdrm->drm, crtc, + imx_drm_crtc->imx_drm_helper_funcs.crtc_funcs); + + drm_mode_group_reinit(imxdrm->drm); + imx_drm_update_possible_crtcs(); mutex_unlock(&imxdrm->mutex); diff --git a/drivers/staging/imx-drm/imx-hdmi.c b/drivers/staging/imx-drm/imx-hdmi.c index f3a1f5e2e492..62ce0e86f14b 100644 --- a/drivers/staging/imx-drm/imx-hdmi.c +++ b/drivers/staging/imx-drm/imx-hdmi.c @@ -16,6 +16,7 @@ #include <linux/delay.h> #include <linux/err.h> #include <linux/clk.h> +#include <linux/hdmi.h> #include <linux/regmap.h> #include <linux/mfd/syscon.h> #include <linux/mfd/syscon/imx6q-iomuxc-gpr.h> @@ -52,11 +53,6 @@ enum hdmi_datamap { YCbCr422_12B = 0x12, }; -enum hdmi_colorimetry { - ITU601, - ITU709, -}; - enum imx_hdmi_devtype { IMX6Q_HDMI, IMX6DL_HDMI, @@ -489,12 +485,12 @@ static void imx_hdmi_update_csc_coeffs(struct imx_hdmi *hdmi) if (is_color_space_conversion(hdmi)) { if (hdmi->hdmi_data.enc_out_format == RGB) { - if (hdmi->hdmi_data.colorimetry == ITU601) + if (hdmi->hdmi_data.colorimetry == HDMI_COLORIMETRY_ITU_601) csc_coeff = &csc_coeff_rgb_out_eitu601; else csc_coeff = &csc_coeff_rgb_out_eitu709; } else if (hdmi->hdmi_data.enc_in_format == RGB) { - if (hdmi->hdmi_data.colorimetry == ITU601) + if (hdmi->hdmi_data.colorimetry == HDMI_COLORIMETRY_ITU_601) csc_coeff = &csc_coeff_rgb_in_eitu601; else csc_coeff = &csc_coeff_rgb_in_eitu709; @@ -1140,16 +1136,16 @@ static void hdmi_config_AVI(struct imx_hdmi *hdmi) /* Set up colorimetry */ if (hdmi->hdmi_data.enc_out_format == XVYCC444) { colorimetry = HDMI_FC_AVICONF1_COLORIMETRY_EXTENDED_INFO; - if (hdmi->hdmi_data.colorimetry == ITU601) + if (hdmi->hdmi_data.colorimetry == HDMI_COLORIMETRY_ITU_601) ext_colorimetry = HDMI_FC_AVICONF2_EXT_COLORIMETRY_XVYCC601; - else /* hdmi->hdmi_data.colorimetry == ITU709 */ + else /*hdmi->hdmi_data.colorimetry == HDMI_COLORIMETRY_ITU_709*/ ext_colorimetry = HDMI_FC_AVICONF2_EXT_COLORIMETRY_XVYCC709; } else if (hdmi->hdmi_data.enc_out_format != RGB) { - if (hdmi->hdmi_data.colorimetry == ITU601) + if (hdmi->hdmi_data.colorimetry == HDMI_COLORIMETRY_ITU_601) colorimetry = HDMI_FC_AVICONF1_COLORIMETRY_SMPTE; - else /* hdmi->hdmi_data.colorimetry == ITU709 */ + else /*hdmi->hdmi_data.colorimetry == HDMI_COLORIMETRY_ITU_709*/ colorimetry = HDMI_FC_AVICONF1_COLORIMETRY_ITUR; ext_colorimetry = HDMI_FC_AVICONF2_EXT_COLORIMETRY_XVYCC601; } else { /* Carries no data */ @@ -1379,9 +1375,9 @@ static int imx_hdmi_setup(struct imx_hdmi *hdmi, struct drm_display_mode *mode) (hdmi->vic == 21) || (hdmi->vic == 22) || (hdmi->vic == 2) || (hdmi->vic == 3) || (hdmi->vic == 17) || (hdmi->vic == 18)) - hdmi->hdmi_data.colorimetry = ITU601; + hdmi->hdmi_data.colorimetry = HDMI_COLORIMETRY_ITU_601; else - hdmi->hdmi_data.colorimetry = ITU709; + hdmi->hdmi_data.colorimetry = HDMI_COLORIMETRY_ITU_709; if ((hdmi->vic == 10) || (hdmi->vic == 11) || (hdmi->vic == 12) || (hdmi->vic == 13) || diff --git a/drivers/staging/lustre/TODO b/drivers/staging/lustre/TODO index 22742d6d62a8..0a2b6cb3775e 100644 --- a/drivers/staging/lustre/TODO +++ b/drivers/staging/lustre/TODO @@ -9,5 +9,6 @@ * Other minor misc cleanups... Please send any patches to Greg Kroah-Hartman <greg@kroah.com>, Andreas Dilger -<andreas.dilger@intel.com> and Peng Tao <tao.peng@emc.com>. CCing -hpdd-discuss <hpdd-discuss@lists.01.org> would be great too. +<andreas.dilger@intel.com>, Oleg Drokin <oleg.drokin@intel.com> and +Peng Tao <tao.peng@emc.com>. CCing hpdd-discuss <hpdd-discuss@lists.01.org> +would be great too. diff --git a/drivers/staging/lustre/include/linux/libcfs/libcfs_kernelcomm.h b/drivers/staging/lustre/include/linux/libcfs/libcfs_kernelcomm.h index 596a15fc8996..037ae8a6d531 100644 --- a/drivers/staging/lustre/include/linux/libcfs/libcfs_kernelcomm.h +++ b/drivers/staging/lustre/include/linux/libcfs/libcfs_kernelcomm.h @@ -61,6 +61,8 @@ struct kuc_hdr { __u16 kuc_msglen; /* Including header */ } __attribute__((aligned(sizeof(__u64)))); +#define KUC_CHANGELOG_MSG_MAXSIZE (sizeof(struct kuc_hdr)+CR_MAXSIZE) + #define KUC_MAGIC 0x191C /*Lustre9etLinC */ #define KUC_FL_BLOCK 0x01 /* Wait for send */ diff --git a/drivers/staging/lustre/include/linux/libcfs/libcfs_private.h b/drivers/staging/lustre/include/linux/libcfs/libcfs_private.h index d0d942ced01a..dddccca120c9 100644 --- a/drivers/staging/lustre/include/linux/libcfs/libcfs_private.h +++ b/drivers/staging/lustre/include/linux/libcfs/libcfs_private.h @@ -120,7 +120,7 @@ do { \ do { \ LASSERT(!in_interrupt() || \ ((size) <= LIBCFS_VMALLOC_SIZE && \ - ((mask) & GFP_ATOMIC)) != 0); \ + ((mask) & __GFP_WAIT) == 0)); \ } while (0) #define LIBCFS_ALLOC_POST(ptr, size) \ diff --git a/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_cb.c b/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_cb.c index 93648632ba26..6f58ead20393 100644 --- a/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_cb.c +++ b/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd_cb.c @@ -529,7 +529,7 @@ kiblnd_kvaddr_to_page (unsigned long vaddr) { struct page *page; - if (is_vmalloc_addr(vaddr)) { + if (is_vmalloc_addr((void *)vaddr)) { page = vmalloc_to_page ((void *)vaddr); LASSERT (page != NULL); return page; diff --git a/drivers/staging/lustre/lnet/klnds/socklnd/socklnd_cb.c b/drivers/staging/lustre/lnet/klnds/socklnd/socklnd_cb.c index 68a4f52ec998..b7b53b579c85 100644 --- a/drivers/staging/lustre/lnet/klnds/socklnd/socklnd_cb.c +++ b/drivers/staging/lustre/lnet/klnds/socklnd/socklnd_cb.c @@ -924,7 +924,7 @@ ksocknal_launch_packet (lnet_ni_t *ni, ksock_tx_t *tx, lnet_process_id_t id) int ksocknal_send(lnet_ni_t *ni, void *private, lnet_msg_t *lntmsg) { - int mpflag = 0; + int mpflag = 1; int type = lntmsg->msg_type; lnet_process_id_t target = lntmsg->msg_target; unsigned int payload_niov = lntmsg->msg_niov; @@ -993,8 +993,9 @@ ksocknal_send(lnet_ni_t *ni, void *private, lnet_msg_t *lntmsg) /* The first fragment will be set later in pro_pack */ rc = ksocknal_launch_packet(ni, tx, target); - if (lntmsg->msg_vmflush) + if (!mpflag) cfs_memory_pressure_restore(mpflag); + if (rc == 0) return (0); diff --git a/drivers/staging/lustre/lustre/include/lustre/lustre_user.h b/drivers/staging/lustre/lustre/include/lustre/lustre_user.h index 6b6c0240e824..7893d83e131f 100644 --- a/drivers/staging/lustre/lustre/include/lustre/lustre_user.h +++ b/drivers/staging/lustre/lustre/include/lustre/lustre_user.h @@ -760,7 +760,8 @@ static inline void hsm_set_cl_error(int *flags, int error) *flags |= (error << CLF_HSM_ERR_L); } -#define CR_MAXSIZE cfs_size_round(2*NAME_MAX + 1 + sizeof(struct changelog_rec)) +#define CR_MAXSIZE cfs_size_round(2*NAME_MAX + 1 + \ + sizeof(struct changelog_ext_rec)) struct changelog_rec { __u16 cr_namelen; diff --git a/drivers/staging/lustre/lustre/llite/dir.c b/drivers/staging/lustre/lustre/llite/dir.c index 22d0acc95bc5..52b7731bcc38 100644 --- a/drivers/staging/lustre/lustre/llite/dir.c +++ b/drivers/staging/lustre/lustre/llite/dir.c @@ -1086,7 +1086,7 @@ static int quotactl_ioctl(struct ll_sb_info *sbi, struct if_quotactl *qctl) break; case Q_GETQUOTA: if (((type == USRQUOTA && - uid_eq(current_euid(), make_kuid(&init_user_ns, id))) || + !uid_eq(current_euid(), make_kuid(&init_user_ns, id))) || (type == GRPQUOTA && !in_egroup_p(make_kgid(&init_user_ns, id)))) && (!cfs_capable(CFS_CAP_SYS_ADMIN) || diff --git a/drivers/staging/lustre/lustre/mdc/mdc_request.c b/drivers/staging/lustre/lustre/mdc/mdc_request.c index d1ad91c34ddc..83013927e131 100644 --- a/drivers/staging/lustre/lustre/mdc/mdc_request.c +++ b/drivers/staging/lustre/lustre/mdc/mdc_request.c @@ -1430,7 +1430,7 @@ static struct kuc_hdr *changelog_kuc_hdr(char *buf, int len, int flags) { struct kuc_hdr *lh = (struct kuc_hdr *)buf; - LASSERT(len <= CR_MAXSIZE); + LASSERT(len <= KUC_CHANGELOG_MSG_MAXSIZE); lh->kuc_magic = KUC_MAGIC; lh->kuc_transport = KUC_TRANSPORT_CHANGELOG; @@ -1503,7 +1503,7 @@ static int mdc_changelog_send_thread(void *csdata) CDEBUG(D_CHANGELOG, "changelog to fp=%p start "LPU64"\n", cs->cs_fp, cs->cs_startrec); - OBD_ALLOC(cs->cs_buf, CR_MAXSIZE); + OBD_ALLOC(cs->cs_buf, KUC_CHANGELOG_MSG_MAXSIZE); if (cs->cs_buf == NULL) GOTO(out, rc = -ENOMEM); @@ -1540,7 +1540,7 @@ out: if (ctxt) llog_ctxt_put(ctxt); if (cs->cs_buf) - OBD_FREE(cs->cs_buf, CR_MAXSIZE); + OBD_FREE(cs->cs_buf, KUC_CHANGELOG_MSG_MAXSIZE); OBD_FREE_PTR(cs); return rc; } diff --git a/drivers/staging/netlogic/xlr_net.c b/drivers/staging/netlogic/xlr_net.c index eedffed17e39..31b269a5fff7 100644 --- a/drivers/staging/netlogic/xlr_net.c +++ b/drivers/staging/netlogic/xlr_net.c @@ -307,7 +307,7 @@ static netdev_tx_t xlr_net_start_xmit(struct sk_buff *skb, } static u16 xlr_net_select_queue(struct net_device *ndev, struct sk_buff *skb, - void *accel_priv) + void *accel_priv, select_queue_fallback_t fallback) { return (u16)smp_processor_id(); } @@ -892,6 +892,11 @@ static int xlr_setup_mdio(struct xlr_net_priv *priv, priv->mii_bus->write = xlr_mii_write; priv->mii_bus->parent = &pdev->dev; priv->mii_bus->irq = kmalloc(sizeof(int)*PHY_MAX_ADDR, GFP_KERNEL); + if (priv->mii_bus->irq == NULL) { + pr_err("irq alloc failed\n"); + mdiobus_free(priv->mii_bus); + return -ENOMEM; + } priv->mii_bus->irq[priv->phy_addr] = priv->ndev->irq; /* Scan only the enabled address */ diff --git a/drivers/staging/octeon-usb/octeon-hcd.c b/drivers/staging/octeon-usb/octeon-hcd.c index 47e0a91238a1..5a001d9b4252 100644 --- a/drivers/staging/octeon-usb/octeon-hcd.c +++ b/drivers/staging/octeon-usb/octeon-hcd.c @@ -275,13 +275,6 @@ enum cvmx_usb_pipe_flags { */ #define MAX_TRANSFER_PACKETS ((1<<10)-1) -enum { - USB_CLOCK_TYPE_REF_12, - USB_CLOCK_TYPE_REF_24, - USB_CLOCK_TYPE_REF_48, - USB_CLOCK_TYPE_CRYSTAL_12, -}; - /** * Logical transactions may take numerous low level * transactions, especially when splits are concerned. This @@ -471,19 +464,6 @@ struct octeon_hcd { /* Returns the IO address to push/pop stuff data from the FIFOs */ #define USB_FIFO_ADDRESS(channel, usb_index) (CVMX_USBCX_GOTGCTL(usb_index) + ((channel)+1)*0x1000) -static int octeon_usb_get_clock_type(void) -{ - switch (cvmx_sysinfo_get()->board_type) { - case CVMX_BOARD_TYPE_BBGW_REF: - case CVMX_BOARD_TYPE_LANAI2_A: - case CVMX_BOARD_TYPE_LANAI2_U: - case CVMX_BOARD_TYPE_LANAI2_G: - case CVMX_BOARD_TYPE_UBNT_E100: - return USB_CLOCK_TYPE_CRYSTAL_12; - } - return USB_CLOCK_TYPE_REF_48; -} - /** * Read a USB 32bit CSR. It performs the necessary address swizzle * for 32bit CSRs and logs the value in a readable format if @@ -582,37 +562,6 @@ static inline int __cvmx_usb_get_data_pid(struct cvmx_usb_pipe *pipe) return 0; /* Data0 */ } - -/** - * Return the number of USB ports supported by this Octeon - * chip. If the chip doesn't support USB, or is not supported - * by this API, a zero will be returned. Most Octeon chips - * support one usb port, but some support two ports. - * cvmx_usb_initialize() must be called on independent - * struct cvmx_usb_state. - * - * Returns: Number of port, zero if usb isn't supported - */ -static int cvmx_usb_get_num_ports(void) -{ - int arch_ports = 0; - - if (OCTEON_IS_MODEL(OCTEON_CN56XX)) - arch_ports = 1; - else if (OCTEON_IS_MODEL(OCTEON_CN52XX)) - arch_ports = 2; - else if (OCTEON_IS_MODEL(OCTEON_CN50XX)) - arch_ports = 1; - else if (OCTEON_IS_MODEL(OCTEON_CN31XX)) - arch_ports = 1; - else if (OCTEON_IS_MODEL(OCTEON_CN30XX)) - arch_ports = 1; - else - arch_ports = 0; - - return arch_ports; -} - /** * Initialize a USB port for use. This must be called before any * other access to the Octeon USB port is made. The port starts @@ -628,41 +577,16 @@ static int cvmx_usb_get_num_ports(void) * Returns: 0 or a negative error code. */ static int cvmx_usb_initialize(struct cvmx_usb_state *usb, - int usb_port_number) + int usb_port_number, + enum cvmx_usb_initialize_flags flags) { union cvmx_usbnx_clk_ctl usbn_clk_ctl; union cvmx_usbnx_usbp_ctl_status usbn_usbp_ctl_status; - enum cvmx_usb_initialize_flags flags = 0; int i; /* At first allow 0-1 for the usb port number */ if ((usb_port_number < 0) || (usb_port_number > 1)) return -EINVAL; - /* For all chips except 52XX there is only one port */ - if (!OCTEON_IS_MODEL(OCTEON_CN52XX) && (usb_port_number > 0)) - return -EINVAL; - /* Try to determine clock type automatically */ - if (octeon_usb_get_clock_type() == USB_CLOCK_TYPE_CRYSTAL_12) { - /* Only 12 MHZ crystals are supported */ - flags |= CVMX_USB_INITIALIZE_FLAGS_CLOCK_XO_XI; - } else { - flags |= CVMX_USB_INITIALIZE_FLAGS_CLOCK_XO_GND; - - switch (octeon_usb_get_clock_type()) { - case USB_CLOCK_TYPE_REF_12: - flags |= CVMX_USB_INITIALIZE_FLAGS_CLOCK_12MHZ; - break; - case USB_CLOCK_TYPE_REF_24: - flags |= CVMX_USB_INITIALIZE_FLAGS_CLOCK_24MHZ; - break; - case USB_CLOCK_TYPE_REF_48: - flags |= CVMX_USB_INITIALIZE_FLAGS_CLOCK_48MHZ; - break; - default: - return -EINVAL; - break; - } - } memset(usb, 0, sizeof(*usb)); usb->init_flags = flags; @@ -3431,7 +3355,6 @@ static int octeon_usb_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue, return 0; } - static const struct hc_driver octeon_hc_driver = { .description = "Octeon USB", .product_desc = "Octeon Host Controller", @@ -3448,15 +3371,74 @@ static const struct hc_driver octeon_hc_driver = { .hub_control = octeon_usb_hub_control, }; - -static int octeon_usb_driver_probe(struct device *dev) +static int octeon_usb_probe(struct platform_device *pdev) { int status; - int usb_num = to_platform_device(dev)->id; - int irq = platform_get_irq(to_platform_device(dev), 0); + int initialize_flags; + int usb_num; + struct resource *res_mem; + struct device_node *usbn_node; + int irq = platform_get_irq(pdev, 0); + struct device *dev = &pdev->dev; struct octeon_hcd *priv; struct usb_hcd *hcd; unsigned long flags; + u32 clock_rate = 48000000; + bool is_crystal_clock = false; + const char *clock_type; + int i; + + if (dev->of_node == NULL) { + dev_err(dev, "Error: empty of_node\n"); + return -ENXIO; + } + usbn_node = dev->of_node->parent; + + i = of_property_read_u32(usbn_node, + "refclk-frequency", &clock_rate); + if (i) { + dev_err(dev, "No USBN \"refclk-frequency\"\n"); + return -ENXIO; + } + switch (clock_rate) { + case 12000000: + initialize_flags = CVMX_USB_INITIALIZE_FLAGS_CLOCK_12MHZ; + break; + case 24000000: + initialize_flags = CVMX_USB_INITIALIZE_FLAGS_CLOCK_24MHZ; + break; + case 48000000: + initialize_flags = CVMX_USB_INITIALIZE_FLAGS_CLOCK_48MHZ; + break; + default: + dev_err(dev, "Illebal USBN \"refclk-frequency\" %u\n", clock_rate); + return -ENXIO; + + } + + i = of_property_read_string(usbn_node, + "refclk-type", &clock_type); + + if (!i && strcmp("crystal", clock_type) == 0) + is_crystal_clock = true; + + if (is_crystal_clock) + initialize_flags |= CVMX_USB_INITIALIZE_FLAGS_CLOCK_XO_XI; + else + initialize_flags |= CVMX_USB_INITIALIZE_FLAGS_CLOCK_XO_GND; + + res_mem = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (res_mem == NULL) { + dev_err(dev, "found no memory resource\n"); + return -ENXIO; + } + usb_num = (res_mem->start >> 44) & 1; + + if (irq < 0) { + /* Defective device tree, but we know how to fix it. */ + irq_hw_number_t hwirq = usb_num ? (1 << 6) + 17 : 56; + irq = irq_create_mapping(NULL, hwirq); + } /* * Set the DMA mask to 64bits so we get buffers already translated for @@ -3465,6 +3447,26 @@ static int octeon_usb_driver_probe(struct device *dev) dev->coherent_dma_mask = ~0; dev->dma_mask = &dev->coherent_dma_mask; + /* + * Only cn52XX and cn56XX have DWC_OTG USB hardware and the + * IOB priority registers. Under heavy network load USB + * hardware can be starved by the IOB causing a crash. Give + * it a priority boost if it has been waiting more than 400 + * cycles to avoid this situation. + * + * Testing indicates that a cnt_val of 8192 is not sufficient, + * but no failures are seen with 4096. We choose a value of + * 400 to give a safety factor of 10. + */ + if (OCTEON_IS_MODEL(OCTEON_CN52XX) || OCTEON_IS_MODEL(OCTEON_CN56XX)) { + union cvmx_iob_n2c_l2c_pri_cnt pri_cnt; + + pri_cnt.u64 = 0; + pri_cnt.s.cnt_enb = 1; + pri_cnt.s.cnt_val = 400; + cvmx_write_csr(CVMX_IOB_N2C_L2C_PRI_CNT, pri_cnt.u64); + } + hcd = usb_create_hcd(&octeon_hc_driver, dev, dev_name(dev)); if (!hcd) { dev_dbg(dev, "Failed to allocate memory for HCD\n"); @@ -3478,7 +3480,7 @@ static int octeon_usb_driver_probe(struct device *dev) tasklet_init(&priv->dequeue_tasklet, octeon_usb_urb_dequeue_work, (unsigned long)priv); INIT_LIST_HEAD(&priv->dequeue_list); - status = cvmx_usb_initialize(&priv->usb, usb_num); + status = cvmx_usb_initialize(&priv->usb, usb_num, initialize_flags); if (status) { dev_dbg(dev, "USB initialization failed with %d\n", status); kfree(hcd); @@ -3492,7 +3494,7 @@ static int octeon_usb_driver_probe(struct device *dev) cvmx_usb_poll(&priv->usb); spin_unlock_irqrestore(&priv->lock, flags); - status = usb_add_hcd(hcd, irq, IRQF_SHARED); + status = usb_add_hcd(hcd, irq, 0); if (status) { dev_dbg(dev, "USB add HCD failed with %d\n", status); kfree(hcd); @@ -3500,14 +3502,15 @@ static int octeon_usb_driver_probe(struct device *dev) } device_wakeup_enable(hcd->self.controller); - dev_dbg(dev, "Registered HCD for port %d on irq %d\n", usb_num, irq); + dev_info(dev, "Registered HCD for port %d on irq %d\n", usb_num, irq); return 0; } -static int octeon_usb_driver_remove(struct device *dev) +static int octeon_usb_remove(struct platform_device *pdev) { int status; + struct device *dev = &pdev->dev; struct usb_hcd *hcd = dev_get_drvdata(dev); struct octeon_hcd *priv = hcd_to_octeon(hcd); unsigned long flags; @@ -3525,85 +3528,41 @@ static int octeon_usb_driver_remove(struct device *dev) return 0; } -static struct device_driver octeon_usb_driver = { - .name = "OcteonUSB", - .bus = &platform_bus_type, - .probe = octeon_usb_driver_probe, - .remove = octeon_usb_driver_remove, +static struct of_device_id octeon_usb_match[] = { + { + .compatible = "cavium,octeon-5750-usbc", + }, + {}, }; +static struct platform_driver octeon_usb_driver = { + .driver = { + .name = "OcteonUSB", + .owner = THIS_MODULE, + .of_match_table = octeon_usb_match, + }, + .probe = octeon_usb_probe, + .remove = octeon_usb_remove, +}; -#define MAX_USB_PORTS 10 -static struct platform_device *pdev_glob[MAX_USB_PORTS]; -static int octeon_usb_registered; -static int __init octeon_usb_module_init(void) +static int __init octeon_usb_driver_init(void) { - int num_devices = cvmx_usb_get_num_ports(); - int device; - - if (usb_disabled() || num_devices == 0) - return -ENODEV; - - if (driver_register(&octeon_usb_driver)) - return -ENOMEM; - - octeon_usb_registered = 1; - - /* - * Only cn52XX and cn56XX have DWC_OTG USB hardware and the - * IOB priority registers. Under heavy network load USB - * hardware can be starved by the IOB causing a crash. Give - * it a priority boost if it has been waiting more than 400 - * cycles to avoid this situation. - * - * Testing indicates that a cnt_val of 8192 is not sufficient, - * but no failures are seen with 4096. We choose a value of - * 400 to give a safety factor of 10. - */ - if (OCTEON_IS_MODEL(OCTEON_CN52XX) || OCTEON_IS_MODEL(OCTEON_CN56XX)) { - union cvmx_iob_n2c_l2c_pri_cnt pri_cnt; - - pri_cnt.u64 = 0; - pri_cnt.s.cnt_enb = 1; - pri_cnt.s.cnt_val = 400; - cvmx_write_csr(CVMX_IOB_N2C_L2C_PRI_CNT, pri_cnt.u64); - } - - for (device = 0; device < num_devices; device++) { - struct resource irq_resource; - struct platform_device *pdev; - memset(&irq_resource, 0, sizeof(irq_resource)); - irq_resource.start = (device == 0) ? OCTEON_IRQ_USB0 : OCTEON_IRQ_USB1; - irq_resource.end = irq_resource.start; - irq_resource.flags = IORESOURCE_IRQ; - pdev = platform_device_register_simple((char *)octeon_usb_driver. name, device, &irq_resource, 1); - if (IS_ERR(pdev)) { - driver_unregister(&octeon_usb_driver); - octeon_usb_registered = 0; - return PTR_ERR(pdev); - } - if (device < MAX_USB_PORTS) - pdev_glob[device] = pdev; + if (usb_disabled()) + return 0; - } - return 0; + return platform_driver_register(&octeon_usb_driver); } +module_init(octeon_usb_driver_init); -static void __exit octeon_usb_module_cleanup(void) +static void __exit octeon_usb_driver_exit(void) { - int i; + if (usb_disabled()) + return; - for (i = 0; i < MAX_USB_PORTS; i++) - if (pdev_glob[i]) { - platform_device_unregister(pdev_glob[i]); - pdev_glob[i] = NULL; - } - if (octeon_usb_registered) - driver_unregister(&octeon_usb_driver); + platform_driver_unregister(&octeon_usb_driver); } +module_exit(octeon_usb_driver_exit); MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Cavium Networks <support@caviumnetworks.com>"); -MODULE_DESCRIPTION("Cavium Networks Octeon USB Host driver."); -module_init(octeon_usb_module_init); -module_exit(octeon_usb_module_cleanup); +MODULE_AUTHOR("Cavium, Inc. <support@cavium.com>"); +MODULE_DESCRIPTION("Cavium Inc. OCTEON USB Host driver."); diff --git a/drivers/staging/ozwpan/ozproto.c b/drivers/staging/ozwpan/ozproto.c index cb060364dfe7..5d965cf06d59 100644 --- a/drivers/staging/ozwpan/ozproto.c +++ b/drivers/staging/ozwpan/ozproto.c @@ -668,8 +668,8 @@ void oz_binding_add(const char *net_dev) if (binding) { binding->ptype.type = __constant_htons(OZ_ETHERTYPE); binding->ptype.func = oz_pkt_recv; - memcpy(binding->name, net_dev, OZ_MAX_BINDING_LEN); if (net_dev && *net_dev) { + memcpy(binding->name, net_dev, OZ_MAX_BINDING_LEN); oz_dbg(ON, "Adding binding: %s\n", net_dev); binding->ptype.dev = dev_get_by_name(&init_net, net_dev); @@ -680,6 +680,7 @@ void oz_binding_add(const char *net_dev) } } else { oz_dbg(ON, "Binding to all netcards\n"); + memset(binding->name, 0, OZ_MAX_BINDING_LEN); binding->ptype.dev = NULL; } if (binding) { diff --git a/drivers/staging/rtl8188eu/core/rtw_wlan_util.c b/drivers/staging/rtl8188eu/core/rtw_wlan_util.c index 153ec61493ab..96df62f95b6b 100644 --- a/drivers/staging/rtl8188eu/core/rtw_wlan_util.c +++ b/drivers/staging/rtl8188eu/core/rtw_wlan_util.c @@ -912,12 +912,12 @@ int rtw_check_bcn_info(struct adapter *Adapter, u8 *pframe, u32 packet_len) unsigned char *pbuf; u32 wpa_ielen = 0; u8 *pbssid = GetAddr3Ptr(pframe); - u32 hidden_ssid = 0; struct HT_info_element *pht_info = NULL; struct rtw_ieee80211_ht_cap *pht_cap = NULL; u32 bcn_channel; unsigned short ht_cap_info; unsigned char ht_info_infos_0; + int ssid_len; if (is_client_associated_to_ap(Adapter) == false) return true; @@ -999,21 +999,15 @@ int rtw_check_bcn_info(struct adapter *Adapter, u8 *pframe, u32 packet_len) } /* checking SSID */ + ssid_len = 0; p = rtw_get_ie(bssid->IEs + _FIXED_IE_LENGTH_, _SSID_IE_, &len, bssid->IELength - _FIXED_IE_LENGTH_); - if (p == NULL) { - DBG_88E("%s marc: cannot find SSID for survey event\n", __func__); - hidden_ssid = true; - } else { - hidden_ssid = false; - } - - if ((NULL != p) && (false == hidden_ssid && (*(p + 1)))) { - memcpy(bssid->Ssid.Ssid, (p + 2), *(p + 1)); - bssid->Ssid.SsidLength = *(p + 1); - } else { - bssid->Ssid.SsidLength = 0; - bssid->Ssid.Ssid[0] = '\0'; + if (p) { + ssid_len = *(p + 1); + if (ssid_len > NDIS_802_11_LENGTH_SSID) + ssid_len = 0; } + memcpy(bssid->Ssid.Ssid, (p + 2), ssid_len); + bssid->Ssid.SsidLength = ssid_len; RT_TRACE(_module_rtl871x_mlme_c_, _drv_info_, ("%s bssid.Ssid.Ssid:%s bssid.Ssid.SsidLength:%d " "cur_network->network.Ssid.Ssid:%s len:%d\n", __func__, bssid->Ssid.Ssid, diff --git a/drivers/staging/rtl8188eu/os_dep/ioctl_linux.c b/drivers/staging/rtl8188eu/os_dep/ioctl_linux.c index dec992569476..4ad80ae1067f 100644 --- a/drivers/staging/rtl8188eu/os_dep/ioctl_linux.c +++ b/drivers/staging/rtl8188eu/os_dep/ioctl_linux.c @@ -2500,7 +2500,7 @@ static int rtw_mp_ioctl_hdl(struct net_device *dev, struct iw_request_info *info ("rtw_mp_ioctl_hdl: subcode [%d], len[%d], buffer_len[%d]\r\n", poidparam->subcode, poidparam->len, len)); - if (poidparam->subcode >= MAX_MP_IOCTL_SUBCODE) { + if (poidparam->subcode >= ARRAY_SIZE(mp_ioctl_hdl)) { RT_TRACE(_module_rtl871x_ioctl_os_c, _drv_err_, ("no matching drvext subcodes\r\n")); ret = -EINVAL; goto _rtw_mp_ioctl_hdl_exit; @@ -3164,9 +3164,7 @@ static int rtw_p2p_get_go_device_address(struct net_device *dev, u8 *p2pie; uint p2pielen = 0, attr_contentlen = 0; u8 attr_content[100] = {0x00}; - - u8 go_devadd_str[17 + 10] = {0x00}; - /* +10 is for the str "go_devadd =", we have to clear it at wrqu->data.pointer */ + u8 go_devadd_str[17 + 12] = {}; /* Commented by Albert 20121209 */ /* The input data is the GO's interface address which the application wants to know its device address. */ @@ -3223,12 +3221,12 @@ static int rtw_p2p_get_go_device_address(struct net_device *dev, spin_unlock_bh(&pmlmepriv->scanned_queue.lock); if (!blnMatch) - sprintf(go_devadd_str, "\n\ndev_add = NULL"); + snprintf(go_devadd_str, sizeof(go_devadd_str), "\n\ndev_add = NULL"); else - sprintf(go_devadd_str, "\n\ndev_add =%.2X:%.2X:%.2X:%.2X:%.2X:%.2X", + snprintf(go_devadd_str, sizeof(go_devadd_str), "\n\ndev_add =%.2X:%.2X:%.2X:%.2X:%.2X:%.2X", attr_content[0], attr_content[1], attr_content[2], attr_content[3], attr_content[4], attr_content[5]); - if (copy_to_user(wrqu->data.pointer, go_devadd_str, 10 + 17)) + if (copy_to_user(wrqu->data.pointer, go_devadd_str, sizeof(go_devadd_str))) return -EFAULT; return ret; } diff --git a/drivers/staging/rtl8188eu/os_dep/os_intfs.c b/drivers/staging/rtl8188eu/os_dep/os_intfs.c index 68f98fa114d2..7c9ee58f47bb 100644 --- a/drivers/staging/rtl8188eu/os_dep/os_intfs.c +++ b/drivers/staging/rtl8188eu/os_dep/os_intfs.c @@ -653,7 +653,7 @@ static unsigned int rtw_classify8021d(struct sk_buff *skb) } static u16 rtw_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv) + void *accel_priv, select_queue_fallback_t fallback) { struct adapter *padapter = rtw_netdev_priv(dev); struct mlme_priv *pmlmepriv = &padapter->mlmepriv; diff --git a/drivers/staging/rtl8188eu/os_dep/usb_intf.c b/drivers/staging/rtl8188eu/os_dep/usb_intf.c index 0a341d6ec51f..2f40ff5901d6 100644 --- a/drivers/staging/rtl8188eu/os_dep/usb_intf.c +++ b/drivers/staging/rtl8188eu/os_dep/usb_intf.c @@ -53,8 +53,9 @@ static struct usb_device_id rtw_usb_id_tbl[] = { {USB_DEVICE(USB_VENDER_ID_REALTEK, 0x0179)}, /* 8188ETV */ /*=== Customer ID ===*/ /****** 8188EUS ********/ - {USB_DEVICE(0x8179, 0x07B8)}, /* Abocom - Abocom */ + {USB_DEVICE(0x07b8, 0x8179)}, /* Abocom - Abocom */ {USB_DEVICE(0x2001, 0x330F)}, /* DLink DWA-125 REV D1 */ + {USB_DEVICE(0x2001, 0x3310)}, /* Dlink DWA-123 REV D1 */ {} /* Terminating entry */ }; diff --git a/drivers/staging/rtl8821ae/Kconfig b/drivers/staging/rtl8821ae/Kconfig index 2aa5dac2f1df..abccc9dabd65 100644 --- a/drivers/staging/rtl8821ae/Kconfig +++ b/drivers/staging/rtl8821ae/Kconfig @@ -1,6 +1,6 @@ config R8821AE tristate "RealTek RTL8821AE Wireless LAN NIC driver" - depends on PCI && WLAN + depends on PCI && WLAN && MAC80211 depends on m select WIRELESS_EXT select WEXT_PRIV diff --git a/drivers/staging/rtl8821ae/wifi.h b/drivers/staging/rtl8821ae/wifi.h index cfe88a1efd55..76bef93ad70a 100644 --- a/drivers/staging/rtl8821ae/wifi.h +++ b/drivers/staging/rtl8821ae/wifi.h @@ -1414,7 +1414,7 @@ struct rtl_dm { /*88e tx power tracking*/ - u8 bb_swing_idx_ofdm[2]; + u8 bb_swing_idx_ofdm[MAX_RF_PATH]; u8 bb_swing_idx_ofdm_current; u8 bb_swing_idx_ofdm_base[MAX_RF_PATH]; bool bb_swing_flag_Ofdm; diff --git a/drivers/staging/usbip/userspace/libsrc/names.c b/drivers/staging/usbip/userspace/libsrc/names.c index 3c8d28b771e0..81ff8522405c 100644 --- a/drivers/staging/usbip/userspace/libsrc/names.c +++ b/drivers/staging/usbip/userspace/libsrc/names.c @@ -169,14 +169,14 @@ static void *my_malloc(size_t size) struct pool *p; p = calloc(1, sizeof(struct pool)); - if (!p) { - free(p); + if (!p) return NULL; - } p->mem = calloc(1, size); - if (!p->mem) + if (!p->mem) { + free(p); return NULL; + } p->next = pool_head; pool_head = p; diff --git a/drivers/staging/usbip/vhci_sysfs.c b/drivers/staging/usbip/vhci_sysfs.c index 9b51586d11d9..0141bc34d5cc 100644 --- a/drivers/staging/usbip/vhci_sysfs.c +++ b/drivers/staging/usbip/vhci_sysfs.c @@ -149,7 +149,8 @@ static int valid_args(__u32 rhport, enum usb_device_speed speed) case USB_SPEED_WIRELESS: break; default: - pr_err("speed %d\n", speed); + pr_err("Failed attach request for unsupported USB speed: %s\n", + usb_speed_string(speed)); return -EINVAL; } diff --git a/drivers/staging/wlags49_h2/wl_wext.c b/drivers/staging/wlags49_h2/wl_wext.c index 4a1ddaf5e00f..187fc060de26 100644 --- a/drivers/staging/wlags49_h2/wl_wext.c +++ b/drivers/staging/wlags49_h2/wl_wext.c @@ -1061,7 +1061,7 @@ static int wireless_set_essid(struct net_device *dev, struct iw_request_info *in goto out; } - if (data->flags != 0 && data->length > HCF_MAX_NAME_LEN + 1) { + if (data->flags != 0 && data->length > HCF_MAX_NAME_LEN) { ret = -EINVAL; goto out; } diff --git a/drivers/target/iscsi/iscsi_target_erl1.c b/drivers/target/iscsi/iscsi_target_erl1.c index e048d6439f4a..cda4d80cfaef 100644 --- a/drivers/target/iscsi/iscsi_target_erl1.c +++ b/drivers/target/iscsi/iscsi_target_erl1.c @@ -507,7 +507,9 @@ int iscsit_handle_status_snack( u32 last_statsn; int found_cmd; - if (conn->exp_statsn > begrun) { + if (!begrun) { + begrun = conn->exp_statsn; + } else if (conn->exp_statsn > begrun) { pr_err("Got Status SNACK Begrun: 0x%08x, RunLength:" " 0x%08x but already got ExpStatSN: 0x%08x on CID:" " %hu.\n", begrun, runlength, conn->exp_statsn, diff --git a/drivers/target/target_core_alua.c b/drivers/target/target_core_alua.c index 12da9b386169..c3d9df6aaf5f 100644 --- a/drivers/target/target_core_alua.c +++ b/drivers/target/target_core_alua.c @@ -500,7 +500,7 @@ static inline int core_alua_state_lba_dependent( if (segment_mult) { u64 tmp = lba; - start_lba = sector_div(tmp, segment_size * segment_mult); + start_lba = do_div(tmp, segment_size * segment_mult); last_lba = first_lba + segment_size - 1; if (start_lba >= first_lba && diff --git a/drivers/target/target_core_pr.c b/drivers/target/target_core_pr.c index 2f5d77932c80..3013287a2aaa 100644 --- a/drivers/target/target_core_pr.c +++ b/drivers/target/target_core_pr.c @@ -2009,7 +2009,7 @@ core_scsi3_emulate_pro_register(struct se_cmd *cmd, u64 res_key, u64 sa_res_key, struct t10_reservation *pr_tmpl = &dev->t10_pr; unsigned char isid_buf[PR_REG_ISID_LEN], *isid_ptr = NULL; sense_reason_t ret = TCM_NO_SENSE; - int pr_holder = 0; + int pr_holder = 0, type; if (!se_sess || !se_lun) { pr_err("SPC-3 PR: se_sess || struct se_lun is NULL!\n"); @@ -2131,6 +2131,7 @@ core_scsi3_emulate_pro_register(struct se_cmd *cmd, u64 res_key, u64 sa_res_key, ret = TCM_RESERVATION_CONFLICT; goto out; } + type = pr_reg->pr_res_type; spin_lock(&pr_tmpl->registration_lock); /* @@ -2161,6 +2162,7 @@ core_scsi3_emulate_pro_register(struct se_cmd *cmd, u64 res_key, u64 sa_res_key, * Release the calling I_T Nexus registration now.. */ __core_scsi3_free_registration(cmd->se_dev, pr_reg, NULL, 1); + pr_reg = NULL; /* * From spc4r17, section 5.7.11.3 Unregistering @@ -2174,8 +2176,8 @@ core_scsi3_emulate_pro_register(struct se_cmd *cmd, u64 res_key, u64 sa_res_key, * RESERVATIONS RELEASED. */ if (pr_holder && - (pr_reg->pr_res_type == PR_TYPE_WRITE_EXCLUSIVE_REGONLY || - pr_reg->pr_res_type == PR_TYPE_EXCLUSIVE_ACCESS_REGONLY)) { + (type == PR_TYPE_WRITE_EXCLUSIVE_REGONLY || + type == PR_TYPE_EXCLUSIVE_ACCESS_REGONLY)) { list_for_each_entry(pr_reg_p, &pr_tmpl->registration_list, pr_reg_list) { @@ -2194,7 +2196,8 @@ core_scsi3_emulate_pro_register(struct se_cmd *cmd, u64 res_key, u64 sa_res_key, ret = core_scsi3_update_and_write_aptpl(dev, aptpl); out: - core_scsi3_put_pr_reg(pr_reg); + if (pr_reg) + core_scsi3_put_pr_reg(pr_reg); return ret; } diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c index fa3cae393e13..42f18fc1067b 100644 --- a/drivers/target/target_core_sbc.c +++ b/drivers/target/target_core_sbc.c @@ -1074,14 +1074,20 @@ sbc_dif_copy_prot(struct se_cmd *cmd, unsigned int sectors, bool read, struct scatterlist *psg; void *paddr, *addr; unsigned int i, len, left; + unsigned int offset = sg_off; left = sectors * dev->prot_length; for_each_sg(cmd->t_prot_sg, psg, cmd->t_prot_nents, i) { len = min(psg->length, left); + if (offset >= sg->length) { + sg = sg_next(sg); + offset = 0; + } + paddr = kmap_atomic(sg_page(psg)) + psg->offset; - addr = kmap_atomic(sg_page(sg)) + sg_off; + addr = kmap_atomic(sg_page(sg)) + sg->offset + offset; if (read) memcpy(paddr, addr, len); @@ -1089,6 +1095,7 @@ sbc_dif_copy_prot(struct se_cmd *cmd, unsigned int sectors, bool read, memcpy(addr, paddr, len); left -= len; + offset += len; kunmap_atomic(paddr); kunmap_atomic(addr); } @@ -1155,7 +1162,7 @@ sbc_dif_verify_read(struct se_cmd *cmd, sector_t start, unsigned int sectors, { struct se_device *dev = cmd->se_dev; struct se_dif_v1_tuple *sdt; - struct scatterlist *dsg; + struct scatterlist *dsg, *psg = sg; sector_t sector = start; void *daddr, *paddr; int i, j, offset = sg_off; @@ -1163,14 +1170,14 @@ sbc_dif_verify_read(struct se_cmd *cmd, sector_t start, unsigned int sectors, for_each_sg(cmd->t_data_sg, dsg, cmd->t_data_nents, i) { daddr = kmap_atomic(sg_page(dsg)) + dsg->offset; - paddr = kmap_atomic(sg_page(sg)) + sg->offset; + paddr = kmap_atomic(sg_page(psg)) + sg->offset; for (j = 0; j < dsg->length; j += dev->dev_attrib.block_size) { - if (offset >= sg->length) { + if (offset >= psg->length) { kunmap_atomic(paddr); - sg = sg_next(sg); - paddr = kmap_atomic(sg_page(sg)) + sg->offset; + psg = sg_next(psg); + paddr = kmap_atomic(sg_page(psg)) + psg->offset; offset = 0; } diff --git a/drivers/target/target_core_spc.c b/drivers/target/target_core_spc.c index 43c5ca9878bc..3bebc71ea033 100644 --- a/drivers/target/target_core_spc.c +++ b/drivers/target/target_core_spc.c @@ -440,8 +440,8 @@ check_scsi_name: padding = ((-scsi_target_len) & 3); if (padding) scsi_target_len += padding; - if (scsi_name_len > 256) - scsi_name_len = 256; + if (scsi_target_len > 256) + scsi_target_len = 256; buf[off-1] = scsi_target_len; off += scsi_target_len; diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index c50fd9f11aab..2956250b7225 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -669,9 +669,6 @@ void target_complete_cmd(struct se_cmd *cmd, u8 scsi_status) return; } - if (!success) - cmd->transport_state |= CMD_T_FAILED; - /* * Check for case where an explicit ABORT_TASK has been received * and transport_wait_for_tasks() will be waiting for completion.. @@ -681,7 +678,7 @@ void target_complete_cmd(struct se_cmd *cmd, u8 scsi_status) spin_unlock_irqrestore(&cmd->t_state_lock, flags); complete(&cmd->t_transport_stop_comp); return; - } else if (cmd->transport_state & CMD_T_FAILED) { + } else if (!success) { INIT_WORK(&cmd->work, target_complete_failure_work); } else { INIT_WORK(&cmd->work, target_complete_ok_work); @@ -1604,6 +1601,9 @@ void transport_generic_request_failure(struct se_cmd *cmd, case TCM_CHECK_CONDITION_ABORT_CMD: case TCM_CHECK_CONDITION_UNIT_ATTENTION: case TCM_CHECK_CONDITION_NOT_READY: + case TCM_LOGICAL_BLOCK_GUARD_CHECK_FAILED: + case TCM_LOGICAL_BLOCK_APP_TAG_CHECK_FAILED: + case TCM_LOGICAL_BLOCK_REF_TAG_CHECK_FAILED: break; case TCM_OUT_OF_RESOURCES: sense_reason = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; diff --git a/drivers/tty/hvc/hvc_opal.c b/drivers/tty/hvc/hvc_opal.c index 6496872e2e47..b01659bd4f7c 100644 --- a/drivers/tty/hvc/hvc_opal.c +++ b/drivers/tty/hvc/hvc_opal.c @@ -255,13 +255,7 @@ static int __init hvc_opal_init(void) /* Register as a vio device to receive callbacks */ return platform_driver_register(&hvc_opal_driver); } -module_init(hvc_opal_init); - -static void __exit hvc_opal_exit(void) -{ - platform_driver_unregister(&hvc_opal_driver); -} -module_exit(hvc_opal_exit); +device_initcall(hvc_opal_init); static void udbg_opal_putc(char c) { diff --git a/drivers/tty/hvc/hvc_rtas.c b/drivers/tty/hvc/hvc_rtas.c index 0069bb86ba49..08c87920b74a 100644 --- a/drivers/tty/hvc/hvc_rtas.c +++ b/drivers/tty/hvc/hvc_rtas.c @@ -102,17 +102,7 @@ static int __init hvc_rtas_init(void) return 0; } -module_init(hvc_rtas_init); - -/* This will tear down the tty portion of the driver */ -static void __exit hvc_rtas_exit(void) -{ - /* Really the fun isn't over until the worker thread breaks down and - * the tty cleans up */ - if (hvc_rtas_dev) - hvc_remove(hvc_rtas_dev); -} -module_exit(hvc_rtas_exit); +device_initcall(hvc_rtas_init); /* This will happen prior to module init. There is no tty at this time? */ static int __init hvc_rtas_console_init(void) diff --git a/drivers/tty/hvc/hvc_udbg.c b/drivers/tty/hvc/hvc_udbg.c index 72228276fe31..9cf573d06a29 100644 --- a/drivers/tty/hvc/hvc_udbg.c +++ b/drivers/tty/hvc/hvc_udbg.c @@ -80,14 +80,7 @@ static int __init hvc_udbg_init(void) return 0; } -module_init(hvc_udbg_init); - -static void __exit hvc_udbg_exit(void) -{ - if (hvc_udbg_dev) - hvc_remove(hvc_udbg_dev); -} -module_exit(hvc_udbg_exit); +device_initcall(hvc_udbg_init); static int __init hvc_udbg_console_init(void) { diff --git a/drivers/tty/hvc/hvc_xen.c b/drivers/tty/hvc/hvc_xen.c index 636c9baad7a5..2dc2831840ca 100644 --- a/drivers/tty/hvc/hvc_xen.c +++ b/drivers/tty/hvc/hvc_xen.c @@ -561,18 +561,7 @@ static int __init xen_hvc_init(void) #endif return r; } - -static void __exit xen_hvc_fini(void) -{ - struct xencons_info *entry, *next; - - if (list_empty(&xenconsoles)) - return; - - list_for_each_entry_safe(entry, next, &xenconsoles, list) { - xen_console_remove(entry); - } -} +device_initcall(xen_hvc_init); static int xen_cons_init(void) { @@ -598,10 +587,6 @@ static int xen_cons_init(void) hvc_instantiate(HVC_COOKIE, 0, ops); return 0; } - - -module_init(xen_hvc_init); -module_exit(xen_hvc_fini); console_initcall(xen_cons_init); #ifdef CONFIG_EARLY_PRINTK diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c index f34461c5f14e..2ebe47b78a3e 100644 --- a/drivers/tty/n_gsm.c +++ b/drivers/tty/n_gsm.c @@ -1090,6 +1090,7 @@ static void gsm_control_modem(struct gsm_mux *gsm, u8 *data, int clen) { unsigned int addr = 0; unsigned int modem = 0; + unsigned int brk = 0; struct gsm_dlci *dlci; int len = clen; u8 *dp = data; @@ -1116,6 +1117,16 @@ static void gsm_control_modem(struct gsm_mux *gsm, u8 *data, int clen) if (len == 0) return; } + len--; + if (len > 0) { + while (gsm_read_ea(&brk, *dp++) == 0) { + len--; + if (len == 0) + return; + } + modem <<= 7; + modem |= (brk & 0x7f); + } tty = tty_port_tty_get(&dlci->port); gsm_process_modem(tty, dlci, modem, clen); if (tty) { diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c index cb8017aa4434..d15624c1b751 100644 --- a/drivers/tty/n_tty.c +++ b/drivers/tty/n_tty.c @@ -817,8 +817,7 @@ static void process_echoes(struct tty_struct *tty) struct n_tty_data *ldata = tty->disc_data; size_t echoed; - if ((!L_ECHO(tty) && !L_ECHONL(tty)) || - ldata->echo_mark == ldata->echo_tail) + if (ldata->echo_mark == ldata->echo_tail) return; mutex_lock(&ldata->output_lock); @@ -1244,7 +1243,8 @@ n_tty_receive_signal_char(struct tty_struct *tty, int signal, unsigned char c) if (L_ECHO(tty)) { echo_char(c, tty); commit_echoes(tty); - } + } else + process_echoes(tty); isig(signal, tty); return; } @@ -1274,7 +1274,7 @@ n_tty_receive_char_special(struct tty_struct *tty, unsigned char c) if (I_IXON(tty)) { if (c == START_CHAR(tty)) { start_tty(tty); - commit_echoes(tty); + process_echoes(tty); return 0; } if (c == STOP_CHAR(tty)) { @@ -1820,8 +1820,10 @@ static void n_tty_set_termios(struct tty_struct *tty, struct ktermios *old) * Fix tty hang when I_IXON(tty) is cleared, but the tty * been stopped by STOP_CHAR(tty) before it. */ - if (!I_IXON(tty) && old && (old->c_iflag & IXON) && !tty->flow_stopped) + if (!I_IXON(tty) && old && (old->c_iflag & IXON) && !tty->flow_stopped) { start_tty(tty); + process_echoes(tty); + } /* The termios change make the tty ready for I/O */ if (waitqueue_active(&tty->write_wait)) @@ -1896,7 +1898,7 @@ err: static inline int input_available_p(struct tty_struct *tty, int poll) { struct n_tty_data *ldata = tty->disc_data; - int amt = poll && !TIME_CHAR(tty) ? MIN_CHAR(tty) : 1; + int amt = poll && !TIME_CHAR(tty) && MIN_CHAR(tty) ? MIN_CHAR(tty) : 1; if (ldata->icanon && !L_EXTPROC(tty)) { if (ldata->canon_head != ldata->read_tail) diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c index 61ecd709a722..69932b7556cf 100644 --- a/drivers/tty/serial/8250/8250_core.c +++ b/drivers/tty/serial/8250/8250_core.c @@ -2433,6 +2433,24 @@ serial8250_do_set_termios(struct uart_port *port, struct ktermios *termios, serial_dl_write(up, quot); /* + * XR17V35x UARTs have an extra fractional divisor register (DLD) + * + * We need to recalculate all of the registers, because DLM and DLL + * are already rounded to a whole integer. + * + * When recalculating we use a 32x clock instead of a 16x clock to + * allow 1-bit for rounding in the fractional part. + */ + if (up->port.type == PORT_XR17V35X) { + unsigned int baud_x32 = (port->uartclk * 2) / baud; + u16 quot = baud_x32 / 32; + u8 quot_frac = DIV_ROUND_CLOSEST(baud_x32 % 32, 2); + + serial_dl_write(up, quot); + serial_port_out(port, 0x2, quot_frac & 0xf); + } + + /* * LCR DLAB must be set to enable 64-byte FIFO mode. If the FCR * is written without DLAB set, this mode will be disabled. */ diff --git a/drivers/tty/serial/8250/8250_dw.c b/drivers/tty/serial/8250/8250_dw.c index faa64e646100..ed3113576740 100644 --- a/drivers/tty/serial/8250/8250_dw.c +++ b/drivers/tty/serial/8250/8250_dw.c @@ -391,7 +391,7 @@ static int dw8250_remove(struct platform_device *pdev) return 0; } -#ifdef CONFIG_PM +#ifdef CONFIG_PM_SLEEP static int dw8250_suspend(struct device *dev) { struct dw8250_data *data = dev_get_drvdata(dev); @@ -409,7 +409,7 @@ static int dw8250_resume(struct device *dev) return 0; } -#endif /* CONFIG_PM */ +#endif /* CONFIG_PM_SLEEP */ #ifdef CONFIG_PM_RUNTIME static int dw8250_runtime_suspend(struct device *dev) diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c index 50228eed3b6f..0ff3e3624d4c 100644 --- a/drivers/tty/serial/8250/8250_pci.c +++ b/drivers/tty/serial/8250/8250_pci.c @@ -783,7 +783,8 @@ static int pci_netmos_9900_setup(struct serial_private *priv, { unsigned int bar; - if ((priv->dev->subsystem_device & 0xff00) == 0x3000) { + if ((priv->dev->device != PCI_DEVICE_ID_NETMOS_9865) && + (priv->dev->subsystem_device & 0xff00) == 0x3000) { /* netmos apparently orders BARs by datasheet layout, so serial * ports get BARs 0 and 3 (or 1 and 4 for memmapped) */ diff --git a/drivers/tty/serial/omap-serial.c b/drivers/tty/serial/omap-serial.c index fa511ebab67c..77f035158d6c 100644 --- a/drivers/tty/serial/omap-serial.c +++ b/drivers/tty/serial/omap-serial.c @@ -738,9 +738,6 @@ static int serial_omap_startup(struct uart_port *port) return retval; } disable_irq(up->wakeirq); - } else { - dev_info(up->port.dev, "no wakeirq for uart%d\n", - up->port.line); } dev_dbg(up->port.dev, "serial_omap_startup+%d\n", up->port.line); @@ -1604,8 +1601,11 @@ static int serial_omap_probe_rs485(struct uart_omap_port *up, flags & SER_RS485_RTS_AFTER_SEND); if (ret < 0) return ret; - } else + } else if (up->rts_gpio == -EPROBE_DEFER) { + return -EPROBE_DEFER; + } else { up->rts_gpio = -EINVAL; + } if (of_property_read_u32_array(np, "rs485-rts-delay", rs485_delay, 2) == 0) { @@ -1687,6 +1687,9 @@ static int serial_omap_probe(struct platform_device *pdev) up->port.iotype = UPIO_MEM; up->port.irq = uartirq; up->wakeirq = wakeirq; + if (!up->wakeirq) + dev_info(up->port.dev, "no wakeirq for uart%d\n", + up->port.line); up->port.regshift = 2; up->port.fifosize = 64; diff --git a/drivers/tty/serial/sirfsoc_uart.c b/drivers/tty/serial/sirfsoc_uart.c index 49a2ffd101a7..b7bfe24d4ebc 100644 --- a/drivers/tty/serial/sirfsoc_uart.c +++ b/drivers/tty/serial/sirfsoc_uart.c @@ -542,8 +542,10 @@ static void sirfsoc_rx_tmo_process_tl(unsigned long param) wr_regl(port, ureg->sirfsoc_rx_dma_io_ctrl, rd_regl(port, ureg->sirfsoc_rx_dma_io_ctrl) | SIRFUART_IO_MODE); - sirfsoc_uart_pio_rx_chars(port, 4 - sirfport->rx_io_count); spin_unlock_irqrestore(&sirfport->rx_lock, flags); + spin_lock(&port->lock); + sirfsoc_uart_pio_rx_chars(port, 4 - sirfport->rx_io_count); + spin_unlock(&port->lock); if (sirfport->rx_io_count == 4) { spin_lock_irqsave(&sirfport->rx_lock, flags); sirfport->rx_io_count = 0; diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index 61b1137d7e56..23b5d32954bf 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -1164,6 +1164,8 @@ static void csi_J(struct vc_data *vc, int vpar) scr_memsetw(vc->vc_screenbuf, vc->vc_video_erase_char, vc->vc_screenbuf_size >> 1); set_origin(vc); + if (CON_IS_VISIBLE(vc)) + update_screen(vc); /* fall through */ case 2: /* erase whole display */ count = vc->vc_cols * vc->vc_rows; diff --git a/drivers/usb/chipidea/udc.c b/drivers/usb/chipidea/udc.c index 80de2f88ed2c..4ab2cb62dfce 100644 --- a/drivers/usb/chipidea/udc.c +++ b/drivers/usb/chipidea/udc.c @@ -105,7 +105,7 @@ static int hw_ep_flush(struct ci_hdrc *ci, int num, int dir) do { /* flush any pending transfer */ - hw_write(ci, OP_ENDPTFLUSH, BIT(n), BIT(n)); + hw_write(ci, OP_ENDPTFLUSH, ~0, BIT(n)); while (hw_read(ci, OP_ENDPTFLUSH, BIT(n))) cpu_relax(); } while (hw_read(ci, OP_ENDPTSTAT, BIT(n))); @@ -205,7 +205,7 @@ static int hw_ep_prime(struct ci_hdrc *ci, int num, int dir, int is_ctrl) if (is_ctrl && dir == RX && hw_read(ci, OP_ENDPTSETUPSTAT, BIT(num))) return -EAGAIN; - hw_write(ci, OP_ENDPTPRIME, BIT(n), BIT(n)); + hw_write(ci, OP_ENDPTPRIME, ~0, BIT(n)); while (hw_read(ci, OP_ENDPTPRIME, BIT(n))) cpu_relax(); diff --git a/drivers/usb/core/driver.c b/drivers/usb/core/driver.c index 5d01558cef66..ab90a0156828 100644 --- a/drivers/usb/core/driver.c +++ b/drivers/usb/core/driver.c @@ -63,8 +63,10 @@ ssize_t usb_store_new_id(struct usb_dynids *dynids, dynid->id.idProduct = idProduct; dynid->id.match_flags = USB_DEVICE_ID_MATCH_DEVICE; if (fields > 2 && bInterfaceClass) { - if (bInterfaceClass > 255) - return -EINVAL; + if (bInterfaceClass > 255) { + retval = -EINVAL; + goto fail; + } dynid->id.bInterfaceClass = (u8)bInterfaceClass; dynid->id.match_flags |= USB_DEVICE_ID_MATCH_INT_CLASS; @@ -73,17 +75,21 @@ ssize_t usb_store_new_id(struct usb_dynids *dynids, if (fields > 4) { const struct usb_device_id *id = id_table; - if (!id) - return -ENODEV; + if (!id) { + retval = -ENODEV; + goto fail; + } for (; id->match_flags; id++) if (id->idVendor == refVendor && id->idProduct == refProduct) break; - if (id->match_flags) + if (id->match_flags) { dynid->id.driver_info = id->driver_info; - else - return -ENODEV; + } else { + retval = -ENODEV; + goto fail; + } } spin_lock(&dynids->lock); @@ -95,6 +101,10 @@ ssize_t usb_store_new_id(struct usb_dynids *dynids, if (retval) return retval; return count; + +fail: + kfree(dynid); + return retval; } EXPORT_SYMBOL_GPL(usb_store_new_id); diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c index 199aaea6bfe0..2518c3250750 100644 --- a/drivers/usb/core/hcd.c +++ b/drivers/usb/core/hcd.c @@ -1032,7 +1032,6 @@ static int register_root_hub(struct usb_hcd *hcd) dev_name(&usb_dev->dev), retval); return retval; } - usb_dev->lpm_capable = usb_device_supports_lpm(usb_dev); } retval = usb_new_device (usb_dev); diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index babba885978d..64ea21971be2 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -128,7 +128,7 @@ struct usb_hub *usb_hub_to_struct_hub(struct usb_device *hdev) return usb_get_intfdata(hdev->actconfig->interface[0]); } -int usb_device_supports_lpm(struct usb_device *udev) +static int usb_device_supports_lpm(struct usb_device *udev) { /* USB 2.1 (and greater) devices indicate LPM support through * their USB 2.0 Extended Capabilities BOS descriptor. @@ -149,11 +149,6 @@ int usb_device_supports_lpm(struct usb_device *udev) "Power management will be impacted.\n"); return 0; } - - /* udev is root hub */ - if (!udev->parent) - return 1; - if (udev->parent->lpm_capable) return 1; diff --git a/drivers/usb/core/usb.h b/drivers/usb/core/usb.h index c49383669cd8..823857767a16 100644 --- a/drivers/usb/core/usb.h +++ b/drivers/usb/core/usb.h @@ -35,7 +35,6 @@ extern int usb_get_device_descriptor(struct usb_device *dev, unsigned int size); extern int usb_get_bos_descriptor(struct usb_device *dev); extern void usb_release_bos_descriptor(struct usb_device *dev); -extern int usb_device_supports_lpm(struct usb_device *udev); extern char *usb_cache_string(struct usb_device *udev, int index); extern int usb_set_configuration(struct usb_device *dev, int configuration); extern int usb_choose_configuration(struct usb_device *udev); diff --git a/drivers/usb/dwc2/core.c b/drivers/usb/dwc2/core.c index 8565d87f94b4..1d129884cc39 100644 --- a/drivers/usb/dwc2/core.c +++ b/drivers/usb/dwc2/core.c @@ -216,7 +216,7 @@ static int dwc2_hs_phy_init(struct dwc2_hsotg *hsotg, bool select_phy) int retval = 0; if (!select_phy) - return -ENODEV; + return 0; usbcfg = readl(hsotg->regs + GUSBCFG); diff --git a/drivers/usb/dwc2/hcd.c b/drivers/usb/dwc2/hcd.c index f59484d43b35..4d918ed8d343 100644 --- a/drivers/usb/dwc2/hcd.c +++ b/drivers/usb/dwc2/hcd.c @@ -2565,25 +2565,14 @@ static void _dwc2_hcd_endpoint_reset(struct usb_hcd *hcd, struct usb_host_endpoint *ep) { struct dwc2_hsotg *hsotg = dwc2_hcd_to_hsotg(hcd); - int is_control = usb_endpoint_xfer_control(&ep->desc); - int is_out = usb_endpoint_dir_out(&ep->desc); - int epnum = usb_endpoint_num(&ep->desc); - struct usb_device *udev; unsigned long flags; dev_dbg(hsotg->dev, "DWC OTG HCD EP RESET: bEndpointAddress=0x%02x\n", ep->desc.bEndpointAddress); - udev = to_usb_device(hsotg->dev); - spin_lock_irqsave(&hsotg->lock, flags); - - usb_settoggle(udev, epnum, is_out, 0); - if (is_control) - usb_settoggle(udev, epnum, !is_out, 0); dwc2_hcd_endpoint_reset(hsotg, ep); - spin_unlock_irqrestore(&hsotg->lock, flags); } diff --git a/drivers/usb/dwc2/platform.c b/drivers/usb/dwc2/platform.c index d01d0d3f2cf0..eaba547ce26b 100644 --- a/drivers/usb/dwc2/platform.c +++ b/drivers/usb/dwc2/platform.c @@ -124,6 +124,9 @@ static int dwc2_driver_probe(struct platform_device *dev) int retval; int irq; + if (usb_disabled()) + return -ENODEV; + match = of_match_device(dwc2_of_match_table, &dev->dev); if (match && match->data) { params = match->data; diff --git a/drivers/usb/gadget/bcm63xx_udc.c b/drivers/usb/gadget/bcm63xx_udc.c index 888fbb43b338..e969eb809a85 100644 --- a/drivers/usb/gadget/bcm63xx_udc.c +++ b/drivers/usb/gadget/bcm63xx_udc.c @@ -360,24 +360,30 @@ static inline void usb_dma_writel(struct bcm63xx_udc *udc, u32 val, u32 off) bcm_writel(val, udc->iudma_regs + off); } -static inline u32 usb_dmac_readl(struct bcm63xx_udc *udc, u32 off) +static inline u32 usb_dmac_readl(struct bcm63xx_udc *udc, u32 off, int chan) { - return bcm_readl(udc->iudma_regs + IUDMA_DMAC_OFFSET + off); + return bcm_readl(udc->iudma_regs + IUDMA_DMAC_OFFSET + off + + (ENETDMA_CHAN_WIDTH * chan)); } -static inline void usb_dmac_writel(struct bcm63xx_udc *udc, u32 val, u32 off) +static inline void usb_dmac_writel(struct bcm63xx_udc *udc, u32 val, u32 off, + int chan) { - bcm_writel(val, udc->iudma_regs + IUDMA_DMAC_OFFSET + off); + bcm_writel(val, udc->iudma_regs + IUDMA_DMAC_OFFSET + off + + (ENETDMA_CHAN_WIDTH * chan)); } -static inline u32 usb_dmas_readl(struct bcm63xx_udc *udc, u32 off) +static inline u32 usb_dmas_readl(struct bcm63xx_udc *udc, u32 off, int chan) { - return bcm_readl(udc->iudma_regs + IUDMA_DMAS_OFFSET + off); + return bcm_readl(udc->iudma_regs + IUDMA_DMAS_OFFSET + off + + (ENETDMA_CHAN_WIDTH * chan)); } -static inline void usb_dmas_writel(struct bcm63xx_udc *udc, u32 val, u32 off) +static inline void usb_dmas_writel(struct bcm63xx_udc *udc, u32 val, u32 off, + int chan) { - bcm_writel(val, udc->iudma_regs + IUDMA_DMAS_OFFSET + off); + bcm_writel(val, udc->iudma_regs + IUDMA_DMAS_OFFSET + off + + (ENETDMA_CHAN_WIDTH * chan)); } static inline void set_clocks(struct bcm63xx_udc *udc, bool is_enabled) @@ -638,7 +644,7 @@ static void iudma_write(struct bcm63xx_udc *udc, struct iudma_ch *iudma, } while (!last_bd); usb_dmac_writel(udc, ENETDMAC_CHANCFG_EN_MASK, - ENETDMAC_CHANCFG_REG(iudma->ch_idx)); + ENETDMAC_CHANCFG_REG, iudma->ch_idx); } /** @@ -694,9 +700,9 @@ static void iudma_reset_channel(struct bcm63xx_udc *udc, struct iudma_ch *iudma) bcm63xx_fifo_reset_ep(udc, max(0, iudma->ep_num)); /* stop DMA, then wait for the hardware to wrap up */ - usb_dmac_writel(udc, 0, ENETDMAC_CHANCFG_REG(ch_idx)); + usb_dmac_writel(udc, 0, ENETDMAC_CHANCFG_REG, ch_idx); - while (usb_dmac_readl(udc, ENETDMAC_CHANCFG_REG(ch_idx)) & + while (usb_dmac_readl(udc, ENETDMAC_CHANCFG_REG, ch_idx) & ENETDMAC_CHANCFG_EN_MASK) { udelay(1); @@ -713,10 +719,10 @@ static void iudma_reset_channel(struct bcm63xx_udc *udc, struct iudma_ch *iudma) dev_warn(udc->dev, "forcibly halting IUDMA channel %d\n", ch_idx); usb_dmac_writel(udc, ENETDMAC_CHANCFG_BUFHALT_MASK, - ENETDMAC_CHANCFG_REG(ch_idx)); + ENETDMAC_CHANCFG_REG, ch_idx); } } - usb_dmac_writel(udc, ~0, ENETDMAC_IR_REG(ch_idx)); + usb_dmac_writel(udc, ~0, ENETDMAC_IR_REG, ch_idx); /* don't leave "live" HW-owned entries for the next guy to step on */ for (d = iudma->bd_ring; d <= iudma->end_bd; d++) @@ -728,11 +734,11 @@ static void iudma_reset_channel(struct bcm63xx_udc *udc, struct iudma_ch *iudma) /* set up IRQs, UBUS burst size, and BD base for this channel */ usb_dmac_writel(udc, ENETDMAC_IR_BUFDONE_MASK, - ENETDMAC_IRMASK_REG(ch_idx)); - usb_dmac_writel(udc, 8, ENETDMAC_MAXBURST_REG(ch_idx)); + ENETDMAC_IRMASK_REG, ch_idx); + usb_dmac_writel(udc, 8, ENETDMAC_MAXBURST_REG, ch_idx); - usb_dmas_writel(udc, iudma->bd_ring_dma, ENETDMAS_RSTART_REG(ch_idx)); - usb_dmas_writel(udc, 0, ENETDMAS_SRAM2_REG(ch_idx)); + usb_dmas_writel(udc, iudma->bd_ring_dma, ENETDMAS_RSTART_REG, ch_idx); + usb_dmas_writel(udc, 0, ENETDMAS_SRAM2_REG, ch_idx); } /** @@ -2035,7 +2041,7 @@ static irqreturn_t bcm63xx_udc_data_isr(int irq, void *dev_id) spin_lock(&udc->lock); usb_dmac_writel(udc, ENETDMAC_IR_BUFDONE_MASK, - ENETDMAC_IR_REG(iudma->ch_idx)); + ENETDMAC_IR_REG, iudma->ch_idx); bep = iudma->bep; rc = iudma_read(udc, iudma); @@ -2175,18 +2181,18 @@ static int bcm63xx_iudma_dbg_show(struct seq_file *s, void *p) seq_printf(s, " [ep%d]:\n", max_t(int, iudma_defaults[ch_idx].ep_num, 0)); seq_printf(s, " cfg: %08x; irqstat: %08x; irqmask: %08x; maxburst: %08x\n", - usb_dmac_readl(udc, ENETDMAC_CHANCFG_REG(ch_idx)), - usb_dmac_readl(udc, ENETDMAC_IR_REG(ch_idx)), - usb_dmac_readl(udc, ENETDMAC_IRMASK_REG(ch_idx)), - usb_dmac_readl(udc, ENETDMAC_MAXBURST_REG(ch_idx))); + usb_dmac_readl(udc, ENETDMAC_CHANCFG_REG, ch_idx), + usb_dmac_readl(udc, ENETDMAC_IR_REG, ch_idx), + usb_dmac_readl(udc, ENETDMAC_IRMASK_REG, ch_idx), + usb_dmac_readl(udc, ENETDMAC_MAXBURST_REG, ch_idx)); - sram2 = usb_dmas_readl(udc, ENETDMAS_SRAM2_REG(ch_idx)); - sram3 = usb_dmas_readl(udc, ENETDMAS_SRAM3_REG(ch_idx)); + sram2 = usb_dmas_readl(udc, ENETDMAS_SRAM2_REG, ch_idx); + sram3 = usb_dmas_readl(udc, ENETDMAS_SRAM3_REG, ch_idx); seq_printf(s, " base: %08x; index: %04x_%04x; desc: %04x_%04x %08x\n", - usb_dmas_readl(udc, ENETDMAS_RSTART_REG(ch_idx)), + usb_dmas_readl(udc, ENETDMAS_RSTART_REG, ch_idx), sram2 >> 16, sram2 & 0xffff, sram3 >> 16, sram3 & 0xffff, - usb_dmas_readl(udc, ENETDMAS_SRAM4_REG(ch_idx))); + usb_dmas_readl(udc, ENETDMAS_SRAM4_REG, ch_idx)); seq_printf(s, " desc: %d/%d used", iudma->n_bds_used, iudma->n_bds); diff --git a/drivers/usb/gadget/f_fs.c b/drivers/usb/gadget/f_fs.c index 306a2b52125c..2b4334394076 100644 --- a/drivers/usb/gadget/f_fs.c +++ b/drivers/usb/gadget/f_fs.c @@ -585,7 +585,6 @@ static ssize_t ffs_epfile_io(struct file *file, char __user *buf, size_t len, int read) { struct ffs_epfile *epfile = file->private_data; - struct usb_gadget *gadget = epfile->ffs->gadget; struct ffs_ep *ep; char *data = NULL; ssize_t ret, data_len; @@ -622,6 +621,12 @@ static ssize_t ffs_epfile_io(struct file *file, /* Allocate & copy */ if (!halt) { /* + * if we _do_ wait above, the epfile->ffs->gadget might be NULL + * before the waiting completes, so do not assign to 'gadget' earlier + */ + struct usb_gadget *gadget = epfile->ffs->gadget; + + /* * Controller may require buffer size to be aligned to * maxpacketsize of an out endpoint. */ diff --git a/drivers/usb/gadget/printer.c b/drivers/usb/gadget/printer.c index bf7a56b6d48a..69b76efd11e9 100644 --- a/drivers/usb/gadget/printer.c +++ b/drivers/usb/gadget/printer.c @@ -1157,7 +1157,7 @@ static int __init printer_bind_config(struct usb_configuration *c) usb_gadget_set_selfpowered(gadget); - if (gadget->is_otg) { + if (gadget_is_otg(gadget)) { otg_descriptor.bmAttributes |= USB_OTG_HNP; printer_cfg_driver.descriptors = otg_desc; printer_cfg_driver.bmAttributes |= USB_CONFIG_ATT_WAKEUP; diff --git a/drivers/usb/gadget/s3c2410_udc.c b/drivers/usb/gadget/s3c2410_udc.c index f04b2c3154de..dd9678f85c58 100644 --- a/drivers/usb/gadget/s3c2410_udc.c +++ b/drivers/usb/gadget/s3c2410_udc.c @@ -1629,7 +1629,7 @@ static void s3c2410_udc_reinit(struct s3c2410_udc *dev) ep->ep.desc = NULL; ep->halted = 0; INIT_LIST_HEAD(&ep->queue); - usb_ep_set_maxpacket_limit(&ep->ep, &ep->ep.maxpacket); + usb_ep_set_maxpacket_limit(&ep->ep, ep->ep.maxpacket); } } diff --git a/drivers/usb/host/ehci-hcd.c b/drivers/usb/host/ehci-hcd.c index 471142725ffe..81cda09b47e3 100644 --- a/drivers/usb/host/ehci-hcd.c +++ b/drivers/usb/host/ehci-hcd.c @@ -685,8 +685,15 @@ static irqreturn_t ehci_irq (struct usb_hcd *hcd) struct ehci_hcd *ehci = hcd_to_ehci (hcd); u32 status, masked_status, pcd_status = 0, cmd; int bh; + unsigned long flags; - spin_lock (&ehci->lock); + /* + * For threadirqs option we use spin_lock_irqsave() variant to prevent + * deadlock with ehci hrtimer callback, because hrtimer callbacks run + * in interrupt context even when threadirqs is specified. We can go + * back to spin_lock() variant when hrtimer callbacks become threaded. + */ + spin_lock_irqsave(&ehci->lock, flags); status = ehci_readl(ehci, &ehci->regs->status); @@ -704,7 +711,7 @@ static irqreturn_t ehci_irq (struct usb_hcd *hcd) /* Shared IRQ? */ if (!masked_status || unlikely(ehci->rh_state == EHCI_RH_HALTED)) { - spin_unlock(&ehci->lock); + spin_unlock_irqrestore(&ehci->lock, flags); return IRQ_NONE; } @@ -815,7 +822,7 @@ dead: if (bh) ehci_work (ehci); - spin_unlock (&ehci->lock); + spin_unlock_irqrestore(&ehci->lock, flags); if (pcd_status) usb_hcd_poll_rh_status(hcd); return IRQ_HANDLED; diff --git a/drivers/usb/host/ehci-hub.c b/drivers/usb/host/ehci-hub.c index 47b858fc50b2..7ae0c4d51741 100644 --- a/drivers/usb/host/ehci-hub.c +++ b/drivers/usb/host/ehci-hub.c @@ -238,6 +238,7 @@ static int ehci_bus_suspend (struct usb_hcd *hcd) int port; int mask; int changed; + bool fs_idle_delay; ehci_dbg(ehci, "suspend root hub\n"); @@ -272,6 +273,7 @@ static int ehci_bus_suspend (struct usb_hcd *hcd) ehci->bus_suspended = 0; ehci->owned_ports = 0; changed = 0; + fs_idle_delay = false; port = HCS_N_PORTS(ehci->hcs_params); while (port--) { u32 __iomem *reg = &ehci->regs->port_status [port]; @@ -300,16 +302,32 @@ static int ehci_bus_suspend (struct usb_hcd *hcd) } if (t1 != t2) { + /* + * On some controllers, Wake-On-Disconnect will + * generate false wakeup signals until the bus + * switches over to full-speed idle. For their + * sake, add a delay if we need one. + */ + if ((t2 & PORT_WKDISC_E) && + ehci_port_speed(ehci, t2) == + USB_PORT_STAT_HIGH_SPEED) + fs_idle_delay = true; ehci_writel(ehci, t2, reg); changed = 1; } } + spin_unlock_irq(&ehci->lock); + + if ((changed && ehci->has_tdi_phy_lpm) || fs_idle_delay) { + /* + * Wait for HCD to enter low-power mode or for the bus + * to switch to full-speed idle. + */ + usleep_range(5000, 5500); + } if (changed && ehci->has_tdi_phy_lpm) { - spin_unlock_irq(&ehci->lock); - msleep(5); /* 5 ms for HCD to enter low-power mode */ spin_lock_irq(&ehci->lock); - port = HCS_N_PORTS(ehci->hcs_params); while (port--) { u32 __iomem *hostpc_reg = &ehci->regs->hostpc[port]; @@ -322,8 +340,8 @@ static int ehci_bus_suspend (struct usb_hcd *hcd) port, (t3 & HOSTPC_PHCD) ? "succeeded" : "failed"); } + spin_unlock_irq(&ehci->lock); } - spin_unlock_irq(&ehci->lock); /* Apparently some devices need a >= 1-uframe delay here */ if (ehci->bus_suspended) diff --git a/drivers/usb/host/xhci-dbg.c b/drivers/usb/host/xhci-dbg.c index b016d38199f2..eb009a457fb5 100644 --- a/drivers/usb/host/xhci-dbg.c +++ b/drivers/usb/host/xhci-dbg.c @@ -203,12 +203,12 @@ void xhci_print_ir_set(struct xhci_hcd *xhci, int set_num) addr, (unsigned int)temp); addr = &ir_set->erst_base; - temp_64 = readq(addr); + temp_64 = xhci_read_64(xhci, addr); xhci_dbg(xhci, " %p: ir_set.erst_base = @%08llx\n", addr, temp_64); addr = &ir_set->erst_dequeue; - temp_64 = readq(addr); + temp_64 = xhci_read_64(xhci, addr); xhci_dbg(xhci, " %p: ir_set.erst_dequeue = @%08llx\n", addr, temp_64); } @@ -412,7 +412,7 @@ void xhci_dbg_cmd_ptrs(struct xhci_hcd *xhci) { u64 val; - val = readq(&xhci->op_regs->cmd_ring); + val = xhci_read_64(xhci, &xhci->op_regs->cmd_ring); xhci_dbg(xhci, "// xHC command ring deq ptr low bits + flags = @%08x\n", lower_32_bits(val)); xhci_dbg(xhci, "// xHC command ring deq ptr high bits = @%08x\n", diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c index 873c272b3ef5..bce4391a0e7d 100644 --- a/drivers/usb/host/xhci-mem.c +++ b/drivers/usb/host/xhci-mem.c @@ -1958,7 +1958,7 @@ static void xhci_set_hc_event_deq(struct xhci_hcd *xhci) xhci_warn(xhci, "WARN something wrong with SW event ring " "dequeue ptr.\n"); /* Update HC event ring dequeue pointer */ - temp = readq(&xhci->ir_set->erst_dequeue); + temp = xhci_read_64(xhci, &xhci->ir_set->erst_dequeue); temp &= ERST_PTR_MASK; /* Don't clear the EHB bit (which is RW1C) because * there might be more events to service. @@ -1967,7 +1967,7 @@ static void xhci_set_hc_event_deq(struct xhci_hcd *xhci) xhci_dbg_trace(xhci, trace_xhci_dbg_init, "// Write event ring dequeue pointer, " "preserving EHB bit"); - writeq(((u64) deq & (u64) ~ERST_PTR_MASK) | temp, + xhci_write_64(xhci, ((u64) deq & (u64) ~ERST_PTR_MASK) | temp, &xhci->ir_set->erst_dequeue); } @@ -2269,7 +2269,7 @@ int xhci_mem_init(struct xhci_hcd *xhci, gfp_t flags) xhci_dbg_trace(xhci, trace_xhci_dbg_init, "// Device context base array address = 0x%llx (DMA), %p (virt)", (unsigned long long)xhci->dcbaa->dma, xhci->dcbaa); - writeq(dma, &xhci->op_regs->dcbaa_ptr); + xhci_write_64(xhci, dma, &xhci->op_regs->dcbaa_ptr); /* * Initialize the ring segment pool. The ring must be a contiguous @@ -2312,13 +2312,13 @@ int xhci_mem_init(struct xhci_hcd *xhci, gfp_t flags) (unsigned long long)xhci->cmd_ring->first_seg->dma); /* Set the address in the Command Ring Control register */ - val_64 = readq(&xhci->op_regs->cmd_ring); + val_64 = xhci_read_64(xhci, &xhci->op_regs->cmd_ring); val_64 = (val_64 & (u64) CMD_RING_RSVD_BITS) | (xhci->cmd_ring->first_seg->dma & (u64) ~CMD_RING_RSVD_BITS) | xhci->cmd_ring->cycle_state; xhci_dbg_trace(xhci, trace_xhci_dbg_init, "// Setting command ring address to 0x%x", val); - writeq(val_64, &xhci->op_regs->cmd_ring); + xhci_write_64(xhci, val_64, &xhci->op_regs->cmd_ring); xhci_dbg_cmd_ptrs(xhci); xhci->lpm_command = xhci_alloc_command(xhci, true, true, flags); @@ -2396,10 +2396,10 @@ int xhci_mem_init(struct xhci_hcd *xhci, gfp_t flags) xhci_dbg_trace(xhci, trace_xhci_dbg_init, "// Set ERST base address for ir_set 0 = 0x%llx", (unsigned long long)xhci->erst.erst_dma_addr); - val_64 = readq(&xhci->ir_set->erst_base); + val_64 = xhci_read_64(xhci, &xhci->ir_set->erst_base); val_64 &= ERST_PTR_MASK; val_64 |= (xhci->erst.erst_dma_addr & (u64) ~ERST_PTR_MASK); - writeq(val_64, &xhci->ir_set->erst_base); + xhci_write_64(xhci, val_64, &xhci->ir_set->erst_base); /* Set the event ring dequeue address */ xhci_set_hc_event_deq(xhci); diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index 3c898c12a06b..04f986d9234f 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -142,6 +142,11 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) "QUIRK: Resetting on resume"); xhci->quirks |= XHCI_TRUST_TX_LENGTH; } + if (pdev->vendor == PCI_VENDOR_ID_RENESAS && + pdev->device == 0x0015 && + pdev->subsystem_vendor == PCI_VENDOR_ID_SAMSUNG && + pdev->subsystem_device == 0xc0cd) + xhci->quirks |= XHCI_RESET_ON_RESUME; if (pdev->vendor == PCI_VENDOR_ID_VIA) xhci->quirks |= XHCI_RESET_ON_RESUME; } diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index a0b248c34526..0ed64eb68e48 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -307,13 +307,14 @@ static int xhci_abort_cmd_ring(struct xhci_hcd *xhci) return 0; } - temp_64 = readq(&xhci->op_regs->cmd_ring); + temp_64 = xhci_read_64(xhci, &xhci->op_regs->cmd_ring); if (!(temp_64 & CMD_RING_RUNNING)) { xhci_dbg(xhci, "Command ring had been stopped\n"); return 0; } xhci->cmd_ring_state = CMD_RING_STATE_ABORTED; - writeq(temp_64 | CMD_RING_ABORT, &xhci->op_regs->cmd_ring); + xhci_write_64(xhci, temp_64 | CMD_RING_ABORT, + &xhci->op_regs->cmd_ring); /* Section 4.6.1.2 of xHCI 1.0 spec says software should * time the completion od all xHCI commands, including @@ -2864,8 +2865,9 @@ hw_died: /* Clear the event handler busy flag (RW1C); * the event ring should be empty. */ - temp_64 = readq(&xhci->ir_set->erst_dequeue); - writeq(temp_64 | ERST_EHB, &xhci->ir_set->erst_dequeue); + temp_64 = xhci_read_64(xhci, &xhci->ir_set->erst_dequeue); + xhci_write_64(xhci, temp_64 | ERST_EHB, + &xhci->ir_set->erst_dequeue); spin_unlock(&xhci->lock); return IRQ_HANDLED; @@ -2877,7 +2879,7 @@ hw_died: */ while (xhci_handle_event(xhci) > 0) {} - temp_64 = readq(&xhci->ir_set->erst_dequeue); + temp_64 = xhci_read_64(xhci, &xhci->ir_set->erst_dequeue); /* If necessary, update the HW's version of the event ring deq ptr. */ if (event_ring_deq != xhci->event_ring->dequeue) { deq = xhci_trb_virt_to_dma(xhci->event_ring->deq_seg, @@ -2892,7 +2894,7 @@ hw_died: /* Clear the event handler busy flag (RW1C); event ring is empty. */ temp_64 |= ERST_EHB; - writeq(temp_64, &xhci->ir_set->erst_dequeue); + xhci_write_64(xhci, temp_64, &xhci->ir_set->erst_dequeue); spin_unlock(&xhci->lock); @@ -2965,58 +2967,8 @@ static int prepare_ring(struct xhci_hcd *xhci, struct xhci_ring *ep_ring, } while (1) { - if (room_on_ring(xhci, ep_ring, num_trbs)) { - union xhci_trb *trb = ep_ring->enqueue; - unsigned int usable = ep_ring->enq_seg->trbs + - TRBS_PER_SEGMENT - 1 - trb; - u32 nop_cmd; - - /* - * Section 4.11.7.1 TD Fragments states that a link - * TRB must only occur at the boundary between - * data bursts (eg 512 bytes for 480M). - * While it is possible to split a large fragment - * we don't know the size yet. - * Simplest solution is to fill the trb before the - * LINK with nop commands. - */ - if (num_trbs == 1 || num_trbs <= usable || usable == 0) - break; - - if (ep_ring->type != TYPE_BULK) - /* - * While isoc transfers might have a buffer that - * crosses a 64k boundary it is unlikely. - * Since we can't add NOPs without generating - * gaps in the traffic just hope it never - * happens at the end of the ring. - * This could be fixed by writing a LINK TRB - * instead of the first NOP - however the - * TRB_TYPE_LINK_LE32() calls would all need - * changing to check the ring length. - */ - break; - - if (num_trbs >= TRBS_PER_SEGMENT) { - xhci_err(xhci, "Too many fragments %d, max %d\n", - num_trbs, TRBS_PER_SEGMENT - 1); - return -EINVAL; - } - - nop_cmd = cpu_to_le32(TRB_TYPE(TRB_TR_NOOP) | - ep_ring->cycle_state); - ep_ring->num_trbs_free -= usable; - do { - trb->generic.field[0] = 0; - trb->generic.field[1] = 0; - trb->generic.field[2] = 0; - trb->generic.field[3] = nop_cmd; - trb++; - } while (--usable); - ep_ring->enqueue = trb; - if (room_on_ring(xhci, ep_ring, num_trbs)) - break; - } + if (room_on_ring(xhci, ep_ring, num_trbs)) + break; if (ep_ring == xhci->cmd_ring) { xhci_err(xhci, "Do not support expand command ring\n"); diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index ad364394885a..6fe577d46fa2 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -611,7 +611,7 @@ int xhci_run(struct usb_hcd *hcd) xhci_dbg(xhci, "Event ring:\n"); xhci_debug_ring(xhci, xhci->event_ring); xhci_dbg_ring_ptrs(xhci, xhci->event_ring); - temp_64 = readq(&xhci->ir_set->erst_dequeue); + temp_64 = xhci_read_64(xhci, &xhci->ir_set->erst_dequeue); temp_64 &= ~ERST_PTR_MASK; xhci_dbg_trace(xhci, trace_xhci_dbg_init, "ERST deq = 64'h%0lx", (long unsigned int) temp_64); @@ -756,11 +756,11 @@ static void xhci_save_registers(struct xhci_hcd *xhci) { xhci->s3.command = readl(&xhci->op_regs->command); xhci->s3.dev_nt = readl(&xhci->op_regs->dev_notification); - xhci->s3.dcbaa_ptr = readq(&xhci->op_regs->dcbaa_ptr); + xhci->s3.dcbaa_ptr = xhci_read_64(xhci, &xhci->op_regs->dcbaa_ptr); xhci->s3.config_reg = readl(&xhci->op_regs->config_reg); xhci->s3.erst_size = readl(&xhci->ir_set->erst_size); - xhci->s3.erst_base = readq(&xhci->ir_set->erst_base); - xhci->s3.erst_dequeue = readq(&xhci->ir_set->erst_dequeue); + xhci->s3.erst_base = xhci_read_64(xhci, &xhci->ir_set->erst_base); + xhci->s3.erst_dequeue = xhci_read_64(xhci, &xhci->ir_set->erst_dequeue); xhci->s3.irq_pending = readl(&xhci->ir_set->irq_pending); xhci->s3.irq_control = readl(&xhci->ir_set->irq_control); } @@ -769,11 +769,11 @@ static void xhci_restore_registers(struct xhci_hcd *xhci) { writel(xhci->s3.command, &xhci->op_regs->command); writel(xhci->s3.dev_nt, &xhci->op_regs->dev_notification); - writeq(xhci->s3.dcbaa_ptr, &xhci->op_regs->dcbaa_ptr); + xhci_write_64(xhci, xhci->s3.dcbaa_ptr, &xhci->op_regs->dcbaa_ptr); writel(xhci->s3.config_reg, &xhci->op_regs->config_reg); writel(xhci->s3.erst_size, &xhci->ir_set->erst_size); - writeq(xhci->s3.erst_base, &xhci->ir_set->erst_base); - writeq(xhci->s3.erst_dequeue, &xhci->ir_set->erst_dequeue); + xhci_write_64(xhci, xhci->s3.erst_base, &xhci->ir_set->erst_base); + xhci_write_64(xhci, xhci->s3.erst_dequeue, &xhci->ir_set->erst_dequeue); writel(xhci->s3.irq_pending, &xhci->ir_set->irq_pending); writel(xhci->s3.irq_control, &xhci->ir_set->irq_control); } @@ -783,7 +783,7 @@ static void xhci_set_cmd_ring_deq(struct xhci_hcd *xhci) u64 val_64; /* step 2: initialize command ring buffer */ - val_64 = readq(&xhci->op_regs->cmd_ring); + val_64 = xhci_read_64(xhci, &xhci->op_regs->cmd_ring); val_64 = (val_64 & (u64) CMD_RING_RSVD_BITS) | (xhci_trb_virt_to_dma(xhci->cmd_ring->deq_seg, xhci->cmd_ring->dequeue) & @@ -792,7 +792,7 @@ static void xhci_set_cmd_ring_deq(struct xhci_hcd *xhci) xhci_dbg_trace(xhci, trace_xhci_dbg_init, "// Setting command ring address to 0x%llx", (long unsigned long) val_64); - writeq(val_64, &xhci->op_regs->cmd_ring); + xhci_write_64(xhci, val_64, &xhci->op_regs->cmd_ring); } /* @@ -3842,7 +3842,7 @@ static int xhci_setup_device(struct usb_hcd *hcd, struct usb_device *udev, if (ret) { return ret; } - temp_64 = readq(&xhci->op_regs->dcbaa_ptr); + temp_64 = xhci_read_64(xhci, &xhci->op_regs->dcbaa_ptr); xhci_dbg_trace(xhci, trace_xhci_dbg_address, "Op regs DCBAA ptr = %#016llx", temp_64); xhci_dbg_trace(xhci, trace_xhci_dbg_address, @@ -4730,11 +4730,8 @@ int xhci_gen_setup(struct usb_hcd *hcd, xhci_get_quirks_t get_quirks) struct device *dev = hcd->self.controller; int retval; - /* Limit the block layer scatter-gather lists to half a segment. */ - hcd->self.sg_tablesize = TRBS_PER_SEGMENT / 2; - - /* support to build packet from discontinuous buffers */ - hcd->self.no_sg_constraint = 1; + /* Accept arbitrarily long scatter-gather lists */ + hcd->self.sg_tablesize = ~0; /* XHCI controllers don't stop the ep queue on short packets :| */ hcd->self.no_stop_on_short = 1; @@ -4760,6 +4757,14 @@ int xhci_gen_setup(struct usb_hcd *hcd, xhci_get_quirks_t get_quirks) /* xHCI private pointer was set in xhci_pci_probe for the second * registered roothub. */ + xhci = hcd_to_xhci(hcd); + /* + * Support arbitrarily aligned sg-list entries on hosts without + * TD fragment rules (which are currently unsupported). + */ + if (xhci->hci_version < 0x100) + hcd->self.no_sg_constraint = 1; + return 0; } @@ -4788,6 +4793,9 @@ int xhci_gen_setup(struct usb_hcd *hcd, xhci_get_quirks_t get_quirks) if (xhci->hci_version > 0x96) xhci->quirks |= XHCI_SPURIOUS_SUCCESS; + if (xhci->hci_version < 0x100) + hcd->self.no_sg_constraint = 1; + /* Make sure the HC is halted. */ retval = xhci_halt(xhci); if (retval) diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index f8416639bf31..58ed9d088e63 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -28,17 +28,6 @@ #include <linux/kernel.h> #include <linux/usb/hcd.h> -/* - * Registers should always be accessed with double word or quad word accesses. - * - * Some xHCI implementations may support 64-bit address pointers. Registers - * with 64-bit address pointers should be written to with dword accesses by - * writing the low dword first (ptr[0]), then the high dword (ptr[1]) second. - * xHCI implementations that do not support 64-bit address pointers will ignore - * the high dword, and write order is irrelevant. - */ -#include <asm-generic/io-64-nonatomic-lo-hi.h> - /* Code sharing between pci-quirks and xhci hcd */ #include "xhci-ext-caps.h" #include "pci-quirks.h" @@ -1279,7 +1268,7 @@ union xhci_trb { * since the command ring is 64-byte aligned. * It must also be greater than 16. */ -#define TRBS_PER_SEGMENT 256 +#define TRBS_PER_SEGMENT 64 /* Allow two commands + a link TRB, along with any reserved command TRBs */ #define MAX_RSVD_CMD_TRBS (TRBS_PER_SEGMENT - 3) #define TRB_SEGMENT_SIZE (TRBS_PER_SEGMENT*16) @@ -1614,6 +1603,34 @@ static inline struct usb_hcd *xhci_to_hcd(struct xhci_hcd *xhci) #define xhci_warn_ratelimited(xhci, fmt, args...) \ dev_warn_ratelimited(xhci_to_hcd(xhci)->self.controller , fmt , ## args) +/* + * Registers should always be accessed with double word or quad word accesses. + * + * Some xHCI implementations may support 64-bit address pointers. Registers + * with 64-bit address pointers should be written to with dword accesses by + * writing the low dword first (ptr[0]), then the high dword (ptr[1]) second. + * xHCI implementations that do not support 64-bit address pointers will ignore + * the high dword, and write order is irrelevant. + */ +static inline u64 xhci_read_64(const struct xhci_hcd *xhci, + __le64 __iomem *regs) +{ + __u32 __iomem *ptr = (__u32 __iomem *) regs; + u64 val_lo = readl(ptr); + u64 val_hi = readl(ptr + 1); + return val_lo + (val_hi << 32); +} +static inline void xhci_write_64(struct xhci_hcd *xhci, + const u64 val, __le64 __iomem *regs) +{ + __u32 __iomem *ptr = (__u32 __iomem *) regs; + u32 val_lo = lower_32_bits(val); + u32 val_hi = upper_32_bits(val); + + writel(val_lo, ptr); + writel(val_hi, ptr + 1); +} + static inline int xhci_link_trb_quirk(struct xhci_hcd *xhci) { return xhci->quirks & XHCI_LINK_TRB_QUIRK; diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c index fc192ad9cc6a..239ad0b1ceb6 100644 --- a/drivers/usb/musb/musb_core.c +++ b/drivers/usb/musb/musb_core.c @@ -477,8 +477,11 @@ static irqreturn_t musb_stage0_irq(struct musb *musb, u8 int_usb, musb->port1_status |= (USB_PORT_STAT_C_SUSPEND << 16) | MUSB_PORT_STAT_RESUME; + musb->rh_timer = jiffies + + msecs_to_jiffies(20); schedule_delayed_work( - &musb->finish_resume_work, 20); + &musb->finish_resume_work, + msecs_to_jiffies(20)); musb->xceiv->state = OTG_STATE_A_HOST; musb->is_active = 1; @@ -2157,11 +2160,19 @@ static void musb_restore_context(struct musb *musb) void __iomem *musb_base = musb->mregs; void __iomem *ep_target_regs; void __iomem *epio; + u8 power; musb_writew(musb_base, MUSB_FRAME, musb->context.frame); musb_writeb(musb_base, MUSB_TESTMODE, musb->context.testmode); musb_write_ulpi_buscontrol(musb->mregs, musb->context.busctl); - musb_writeb(musb_base, MUSB_POWER, musb->context.power); + + /* Don't affect SUSPENDM/RESUME bits in POWER reg */ + power = musb_readb(musb_base, MUSB_POWER); + power &= MUSB_POWER_SUSPENDM | MUSB_POWER_RESUME; + musb->context.power &= ~(MUSB_POWER_SUSPENDM | MUSB_POWER_RESUME); + power |= musb->context.power; + musb_writeb(musb_base, MUSB_POWER, power); + musb_writew(musb_base, MUSB_INTRTXE, musb->intrtxe); musb_writew(musb_base, MUSB_INTRRXE, musb->intrrxe); musb_writeb(musb_base, MUSB_INTRUSBE, musb->context.intrusbe); diff --git a/drivers/usb/musb/musb_host.c b/drivers/usb/musb/musb_host.c index ed455724017b..abb38c3833ef 100644 --- a/drivers/usb/musb/musb_host.c +++ b/drivers/usb/musb/musb_host.c @@ -1183,6 +1183,9 @@ irqreturn_t musb_h_ep0_irq(struct musb *musb) csr = MUSB_CSR0_H_STATUSPKT | MUSB_CSR0_TXPKTRDY; + /* disable ping token in status phase */ + csr |= MUSB_CSR0_H_DIS_PING; + /* flag status stage */ musb->ep0_stage = MUSB_EP0_STATUS; diff --git a/drivers/usb/musb/musb_virthub.c b/drivers/usb/musb/musb_virthub.c index eb634433ef09..e2d2d8c9891b 100644 --- a/drivers/usb/musb/musb_virthub.c +++ b/drivers/usb/musb/musb_virthub.c @@ -135,7 +135,8 @@ void musb_port_suspend(struct musb *musb, bool do_suspend) /* later, GetPortStatus will stop RESUME signaling */ musb->port1_status |= MUSB_PORT_STAT_RESUME; - schedule_delayed_work(&musb->finish_resume_work, 20); + schedule_delayed_work(&musb->finish_resume_work, + msecs_to_jiffies(20)); } } @@ -158,7 +159,6 @@ void musb_port_reset(struct musb *musb, bool do_reset) */ power = musb_readb(mbase, MUSB_POWER); if (do_reset) { - /* * If RESUME is set, we must make sure it stays minimum 20 ms. * Then we must clear RESUME and wait a bit to let musb start @@ -167,11 +167,22 @@ void musb_port_reset(struct musb *musb, bool do_reset) * detected". */ if (power & MUSB_POWER_RESUME) { - while (time_before(jiffies, musb->rh_timer)) - msleep(1); + long remain = (unsigned long) musb->rh_timer - jiffies; + + if (musb->rh_timer > 0 && remain > 0) { + /* take into account the minimum delay after resume */ + schedule_delayed_work( + &musb->deassert_reset_work, remain); + return; + } + musb_writeb(mbase, MUSB_POWER, - power & ~MUSB_POWER_RESUME); - msleep(1); + power & ~MUSB_POWER_RESUME); + + /* Give the core 1 ms to clear MUSB_POWER_RESUME */ + schedule_delayed_work(&musb->deassert_reset_work, + msecs_to_jiffies(1)); + return; } power &= 0xf0; @@ -180,7 +191,8 @@ void musb_port_reset(struct musb *musb, bool do_reset) musb->port1_status |= USB_PORT_STAT_RESET; musb->port1_status &= ~USB_PORT_STAT_ENABLE; - schedule_delayed_work(&musb->deassert_reset_work, 50); + schedule_delayed_work(&musb->deassert_reset_work, + msecs_to_jiffies(50)); } else { dev_dbg(musb->controller, "root port reset stopped\n"); musb_writeb(mbase, MUSB_POWER, diff --git a/drivers/usb/musb/omap2430.c b/drivers/usb/musb/omap2430.c index 2a408cdaf7b2..8aa59a2c5eb2 100644 --- a/drivers/usb/musb/omap2430.c +++ b/drivers/usb/musb/omap2430.c @@ -659,7 +659,6 @@ static int omap2430_runtime_suspend(struct device *dev) OTG_INTERFSEL); omap2430_low_level_exit(musb); - phy_power_off(musb->phy); } return 0; @@ -674,7 +673,6 @@ static int omap2430_runtime_resume(struct device *dev) omap2430_low_level_init(musb); musb_writel(musb->mregs, OTG_INTERFSEL, musb->context.otg_interfsel); - phy_power_on(musb->phy); } return 0; diff --git a/drivers/usb/phy/phy-msm-usb.c b/drivers/usb/phy/phy-msm-usb.c index 8546c8dccd51..d204f745ed05 100644 --- a/drivers/usb/phy/phy-msm-usb.c +++ b/drivers/usb/phy/phy-msm-usb.c @@ -159,32 +159,6 @@ put_3p3: return rc; } -#ifdef CONFIG_PM_SLEEP -#define USB_PHY_SUSP_DIG_VOL 500000 -static int msm_hsusb_config_vddcx(int high) -{ - int max_vol = USB_PHY_VDD_DIG_VOL_MAX; - int min_vol; - int ret; - - if (high) - min_vol = USB_PHY_VDD_DIG_VOL_MIN; - else - min_vol = USB_PHY_SUSP_DIG_VOL; - - ret = regulator_set_voltage(hsusb_vddcx, min_vol, max_vol); - if (ret) { - pr_err("%s: unable to set the voltage for regulator " - "HSUSB_VDDCX\n", __func__); - return ret; - } - - pr_debug("%s: min_vol:%d max_vol:%d\n", __func__, min_vol, max_vol); - - return ret; -} -#endif - static int msm_hsusb_ldo_set_mode(int on) { int ret = 0; @@ -440,7 +414,32 @@ static int msm_otg_reset(struct usb_phy *phy) #define PHY_SUSPEND_TIMEOUT_USEC (500 * 1000) #define PHY_RESUME_TIMEOUT_USEC (100 * 1000) -#ifdef CONFIG_PM_SLEEP +#ifdef CONFIG_PM + +#define USB_PHY_SUSP_DIG_VOL 500000 +static int msm_hsusb_config_vddcx(int high) +{ + int max_vol = USB_PHY_VDD_DIG_VOL_MAX; + int min_vol; + int ret; + + if (high) + min_vol = USB_PHY_VDD_DIG_VOL_MIN; + else + min_vol = USB_PHY_SUSP_DIG_VOL; + + ret = regulator_set_voltage(hsusb_vddcx, min_vol, max_vol); + if (ret) { + pr_err("%s: unable to set the voltage for regulator " + "HSUSB_VDDCX\n", __func__); + return ret; + } + + pr_debug("%s: min_vol:%d max_vol:%d\n", __func__, min_vol, max_vol); + + return ret; +} + static int msm_otg_suspend(struct msm_otg *motg) { struct usb_phy *phy = &motg->phy; @@ -1733,22 +1732,18 @@ static int msm_otg_pm_resume(struct device *dev) } #endif -#ifdef CONFIG_PM static const struct dev_pm_ops msm_otg_dev_pm_ops = { SET_SYSTEM_SLEEP_PM_OPS(msm_otg_pm_suspend, msm_otg_pm_resume) SET_RUNTIME_PM_OPS(msm_otg_runtime_suspend, msm_otg_runtime_resume, msm_otg_runtime_idle) }; -#endif static struct platform_driver msm_otg_driver = { .remove = msm_otg_remove, .driver = { .name = DRIVER_NAME, .owner = THIS_MODULE, -#ifdef CONFIG_PM .pm = &msm_otg_dev_pm_ops, -#endif }, }; diff --git a/drivers/usb/phy/phy.c b/drivers/usb/phy/phy.c index e6f61e4361df..8afa813d690b 100644 --- a/drivers/usb/phy/phy.c +++ b/drivers/usb/phy/phy.c @@ -130,7 +130,7 @@ struct usb_phy *usb_get_phy(enum usb_phy_type type) phy = __usb_find_phy(&phy_list, type); if (IS_ERR(phy) || !try_module_get(phy->dev->driver->owner)) { - pr_err("unable to find transceiver of type %s\n", + pr_debug("PHY: unable to find transceiver of type %s\n", usb_phy_type_string(type)); goto err0; } @@ -228,7 +228,7 @@ struct usb_phy *usb_get_phy_dev(struct device *dev, u8 index) phy = __usb_find_phy_dev(dev, &phy_bind_list, index); if (IS_ERR(phy) || !try_module_get(phy->dev->driver->owner)) { - pr_err("unable to find transceiver\n"); + dev_dbg(dev, "unable to find transceiver\n"); goto err0; } @@ -424,10 +424,8 @@ int usb_bind_phy(const char *dev_name, u8 index, unsigned long flags; phy_bind = kzalloc(sizeof(*phy_bind), GFP_KERNEL); - if (!phy_bind) { - pr_err("phy_bind(): No memory for phy_bind"); + if (!phy_bind) return -ENOMEM; - } phy_bind->dev_name = dev_name; phy_bind->phy_dev_name = phy_dev_name; diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c index ce0d7b0db012..44ab12986805 100644 --- a/drivers/usb/serial/ftdi_sio.c +++ b/drivers/usb/serial/ftdi_sio.c @@ -152,6 +152,7 @@ static const struct usb_device_id id_table_combined[] = { { USB_DEVICE(FTDI_VID, FTDI_CANUSB_PID) }, { USB_DEVICE(FTDI_VID, FTDI_CANDAPTER_PID) }, { USB_DEVICE(FTDI_VID, FTDI_NXTCAM_PID) }, + { USB_DEVICE(FTDI_VID, FTDI_EV3CON_PID) }, { USB_DEVICE(FTDI_VID, FTDI_SCS_DEVICE_0_PID) }, { USB_DEVICE(FTDI_VID, FTDI_SCS_DEVICE_1_PID) }, { USB_DEVICE(FTDI_VID, FTDI_SCS_DEVICE_2_PID) }, @@ -191,6 +192,8 @@ static const struct usb_device_id id_table_combined[] = { { USB_DEVICE(INTERBIOMETRICS_VID, INTERBIOMETRICS_IOBOARD_PID) }, { USB_DEVICE(INTERBIOMETRICS_VID, INTERBIOMETRICS_MINI_IOBOARD_PID) }, { USB_DEVICE(FTDI_VID, FTDI_SPROG_II) }, + { USB_DEVICE(FTDI_VID, FTDI_TAGSYS_LP101_PID) }, + { USB_DEVICE(FTDI_VID, FTDI_TAGSYS_P200X_PID) }, { USB_DEVICE(FTDI_VID, FTDI_LENZ_LIUSB_PID) }, { USB_DEVICE(FTDI_VID, FTDI_XF_632_PID) }, { USB_DEVICE(FTDI_VID, FTDI_XF_634_PID) }, @@ -904,6 +907,8 @@ static const struct usb_device_id id_table_combined[] = { /* Crucible Devices */ { USB_DEVICE(FTDI_VID, FTDI_CT_COMET_PID) }, { USB_DEVICE(FTDI_VID, FTDI_Z3X_PID) }, + /* Cressi Devices */ + { USB_DEVICE(FTDI_VID, FTDI_CRESSI_PID) }, { } /* Terminating entry */ }; diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h index a7019d1e3058..e599fbfcde5f 100644 --- a/drivers/usb/serial/ftdi_sio_ids.h +++ b/drivers/usb/serial/ftdi_sio_ids.h @@ -50,6 +50,7 @@ #define TI_XDS100V2_PID 0xa6d0 #define FTDI_NXTCAM_PID 0xABB8 /* NXTCam for Mindstorms NXT */ +#define FTDI_EV3CON_PID 0xABB9 /* Mindstorms EV3 Console Adapter */ /* US Interface Navigator (http://www.usinterface.com/) */ #define FTDI_USINT_CAT_PID 0xb810 /* Navigator CAT and 2nd PTT lines */ @@ -363,6 +364,12 @@ /* Sprog II (Andrew Crosland's SprogII DCC interface) */ #define FTDI_SPROG_II 0xF0C8 +/* + * Two of the Tagsys RFID Readers + */ +#define FTDI_TAGSYS_LP101_PID 0xF0E9 /* Tagsys L-P101 RFID*/ +#define FTDI_TAGSYS_P200X_PID 0xF0EE /* Tagsys Medio P200x RFID*/ + /* an infrared receiver for user access control with IR tags */ #define FTDI_PIEGROUP_PID 0xF208 /* Product Id */ @@ -1313,3 +1320,9 @@ * Manufacturer: Smart GSM Team */ #define FTDI_Z3X_PID 0x0011 + +/* + * Product: Cressi PC Interface + * Manufacturer: Cressi + */ +#define FTDI_CRESSI_PID 0x87d0 diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 5c86f57e4afa..68fc9fe65936 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -1362,7 +1362,8 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1267, 0xff, 0xff, 0xff) }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1268, 0xff, 0xff, 0xff) }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1269, 0xff, 0xff, 0xff) }, - { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1270, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1270, 0xff, 0xff, 0xff), + .driver_info = (kernel_ulong_t)&net_intf5_blacklist }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1271, 0xff, 0xff, 0xff) }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1272, 0xff, 0xff, 0xff) }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1273, 0xff, 0xff, 0xff) }, @@ -1525,7 +1526,8 @@ static const struct usb_device_id option_ids[] = { /* Cinterion */ { USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_EU3_E) }, { USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_EU3_P) }, - { USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_PH8) }, + { USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_PH8), + .driver_info = (kernel_ulong_t)&net_intf4_blacklist }, { USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_AHXX) }, { USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_PLXX), .driver_info = (kernel_ulong_t)&net_intf4_blacklist }, diff --git a/drivers/usb/serial/qcserial.c b/drivers/usb/serial/qcserial.c index c65437cfd4a2..968a40201e5f 100644 --- a/drivers/usb/serial/qcserial.c +++ b/drivers/usb/serial/qcserial.c @@ -139,6 +139,9 @@ static const struct usb_device_id id_table[] = { {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x901c, 0)}, /* Sierra Wireless EM7700 Device Management */ {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x901c, 2)}, /* Sierra Wireless EM7700 NMEA */ {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x901c, 3)}, /* Sierra Wireless EM7700 Modem */ + {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9051, 0)}, /* Netgear AirCard 340U Device Management */ + {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9051, 2)}, /* Netgear AirCard 340U NMEA */ + {USB_DEVICE_INTERFACE_NUMBER(0x1199, 0x9051, 3)}, /* Netgear AirCard 340U Modem */ { } /* Terminating entry */ }; diff --git a/drivers/usb/serial/usb-serial-simple.c b/drivers/usb/serial/usb-serial-simple.c index f112b079ddfc..fb79775447b0 100644 --- a/drivers/usb/serial/usb-serial-simple.c +++ b/drivers/usb/serial/usb-serial-simple.c @@ -71,7 +71,8 @@ DEVICE(hp4x, HP4X_IDS); /* Suunto ANT+ USB Driver */ #define SUUNTO_IDS() \ - { USB_DEVICE(0x0fcf, 0x1008) } + { USB_DEVICE(0x0fcf, 0x1008) }, \ + { USB_DEVICE(0x0fcf, 0x1009) } /* Dynastream ANT USB-m Stick */ DEVICE(suunto, SUUNTO_IDS); /* Siemens USB/MPI adapter */ diff --git a/drivers/usb/storage/Kconfig b/drivers/usb/storage/Kconfig index 8470e1b114f2..1dd0604d1911 100644 --- a/drivers/usb/storage/Kconfig +++ b/drivers/usb/storage/Kconfig @@ -18,7 +18,9 @@ config USB_STORAGE This option depends on 'SCSI' support being enabled, but you probably also need 'SCSI device support: SCSI disk support' - (BLK_DEV_SD) for most USB storage devices. + (BLK_DEV_SD) for most USB storage devices. Some devices also + will require 'Probe all LUNs on each SCSI device' + (SCSI_MULTI_LUN). To compile this driver as a module, choose M here: the module will be called usb-storage. diff --git a/drivers/usb/storage/scsiglue.c b/drivers/usb/storage/scsiglue.c index 18509e6c21ab..9d38ddc8da49 100644 --- a/drivers/usb/storage/scsiglue.c +++ b/drivers/usb/storage/scsiglue.c @@ -78,6 +78,8 @@ static const char* host_info(struct Scsi_Host *host) static int slave_alloc (struct scsi_device *sdev) { + struct us_data *us = host_to_us(sdev->host); + /* * Set the INQUIRY transfer length to 36. We don't use any of * the extra data and many devices choke if asked for more or @@ -102,6 +104,10 @@ static int slave_alloc (struct scsi_device *sdev) */ blk_queue_update_dma_alignment(sdev->request_queue, (512 - 1)); + /* Tell the SCSI layer if we know there is more than one LUN */ + if (us->protocol == USB_PR_BULK && us->max_lun > 0) + sdev->sdev_bflags |= BLIST_FORCELUN; + return 0; } diff --git a/drivers/usb/storage/unusual_cypress.h b/drivers/usb/storage/unusual_cypress.h index 65a6a75066a8..82e8ed0324e3 100644 --- a/drivers/usb/storage/unusual_cypress.h +++ b/drivers/usb/storage/unusual_cypress.h @@ -31,7 +31,7 @@ UNUSUAL_DEV( 0x04b4, 0x6831, 0x0000, 0x9999, "Cypress ISD-300LP", USB_SC_CYP_ATACB, USB_PR_DEVICE, NULL, 0), -UNUSUAL_DEV( 0x14cd, 0x6116, 0x0000, 0x0219, +UNUSUAL_DEV( 0x14cd, 0x6116, 0x0160, 0x0160, "Super Top", "USB 2.0 SATA BRIDGE", USB_SC_CYP_ATACB, USB_PR_DEVICE, NULL, 0), diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h index ad06255c2ade..adbeb255616a 100644 --- a/drivers/usb/storage/unusual_devs.h +++ b/drivers/usb/storage/unusual_devs.h @@ -1455,6 +1455,13 @@ UNUSUAL_DEV( 0x0f88, 0x042e, 0x0100, 0x0100, USB_SC_DEVICE, USB_PR_DEVICE, NULL, US_FL_FIX_CAPACITY ), +/* Reported by Moritz Moeller-Herrmann <moritz-kernel@moeller-herrmann.de> */ +UNUSUAL_DEV( 0x0fca, 0x8004, 0x0201, 0x0201, + "Research In Motion", + "BlackBerry Bold 9000", + USB_SC_DEVICE, USB_PR_DEVICE, NULL, + US_FL_MAX_SECTORS_64 ), + /* Reported by Michael Stattmann <michael@stattmann.com> */ UNUSUAL_DEV( 0x0fce, 0xd008, 0x0000, 0x0000, "Sony Ericsson", diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index 4fb7a8f83c8a..54af4e933695 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -186,12 +186,12 @@ static bool is_invalid_reserved_pfn(unsigned long pfn) if (pfn_valid(pfn)) { bool reserved; struct page *tail = pfn_to_page(pfn); - struct page *head = compound_trans_head(tail); + struct page *head = compound_head(tail); reserved = !!(PageReserved(head)); if (head != tail) { /* * "head" is not a dangling pointer - * (compound_trans_head takes care of that) + * (compound_head takes care of that) * but the hugepage may have been split * from under us (and we may not hold a * reference count on the head page so it can diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 9a68409580d5..a0fa5de210cf 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -70,7 +70,12 @@ enum { }; struct vhost_net_ubuf_ref { - struct kref kref; + /* refcount follows semantics similar to kref: + * 0: object is released + * 1: no outstanding ubufs + * >1: outstanding ubufs + */ + atomic_t refcount; wait_queue_head_t wait; struct vhost_virtqueue *vq; }; @@ -116,14 +121,6 @@ static void vhost_net_enable_zcopy(int vq) vhost_net_zcopy_mask |= 0x1 << vq; } -static void vhost_net_zerocopy_done_signal(struct kref *kref) -{ - struct vhost_net_ubuf_ref *ubufs; - - ubufs = container_of(kref, struct vhost_net_ubuf_ref, kref); - wake_up(&ubufs->wait); -} - static struct vhost_net_ubuf_ref * vhost_net_ubuf_alloc(struct vhost_virtqueue *vq, bool zcopy) { @@ -134,21 +131,24 @@ vhost_net_ubuf_alloc(struct vhost_virtqueue *vq, bool zcopy) ubufs = kmalloc(sizeof(*ubufs), GFP_KERNEL); if (!ubufs) return ERR_PTR(-ENOMEM); - kref_init(&ubufs->kref); + atomic_set(&ubufs->refcount, 1); init_waitqueue_head(&ubufs->wait); ubufs->vq = vq; return ubufs; } -static void vhost_net_ubuf_put(struct vhost_net_ubuf_ref *ubufs) +static int vhost_net_ubuf_put(struct vhost_net_ubuf_ref *ubufs) { - kref_put(&ubufs->kref, vhost_net_zerocopy_done_signal); + int r = atomic_sub_return(1, &ubufs->refcount); + if (unlikely(!r)) + wake_up(&ubufs->wait); + return r; } static void vhost_net_ubuf_put_and_wait(struct vhost_net_ubuf_ref *ubufs) { - kref_put(&ubufs->kref, vhost_net_zerocopy_done_signal); - wait_event(ubufs->wait, !atomic_read(&ubufs->kref.refcount)); + vhost_net_ubuf_put(ubufs); + wait_event(ubufs->wait, !atomic_read(&ubufs->refcount)); } static void vhost_net_ubuf_put_wait_and_free(struct vhost_net_ubuf_ref *ubufs) @@ -306,23 +306,26 @@ static void vhost_zerocopy_callback(struct ubuf_info *ubuf, bool success) { struct vhost_net_ubuf_ref *ubufs = ubuf->ctx; struct vhost_virtqueue *vq = ubufs->vq; - int cnt = atomic_read(&ubufs->kref.refcount); + int cnt; + + rcu_read_lock_bh(); /* set len to mark this desc buffers done DMA */ vq->heads[ubuf->desc].len = success ? VHOST_DMA_DONE_LEN : VHOST_DMA_FAILED_LEN; - vhost_net_ubuf_put(ubufs); + cnt = vhost_net_ubuf_put(ubufs); /* * Trigger polling thread if guest stopped submitting new buffers: - * in this case, the refcount after decrement will eventually reach 1 - * so here it is 2. + * in this case, the refcount after decrement will eventually reach 1. * We also trigger polling periodically after each 16 packets * (the value 16 here is more or less arbitrary, it's tuned to trigger * less than 10% of times). */ - if (cnt <= 2 || !(cnt % 16)) + if (cnt <= 1 || !(cnt % 16)) vhost_poll_queue(&vq->poll); + + rcu_read_unlock_bh(); } /* Expects to be always run from workqueue - which acts as @@ -420,7 +423,7 @@ static void handle_tx(struct vhost_net *net) msg.msg_control = ubuf; msg.msg_controllen = sizeof(ubuf); ubufs = nvq->ubufs; - kref_get(&ubufs->kref); + atomic_inc(&ubufs->refcount); nvq->upend_idx = (nvq->upend_idx + 1) % UIO_MAXIOV; } else { msg.msg_control = NULL; @@ -780,7 +783,7 @@ static void vhost_net_flush(struct vhost_net *n) vhost_net_ubuf_put_and_wait(n->vqs[VHOST_NET_VQ_TX].ubufs); mutex_lock(&n->vqs[VHOST_NET_VQ_TX].vq.mutex); n->tx_flush = false; - kref_init(&n->vqs[VHOST_NET_VQ_TX].ubufs->kref); + atomic_set(&n->vqs[VHOST_NET_VQ_TX].ubufs->refcount, 1); mutex_unlock(&n->vqs[VHOST_NET_VQ_TX].vq.mutex); } } @@ -800,6 +803,8 @@ static int vhost_net_release(struct inode *inode, struct file *f) fput(tx_sock->file); if (rx_sock) fput(rx_sock->file); + /* Make sure no callbacks are outstanding */ + synchronize_rcu_bh(); /* We do an extra flush before freeing memory, * since jobs can re-queue themselves. */ vhost_net_flush(n); diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index 0a025b8e2a12..e48d4a672580 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -1001,6 +1001,12 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq) break; } + /* virtio-scsi spec requires byte 0 of the lun to be 1 */ + if (unlikely(v_req.lun[0] != 1)) { + vhost_scsi_send_bad_target(vs, vq, head, out); + continue; + } + /* Extract the tpgt */ target = v_req.lun[1]; tpg = ACCESS_ONCE(vs_tpg[target]); diff --git a/drivers/video/Kconfig b/drivers/video/Kconfig index 22262a3a0e2d..dade5b7699bc 100644 --- a/drivers/video/Kconfig +++ b/drivers/video/Kconfig @@ -364,7 +364,7 @@ config FB_SA1100 config FB_IMX tristate "Freescale i.MX1/21/25/27 LCD support" - depends on FB && IMX_HAVE_PLATFORM_IMX_FB + depends on FB && ARCH_MXC select FB_CFB_FILLRECT select FB_CFB_COPYAREA select FB_CFB_IMAGEBLIT diff --git a/drivers/video/exynos/Kconfig b/drivers/video/exynos/Kconfig index 1129d0e9e640..75c8a8e7efc0 100644 --- a/drivers/video/exynos/Kconfig +++ b/drivers/video/exynos/Kconfig @@ -22,7 +22,8 @@ config EXYNOS_MIPI_DSI config EXYNOS_LCD_S6E8AX0 bool "S6E8AX0 MIPI AMOLED LCD Driver" - depends on (EXYNOS_MIPI_DSI && BACKLIGHT_CLASS_DEVICE && LCD_CLASS_DEVICE) + depends on EXYNOS_MIPI_DSI && BACKLIGHT_CLASS_DEVICE + depends on (LCD_CLASS_DEVICE = y) default n help If you have an S6E8AX0 MIPI AMOLED LCD Panel, say Y to enable its diff --git a/drivers/video/omap2/dss/dispc.c b/drivers/video/omap2/dss/dispc.c index bbeb8dd7f108..77d6221618f4 100644 --- a/drivers/video/omap2/dss/dispc.c +++ b/drivers/video/omap2/dss/dispc.c @@ -2160,8 +2160,8 @@ static int dispc_ovl_calc_scaling_24xx(unsigned long pclk, unsigned long lclk, *five_taps = false; do { - in_height = DIV_ROUND_UP(height, *decim_y); - in_width = DIV_ROUND_UP(width, *decim_x); + in_height = height / *decim_y; + in_width = width / *decim_x; *core_clk = dispc.feat->calc_core_clk(pclk, in_width, in_height, out_width, out_height, mem_to_mem); error = (in_width > maxsinglelinewidth || !*core_clk || @@ -2199,8 +2199,8 @@ static int dispc_ovl_calc_scaling_34xx(unsigned long pclk, unsigned long lclk, dss_feat_get_param_max(FEAT_PARAM_LINEWIDTH); do { - in_height = DIV_ROUND_UP(height, *decim_y); - in_width = DIV_ROUND_UP(width, *decim_x); + in_height = height / *decim_y; + in_width = width / *decim_x; *five_taps = in_height > out_height; if (in_width > maxsinglelinewidth) @@ -2268,7 +2268,7 @@ static int dispc_ovl_calc_scaling_44xx(unsigned long pclk, unsigned long lclk, { u16 in_width, in_width_max; int decim_x_min = *decim_x; - u16 in_height = DIV_ROUND_UP(height, *decim_y); + u16 in_height = height / *decim_y; const int maxsinglelinewidth = dss_feat_get_param_max(FEAT_PARAM_LINEWIDTH); const int maxdownscale = dss_feat_get_param_max(FEAT_PARAM_DOWNSCALE); @@ -2287,7 +2287,7 @@ static int dispc_ovl_calc_scaling_44xx(unsigned long pclk, unsigned long lclk, return -EINVAL; do { - in_width = DIV_ROUND_UP(width, *decim_x); + in_width = width / *decim_x; } while (*decim_x <= *x_predecim && in_width > maxsinglelinewidth && ++*decim_x); @@ -2466,8 +2466,8 @@ static int dispc_ovl_setup_common(enum omap_plane plane, if (r) return r; - in_width = DIV_ROUND_UP(in_width, x_predecim); - in_height = DIV_ROUND_UP(in_height, y_predecim); + in_width = in_width / x_predecim; + in_height = in_height / y_predecim; if (color_mode == OMAP_DSS_COLOR_YUV2 || color_mode == OMAP_DSS_COLOR_UYVY || diff --git a/drivers/video/omap2/dss/dpi.c b/drivers/video/omap2/dss/dpi.c index 7411f2674e16..23ef21ffc2c4 100644 --- a/drivers/video/omap2/dss/dpi.c +++ b/drivers/video/omap2/dss/dpi.c @@ -117,7 +117,7 @@ struct dpi_clk_calc_ctx { /* outputs */ struct dsi_clock_info dsi_cinfo; - unsigned long long fck; + unsigned long fck; struct dispc_clock_info dispc_cinfo; }; diff --git a/drivers/video/omap2/dss/sdi.c b/drivers/video/omap2/dss/sdi.c index efb9ee9e3c96..ba806c9e7f54 100644 --- a/drivers/video/omap2/dss/sdi.c +++ b/drivers/video/omap2/dss/sdi.c @@ -46,7 +46,7 @@ static struct { struct sdi_clk_calc_ctx { unsigned long pck_min, pck_max; - unsigned long long fck; + unsigned long fck; struct dispc_clock_info dispc_cinfo; }; diff --git a/drivers/vme/bridges/vme_ca91cx42.c b/drivers/vme/bridges/vme_ca91cx42.c index a06edbfa95ca..1b5d48c578e1 100644 --- a/drivers/vme/bridges/vme_ca91cx42.c +++ b/drivers/vme/bridges/vme_ca91cx42.c @@ -884,7 +884,7 @@ static ssize_t ca91cx42_master_read(struct vme_master_resource *image, if (done == count) goto out; } - if ((uintptr_t)addr & 0x2) { + if ((uintptr_t)(addr + done) & 0x2) { if ((count - done) < 2) { *(u8 *)(buf + done) = ioread8(addr + done); done += 1; @@ -938,7 +938,7 @@ static ssize_t ca91cx42_master_write(struct vme_master_resource *image, if (done == count) goto out; } - if ((uintptr_t)addr & 0x2) { + if ((uintptr_t)(addr + done) & 0x2) { if ((count - done) < 2) { iowrite8(*(u8 *)(buf + done), addr + done); done += 1; diff --git a/drivers/vme/bridges/vme_tsi148.c b/drivers/vme/bridges/vme_tsi148.c index 16830d8b777c..9911cd5fddb5 100644 --- a/drivers/vme/bridges/vme_tsi148.c +++ b/drivers/vme/bridges/vme_tsi148.c @@ -1289,7 +1289,7 @@ static ssize_t tsi148_master_read(struct vme_master_resource *image, void *buf, if (done == count) goto out; } - if ((uintptr_t)addr & 0x2) { + if ((uintptr_t)(addr + done) & 0x2) { if ((count - done) < 2) { *(u8 *)(buf + done) = ioread8(addr + done); done += 1; @@ -1371,7 +1371,7 @@ static ssize_t tsi148_master_write(struct vme_master_resource *image, void *buf, if (done == count) goto out; } - if ((uintptr_t)addr & 0x2) { + if ((uintptr_t)(addr + done) & 0x2) { if ((count - done) < 2) { iowrite8(*(u8 *)(buf + done), addr + done); done += 1; diff --git a/drivers/watchdog/w83697hf_wdt.c b/drivers/watchdog/w83697hf_wdt.c index aaf2995d37f4..68b45fc9ba6a 100644 --- a/drivers/watchdog/w83697hf_wdt.c +++ b/drivers/watchdog/w83697hf_wdt.c @@ -402,7 +402,7 @@ static int __init wdt_init(void) if (!found) { pr_err("No W83697HF/HG could be found\n"); - ret = -EIO; + ret = -ENODEV; goto out; } diff --git a/drivers/xen/Makefile b/drivers/xen/Makefile index d75c811bfa56..45e00afa7f2d 100644 --- a/drivers/xen/Makefile +++ b/drivers/xen/Makefile @@ -16,7 +16,6 @@ xen-pad-$(CONFIG_X86) += xen-acpi-pad.o dom0-$(CONFIG_X86) += pcpu.o obj-$(CONFIG_XEN_DOM0) += $(dom0-y) obj-$(CONFIG_BLOCK) += biomerge.o -obj-$(CONFIG_XEN_XENCOMM) += xencomm.o obj-$(CONFIG_XEN_BALLOON) += xen-balloon.o obj-$(CONFIG_XEN_SELFBALLOONING) += xen-selfballoon.o obj-$(CONFIG_XEN_DEV_EVTCHN) += xen-evtchn.o diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c index 4672e003c0ad..f4a9e3311297 100644 --- a/drivers/xen/events/events_base.c +++ b/drivers/xen/events/events_base.c @@ -862,6 +862,8 @@ int bind_evtchn_to_irq(unsigned int evtchn) irq = ret; goto out; } + /* New interdomain events are bound to VCPU 0. */ + bind_evtchn_to_cpu(evtchn, 0); } else { struct irq_info *info = info_for_irq(irq); WARN_ON(info == NULL || info->type != IRQT_EVTCHN); diff --git a/drivers/xen/xencomm.c b/drivers/xen/xencomm.c deleted file mode 100644 index 4793fc594549..000000000000 --- a/drivers/xen/xencomm.c +++ /dev/null @@ -1,219 +0,0 @@ -/* - * 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. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - * - * Copyright (C) IBM Corp. 2006 - * - * Authors: Hollis Blanchard <hollisb@us.ibm.com> - */ - -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include <linux/mm.h> -#include <linux/slab.h> -#include <asm/page.h> -#include <xen/xencomm.h> -#include <xen/interface/xen.h> -#include <asm/xen/xencomm.h> /* for xencomm_is_phys_contiguous() */ - -static int xencomm_init(struct xencomm_desc *desc, - void *buffer, unsigned long bytes) -{ - unsigned long recorded = 0; - int i = 0; - - while ((recorded < bytes) && (i < desc->nr_addrs)) { - unsigned long vaddr = (unsigned long)buffer + recorded; - unsigned long paddr; - int offset; - int chunksz; - - offset = vaddr % PAGE_SIZE; /* handle partial pages */ - chunksz = min(PAGE_SIZE - offset, bytes - recorded); - - paddr = xencomm_vtop(vaddr); - if (paddr == ~0UL) { - printk(KERN_DEBUG "%s: couldn't translate vaddr %lx\n", - __func__, vaddr); - return -EINVAL; - } - - desc->address[i++] = paddr; - recorded += chunksz; - } - - if (recorded < bytes) { - printk(KERN_DEBUG - "%s: could only translate %ld of %ld bytes\n", - __func__, recorded, bytes); - return -ENOSPC; - } - - /* mark remaining addresses invalid (just for safety) */ - while (i < desc->nr_addrs) - desc->address[i++] = XENCOMM_INVALID; - - desc->magic = XENCOMM_MAGIC; - - return 0; -} - -static struct xencomm_desc *xencomm_alloc(gfp_t gfp_mask, - void *buffer, unsigned long bytes) -{ - struct xencomm_desc *desc; - unsigned long buffer_ulong = (unsigned long)buffer; - unsigned long start = buffer_ulong & PAGE_MASK; - unsigned long end = (buffer_ulong + bytes) | ~PAGE_MASK; - unsigned long nr_addrs = (end - start + 1) >> PAGE_SHIFT; - unsigned long size = sizeof(*desc) + - sizeof(desc->address[0]) * nr_addrs; - - /* - * slab allocator returns at least sizeof(void*) aligned pointer. - * When sizeof(*desc) > sizeof(void*), struct xencomm_desc might - * cross page boundary. - */ - if (sizeof(*desc) > sizeof(void *)) { - unsigned long order = get_order(size); - desc = (struct xencomm_desc *)__get_free_pages(gfp_mask, - order); - if (desc == NULL) - return NULL; - - desc->nr_addrs = - ((PAGE_SIZE << order) - sizeof(struct xencomm_desc)) / - sizeof(*desc->address); - } else { - desc = kmalloc(size, gfp_mask); - if (desc == NULL) - return NULL; - - desc->nr_addrs = nr_addrs; - } - return desc; -} - -void xencomm_free(struct xencomm_handle *desc) -{ - if (desc && !((ulong)desc & XENCOMM_INLINE_FLAG)) { - struct xencomm_desc *desc__ = (struct xencomm_desc *)desc; - if (sizeof(*desc__) > sizeof(void *)) { - unsigned long size = sizeof(*desc__) + - sizeof(desc__->address[0]) * desc__->nr_addrs; - unsigned long order = get_order(size); - free_pages((unsigned long)__va(desc), order); - } else - kfree(__va(desc)); - } -} - -static int xencomm_create(void *buffer, unsigned long bytes, - struct xencomm_desc **ret, gfp_t gfp_mask) -{ - struct xencomm_desc *desc; - int rc; - - pr_debug("%s: %p[%ld]\n", __func__, buffer, bytes); - - if (bytes == 0) { - /* don't create a descriptor; Xen recognizes NULL. */ - BUG_ON(buffer != NULL); - *ret = NULL; - return 0; - } - - BUG_ON(buffer == NULL); /* 'bytes' is non-zero */ - - desc = xencomm_alloc(gfp_mask, buffer, bytes); - if (!desc) { - printk(KERN_DEBUG "%s failure\n", "xencomm_alloc"); - return -ENOMEM; - } - - rc = xencomm_init(desc, buffer, bytes); - if (rc) { - printk(KERN_DEBUG "%s failure: %d\n", "xencomm_init", rc); - xencomm_free((struct xencomm_handle *)__pa(desc)); - return rc; - } - - *ret = desc; - return 0; -} - -static struct xencomm_handle *xencomm_create_inline(void *ptr) -{ - unsigned long paddr; - - BUG_ON(!xencomm_is_phys_contiguous((unsigned long)ptr)); - - paddr = (unsigned long)xencomm_pa(ptr); - BUG_ON(paddr & XENCOMM_INLINE_FLAG); - return (struct xencomm_handle *)(paddr | XENCOMM_INLINE_FLAG); -} - -/* "mini" routine, for stack-based communications: */ -static int xencomm_create_mini(void *buffer, - unsigned long bytes, struct xencomm_mini *xc_desc, - struct xencomm_desc **ret) -{ - int rc = 0; - struct xencomm_desc *desc; - BUG_ON(((unsigned long)xc_desc) % sizeof(*xc_desc) != 0); - - desc = (void *)xc_desc; - - desc->nr_addrs = XENCOMM_MINI_ADDRS; - - rc = xencomm_init(desc, buffer, bytes); - if (!rc) - *ret = desc; - - return rc; -} - -struct xencomm_handle *xencomm_map(void *ptr, unsigned long bytes) -{ - int rc; - struct xencomm_desc *desc; - - if (xencomm_is_phys_contiguous((unsigned long)ptr)) - return xencomm_create_inline(ptr); - - rc = xencomm_create(ptr, bytes, &desc, GFP_KERNEL); - - if (rc || desc == NULL) - return NULL; - - return xencomm_pa(desc); -} - -struct xencomm_handle *__xencomm_map_no_alloc(void *ptr, unsigned long bytes, - struct xencomm_mini *xc_desc) -{ - int rc; - struct xencomm_desc *desc = NULL; - - if (xencomm_is_phys_contiguous((unsigned long)ptr)) - return xencomm_create_inline(ptr); - - rc = xencomm_create_mini(ptr, bytes, xc_desc, - &desc); - - if (rc) - return NULL; - - return xencomm_pa(desc); -} diff --git a/fs/bio-integrity.c b/fs/bio-integrity.c index 0bad24ddc2e7..0129b78a6908 100644 --- a/fs/bio-integrity.c +++ b/fs/bio-integrity.c @@ -114,6 +114,14 @@ void bio_integrity_free(struct bio *bio) } EXPORT_SYMBOL(bio_integrity_free); +static inline unsigned int bip_integrity_vecs(struct bio_integrity_payload *bip) +{ + if (bip->bip_slab == BIO_POOL_NONE) + return BIP_INLINE_VECS; + + return bvec_nr_vecs(bip->bip_slab); +} + /** * bio_integrity_add_page - Attach integrity metadata * @bio: bio to update @@ -129,7 +137,7 @@ int bio_integrity_add_page(struct bio *bio, struct page *page, struct bio_integrity_payload *bip = bio->bi_integrity; struct bio_vec *iv; - if (bip->bip_vcnt >= bvec_nr_vecs(bip->bip_slab)) { + if (bip->bip_vcnt >= bip_integrity_vecs(bip)) { printk(KERN_ERR "%s: bip_vec full\n", __func__); return 0; } @@ -226,7 +234,8 @@ unsigned int bio_integrity_tag_size(struct bio *bio) } EXPORT_SYMBOL(bio_integrity_tag_size); -int bio_integrity_tag(struct bio *bio, void *tag_buf, unsigned int len, int set) +static int bio_integrity_tag(struct bio *bio, void *tag_buf, unsigned int len, + int set) { struct bio_integrity_payload *bip = bio->bi_integrity; struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev); @@ -611,7 +611,6 @@ EXPORT_SYMBOL(bio_clone_fast); struct bio *bio_clone_bioset(struct bio *bio_src, gfp_t gfp_mask, struct bio_set *bs) { - unsigned nr_iovecs = 0; struct bvec_iter iter; struct bio_vec bv; struct bio *bio; @@ -638,10 +637,7 @@ struct bio *bio_clone_bioset(struct bio *bio_src, gfp_t gfp_mask, * __bio_clone_fast() anyways. */ - bio_for_each_segment(bv, bio_src, iter) - nr_iovecs++; - - bio = bio_alloc_bioset(gfp_mask, nr_iovecs, bs); + bio = bio_alloc_bioset(gfp_mask, bio_segments(bio_src), bs); if (!bio) return NULL; @@ -650,9 +646,18 @@ struct bio *bio_clone_bioset(struct bio *bio_src, gfp_t gfp_mask, bio->bi_iter.bi_sector = bio_src->bi_iter.bi_sector; bio->bi_iter.bi_size = bio_src->bi_iter.bi_size; + if (bio->bi_rw & REQ_DISCARD) + goto integrity_clone; + + if (bio->bi_rw & REQ_WRITE_SAME) { + bio->bi_io_vec[bio->bi_vcnt++] = bio_src->bi_io_vec[0]; + goto integrity_clone; + } + bio_for_each_segment(bv, bio_src, iter) bio->bi_io_vec[bio->bi_vcnt++] = bv; +integrity_clone: if (bio_integrity(bio_src)) { int ret; diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 5215f04260b2..81ea55314b1f 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -3839,7 +3839,6 @@ static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans, rb_erase(&ref->rb_node, &head->ref_root); atomic_dec(&delayed_refs->num_entries); btrfs_put_delayed_ref(ref); - cond_resched_lock(&head->lock); } if (head->must_insert_reserved) pin_bytes = true; diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 184e9cb39647..d3d44486290b 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -5154,7 +5154,7 @@ static struct dentry *btrfs_lookup(struct inode *dir, struct dentry *dentry, return ERR_CAST(inode); } - return d_splice_alias(inode, dentry); + return d_materialise_unique(dentry, inode); } unsigned char btrfs_filetype_table[] = { diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 383ab455bfa7..a6d8efa46bfe 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -3537,20 +3537,6 @@ out: return ret; } -static long btrfs_ioctl_global_rsv(struct btrfs_root *root, void __user *arg) -{ - struct btrfs_block_rsv *block_rsv = &root->fs_info->global_block_rsv; - u64 reserved; - - spin_lock(&block_rsv->lock); - reserved = block_rsv->reserved; - spin_unlock(&block_rsv->lock); - - if (arg && copy_to_user(arg, &reserved, sizeof(reserved))) - return -EFAULT; - return 0; -} - /* * there are many ways the trans_start and trans_end ioctls can lead * to deadlocks. They should only be used by applications that @@ -4757,8 +4743,6 @@ long btrfs_ioctl(struct file *file, unsigned int return btrfs_ioctl_logical_to_ino(root, argp); case BTRFS_IOC_SPACE_INFO: return btrfs_ioctl_space_info(root, argp); - case BTRFS_IOC_GLOBAL_RSV: - return btrfs_ioctl_global_rsv(root, argp); case BTRFS_IOC_SYNC: { int ret; diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 9c8d1a3fdc3a..9dde9717c1b9 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -1332,6 +1332,16 @@ verbose_printk(KERN_DEBUG "btrfs: find_extent_clone: data_offset=%llu, " } if (cur_clone_root) { + if (compressed != BTRFS_COMPRESS_NONE) { + /* + * Offsets given by iterate_extent_inodes() are relative + * to the start of the extent, we need to add logical + * offset from the file extent item. + * (See why at backref.c:check_extent_in_eb()) + */ + cur_clone_root->offset += btrfs_file_extent_offset(eb, + fi); + } *found = cur_clone_root; ret = 0; } else { diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 97cc24198554..d04db817be5c 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -566,7 +566,7 @@ int btrfs_parse_options(struct btrfs_root *root, char *options) kfree(num); if (info->max_inline) { - info->max_inline = max_t(u64, + info->max_inline = min_t(u64, info->max_inline, root->sectorsize); } @@ -855,6 +855,7 @@ static struct dentry *get_default_root(struct super_block *sb, struct btrfs_path *path; struct btrfs_key location; struct inode *inode; + struct dentry *dentry; u64 dir_id; int new = 0; @@ -925,7 +926,13 @@ setup_root: return dget(sb->s_root); } - return d_obtain_alias(inode); + dentry = d_obtain_alias(inode); + if (!IS_ERR(dentry)) { + spin_lock(&dentry->d_lock); + dentry->d_flags &= ~DCACHE_DISCONNECTED; + spin_unlock(&dentry->d_lock); + } + return dentry; } static int btrfs_fill_super(struct super_block *sb, diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c index 782374d8fd19..865f4cf9a769 100644 --- a/fs/btrfs/sysfs.c +++ b/fs/btrfs/sysfs.c @@ -578,8 +578,14 @@ static int add_device_membership(struct btrfs_fs_info *fs_info) return -ENOMEM; list_for_each_entry(dev, &fs_devices->devices, dev_list) { - struct hd_struct *disk = dev->bdev->bd_part; - struct kobject *disk_kobj = &part_to_dev(disk)->kobj; + struct hd_struct *disk; + struct kobject *disk_kobj; + + if (!dev->bdev) + continue; + + disk = dev->bdev->bd_part; + disk_kobj = &part_to_dev(disk)->kobj; error = sysfs_create_link(fs_info->device_dir_kobj, disk_kobj, disk_kobj->name); diff --git a/fs/ceph/acl.c b/fs/ceph/acl.c index 4c2d452c4bfc..21887d63dad5 100644 --- a/fs/ceph/acl.c +++ b/fs/ceph/acl.c @@ -54,11 +54,6 @@ static inline struct posix_acl *ceph_get_cached_acl(struct inode *inode, return acl; } -void ceph_forget_all_cached_acls(struct inode *inode) -{ - forget_all_cached_acls(inode); -} - struct posix_acl *ceph_get_acl(struct inode *inode, int type) { int size; @@ -160,11 +155,7 @@ int ceph_set_acl(struct inode *inode, struct posix_acl *acl, int type) goto out_dput; } - if (value) - ret = __ceph_setxattr(dentry, name, value, size, 0); - else - ret = __ceph_removexattr(dentry, name); - + ret = __ceph_setxattr(dentry, name, value, size, 0); if (ret) { if (new_mode != old_mode) { newattrs.ia_mode = old_mode; diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index 6da4df84ba30..45eda6d7a40c 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -100,6 +100,14 @@ static unsigned fpos_off(loff_t p) return p & 0xffffffff; } +static int fpos_cmp(loff_t l, loff_t r) +{ + int v = ceph_frag_compare(fpos_frag(l), fpos_frag(r)); + if (v) + return v; + return (int)(fpos_off(l) - fpos_off(r)); +} + /* * When possible, we try to satisfy a readdir by peeking at the * dcache. We make this work by carefully ordering dentries on @@ -156,7 +164,7 @@ more: if (!d_unhashed(dentry) && dentry->d_inode && ceph_snap(dentry->d_inode) != CEPH_SNAPDIR && ceph_ino(dentry->d_inode) != CEPH_INO_CEPH && - ctx->pos <= di->offset) + fpos_cmp(ctx->pos, di->offset) <= 0) break; dout(" skipping %p %.*s at %llu (%llu)%s%s\n", dentry, dentry->d_name.len, dentry->d_name.name, di->offset, @@ -695,9 +703,8 @@ static int ceph_mknod(struct inode *dir, struct dentry *dentry, ceph_mdsc_put_request(req); if (!err) - err = ceph_init_acl(dentry, dentry->d_inode, dir); - - if (err) + ceph_init_acl(dentry, dentry->d_inode, dir); + else d_drop(dentry); return err; } @@ -735,7 +742,9 @@ static int ceph_symlink(struct inode *dir, struct dentry *dentry, if (!err && !req->r_reply_info.head->is_dentry) err = ceph_handle_notrace_create(dir, dentry); ceph_mdsc_put_request(req); - if (err) + if (!err) + ceph_init_acl(dentry, dentry->d_inode, dir); + else d_drop(dentry); return err; } @@ -776,7 +785,9 @@ static int ceph_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) err = ceph_handle_notrace_create(dir, dentry); ceph_mdsc_put_request(req); out: - if (err < 0) + if (!err) + ceph_init_acl(dentry, dentry->d_inode, dir); + else d_drop(dentry); return err; } diff --git a/fs/ceph/file.c b/fs/ceph/file.c index dfd2ce3419f8..09c7afe32e49 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -286,6 +286,7 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry, } else { dout("atomic_open finish_open on dn %p\n", dn); if (req->r_op == CEPH_MDS_OP_CREATE && req->r_reply_info.has_create_ino) { + ceph_init_acl(dentry, dentry->d_inode, dir); *opened |= FILE_CREATED; } err = finish_open(file, dentry, ceph_open, opened); diff --git a/fs/ceph/super.c b/fs/ceph/super.c index 2df963f1cf5a..10a4ccbf38da 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -144,7 +144,11 @@ enum { Opt_ino32, Opt_noino32, Opt_fscache, - Opt_nofscache + Opt_nofscache, +#ifdef CONFIG_CEPH_FS_POSIX_ACL + Opt_acl, +#endif + Opt_noacl }; static match_table_t fsopt_tokens = { @@ -172,6 +176,10 @@ static match_table_t fsopt_tokens = { {Opt_noino32, "noino32"}, {Opt_fscache, "fsc"}, {Opt_nofscache, "nofsc"}, +#ifdef CONFIG_CEPH_FS_POSIX_ACL + {Opt_acl, "acl"}, +#endif + {Opt_noacl, "noacl"}, {-1, NULL} }; @@ -271,6 +279,14 @@ static int parse_fsopt_token(char *c, void *private) case Opt_nofscache: fsopt->flags &= ~CEPH_MOUNT_OPT_FSCACHE; break; +#ifdef CONFIG_CEPH_FS_POSIX_ACL + case Opt_acl: + fsopt->sb_flags |= MS_POSIXACL; + break; +#endif + case Opt_noacl: + fsopt->sb_flags &= ~MS_POSIXACL; + break; default: BUG_ON(token); } @@ -438,6 +454,13 @@ static int ceph_show_options(struct seq_file *m, struct dentry *root) else seq_puts(m, ",nofsc"); +#ifdef CONFIG_CEPH_FS_POSIX_ACL + if (fsopt->sb_flags & MS_POSIXACL) + seq_puts(m, ",acl"); + else + seq_puts(m, ",noacl"); +#endif + if (fsopt->wsize) seq_printf(m, ",wsize=%d", fsopt->wsize); if (fsopt->rsize != CEPH_RSIZE_DEFAULT) @@ -819,9 +842,6 @@ static int ceph_set_super(struct super_block *s, void *data) s->s_flags = fsc->mount_options->sb_flags; s->s_maxbytes = 1ULL << 40; /* temp value until we get mdsmap */ -#ifdef CONFIG_CEPH_FS_POSIX_ACL - s->s_flags |= MS_POSIXACL; -#endif s->s_xattr = ceph_xattr_handlers; s->s_fs_info = fsc; @@ -911,6 +931,10 @@ static struct dentry *ceph_mount(struct file_system_type *fs_type, struct ceph_options *opt = NULL; dout("ceph_mount\n"); + +#ifdef CONFIG_CEPH_FS_POSIX_ACL + flags |= MS_POSIXACL; +#endif err = parse_mount_options(&fsopt, &opt, flags, data, dev_name, &path); if (err < 0) { res = ERR_PTR(err); diff --git a/fs/ceph/super.h b/fs/ceph/super.h index 19793b56d0a7..d8801a95b685 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -13,6 +13,7 @@ #include <linux/wait.h> #include <linux/writeback.h> #include <linux/slab.h> +#include <linux/posix_acl.h> #include <linux/ceph/libceph.h> @@ -743,7 +744,11 @@ extern const struct xattr_handler *ceph_xattr_handlers[]; struct posix_acl *ceph_get_acl(struct inode *, int); int ceph_set_acl(struct inode *inode, struct posix_acl *acl, int type); int ceph_init_acl(struct dentry *, struct inode *, struct inode *); -void ceph_forget_all_cached_acls(struct inode *inode); + +static inline void ceph_forget_all_cached_acls(struct inode *inode) +{ + forget_all_cached_acls(inode); +} #else diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c index 898b6565ad3e..a55ec37378c6 100644 --- a/fs/ceph/xattr.c +++ b/fs/ceph/xattr.c @@ -12,6 +12,9 @@ #define XATTR_CEPH_PREFIX "ceph." #define XATTR_CEPH_PREFIX_LEN (sizeof (XATTR_CEPH_PREFIX) - 1) +static int __remove_xattr(struct ceph_inode_info *ci, + struct ceph_inode_xattr *xattr); + /* * List of handlers for synthetic system.* attributes. Other * attributes are handled directly. @@ -319,8 +322,7 @@ static struct ceph_vxattr *ceph_match_vxattr(struct inode *inode, static int __set_xattr(struct ceph_inode_info *ci, const char *name, int name_len, const char *val, int val_len, - int dirty, - int should_free_name, int should_free_val, + int flags, int update_xattr, struct ceph_inode_xattr **newxattr) { struct rb_node **p; @@ -349,12 +351,31 @@ static int __set_xattr(struct ceph_inode_info *ci, xattr = NULL; } + if (update_xattr) { + int err = 0; + if (xattr && (flags & XATTR_CREATE)) + err = -EEXIST; + else if (!xattr && (flags & XATTR_REPLACE)) + err = -ENODATA; + if (err) { + kfree(name); + kfree(val); + return err; + } + if (update_xattr < 0) { + if (xattr) + __remove_xattr(ci, xattr); + kfree(name); + return 0; + } + } + if (!xattr) { new = 1; xattr = *newxattr; xattr->name = name; xattr->name_len = name_len; - xattr->should_free_name = should_free_name; + xattr->should_free_name = update_xattr; ci->i_xattrs.count++; dout("__set_xattr count=%d\n", ci->i_xattrs.count); @@ -364,7 +385,7 @@ static int __set_xattr(struct ceph_inode_info *ci, if (xattr->should_free_val) kfree((void *)xattr->val); - if (should_free_name) { + if (update_xattr) { kfree((void *)name); name = xattr->name; } @@ -379,8 +400,8 @@ static int __set_xattr(struct ceph_inode_info *ci, xattr->val = ""; xattr->val_len = val_len; - xattr->dirty = dirty; - xattr->should_free_val = (val && should_free_val); + xattr->dirty = update_xattr; + xattr->should_free_val = (val && update_xattr); if (new) { rb_link_node(&xattr->node, parent, p); @@ -442,7 +463,7 @@ static int __remove_xattr(struct ceph_inode_info *ci, struct ceph_inode_xattr *xattr) { if (!xattr) - return -EOPNOTSUPP; + return -ENODATA; rb_erase(&xattr->node, &ci->i_xattrs.index); @@ -588,7 +609,7 @@ start: p += len; err = __set_xattr(ci, name, namelen, val, len, - 0, 0, 0, &xattrs[numattr]); + 0, 0, &xattrs[numattr]); if (err < 0) goto bad; @@ -850,6 +871,9 @@ static int ceph_sync_setxattr(struct dentry *dentry, const char *name, dout("setxattr value=%.*s\n", (int)size, value); + if (!value) + flags |= CEPH_XATTR_REMOVE; + /* do request */ req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_SETXATTR, USE_AUTH_MDS); @@ -892,7 +916,7 @@ int __ceph_setxattr(struct dentry *dentry, const char *name, struct ceph_inode_info *ci = ceph_inode(inode); int issued; int err; - int dirty; + int dirty = 0; int name_len = strlen(name); int val_len = size; char *newname = NULL; @@ -953,12 +977,14 @@ retry: goto retry; } - err = __set_xattr(ci, newname, name_len, newval, - val_len, 1, 1, 1, &xattr); + err = __set_xattr(ci, newname, name_len, newval, val_len, + flags, value ? 1 : -1, &xattr); - dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_XATTR_EXCL); - ci->i_xattrs.dirty = true; - inode->i_ctime = CURRENT_TIME; + if (!err) { + dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_XATTR_EXCL); + ci->i_xattrs.dirty = true; + inode->i_ctime = CURRENT_TIME; + } spin_unlock(&ci->i_ceph_lock); if (dirty) diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c index 8f9b4f710d4a..7ff866dbb89e 100644 --- a/fs/cifs/cifsacl.c +++ b/fs/cifs/cifsacl.c @@ -865,8 +865,8 @@ static int build_sec_desc(struct cifs_ntsd *pntsd, struct cifs_ntsd *pnntsd, return rc; } -static struct cifs_ntsd *get_cifs_acl_by_fid(struct cifs_sb_info *cifs_sb, - __u16 fid, u32 *pacllen) +struct cifs_ntsd *get_cifs_acl_by_fid(struct cifs_sb_info *cifs_sb, + const struct cifs_fid *cifsfid, u32 *pacllen) { struct cifs_ntsd *pntsd = NULL; unsigned int xid; @@ -877,7 +877,8 @@ static struct cifs_ntsd *get_cifs_acl_by_fid(struct cifs_sb_info *cifs_sb, return ERR_CAST(tlink); xid = get_xid(); - rc = CIFSSMBGetCIFSACL(xid, tlink_tcon(tlink), fid, &pntsd, pacllen); + rc = CIFSSMBGetCIFSACL(xid, tlink_tcon(tlink), cifsfid->netfid, &pntsd, + pacllen); free_xid(xid); cifs_put_tlink(tlink); @@ -946,7 +947,7 @@ struct cifs_ntsd *get_cifs_acl(struct cifs_sb_info *cifs_sb, if (!open_file) return get_cifs_acl_by_path(cifs_sb, path, pacllen); - pntsd = get_cifs_acl_by_fid(cifs_sb, open_file->fid.netfid, pacllen); + pntsd = get_cifs_acl_by_fid(cifs_sb, &open_file->fid, pacllen); cifsFileInfo_put(open_file); return pntsd; } @@ -1006,19 +1007,31 @@ out: /* Translate the CIFS ACL (simlar to NTFS ACL) for a file into mode bits */ int cifs_acl_to_fattr(struct cifs_sb_info *cifs_sb, struct cifs_fattr *fattr, - struct inode *inode, const char *path, const __u16 *pfid) + struct inode *inode, const char *path, + const struct cifs_fid *pfid) { struct cifs_ntsd *pntsd = NULL; u32 acllen = 0; int rc = 0; + struct tcon_link *tlink = cifs_sb_tlink(cifs_sb); + struct cifs_tcon *tcon; cifs_dbg(NOISY, "converting ACL to mode for %s\n", path); - if (pfid) - pntsd = get_cifs_acl_by_fid(cifs_sb, *pfid, &acllen); - else - pntsd = get_cifs_acl(cifs_sb, inode, path, &acllen); + if (IS_ERR(tlink)) + return PTR_ERR(tlink); + tcon = tlink_tcon(tlink); + if (pfid && (tcon->ses->server->ops->get_acl_by_fid)) + pntsd = tcon->ses->server->ops->get_acl_by_fid(cifs_sb, pfid, + &acllen); + else if (tcon->ses->server->ops->get_acl) + pntsd = tcon->ses->server->ops->get_acl(cifs_sb, inode, path, + &acllen); + else { + cifs_put_tlink(tlink); + return -EOPNOTSUPP; + } /* if we can retrieve the ACL, now parse Access Control Entries, ACEs */ if (IS_ERR(pntsd)) { rc = PTR_ERR(pntsd); @@ -1030,6 +1043,8 @@ cifs_acl_to_fattr(struct cifs_sb_info *cifs_sb, struct cifs_fattr *fattr, cifs_dbg(VFS, "parse sec desc failed rc = %d\n", rc); } + cifs_put_tlink(tlink); + return rc; } @@ -1043,15 +1058,30 @@ id_mode_to_cifs_acl(struct inode *inode, const char *path, __u64 nmode, __u32 secdesclen = 0; struct cifs_ntsd *pntsd = NULL; /* acl obtained from server */ struct cifs_ntsd *pnntsd = NULL; /* modified acl to be sent to server */ + struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); + struct tcon_link *tlink = cifs_sb_tlink(cifs_sb); + struct cifs_tcon *tcon; + + if (IS_ERR(tlink)) + return PTR_ERR(tlink); + tcon = tlink_tcon(tlink); cifs_dbg(NOISY, "set ACL from mode for %s\n", path); /* Get the security descriptor */ - pntsd = get_cifs_acl(CIFS_SB(inode->i_sb), inode, path, &secdesclen); + + if (tcon->ses->server->ops->get_acl == NULL) { + cifs_put_tlink(tlink); + return -EOPNOTSUPP; + } + + pntsd = tcon->ses->server->ops->get_acl(cifs_sb, inode, path, + &secdesclen); if (IS_ERR(pntsd)) { rc = PTR_ERR(pntsd); cifs_dbg(VFS, "%s: error %d getting sec desc\n", __func__, rc); - goto out; + cifs_put_tlink(tlink); + return rc; } /* @@ -1064,6 +1094,7 @@ id_mode_to_cifs_acl(struct inode *inode, const char *path, __u64 nmode, pnntsd = kmalloc(secdesclen, GFP_KERNEL); if (!pnntsd) { kfree(pntsd); + cifs_put_tlink(tlink); return -ENOMEM; } @@ -1072,14 +1103,18 @@ id_mode_to_cifs_acl(struct inode *inode, const char *path, __u64 nmode, cifs_dbg(NOISY, "build_sec_desc rc: %d\n", rc); + if (tcon->ses->server->ops->set_acl == NULL) + rc = -EOPNOTSUPP; + if (!rc) { /* Set the security descriptor */ - rc = set_cifs_acl(pnntsd, secdesclen, inode, path, aclflag); + rc = tcon->ses->server->ops->set_acl(pnntsd, secdesclen, inode, + path, aclflag); cifs_dbg(NOISY, "set_cifs_acl rc: %d\n", rc); } + cifs_put_tlink(tlink); kfree(pnntsd); kfree(pntsd); -out: return rc; } diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index a245d1809ed8..cf32f0393369 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -323,7 +323,8 @@ struct smb_version_operations { /* async read from the server */ int (*async_readv)(struct cifs_readdata *); /* async write to the server */ - int (*async_writev)(struct cifs_writedata *); + int (*async_writev)(struct cifs_writedata *, + void (*release)(struct kref *)); /* sync read from the server */ int (*sync_read)(const unsigned int, struct cifsFileInfo *, struct cifs_io_parms *, unsigned int *, char **, @@ -395,6 +396,12 @@ struct smb_version_operations { int (*set_EA)(const unsigned int, struct cifs_tcon *, const char *, const char *, const void *, const __u16, const struct nls_table *, int); + struct cifs_ntsd * (*get_acl)(struct cifs_sb_info *, struct inode *, + const char *, u32 *); + struct cifs_ntsd * (*get_acl_by_fid)(struct cifs_sb_info *, + const struct cifs_fid *, u32 *); + int (*set_acl)(struct cifs_ntsd *, __u32, struct inode *, const char *, + int); }; struct smb_version_values { @@ -1064,7 +1071,7 @@ struct cifs_writedata { unsigned int pagesz; unsigned int tailsz; unsigned int nr_pages; - struct page *pages[1]; + struct page *pages[]; }; /* diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h index 79e6e9a93a8c..acc4ee8ed075 100644 --- a/fs/cifs/cifsproto.h +++ b/fs/cifs/cifsproto.h @@ -151,7 +151,7 @@ extern struct inode *cifs_iget(struct super_block *sb, extern int cifs_get_inode_info(struct inode **inode, const char *full_path, FILE_ALL_INFO *data, struct super_block *sb, - int xid, const __u16 *fid); + int xid, const struct cifs_fid *fid); extern int cifs_get_inode_info_unix(struct inode **pinode, const unsigned char *search_path, struct super_block *sb, unsigned int xid); @@ -162,11 +162,13 @@ extern int cifs_rename_pending_delete(const char *full_path, const unsigned int xid); extern int cifs_acl_to_fattr(struct cifs_sb_info *cifs_sb, struct cifs_fattr *fattr, struct inode *inode, - const char *path, const __u16 *pfid); + const char *path, const struct cifs_fid *pfid); extern int id_mode_to_cifs_acl(struct inode *inode, const char *path, __u64, kuid_t, kgid_t); extern struct cifs_ntsd *get_cifs_acl(struct cifs_sb_info *, struct inode *, const char *, u32 *); +extern struct cifs_ntsd *get_cifs_acl_by_fid(struct cifs_sb_info *, + const struct cifs_fid *, u32 *); extern int set_cifs_acl(struct cifs_ntsd *, __u32, struct inode *, const char *, int); @@ -488,7 +490,8 @@ void cifs_readdata_release(struct kref *refcount); int cifs_async_readv(struct cifs_readdata *rdata); int cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid); -int cifs_async_writev(struct cifs_writedata *wdata); +int cifs_async_writev(struct cifs_writedata *wdata, + void (*release)(struct kref *kref)); void cifs_writev_complete(struct work_struct *work); struct cifs_writedata *cifs_writedata_alloc(unsigned int nr_pages, work_func_t complete); diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index 4d881c35eeca..f3264bd7a83d 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -1910,7 +1910,7 @@ cifs_writev_requeue(struct cifs_writedata *wdata) do { server = tlink_tcon(wdata->cfile->tlink)->ses->server; - rc = server->ops->async_writev(wdata); + rc = server->ops->async_writev(wdata, cifs_writedata_release); } while (rc == -EAGAIN); for (i = 0; i < wdata->nr_pages; i++) { @@ -1962,15 +1962,9 @@ cifs_writedata_alloc(unsigned int nr_pages, work_func_t complete) { struct cifs_writedata *wdata; - /* this would overflow */ - if (nr_pages == 0) { - cifs_dbg(VFS, "%s: called with nr_pages == 0!\n", __func__); - return NULL; - } - /* writedata + number of page pointers */ wdata = kzalloc(sizeof(*wdata) + - sizeof(struct page *) * (nr_pages - 1), GFP_NOFS); + sizeof(struct page *) * nr_pages, GFP_NOFS); if (wdata != NULL) { kref_init(&wdata->refcount); INIT_LIST_HEAD(&wdata->list); @@ -2031,7 +2025,8 @@ cifs_writev_callback(struct mid_q_entry *mid) /* cifs_async_writev - send an async write, and set up mid to handle result */ int -cifs_async_writev(struct cifs_writedata *wdata) +cifs_async_writev(struct cifs_writedata *wdata, + void (*release)(struct kref *kref)) { int rc = -EACCES; WRITE_REQ *smb = NULL; @@ -2105,7 +2100,7 @@ cifs_async_writev(struct cifs_writedata *wdata) if (rc == 0) cifs_stats_inc(&tcon->stats.cifs_stats.num_writes); else - kref_put(&wdata->refcount, cifs_writedata_release); + kref_put(&wdata->refcount, release); async_writev_out: cifs_small_buf_release(smb); diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c index d3a6796caa5a..3db0c5fd9a11 100644 --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -378,7 +378,7 @@ cifs_create_get_file_info: xid); else { rc = cifs_get_inode_info(&newinode, full_path, buf, inode->i_sb, - xid, &fid->netfid); + xid, fid); if (newinode) { if (server->ops->set_lease_key) server->ops->set_lease_key(newinode, fid); diff --git a/fs/cifs/file.c b/fs/cifs/file.c index a7eda8ebfacc..53c15074bb36 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -244,7 +244,7 @@ cifs_nt_open(char *full_path, struct inode *inode, struct cifs_sb_info *cifs_sb, xid); else rc = cifs_get_inode_info(&inode, full_path, buf, inode->i_sb, - xid, &fid->netfid); + xid, fid); out: kfree(buf); @@ -2043,7 +2043,8 @@ retry: } wdata->pid = wdata->cfile->pid; server = tlink_tcon(wdata->cfile->tlink)->ses->server; - rc = server->ops->async_writev(wdata); + rc = server->ops->async_writev(wdata, + cifs_writedata_release); } while (wbc->sync_mode == WB_SYNC_ALL && rc == -EAGAIN); for (i = 0; i < nr_pages; ++i) @@ -2331,9 +2332,20 @@ size_t get_numpages(const size_t wsize, const size_t len, size_t *cur_len) } static void -cifs_uncached_writev_complete(struct work_struct *work) +cifs_uncached_writedata_release(struct kref *refcount) { int i; + struct cifs_writedata *wdata = container_of(refcount, + struct cifs_writedata, refcount); + + for (i = 0; i < wdata->nr_pages; i++) + put_page(wdata->pages[i]); + cifs_writedata_release(refcount); +} + +static void +cifs_uncached_writev_complete(struct work_struct *work) +{ struct cifs_writedata *wdata = container_of(work, struct cifs_writedata, work); struct inode *inode = wdata->cfile->dentry->d_inode; @@ -2347,12 +2359,7 @@ cifs_uncached_writev_complete(struct work_struct *work) complete(&wdata->done); - if (wdata->result != -EAGAIN) { - for (i = 0; i < wdata->nr_pages; i++) - put_page(wdata->pages[i]); - } - - kref_put(&wdata->refcount, cifs_writedata_release); + kref_put(&wdata->refcount, cifs_uncached_writedata_release); } /* attempt to send write to server, retry on any -EAGAIN errors */ @@ -2370,7 +2377,8 @@ cifs_uncached_retry_writev(struct cifs_writedata *wdata) if (rc != 0) continue; } - rc = server->ops->async_writev(wdata); + rc = server->ops->async_writev(wdata, + cifs_uncached_writedata_release); } while (rc == -EAGAIN); return rc; @@ -2381,7 +2389,7 @@ cifs_iovec_write(struct file *file, const struct iovec *iov, unsigned long nr_segs, loff_t *poffset) { unsigned long nr_pages, i; - size_t copied, len, cur_len; + size_t bytes, copied, len, cur_len; ssize_t total_written = 0; loff_t offset; struct iov_iter it; @@ -2436,14 +2444,45 @@ cifs_iovec_write(struct file *file, const struct iovec *iov, save_len = cur_len; for (i = 0; i < nr_pages; i++) { - copied = min_t(const size_t, cur_len, PAGE_SIZE); + bytes = min_t(const size_t, cur_len, PAGE_SIZE); copied = iov_iter_copy_from_user(wdata->pages[i], &it, - 0, copied); + 0, bytes); cur_len -= copied; iov_iter_advance(&it, copied); + /* + * If we didn't copy as much as we expected, then that + * may mean we trod into an unmapped area. Stop copying + * at that point. On the next pass through the big + * loop, we'll likely end up getting a zero-length + * write and bailing out of it. + */ + if (copied < bytes) + break; } cur_len = save_len - cur_len; + /* + * If we have no data to send, then that probably means that + * the copy above failed altogether. That's most likely because + * the address in the iovec was bogus. Set the rc to -EFAULT, + * free anything we allocated and bail out. + */ + if (!cur_len) { + for (i = 0; i < nr_pages; i++) + put_page(wdata->pages[i]); + kfree(wdata); + rc = -EFAULT; + break; + } + + /* + * i + 1 now represents the number of pages we actually used in + * the copy phase above. Bring nr_pages down to that, and free + * any pages that we didn't use. + */ + for ( ; nr_pages > i + 1; nr_pages--) + put_page(wdata->pages[nr_pages - 1]); + wdata->sync_mode = WB_SYNC_ALL; wdata->nr_pages = nr_pages; wdata->offset = (__u64)offset; @@ -2454,7 +2493,8 @@ cifs_iovec_write(struct file *file, const struct iovec *iov, wdata->tailsz = cur_len - ((nr_pages - 1) * PAGE_SIZE); rc = cifs_uncached_retry_writev(wdata); if (rc) { - kref_put(&wdata->refcount, cifs_writedata_release); + kref_put(&wdata->refcount, + cifs_uncached_writedata_release); break; } @@ -2496,7 +2536,7 @@ restart_loop: } } list_del_init(&wdata->list); - kref_put(&wdata->refcount, cifs_writedata_release); + kref_put(&wdata->refcount, cifs_uncached_writedata_release); } if (total_written > 0) diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 9cb9679d7357..aadc2b68678b 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -527,10 +527,15 @@ static int cifs_sfu_mode(struct cifs_fattr *fattr, const unsigned char *path, return PTR_ERR(tlink); tcon = tlink_tcon(tlink); - rc = CIFSSMBQAllEAs(xid, tcon, path, "SETFILEBITS", - ea_value, 4 /* size of buf */, cifs_sb->local_nls, - cifs_sb->mnt_cifs_flags & - CIFS_MOUNT_MAP_SPECIAL_CHR); + if (tcon->ses->server->ops->query_all_EAs == NULL) { + cifs_put_tlink(tlink); + return -EOPNOTSUPP; + } + + rc = tcon->ses->server->ops->query_all_EAs(xid, tcon, path, + "SETFILEBITS", ea_value, 4 /* size of buf */, + cifs_sb->local_nls, + cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR); cifs_put_tlink(tlink); if (rc < 0) return (int)rc; @@ -672,7 +677,7 @@ cgfi_exit: int cifs_get_inode_info(struct inode **inode, const char *full_path, FILE_ALL_INFO *data, struct super_block *sb, int xid, - const __u16 *fid) + const struct cifs_fid *fid) { bool validinum = false; __u16 srchflgs; diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c index 9ac5bfc9cc56..526fb89f9230 100644 --- a/fs/cifs/smb1ops.c +++ b/fs/cifs/smb1ops.c @@ -1067,6 +1067,15 @@ struct smb_version_operations smb1_operations = { .query_mf_symlink = cifs_query_mf_symlink, .create_mf_symlink = cifs_create_mf_symlink, .is_read_op = cifs_is_read_op, +#ifdef CONFIG_CIFS_XATTR + .query_all_EAs = CIFSSMBQAllEAs, + .set_EA = CIFSSMBSetEA, +#endif /* CIFS_XATTR */ +#ifdef CONFIG_CIFS_ACL + .get_acl = get_cifs_acl, + .get_acl_by_fid = get_cifs_acl_by_fid, + .set_acl = set_cifs_acl, +#endif /* CIFS_ACL */ }; struct smb_version_values smb1_values = { diff --git a/fs/cifs/smb2glob.h b/fs/cifs/smb2glob.h index c38350851b08..bc0bb9c34f72 100644 --- a/fs/cifs/smb2glob.h +++ b/fs/cifs/smb2glob.h @@ -57,4 +57,7 @@ #define SMB2_CMACAES_SIZE (16) #define SMB3_SIGNKEY_SIZE (16) +/* Maximum buffer size value we can send with 1 credit */ +#define SMB2_MAX_BUFFER_SIZE 65536 + #endif /* _SMB2_GLOB_H */ diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 757da3e54d3d..192f51a12cf1 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -182,11 +182,8 @@ smb2_negotiate_wsize(struct cifs_tcon *tcon, struct smb_vol *volume_info) /* start with specified wsize, or default */ wsize = volume_info->wsize ? volume_info->wsize : CIFS_DEFAULT_IOSIZE; wsize = min_t(unsigned int, wsize, server->max_write); - /* - * limit write size to 2 ** 16, because we don't support multicredit - * requests now. - */ - wsize = min_t(unsigned int, wsize, 2 << 15); + /* set it to the maximum buffer size value we can send with 1 credit */ + wsize = min_t(unsigned int, wsize, SMB2_MAX_BUFFER_SIZE); return wsize; } @@ -200,11 +197,8 @@ smb2_negotiate_rsize(struct cifs_tcon *tcon, struct smb_vol *volume_info) /* start with specified rsize, or default */ rsize = volume_info->rsize ? volume_info->rsize : CIFS_DEFAULT_IOSIZE; rsize = min_t(unsigned int, rsize, server->max_read); - /* - * limit write size to 2 ** 16, because we don't support multicredit - * requests now. - */ - rsize = min_t(unsigned int, rsize, 2 << 15); + /* set it to the maximum buffer size value we can send with 1 credit */ + rsize = min_t(unsigned int, rsize, SMB2_MAX_BUFFER_SIZE); return rsize; } diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 2013234b73ad..860344701067 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -413,7 +413,9 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses) /* SMB2 only has an extended negflavor */ server->negflavor = CIFS_NEGFLAVOR_EXTENDED; - server->maxBuf = le32_to_cpu(rsp->MaxTransactSize); + /* set it to the maximum buffer size value we can send with 1 credit */ + server->maxBuf = min_t(unsigned int, le32_to_cpu(rsp->MaxTransactSize), + SMB2_MAX_BUFFER_SIZE); server->max_read = le32_to_cpu(rsp->MaxReadSize); server->max_write = le32_to_cpu(rsp->MaxWriteSize); /* BB Do we need to validate the SecurityMode? */ @@ -1890,7 +1892,8 @@ smb2_writev_callback(struct mid_q_entry *mid) /* smb2_async_writev - send an async write, and set up mid to handle result */ int -smb2_async_writev(struct cifs_writedata *wdata) +smb2_async_writev(struct cifs_writedata *wdata, + void (*release)(struct kref *kref)) { int rc = -EACCES; struct smb2_write_req *req = NULL; @@ -1938,7 +1941,7 @@ smb2_async_writev(struct cifs_writedata *wdata) smb2_writev_callback, wdata, 0); if (rc) { - kref_put(&wdata->refcount, cifs_writedata_release); + kref_put(&wdata->refcount, release); cifs_stats_fail_inc(tcon, SMB2_WRITE_HE); } diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h index 93adc64666f3..0ce48db20a65 100644 --- a/fs/cifs/smb2proto.h +++ b/fs/cifs/smb2proto.h @@ -123,7 +123,8 @@ extern int SMB2_get_srv_num(const unsigned int xid, struct cifs_tcon *tcon, extern int smb2_async_readv(struct cifs_readdata *rdata); extern int SMB2_read(const unsigned int xid, struct cifs_io_parms *io_parms, unsigned int *nbytes, char **buf, int *buf_type); -extern int smb2_async_writev(struct cifs_writedata *wdata); +extern int smb2_async_writev(struct cifs_writedata *wdata, + void (*release)(struct kref *kref)); extern int SMB2_write(const unsigned int xid, struct cifs_io_parms *io_parms, unsigned int *nbytes, struct kvec *iov, int n_vec); extern int SMB2_echo(struct TCP_Server_Info *server); diff --git a/fs/cifs/xattr.c b/fs/cifs/xattr.c index 95c43bb20335..5ac836a86b18 100644 --- a/fs/cifs/xattr.c +++ b/fs/cifs/xattr.c @@ -176,8 +176,12 @@ int cifs_setxattr(struct dentry *direntry, const char *ea_name, rc = -ENOMEM; } else { memcpy(pacl, ea_value, value_size); - rc = set_cifs_acl(pacl, value_size, - direntry->d_inode, full_path, CIFS_ACL_DACL); + if (pTcon->ses->server->ops->set_acl) + rc = pTcon->ses->server->ops->set_acl(pacl, + value_size, direntry->d_inode, + full_path, CIFS_ACL_DACL); + else + rc = -EOPNOTSUPP; if (rc == 0) /* force revalidate of the inode */ CIFS_I(direntry->d_inode)->time = 0; kfree(pacl); @@ -323,8 +327,11 @@ ssize_t cifs_getxattr(struct dentry *direntry, const char *ea_name, u32 acllen; struct cifs_ntsd *pacl; - pacl = get_cifs_acl(cifs_sb, direntry->d_inode, - full_path, &acllen); + if (pTcon->ses->server->ops->get_acl == NULL) + goto get_ea_exit; /* rc already EOPNOTSUPP */ + + pacl = pTcon->ses->server->ops->get_acl(cifs_sb, + direntry->d_inode, full_path, &acllen); if (IS_ERR(pacl)) { rc = PTR_ERR(pacl); cifs_dbg(VFS, "%s: error %zd getting sec desc\n", diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index ece55565b9cd..d3a534fdc5ff 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -771,6 +771,8 @@ do { \ if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime)) \ (einode)->xtime.tv_sec = \ (signed)le32_to_cpu((raw_inode)->xtime); \ + else \ + (einode)->xtime.tv_sec = 0; \ if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime ## _extra)) \ ext4_decode_extra_time(&(einode)->xtime, \ raw_inode->xtime ## _extra); \ diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 10cff4736b11..74bc2d549c58 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -3906,6 +3906,7 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode, } else err = ret; map->m_flags |= EXT4_MAP_MAPPED; + map->m_pblk = newblock; if (allocated > map->m_len) allocated = map->m_len; map->m_len = allocated; diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index 6bea80614d77..a2a837f00407 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -140,7 +140,7 @@ static long swap_inode_boot_loader(struct super_block *sb, handle = ext4_journal_start(inode_bl, EXT4_HT_MOVE_EXTENTS, 2); if (IS_ERR(handle)) { err = -EINVAL; - goto swap_boot_out; + goto journal_err_out; } /* Protect extent tree against block allocations via delalloc */ @@ -198,6 +198,7 @@ static long swap_inode_boot_loader(struct super_block *sb, ext4_double_up_write_data_sem(inode, inode_bl); +journal_err_out: ext4_inode_resume_unlocked_dio(inode); ext4_inode_resume_unlocked_dio(inode_bl); diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index c5adbb318a90..f3b84cd9de56 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -243,6 +243,7 @@ static int ext4_alloc_group_tables(struct super_block *sb, ext4_group_t group; ext4_group_t last_group; unsigned overhead; + __u16 uninit_mask = (flexbg_size > 1) ? ~EXT4_BG_BLOCK_UNINIT : ~0; BUG_ON(flex_gd->count == 0 || group_data == NULL); @@ -266,7 +267,7 @@ next_group: src_group++; for (; src_group <= last_group; src_group++) { overhead = ext4_group_overhead_blocks(sb, src_group); - if (overhead != 0) + if (overhead == 0) last_blk += group_data[src_group - group].blocks_count; else break; @@ -280,8 +281,7 @@ next_group: group = ext4_get_group_number(sb, start_blk - 1); group -= group_data[0].group; group_data[group].free_blocks_count--; - if (flexbg_size > 1) - flex_gd->bg_flags[group] &= ~EXT4_BG_BLOCK_UNINIT; + flex_gd->bg_flags[group] &= uninit_mask; } /* Allocate inode bitmaps */ @@ -292,22 +292,30 @@ next_group: group = ext4_get_group_number(sb, start_blk - 1); group -= group_data[0].group; group_data[group].free_blocks_count--; - if (flexbg_size > 1) - flex_gd->bg_flags[group] &= ~EXT4_BG_BLOCK_UNINIT; + flex_gd->bg_flags[group] &= uninit_mask; } /* Allocate inode tables */ for (; it_index < flex_gd->count; it_index++) { - if (start_blk + EXT4_SB(sb)->s_itb_per_group > last_blk) + unsigned int itb = EXT4_SB(sb)->s_itb_per_group; + ext4_fsblk_t next_group_start; + + if (start_blk + itb > last_blk) goto next_group; group_data[it_index].inode_table = start_blk; - group = ext4_get_group_number(sb, start_blk - 1); + group = ext4_get_group_number(sb, start_blk); + next_group_start = ext4_group_first_block_no(sb, group + 1); group -= group_data[0].group; - group_data[group].free_blocks_count -= - EXT4_SB(sb)->s_itb_per_group; - if (flexbg_size > 1) - flex_gd->bg_flags[group] &= ~EXT4_BG_BLOCK_UNINIT; + if (start_blk + itb > next_group_start) { + flex_gd->bg_flags[group + 1] &= uninit_mask; + overhead = start_blk + itb - next_group_start; + group_data[group + 1].free_blocks_count -= overhead; + itb -= overhead; + } + + group_data[group].free_blocks_count -= itb; + flex_gd->bg_flags[group] &= uninit_mask; start_blk += EXT4_SB(sb)->s_itb_per_group; } @@ -401,7 +409,7 @@ static int set_flexbg_block_bitmap(struct super_block *sb, handle_t *handle, start = ext4_group_first_block_no(sb, group); group -= flex_gd->groups[0].group; - count2 = sb->s_blocksize * 8 - (block - start); + count2 = EXT4_BLOCKS_PER_GROUP(sb) - (block - start); if (count2 > count) count2 = count; @@ -620,7 +628,7 @@ handle_ib: if (err) goto out; count = group_table_count[j]; - start = group_data[i].block_bitmap; + start = (&group_data[i].block_bitmap)[j]; block = start; } diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 1f7784de05b6..710fed2377d4 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -3695,16 +3695,22 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) for (i = 0; i < 4; i++) sbi->s_hash_seed[i] = le32_to_cpu(es->s_hash_seed[i]); sbi->s_def_hash_version = es->s_def_hash_version; - i = le32_to_cpu(es->s_flags); - if (i & EXT2_FLAGS_UNSIGNED_HASH) - sbi->s_hash_unsigned = 3; - else if ((i & EXT2_FLAGS_SIGNED_HASH) == 0) { + if (EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_DIR_INDEX)) { + i = le32_to_cpu(es->s_flags); + if (i & EXT2_FLAGS_UNSIGNED_HASH) + sbi->s_hash_unsigned = 3; + else if ((i & EXT2_FLAGS_SIGNED_HASH) == 0) { #ifdef __CHAR_UNSIGNED__ - es->s_flags |= cpu_to_le32(EXT2_FLAGS_UNSIGNED_HASH); - sbi->s_hash_unsigned = 3; + if (!(sb->s_flags & MS_RDONLY)) + es->s_flags |= + cpu_to_le32(EXT2_FLAGS_UNSIGNED_HASH); + sbi->s_hash_unsigned = 3; #else - es->s_flags |= cpu_to_le32(EXT2_FLAGS_SIGNED_HASH); + if (!(sb->s_flags & MS_RDONLY)) + es->s_flags |= + cpu_to_le32(EXT2_FLAGS_SIGNED_HASH); #endif + } } /* Handle clustersize */ diff --git a/fs/file.c b/fs/file.c index 771578b33fb6..db25c2bdfe46 100644 --- a/fs/file.c +++ b/fs/file.c @@ -34,7 +34,7 @@ static void *alloc_fdmem(size_t size) * vmalloc() if the allocation size will be considered "large" by the VM. */ if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) { - void *data = kmalloc(size, GFP_KERNEL|__GFP_NOWARN); + void *data = kmalloc(size, GFP_KERNEL|__GFP_NOWARN|__GFP_NORETRY); if (data != NULL) return data; } diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index e0259a163f98..d754e3cf99a8 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -40,18 +40,13 @@ struct wb_writeback_work { long nr_pages; struct super_block *sb; - /* - * Write only inodes dirtied before this time. Don't forget to set - * older_than_this_is_set when you set this. - */ - unsigned long older_than_this; + unsigned long *older_than_this; enum writeback_sync_modes sync_mode; unsigned int tagged_writepages:1; unsigned int for_kupdate:1; unsigned int range_cyclic:1; unsigned int for_background:1; unsigned int for_sync:1; /* sync(2) WB_SYNC_ALL writeback */ - unsigned int older_than_this_is_set:1; enum wb_reason reason; /* why was writeback initiated? */ struct list_head list; /* pending work list */ @@ -252,10 +247,10 @@ static int move_expired_inodes(struct list_head *delaying_queue, int do_sb_sort = 0; int moved = 0; - WARN_ON_ONCE(!work->older_than_this_is_set); while (!list_empty(delaying_queue)) { inode = wb_inode(delaying_queue->prev); - if (inode_dirtied_after(inode, work->older_than_this)) + if (work->older_than_this && + inode_dirtied_after(inode, *work->older_than_this)) break; list_move(&inode->i_wb_list, &tmp); moved++; @@ -742,8 +737,6 @@ static long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages, .sync_mode = WB_SYNC_NONE, .range_cyclic = 1, .reason = reason, - .older_than_this = jiffies, - .older_than_this_is_set = 1, }; spin_lock(&wb->list_lock); @@ -802,13 +795,12 @@ static long wb_writeback(struct bdi_writeback *wb, { unsigned long wb_start = jiffies; long nr_pages = work->nr_pages; + unsigned long oldest_jif; struct inode *inode; long progress; - if (!work->older_than_this_is_set) { - work->older_than_this = jiffies; - work->older_than_this_is_set = 1; - } + oldest_jif = jiffies; + work->older_than_this = &oldest_jif; spin_lock(&wb->list_lock); for (;;) { @@ -842,10 +834,10 @@ static long wb_writeback(struct bdi_writeback *wb, * safe. */ if (work->for_kupdate) { - work->older_than_this = jiffies - + oldest_jif = jiffies - msecs_to_jiffies(dirty_expire_interval * 10); } else if (work->for_background) - work->older_than_this = jiffies; + oldest_jif = jiffies; trace_writeback_start(wb->bdi, work); if (list_empty(&wb->b_io)) @@ -1357,21 +1349,18 @@ EXPORT_SYMBOL(try_to_writeback_inodes_sb); /** * sync_inodes_sb - sync sb inode pages - * @sb: the superblock - * @older_than_this: timestamp + * @sb: the superblock * * This function writes and waits on any dirty inode belonging to this - * superblock that has been dirtied before given timestamp. + * super_block. */ -void sync_inodes_sb(struct super_block *sb, unsigned long older_than_this) +void sync_inodes_sb(struct super_block *sb) { DECLARE_COMPLETION_ONSTACK(done); struct wb_writeback_work work = { .sb = sb, .sync_mode = WB_SYNC_ALL, .nr_pages = LONG_MAX, - .older_than_this = older_than_this, - .older_than_this_is_set = 1, .range_cyclic = 0, .done = &done, .reason = WB_REASON_SYNC, diff --git a/fs/fscache/object-list.c b/fs/fscache/object-list.c index e1959efad64f..b5ebc2d7d80d 100644 --- a/fs/fscache/object-list.c +++ b/fs/fscache/object-list.c @@ -50,6 +50,8 @@ void fscache_objlist_add(struct fscache_object *obj) struct fscache_object *xobj; struct rb_node **p = &fscache_object_list.rb_node, *parent = NULL; + ASSERT(RB_EMPTY_NODE(&obj->objlist_link)); + write_lock(&fscache_object_list_lock); while (*p) { @@ -75,6 +77,9 @@ void fscache_objlist_add(struct fscache_object *obj) */ void fscache_objlist_remove(struct fscache_object *obj) { + if (RB_EMPTY_NODE(&obj->objlist_link)) + return; + write_lock(&fscache_object_list_lock); BUG_ON(RB_EMPTY_ROOT(&fscache_object_list)); diff --git a/fs/fscache/object.c b/fs/fscache/object.c index 53d35c504240..d3b4539f1651 100644 --- a/fs/fscache/object.c +++ b/fs/fscache/object.c @@ -314,6 +314,9 @@ void fscache_object_init(struct fscache_object *object, object->cache = cache; object->cookie = cookie; object->parent = NULL; +#ifdef CONFIG_FSCACHE_OBJECT_LIST + RB_CLEAR_NODE(&object->objlist_link); +#endif object->oob_event_mask = 0; for (t = object->oob_table; t->events; t++) diff --git a/fs/hfsplus/options.c b/fs/hfsplus/options.c index 968eab5bc1f5..68537e8b7a09 100644 --- a/fs/hfsplus/options.c +++ b/fs/hfsplus/options.c @@ -75,7 +75,7 @@ int hfsplus_parse_options_remount(char *input, int *force) int token; if (!input) - return 0; + return 1; while ((p = strsep(&input, ",")) != NULL) { if (!*p) diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 8360674c85bc..60bb365f54a5 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -514,11 +514,13 @@ int jbd2_journal_start_reserved(handle_t *handle, unsigned int type, * similarly constrained call sites */ ret = start_this_handle(journal, handle, GFP_NOFS); - if (ret < 0) + if (ret < 0) { jbd2_journal_free_reserved(handle); + return ret; + } handle->h_type = type; handle->h_line_no = line_no; - return ret; + return 0; } EXPORT_SYMBOL(jbd2_journal_start_reserved); diff --git a/fs/jfs/acl.c b/fs/jfs/acl.c index e973b85d6afd..5a8ea16eedbc 100644 --- a/fs/jfs/acl.c +++ b/fs/jfs/acl.c @@ -86,6 +86,8 @@ static int __jfs_set_acl(tid_t tid, struct inode *inode, int type, rc = posix_acl_equiv_mode(acl, &inode->i_mode); if (rc < 0) return rc; + inode->i_ctime = CURRENT_TIME; + mark_inode_dirty(inode); if (rc == 0) acl = NULL; break; diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c index 0d6ce895a9ee..0f4152defe7b 100644 --- a/fs/kernfs/mount.c +++ b/fs/kernfs/mount.c @@ -94,6 +94,7 @@ const void *kernfs_super_ns(struct super_block *sb) * @fs_type: file_system_type of the fs being mounted * @flags: mount flags specified for the mount * @root: kernfs_root of the hierarchy being mounted + * @new_sb_created: tell the caller if we allocated a new superblock * @ns: optional namespace tag of the mount * * This is to be called from each kernfs user's file_system_type->mount() @@ -104,7 +105,8 @@ const void *kernfs_super_ns(struct super_block *sb) * The return value can be passed to the vfs layer verbatim. */ struct dentry *kernfs_mount_ns(struct file_system_type *fs_type, int flags, - struct kernfs_root *root, const void *ns) + struct kernfs_root *root, bool *new_sb_created, + const void *ns) { struct super_block *sb; struct kernfs_super_info *info; @@ -122,6 +124,10 @@ struct dentry *kernfs_mount_ns(struct file_system_type *fs_type, int flags, kfree(info); if (IS_ERR(sb)) return ERR_CAST(sb); + + if (new_sb_created) + *new_sb_created = !sb->s_root; + if (!sb->s_root) { error = kernfs_fill_super(sb); if (error) { diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c index e066a3902973..ab798a88ec1d 100644 --- a/fs/lockd/svclock.c +++ b/fs/lockd/svclock.c @@ -779,6 +779,7 @@ nlmsvc_grant_blocked(struct nlm_block *block) struct nlm_file *file = block->b_file; struct nlm_lock *lock = &block->b_call->a_args.lock; int error; + loff_t fl_start, fl_end; dprintk("lockd: grant blocked lock %p\n", block); @@ -796,9 +797,16 @@ nlmsvc_grant_blocked(struct nlm_block *block) } /* Try the lock operation again */ + /* vfs_lock_file() can mangle fl_start and fl_end, but we need + * them unchanged for the GRANT_MSG + */ lock->fl.fl_flags |= FL_SLEEP; + fl_start = lock->fl.fl_start; + fl_end = lock->fl.fl_end; error = vfs_lock_file(file->f_file, F_SETLK, &lock->fl, NULL); lock->fl.fl_flags &= ~FL_SLEEP; + lock->fl.fl_start = fl_start; + lock->fl.fl_end = fl_end; switch (error) { case 0: diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index be38b573495a..4a48fe4b84b6 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -1846,6 +1846,11 @@ int nfs_symlink(struct inode *dir, struct dentry *dentry, const char *symname) GFP_KERNEL)) { SetPageUptodate(page); unlock_page(page); + /* + * add_to_page_cache_lru() grabs an extra page refcount. + * Drop it here to avoid leaking this page later. + */ + page_cache_release(page); } else __free_page(page); diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 28a0a3cbd3b7..360114ae8b82 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -164,17 +164,16 @@ static void nfs_zap_caches_locked(struct inode *inode) if (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)) { nfs_fscache_invalidate(inode); nfsi->cache_validity |= NFS_INO_INVALID_ATTR - | NFS_INO_INVALID_LABEL | NFS_INO_INVALID_DATA | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL | NFS_INO_REVAL_PAGECACHE; } else nfsi->cache_validity |= NFS_INO_INVALID_ATTR - | NFS_INO_INVALID_LABEL | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL | NFS_INO_REVAL_PAGECACHE; + nfs_zap_label_cache_locked(nfsi); } void nfs_zap_caches(struct inode *inode) @@ -266,6 +265,13 @@ nfs_init_locked(struct inode *inode, void *opaque) } #ifdef CONFIG_NFS_V4_SECURITY_LABEL +static void nfs_clear_label_invalid(struct inode *inode) +{ + spin_lock(&inode->i_lock); + NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_LABEL; + spin_unlock(&inode->i_lock); +} + void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr, struct nfs4_label *label) { @@ -283,6 +289,7 @@ void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr, __func__, (char *)label->label, label->len, error); + nfs_clear_label_invalid(inode); } } @@ -1648,7 +1655,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) inode->i_blocks = fattr->du.nfs2.blocks; /* Update attrtimeo value if we're out of the unstable period */ - if (invalid & (NFS_INO_INVALID_ATTR|NFS_INO_INVALID_LABEL)) { + if (invalid & NFS_INO_INVALID_ATTR) { nfs_inc_stats(inode, NFSIOS_ATTRINVALIDATE); nfsi->attrtimeo = NFS_MINATTRTIMEO(inode); nfsi->attrtimeo_timestamp = now; @@ -1661,7 +1668,6 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) } } invalid &= ~NFS_INO_INVALID_ATTR; - invalid &= ~NFS_INO_INVALID_LABEL; /* Don't invalidate the data if we were to blame */ if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))) diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 8b5cc04a8611..b46cf5a67329 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -176,7 +176,8 @@ extern struct nfs_server *nfs4_create_server( extern struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *, struct nfs_fh *); extern int nfs4_update_server(struct nfs_server *server, const char *hostname, - struct sockaddr *sap, size_t salen); + struct sockaddr *sap, size_t salen, + struct net *net); extern void nfs_free_server(struct nfs_server *server); extern struct nfs_server *nfs_clone_server(struct nfs_server *, struct nfs_fh *, @@ -279,9 +280,18 @@ static inline void nfs4_label_free(struct nfs4_label *label) } return; } + +static inline void nfs_zap_label_cache_locked(struct nfs_inode *nfsi) +{ + if (nfs_server_capable(&nfsi->vfs_inode, NFS_CAP_SECURITY_LABEL)) + nfsi->cache_validity |= NFS_INO_INVALID_LABEL; +} #else static inline struct nfs4_label *nfs4_label_alloc(struct nfs_server *server, gfp_t flags) { return NULL; } static inline void nfs4_label_free(void *label) {} +static inline void nfs_zap_label_cache_locked(struct nfs_inode *nfsi) +{ +} #endif /* CONFIG_NFS_V4_SECURITY_LABEL */ /* proc.c */ diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index aa9bc973f36a..a462ef0fb5d6 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -18,6 +18,7 @@ #include <linux/lockd/bind.h> #include <linux/nfs_mount.h> #include <linux/freezer.h> +#include <linux/xattr.h> #include "iostat.h" #include "internal.h" diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index 860ad26a5590..0e46d3d1b6cc 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -1135,6 +1135,7 @@ static int nfs_probe_destination(struct nfs_server *server) * @hostname: new end-point's hostname * @sap: new end-point's socket address * @salen: size of "sap" + * @net: net namespace * * The nfs_server must be quiescent before this function is invoked. * Either its session is drained (NFSv4.1+), or its transport is @@ -1143,13 +1144,13 @@ static int nfs_probe_destination(struct nfs_server *server) * Returns zero on success, or a negative errno value. */ int nfs4_update_server(struct nfs_server *server, const char *hostname, - struct sockaddr *sap, size_t salen) + struct sockaddr *sap, size_t salen, struct net *net) { struct nfs_client *clp = server->nfs_client; struct rpc_clnt *clnt = server->client; struct xprt_create xargs = { .ident = clp->cl_proto, - .net = &init_net, + .net = net, .dstaddr = sap, .addrlen = salen, .servername = hostname, @@ -1189,7 +1190,7 @@ int nfs4_update_server(struct nfs_server *server, const char *hostname, error = nfs4_set_client(server, hostname, sap, salen, buf, clp->cl_rpcclient->cl_auth->au_flavor, clp->cl_proto, clnt->cl_timeout, - clp->cl_minorversion, clp->cl_net); + clp->cl_minorversion, net); nfs_put_client(clp); if (error != 0) { nfs_server_insert_lists(server); diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c index 4e7f05d3e9db..3d5dbf80d46a 100644 --- a/fs/nfs/nfs4namespace.c +++ b/fs/nfs/nfs4namespace.c @@ -121,9 +121,8 @@ static int nfs4_validate_fspath(struct dentry *dentry, } static size_t nfs_parse_server_name(char *string, size_t len, - struct sockaddr *sa, size_t salen, struct nfs_server *server) + struct sockaddr *sa, size_t salen, struct net *net) { - struct net *net = rpc_net_ns(server->client); ssize_t ret; ret = rpc_pton(net, string, len, sa, salen); @@ -223,6 +222,7 @@ static struct vfsmount *try_location(struct nfs_clone_mount *mountdata, const struct nfs4_fs_location *location) { const size_t addr_bufsize = sizeof(struct sockaddr_storage); + struct net *net = rpc_net_ns(NFS_SB(mountdata->sb)->client); struct vfsmount *mnt = ERR_PTR(-ENOENT); char *mnt_path; unsigned int maxbuflen; @@ -248,8 +248,7 @@ static struct vfsmount *try_location(struct nfs_clone_mount *mountdata, continue; mountdata->addrlen = nfs_parse_server_name(buf->data, buf->len, - mountdata->addr, addr_bufsize, - NFS_SB(mountdata->sb)); + mountdata->addr, addr_bufsize, net); if (mountdata->addrlen == 0) continue; @@ -419,6 +418,7 @@ static int nfs4_try_replacing_one_location(struct nfs_server *server, const struct nfs4_fs_location *location) { const size_t addr_bufsize = sizeof(struct sockaddr_storage); + struct net *net = rpc_net_ns(server->client); struct sockaddr *sap; unsigned int s; size_t salen; @@ -440,7 +440,7 @@ static int nfs4_try_replacing_one_location(struct nfs_server *server, continue; salen = nfs_parse_server_name(buf->data, buf->len, - sap, addr_bufsize, server); + sap, addr_bufsize, net); if (salen == 0) continue; rpc_set_port(sap, NFS_PORT); @@ -450,7 +450,7 @@ static int nfs4_try_replacing_one_location(struct nfs_server *server, if (hostname == NULL) break; - error = nfs4_update_server(server, hostname, sap, salen); + error = nfs4_update_server(server, hostname, sap, salen, net); kfree(hostname); if (error == 0) break; diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index e5be72518bd7..e1a47217c05e 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1015,8 +1015,11 @@ int nfs4_select_rw_stateid(nfs4_stateid *dst, struct nfs4_state *state, if (ret == -EIO) /* A lost lock - don't even consider delegations */ goto out; - if (nfs4_copy_delegation_stateid(dst, state->inode, fmode)) + /* returns true if delegation stateid found and copied */ + if (nfs4_copy_delegation_stateid(dst, state->inode, fmode)) { + ret = 0; goto out; + } if (ret != -ENOENT) /* nfs4_copy_delegation_stateid() didn't over-write * dst, so it still has the lock stateid which we now diff --git a/fs/nfsd/nfs4acl.c b/fs/nfsd/nfs4acl.c index d3a587144222..d190e33d0ec2 100644 --- a/fs/nfsd/nfs4acl.c +++ b/fs/nfsd/nfs4acl.c @@ -151,17 +151,15 @@ nfsd4_get_nfs4_acl(struct svc_rqst *rqstp, struct dentry *dentry, pacl = posix_acl_from_mode(inode->i_mode, GFP_KERNEL); if (IS_ERR(pacl)) return PTR_ERR(pacl); - /* allocate for worst case: one (deny, allow) pair each: */ - size += 2 * pacl->a_count; } + /* allocate for worst case: one (deny, allow) pair each: */ + size += 2 * pacl->a_count; if (S_ISDIR(inode->i_mode)) { flags = NFS4_ACL_DIR; dpacl = get_acl(inode, ACL_TYPE_DEFAULT); if (dpacl) size += 2 * dpacl->a_count; - } else { - dpacl = NULL; } *acl = nfs4_acl_new(size); @@ -170,8 +168,7 @@ nfsd4_get_nfs4_acl(struct svc_rqst *rqstp, struct dentry *dentry, goto out; } - if (pacl) - _posix_to_nfsv4_one(pacl, *acl, flags & ~NFS4_ACL_TYPE_DEFAULT); + _posix_to_nfsv4_one(pacl, *acl, flags & ~NFS4_ACL_TYPE_DEFAULT); if (dpacl) _posix_to_nfsv4_one(dpacl, *acl, flags | NFS4_ACL_TYPE_DEFAULT); diff --git a/fs/notify/dnotify/dnotify.c b/fs/notify/dnotify/dnotify.c index 0b9ff4395e6a..abc8cbcfe90e 100644 --- a/fs/notify/dnotify/dnotify.c +++ b/fs/notify/dnotify/dnotify.c @@ -86,7 +86,7 @@ static int dnotify_handle_event(struct fsnotify_group *group, struct fsnotify_mark *inode_mark, struct fsnotify_mark *vfsmount_mark, u32 mask, void *data, int data_type, - const unsigned char *file_name) + const unsigned char *file_name, u32 cookie) { struct dnotify_mark *dn_mark; struct dnotify_struct *dn; diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index 0e792f5e3147..dc638f786d5c 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -147,7 +147,7 @@ static int fanotify_handle_event(struct fsnotify_group *group, struct fsnotify_mark *inode_mark, struct fsnotify_mark *fanotify_mark, u32 mask, void *data, int data_type, - const unsigned char *file_name) + const unsigned char *file_name, u32 cookie) { int ret = 0; struct fanotify_event_info *event; @@ -192,10 +192,12 @@ static int fanotify_handle_event(struct fsnotify_group *group, ret = fsnotify_add_notify_event(group, fsn_event, fanotify_merge); if (ret) { - BUG_ON(mask & FAN_ALL_PERM_EVENTS); + /* Permission events shouldn't be merged */ + BUG_ON(ret == 1 && mask & FAN_ALL_PERM_EVENTS); /* Our event wasn't used in the end. Free it. */ fsnotify_destroy_event(group, fsn_event); - ret = 0; + + return 0; } #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index b6175fa11bf8..287a22c04149 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -698,6 +698,7 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) struct fsnotify_group *group; int f_flags, fd; struct user_struct *user; + struct fanotify_event_info *oevent; pr_debug("%s: flags=%d event_f_flags=%d\n", __func__, flags, event_f_flags); @@ -730,8 +731,20 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) group->fanotify_data.user = user; atomic_inc(&user->fanotify_listeners); + oevent = kmem_cache_alloc(fanotify_event_cachep, GFP_KERNEL); + if (unlikely(!oevent)) { + fd = -ENOMEM; + goto out_destroy_group; + } + group->overflow_event = &oevent->fse; + fsnotify_init_event(group->overflow_event, NULL, FS_Q_OVERFLOW); + oevent->tgid = get_pid(task_tgid(current)); + oevent->path.mnt = NULL; + oevent->path.dentry = NULL; + group->fanotify_data.f_flags = event_f_flags; #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS + oevent->response = 0; mutex_init(&group->fanotify_data.access_mutex); init_waitqueue_head(&group->fanotify_data.access_waitq); INIT_LIST_HEAD(&group->fanotify_data.access_list); diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c index 1d4e1ea2f37c..9d3e9c50066a 100644 --- a/fs/notify/fsnotify.c +++ b/fs/notify/fsnotify.c @@ -179,7 +179,7 @@ static int send_to_group(struct inode *to_tell, return group->ops->handle_event(group, to_tell, inode_mark, vfsmount_mark, mask, data, data_is, - file_name); + file_name, cookie); } /* diff --git a/fs/notify/group.c b/fs/notify/group.c index ee674fe2cec7..ad1995980456 100644 --- a/fs/notify/group.c +++ b/fs/notify/group.c @@ -55,6 +55,13 @@ void fsnotify_destroy_group(struct fsnotify_group *group) /* clear the notification queue of all events */ fsnotify_flush_notify(group); + /* + * Destroy overflow event (we cannot use fsnotify_destroy_event() as + * that deliberately ignores overflow events. + */ + if (group->overflow_event) + group->ops->free_event(group->overflow_event); + fsnotify_put_group(group); } @@ -99,7 +106,6 @@ struct fsnotify_group *fsnotify_alloc_group(const struct fsnotify_ops *ops) INIT_LIST_HEAD(&group->marks_list); group->ops = ops; - fsnotify_init_event(&group->overflow_event, NULL, FS_Q_OVERFLOW); return group; } diff --git a/fs/notify/inotify/inotify.h b/fs/notify/inotify/inotify.h index 485eef3f4407..ed855ef6f077 100644 --- a/fs/notify/inotify/inotify.h +++ b/fs/notify/inotify/inotify.h @@ -27,6 +27,6 @@ extern int inotify_handle_event(struct fsnotify_group *group, struct fsnotify_mark *inode_mark, struct fsnotify_mark *vfsmount_mark, u32 mask, void *data, int data_type, - const unsigned char *file_name); + const unsigned char *file_name, u32 cookie); extern const struct fsnotify_ops inotify_fsnotify_ops; diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c index d5ee56348bb8..43ab1e1a07a2 100644 --- a/fs/notify/inotify/inotify_fsnotify.c +++ b/fs/notify/inotify/inotify_fsnotify.c @@ -67,7 +67,7 @@ int inotify_handle_event(struct fsnotify_group *group, struct fsnotify_mark *inode_mark, struct fsnotify_mark *vfsmount_mark, u32 mask, void *data, int data_type, - const unsigned char *file_name) + const unsigned char *file_name, u32 cookie) { struct inotify_inode_mark *i_mark; struct inotify_event_info *event; @@ -103,6 +103,7 @@ int inotify_handle_event(struct fsnotify_group *group, fsn_event = &event->fse; fsnotify_init_event(fsn_event, inode, mask); event->wd = i_mark->wd; + event->sync_cookie = cookie; event->name_len = len; if (len) strcpy(event->name, file_name); diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c index 497395c8274b..78a2ca3966c3 100644 --- a/fs/notify/inotify/inotify_user.c +++ b/fs/notify/inotify/inotify_user.c @@ -495,7 +495,7 @@ void inotify_ignored_and_remove_idr(struct fsnotify_mark *fsn_mark, /* Queue ignore event for the watch */ inotify_handle_event(group, NULL, fsn_mark, NULL, FS_IN_IGNORED, - NULL, FSNOTIFY_EVENT_NONE, NULL); + NULL, FSNOTIFY_EVENT_NONE, NULL, 0); i_mark = container_of(fsn_mark, struct inotify_inode_mark, fsn_mark); /* remove this mark from the idr */ @@ -633,11 +633,23 @@ static int inotify_update_watch(struct fsnotify_group *group, struct inode *inod static struct fsnotify_group *inotify_new_group(unsigned int max_events) { struct fsnotify_group *group; + struct inotify_event_info *oevent; group = fsnotify_alloc_group(&inotify_fsnotify_ops); if (IS_ERR(group)) return group; + oevent = kmalloc(sizeof(struct inotify_event_info), GFP_KERNEL); + if (unlikely(!oevent)) { + fsnotify_destroy_group(group); + return ERR_PTR(-ENOMEM); + } + group->overflow_event = &oevent->fse; + fsnotify_init_event(group->overflow_event, NULL, FS_Q_OVERFLOW); + oevent->wd = -1; + oevent->sync_cookie = 0; + oevent->name_len = 0; + group->max_events = max_events; spin_lock_init(&group->inotify_data.idr_lock); diff --git a/fs/notify/notification.c b/fs/notify/notification.c index 18b3c4427dca..1e58402171a5 100644 --- a/fs/notify/notification.c +++ b/fs/notify/notification.c @@ -80,7 +80,8 @@ void fsnotify_destroy_event(struct fsnotify_group *group, /* * Add an event to the group notification queue. The group can later pull this * event off the queue to deal with. The function returns 0 if the event was - * added to the queue, 1 if the event was merged with some other queued event. + * added to the queue, 1 if the event was merged with some other queued event, + * 2 if the queue of events has overflown. */ int fsnotify_add_notify_event(struct fsnotify_group *group, struct fsnotify_event *event, @@ -95,10 +96,14 @@ int fsnotify_add_notify_event(struct fsnotify_group *group, mutex_lock(&group->notification_mutex); if (group->q_len >= group->max_events) { + ret = 2; /* Queue overflow event only if it isn't already queued */ - if (list_empty(&group->overflow_event.list)) - event = &group->overflow_event; - ret = 1; + if (!list_empty(&group->overflow_event->list)) { + mutex_unlock(&group->notification_mutex); + return ret; + } + event = group->overflow_event; + goto queue; } if (!list_empty(list) && merge) { @@ -109,6 +114,7 @@ int fsnotify_add_notify_event(struct fsnotify_group *group, } } +queue: group->q_len++; list_add_tail(&event->list, list); mutex_unlock(&group->notification_mutex); @@ -132,7 +138,11 @@ struct fsnotify_event *fsnotify_remove_notify_event(struct fsnotify_group *group event = list_first_entry(&group->notification_list, struct fsnotify_event, list); - list_del(&event->list); + /* + * We need to init list head for the case of overflow event so that + * check in fsnotify_add_notify_events() works + */ + list_del_init(&event->list); group->q_len--; return event; diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c index aada5801567a..e2edff38be52 100644 --- a/fs/ocfs2/alloc.c +++ b/fs/ocfs2/alloc.c @@ -7158,7 +7158,7 @@ int ocfs2_truncate_inline(struct inode *inode, struct buffer_head *di_bh, if (end > i_size_read(inode)) end = i_size_read(inode); - BUG_ON(start >= end); + BUG_ON(start > end); if (!(OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) || !(le16_to_cpu(di->i_dyn_features) & OCFS2_INLINE_DATA_FL) || diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index d77d71ead8d1..8450262bcf2a 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -185,6 +185,9 @@ static int ocfs2_sync_file(struct file *file, loff_t start, loff_t end, file->f_path.dentry->d_name.name, (unsigned long long)datasync); + if (ocfs2_is_hard_readonly(osb) || ocfs2_is_soft_readonly(osb)) + return -EROFS; + err = filemap_write_and_wait_range(inode->i_mapping, start, end); if (err) return err; @@ -474,11 +477,6 @@ static int ocfs2_truncate_file(struct inode *inode, goto bail; } - /* lets handle the simple truncate cases before doing any more - * cluster locking. */ - if (new_i_size == le64_to_cpu(fe->i_size)) - goto bail; - down_write(&OCFS2_I(inode)->ip_alloc_sem); ocfs2_resv_discard(&osb->osb_la_resmap, @@ -718,7 +716,8 @@ leave: * While a write will already be ordering the data, a truncate will not. * Thus, we need to explicitly order the zeroed pages. */ -static handle_t *ocfs2_zero_start_ordered_transaction(struct inode *inode) +static handle_t *ocfs2_zero_start_ordered_transaction(struct inode *inode, + struct buffer_head *di_bh) { struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); handle_t *handle = NULL; @@ -735,7 +734,14 @@ static handle_t *ocfs2_zero_start_ordered_transaction(struct inode *inode) } ret = ocfs2_jbd2_file_inode(handle, inode); - if (ret < 0) + if (ret < 0) { + mlog_errno(ret); + goto out; + } + + ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), di_bh, + OCFS2_JOURNAL_ACCESS_WRITE); + if (ret) mlog_errno(ret); out: @@ -751,7 +757,7 @@ out: * to be too fragile to do exactly what we need without us having to * worry about recursive locking in ->write_begin() and ->write_end(). */ static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from, - u64 abs_to) + u64 abs_to, struct buffer_head *di_bh) { struct address_space *mapping = inode->i_mapping; struct page *page; @@ -759,6 +765,7 @@ static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from, handle_t *handle = NULL; int ret = 0; unsigned zero_from, zero_to, block_start, block_end; + struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data; BUG_ON(abs_from >= abs_to); BUG_ON(abs_to > (((u64)index + 1) << PAGE_CACHE_SHIFT)); @@ -801,7 +808,8 @@ static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from, } if (!handle) { - handle = ocfs2_zero_start_ordered_transaction(inode); + handle = ocfs2_zero_start_ordered_transaction(inode, + di_bh); if (IS_ERR(handle)) { ret = PTR_ERR(handle); handle = NULL; @@ -818,8 +826,22 @@ static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from, ret = 0; } - if (handle) + if (handle) { + /* + * fs-writeback will release the dirty pages without page lock + * whose offset are over inode size, the release happens at + * block_write_full_page_endio(). + */ + i_size_write(inode, abs_to); + inode->i_blocks = ocfs2_inode_sector_count(inode); + di->i_size = cpu_to_le64((u64)i_size_read(inode)); + inode->i_mtime = inode->i_ctime = CURRENT_TIME; + di->i_mtime = di->i_ctime = cpu_to_le64(inode->i_mtime.tv_sec); + di->i_ctime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec); + di->i_mtime_nsec = di->i_ctime_nsec; + ocfs2_journal_dirty(handle, di_bh); ocfs2_commit_trans(OCFS2_SB(inode->i_sb), handle); + } out_unlock: unlock_page(page); @@ -915,7 +937,7 @@ out: * has made sure that the entire range needs zeroing. */ static int ocfs2_zero_extend_range(struct inode *inode, u64 range_start, - u64 range_end) + u64 range_end, struct buffer_head *di_bh) { int rc = 0; u64 next_pos; @@ -931,7 +953,7 @@ static int ocfs2_zero_extend_range(struct inode *inode, u64 range_start, next_pos = (zero_pos & PAGE_CACHE_MASK) + PAGE_CACHE_SIZE; if (next_pos > range_end) next_pos = range_end; - rc = ocfs2_write_zero_page(inode, zero_pos, next_pos); + rc = ocfs2_write_zero_page(inode, zero_pos, next_pos, di_bh); if (rc < 0) { mlog_errno(rc); break; @@ -977,7 +999,7 @@ int ocfs2_zero_extend(struct inode *inode, struct buffer_head *di_bh, range_end = zero_to_size; ret = ocfs2_zero_extend_range(inode, range_start, - range_end); + range_end, di_bh); if (ret) { mlog_errno(ret); break; @@ -1145,14 +1167,14 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr) goto bail_unlock_rw; } - if (size_change && attr->ia_size != i_size_read(inode)) { + if (size_change) { status = inode_newsize_ok(inode, attr->ia_size); if (status) goto bail_unlock; inode_dio_wait(inode); - if (i_size_read(inode) > attr->ia_size) { + if (i_size_read(inode) >= attr->ia_size) { if (ocfs2_should_order_data(inode)) { status = ocfs2_begin_ordered_truncate(inode, attr->ia_size); diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index f4d609be9400..3683643f3f0e 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -664,6 +664,7 @@ static int ocfs2_link(struct dentry *old_dentry, struct ocfs2_super *osb = OCFS2_SB(dir->i_sb); struct ocfs2_dir_lookup_result lookup = { NULL, }; sigset_t oldset; + u64 old_de_ino; trace_ocfs2_link((unsigned long long)OCFS2_I(inode)->ip_blkno, old_dentry->d_name.len, old_dentry->d_name.name, @@ -686,6 +687,22 @@ static int ocfs2_link(struct dentry *old_dentry, goto out; } + err = ocfs2_lookup_ino_from_name(dir, old_dentry->d_name.name, + old_dentry->d_name.len, &old_de_ino); + if (err) { + err = -ENOENT; + goto out; + } + + /* + * Check whether another node removed the source inode while we + * were in the vfs. + */ + if (old_de_ino != OCFS2_I(inode)->ip_blkno) { + err = -ENOENT; + goto out; + } + err = ocfs2_check_dir_for_entry(dir, dentry->d_name.name, dentry->d_name.len); if (err) diff --git a/fs/ocfs2/quota_global.c b/fs/ocfs2/quota_global.c index aaa50611ec66..d7b5108789e2 100644 --- a/fs/ocfs2/quota_global.c +++ b/fs/ocfs2/quota_global.c @@ -717,6 +717,12 @@ static int ocfs2_release_dquot(struct dquot *dquot) */ if (status < 0) mlog_errno(status); + /* + * Clear dq_off so that we search for the structure in quota file next + * time we acquire it. The structure might be deleted and reallocated + * elsewhere by another node while our dquot structure is on freelist. + */ + dquot->dq_off = 0; clear_bit(DQ_ACTIVE_B, &dquot->dq_flags); out_trans: ocfs2_commit_trans(osb, handle); @@ -756,16 +762,17 @@ static int ocfs2_acquire_dquot(struct dquot *dquot) status = ocfs2_lock_global_qf(info, 1); if (status < 0) goto out; - if (!test_bit(DQ_READ_B, &dquot->dq_flags)) { - status = ocfs2_qinfo_lock(info, 0); - if (status < 0) - goto out_dq; - status = qtree_read_dquot(&info->dqi_gi, dquot); - ocfs2_qinfo_unlock(info, 0); - if (status < 0) - goto out_dq; - } - set_bit(DQ_READ_B, &dquot->dq_flags); + status = ocfs2_qinfo_lock(info, 0); + if (status < 0) + goto out_dq; + /* + * We always want to read dquot structure from disk because we don't + * know what happened with it while it was on freelist. + */ + status = qtree_read_dquot(&info->dqi_gi, dquot); + ocfs2_qinfo_unlock(info, 0); + if (status < 0) + goto out_dq; OCFS2_DQUOT(dquot)->dq_use_count++; OCFS2_DQUOT(dquot)->dq_origspace = dquot->dq_dqb.dqb_curspace; diff --git a/fs/ocfs2/quota_local.c b/fs/ocfs2/quota_local.c index 2e4344be3b96..2001862bf2b1 100644 --- a/fs/ocfs2/quota_local.c +++ b/fs/ocfs2/quota_local.c @@ -1303,10 +1303,6 @@ int ocfs2_local_release_dquot(handle_t *handle, struct dquot *dquot) ocfs2_journal_dirty(handle, od->dq_chunk->qc_headerbh); out: - /* Clear the read bit so that next time someone uses this - * dquot he reads fresh info from disk and allocates local - * dquot structure */ - clear_bit(DQ_READ_B, &dquot->dq_flags); return status; } diff --git a/fs/proc/page.c b/fs/proc/page.c index 02174a610315..e647c55275d9 100644 --- a/fs/proc/page.c +++ b/fs/proc/page.c @@ -121,9 +121,8 @@ u64 stable_page_flags(struct page *page) * just checks PG_head/PG_tail, so we need to check PageLRU/PageAnon * to make sure a given page is a thp, not a non-huge compound page. */ - else if (PageTransCompound(page) && - (PageLRU(compound_trans_head(page)) || - PageAnon(compound_trans_head(page)))) + else if (PageTransCompound(page) && (PageLRU(compound_head(page)) || + PageAnon(compound_head(page)))) u |= 1 << KPF_THP; /* diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c index 2ca7ba047f04..88d4585b30f1 100644 --- a/fs/proc/vmcore.c +++ b/fs/proc/vmcore.c @@ -468,17 +468,24 @@ static int __init update_note_header_size_elf64(const Elf64_Ehdr *ehdr_ptr) return rc; } nhdr_ptr = notes_section; - while (real_sz < max_sz) { - if (nhdr_ptr->n_namesz == 0) - break; + while (nhdr_ptr->n_namesz != 0) { sz = sizeof(Elf64_Nhdr) + ((nhdr_ptr->n_namesz + 3) & ~3) + ((nhdr_ptr->n_descsz + 3) & ~3); + if ((real_sz + sz) > max_sz) { + pr_warn("Warning: Exceeded p_memsz, dropping PT_NOTE entry n_namesz=0x%x, n_descsz=0x%x\n", + nhdr_ptr->n_namesz, nhdr_ptr->n_descsz); + break; + } real_sz += sz; nhdr_ptr = (Elf64_Nhdr*)((char*)nhdr_ptr + sz); } kfree(notes_section); phdr_ptr->p_memsz = real_sz; + if (real_sz == 0) { + pr_warn("Warning: Zero PT_NOTE entries found\n"); + return -EINVAL; + } } return 0; @@ -648,17 +655,24 @@ static int __init update_note_header_size_elf32(const Elf32_Ehdr *ehdr_ptr) return rc; } nhdr_ptr = notes_section; - while (real_sz < max_sz) { - if (nhdr_ptr->n_namesz == 0) - break; + while (nhdr_ptr->n_namesz != 0) { sz = sizeof(Elf32_Nhdr) + ((nhdr_ptr->n_namesz + 3) & ~3) + ((nhdr_ptr->n_descsz + 3) & ~3); + if ((real_sz + sz) > max_sz) { + pr_warn("Warning: Exceeded p_memsz, dropping PT_NOTE entry n_namesz=0x%x, n_descsz=0x%x\n", + nhdr_ptr->n_namesz, nhdr_ptr->n_descsz); + break; + } real_sz += sz; nhdr_ptr = (Elf32_Nhdr*)((char*)nhdr_ptr + sz); } kfree(notes_section); phdr_ptr->p_memsz = real_sz; + if (real_sz == 0) { + pr_warn("Warning: Zero PT_NOTE entries found\n"); + return -EINVAL; + } } return 0; diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 831d49a4111f..cfc8dcc16043 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -581,9 +581,17 @@ int dquot_scan_active(struct super_block *sb, dqstats_inc(DQST_LOOKUPS); dqput(old_dquot); old_dquot = dquot; - ret = fn(dquot, priv); - if (ret < 0) - goto out; + /* + * ->release_dquot() can be racing with us. Our reference + * protects us from new calls to it so just wait for any + * outstanding call and recheck the DQ_ACTIVE_B after that. + */ + wait_on_dquot(dquot); + if (test_bit(DQ_ACTIVE_B, &dquot->dq_flags)) { + ret = fn(dquot, priv); + if (ret < 0) + goto out; + } spin_lock(&dq_list_lock); /* We are safe to continue now because our dquot could not * be moved out of the inuse list while we hold the reference */ diff --git a/fs/reiserfs/do_balan.c b/fs/reiserfs/do_balan.c index 2b7882b508db..9a3c68cf6026 100644 --- a/fs/reiserfs/do_balan.c +++ b/fs/reiserfs/do_balan.c @@ -324,23 +324,17 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h switch (flag) { case M_INSERT: /* insert item into L[0] */ - if (item_pos == tb->lnum[0] - 1 - && tb->lbytes != -1) { + if (item_pos == tb->lnum[0] - 1 && tb->lbytes != -1) { /* part of new item falls into L[0] */ int new_item_len; int version; - ret_val = - leaf_shift_left(tb, tb->lnum[0] - 1, - -1); + ret_val = leaf_shift_left(tb, tb->lnum[0] - 1, -1); /* Calculate item length to insert to S[0] */ - new_item_len = - ih_item_len(ih) - tb->lbytes; + new_item_len = ih_item_len(ih) - tb->lbytes; /* Calculate and check item length to insert to L[0] */ - put_ih_item_len(ih, - ih_item_len(ih) - - new_item_len); + put_ih_item_len(ih, ih_item_len(ih) - new_item_len); RFALSE(ih_item_len(ih) <= 0, "PAP-12080: there is nothing to insert into L[0]: ih_item_len=%d", @@ -349,30 +343,18 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h /* Insert new item into L[0] */ buffer_info_init_left(tb, &bi); leaf_insert_into_buf(&bi, - n + item_pos - - ret_val, ih, body, - zeros_num > - ih_item_len(ih) ? - ih_item_len(ih) : - zeros_num); + n + item_pos - ret_val, ih, body, + zeros_num > ih_item_len(ih) ? ih_item_len(ih) : zeros_num); version = ih_version(ih); /* Calculate key component, item length and body to insert into S[0] */ - set_le_ih_k_offset(ih, - le_ih_k_offset(ih) + - (tb-> - lbytes << - (is_indirect_le_ih - (ih) ? tb->tb_sb-> - s_blocksize_bits - - UNFM_P_SHIFT : - 0))); + set_le_ih_k_offset(ih, le_ih_k_offset(ih) + + (tb-> lbytes << (is_indirect_le_ih(ih) ? tb->tb_sb-> s_blocksize_bits - UNFM_P_SHIFT : 0))); put_ih_item_len(ih, new_item_len); if (tb->lbytes > zeros_num) { - body += - (tb->lbytes - zeros_num); + body += (tb->lbytes - zeros_num); zeros_num = 0; } else zeros_num -= tb->lbytes; @@ -383,15 +365,10 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h } else { /* new item in whole falls into L[0] */ /* Shift lnum[0]-1 items to L[0] */ - ret_val = - leaf_shift_left(tb, tb->lnum[0] - 1, - tb->lbytes); + ret_val = leaf_shift_left(tb, tb->lnum[0] - 1, tb->lbytes); /* Insert new item into L[0] */ buffer_info_init_left(tb, &bi); - leaf_insert_into_buf(&bi, - n + item_pos - - ret_val, ih, body, - zeros_num); + leaf_insert_into_buf(&bi, n + item_pos - ret_val, ih, body, zeros_num); tb->insert_size[0] = 0; zeros_num = 0; } @@ -399,264 +376,117 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h case M_PASTE: /* append item in L[0] */ - if (item_pos == tb->lnum[0] - 1 - && tb->lbytes != -1) { + if (item_pos == tb->lnum[0] - 1 && tb->lbytes != -1) { /* we must shift the part of the appended item */ - if (is_direntry_le_ih - (B_N_PITEM_HEAD(tbS0, item_pos))) { + if (is_direntry_le_ih(B_N_PITEM_HEAD(tbS0, item_pos))) { RFALSE(zeros_num, "PAP-12090: invalid parameter in case of a directory"); /* directory item */ if (tb->lbytes > pos_in_item) { /* new directory entry falls into L[0] */ - struct item_head - *pasted; - int l_pos_in_item = - pos_in_item; + struct item_head *pasted; + int l_pos_in_item = pos_in_item; /* Shift lnum[0] - 1 items in whole. Shift lbytes - 1 entries from given directory item */ - ret_val = - leaf_shift_left(tb, - tb-> - lnum - [0], - tb-> - lbytes - - - 1); - if (ret_val - && !item_pos) { - pasted = - B_N_PITEM_HEAD - (tb->L[0], - B_NR_ITEMS - (tb-> - L[0]) - - 1); - l_pos_in_item += - I_ENTRY_COUNT - (pasted) - - (tb-> - lbytes - - 1); + ret_val = leaf_shift_left(tb, tb->lnum[0], tb->lbytes-1); + if (ret_val && !item_pos) { + pasted = B_N_PITEM_HEAD(tb->L[0], B_NR_ITEMS(tb->L[0]) - 1); + l_pos_in_item += I_ENTRY_COUNT(pasted) - (tb->lbytes -1); } /* Append given directory entry to directory item */ buffer_info_init_left(tb, &bi); - leaf_paste_in_buffer - (&bi, - n + item_pos - - ret_val, - l_pos_in_item, - tb->insert_size[0], - body, zeros_num); + leaf_paste_in_buffer(&bi, n + item_pos - ret_val, l_pos_in_item, tb->insert_size[0], body, zeros_num); /* previous string prepared space for pasting new entry, following string pastes this entry */ /* when we have merge directory item, pos_in_item has been changed too */ /* paste new directory entry. 1 is entry number */ - leaf_paste_entries(&bi, - n + - item_pos - - - ret_val, - l_pos_in_item, - 1, - (struct - reiserfs_de_head - *) - body, - body - + - DEH_SIZE, - tb-> - insert_size - [0] - ); + leaf_paste_entries(&bi, n + item_pos - ret_val, l_pos_in_item, + 1, (struct reiserfs_de_head *) body, + body + DEH_SIZE, tb->insert_size[0]); tb->insert_size[0] = 0; } else { /* new directory item doesn't fall into L[0] */ /* Shift lnum[0]-1 items in whole. Shift lbytes directory entries from directory item number lnum[0] */ - leaf_shift_left(tb, - tb-> - lnum[0], - tb-> - lbytes); + leaf_shift_left(tb, tb->lnum[0], tb->lbytes); } /* Calculate new position to append in item body */ pos_in_item -= tb->lbytes; } else { /* regular object */ - RFALSE(tb->lbytes <= 0, - "PAP-12095: there is nothing to shift to L[0]. lbytes=%d", - tb->lbytes); - RFALSE(pos_in_item != - ih_item_len - (B_N_PITEM_HEAD - (tbS0, item_pos)), + RFALSE(tb->lbytes <= 0, "PAP-12095: there is nothing to shift to L[0]. lbytes=%d", tb->lbytes); + RFALSE(pos_in_item != ih_item_len(B_N_PITEM_HEAD(tbS0, item_pos)), "PAP-12100: incorrect position to paste: item_len=%d, pos_in_item=%d", - ih_item_len - (B_N_PITEM_HEAD - (tbS0, item_pos)), - pos_in_item); + ih_item_len(B_N_PITEM_HEAD(tbS0, item_pos)),pos_in_item); if (tb->lbytes >= pos_in_item) { /* appended item will be in L[0] in whole */ int l_n; /* this bytes number must be appended to the last item of L[h] */ - l_n = - tb->lbytes - - pos_in_item; + l_n = tb->lbytes - pos_in_item; /* Calculate new insert_size[0] */ - tb->insert_size[0] -= - l_n; + tb->insert_size[0] -= l_n; - RFALSE(tb-> - insert_size[0] <= - 0, + RFALSE(tb->insert_size[0] <= 0, "PAP-12105: there is nothing to paste into L[0]. insert_size=%d", - tb-> - insert_size[0]); - ret_val = - leaf_shift_left(tb, - tb-> - lnum - [0], - ih_item_len - (B_N_PITEM_HEAD - (tbS0, - item_pos))); + tb->insert_size[0]); + ret_val = leaf_shift_left(tb, tb->lnum[0], ih_item_len + (B_N_PITEM_HEAD(tbS0, item_pos))); /* Append to body of item in L[0] */ buffer_info_init_left(tb, &bi); leaf_paste_in_buffer - (&bi, - n + item_pos - - ret_val, - ih_item_len - (B_N_PITEM_HEAD - (tb->L[0], - n + item_pos - - ret_val)), l_n, - body, - zeros_num > - l_n ? l_n : - zeros_num); + (&bi, n + item_pos - ret_val, ih_item_len + (B_N_PITEM_HEAD(tb->L[0], n + item_pos - ret_val)), + l_n, body, + zeros_num > l_n ? l_n : zeros_num); /* 0-th item in S0 can be only of DIRECT type when l_n != 0 */ { int version; - int temp_l = - l_n; - - RFALSE - (ih_item_len - (B_N_PITEM_HEAD - (tbS0, - 0)), + int temp_l = l_n; + + RFALSE(ih_item_len(B_N_PITEM_HEAD(tbS0, 0)), "PAP-12106: item length must be 0"); - RFALSE - (comp_short_le_keys - (B_N_PKEY - (tbS0, 0), - B_N_PKEY - (tb->L[0], - n + - item_pos - - - ret_val)), + RFALSE(comp_short_le_keys(B_N_PKEY(tbS0, 0), B_N_PKEY + (tb->L[0], n + item_pos - ret_val)), "PAP-12107: items must be of the same file"); if (is_indirect_le_ih(B_N_PITEM_HEAD(tb->L[0], n + item_pos - ret_val))) { - temp_l = - l_n - << - (tb-> - tb_sb-> - s_blocksize_bits - - - UNFM_P_SHIFT); + temp_l = l_n << (tb->tb_sb-> s_blocksize_bits - UNFM_P_SHIFT); } /* update key of first item in S0 */ - version = - ih_version - (B_N_PITEM_HEAD - (tbS0, 0)); - set_le_key_k_offset - (version, - B_N_PKEY - (tbS0, 0), - le_key_k_offset - (version, - B_N_PKEY - (tbS0, - 0)) + - temp_l); + version = ih_version(B_N_PITEM_HEAD(tbS0, 0)); + set_le_key_k_offset(version, B_N_PKEY(tbS0, 0), + le_key_k_offset(version,B_N_PKEY(tbS0, 0)) + temp_l); /* update left delimiting key */ - set_le_key_k_offset - (version, - B_N_PDELIM_KEY - (tb-> - CFL[0], - tb-> - lkey[0]), - le_key_k_offset - (version, - B_N_PDELIM_KEY - (tb-> - CFL[0], - tb-> - lkey[0])) - + temp_l); + set_le_key_k_offset(version, B_N_PDELIM_KEY(tb->CFL[0], tb->lkey[0]), + le_key_k_offset(version, B_N_PDELIM_KEY(tb->CFL[0], tb->lkey[0])) + temp_l); } /* Calculate new body, position in item and insert_size[0] */ if (l_n > zeros_num) { - body += - (l_n - - zeros_num); + body += (l_n - zeros_num); zeros_num = 0; } else - zeros_num -= - l_n; + zeros_num -= l_n; pos_in_item = 0; - RFALSE - (comp_short_le_keys - (B_N_PKEY(tbS0, 0), - B_N_PKEY(tb->L[0], - B_NR_ITEMS - (tb-> - L[0]) - - 1)) - || - !op_is_left_mergeable - (B_N_PKEY(tbS0, 0), - tbS0->b_size) - || - !op_is_left_mergeable - (B_N_PDELIM_KEY - (tb->CFL[0], - tb->lkey[0]), - tbS0->b_size), + RFALSE(comp_short_le_keys(B_N_PKEY(tbS0, 0), B_N_PKEY(tb->L[0], B_NR_ITEMS(tb->L[0]) - 1)) + || !op_is_left_mergeable(B_N_PKEY(tbS0, 0), tbS0->b_size) + || !op_is_left_mergeable(B_N_PDELIM_KEY(tb->CFL[0], tb->lkey[0]), tbS0->b_size), "PAP-12120: item must be merge-able with left neighboring item"); } else { /* only part of the appended item will be in L[0] */ /* Calculate position in item for append in S[0] */ - pos_in_item -= - tb->lbytes; + pos_in_item -= tb->lbytes; - RFALSE(pos_in_item <= 0, - "PAP-12125: no place for paste. pos_in_item=%d", - pos_in_item); + RFALSE(pos_in_item <= 0, "PAP-12125: no place for paste. pos_in_item=%d", pos_in_item); /* Shift lnum[0] - 1 items in whole. Shift lbytes - 1 byte from item number lnum[0] */ - leaf_shift_left(tb, - tb-> - lnum[0], - tb-> - lbytes); + leaf_shift_left(tb, tb->lnum[0], tb->lbytes); } } } else { /* appended item will be in L[0] in whole */ @@ -665,52 +495,30 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h if (!item_pos && op_is_left_mergeable(B_N_PKEY(tbS0, 0), tbS0->b_size)) { /* if we paste into first item of S[0] and it is left mergable */ /* then increment pos_in_item by the size of the last item in L[0] */ - pasted = - B_N_PITEM_HEAD(tb->L[0], - n - 1); + pasted = B_N_PITEM_HEAD(tb->L[0], n - 1); if (is_direntry_le_ih(pasted)) - pos_in_item += - ih_entry_count - (pasted); + pos_in_item += ih_entry_count(pasted); else - pos_in_item += - ih_item_len(pasted); + pos_in_item += ih_item_len(pasted); } /* Shift lnum[0] - 1 items in whole. Shift lbytes - 1 byte from item number lnum[0] */ - ret_val = - leaf_shift_left(tb, tb->lnum[0], - tb->lbytes); + ret_val = leaf_shift_left(tb, tb->lnum[0], tb->lbytes); /* Append to body of item in L[0] */ buffer_info_init_left(tb, &bi); - leaf_paste_in_buffer(&bi, - n + item_pos - - ret_val, + leaf_paste_in_buffer(&bi, n + item_pos - ret_val, pos_in_item, tb->insert_size[0], body, zeros_num); /* if appended item is directory, paste entry */ - pasted = - B_N_PITEM_HEAD(tb->L[0], - n + item_pos - - ret_val); + pasted = B_N_PITEM_HEAD(tb->L[0], n + item_pos - ret_val); if (is_direntry_le_ih(pasted)) - leaf_paste_entries(&bi, - n + - item_pos - - ret_val, - pos_in_item, - 1, - (struct - reiserfs_de_head - *)body, - body + - DEH_SIZE, - tb-> - insert_size - [0] - ); + leaf_paste_entries(&bi, n + item_pos - ret_val, + pos_in_item, 1, + (struct reiserfs_de_head *) body, + body + DEH_SIZE, + tb->insert_size[0]); /* if appended item is indirect item, put unformatted node into un list */ if (is_indirect_le_ih(pasted)) set_ih_free_space(pasted, 0); @@ -722,13 +530,7 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h reiserfs_panic(tb->tb_sb, "PAP-12130", "lnum > 0: unexpected mode: " " %s(%d)", - (flag == - M_DELETE) ? "DELETE" : ((flag == - M_CUT) - ? "CUT" - : - "UNKNOWN"), - flag); + (flag == M_DELETE) ? "DELETE" : ((flag == M_CUT) ? "CUT" : "UNKNOWN"), flag); } } else { /* new item doesn't fall into L[0] */ @@ -748,14 +550,12 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h case M_INSERT: /* insert item */ if (n - tb->rnum[0] < item_pos) { /* new item or its part falls to R[0] */ if (item_pos == n - tb->rnum[0] + 1 && tb->rbytes != -1) { /* part of new item falls into R[0] */ - loff_t old_key_comp, old_len, - r_zeros_number; + loff_t old_key_comp, old_len, r_zeros_number; const char *r_body; int version; loff_t offset; - leaf_shift_right(tb, tb->rnum[0] - 1, - -1); + leaf_shift_right(tb, tb->rnum[0] - 1, -1); version = ih_version(ih); /* Remember key component and item length */ @@ -763,29 +563,17 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h old_len = ih_item_len(ih); /* Calculate key component and item length to insert into R[0] */ - offset = - le_ih_k_offset(ih) + - ((old_len - - tb-> - rbytes) << (is_indirect_le_ih(ih) - ? tb->tb_sb-> - s_blocksize_bits - - UNFM_P_SHIFT : 0)); + offset = le_ih_k_offset(ih) + ((old_len - tb->rbytes) << (is_indirect_le_ih(ih) ? tb->tb_sb->s_blocksize_bits - UNFM_P_SHIFT : 0)); set_le_ih_k_offset(ih, offset); put_ih_item_len(ih, tb->rbytes); /* Insert part of the item into R[0] */ buffer_info_init_right(tb, &bi); if ((old_len - tb->rbytes) > zeros_num) { r_zeros_number = 0; - r_body = - body + (old_len - - tb->rbytes) - - zeros_num; + r_body = body + (old_len - tb->rbytes) - zeros_num; } else { r_body = body; - r_zeros_number = - zeros_num - (old_len - - tb->rbytes); + r_zeros_number = zeros_num - (old_len - tb->rbytes); zeros_num -= r_zeros_number; } @@ -798,25 +586,18 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h /* Calculate key component and item length to insert into S[0] */ set_le_ih_k_offset(ih, old_key_comp); - put_ih_item_len(ih, - old_len - tb->rbytes); + put_ih_item_len(ih, old_len - tb->rbytes); tb->insert_size[0] -= tb->rbytes; } else { /* whole new item falls into R[0] */ /* Shift rnum[0]-1 items to R[0] */ - ret_val = - leaf_shift_right(tb, - tb->rnum[0] - 1, - tb->rbytes); + ret_val = leaf_shift_right(tb, tb->rnum[0] - 1, tb->rbytes); /* Insert new item into R[0] */ buffer_info_init_right(tb, &bi); - leaf_insert_into_buf(&bi, - item_pos - n + - tb->rnum[0] - 1, - ih, body, - zeros_num); + leaf_insert_into_buf(&bi, item_pos - n + tb->rnum[0] - 1, + ih, body, zeros_num); if (item_pos - n + tb->rnum[0] - 1 == 0) { replace_key(tb, tb->CFR[0], @@ -841,200 +622,97 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h RFALSE(zeros_num, "PAP-12145: invalid parameter in case of a directory"); - entry_count = - I_ENTRY_COUNT(B_N_PITEM_HEAD - (tbS0, - item_pos)); + entry_count = I_ENTRY_COUNT(B_N_PITEM_HEAD + (tbS0, item_pos)); if (entry_count - tb->rbytes < pos_in_item) /* new directory entry falls into R[0] */ { int paste_entry_position; - RFALSE(tb->rbytes - 1 >= - entry_count - || !tb-> - insert_size[0], + RFALSE(tb->rbytes - 1 >= entry_count || !tb-> insert_size[0], "PAP-12150: no enough of entries to shift to R[0]: rbytes=%d, entry_count=%d", - tb->rbytes, - entry_count); + tb->rbytes, entry_count); /* Shift rnum[0]-1 items in whole. Shift rbytes-1 directory entries from directory item number rnum[0] */ - leaf_shift_right(tb, - tb-> - rnum - [0], - tb-> - rbytes - - 1); + leaf_shift_right(tb, tb->rnum[0], tb->rbytes - 1); /* Paste given directory entry to directory item */ - paste_entry_position = - pos_in_item - - entry_count + - tb->rbytes - 1; + paste_entry_position = pos_in_item - entry_count + tb->rbytes - 1; buffer_info_init_right(tb, &bi); - leaf_paste_in_buffer - (&bi, 0, - paste_entry_position, - tb->insert_size[0], - body, zeros_num); + leaf_paste_in_buffer(&bi, 0, paste_entry_position, tb->insert_size[0], body, zeros_num); /* paste entry */ - leaf_paste_entries(&bi, - 0, - paste_entry_position, - 1, - (struct - reiserfs_de_head - *) - body, - body - + - DEH_SIZE, - tb-> - insert_size - [0] - ); - - if (paste_entry_position - == 0) { + leaf_paste_entries(&bi, 0, paste_entry_position, 1, + (struct reiserfs_de_head *) body, + body + DEH_SIZE, tb->insert_size[0]); + + if (paste_entry_position == 0) { /* change delimiting keys */ - replace_key(tb, - tb-> - CFR - [0], - tb-> - rkey - [0], - tb-> - R - [0], - 0); + replace_key(tb, tb->CFR[0], tb->rkey[0], tb->R[0],0); } tb->insert_size[0] = 0; pos_in_item++; } else { /* new directory entry doesn't fall into R[0] */ - leaf_shift_right(tb, - tb-> - rnum - [0], - tb-> - rbytes); + leaf_shift_right(tb, tb->rnum[0], tb->rbytes); } } else { /* regular object */ - int n_shift, n_rem, - r_zeros_number; + int n_shift, n_rem, r_zeros_number; const char *r_body; /* Calculate number of bytes which must be shifted from appended item */ - if ((n_shift = - tb->rbytes - - tb->insert_size[0]) < 0) + if ((n_shift = tb->rbytes - tb->insert_size[0]) < 0) n_shift = 0; - RFALSE(pos_in_item != - ih_item_len - (B_N_PITEM_HEAD - (tbS0, item_pos)), + RFALSE(pos_in_item != ih_item_len + (B_N_PITEM_HEAD(tbS0, item_pos)), "PAP-12155: invalid position to paste. ih_item_len=%d, pos_in_item=%d", - pos_in_item, - ih_item_len - (B_N_PITEM_HEAD - (tbS0, item_pos))); - - leaf_shift_right(tb, - tb->rnum[0], - n_shift); + pos_in_item, ih_item_len + (B_N_PITEM_HEAD(tbS0, item_pos))); + + leaf_shift_right(tb, tb->rnum[0], n_shift); /* Calculate number of bytes which must remain in body after appending to R[0] */ - if ((n_rem = - tb->insert_size[0] - - tb->rbytes) < 0) + if ((n_rem = tb->insert_size[0] - tb->rbytes) < 0) n_rem = 0; { int version; - unsigned long temp_rem = - n_rem; - - version = - ih_version - (B_N_PITEM_HEAD - (tb->R[0], 0)); - if (is_indirect_le_key - (version, - B_N_PKEY(tb->R[0], - 0))) { - temp_rem = - n_rem << - (tb->tb_sb-> - s_blocksize_bits - - - UNFM_P_SHIFT); + unsigned long temp_rem = n_rem; + + version = ih_version(B_N_PITEM_HEAD(tb->R[0], 0)); + if (is_indirect_le_key(version, B_N_PKEY(tb->R[0], 0))) { + temp_rem = n_rem << (tb->tb_sb->s_blocksize_bits - UNFM_P_SHIFT); } - set_le_key_k_offset - (version, - B_N_PKEY(tb->R[0], - 0), - le_key_k_offset - (version, - B_N_PKEY(tb->R[0], - 0)) + - temp_rem); - set_le_key_k_offset - (version, - B_N_PDELIM_KEY(tb-> - CFR - [0], - tb-> - rkey - [0]), - le_key_k_offset - (version, - B_N_PDELIM_KEY - (tb->CFR[0], - tb->rkey[0])) + - temp_rem); + set_le_key_k_offset(version, B_N_PKEY(tb->R[0], 0), + le_key_k_offset(version, B_N_PKEY(tb->R[0], 0)) + temp_rem); + set_le_key_k_offset(version, B_N_PDELIM_KEY(tb->CFR[0], tb->rkey[0]), + le_key_k_offset(version, B_N_PDELIM_KEY(tb->CFR[0], tb->rkey[0])) + temp_rem); } /* k_offset (B_N_PKEY(tb->R[0],0)) += n_rem; k_offset (B_N_PDELIM_KEY(tb->CFR[0],tb->rkey[0])) += n_rem;*/ - do_balance_mark_internal_dirty - (tb, tb->CFR[0], 0); + do_balance_mark_internal_dirty(tb, tb->CFR[0], 0); /* Append part of body into R[0] */ buffer_info_init_right(tb, &bi); if (n_rem > zeros_num) { r_zeros_number = 0; - r_body = - body + n_rem - - zeros_num; + r_body = body + n_rem - zeros_num; } else { r_body = body; - r_zeros_number = - zeros_num - n_rem; - zeros_num -= - r_zeros_number; + r_zeros_number = zeros_num - n_rem; + zeros_num -= r_zeros_number; } - leaf_paste_in_buffer(&bi, 0, - n_shift, - tb-> - insert_size - [0] - - n_rem, - r_body, - r_zeros_number); - - if (is_indirect_le_ih - (B_N_PITEM_HEAD - (tb->R[0], 0))) { + leaf_paste_in_buffer(&bi, 0, n_shift, + tb->insert_size[0] - n_rem, + r_body, r_zeros_number); + + if (is_indirect_le_ih(B_N_PITEM_HEAD(tb->R[0], 0))) { #if 0 RFALSE(n_rem, "PAP-12160: paste more than one unformatted node pointer"); #endif - set_ih_free_space - (B_N_PITEM_HEAD - (tb->R[0], 0), 0); + set_ih_free_space(B_N_PITEM_HEAD(tb->R[0], 0), 0); } tb->insert_size[0] = n_rem; if (!n_rem) @@ -1044,58 +722,28 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h struct item_head *pasted; - ret_val = - leaf_shift_right(tb, tb->rnum[0], - tb->rbytes); + ret_val = leaf_shift_right(tb, tb->rnum[0], tb->rbytes); /* append item in R[0] */ if (pos_in_item >= 0) { buffer_info_init_right(tb, &bi); - leaf_paste_in_buffer(&bi, - item_pos - - n + - tb-> - rnum[0], - pos_in_item, - tb-> - insert_size - [0], body, - zeros_num); + leaf_paste_in_buffer(&bi, item_pos - n + tb->rnum[0], pos_in_item, + tb->insert_size[0], body, zeros_num); } /* paste new entry, if item is directory item */ - pasted = - B_N_PITEM_HEAD(tb->R[0], - item_pos - n + - tb->rnum[0]); - if (is_direntry_le_ih(pasted) - && pos_in_item >= 0) { - leaf_paste_entries(&bi, - item_pos - - n + - tb->rnum[0], - pos_in_item, - 1, - (struct - reiserfs_de_head - *)body, - body + - DEH_SIZE, - tb-> - insert_size - [0] - ); + pasted = B_N_PITEM_HEAD(tb->R[0], item_pos - n + tb->rnum[0]); + if (is_direntry_le_ih(pasted) && pos_in_item >= 0) { + leaf_paste_entries(&bi, item_pos - n + tb->rnum[0], + pos_in_item, 1, + (struct reiserfs_de_head *) body, + body + DEH_SIZE, tb->insert_size[0]); if (!pos_in_item) { - RFALSE(item_pos - n + - tb->rnum[0], + RFALSE(item_pos - n + tb->rnum[0], "PAP-12165: directory item must be first item of node when pasting is in 0th position"); /* update delimiting keys */ - replace_key(tb, - tb->CFR[0], - tb->rkey[0], - tb->R[0], - 0); + replace_key(tb, tb->CFR[0], tb->rkey[0], tb->R[0], 0); } } @@ -1111,22 +759,16 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h default: /* cases d and t */ reiserfs_panic(tb->tb_sb, "PAP-12175", "rnum > 0: unexpected mode: %s(%d)", - (flag == - M_DELETE) ? "DELETE" : ((flag == - M_CUT) ? "CUT" - : "UNKNOWN"), - flag); + (flag == M_DELETE) ? "DELETE" : ((flag == M_CUT) ? "CUT" : "UNKNOWN"), flag); } } /* tb->rnum[0] > 0 */ RFALSE(tb->blknum[0] > 3, - "PAP-12180: blknum can not be %d. It must be <= 3", - tb->blknum[0]); + "PAP-12180: blknum can not be %d. It must be <= 3", tb->blknum[0]); RFALSE(tb->blknum[0] < 0, - "PAP-12185: blknum can not be %d. It must be >= 0", - tb->blknum[0]); + "PAP-12185: blknum can not be %d. It must be >= 0", tb->blknum[0]); /* if while adding to a node we discover that it is possible to split it in two, and merge the left part into the left neighbor and the @@ -1177,8 +819,7 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h if (n - snum[i] < item_pos) { /* new item or it's part falls to first new node S_new[i] */ if (item_pos == n - snum[i] + 1 && sbytes[i] != -1) { /* part of new item falls into S_new[i] */ - int old_key_comp, old_len, - r_zeros_number; + int old_key_comp, old_len, r_zeros_number; const char *r_body; int version; @@ -1192,15 +833,8 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h old_len = ih_item_len(ih); /* Calculate key component and item length to insert into S_new[i] */ - set_le_ih_k_offset(ih, - le_ih_k_offset(ih) + - ((old_len - - sbytes[i]) << - (is_indirect_le_ih - (ih) ? tb->tb_sb-> - s_blocksize_bits - - UNFM_P_SHIFT : - 0))); + set_le_ih_k_offset(ih, le_ih_k_offset(ih) + + ((old_len - sbytes[i]) << (is_indirect_le_ih(ih) ? tb->tb_sb-> s_blocksize_bits - UNFM_P_SHIFT : 0))); put_ih_item_len(ih, sbytes[i]); @@ -1209,39 +843,29 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h if ((old_len - sbytes[i]) > zeros_num) { r_zeros_number = 0; - r_body = - body + (old_len - - sbytes[i]) - - zeros_num; + r_body = body + (old_len - sbytes[i]) - zeros_num; } else { r_body = body; - r_zeros_number = - zeros_num - (old_len - - sbytes[i]); + r_zeros_number = zeros_num - (old_len - sbytes[i]); zeros_num -= r_zeros_number; } - leaf_insert_into_buf(&bi, 0, ih, r_body, - r_zeros_number); + leaf_insert_into_buf(&bi, 0, ih, r_body, r_zeros_number); /* Calculate key component and item length to insert into S[i] */ set_le_ih_k_offset(ih, old_key_comp); - put_ih_item_len(ih, - old_len - sbytes[i]); + put_ih_item_len(ih, old_len - sbytes[i]); tb->insert_size[0] -= sbytes[i]; } else { /* whole new item falls into S_new[i] */ /* Shift snum[0] - 1 items to S_new[i] (sbytes[i] of split item) */ leaf_move_items(LEAF_FROM_S_TO_SNEW, tb, - snum[i] - 1, sbytes[i], - S_new[i]); + snum[i] - 1, sbytes[i], S_new[i]); /* Insert new item into S_new[i] */ buffer_info_init_bh(tb, &bi, S_new[i]); - leaf_insert_into_buf(&bi, - item_pos - n + - snum[i] - 1, ih, - body, zeros_num); + leaf_insert_into_buf(&bi, item_pos - n + snum[i] - 1, + ih, body, zeros_num); zeros_num = tb->insert_size[0] = 0; } @@ -1268,150 +892,73 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h int entry_count; - entry_count = - ih_entry_count(aux_ih); + entry_count = ih_entry_count(aux_ih); - if (entry_count - sbytes[i] < - pos_in_item - && pos_in_item <= - entry_count) { + if (entry_count - sbytes[i] < pos_in_item && pos_in_item <= entry_count) { /* new directory entry falls into S_new[i] */ - RFALSE(!tb-> - insert_size[0], - "PAP-12215: insert_size is already 0"); - RFALSE(sbytes[i] - 1 >= - entry_count, + RFALSE(!tb->insert_size[0], "PAP-12215: insert_size is already 0"); + RFALSE(sbytes[i] - 1 >= entry_count, "PAP-12220: there are no so much entries (%d), only %d", - sbytes[i] - 1, - entry_count); + sbytes[i] - 1, entry_count); /* Shift snum[i]-1 items in whole. Shift sbytes[i] directory entries from directory item number snum[i] */ - leaf_move_items - (LEAF_FROM_S_TO_SNEW, - tb, snum[i], - sbytes[i] - 1, - S_new[i]); + leaf_move_items(LEAF_FROM_S_TO_SNEW, tb, snum[i], sbytes[i] - 1, S_new[i]); /* Paste given directory entry to directory item */ buffer_info_init_bh(tb, &bi, S_new[i]); - leaf_paste_in_buffer - (&bi, 0, - pos_in_item - - entry_count + - sbytes[i] - 1, - tb->insert_size[0], - body, zeros_num); + leaf_paste_in_buffer(&bi, 0, pos_in_item - entry_count + sbytes[i] - 1, + tb->insert_size[0], body, zeros_num); /* paste new directory entry */ - leaf_paste_entries(&bi, - 0, - pos_in_item - - - entry_count - + - sbytes - [i] - - 1, 1, - (struct - reiserfs_de_head - *) - body, - body - + - DEH_SIZE, - tb-> - insert_size - [0] - ); + leaf_paste_entries(&bi, 0, pos_in_item - entry_count + sbytes[i] - 1, 1, + (struct reiserfs_de_head *) body, + body + DEH_SIZE, tb->insert_size[0]); tb->insert_size[0] = 0; pos_in_item++; } else { /* new directory entry doesn't fall into S_new[i] */ - leaf_move_items - (LEAF_FROM_S_TO_SNEW, - tb, snum[i], - sbytes[i], - S_new[i]); + leaf_move_items(LEAF_FROM_S_TO_SNEW,tb, snum[i], sbytes[i], S_new[i]); } } else { /* regular object */ - int n_shift, n_rem, - r_zeros_number; + int n_shift, n_rem, r_zeros_number; const char *r_body; - RFALSE(pos_in_item != - ih_item_len - (B_N_PITEM_HEAD - (tbS0, item_pos)) - || tb->insert_size[0] <= - 0, + RFALSE(pos_in_item != ih_item_len(B_N_PITEM_HEAD(tbS0, item_pos)) || tb->insert_size[0] <= 0, "PAP-12225: item too short or insert_size <= 0"); /* Calculate number of bytes which must be shifted from appended item */ - n_shift = - sbytes[i] - - tb->insert_size[0]; + n_shift = sbytes[i] - tb->insert_size[0]; if (n_shift < 0) n_shift = 0; - leaf_move_items - (LEAF_FROM_S_TO_SNEW, tb, - snum[i], n_shift, - S_new[i]); + leaf_move_items(LEAF_FROM_S_TO_SNEW, tb, snum[i], n_shift, S_new[i]); /* Calculate number of bytes which must remain in body after append to S_new[i] */ - n_rem = - tb->insert_size[0] - - sbytes[i]; + n_rem = tb->insert_size[0] - sbytes[i]; if (n_rem < 0) n_rem = 0; /* Append part of body into S_new[0] */ buffer_info_init_bh(tb, &bi, S_new[i]); if (n_rem > zeros_num) { r_zeros_number = 0; - r_body = - body + n_rem - - zeros_num; + r_body = body + n_rem - zeros_num; } else { r_body = body; - r_zeros_number = - zeros_num - n_rem; - zeros_num -= - r_zeros_number; + r_zeros_number = zeros_num - n_rem; + zeros_num -= r_zeros_number; } - leaf_paste_in_buffer(&bi, 0, - n_shift, - tb-> - insert_size - [0] - - n_rem, - r_body, - r_zeros_number); + leaf_paste_in_buffer(&bi, 0, n_shift, + tb->insert_size[0] - n_rem, + r_body, r_zeros_number); { struct item_head *tmp; - tmp = - B_N_PITEM_HEAD(S_new - [i], - 0); + tmp = B_N_PITEM_HEAD(S_new[i], 0); if (is_indirect_le_ih (tmp)) { - set_ih_free_space - (tmp, 0); - set_le_ih_k_offset - (tmp, - le_ih_k_offset - (tmp) + - (n_rem << - (tb-> - tb_sb-> - s_blocksize_bits - - - UNFM_P_SHIFT))); + set_ih_free_space(tmp, 0); + set_le_ih_k_offset(tmp, le_ih_k_offset(tmp) + (n_rem << (tb->tb_sb->s_blocksize_bits - UNFM_P_SHIFT))); } else { - set_le_ih_k_offset - (tmp, - le_ih_k_offset - (tmp) + - n_rem); + set_le_ih_k_offset(tmp, le_ih_k_offset(tmp) + n_rem); } } @@ -1426,8 +973,7 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h struct item_head *pasted; #ifdef CONFIG_REISERFS_CHECK - struct item_head *ih_check = - B_N_PITEM_HEAD(tbS0, item_pos); + struct item_head *ih_check = B_N_PITEM_HEAD(tbS0, item_pos); if (!is_direntry_le_ih(ih_check) && (pos_in_item != ih_item_len(ih_check) @@ -1439,8 +985,7 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h "to ih_item_len"); #endif /* CONFIG_REISERFS_CHECK */ - leaf_mi = - leaf_move_items(LEAF_FROM_S_TO_SNEW, + leaf_mi = leaf_move_items(LEAF_FROM_S_TO_SNEW, tb, snum[i], sbytes[i], S_new[i]); @@ -1452,30 +997,19 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h /* paste into item */ buffer_info_init_bh(tb, &bi, S_new[i]); leaf_paste_in_buffer(&bi, - item_pos - n + - snum[i], + item_pos - n + snum[i], pos_in_item, tb->insert_size[0], body, zeros_num); - pasted = - B_N_PITEM_HEAD(S_new[i], - item_pos - n + - snum[i]); + pasted = B_N_PITEM_HEAD(S_new[i], item_pos - n + snum[i]); if (is_direntry_le_ih(pasted)) { leaf_paste_entries(&bi, - item_pos - - n + snum[i], - pos_in_item, - 1, - (struct - reiserfs_de_head - *)body, - body + - DEH_SIZE, - tb-> - insert_size - [0] + item_pos - n + snum[i], + pos_in_item, 1, + (struct reiserfs_de_head *)body, + body + DEH_SIZE, + tb->insert_size[0] ); } @@ -1495,11 +1029,7 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h default: /* cases d and t */ reiserfs_panic(tb->tb_sb, "PAP-12245", "blknum > 2: unexpected mode: %s(%d)", - (flag == - M_DELETE) ? "DELETE" : ((flag == - M_CUT) ? "CUT" - : "UNKNOWN"), - flag); + (flag == M_DELETE) ? "DELETE" : ((flag == M_CUT) ? "CUT" : "UNKNOWN"), flag); } memcpy(insert_key + i, B_N_PKEY(S_new[i], 0), KEY_SIZE); @@ -1524,9 +1054,7 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h /* If we insert the first key change the delimiting key */ if (item_pos == 0) { if (tb->CFL[0]) /* can be 0 in reiserfsck */ - replace_key(tb, tb->CFL[0], tb->lkey[0], - tbS0, 0); - + replace_key(tb, tb->CFL[0], tb->lkey[0], tbS0, 0); } break; @@ -1536,53 +1064,27 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h pasted = B_N_PITEM_HEAD(tbS0, item_pos); /* when directory, may be new entry already pasted */ if (is_direntry_le_ih(pasted)) { - if (pos_in_item >= 0 && - pos_in_item <= - ih_entry_count(pasted)) { + if (pos_in_item >= 0 && pos_in_item <= ih_entry_count(pasted)) { RFALSE(!tb->insert_size[0], "PAP-12260: insert_size is 0 already"); /* prepare space */ buffer_info_init_tbS0(tb, &bi); - leaf_paste_in_buffer(&bi, - item_pos, - pos_in_item, - tb-> - insert_size - [0], body, + leaf_paste_in_buffer(&bi, item_pos, pos_in_item, + tb->insert_size[0], body, zeros_num); /* paste entry */ - leaf_paste_entries(&bi, - item_pos, - pos_in_item, - 1, - (struct - reiserfs_de_head - *)body, - body + - DEH_SIZE, - tb-> - insert_size - [0] - ); + leaf_paste_entries(&bi, item_pos, pos_in_item, 1, + (struct reiserfs_de_head *)body, + body + DEH_SIZE, + tb->insert_size[0]); if (!item_pos && !pos_in_item) { - RFALSE(!tb->CFL[0] - || !tb->L[0], + RFALSE(!tb->CFL[0] || !tb->L[0], "PAP-12270: CFL[0]/L[0] must be specified"); - if (tb->CFL[0]) { - replace_key(tb, - tb-> - CFL - [0], - tb-> - lkey - [0], - tbS0, - 0); - - } + if (tb->CFL[0]) + replace_key(tb, tb->CFL[0], tb->lkey[0], tbS0, 0); } tb->insert_size[0] = 0; } @@ -1593,13 +1095,8 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h "PAP-12275: insert size must not be %d", tb->insert_size[0]); buffer_info_init_tbS0(tb, &bi); - leaf_paste_in_buffer(&bi, - item_pos, - pos_in_item, - tb-> - insert_size - [0], body, - zeros_num); + leaf_paste_in_buffer(&bi, item_pos, pos_in_item, + tb->insert_size[0], body, zeros_num); if (is_indirect_le_ih(pasted)) { #if 0 @@ -1611,8 +1108,7 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h tb-> insert_size[0]); #endif - set_ih_free_space - (pasted, 0); + set_ih_free_space(pasted, 0); } tb->insert_size[0] = 0; } @@ -1620,8 +1116,7 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h else { if (tb->insert_size[0]) { print_cur_tb("12285"); - reiserfs_panic(tb-> - tb_sb, + reiserfs_panic(tb->tb_sb, "PAP-12285", "insert_size " "must be 0 " diff --git a/fs/sync.c b/fs/sync.c index e8ba024a055b..b28d1dd10e8b 100644 --- a/fs/sync.c +++ b/fs/sync.c @@ -27,11 +27,10 @@ * wait == 1 case since in that case write_inode() functions do * sync_dirty_buffer() and thus effectively write one block at a time. */ -static int __sync_filesystem(struct super_block *sb, int wait, - unsigned long start) +static int __sync_filesystem(struct super_block *sb, int wait) { if (wait) - sync_inodes_sb(sb, start); + sync_inodes_sb(sb); else writeback_inodes_sb(sb, WB_REASON_SYNC); @@ -48,7 +47,6 @@ static int __sync_filesystem(struct super_block *sb, int wait, int sync_filesystem(struct super_block *sb) { int ret; - unsigned long start = jiffies; /* * We need to be protected against the filesystem going from @@ -62,17 +60,17 @@ int sync_filesystem(struct super_block *sb) if (sb->s_flags & MS_RDONLY) return 0; - ret = __sync_filesystem(sb, 0, start); + ret = __sync_filesystem(sb, 0); if (ret < 0) return ret; - return __sync_filesystem(sb, 1, start); + return __sync_filesystem(sb, 1); } EXPORT_SYMBOL_GPL(sync_filesystem); static void sync_inodes_one_sb(struct super_block *sb, void *arg) { if (!(sb->s_flags & MS_RDONLY)) - sync_inodes_sb(sb, *((unsigned long *)arg)); + sync_inodes_sb(sb); } static void sync_fs_one_sb(struct super_block *sb, void *arg) @@ -104,10 +102,9 @@ static void fdatawait_one_bdev(struct block_device *bdev, void *arg) SYSCALL_DEFINE0(sync) { int nowait = 0, wait = 1; - unsigned long start = jiffies; wakeup_flusher_threads(0, WB_REASON_SYNC); - iterate_supers(sync_inodes_one_sb, &start); + iterate_supers(sync_inodes_one_sb, NULL); iterate_supers(sync_fs_one_sb, &nowait); iterate_supers(sync_fs_one_sb, &wait); iterate_bdevs(fdatawrite_one_bdev, NULL); diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c index 6211230814fd..3eaf5c6622eb 100644 --- a/fs/sysfs/mount.c +++ b/fs/sysfs/mount.c @@ -27,6 +27,7 @@ static struct dentry *sysfs_mount(struct file_system_type *fs_type, { struct dentry *root; void *ns; + bool new_sb; if (!(flags & MS_KERNMOUNT)) { if (!capable(CAP_SYS_ADMIN) && !fs_fully_visible(fs_type)) @@ -37,8 +38,8 @@ static struct dentry *sysfs_mount(struct file_system_type *fs_type, } ns = kobj_ns_grab_current(KOBJ_NS_TYPE_NET); - root = kernfs_mount_ns(fs_type, flags, sysfs_root, ns); - if (IS_ERR(root)) + root = kernfs_mount_ns(fs_type, flags, sysfs_root, &new_sb, ns); + if (IS_ERR(root) || !new_sb) kobj_ns_drop(KOBJ_NS_TYPE_NET, ns); return root; } diff --git a/fs/udf/file.c b/fs/udf/file.c index c02a27a19c6d..1037637957c7 100644 --- a/fs/udf/file.c +++ b/fs/udf/file.c @@ -144,6 +144,7 @@ static ssize_t udf_file_aio_write(struct kiocb *iocb, const struct iovec *iov, size_t count = iocb->ki_nbytes; struct udf_inode_info *iinfo = UDF_I(inode); + mutex_lock(&inode->i_mutex); down_write(&iinfo->i_data_sem); if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) { if (file->f_flags & O_APPEND) @@ -156,6 +157,7 @@ static ssize_t udf_file_aio_write(struct kiocb *iocb, const struct iovec *iov, pos + count)) { err = udf_expand_file_adinicb(inode); if (err) { + mutex_unlock(&inode->i_mutex); udf_debug("udf_expand_adinicb: err=%d\n", err); return err; } @@ -169,9 +171,17 @@ static ssize_t udf_file_aio_write(struct kiocb *iocb, const struct iovec *iov, } else up_write(&iinfo->i_data_sem); - retval = generic_file_aio_write(iocb, iov, nr_segs, ppos); - if (retval > 0) + retval = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos); + mutex_unlock(&inode->i_mutex); + + if (retval > 0) { + ssize_t err; + mark_inode_dirty(inode); + err = generic_write_sync(file, iocb->ki_pos - retval, retval); + if (err < 0) + retval = err; + } return retval; } diff --git a/fs/udf/inode.c b/fs/udf/inode.c index 062b7925bca0..982ce05c87ed 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -265,6 +265,7 @@ int udf_expand_file_adinicb(struct inode *inode) .nr_to_write = 1, }; + WARN_ON_ONCE(!mutex_is_locked(&inode->i_mutex)); if (!iinfo->i_lenAlloc) { if (UDF_QUERY_FLAG(inode->i_sb, UDF_FLAG_USE_SHORT_AD)) iinfo->i_alloc_type = ICBTAG_FLAG_AD_SHORT; diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index f35d5c953ff9..9ddfb8190ca1 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -705,7 +705,6 @@ xfs_setattr_size( { struct xfs_mount *mp = ip->i_mount; struct inode *inode = VFS_I(ip); - int mask = iattr->ia_valid; xfs_off_t oldsize, newsize; struct xfs_trans *tp; int error; @@ -726,8 +725,8 @@ xfs_setattr_size( ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL)); ASSERT(S_ISREG(ip->i_d.di_mode)); - ASSERT((mask & (ATTR_UID|ATTR_GID|ATTR_ATIME|ATTR_ATIME_SET| - ATTR_MTIME_SET|ATTR_KILL_PRIV|ATTR_TIMES_SET)) == 0); + ASSERT((iattr->ia_valid & (ATTR_UID|ATTR_GID|ATTR_ATIME|ATTR_ATIME_SET| + ATTR_MTIME_SET|ATTR_KILL_PRIV|ATTR_TIMES_SET)) == 0); oldsize = inode->i_size; newsize = iattr->ia_size; @@ -736,7 +735,7 @@ xfs_setattr_size( * Short circuit the truncate case for zero length files. */ if (newsize == 0 && oldsize == 0 && ip->i_d.di_nextents == 0) { - if (!(mask & (ATTR_CTIME|ATTR_MTIME))) + if (!(iattr->ia_valid & (ATTR_CTIME|ATTR_MTIME))) return 0; /* @@ -824,10 +823,11 @@ xfs_setattr_size( * these flags set. For all other operations the VFS set these flags * explicitly if it wants a timestamp update. */ - if (newsize != oldsize && (!(mask & (ATTR_CTIME | ATTR_MTIME)))) { + if (newsize != oldsize && + !(iattr->ia_valid & (ATTR_CTIME | ATTR_MTIME))) { iattr->ia_ctime = iattr->ia_mtime = current_fs_time(inode->i_sb); - mask |= ATTR_CTIME | ATTR_MTIME; + iattr->ia_valid |= ATTR_CTIME | ATTR_MTIME; } /* @@ -863,9 +863,9 @@ xfs_setattr_size( xfs_inode_clear_eofblocks_tag(ip); } - if (mask & ATTR_MODE) + if (iattr->ia_valid & ATTR_MODE) xfs_setattr_mode(ip, iattr); - if (mask & (ATTR_ATIME|ATTR_CTIME|ATTR_MTIME)) + if (iattr->ia_valid & (ATTR_ATIME|ATTR_CTIME|ATTR_MTIME)) xfs_setattr_time(ip, iattr); xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c index cdebd832c3db..4ef6fdbced78 100644 --- a/fs/xfs/xfs_log_cil.c +++ b/fs/xfs/xfs_log_cil.c @@ -205,16 +205,25 @@ xlog_cil_insert_format_items( /* * We 64-bit align the length of each iovec so that the start * of the next one is naturally aligned. We'll need to - * account for that slack space here. + * account for that slack space here. Then round nbytes up + * to 64-bit alignment so that the initial buffer alignment is + * easy to calculate and verify. */ nbytes += niovecs * sizeof(uint64_t); + nbytes = round_up(nbytes, sizeof(uint64_t)); /* grab the old item if it exists for reservation accounting */ old_lv = lip->li_lv; - /* calc buffer size */ - buf_size = sizeof(struct xfs_log_vec) + nbytes + - niovecs * sizeof(struct xfs_log_iovec); + /* + * The data buffer needs to start 64-bit aligned, so round up + * that space to ensure we can align it appropriately and not + * overrun the buffer. + */ + buf_size = nbytes + + round_up((sizeof(struct xfs_log_vec) + + niovecs * sizeof(struct xfs_log_iovec)), + sizeof(uint64_t)); /* compare to existing item size */ if (lip->li_lv && buf_size <= lip->li_lv->lv_size) { @@ -251,6 +260,8 @@ xlog_cil_insert_format_items( /* The allocated data region lies beyond the iovec region */ lv->lv_buf_len = 0; lv->lv_buf = (char *)lv + buf_size - nbytes; + ASSERT(IS_ALIGNED((unsigned long)lv->lv_buf, sizeof(uint64_t))); + lip->li_ops->iop_format(lip, lv); insert: ASSERT(lv->lv_buf_len <= nbytes); diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index 02df7b408a26..f96c05669a9e 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -282,22 +282,29 @@ xfs_readsb( struct xfs_sb *sbp = &mp->m_sb; int error; int loud = !(flags & XFS_MFSI_QUIET); + const struct xfs_buf_ops *buf_ops; ASSERT(mp->m_sb_bp == NULL); ASSERT(mp->m_ddev_targp != NULL); /* + * For the initial read, we must guess at the sector + * size based on the block device. It's enough to + * get the sb_sectsize out of the superblock and + * then reread with the proper length. + * We don't verify it yet, because it may not be complete. + */ + sector_size = xfs_getsize_buftarg(mp->m_ddev_targp); + buf_ops = NULL; + + /* * Allocate a (locked) buffer to hold the superblock. * This will be kept around at all times to optimize * access to the superblock. */ - sector_size = xfs_getsize_buftarg(mp->m_ddev_targp); - reread: bp = xfs_buf_read_uncached(mp->m_ddev_targp, XFS_SB_DADDR, - BTOBB(sector_size), 0, - loud ? &xfs_sb_buf_ops - : &xfs_sb_quiet_buf_ops); + BTOBB(sector_size), 0, buf_ops); if (!bp) { if (loud) xfs_warn(mp, "SB buffer read failed"); @@ -328,12 +335,13 @@ reread: } /* - * If device sector size is smaller than the superblock size, - * re-read the superblock so the buffer is correctly sized. + * Re-read the superblock so the buffer is correctly sized, + * and properly verified. */ - if (sector_size < sbp->sb_sectsize) { + if (buf_ops == NULL) { xfs_buf_relse(bp); sector_size = sbp->sb_sectsize; + buf_ops = loud ? &xfs_sb_buf_ops : &xfs_sb_quiet_buf_ops; goto reread; } diff --git a/fs/xfs/xfs_sb.c b/fs/xfs/xfs_sb.c index b7c9aea77f8f..1e116794bb66 100644 --- a/fs/xfs/xfs_sb.c +++ b/fs/xfs/xfs_sb.c @@ -295,8 +295,7 @@ xfs_mount_validate_sb( sbp->sb_dblocks == 0 || sbp->sb_dblocks > XFS_MAX_DBLOCKS(sbp) || sbp->sb_dblocks < XFS_MIN_DBLOCKS(sbp))) { - XFS_CORRUPTION_ERROR("SB sanity check failed", - XFS_ERRLEVEL_LOW, mp, sbp); + xfs_notice(mp, "SB sanity check failed"); return XFS_ERROR(EFSCORRUPTED); } @@ -611,10 +610,10 @@ xfs_sb_read_verify( XFS_SB_VERSION_5) || dsb->sb_crc != 0)) { - if (!xfs_verify_cksum(bp->b_addr, be16_to_cpu(dsb->sb_sectsize), + if (!xfs_verify_cksum(bp->b_addr, BBTOB(bp->b_length), offsetof(struct xfs_sb, sb_crc))) { /* Only fail bad secondaries on a known V5 filesystem */ - if (bp->b_bn != XFS_SB_DADDR && + if (bp->b_bn == XFS_SB_DADDR || xfs_sb_version_hascrc(&mp->m_sb)) { error = EFSCORRUPTED; goto out_error; @@ -625,7 +624,7 @@ xfs_sb_read_verify( out_error: if (error) { - if (error != EWRONGFS) + if (error == EFSCORRUPTED) XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, bp->b_addr); xfs_buf_ioerror(bp, error); @@ -644,7 +643,6 @@ xfs_sb_quiet_read_verify( { struct xfs_dsb *dsb = XFS_BUF_TO_SBP(bp); - if (dsb->sb_magicnum == cpu_to_be32(XFS_SB_MAGIC)) { /* XFS filesystem, verify noisily! */ xfs_sb_read_verify(bp); diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index f317488263dd..d971f4932b5d 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -913,7 +913,7 @@ xfs_flush_inodes( struct super_block *sb = mp->m_super; if (down_read_trylock(&sb->s_umount)) { - sync_inodes_sb(sb, jiffies); + sync_inodes_sb(sb); up_read(&sb->s_umount); } } diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index 8e4f41d9af4d..34c7bdc06014 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -701,6 +701,18 @@ static inline pte_t pte_mknuma(pte_t pte) } #endif +#ifndef ptep_set_numa +static inline void ptep_set_numa(struct mm_struct *mm, unsigned long addr, + pte_t *ptep) +{ + pte_t ptent = *ptep; + + ptent = pte_mknuma(ptent); + set_pte_at(mm, addr, ptep, ptent); + return; +} +#endif + #ifndef pmd_mknuma static inline pmd_t pmd_mknuma(pmd_t pmd) { @@ -708,6 +720,18 @@ static inline pmd_t pmd_mknuma(pmd_t pmd) return pmd_clear_flags(pmd, _PAGE_PRESENT); } #endif + +#ifndef pmdp_set_numa +static inline void pmdp_set_numa(struct mm_struct *mm, unsigned long addr, + pmd_t *pmdp) +{ + pmd_t pmd = *pmdp; + + pmd = pmd_mknuma(pmd); + set_pmd_at(mm, addr, pmdp, pmd); + return; +} +#endif #else extern int pte_numa(pte_t pte); extern int pmd_numa(pmd_t pmd); @@ -715,6 +739,8 @@ extern pte_t pte_mknonnuma(pte_t pte); extern pmd_t pmd_mknonnuma(pmd_t pmd); extern pte_t pte_mknuma(pte_t pte); extern pmd_t pmd_mknuma(pmd_t pmd); +extern void ptep_set_numa(struct mm_struct *mm, unsigned long addr, pte_t *ptep); +extern void pmdp_set_numa(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp); #endif /* CONFIG_ARCH_USES_NUMA_PROT_NONE */ #else static inline int pmd_numa(pmd_t pmd) @@ -742,10 +768,23 @@ static inline pte_t pte_mknuma(pte_t pte) return pte; } +static inline void ptep_set_numa(struct mm_struct *mm, unsigned long addr, + pte_t *ptep) +{ + return; +} + + static inline pmd_t pmd_mknuma(pmd_t pmd) { return pmd; } + +static inline void pmdp_set_numa(struct mm_struct *mm, unsigned long addr, + pmd_t *pmdp) +{ + return ; +} #endif /* CONFIG_NUMA_BALANCING */ #endif /* CONFIG_MMU */ diff --git a/include/drm/drmP.h b/include/drm/drmP.h index 04086c5be930..04a7f31301f8 100644 --- a/include/drm/drmP.h +++ b/include/drm/drmP.h @@ -199,6 +199,9 @@ int drm_err(const char *func, const char *format, ...); #define DRM_INFO(fmt, ...) \ printk(KERN_INFO "[" DRM_NAME "] " fmt, ##__VA_ARGS__) +#define DRM_INFO_ONCE(fmt, ...) \ + printk_once(KERN_INFO "[" DRM_NAME "] " fmt, ##__VA_ARGS__) + /** * Debug output. * diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h index 71727b6210ae..8f3dee097579 100644 --- a/include/drm/drm_crtc.h +++ b/include/drm/drm_crtc.h @@ -907,6 +907,9 @@ struct drm_mode_config { /* whether async page flip is supported or not */ bool async_page_flip; + + /* cursor size */ + uint32_t cursor_width, cursor_height; }; #define obj_to_crtc(x) container_of(x, struct drm_crtc, base) diff --git a/include/drm/ttm/ttm_page_alloc.h b/include/drm/ttm/ttm_page_alloc.h index d1f61bfe0ebe..49a828425fa2 100644 --- a/include/drm/ttm/ttm_page_alloc.h +++ b/include/drm/ttm/ttm_page_alloc.h @@ -29,6 +29,8 @@ #include <drm/ttm/ttm_bo_driver.h> #include <drm/ttm/ttm_memory.h> +struct device; + /** * Initialize pool allocator. */ diff --git a/include/dt-bindings/clock/tegra124-car.h b/include/dt-bindings/clock/tegra124-car.h index a1116a3b54ef..8c1603b10665 100644 --- a/include/dt-bindings/clock/tegra124-car.h +++ b/include/dt-bindings/clock/tegra124-car.h @@ -36,10 +36,10 @@ #define TEGRA124_CLK_PWM 17 #define TEGRA124_CLK_I2S2 18 /* 20 (register bit affects vi and vi_sensor) */ -#define TEGRA124_CLK_GR_2D 21 +/* 21 */ #define TEGRA124_CLK_USBD 22 #define TEGRA124_CLK_ISP 23 -#define TEGRA124_CLK_GR_3D 24 +/* 26 */ /* 25 */ #define TEGRA124_CLK_DISP2 26 #define TEGRA124_CLK_DISP1 27 diff --git a/include/linux/bio.h b/include/linux/bio.h index 70654521dab6..5a4d39b4686b 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -250,6 +250,17 @@ static inline unsigned bio_segments(struct bio *bio) struct bio_vec bv; struct bvec_iter iter; + /* + * We special case discard/write same, because they interpret bi_size + * differently: + */ + + if (bio->bi_rw & REQ_DISCARD) + return 1; + + if (bio->bi_rw & REQ_WRITE_SAME) + return 1; + bio_for_each_segment(bv, bio, iter) segs++; @@ -332,6 +343,7 @@ extern struct bio *bio_clone_fast(struct bio *, gfp_t, struct bio_set *); extern struct bio *bio_clone_bioset(struct bio *, gfp_t, struct bio_set *bs); extern struct bio_set *fs_bio_set; +unsigned int bio_integrity_tag_size(struct bio *bio); static inline struct bio *bio_alloc(gfp_t gfp_mask, unsigned int nr_iovecs) { diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 161b23105b1e..18ba8a627f46 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -83,6 +83,8 @@ struct blk_mq_ops { */ rq_timed_out_fn *timeout; + softirq_done_fn *complete; + /* * Override for hctx allocations (should probably go) */ @@ -119,11 +121,12 @@ void blk_mq_init_commands(struct request_queue *, void (*init)(void *data, struc void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule); -void blk_mq_insert_request(struct request_queue *, struct request *, bool); +void blk_mq_insert_request(struct request_queue *, struct request *, + bool, bool); void blk_mq_run_queues(struct request_queue *q, bool async); void blk_mq_free_request(struct request *rq); bool blk_mq_can_queue(struct blk_mq_hw_ctx *); -struct request *blk_mq_alloc_request(struct request_queue *q, int rw, gfp_t gfp, bool reserved); +struct request *blk_mq_alloc_request(struct request_queue *q, int rw, gfp_t gfp); struct request *blk_mq_alloc_reserved_request(struct request_queue *q, int rw, gfp_t gfp); struct request *blk_mq_rq_from_tag(struct request_queue *q, unsigned int tag); @@ -133,6 +136,8 @@ void blk_mq_free_single_hw_queue(struct blk_mq_hw_ctx *, unsigned int); void blk_mq_end_io(struct request *rq, int error); +void blk_mq_complete_request(struct request *rq); + void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx); void blk_mq_start_hw_queue(struct blk_mq_hw_ctx *hctx); void blk_mq_stop_hw_queues(struct request_queue *q); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 8678c4322b44..4afa4f8f6090 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -98,7 +98,7 @@ struct request { struct list_head queuelist; union { struct call_single_data csd; - struct work_struct mq_flush_data; + struct work_struct mq_flush_work; }; struct request_queue *q; @@ -448,13 +448,8 @@ struct request_queue { unsigned long flush_pending_since; struct list_head flush_queue[2]; struct list_head flush_data_in_flight; - union { - struct request flush_rq; - struct { - spinlock_t mq_flush_lock; - struct work_struct mq_flush_work; - }; - }; + struct request *flush_rq; + spinlock_t mq_flush_lock; struct mutex sysfs_lock; diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index 677b4f01b2d0..6f76277baf39 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -13,10 +13,17 @@ #define PHY_ID_BCM5461 0x002060c0 #define PHY_ID_BCM57780 0x03625d90 +#define PHY_ID_BCM7366 0x600d8490 +#define PHY_ID_BCM7439 0x600d8480 +#define PHY_ID_BCM7445 0x600d8510 +#define PHY_ID_BCM7XXX_28 0x600d8400 + #define PHY_BCM_OUI_MASK 0xfffffc00 #define PHY_BCM_OUI_1 0x00206000 #define PHY_BCM_OUI_2 0x0143bc00 #define PHY_BCM_OUI_3 0x03625c00 +#define PHY_BCM_OUI_4 0x600d0000 +#define PHY_BCM_OUI_5 0x03625e00 #define PHY_BCM_FLAGS_MODE_COPPER 0x00000001 @@ -31,6 +38,59 @@ #define PHY_BRCM_EXT_IBND_TX_ENABLE 0x00002000 #define PHY_BRCM_CLEAR_RGMII_MODE 0x00004000 #define PHY_BRCM_DIS_TXCRXC_NOENRGY 0x00008000 +/* Broadcom BCM7xxx specific workarounds */ +#define PHY_BRCM_100MBPS_WAR 0x00010000 #define PHY_BCM_FLAGS_VALID 0x80000000 +/* Broadcom BCM54XX register definitions, common to most Broadcom PHYs */ +#define MII_BCM54XX_ECR 0x10 /* BCM54xx extended control register */ +#define MII_BCM54XX_ECR_IM 0x1000 /* Interrupt mask */ +#define MII_BCM54XX_ECR_IF 0x0800 /* Interrupt force */ + +#define MII_BCM54XX_ESR 0x11 /* BCM54xx extended status register */ +#define MII_BCM54XX_ESR_IS 0x1000 /* Interrupt status */ + +#define MII_BCM54XX_EXP_DATA 0x15 /* Expansion register data */ +#define MII_BCM54XX_EXP_SEL 0x17 /* Expansion register select */ +#define MII_BCM54XX_EXP_SEL_SSD 0x0e00 /* Secondary SerDes select */ +#define MII_BCM54XX_EXP_SEL_ER 0x0f00 /* Expansion register select */ + +#define MII_BCM54XX_AUX_CTL 0x18 /* Auxiliary control register */ +#define MII_BCM54XX_ISR 0x1a /* BCM54xx interrupt status register */ +#define MII_BCM54XX_IMR 0x1b /* BCM54xx interrupt mask register */ +#define MII_BCM54XX_INT_CRCERR 0x0001 /* CRC error */ +#define MII_BCM54XX_INT_LINK 0x0002 /* Link status changed */ +#define MII_BCM54XX_INT_SPEED 0x0004 /* Link speed change */ +#define MII_BCM54XX_INT_DUPLEX 0x0008 /* Duplex mode changed */ +#define MII_BCM54XX_INT_LRS 0x0010 /* Local receiver status changed */ +#define MII_BCM54XX_INT_RRS 0x0020 /* Remote receiver status changed */ +#define MII_BCM54XX_INT_SSERR 0x0040 /* Scrambler synchronization error */ +#define MII_BCM54XX_INT_UHCD 0x0080 /* Unsupported HCD negotiated */ +#define MII_BCM54XX_INT_NHCD 0x0100 /* No HCD */ +#define MII_BCM54XX_INT_NHCDL 0x0200 /* No HCD link */ +#define MII_BCM54XX_INT_ANPR 0x0400 /* Auto-negotiation page received */ +#define MII_BCM54XX_INT_LC 0x0800 /* All counters below 128 */ +#define MII_BCM54XX_INT_HC 0x1000 /* Counter above 32768 */ +#define MII_BCM54XX_INT_MDIX 0x2000 /* MDIX status change */ +#define MII_BCM54XX_INT_PSERR 0x4000 /* Pair swap error */ + +#define MII_BCM54XX_SHD 0x1c /* 0x1c shadow registers */ +#define MII_BCM54XX_SHD_WRITE 0x8000 +#define MII_BCM54XX_SHD_VAL(x) ((x & 0x1f) << 10) +#define MII_BCM54XX_SHD_DATA(x) ((x & 0x3ff) << 0) + +/* + * AUXILIARY CONTROL SHADOW ACCESS REGISTERS. (PHY REG 0x18) + */ +#define MII_BCM54XX_AUXCTL_SHDWSEL_AUXCTL 0x0000 +#define MII_BCM54XX_AUXCTL_ACTL_TX_6DB 0x0400 +#define MII_BCM54XX_AUXCTL_ACTL_SMDSP_ENA 0x0800 + +#define MII_BCM54XX_AUXCTL_MISC_WREN 0x8000 +#define MII_BCM54XX_AUXCTL_MISC_FORCE_AMDIX 0x0200 +#define MII_BCM54XX_AUXCTL_MISC_RDSEL_MISC 0x7000 +#define MII_BCM54XX_AUXCTL_SHDWSEL_MISC 0x0007 + +#define MII_BCM54XX_AUXCTL_SHDWSEL_AUXCTL 0x0000 + #endif /* _LINUX_BRCMPHY_H */ diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index fb0ab651a041..3ce5e526525f 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -33,8 +33,9 @@ enum can_mode { struct can_priv { struct can_device_stats can_stats; - struct can_bittiming bittiming; - const struct can_bittiming_const *bittiming_const; + struct can_bittiming bittiming, data_bittiming; + const struct can_bittiming_const *bittiming_const, + *data_bittiming_const; struct can_clock clock; enum can_state state; @@ -45,6 +46,7 @@ struct can_priv { struct timer_list restart_timer; int (*do_set_bittiming)(struct net_device *dev); + int (*do_set_data_bittiming)(struct net_device *dev); int (*do_set_mode)(struct net_device *dev, enum can_mode mode); int (*do_get_state)(const struct net_device *dev, enum can_state *state); @@ -111,6 +113,7 @@ struct can_priv *safe_candev_priv(struct net_device *dev); int open_candev(struct net_device *dev); void close_candev(struct net_device *dev); +int can_change_mtu(struct net_device *dev, int new_mtu); int register_candev(struct net_device *dev); void unregister_candev(struct net_device *dev); @@ -124,6 +127,8 @@ unsigned int can_get_echo_skb(struct net_device *dev, unsigned int idx); void can_free_echo_skb(struct net_device *dev, unsigned int idx); struct sk_buff *alloc_can_skb(struct net_device *dev, struct can_frame **cf); +struct sk_buff *alloc_canfd_skb(struct net_device *dev, + struct canfd_frame **cfd); struct sk_buff *alloc_can_err_skb(struct net_device *dev, struct can_frame **cf); diff --git a/include/linux/can/skb.h b/include/linux/can/skb.h index 2f0543f7510c..f9bbbb472663 100644 --- a/include/linux/can/skb.h +++ b/include/linux/can/skb.h @@ -11,7 +11,9 @@ #define CAN_SKB_H #include <linux/types.h> +#include <linux/skbuff.h> #include <linux/can.h> +#include <net/sock.h> /* * The struct can_skb_priv is used to transport additional information along @@ -42,4 +44,40 @@ 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->sk = sk; + } +} + +/* + * returns an unshared skb owned by the original sock to be echo'ed back + */ +static inline struct sk_buff *can_create_echo_skb(struct sk_buff *skb) +{ + if (skb_shared(skb)) { + struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC); + + if (likely(nskb)) { + can_skb_set_owner(nskb, skb->sk); + consume_skb(skb); + return nskb; + } else { + kfree_skb(skb); + return NULL; + } + } + + /* we can assume to have an unshared skb with proper owner */ + return skb; +} + #endif /* CAN_SKB_H */ diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h index 2623cffc73a1..25bfb0eff772 100644 --- a/include/linux/ceph/ceph_fs.h +++ b/include/linux/ceph/ceph_fs.h @@ -373,8 +373,9 @@ extern const char *ceph_mds_op_name(int op); /* * Ceph setxattr request flags. */ -#define CEPH_XATTR_CREATE 1 -#define CEPH_XATTR_REPLACE 2 +#define CEPH_XATTR_CREATE (1 << 0) +#define CEPH_XATTR_REPLACE (1 << 1) +#define CEPH_XATTR_REMOVE (1 << 31) union ceph_mds_request_args { struct { diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 5c097596104b..9450f025fe0c 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -166,6 +166,8 @@ struct cgroup { * * The ID of the root cgroup is always 0, and a new cgroup * will be assigned with a smallest available ID. + * + * Allocating/Removing ID must be protected by cgroup_mutex. */ int id; diff --git a/include/linux/compiler-gcc4.h b/include/linux/compiler-gcc4.h index ded429966c1f..2507fd2a1eb4 100644 --- a/include/linux/compiler-gcc4.h +++ b/include/linux/compiler-gcc4.h @@ -75,11 +75,7 @@ * * (asm goto is automatically volatile - the naming reflects this.) */ -#if GCC_VERSION <= 40801 -# define asm_volatile_goto(x...) do { asm goto(x); asm (""); } while (0) -#else -# define asm_volatile_goto(x...) do { asm goto(x); } while (0) -#endif +#define asm_volatile_goto(x...) do { asm goto(x); asm (""); } while (0) #ifdef CONFIG_ARCH_USE_BUILTIN_BSWAP #if GCC_VERSION >= 40400 diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index dfac5ed31120..f886985a28b2 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -171,7 +171,7 @@ struct dma_buf *dma_buf_export_named(void *priv, const struct dma_buf_ops *ops, size_t size, int flags, const char *); #define dma_buf_export(priv, ops, size, flags) \ - dma_buf_export_named(priv, ops, size, flags, __FILE__) + dma_buf_export_named(priv, ops, size, flags, KBUILD_MODNAME) int dma_buf_fd(struct dma_buf *dmabuf, int flags); struct dma_buf *dma_buf_get(int fd); diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index c8e3e7e39c6b..0a114d05f68d 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -183,6 +183,9 @@ static inline u32 ethtool_rxfh_indir_default(u32 index, u32 n_rx_rings) * hold the RTNL lock. * * See the structures used by these operations for further documentation. + * Note that for all operations using a structure ending with a zero- + * length array, the array is allocated separately in the kernel and + * is passed to the driver as an additional parameter. * * See &struct net_device and &struct net_device_ops for documentation * of the generic netdev features interface. diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 3d286ff49ab0..64cf3ef50696 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -99,7 +99,7 @@ struct fsnotify_ops { struct fsnotify_mark *inode_mark, struct fsnotify_mark *vfsmount_mark, u32 mask, void *data, int data_type, - const unsigned char *file_name); + const unsigned char *file_name, u32 cookie); void (*free_group_priv)(struct fsnotify_group *group); void (*freeing_mark)(struct fsnotify_mark *mark, struct fsnotify_group *group); void (*free_event)(struct fsnotify_event *event); @@ -160,7 +160,7 @@ struct fsnotify_group { struct fasync_struct *fsn_fa; /* async notification */ - struct fsnotify_event overflow_event; /* Event we queue when the + struct fsnotify_event *overflow_event; /* Event we queue when the * notification list is too * full */ diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h index 4d34dbbbad4d..7a8144fef406 100644 --- a/include/linux/gpio/consumer.h +++ b/include/linux/gpio/consumer.h @@ -4,8 +4,6 @@ #include <linux/err.h> #include <linux/kernel.h> -#ifdef CONFIG_GPIOLIB - struct device; struct gpio_chip; @@ -18,6 +16,8 @@ struct gpio_chip; */ struct gpio_desc; +#ifdef CONFIG_GPIOLIB + /* Acquire and dispose GPIOs */ struct gpio_desc *__must_check gpiod_get(struct device *dev, const char *con_id); diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index db512014e061..b826239bdce0 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -157,46 +157,6 @@ static inline int hpage_nr_pages(struct page *page) return HPAGE_PMD_NR; return 1; } -/* - * compound_trans_head() should be used instead of compound_head(), - * whenever the "page" passed as parameter could be the tail of a - * transparent hugepage that could be undergoing a - * __split_huge_page_refcount(). The page structure layout often - * changes across releases and it makes extensive use of unions. So if - * the page structure layout will change in a way that - * page->first_page gets clobbered by __split_huge_page_refcount, the - * implementation making use of smp_rmb() will be required. - * - * Currently we define compound_trans_head as compound_head, because - * page->private is in the same union with page->first_page, and - * page->private isn't clobbered. However this also means we're - * currently leaving dirt into the page->private field of anonymous - * pages resulting from a THP split, instead of setting page->private - * to zero like for every other page that has PG_private not set. But - * anonymous pages don't use page->private so this is not a problem. - */ -#if 0 -/* This will be needed if page->private will be clobbered in split_huge_page */ -static inline struct page *compound_trans_head(struct page *page) -{ - if (PageTail(page)) { - struct page *head; - head = page->first_page; - smp_rmb(); - /* - * head may be a dangling pointer. - * __split_huge_page_refcount clears PageTail before - * overwriting first_page, so if PageTail is still - * there it means the head pointer isn't dangling. - */ - if (PageTail(page)) - return head; - } - return page; -} -#else -#define compound_trans_head(page) compound_head(page) -#endif extern int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pmd_t pmd, pmd_t *pmdp); @@ -226,7 +186,6 @@ static inline int split_huge_page(struct page *page) do { } while (0) #define split_huge_page_pmd_mm(__mm, __address, __pmd) \ do { } while (0) -#define compound_trans_head(page) compound_head(page) static inline int hugepage_madvise(struct vm_area_struct *vma, unsigned long *vm_flags, int advice) { diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 15da677478dd..344883dce584 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -875,7 +875,7 @@ struct vmbus_channel_relid_released { struct vmbus_channel_initiate_contact { struct vmbus_channel_message_header header; u32 vmbus_version_requested; - u32 padding2; + u32 target_vcpu; /* The VCPU the host should respond to */ u64 interrupt_page; u64 monitor_page1; u64 monitor_page2; diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 0053adde0ed9..a2678d35b5a2 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -158,6 +158,11 @@ devm_request_irq(struct device *dev, unsigned int irq, irq_handler_t handler, devname, dev_id); } +extern int __must_check +devm_request_any_context_irq(struct device *dev, unsigned int irq, + irq_handler_t handler, unsigned long irqflags, + const char *devname, void *dev_id); + extern void devm_free_irq(struct device *dev, unsigned int irq, void *dev_id); /* diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h index e7831d203737..35e7eca4e33b 100644 --- a/include/linux/ipc_namespace.h +++ b/include/linux/ipc_namespace.h @@ -118,9 +118,7 @@ extern int mq_init_ns(struct ipc_namespace *ns); * the new maximum will handle anyone else. I may have to revisit this * in the future. */ -#define MIN_QUEUESMAX 1 #define DFLT_QUEUESMAX 256 -#define HARD_QUEUESMAX 1024 #define MIN_MSGMAX 1 #define DFLT_MSG 10U #define DFLT_MSGMAX 10 diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index 5be9f0228a3b..d267623c28cf 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -249,7 +249,8 @@ void kernfs_notify(struct kernfs_node *kn); const void *kernfs_super_ns(struct super_block *sb); struct dentry *kernfs_mount_ns(struct file_system_type *fs_type, int flags, - struct kernfs_root *root, const void *ns); + struct kernfs_root *root, bool *new_sb_created, + const void *ns); void kernfs_kill_sb(struct super_block *sb); void kernfs_init(void); @@ -317,7 +318,7 @@ static inline const void *kernfs_super_ns(struct super_block *sb) static inline struct dentry * kernfs_mount_ns(struct file_system_type *fs_type, int flags, - struct kernfs_root *root, const void *ns) + struct kernfs_root *root, bool *new_sb_created, const void *ns) { return ERR_PTR(-ENOSYS); } static inline void kernfs_kill_sb(struct super_block *sb) { } @@ -368,9 +369,9 @@ static inline int kernfs_remove_by_name(struct kernfs_node *parent, static inline struct dentry * kernfs_mount(struct file_system_type *fs_type, int flags, - struct kernfs_root *root) + struct kernfs_root *root, bool *new_sb_created) { - return kernfs_mount_ns(fs_type, flags, root, NULL); + return kernfs_mount_ns(fs_type, flags, root, new_sb_created, NULL); } #endif /* __LINUX_KERNFS_H */ diff --git a/include/linux/mfd/max8997-private.h b/include/linux/mfd/max8997-private.h index ad1ae7f345ad..78c76cd4d37b 100644 --- a/include/linux/mfd/max8997-private.h +++ b/include/linux/mfd/max8997-private.h @@ -387,7 +387,7 @@ struct max8997_dev { struct i2c_client *muic; /* slave addr 0x4a */ struct mutex iolock; - int type; + unsigned long type; struct platform_device *battery; /* battery control (not fuel gauge) */ int irq; diff --git a/include/linux/mfd/max8998-private.h b/include/linux/mfd/max8998-private.h index 4ecb24b4b863..d68ada502ff3 100644 --- a/include/linux/mfd/max8998-private.h +++ b/include/linux/mfd/max8998-private.h @@ -163,7 +163,7 @@ struct max8998_dev { int ono; u8 irq_masks_cur[MAX8998_NUM_IRQ_REGS]; u8 irq_masks_cache[MAX8998_NUM_IRQ_REGS]; - int type; + unsigned long type; bool wakeup; }; diff --git a/include/linux/mfd/tps65217.h b/include/linux/mfd/tps65217.h index a5a7f0130e96..54b5458ec084 100644 --- a/include/linux/mfd/tps65217.h +++ b/include/linux/mfd/tps65217.h @@ -252,7 +252,7 @@ struct tps65217_board { struct tps65217 { struct device *dev; struct tps65217_board *pdata; - unsigned int id; + unsigned long id; struct regulator_desc desc[TPS65217_NUM_REGULATOR]; struct regulator_dev *rdev[TPS65217_NUM_REGULATOR]; struct regmap *regmap; @@ -263,7 +263,7 @@ static inline struct tps65217 *dev_to_tps65217(struct device *dev) return dev_get_drvdata(dev); } -static inline int tps65217_chip_id(struct tps65217 *tps65217) +static inline unsigned long tps65217_chip_id(struct tps65217 *tps65217) { return tps65217->id; } diff --git a/include/linux/mlx4/cmd.h b/include/linux/mlx4/cmd.h index 79a347238168..009985628257 100644 --- a/include/linux/mlx4/cmd.h +++ b/include/linux/mlx4/cmd.h @@ -240,6 +240,13 @@ int mlx4_set_vf_vlan(struct mlx4_dev *dev, int port, int vf, u16 vlan, u8 qos); int mlx4_set_vf_spoofchk(struct mlx4_dev *dev, int port, int vf, bool setting); int mlx4_get_vf_config(struct mlx4_dev *dev, int port, int vf, struct ifla_vf_info *ivf); int mlx4_set_vf_link_state(struct mlx4_dev *dev, int port, int vf, int link_state); +/* + * mlx4_get_slave_default_vlan - + * return true if VST ( default vlan) + * if VST, will return vlan & qos (if not NULL) + */ +bool mlx4_get_slave_default_vlan(struct mlx4_dev *dev, int port, int slave, + u16 *vlan, u8 *qos); #define MLX4_COMM_GET_IF_REV(cmd_chan_ver) (u8)((cmd_chan_ver) >> 8) diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 5edd2c68274d..f211b51dc726 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -48,6 +48,9 @@ #define MSIX_LEGACY_SZ 4 #define MIN_MSIX_P_PORT 5 +#define MLX4_ROCE_MAX_GIDS 128 +#define MLX4_ROCE_PF_GIDS 16 + enum { MLX4_FLAG_MSI_X = 1 << 0, MLX4_FLAG_OLD_PORT_CMDS = 1 << 1, @@ -629,7 +632,8 @@ struct mlx4_eth_av { u8 hop_limit; __be32 sl_tclass_flowlabel; u8 dgid[16]; - u32 reserved4[2]; + u8 s_mac[6]; + u8 reserved4[2]; __be16 vlan; u8 mac[ETH_ALEN]; }; @@ -1183,6 +1187,11 @@ int set_and_calc_slave_port_state(struct mlx4_dev *dev, int slave, u8 port, int void mlx4_put_slave_node_guid(struct mlx4_dev *dev, int slave, __be64 guid); __be64 mlx4_get_slave_node_guid(struct mlx4_dev *dev, int slave); +int mlx4_get_slave_from_roce_gid(struct mlx4_dev *dev, int port, u8 *gid, + int *slave_id); +int mlx4_get_roce_gid_from_slave(struct mlx4_dev *dev, int port, int slave_id, + u8 *gid); + int mlx4_FLOW_STEERING_IB_UC_QP_RANGE(struct mlx4_dev *dev, u32 min_range_qpn, u32 max_range_qpn); diff --git a/include/linux/mlx4/driver.h b/include/linux/mlx4/driver.h index c257e1b211be..022055c8fb26 100644 --- a/include/linux/mlx4/driver.h +++ b/include/linux/mlx4/driver.h @@ -64,4 +64,16 @@ void mlx4_unregister_interface(struct mlx4_interface *intf); void *mlx4_get_protocol_dev(struct mlx4_dev *dev, enum mlx4_protocol proto, int port); +static inline u64 mlx4_mac_to_u64(u8 *addr) +{ + u64 mac = 0; + int i; + + for (i = 0; i < ETH_ALEN; i++) { + mac <<= 8; + mac |= addr[i]; + } + return mac; +} + #endif /* MLX4_DRIVER_H */ diff --git a/include/linux/mlx4/qp.h b/include/linux/mlx4/qp.h index 59f8ba84568b..b66e7610d4ee 100644 --- a/include/linux/mlx4/qp.h +++ b/include/linux/mlx4/qp.h @@ -270,9 +270,14 @@ enum { struct mlx4_wqe_ctrl_seg { __be32 owner_opcode; - __be16 vlan_tag; - u8 ins_vlan; - u8 fence_size; + union { + struct { + __be16 vlan_tag; + u8 ins_vlan; + u8 fence_size; + }; + __be32 bf_qpn; + }; /* * High 24 bits are SRC remote buffer; low 8 bits are flags: * [7] SO (strong ordering) diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 554548cd3dd4..130bc8d77fa5 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -38,8 +38,10 @@ #include <linux/pci.h> #include <linux/spinlock_types.h> #include <linux/semaphore.h> +#include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/radix-tree.h> + #include <linux/mlx5/device.h> #include <linux/mlx5/doorbell.h> @@ -227,6 +229,7 @@ struct mlx5_uuar_info { * protect uuar allocation data structs */ struct mutex lock; + u32 ver; }; struct mlx5_bf { diff --git a/include/linux/mm.h b/include/linux/mm.h index f28f46eade6a..c1b7414c7bef 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -175,7 +175,7 @@ extern unsigned int kobjsize(const void *objp); * Special vmas that are non-mergable, non-mlock()able. * Note: mm/huge_memory.c VM_NO_THP depends on this definition. */ -#define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_PFNMAP) +#define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_PFNMAP | VM_MIXEDMAP) /* * mapping from the currently active vm_flags protection bits (the @@ -399,8 +399,18 @@ static inline void compound_unlock_irqrestore(struct page *page, static inline struct page *compound_head(struct page *page) { - if (unlikely(PageTail(page))) - return page->first_page; + if (unlikely(PageTail(page))) { + struct page *head = page->first_page; + + /* + * page->first_page may be a dangling pointer to an old + * compound page, so recheck that it is still a tail + * page before returning. + */ + smp_rmb(); + if (likely(PageTail(page))) + return head; + } return page; } @@ -757,7 +767,7 @@ static inline bool __cpupid_match_pid(pid_t task_pid, int cpupid) #ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS static inline int page_cpupid_xchg_last(struct page *page, int cpupid) { - return xchg(&page->_last_cpupid, cpupid); + return xchg(&page->_last_cpupid, cpupid & LAST_CPUPID_MASK); } static inline int page_cpupid_last(struct page *page) @@ -766,7 +776,7 @@ static inline int page_cpupid_last(struct page *page) } static inline void page_cpupid_reset_last(struct page *page) { - page->_last_cpupid = -1; + page->_last_cpupid = -1 & LAST_CPUPID_MASK; } #else static inline int page_cpupid_last(struct page *page) diff --git a/include/linux/mpls.h b/include/linux/mpls.h new file mode 100644 index 000000000000..9999145bc190 --- /dev/null +++ b/include/linux/mpls.h @@ -0,0 +1,6 @@ +#ifndef _LINUX_MPLS_H +#define _LINUX_MPLS_H + +#include <uapi/linux/mpls.h> + +#endif /* _LINUX_MPLS_H */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 440a02ee6f92..b8d8c805fd75 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -752,6 +752,9 @@ struct netdev_phys_port_id { unsigned char id_len; }; +typedef u16 (*select_queue_fallback_t)(struct net_device *dev, + struct sk_buff *skb); + /* * This structure defines the management hooks for network devices. * The following hooks can be defined; unless noted otherwise, they are @@ -783,7 +786,7 @@ struct netdev_phys_port_id { * Required can not be NULL. * * u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb, - * void *accel_priv); + * void *accel_priv, select_queue_fallback_t fallback); * Called to decide which queue to when device supports multiple * transmit queues. * @@ -1005,7 +1008,8 @@ struct net_device_ops { struct net_device *dev); u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb, - void *accel_priv); + void *accel_priv, + select_queue_fallback_t fallback); void (*ndo_change_rx_flags)(struct net_device *dev, int flags); void (*ndo_set_rx_mode)(struct net_device *dev); @@ -1143,6 +1147,89 @@ struct net_device_ops { void *priv); }; +/** + * enum net_device_priv_flags - &struct net_device priv_flags + * + * These are the &struct net_device, they are only set internally + * by drivers and used in the kernel. These flags are invisible to + * userspace, this means that the order of these flags can change + * during any kernel release. + * + * You should have a pretty good reason to be extending these flags. + * + * @IFF_802_1Q_VLAN: 802.1Q VLAN device + * @IFF_EBRIDGE: Ethernet bridging device + * @IFF_SLAVE_INACTIVE: bonding slave not the curr. active + * @IFF_MASTER_8023AD: bonding master, 802.3ad + * @IFF_MASTER_ALB: bonding master, balance-alb + * @IFF_BONDING: bonding master or slave + * @IFF_SLAVE_NEEDARP: need ARPs for validation + * @IFF_ISATAP: ISATAP interface (RFC4214) + * @IFF_MASTER_ARPMON: bonding master, ARP mon in use + * @IFF_WAN_HDLC: WAN HDLC device + * @IFF_XMIT_DST_RELEASE: dev_hard_start_xmit() is allowed to + * release skb->dst + * @IFF_DONT_BRIDGE: disallow bridging this ether dev + * @IFF_DISABLE_NETPOLL: disable netpoll at run-time + * @IFF_MACVLAN_PORT: device used as macvlan port + * @IFF_BRIDGE_PORT: device used as bridge port + * @IFF_OVS_DATAPATH: device used as Open vSwitch datapath port + * @IFF_TX_SKB_SHARING: The interface supports sharing skbs on transmit + * @IFF_UNICAST_FLT: Supports unicast filtering + * @IFF_TEAM_PORT: device used as team port + * @IFF_SUPP_NOFCS: device supports sending custom FCS + * @IFF_LIVE_ADDR_CHANGE: device supports hardware address + * change when it's running + * @IFF_MACVLAN: Macvlan device + */ +enum netdev_priv_flags { + IFF_802_1Q_VLAN = 1<<0, + IFF_EBRIDGE = 1<<1, + IFF_SLAVE_INACTIVE = 1<<2, + IFF_MASTER_8023AD = 1<<3, + IFF_MASTER_ALB = 1<<4, + IFF_BONDING = 1<<5, + IFF_SLAVE_NEEDARP = 1<<6, + IFF_ISATAP = 1<<7, + IFF_MASTER_ARPMON = 1<<8, + IFF_WAN_HDLC = 1<<9, + IFF_XMIT_DST_RELEASE = 1<<10, + IFF_DONT_BRIDGE = 1<<11, + IFF_DISABLE_NETPOLL = 1<<12, + IFF_MACVLAN_PORT = 1<<13, + IFF_BRIDGE_PORT = 1<<14, + IFF_OVS_DATAPATH = 1<<15, + IFF_TX_SKB_SHARING = 1<<16, + IFF_UNICAST_FLT = 1<<17, + IFF_TEAM_PORT = 1<<18, + IFF_SUPP_NOFCS = 1<<19, + IFF_LIVE_ADDR_CHANGE = 1<<20, + IFF_MACVLAN = 1<<21, +}; + +#define IFF_802_1Q_VLAN IFF_802_1Q_VLAN +#define IFF_EBRIDGE IFF_EBRIDGE +#define IFF_SLAVE_INACTIVE IFF_SLAVE_INACTIVE +#define IFF_MASTER_8023AD IFF_MASTER_8023AD +#define IFF_MASTER_ALB IFF_MASTER_ALB +#define IFF_BONDING IFF_BONDING +#define IFF_SLAVE_NEEDARP IFF_SLAVE_NEEDARP +#define IFF_ISATAP IFF_ISATAP +#define IFF_MASTER_ARPMON IFF_MASTER_ARPMON +#define IFF_WAN_HDLC IFF_WAN_HDLC +#define IFF_XMIT_DST_RELEASE IFF_XMIT_DST_RELEASE +#define IFF_DONT_BRIDGE IFF_DONT_BRIDGE +#define IFF_DISABLE_NETPOLL IFF_DISABLE_NETPOLL +#define IFF_MACVLAN_PORT IFF_MACVLAN_PORT +#define IFF_BRIDGE_PORT IFF_BRIDGE_PORT +#define IFF_OVS_DATAPATH IFF_OVS_DATAPATH +#define IFF_TX_SKB_SHARING IFF_TX_SKB_SHARING +#define IFF_UNICAST_FLT IFF_UNICAST_FLT +#define IFF_TEAM_PORT IFF_TEAM_PORT +#define IFF_SUPP_NOFCS IFF_SUPP_NOFCS +#define IFF_LIVE_ADDR_CHANGE IFF_LIVE_ADDR_CHANGE +#define IFF_MACVLAN IFF_MACVLAN + /* * The DEVICE structure. * Actually, this whole structure is a big mistake. It mixes I/O @@ -1275,6 +1362,10 @@ struct net_device { * that share the same link * layer address */ + unsigned short dev_port; /* Used to differentiate + * devices that share the same + * function + */ spinlock_t addr_list_lock; struct netdev_hw_addr_list uc; /* Unicast mac addresses */ struct netdev_hw_addr_list mc; /* Multicast mac addresses */ @@ -1312,13 +1403,7 @@ struct net_device { /* * Cache lines mostly used on receive path (including eth_type_trans()) */ - unsigned long last_rx; /* Time of last Rx - * This should not be set in - * drivers, unless really needed, - * because network stack (bonding) - * use it if/when necessary, to - * avoid dirtying this cache line. - */ + unsigned long last_rx; /* Time of last Rx */ /* Interface address info used in eth_type_trans() */ unsigned char *dev_addr; /* hw address, (before bcast @@ -1551,7 +1636,6 @@ static inline void netdev_for_each_tx_queue(struct net_device *dev, struct netdev_queue *netdev_pick_tx(struct net_device *dev, struct sk_buff *skb, void *accel_priv); -u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb); /* * Net namespace inlines @@ -1726,6 +1810,20 @@ struct pcpu_sw_netstats { struct u64_stats_sync syncp; }; +#define netdev_alloc_pcpu_stats(type) \ +({ \ + typeof(type) __percpu *pcpu_stats = alloc_percpu(type); \ + if (pcpu_stats) { \ + int i; \ + for_each_possible_cpu(i) { \ + typeof(type) *stat; \ + stat = per_cpu_ptr(pcpu_stats, i); \ + u64_stats_init(&stat->syncp); \ + } \ + } \ + pcpu_stats; \ +}) + #include <linux/notifier.h> /* netdevice notifier chain. Please remember to update the rtnetlink @@ -2276,6 +2374,26 @@ static inline void netdev_reset_queue(struct net_device *dev_queue) } /** + * netdev_cap_txqueue - check if selected tx queue exceeds device queues + * @dev: network device + * @queue_index: given tx queue index + * + * Returns 0 if given tx queue index >= number of device tx queues, + * otherwise returns the originally passed tx queue index. + */ +static inline u16 netdev_cap_txqueue(struct net_device *dev, u16 queue_index) +{ + if (unlikely(queue_index >= dev->real_num_tx_queues)) { + net_warn_ratelimited("%s selects TX queue %d, but real number of TX queues is %d\n", + dev->name, queue_index, + dev->real_num_tx_queues); + return 0; + } + + return queue_index; +} + +/** * netif_running - test if up * @dev: network device * @@ -3068,7 +3186,12 @@ 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 netif_skb_features(struct sk_buff *skb); +netdev_features_t netif_skb_dev_features(struct sk_buff *skb, + const struct net_device *dev); +static inline netdev_features_t netif_skb_features(struct sk_buff *skb) +{ + return netif_skb_dev_features(skb, skb->dev); +} static inline bool net_gso_ok(netdev_features_t features, int gso_type) { diff --git a/include/linux/nl802154.h b/include/linux/nl802154.h index fd4f2d1cdf6c..e110b8c266f5 100644 --- a/include/linux/nl802154.h +++ b/include/linux/nl802154.h @@ -70,6 +70,16 @@ enum { IEEE802154_ATTR_PHY_NAME, IEEE802154_ATTR_DEV_TYPE, + IEEE802154_ATTR_TXPOWER, + IEEE802154_ATTR_LBT_ENABLED, + IEEE802154_ATTR_CCA_MODE, + IEEE802154_ATTR_CCA_ED_LEVEL, + IEEE802154_ATTR_CSMA_RETRIES, + IEEE802154_ATTR_CSMA_MIN_BE, + IEEE802154_ATTR_CSMA_MAX_BE, + + IEEE802154_ATTR_FRAME_RETRIES, + __IEEE802154_ATTR_MAX, }; @@ -122,6 +132,8 @@ enum { IEEE802154_ADD_IFACE, IEEE802154_DEL_IFACE, + IEEE802154_SET_PHYPARAMS, + __IEEE802154_CMD_MAX, }; diff --git a/include/linux/of.h b/include/linux/of.h index 70c64ba17fa5..435cb995904d 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -169,35 +169,15 @@ static inline const char *of_node_full_name(const struct device_node *np) extern struct device_node *of_find_node_by_name(struct device_node *from, const char *name); -#define for_each_node_by_name(dn, name) \ - for (dn = of_find_node_by_name(NULL, name); dn; \ - dn = of_find_node_by_name(dn, name)) extern struct device_node *of_find_node_by_type(struct device_node *from, const char *type); -#define for_each_node_by_type(dn, type) \ - for (dn = of_find_node_by_type(NULL, type); dn; \ - dn = of_find_node_by_type(dn, type)) extern struct device_node *of_find_compatible_node(struct device_node *from, const char *type, const char *compat); -#define for_each_compatible_node(dn, type, compatible) \ - for (dn = of_find_compatible_node(NULL, type, compatible); dn; \ - dn = of_find_compatible_node(dn, type, compatible)) extern struct device_node *of_find_matching_node_and_match( struct device_node *from, const struct of_device_id *matches, const struct of_device_id **match); -static inline struct device_node *of_find_matching_node( - struct device_node *from, - const struct of_device_id *matches) -{ - return of_find_matching_node_and_match(from, matches, NULL); -} -#define for_each_matching_node(dn, matches) \ - for (dn = of_find_matching_node(NULL, matches); dn; \ - dn = of_find_matching_node(dn, matches)) -#define for_each_matching_node_and_match(dn, matches, match) \ - for (dn = of_find_matching_node_and_match(NULL, matches, match); \ - dn; dn = of_find_matching_node_and_match(dn, matches, match)) + extern struct device_node *of_find_node_by_path(const char *path); extern struct device_node *of_find_node_by_phandle(phandle handle); extern struct device_node *of_get_parent(const struct device_node *node); @@ -209,43 +189,11 @@ extern struct device_node *of_get_next_available_child( extern struct device_node *of_get_child_by_name(const struct device_node *node, const char *name); -#define for_each_child_of_node(parent, child) \ - for (child = of_get_next_child(parent, NULL); child != NULL; \ - child = of_get_next_child(parent, child)) - -#define for_each_available_child_of_node(parent, child) \ - for (child = of_get_next_available_child(parent, NULL); child != NULL; \ - child = of_get_next_available_child(parent, child)) - -static inline int of_get_child_count(const struct device_node *np) -{ - struct device_node *child; - int num = 0; - - for_each_child_of_node(np, child) - num++; - - return num; -} - -static inline int of_get_available_child_count(const struct device_node *np) -{ - struct device_node *child; - int num = 0; - - for_each_available_child_of_node(np, child) - num++; - - return num; -} /* cache lookup */ extern struct device_node *of_find_next_cache_node(const struct device_node *); extern struct device_node *of_find_node_with_property( struct device_node *from, const char *prop_name); -#define for_each_node_with_property(dn, prop_name) \ - for (dn = of_find_node_with_property(NULL, prop_name); dn; \ - dn = of_find_node_with_property(dn, prop_name)) extern struct property *of_find_property(const struct device_node *np, const char *name, @@ -367,42 +315,53 @@ static inline struct device_node *of_find_node_by_name(struct device_node *from, return NULL; } -static inline struct device_node *of_get_parent(const struct device_node *node) +static inline struct device_node *of_find_node_by_type(struct device_node *from, + const char *type) { return NULL; } -static inline bool of_have_populated_dt(void) +static inline struct device_node *of_find_matching_node_and_match( + struct device_node *from, + const struct of_device_id *matches, + const struct of_device_id **match) { - return false; + return NULL; } -/* Kill an unused variable warning on a device_node pointer */ -static inline void __of_use_dn(const struct device_node *np) +static inline struct device_node *of_get_parent(const struct device_node *node) { + return NULL; } -#define for_each_child_of_node(parent, child) \ - while (__of_use_dn(parent), __of_use_dn(child), 0) +static inline struct device_node *of_get_next_child( + const struct device_node *node, struct device_node *prev) +{ + return NULL; +} -#define for_each_available_child_of_node(parent, child) \ - while (0) +static inline struct device_node *of_get_next_available_child( + const struct device_node *node, struct device_node *prev) +{ + return NULL; +} -static inline struct device_node *of_get_child_by_name( - const struct device_node *node, - const char *name) +static inline struct device_node *of_find_node_with_property( + struct device_node *from, const char *prop_name) { return NULL; } -static inline int of_get_child_count(const struct device_node *np) +static inline bool of_have_populated_dt(void) { - return 0; + return false; } -static inline int of_get_available_child_count(const struct device_node *np) +static inline struct device_node *of_get_child_by_name( + const struct device_node *node, + const char *name) { - return 0; + return NULL; } static inline int of_device_is_compatible(const struct device_node *device, @@ -569,6 +528,13 @@ extern int of_node_to_nid(struct device_node *np); static inline int of_node_to_nid(struct device_node *device) { return 0; } #endif +static inline struct device_node *of_find_matching_node( + struct device_node *from, + const struct of_device_id *matches) +{ + return of_find_matching_node_and_match(from, matches, NULL); +} + /** * of_property_read_bool - Findfrom a property * @np: device node from which the property value is to be read. @@ -618,6 +584,55 @@ static inline int of_property_read_u32(const struct device_node *np, s; \ s = of_prop_next_string(prop, s)) +#define for_each_node_by_name(dn, name) \ + for (dn = of_find_node_by_name(NULL, name); dn; \ + dn = of_find_node_by_name(dn, name)) +#define for_each_node_by_type(dn, type) \ + for (dn = of_find_node_by_type(NULL, type); dn; \ + dn = of_find_node_by_type(dn, type)) +#define for_each_compatible_node(dn, type, compatible) \ + for (dn = of_find_compatible_node(NULL, type, compatible); dn; \ + dn = of_find_compatible_node(dn, type, compatible)) +#define for_each_matching_node(dn, matches) \ + for (dn = of_find_matching_node(NULL, matches); dn; \ + dn = of_find_matching_node(dn, matches)) +#define for_each_matching_node_and_match(dn, matches, match) \ + for (dn = of_find_matching_node_and_match(NULL, matches, match); \ + dn; dn = of_find_matching_node_and_match(dn, matches, match)) + +#define for_each_child_of_node(parent, child) \ + for (child = of_get_next_child(parent, NULL); child != NULL; \ + child = of_get_next_child(parent, child)) +#define for_each_available_child_of_node(parent, child) \ + for (child = of_get_next_available_child(parent, NULL); child != NULL; \ + child = of_get_next_available_child(parent, child)) + +#define for_each_node_with_property(dn, prop_name) \ + for (dn = of_find_node_with_property(NULL, prop_name); dn; \ + dn = of_find_node_with_property(dn, prop_name)) + +static inline int of_get_child_count(const struct device_node *np) +{ + struct device_node *child; + int num = 0; + + for_each_child_of_node(np, child) + num++; + + return num; +} + +static inline int of_get_available_child_count(const struct device_node *np) +{ + struct device_node *child; + int num = 0; + + for_each_available_child_of_node(np, child) + num++; + + return num; +} + #if defined(CONFIG_PROC_FS) && defined(CONFIG_PROC_DEVICETREE) extern void proc_device_tree_add_node(struct device_node *, struct proc_dir_entry *); extern void proc_device_tree_add_prop(struct proc_dir_entry *pde, struct property *prop); diff --git a/include/linux/of_device.h b/include/linux/of_device.h index 8d7dd6768cb7..ef370210ffb2 100644 --- a/include/linux/of_device.h +++ b/include/linux/of_device.h @@ -78,11 +78,13 @@ static inline int of_device_uevent_modalias(struct device *dev, static inline void of_device_node_put(struct device *dev) { } -static inline const struct of_device_id *of_match_device( +static inline const struct of_device_id *__of_match_device( const struct of_device_id *matches, const struct device *dev) { return NULL; } +#define of_match_device(matches, dev) \ + __of_match_device(of_match_ptr(matches), (dev)) static inline struct device_node *of_cpu_device_node_get(int cpu) { diff --git a/include/linux/pci.h b/include/linux/pci.h index fb57c892b214..33aa2caf0f0c 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1169,8 +1169,23 @@ void msi_remove_pci_irq_vectors(struct pci_dev *dev); void pci_restore_msi_state(struct pci_dev *dev); int pci_msi_enabled(void); int pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec); +static inline int pci_enable_msi_exact(struct pci_dev *dev, int nvec) +{ + int rc = pci_enable_msi_range(dev, nvec, nvec); + if (rc < 0) + return rc; + return 0; +} int pci_enable_msix_range(struct pci_dev *dev, struct msix_entry *entries, int minvec, int maxvec); +static inline int pci_enable_msix_exact(struct pci_dev *dev, + struct msix_entry *entries, int nvec) +{ + int rc = pci_enable_msix_range(dev, entries, nvec, nvec); + if (rc < 0) + return rc; + return 0; +} #else static inline int pci_msi_vec_count(struct pci_dev *dev) { return -ENOSYS; } static inline int pci_enable_msi_block(struct pci_dev *dev, int nvec) @@ -1189,9 +1204,14 @@ static inline int pci_msi_enabled(void) { return 0; } static inline int pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec) { return -ENOSYS; } +static inline int pci_enable_msi_exact(struct pci_dev *dev, int nvec) +{ return -ENOSYS; } static inline int pci_enable_msix_range(struct pci_dev *dev, struct msix_entry *entries, int minvec, int maxvec) { return -ENOSYS; } +static inline int pci_enable_msix_exact(struct pci_dev *dev, + struct msix_entry *entries, int nvec) +{ return -ENOSYS; } #endif #ifdef CONFIG_PCIEPORTBUS diff --git a/include/linux/phy.h b/include/linux/phy.h index 565188ca328f..24126c4b27b5 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -74,8 +74,53 @@ typedef enum { PHY_INTERFACE_MODE_RTBI, PHY_INTERFACE_MODE_SMII, PHY_INTERFACE_MODE_XGMII, + PHY_INTERFACE_MODE_MOCA, + PHY_INTERFACE_MODE_MAX, } phy_interface_t; +/** + * It maps 'enum phy_interface_t' found in include/linux/phy.h + * into the device tree binding of 'phy-mode', so that Ethernet + * device driver can get phy interface from device tree. + */ +static inline const char *phy_modes(phy_interface_t interface) +{ + switch (interface) { + case PHY_INTERFACE_MODE_NA: + return ""; + case PHY_INTERFACE_MODE_MII: + return "mii"; + case PHY_INTERFACE_MODE_GMII: + return "gmii"; + case PHY_INTERFACE_MODE_SGMII: + return "sgmii"; + case PHY_INTERFACE_MODE_TBI: + return "tbi"; + case PHY_INTERFACE_MODE_REVMII: + return "rev-mii"; + case PHY_INTERFACE_MODE_RMII: + return "rmii"; + case PHY_INTERFACE_MODE_RGMII: + return "rgmii"; + case PHY_INTERFACE_MODE_RGMII_ID: + return "rgmii-id"; + case PHY_INTERFACE_MODE_RGMII_RXID: + return "rgmii-rxid"; + case PHY_INTERFACE_MODE_RGMII_TXID: + return "rgmii-txid"; + case PHY_INTERFACE_MODE_RTBI: + return "rtbi"; + case PHY_INTERFACE_MODE_SMII: + return "smii"; + case PHY_INTERFACE_MODE_XGMII: + return "xgmii"; + case PHY_INTERFACE_MODE_MOCA: + return "moca"; + default: + return "unknown"; + } +} + #define PHY_INIT_TIMEOUT 100000 #define PHY_STATE_TIME 1 @@ -308,6 +353,7 @@ struct phy_device { struct phy_c45_device_ids c45_ids; bool is_c45; bool is_internal; + bool has_fixups; enum phy_state state; @@ -394,6 +440,11 @@ struct phy_driver { u32 flags; /* + * Called to issue a PHY software reset + */ + int (*soft_reset)(struct phy_device *phydev); + + /* * Called to initialize the PHY, * including after a reset */ @@ -417,6 +468,9 @@ struct phy_driver { */ int (*config_aneg)(struct phy_device *phydev); + /* Determines the auto negotiation result */ + int (*aneg_done)(struct phy_device *phydev); + /* Determines the negotiated speed and duplex */ int (*read_status)(struct phy_device *phydev); @@ -612,10 +666,12 @@ static inline int phy_read_status(struct phy_device *phydev) int genphy_setup_forced(struct phy_device *phydev); int genphy_restart_aneg(struct phy_device *phydev); int genphy_config_aneg(struct phy_device *phydev); +int genphy_aneg_done(struct phy_device *phydev); int genphy_update_link(struct phy_device *phydev); int genphy_read_status(struct phy_device *phydev); int genphy_suspend(struct phy_device *phydev); int genphy_resume(struct phy_device *phydev); +int genphy_soft_reset(struct phy_device *phydev); void phy_driver_unregister(struct phy_driver *drv); void phy_drivers_unregister(struct phy_driver *drv, int n); int phy_driver_register(struct phy_driver *new_driver); diff --git a/include/linux/phy/phy.h b/include/linux/phy/phy.h index e273e5ac19c9..3f83459dbb20 100644 --- a/include/linux/phy/phy.h +++ b/include/linux/phy/phy.h @@ -146,7 +146,9 @@ static inline void phy_set_bus_width(struct phy *phy, int bus_width) phy->attrs.bus_width = bus_width; } struct phy *phy_get(struct device *dev, const char *string); +struct phy *phy_optional_get(struct device *dev, const char *string); struct phy *devm_phy_get(struct device *dev, const char *string); +struct phy *devm_phy_optional_get(struct device *dev, const char *string); void phy_put(struct phy *phy); void devm_phy_put(struct device *dev, struct phy *phy); struct phy *of_phy_simple_xlate(struct device *dev, @@ -232,11 +234,23 @@ static inline struct phy *phy_get(struct device *dev, const char *string) return ERR_PTR(-ENOSYS); } +static inline struct phy *phy_optional_get(struct device *dev, + const char *string) +{ + return ERR_PTR(-ENOSYS); +} + static inline struct phy *devm_phy_get(struct device *dev, const char *string) { return ERR_PTR(-ENOSYS); } +static inline struct phy *devm_phy_optional_get(struct device *dev, + const char *string) +{ + return ERR_PTR(-ENOSYS); +} + static inline void phy_put(struct phy *phy) { } diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index f589c9af8cbf..03db95ab8a8c 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -32,6 +32,7 @@ #include <linux/hrtimer.h> #include <linux/dma-mapping.h> #include <linux/netdev_features.h> +#include <linux/sched.h> #include <net/flow_keys.h> /* A. Checksumming of received packets by device. @@ -356,11 +357,62 @@ typedef unsigned int sk_buff_data_t; typedef unsigned char *sk_buff_data_t; #endif +/** + * struct skb_mstamp - multi resolution time stamps + * @stamp_us: timestamp in us resolution + * @stamp_jiffies: timestamp in jiffies + */ +struct skb_mstamp { + union { + u64 v64; + struct { + u32 stamp_us; + u32 stamp_jiffies; + }; + }; +}; + +/** + * skb_mstamp_get - get current timestamp + * @cl: place to store timestamps + */ +static inline void skb_mstamp_get(struct skb_mstamp *cl) +{ + u64 val = local_clock(); + + do_div(val, NSEC_PER_USEC); + cl->stamp_us = (u32)val; + cl->stamp_jiffies = (u32)jiffies; +} + +/** + * skb_mstamp_delta - compute the difference in usec between two skb_mstamp + * @t1: pointer to newest sample + * @t0: pointer to oldest sample + */ +static inline u32 skb_mstamp_us_delta(const struct skb_mstamp *t1, + const struct skb_mstamp *t0) +{ + s32 delta_us = t1->stamp_us - t0->stamp_us; + u32 delta_jiffies = t1->stamp_jiffies - t0->stamp_jiffies; + + /* If delta_us is negative, this might be because interval is too big, + * or local_clock() drift is too big : fallback using jiffies. + */ + if (delta_us <= 0 || + delta_jiffies >= (INT_MAX / (USEC_PER_SEC / HZ))) + + delta_us = jiffies_to_usecs(delta_jiffies); + + return delta_us; +} + + /** * struct sk_buff - socket buffer * @next: Next buffer in list * @prev: Previous buffer in list - * @tstamp: Time we arrived + * @tstamp: Time we arrived/left * @sk: Socket we are owned by * @dev: Device we arrived on/are leaving by * @cb: Control buffer. Free for use by every layer. Put private vars here @@ -429,7 +481,10 @@ struct sk_buff { struct sk_buff *next; struct sk_buff *prev; - ktime_t tstamp; + union { + ktime_t tstamp; + struct skb_mstamp skb_mstamp; + }; struct sock *sk; struct net_device *dev; @@ -691,6 +746,8 @@ struct sk_buff *skb_realloc_headroom(struct sk_buff *skb, unsigned int headroom); struct sk_buff *skb_copy_expand(const struct sk_buff *skb, int newheadroom, int newtailroom, gfp_t priority); +int skb_to_sgvec_nomark(struct sk_buff *skb, struct scatterlist *sg, + int offset, int len); int skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len); int skb_cow_data(struct sk_buff *skb, int tailbits, struct sk_buff **trailer); @@ -2725,7 +2782,7 @@ static inline void nf_reset(struct sk_buff *skb) static inline void nf_reset_trace(struct sk_buff *skb) { -#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) +#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || defined(CONFIG_NF_TABLES) skb->nf_trace = 0; #endif } @@ -2742,6 +2799,9 @@ static inline void __nf_copy(struct sk_buff *dst, const struct sk_buff *src) dst->nf_bridge = src->nf_bridge; nf_bridge_get(src->nf_bridge); #endif +#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || defined(CONFIG_NF_TABLES) + dst->nf_trace = src->nf_trace; +#endif } static inline void nf_copy(struct sk_buff *dst, const struct sk_buff *src) @@ -2916,5 +2976,22 @@ static inline bool skb_head_is_locked(const struct sk_buff *skb) { return !skb->head_frag || skb_cloned(skb); } + +/** + * skb_gso_network_seglen - Return length of individual segments of a gso packet + * + * @skb: GSO skb + * + * skb_gso_network_seglen is used to determine the real size of the + * individual segments, including Layer3 (IP, IPv6) and L4 headers (TCP/UDP). + * + * The MAC/L2 header is not accounted for. + */ +static inline unsigned int skb_gso_network_seglen(const struct sk_buff *skb) +{ + unsigned int hdr_len = skb_transport_header(skb) - + skb_network_header(skb); + return hdr_len + skb_gso_transport_seglen(skb); +} #endif /* __KERNEL__ */ #endif /* _LINUX_SKBUFF_H */ diff --git a/include/linux/smp.h b/include/linux/smp.h index 3834f43f9993..6ae004e437ea 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -188,6 +188,9 @@ static inline void kick_all_cpus_sync(void) { } */ extern void arch_disable_smp_support(void); +extern void arch_enable_nonboot_cpus_begin(void); +extern void arch_enable_nonboot_cpus_end(void); + void smp_setup_processor_id(void); #endif /* __LINUX_SMP_H */ diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index a1d4ca290862..4203c66d8803 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -273,7 +273,7 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv) * message while queuing transfers that arrive in the meantime. When the * driver is finished with this message, it must call * spi_finalize_current_message() so the subsystem can issue the next - * transfer + * message * @unprepare_transfer_hardware: there are currently no more messages on the * queue so the subsystem notifies the driver that it may relax the * hardware by issuing this call @@ -287,7 +287,10 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv) * - return 1 if the transfer is still in progress. When * the driver is finished with this transfer it must * call spi_finalize_current_transfer() so the subsystem - * can issue the next transfer + * can issue the next transfer. Note: transfer_one and + * transfer_one_message are mutually exclusive; when both + * are set, the generic subsystem does not call your + * transfer_one callback. * @unprepare_message: undo any work done by prepare_message(). * @cs_gpios: Array of GPIOs to use as chip select lines; one per CS * number. Any individual value may be -ENOENT for CS lines that diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 40ed9e9a77e5..a747a77ea584 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -281,13 +281,15 @@ asmlinkage long sys_sched_setscheduler(pid_t pid, int policy, asmlinkage long sys_sched_setparam(pid_t pid, struct sched_param __user *param); asmlinkage long sys_sched_setattr(pid_t pid, - struct sched_attr __user *attr); + struct sched_attr __user *attr, + unsigned int flags); asmlinkage long sys_sched_getscheduler(pid_t pid); asmlinkage long sys_sched_getparam(pid_t pid, struct sched_param __user *param); asmlinkage long sys_sched_getattr(pid_t pid, struct sched_attr __user *attr, - unsigned int size); + unsigned int size, + unsigned int flags); asmlinkage long sys_sched_setaffinity(pid_t pid, unsigned int len, unsigned long __user *user_mask_ptr); asmlinkage long sys_sched_getaffinity(pid_t pid, unsigned int len, diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 4ad0706d40eb..239946868142 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -201,10 +201,10 @@ struct tcp_sock { u32 tlp_high_seq; /* snd_nxt at the time of TLP retransmit. */ /* RTT measurement */ - u32 srtt; /* smoothed round trip time << 3 */ - u32 mdev; /* medium deviation */ - u32 mdev_max; /* maximal mdev for the last rtt period */ - u32 rttvar; /* smoothed mdev_max */ + u32 srtt_us; /* smoothed round trip time << 3 in usecs */ + u32 mdev_us; /* medium deviation */ + u32 mdev_max_us; /* maximal mdev for the last rtt period */ + u32 rttvar_us; /* smoothed mdev_max */ u32 rtt_seq; /* sequence number to update rttvar */ u32 packets_out; /* Packets which are "in flight" */ diff --git a/include/linux/usb.h b/include/linux/usb.h index c716da18c668..7f6eb859873e 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -1265,8 +1265,6 @@ typedef void (*usb_complete_t)(struct urb *); * @sg: scatter gather buffer list, the buffer size of each element in * the list (except the last) must be divisible by the endpoint's * max packet size if no_sg_constraint isn't set in 'struct usb_bus' - * (FIXME: scatter-gather under xHCI is broken for periodic transfers. - * Do not use urb->sg for interrupt endpoints for now, only bulk.) * @num_mapped_sgs: (internal) number of mapped sg entries * @num_sgs: number of entries in the sg list * @transfer_buffer_length: How big is transfer_buffer. The transfer may diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 594521ba0d43..704f4f652d0a 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -419,10 +419,7 @@ __alloc_workqueue_key(const char *fmt, unsigned int flags, int max_active, static struct lock_class_key __key; \ const char *__lock_name; \ \ - if (__builtin_constant_p(fmt)) \ - __lock_name = (fmt); \ - else \ - __lock_name = #fmt; \ + __lock_name = #fmt#args; \ \ __alloc_workqueue_key((fmt), (flags), (max_active), \ &__key, __lock_name, ##args); \ diff --git a/include/linux/writeback.h b/include/linux/writeback.h index fc0e4320aa6d..021b8a319b9e 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -97,7 +97,7 @@ void writeback_inodes_sb_nr(struct super_block *, unsigned long nr, int try_to_writeback_inodes_sb(struct super_block *, enum wb_reason reason); int try_to_writeback_inodes_sb_nr(struct super_block *, unsigned long nr, enum wb_reason reason); -void sync_inodes_sb(struct super_block *sb, unsigned long older_than_this); +void sync_inodes_sb(struct super_block *); void wakeup_flusher_threads(long nr_pages, enum wb_reason reason); void inode_wait_for_writeback(struct inode *inode); diff --git a/net/ieee802154/6lowpan.h b/include/net/6lowpan.h index 2b835db3bda8..f7d372b7d4ff 100644 --- a/net/ieee802154/6lowpan.h +++ b/include/net/6lowpan.h @@ -53,6 +53,8 @@ #ifndef __6LOWPAN_H__ #define __6LOWPAN_H__ +#include <net/ipv6.h> + #define UIP_802154_SHORTADDR_LEN 2 /* compressed ipv6 address length */ #define UIP_IPH_LEN 40 /* ipv6 fixed header size */ #define UIP_PROTO_UDP 17 /* ipv6 next header value for UDP */ @@ -306,6 +308,119 @@ static inline void lowpan_push_hc_data(u8 **hc_ptr, const void *data, *hc_ptr += len; } +static inline u8 lowpan_addr_mode_size(const u8 addr_mode) +{ + static const u8 addr_sizes[] = { + [LOWPAN_IPHC_ADDR_00] = 16, + [LOWPAN_IPHC_ADDR_01] = 8, + [LOWPAN_IPHC_ADDR_02] = 2, + [LOWPAN_IPHC_ADDR_03] = 0, + }; + return addr_sizes[addr_mode]; +} + +static inline u8 lowpan_next_hdr_size(const u8 h_enc, u16 *uncomp_header) +{ + u8 ret = 1; + + if ((h_enc & LOWPAN_NHC_UDP_MASK) == LOWPAN_NHC_UDP_ID) { + *uncomp_header += sizeof(struct udphdr); + + switch (h_enc & LOWPAN_NHC_UDP_CS_P_11) { + case LOWPAN_NHC_UDP_CS_P_00: + ret += 4; + break; + case LOWPAN_NHC_UDP_CS_P_01: + case LOWPAN_NHC_UDP_CS_P_10: + ret += 3; + break; + case LOWPAN_NHC_UDP_CS_P_11: + ret++; + break; + default: + break; + } + + if (!(h_enc & LOWPAN_NHC_UDP_CS_C)) + ret += 2; + } + + return ret; +} + +/** + * lowpan_uncompress_size - returns skb->len size with uncompressed header + * @skb: sk_buff with 6lowpan header inside + * @datagram_offset: optional to get the datagram_offset value + * + * Returns the skb->len with uncompressed header + */ +static inline u16 +lowpan_uncompress_size(const struct sk_buff *skb, u16 *dgram_offset) +{ + u16 ret = 2, uncomp_header = sizeof(struct ipv6hdr); + u8 iphc0, iphc1, h_enc; + + iphc0 = skb_network_header(skb)[0]; + iphc1 = skb_network_header(skb)[1]; + + switch ((iphc0 & LOWPAN_IPHC_TF) >> 3) { + case 0: + ret += 4; + break; + case 1: + ret += 3; + break; + case 2: + ret++; + break; + default: + break; + } + + if (!(iphc0 & LOWPAN_IPHC_NH_C)) + ret++; + + if (!(iphc0 & 0x03)) + ret++; + + ret += lowpan_addr_mode_size((iphc1 & LOWPAN_IPHC_SAM) >> + LOWPAN_IPHC_SAM_BIT); + + if (iphc1 & LOWPAN_IPHC_M) { + switch ((iphc1 & LOWPAN_IPHC_DAM_11) >> + LOWPAN_IPHC_DAM_BIT) { + case LOWPAN_IPHC_DAM_00: + ret += 16; + break; + case LOWPAN_IPHC_DAM_01: + ret += 6; + break; + case LOWPAN_IPHC_DAM_10: + ret += 4; + break; + case LOWPAN_IPHC_DAM_11: + ret++; + break; + default: + break; + } + } else { + ret += lowpan_addr_mode_size((iphc1 & LOWPAN_IPHC_DAM_11) >> + LOWPAN_IPHC_DAM_BIT); + } + + if (iphc0 & LOWPAN_IPHC_NH_C) { + h_enc = skb_network_header(skb)[ret]; + ret += lowpan_next_hdr_size(h_enc, &uncomp_header); + } + + if (dgram_offset) + *dgram_offset = uncomp_header; + + return skb->len + uncomp_header - ret; +} + typedef int (*skb_delivery_cb)(struct sk_buff *skb, struct net_device *dev); int lowpan_process_data(struct sk_buff *skb, struct net_device *dev, diff --git a/include/net/act_api.h b/include/net/act_api.h index 788d8378e587..3ee4c92afd1b 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -89,7 +89,7 @@ struct tc_action_ops { struct module *owner; int (*act)(struct sk_buff *, const struct tc_action *, struct tcf_result *); int (*dump)(struct sk_buff *, struct tc_action *, int, int); - int (*cleanup)(struct tc_action *, int bind); + void (*cleanup)(struct tc_action *, int bind); int (*lookup)(struct tc_action *, u32); int (*init)(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action *act, int ovr, @@ -98,20 +98,18 @@ struct tc_action_ops { }; int tcf_hash_search(struct tc_action *a, u32 index); -void tcf_hash_destroy(struct tcf_common *p, struct tcf_hashinfo *hinfo); -int tcf_hash_release(struct tcf_common *p, int bind, - struct tcf_hashinfo *hinfo); +void tcf_hash_destroy(struct tc_action *a); +int tcf_hash_release(struct tc_action *a, int bind); u32 tcf_hash_new_index(struct tcf_hashinfo *hinfo); -struct tcf_common *tcf_hash_check(u32 index, struct tc_action *a, - int bind); -struct tcf_common *tcf_hash_create(u32 index, struct nlattr *est, - struct tc_action *a, int size, - int bind); -void tcf_hash_insert(struct tcf_common *p, struct tcf_hashinfo *hinfo); +int tcf_hash_check(u32 index, struct tc_action *a, int bind); +int tcf_hash_create(u32 index, struct nlattr *est, struct tc_action *a, + int size, int bind); +void tcf_hash_cleanup(struct tc_action *a, struct nlattr *est); +void tcf_hash_insert(struct tc_action *a); -int tcf_register_action(struct tc_action_ops *a); +int tcf_register_action(struct tc_action_ops *a, unsigned int mask); int tcf_unregister_action(struct tc_action_ops *a); -void tcf_action_destroy(struct list_head *actions, int bind); +int tcf_action_destroy(struct list_head *actions, int bind); int tcf_action_exec(struct sk_buff *skb, const struct list_head *actions, struct tcf_result *res); int tcf_action_init(struct net *net, struct nlattr *nla, diff --git a/include/net/addrconf.h b/include/net/addrconf.h index 50e39a8822b4..933a9f22a05f 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -314,7 +314,7 @@ static inline bool ipv6_addr_is_multicast(const struct in6_addr *addr) static inline bool ipv6_addr_is_ll_all_nodes(const struct in6_addr *addr) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 - __u64 *p = (__u64 *)addr; + __be64 *p = (__be64 *)addr; return ((p[0] ^ cpu_to_be64(0xff02000000000000UL)) | (p[1] ^ cpu_to_be64(1))) == 0UL; #else return ((addr->s6_addr32[0] ^ htonl(0xff020000)) | @@ -326,7 +326,7 @@ static inline bool ipv6_addr_is_ll_all_nodes(const struct in6_addr *addr) static inline bool ipv6_addr_is_ll_all_routers(const struct in6_addr *addr) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 - __u64 *p = (__u64 *)addr; + __be64 *p = (__be64 *)addr; return ((p[0] ^ cpu_to_be64(0xff02000000000000UL)) | (p[1] ^ cpu_to_be64(2))) == 0UL; #else return ((addr->s6_addr32[0] ^ htonl(0xff020000)) | @@ -343,7 +343,7 @@ static inline bool ipv6_addr_is_isatap(const struct in6_addr *addr) static inline bool ipv6_addr_is_solict_mult(const struct in6_addr *addr) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 - __u64 *p = (__u64 *)addr; + __be64 *p = (__be64 *)addr; return ((p[0] ^ cpu_to_be64(0xff02000000000000UL)) | ((p[1] ^ cpu_to_be64(0x00000001ff000000UL)) & cpu_to_be64(0xffffffffff000000UL))) == 0UL; diff --git a/include/net/datalink.h b/include/net/datalink.h index deb7ca75db48..93cb18f729b5 100644 --- a/include/net/datalink.h +++ b/include/net/datalink.h @@ -15,4 +15,6 @@ struct datalink_proto { struct list_head node; }; +struct datalink_proto *make_EII_client(void); +void destroy_EII_client(struct datalink_proto *dl); #endif diff --git a/include/net/dn.h b/include/net/dn.h index ccc15588d108..913b73d239f5 100644 --- a/include/net/dn.h +++ b/include/net/dn.h @@ -200,6 +200,8 @@ static inline void dn_sk_ports_copy(struct flowidn *fld, struct dn_scp *scp) } unsigned int dn_mss_from_pmtu(struct net_device *dev, int mtu); +void dn_register_sysctl(void); +void dn_unregister_sysctl(void); #define DN_MENUVER_ACC 0x01 #define DN_MENUVER_USR 0x02 diff --git a/include/net/dn_route.h b/include/net/dn_route.h index b409ad6b8d7a..55df9939bca2 100644 --- a/include/net/dn_route.h +++ b/include/net/dn_route.h @@ -20,6 +20,8 @@ int dn_route_output_sock(struct dst_entry __rcu **pprt, struct flowidn *, struct sock *sk, int flags); int dn_cache_dump(struct sk_buff *skb, struct netlink_callback *cb); void dn_rt_cache_flush(int delay); +int dn_route_rcv(struct sk_buff *skb, struct net_device *dev, + struct packet_type *pt, struct net_device *orig_dev); /* Masks for flags field */ #define DN_RT_F_PID 0x07 /* Mask for packet type */ diff --git a/include/net/dst.h b/include/net/dst.h index 77eb53fabfb0..e01a826f2a9c 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -54,10 +54,9 @@ struct dst_entry { #define DST_NOHASH 0x0008 #define DST_NOCACHE 0x0010 #define DST_NOCOUNT 0x0020 -#define DST_NOPEER 0x0040 -#define DST_FAKE_RTABLE 0x0080 -#define DST_XFRM_TUNNEL 0x0100 -#define DST_XFRM_QUEUE 0x0200 +#define DST_FAKE_RTABLE 0x0040 +#define DST_XFRM_TUNNEL 0x0080 +#define DST_XFRM_QUEUE 0x0100 unsigned short pending_confirm; diff --git a/include/net/ethoc.h b/include/net/ethoc.h index 96f3789b27bc..2a2d6bb34eb8 100644 --- a/include/net/ethoc.h +++ b/include/net/ethoc.h @@ -16,6 +16,7 @@ struct ethoc_platform_data { u8 hwaddr[IFHWADDRLEN]; s8 phy_id; + u32 eth_clkfreq; }; #endif /* !LINUX_NET_ETHOC_H */ diff --git a/include/net/flow.h b/include/net/flow.h index d23e7fa2042e..64fd24836650 100644 --- a/include/net/flow.h +++ b/include/net/flow.h @@ -218,9 +218,11 @@ struct flow_cache_object *flow_cache_lookup(struct net *net, const struct flowi *key, u16 family, u8 dir, flow_resolve_t resolver, void *ctx); +int flow_cache_init(struct net *net); +void flow_cache_fini(struct net *net); -void flow_cache_flush(void); -void flow_cache_flush_deferred(void); +void flow_cache_flush(struct net *net); +void flow_cache_flush_deferred(struct net *net); extern atomic_t flow_cache_genid; #endif diff --git a/include/net/flowcache.h b/include/net/flowcache.h new file mode 100644 index 000000000000..c8f665ec6e0d --- /dev/null +++ b/include/net/flowcache.h @@ -0,0 +1,25 @@ +#ifndef _NET_FLOWCACHE_H +#define _NET_FLOWCACHE_H + +#include <linux/interrupt.h> +#include <linux/types.h> +#include <linux/timer.h> +#include <linux/notifier.h> + +struct flow_cache_percpu { + struct hlist_head *hash_table; + int hash_count; + u32 hash_rnd; + int hash_rnd_recalc; + struct tasklet_struct flush_tasklet; +}; + +struct flow_cache { + u32 hash_shift; + struct flow_cache_percpu __percpu *percpu; + struct notifier_block hotcpu_notifier; + int low_watermark; + int high_watermark; + struct timer_list rnd_timer; +}; +#endif /* _NET_FLOWCACHE_H */ diff --git a/include/net/ieee802154_netdev.h b/include/net/ieee802154_netdev.h index 8196d5d40359..97b2e34d87f7 100644 --- a/include/net/ieee802154_netdev.h +++ b/include/net/ieee802154_netdev.h @@ -29,6 +29,12 @@ #include <net/af_ieee802154.h> +struct ieee802154_frag_info { + __be16 d_tag; + u16 d_size; + u8 d_offset; +}; + /* * A control block of skb passed between the ARPHRD_IEEE802154 device * and other stack parts. @@ -39,6 +45,7 @@ struct ieee802154_mac_cb { struct ieee802154_addr da; u8 flags; u8 seq; + struct ieee802154_frag_info frag_info; }; static inline struct ieee802154_mac_cb *mac_cb(struct sk_buff *skb) diff --git a/include/net/ip.h b/include/net/ip.h index 23be0fd37937..25064c28e059 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -187,6 +187,7 @@ void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr, #define NET_INC_STATS(net, field) SNMP_INC_STATS((net)->mib.net_statistics, field) #define NET_INC_STATS_BH(net, field) SNMP_INC_STATS_BH((net)->mib.net_statistics, field) #define NET_INC_STATS_USER(net, field) SNMP_INC_STATS_USER((net)->mib.net_statistics, field) +#define NET_ADD_STATS(net, field, adnd) SNMP_ADD_STATS((net)->mib.net_statistics, field, adnd) #define NET_ADD_STATS_BH(net, field, adnd) SNMP_ADD_STATS_BH((net)->mib.net_statistics, field, adnd) #define NET_ADD_STATS_USER(net, field, adnd) SNMP_ADD_STATS_USER((net)->mib.net_statistics, field, adnd) @@ -266,7 +267,8 @@ int ip_dont_fragment(struct sock *sk, struct dst_entry *dst) static inline bool ip_sk_accept_pmtu(const struct sock *sk) { - return inet_sk(sk)->pmtudisc != IP_PMTUDISC_INTERFACE; + return inet_sk(sk)->pmtudisc != IP_PMTUDISC_INTERFACE && + inet_sk(sk)->pmtudisc != IP_PMTUDISC_OMIT; } static inline bool ip_sk_use_pmtu(const struct sock *sk) @@ -274,6 +276,12 @@ static inline bool ip_sk_use_pmtu(const struct sock *sk) return inet_sk(sk)->pmtudisc < IP_PMTUDISC_PROBE; } +static inline bool ip_sk_local_df(const struct sock *sk) +{ + return inet_sk(sk)->pmtudisc < IP_PMTUDISC_DO || + inet_sk(sk)->pmtudisc == IP_PMTUDISC_OMIT; +} + static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst, bool forwarding) { @@ -489,7 +497,8 @@ int ip_options_rcv_srr(struct sk_buff *skb); void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb); void ip_cmsg_recv(struct msghdr *msg, struct sk_buff *skb); -int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc); +int ip_cmsg_send(struct net *net, struct msghdr *msg, + struct ipcm_cookie *ipc, bool allow_ipv6); int ip_setsockopt(struct sock *sk, int level, int optname, char __user *optval, unsigned int optlen); int ip_getsockopt(struct sock *sk, int level, int optname, char __user *optval, diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 017badb1aec7..00e3f12cb2f9 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -171,7 +171,14 @@ static inline int ip6_skb_dst_mtu(struct sk_buff *skb) static inline bool ip6_sk_accept_pmtu(const struct sock *sk) { - return inet6_sk(sk)->pmtudisc != IPV6_PMTUDISC_INTERFACE; + return inet6_sk(sk)->pmtudisc != IPV6_PMTUDISC_INTERFACE && + inet6_sk(sk)->pmtudisc != IPV6_PMTUDISC_OMIT; +} + +static inline bool ip6_sk_local_df(const struct sock *sk) +{ + return inet6_sk(sk)->pmtudisc < IPV6_PMTUDISC_DO || + inet6_sk(sk)->pmtudisc == IPV6_PMTUDISC_OMIT; } static inline struct in6_addr *rt6_nexthop(struct rt6_info *rt) diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 48ed75c21260..e77c10405d51 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -129,6 +129,7 @@ int ip_tunnel_changelink(struct net_device *dev, struct nlattr *tb[], int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[], struct ip_tunnel_parm *p); void ip_tunnel_setup(struct net_device *dev, int net_id); +void ip_tunnel_dst_reset_all(struct ip_tunnel *t); /* Extract dsfield from inner protocol */ static inline u8 ip_tunnel_get_dsfield(const struct iphdr *iph, diff --git a/include/net/ipx.h b/include/net/ipx.h index 9e9e35465baf..0143180fecc9 100644 --- a/include/net/ipx.h +++ b/include/net/ipx.h @@ -140,6 +140,17 @@ static __inline__ void ipxitf_hold(struct ipx_interface *intrfc) } void ipxitf_down(struct ipx_interface *intrfc); +struct ipx_interface *ipxitf_find_using_net(__be32 net); +int ipxitf_send(struct ipx_interface *intrfc, struct sk_buff *skb, char *node); +__be16 ipx_cksum(struct ipxhdr *packet, int length); +int ipxrtr_add_route(__be32 network, struct ipx_interface *intrfc, + unsigned char *node); +void ipxrtr_del_routes(struct ipx_interface *intrfc); +int ipxrtr_route_packet(struct sock *sk, struct sockaddr_ipx *usipx, + struct iovec *iov, size_t len, int noblock); +int ipxrtr_route_skb(struct sk_buff *skb); +struct ipx_route *ipxrtr_lookup(__be32 net); +int ipxrtr_ioctl(unsigned int cmd, void __user *arg); static __inline__ void ipxitf_put(struct ipx_interface *intrfc) { diff --git a/include/net/mac802154.h b/include/net/mac802154.h index 807d6b7a943f..8ca3d04e7558 100644 --- a/include/net/mac802154.h +++ b/include/net/mac802154.h @@ -113,6 +113,32 @@ struct ieee802154_dev { * Set radio for listening on specific address. * Set the device for listening on specified address. * Returns either zero, or negative errno. + * + * set_txpower: + * Set radio transmit power in dB. Called with pib_lock held. + * Returns either zero, or negative errno. + * + * set_lbt + * Enables or disables listen before talk on the device. Called with + * pib_lock held. + * Returns either zero, or negative errno. + * + * set_cca_mode + * Sets the CCA mode used by the device. Called with pib_lock held. + * Returns either zero, or negative errno. + * + * set_cca_ed_level + * Sets the CCA energy detection threshold in dBm. Called with pib_lock + * held. + * Returns either zero, or negative errno. + * + * set_csma_params + * Sets the CSMA parameter set for the PHY. Called with pib_lock held. + * Returns either zero, or negative errno. + * + * set_frame_retries + * Sets the retransmission attempt limit. Called with pib_lock held. + * Returns either zero, or negative errno. */ struct ieee802154_ops { struct module *owner; @@ -129,6 +155,15 @@ struct ieee802154_ops { unsigned long changed); int (*ieee_addr)(struct ieee802154_dev *dev, u8 addr[IEEE802154_ADDR_LEN]); + int (*set_txpower)(struct ieee802154_dev *dev, int db); + int (*set_lbt)(struct ieee802154_dev *dev, bool on); + int (*set_cca_mode)(struct ieee802154_dev *dev, u8 mode); + int (*set_cca_ed_level)(struct ieee802154_dev *dev, + s32 level); + int (*set_csma_params)(struct ieee802154_dev *dev, + u8 min_be, u8 max_be, u8 retries); + int (*set_frame_retries)(struct ieee802154_dev *dev, + s8 retries); }; /* Basic interface to register ieee802154 device */ diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index da68c9a90ac5..79387f73f875 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -15,6 +15,7 @@ #include <net/netns/packet.h> #include <net/netns/ipv4.h> #include <net/netns/ipv6.h> +#include <net/netns/ieee802154_6lowpan.h> #include <net/netns/sctp.h> #include <net/netns/dccp.h> #include <net/netns/netfilter.h> @@ -90,6 +91,9 @@ struct net { #if IS_ENABLED(CONFIG_IPV6) struct netns_ipv6 ipv6; #endif +#if IS_ENABLED(CONFIG_IEEE802154_6LOWPAN) + struct netns_ieee802154_lowpan ieee802154_lowpan; +#endif #if defined(CONFIG_IP_SCTP) || defined(CONFIG_IP_SCTP_MODULE) struct netns_sctp sctp; #endif @@ -162,6 +166,14 @@ extern struct list_head net_namespace_list; struct net *get_net_ns_by_pid(pid_t pid); struct net *get_net_ns_by_fd(int pid); +#ifdef CONFIG_SYSCTL +void ipx_register_sysctl(void); +void ipx_unregister_sysctl(void); +#else +#define ipx_register_sysctl() +#define ipx_unregister_sysctl() +#endif + #ifdef CONFIG_NET_NS void __put_net(struct net *net); diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index 01ea6eed1bb1..b2ac6246b7e0 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -284,6 +284,8 @@ extern unsigned int nf_conntrack_max; extern unsigned int nf_conntrack_hash_rnd; void init_nf_conntrack_hash_rnd(void); +void nf_conntrack_tmpl_insert(struct net *net, struct nf_conn *tmpl); + #define NF_CT_STAT_INC(net, count) __this_cpu_inc((net)->ct.stat->count) #define NF_CT_STAT_INC_ATOMIC(net, count) this_cpu_inc((net)->ct.stat->count) diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 57c8ff7955df..e7e14ffe0f6a 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -252,6 +252,7 @@ void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set, * @owner: module reference * @policy: netlink attribute policy * @maxattr: highest netlink attribute number + * @family: address family for AF-specific types */ struct nft_expr_type { const struct nft_expr_ops *(*select_ops)(const struct nft_ctx *, @@ -262,6 +263,7 @@ struct nft_expr_type { struct module *owner; const struct nla_policy *policy; unsigned int maxattr; + u8 family; }; /** @@ -320,7 +322,6 @@ static inline void *nft_expr_priv(const struct nft_expr *expr) * struct nft_rule - nf_tables rule * * @list: used internally - * @rcu_head: used internally for rcu * @handle: rule handle * @genmask: generation mask * @dlen: length of expression data @@ -328,7 +329,6 @@ static inline void *nft_expr_priv(const struct nft_expr *expr) */ struct nft_rule { struct list_head list; - struct rcu_head rcu_head; u64 handle:46, genmask:2, dlen:16; @@ -389,7 +389,6 @@ enum nft_chain_flags { * * @rules: list of rules in the chain * @list: used internally - * @rcu_head: used internally * @net: net namespace that this chain belongs to * @table: table that this chain belongs to * @handle: chain handle @@ -401,7 +400,6 @@ enum nft_chain_flags { struct nft_chain { struct list_head rules; struct list_head list; - struct rcu_head rcu_head; struct net *net; struct nft_table *table; u64 handle; @@ -529,6 +527,9 @@ void nft_unregister_expr(struct nft_expr_type *); #define MODULE_ALIAS_NFT_CHAIN(family, name) \ MODULE_ALIAS("nft-chain-" __stringify(family) "-" name) +#define MODULE_ALIAS_NFT_AF_EXPR(family, name) \ + MODULE_ALIAS("nft-expr-" __stringify(family) "-" name) + #define MODULE_ALIAS_NFT_EXPR(name) \ MODULE_ALIAS("nft-expr-" name) diff --git a/include/net/netfilter/nft_reject.h b/include/net/netfilter/nft_reject.h new file mode 100644 index 000000000000..36b0da2d55bb --- /dev/null +++ b/include/net/netfilter/nft_reject.h @@ -0,0 +1,25 @@ +#ifndef _NFT_REJECT_H_ +#define _NFT_REJECT_H_ + +struct nft_reject { + enum nft_reject_types type:8; + u8 icmp_code; +}; + +extern const struct nla_policy nft_reject_policy[]; + +int nft_reject_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]); + +int nft_reject_dump(struct sk_buff *skb, const struct nft_expr *expr); + +void nft_reject_ipv4_eval(const struct nft_expr *expr, + struct nft_data data[NFT_REG_MAX + 1], + const struct nft_pktinfo *pkt); + +void nft_reject_ipv6_eval(const struct nft_expr *expr, + struct nft_data data[NFT_REG_MAX + 1], + const struct nft_pktinfo *pkt); + +#endif diff --git a/include/net/netns/ieee802154_6lowpan.h b/include/net/netns/ieee802154_6lowpan.h new file mode 100644 index 000000000000..079030c853d8 --- /dev/null +++ b/include/net/netns/ieee802154_6lowpan.h @@ -0,0 +1,22 @@ +/* + * ieee802154 6lowpan in net namespaces + */ + +#include <net/inet_frag.h> + +#ifndef __NETNS_IEEE802154_6LOWPAN_H__ +#define __NETNS_IEEE802154_6LOWPAN_H__ + +struct netns_sysctl_lowpan { +#ifdef CONFIG_SYSCTL + struct ctl_table_header *frags_hdr; +#endif +}; + +struct netns_ieee802154_lowpan { + struct netns_sysctl_lowpan sysctl; + struct netns_frags frags; + u16 max_dsize; +}; + +#endif diff --git a/include/net/netns/xfrm.h b/include/net/netns/xfrm.h index 1006a265beb3..3492434baf88 100644 --- a/include/net/netns/xfrm.h +++ b/include/net/netns/xfrm.h @@ -6,6 +6,7 @@ #include <linux/workqueue.h> #include <linux/xfrm.h> #include <net/dst_ops.h> +#include <net/flowcache.h> struct ctl_table_header; @@ -58,9 +59,17 @@ struct netns_xfrm { struct dst_ops xfrm6_dst_ops; #endif spinlock_t xfrm_state_lock; - spinlock_t xfrm_policy_sk_bundle_lock; rwlock_t xfrm_policy_lock; struct mutex xfrm_cfg_mutex; + + /* flow cache part */ + struct flow_cache flow_cache_global; + atomic_t flow_cache_genid; + struct list_head flow_cache_gc_list; + spinlock_t flow_cache_gc_lock; + struct work_struct flow_cache_gc_work; + struct work_struct flow_cache_flush_work; + struct mutex flow_flush_sem; }; #endif diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index 661e45d38051..72240e5ac2c4 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -140,7 +140,7 @@ struct net_device *rtnl_create_link(struct net *net, char *ifname, struct nlattr *tb[]); int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm); -extern const struct nla_policy ifla_policy[IFLA_MAX+1]; +int rtnl_nla_parse_ifla(struct nlattr **tb, const struct nlattr *head, int len); #define MODULE_ALIAS_RTNL_LINK(kind) MODULE_ALIAS("rtnl-link-" kind) diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index d992ca3145fe..6ee76c804893 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -1653,17 +1653,6 @@ struct sctp_association { /* This is the last advertised value of rwnd over a SACK chunk. */ __u32 a_rwnd; - /* Number of bytes by which the rwnd has slopped. The rwnd is allowed - * to slop over a maximum of the association's frag_point. - */ - __u32 rwnd_over; - - /* Keeps treack of rwnd pressure. This happens when we have - * a window, but not recevie buffer (i.e small packets). This one - * is releases slowly (1 PMTU at a time ). - */ - __u32 rwnd_press; - /* This is the sndbuf size in use for the association. * This corresponds to the sndbuf size for the association, * as specified in the sk->sndbuf. @@ -1892,8 +1881,7 @@ void sctp_assoc_update(struct sctp_association *old, __u32 sctp_association_get_next_tsn(struct sctp_association *); void sctp_assoc_sync_pmtu(struct sock *, struct sctp_association *); -void sctp_assoc_rwnd_increase(struct sctp_association *, unsigned int); -void sctp_assoc_rwnd_decrease(struct sctp_association *, unsigned int); +void sctp_assoc_rwnd_update(struct sctp_association *, bool); void sctp_assoc_set_primary(struct sctp_association *, struct sctp_transport *); void sctp_assoc_del_nonprimary_peers(struct sctp_association *, diff --git a/include/net/sock.h b/include/net/sock.h index 5c3f7c3624aa..967856970a51 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2252,8 +2252,12 @@ void sock_net_set(struct sock *sk, struct net *net) */ static inline void sk_change_net(struct sock *sk, struct net *net) { - put_net(sock_net(sk)); - sock_net_set(sk, hold_net(net)); + struct net *current_net = sock_net(sk); + + if (!net_eq(current_net, net)) { + put_net(current_net); + sock_net_set(sk, hold_net(net)); + } } static inline struct sock *skb_steal_sock(struct sk_buff *skb) diff --git a/include/net/tc_act/tc_csum.h b/include/net/tc_act/tc_csum.h index 9e8710be7a04..fa8f5fac65e9 100644 --- a/include/net/tc_act/tc_csum.h +++ b/include/net/tc_act/tc_csum.h @@ -9,7 +9,7 @@ struct tcf_csum { u32 update_flags; }; -#define to_tcf_csum(pc) \ - container_of(pc,struct tcf_csum,common) +#define to_tcf_csum(a) \ + container_of(a->priv,struct tcf_csum,common) #endif /* __NET_TC_CSUM_H */ diff --git a/include/net/tc_act/tc_defact.h b/include/net/tc_act/tc_defact.h index 65f024b80958..9763dcbb9bc3 100644 --- a/include/net/tc_act/tc_defact.h +++ b/include/net/tc_act/tc_defact.h @@ -8,7 +8,7 @@ struct tcf_defact { u32 tcfd_datalen; void *tcfd_defdata; }; -#define to_defact(pc) \ - container_of(pc, struct tcf_defact, common) +#define to_defact(a) \ + container_of(a->priv, struct tcf_defact, common) #endif /* __NET_TC_DEF_H */ diff --git a/include/net/tc_act/tc_gact.h b/include/net/tc_act/tc_gact.h index 9e3f6767b80e..9fc9b578908a 100644 --- a/include/net/tc_act/tc_gact.h +++ b/include/net/tc_act/tc_gact.h @@ -11,7 +11,7 @@ struct tcf_gact { int tcfg_paction; #endif }; -#define to_gact(pc) \ - container_of(pc, struct tcf_gact, common) +#define to_gact(a) \ + container_of(a->priv, struct tcf_gact, common) #endif /* __NET_TC_GACT_H */ diff --git a/include/net/tc_act/tc_ipt.h b/include/net/tc_act/tc_ipt.h index f7d25dfcc4b7..c0f4193f432c 100644 --- a/include/net/tc_act/tc_ipt.h +++ b/include/net/tc_act/tc_ipt.h @@ -11,7 +11,7 @@ struct tcf_ipt { char *tcfi_tname; struct xt_entry_target *tcfi_t; }; -#define to_ipt(pc) \ - container_of(pc, struct tcf_ipt, common) +#define to_ipt(a) \ + container_of(a->priv, struct tcf_ipt, common) #endif /* __NET_TC_IPT_H */ diff --git a/include/net/tc_act/tc_mirred.h b/include/net/tc_act/tc_mirred.h index cfe2943690ff..4dd77a1c106b 100644 --- a/include/net/tc_act/tc_mirred.h +++ b/include/net/tc_act/tc_mirred.h @@ -11,7 +11,7 @@ struct tcf_mirred { struct net_device *tcfm_dev; struct list_head tcfm_list; }; -#define to_mirred(pc) \ - container_of(pc, struct tcf_mirred, common) +#define to_mirred(a) \ + container_of(a->priv, struct tcf_mirred, common) #endif /* __NET_TC_MIR_H */ diff --git a/include/net/tc_act/tc_nat.h b/include/net/tc_act/tc_nat.h index 4a691f34d703..63d8e9ca9d99 100644 --- a/include/net/tc_act/tc_nat.h +++ b/include/net/tc_act/tc_nat.h @@ -13,9 +13,9 @@ struct tcf_nat { u32 flags; }; -static inline struct tcf_nat *to_tcf_nat(struct tcf_common *pc) +static inline struct tcf_nat *to_tcf_nat(struct tc_action *a) { - return container_of(pc, struct tcf_nat, common); + return container_of(a->priv, struct tcf_nat, common); } #endif /* __NET_TC_NAT_H */ diff --git a/include/net/tc_act/tc_pedit.h b/include/net/tc_act/tc_pedit.h index e6f6e15956f5..5b80998879c7 100644 --- a/include/net/tc_act/tc_pedit.h +++ b/include/net/tc_act/tc_pedit.h @@ -9,7 +9,7 @@ struct tcf_pedit { unsigned char tcfp_flags; struct tc_pedit_key *tcfp_keys; }; -#define to_pedit(pc) \ - container_of(pc, struct tcf_pedit, common) +#define to_pedit(a) \ + container_of(a->priv, struct tcf_pedit, common) #endif /* __NET_TC_PED_H */ diff --git a/include/net/tc_act/tc_skbedit.h b/include/net/tc_act/tc_skbedit.h index dd5d86fab030..0df9a0db4a8e 100644 --- a/include/net/tc_act/tc_skbedit.h +++ b/include/net/tc_act/tc_skbedit.h @@ -29,7 +29,7 @@ struct tcf_skbedit { u16 queue_mapping; /* XXX: 16-bit pad here? */ }; -#define to_skbedit(pc) \ - container_of(pc, struct tcf_skbedit, common) +#define to_skbedit(a) \ + container_of(a->priv, struct tcf_skbedit, common) #endif /* __NET_TC_SKBEDIT_H */ diff --git a/include/net/tcp.h b/include/net/tcp.h index 56fc366da6d5..bb253b9b2f06 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -31,6 +31,7 @@ #include <linux/crypto.h> #include <linux/cryptohash.h> #include <linux/kref.h> +#include <linux/ktime.h> #include <net/inet_connection_sock.h> #include <net/inet_timewait_sock.h> @@ -478,7 +479,6 @@ int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th, struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, struct ip_options *opt); #ifdef CONFIG_SYN_COOKIES -#include <linux/ktime.h> /* Syncookies use a monotonic timer which increments every 64 seconds. * This counter is used both as a hash input and partially encoded into @@ -619,7 +619,7 @@ static inline void tcp_bound_rto(const struct sock *sk) static inline u32 __tcp_set_rto(const struct tcp_sock *tp) { - return (tp->srtt >> 3) + tp->rttvar; + return usecs_to_jiffies((tp->srtt_us >> 3) + tp->rttvar_us); } static inline void __tcp_fast_path_on(struct tcp_sock *tp, u32 snd_wnd) @@ -656,6 +656,11 @@ static inline u32 tcp_rto_min(struct sock *sk) return rto_min; } +static inline u32 tcp_rto_min_us(struct sock *sk) +{ + return jiffies_to_usecs(tcp_rto_min(sk)); +} + /* Compute the actual receive window we are currently advertising. * Rcv_nxt can be after the window if our peer push more data * than the offered window. @@ -778,7 +783,6 @@ enum tcp_ca_event { #define TCP_CA_BUF_MAX (TCP_CA_NAME_MAX*TCP_CA_MAX) #define TCP_CONG_NON_RESTRICTED 0x1 -#define TCP_CONG_RTT_STAMP 0x2 struct tcp_congestion_ops { struct list_head list; @@ -791,8 +795,6 @@ struct tcp_congestion_ops { /* return slow start threshold (required) */ u32 (*ssthresh)(struct sock *sk); - /* lower bound for congestion window (optional) */ - u32 (*min_cwnd)(const struct sock *sk); /* do new cwnd calculation (required) */ void (*cong_avoid)(struct sock *sk, u32 ack, u32 acked, u32 in_flight); /* call before changing ca_state (optional) */ @@ -827,7 +829,6 @@ void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w); extern struct tcp_congestion_ops tcp_init_congestion_ops; u32 tcp_reno_ssthresh(struct sock *sk); void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked, u32 in_flight); -u32 tcp_reno_min_cwnd(const struct sock *sk); extern struct tcp_congestion_ops tcp_reno; static inline void tcp_set_ca_state(struct sock *sk, const u8 ca_state) @@ -1303,7 +1304,8 @@ struct tcp_fastopen_request { /* Fast Open cookie. Size 0 means a cookie request */ struct tcp_fastopen_cookie cookie; struct msghdr *data; /* data in MSG_FASTOPEN */ - u16 copied; /* queued in tcp_connect() */ + size_t size; + int copied; /* queued in tcp_connect() */ }; void tcp_free_fastopen_req(struct tcp_sock *tp); diff --git a/include/net/wpan-phy.h b/include/net/wpan-phy.h index b52bda8d13b1..10ab0fc6d4f7 100644 --- a/include/net/wpan-phy.h +++ b/include/net/wpan-phy.h @@ -37,15 +37,22 @@ struct wpan_phy { struct mutex pib_lock; /* - * This is a PIB according to 802.15.4-2006. + * This is a PIB according to 802.15.4-2011. * We do not provide timing-related variables, as they * aren't used outside of driver */ u8 current_channel; u8 current_page; u32 channels_supported[32]; - u8 transmit_power; + s8 transmit_power; u8 cca_mode; + u8 min_be; + u8 max_be; + u8 csma_retries; + s8 frame_retries; + + bool lbt; + s32 cca_ed_level; struct device dev; int idx; @@ -54,6 +61,14 @@ struct wpan_phy { const char *name, int type); void (*del_iface)(struct wpan_phy *phy, struct net_device *dev); + int (*set_txpower)(struct wpan_phy *phy, int db); + int (*set_lbt)(struct wpan_phy *phy, bool on); + int (*set_cca_mode)(struct wpan_phy *phy, u8 cca_mode); + int (*set_cca_ed_level)(struct wpan_phy *phy, int level); + int (*set_csma_params)(struct wpan_phy *phy, u8 min_be, u8 max_be, + u8 retries); + int (*set_frame_retries)(struct wpan_phy *phy, s8 retries); + char priv[0] __attribute__((__aligned__(NETDEV_ALIGN))); }; diff --git a/include/net/xfrm.h b/include/net/xfrm.h index afa5730fb3bd..23bfd4591e8b 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -118,11 +118,10 @@ struct xfrm_state_walk { struct list_head all; u8 state; - union { - u8 dying; - u8 proto; - }; + u8 dying; + u8 proto; u32 seq; + struct xfrm_filter *filter; }; /* Full description of state of transformer. */ @@ -594,21 +593,33 @@ struct xfrm_mgr { const struct xfrm_migrate *m, int num_bundles, const struct xfrm_kmaddress *k); + bool (*is_alive)(const struct km_event *c); }; int xfrm_register_km(struct xfrm_mgr *km); int xfrm_unregister_km(struct xfrm_mgr *km); +struct xfrm_tunnel_skb_cb { + union { + struct inet_skb_parm h4; + struct inet6_skb_parm h6; + } header; + + union { + struct ip_tunnel *ip4; + struct ip6_tnl *ip6; + } tunnel; +}; + +#define XFRM_TUNNEL_SKB_CB(__skb) ((struct xfrm_tunnel_skb_cb *)&((__skb)->cb[0])) + /* * This structure is used for the duration where packets are being * transformed by IPsec. As soon as the packet leaves IPsec the * area beyond the generic IP part may be overwritten. */ struct xfrm_skb_cb { - union { - struct inet_skb_parm h4; - struct inet6_skb_parm h6; - } header; + struct xfrm_tunnel_skb_cb header; /* Sequence number for replay protection. */ union { @@ -630,10 +641,7 @@ struct xfrm_skb_cb { * to transmit header information to the mode input/output functions. */ struct xfrm_mode_skb_cb { - union { - struct inet_skb_parm h4; - struct inet6_skb_parm h6; - } header; + struct xfrm_tunnel_skb_cb header; /* Copied from header for IPv4, always set to zero and DF for IPv6. */ __be16 id; @@ -665,10 +673,7 @@ struct xfrm_mode_skb_cb { * related information. */ struct xfrm_spi_skb_cb { - union { - struct inet_skb_parm h4; - struct inet6_skb_parm h6; - } header; + struct xfrm_tunnel_skb_cb header; unsigned int daddroff; unsigned int family; @@ -1347,6 +1352,18 @@ struct xfrm_algo_desc { struct sadb_alg desc; }; +/* XFRM protocol handlers. */ +struct xfrm4_protocol { + int (*handler)(struct sk_buff *skb); + int (*input_handler)(struct sk_buff *skb, int nexthdr, __be32 spi, + int encap_type); + int (*cb_handler)(struct sk_buff *skb, int err); + int (*err_handler)(struct sk_buff *skb, u32 info); + + struct xfrm4_protocol __rcu *next; + int priority; +}; + /* XFRM tunnel handlers. */ struct xfrm_tunnel { int (*handler)(struct sk_buff *skb); @@ -1405,7 +1422,8 @@ static inline void xfrm_sysctl_fini(struct net *net) } #endif -void xfrm_state_walk_init(struct xfrm_state_walk *walk, u8 proto); +void xfrm_state_walk_init(struct xfrm_state_walk *walk, u8 proto, + struct xfrm_filter *filter); int xfrm_state_walk(struct net *net, struct xfrm_state_walk *walk, int (*func)(struct xfrm_state *, int, void*), void *); void xfrm_state_walk_done(struct xfrm_state_walk *walk, struct net *net); @@ -1497,18 +1515,22 @@ int xfrm4_rcv(struct sk_buff *skb); static inline int xfrm4_rcv_spi(struct sk_buff *skb, int nexthdr, __be32 spi) { - return xfrm4_rcv_encap(skb, nexthdr, spi, 0); + XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL; + XFRM_SPI_SKB_CB(skb)->family = AF_INET; + XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr); + return xfrm_input(skb, nexthdr, spi, 0); } int xfrm4_extract_output(struct xfrm_state *x, struct sk_buff *skb); int xfrm4_prepare_output(struct xfrm_state *x, struct sk_buff *skb); int xfrm4_output(struct sk_buff *skb); int xfrm4_output_finish(struct sk_buff *skb); +int xfrm4_rcv_cb(struct sk_buff *skb, u8 protocol, int err); +int xfrm4_protocol_register(struct xfrm4_protocol *handler, unsigned char protocol); +int xfrm4_protocol_deregister(struct xfrm4_protocol *handler, unsigned char protocol); int xfrm4_tunnel_register(struct xfrm_tunnel *handler, unsigned short family); int xfrm4_tunnel_deregister(struct xfrm_tunnel *handler, unsigned short family); void xfrm4_local_error(struct sk_buff *skb, u32 mtu); -int xfrm4_mode_tunnel_input_register(struct xfrm_tunnel_notifier *handler); -int xfrm4_mode_tunnel_input_deregister(struct xfrm_tunnel_notifier *handler); int xfrm6_mode_tunnel_input_register(struct xfrm_tunnel_notifier *handler); int xfrm6_mode_tunnel_input_deregister(struct xfrm_tunnel_notifier *handler); int xfrm6_extract_header(struct sk_buff *skb); @@ -1646,8 +1668,27 @@ static inline int xfrm_aevent_is_on(struct net *net) rcu_read_unlock(); return ret; } + +static inline int xfrm_acquire_is_on(struct net *net) +{ + struct sock *nlsk; + int ret = 0; + + rcu_read_lock(); + nlsk = rcu_dereference(net->xfrm.nlsk); + if (nlsk) + ret = netlink_has_listeners(nlsk, XFRMNLGRP_ACQUIRE); + rcu_read_unlock(); + + return ret; +} #endif +static inline int aead_len(struct xfrm_algo_aead *alg) +{ + return sizeof(*alg) + ((alg->alg_key_len + 7) / 8); +} + static inline int xfrm_alg_len(const struct xfrm_algo *alg) { return sizeof(*alg) + ((alg->alg_key_len + 7) / 8); @@ -1686,6 +1727,12 @@ static inline int xfrm_replay_clone(struct xfrm_state *x, return 0; } +static inline struct xfrm_algo_aead *xfrm_algo_aead_clone(struct xfrm_algo_aead *orig) +{ + return kmemdup(orig, aead_len(orig), GFP_KERNEL); +} + + static inline struct xfrm_algo *xfrm_algo_clone(struct xfrm_algo *orig) { return kmemdup(orig, xfrm_alg_len(orig), GFP_KERNEL); @@ -1737,4 +1784,36 @@ static inline int xfrm_mark_put(struct sk_buff *skb, const struct xfrm_mark *m) return ret; } +static inline int xfrm_rcv_cb(struct sk_buff *skb, unsigned int family, + u8 protocol, int err) +{ + switch(family) { +#ifdef CONFIG_INET + case AF_INET: + return xfrm4_rcv_cb(skb, protocol, err); +#endif + } + return 0; +} + +static inline int xfrm_tunnel_check(struct sk_buff *skb, struct xfrm_state *x, + unsigned int family) +{ + bool tunnel = false; + + switch(family) { + case AF_INET: + if (XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4) + tunnel = true; + break; + case AF_INET6: + if (XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6) + tunnel = true; + break; + } + if (tunnel && !(x->outer_mode->flags & XFRM_MODE_FLAG_TUNNEL)) + return -EINVAL; + + return 0; +} #endif /* _NET_XFRM_H */ diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 8d4a1c06f7e4..6793f32ccb58 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -226,7 +226,8 @@ enum ib_port_cap_flags { IB_PORT_CAP_MASK_NOTICE_SUP = 1 << 22, IB_PORT_BOOT_MGMT_SUP = 1 << 23, IB_PORT_LINK_LATENCY_SUP = 1 << 24, - IB_PORT_CLIENT_REG_SUP = 1 << 25 + IB_PORT_CLIENT_REG_SUP = 1 << 25, + IB_PORT_IP_BASED_GIDS = 1 << 26 }; enum ib_port_width { diff --git a/include/sound/soc-dapm.h b/include/sound/soc-dapm.h index 68d92e36facd..6e89ef6c11c1 100644 --- a/include/sound/soc-dapm.h +++ b/include/sound/soc-dapm.h @@ -449,14 +449,22 @@ void snd_soc_dapm_debugfs_init(struct snd_soc_dapm_context *dapm, /* dapm audio pin control and status */ int snd_soc_dapm_enable_pin(struct snd_soc_dapm_context *dapm, const char *pin); +int snd_soc_dapm_enable_pin_unlocked(struct snd_soc_dapm_context *dapm, + const char *pin); int snd_soc_dapm_disable_pin(struct snd_soc_dapm_context *dapm, const char *pin); +int snd_soc_dapm_disable_pin_unlocked(struct snd_soc_dapm_context *dapm, + const char *pin); int snd_soc_dapm_nc_pin(struct snd_soc_dapm_context *dapm, const char *pin); +int snd_soc_dapm_nc_pin_unlocked(struct snd_soc_dapm_context *dapm, + const char *pin); int snd_soc_dapm_get_pin_status(struct snd_soc_dapm_context *dapm, const char *pin); int snd_soc_dapm_sync(struct snd_soc_dapm_context *dapm); int snd_soc_dapm_force_enable_pin(struct snd_soc_dapm_context *dapm, const char *pin); +int snd_soc_dapm_force_enable_pin_unlocked(struct snd_soc_dapm_context *dapm, + const char *pin); int snd_soc_dapm_ignore_suspend(struct snd_soc_dapm_context *dapm, const char *pin); void snd_soc_dapm_auto_nc_codec_pins(struct snd_soc_codec *codec); diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h index c9c791209cd1..1772fadcff62 100644 --- a/include/target/target_core_base.h +++ b/include/target/target_core_base.h @@ -525,7 +525,6 @@ struct se_cmd { #define CMD_T_COMPLETE (1 << 2) #define CMD_T_SENT (1 << 4) #define CMD_T_STOP (1 << 5) -#define CMD_T_FAILED (1 << 6) #define CMD_T_DEV_ACTIVE (1 << 7) #define CMD_T_REQUEST_STOP (1 << 8) #define CMD_T_BUSY (1 << 9) diff --git a/include/trace/events/power.h b/include/trace/events/power.h index 9e9475c85de5..e5bf9a76f169 100644 --- a/include/trace/events/power.h +++ b/include/trace/events/power.h @@ -42,7 +42,6 @@ TRACE_EVENT(pstate_sample, u32 state, u64 mperf, u64 aperf, - u32 energy, u32 freq ), @@ -51,7 +50,6 @@ TRACE_EVENT(pstate_sample, state, mperf, aperf, - energy, freq ), @@ -61,7 +59,6 @@ TRACE_EVENT(pstate_sample, __field(u32, state) __field(u64, mperf) __field(u64, aperf) - __field(u32, energy) __field(u32, freq) ), @@ -72,17 +69,15 @@ TRACE_EVENT(pstate_sample, __entry->state = state; __entry->mperf = mperf; __entry->aperf = aperf; - __entry->energy = energy; __entry->freq = freq; ), - TP_printk("core_busy=%lu scaled=%lu state=%lu mperf=%llu aperf=%llu energy=%lu freq=%lu ", + TP_printk("core_busy=%lu scaled=%lu state=%lu mperf=%llu aperf=%llu freq=%lu ", (unsigned long)__entry->core_busy, (unsigned long)__entry->scaled_busy, (unsigned long)__entry->state, (unsigned long long)__entry->mperf, (unsigned long long)__entry->aperf, - (unsigned long)__entry->energy, (unsigned long)__entry->freq ) diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h index c7bbbe794e65..464ea82e10db 100644 --- a/include/trace/events/writeback.h +++ b/include/trace/events/writeback.h @@ -287,11 +287,11 @@ TRACE_EVENT(writeback_queue_io, __field(int, reason) ), TP_fast_assign( - unsigned long older_than_this = work->older_than_this; + unsigned long *older_than_this = work->older_than_this; strncpy(__entry->name, dev_name(wb->bdi->dev), 32); - __entry->older = older_than_this; + __entry->older = older_than_this ? *older_than_this : 0; __entry->age = older_than_this ? - (jiffies - older_than_this) * 1000 / HZ : -1; + (jiffies - *older_than_this) * 1000 / HZ : -1; __entry->moved = moved; __entry->reason = work->reason; ), diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index a20a9b4d3871..dde8041f40d2 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -692,9 +692,13 @@ __SC_COMP(__NR_process_vm_writev, sys_process_vm_writev, \ __SYSCALL(__NR_kcmp, sys_kcmp) #define __NR_finit_module 273 __SYSCALL(__NR_finit_module, sys_finit_module) +#define __NR_sched_setattr 274 +__SYSCALL(__NR_sched_setattr, sys_sched_setattr) +#define __NR_sched_getattr 275 +__SYSCALL(__NR_sched_getattr, sys_sched_getattr) #undef __NR_syscalls -#define __NR_syscalls 274 +#define __NR_syscalls 276 /* * All syscalls below here should go away really, diff --git a/include/uapi/drm/drm.h b/include/uapi/drm/drm.h index 3c9a833992e8..b06c8ed68707 100644 --- a/include/uapi/drm/drm.h +++ b/include/uapi/drm/drm.h @@ -619,6 +619,8 @@ struct drm_gem_open { #define DRM_PRIME_CAP_EXPORT 0x2 #define DRM_CAP_TIMESTAMP_MONOTONIC 0x6 #define DRM_CAP_ASYNC_PAGE_FLIP 0x7 +#define DRM_CAP_CURSOR_WIDTH 0x8 +#define DRM_CAP_CURSOR_HEIGHT 0x9 /** DRM_IOCTL_GET_CAP ioctl argument type */ struct drm_get_cap { diff --git a/include/uapi/drm/vmwgfx_drm.h b/include/uapi/drm/vmwgfx_drm.h index 9971c560ed9a..87792a5fee3b 100644 --- a/include/uapi/drm/vmwgfx_drm.h +++ b/include/uapi/drm/vmwgfx_drm.h @@ -87,6 +87,7 @@ #define DRM_VMW_PARAM_MAX_SURF_MEMORY 7 #define DRM_VMW_PARAM_3D_CAPS_SIZE 8 #define DRM_VMW_PARAM_MAX_MOB_MEMORY 9 +#define DRM_VMW_PARAM_MAX_MOB_SIZE 10 /** * struct drm_vmw_getparam_arg diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h index 1b8a0f4c9590..b4d69092fbdb 100644 --- a/include/uapi/linux/btrfs.h +++ b/include/uapi/linux/btrfs.h @@ -558,7 +558,6 @@ static inline char *btrfs_err_str(enum btrfs_err_code err_code) #define BTRFS_IOC_DEFAULT_SUBVOL _IOW(BTRFS_IOCTL_MAGIC, 19, __u64) #define BTRFS_IOC_SPACE_INFO _IOWR(BTRFS_IOCTL_MAGIC, 20, \ struct btrfs_ioctl_space_args) -#define BTRFS_IOC_GLOBAL_RSV _IOR(BTRFS_IOCTL_MAGIC, 20, __u64) #define BTRFS_IOC_START_SYNC _IOR(BTRFS_IOCTL_MAGIC, 24, __u64) #define BTRFS_IOC_WAIT_SYNC _IOW(BTRFS_IOCTL_MAGIC, 22, __u64) #define BTRFS_IOC_SNAP_CREATE_V2 _IOW(BTRFS_IOCTL_MAGIC, 23, \ diff --git a/include/uapi/linux/can.h b/include/uapi/linux/can.h index e52958d7c2d1..5d9d1d140718 100644 --- a/include/uapi/linux/can.h +++ b/include/uapi/linux/can.h @@ -8,6 +8,38 @@ * Copyright (c) 2002-2007 Volkswagen Group Electronic Research * All rights reserved. * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. 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. + * 3. Neither the name of Volkswagen nor the names of its contributors + * may be used to endorse or promote products derived from this software + * without specific prior written permission. + * + * Alternatively, provided that this notice is retained in full, this + * software may be distributed under the terms of the GNU General + * Public License ("GPL") version 2, in which case the provisions of the + * GPL apply INSTEAD OF those given above. + * + * The provided data structures and external interfaces from this code + * are not restricted to be used by modules with a GPL compatible license. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH + * DAMAGE. */ #ifndef CAN_H diff --git a/include/uapi/linux/can/netlink.h b/include/uapi/linux/can/netlink.h index df944ed206a8..7e2e1863db16 100644 --- a/include/uapi/linux/can/netlink.h +++ b/include/uapi/linux/can/netlink.h @@ -96,6 +96,7 @@ struct can_ctrlmode { #define CAN_CTRLMODE_3_SAMPLES 0x04 /* Triple sampling mode */ #define CAN_CTRLMODE_ONE_SHOT 0x08 /* One-Shot mode */ #define CAN_CTRLMODE_BERR_REPORTING 0x10 /* Bus-error reporting */ +#define CAN_CTRLMODE_FD 0x20 /* CAN FD mode */ /* * CAN device statistics @@ -122,6 +123,8 @@ enum { IFLA_CAN_RESTART_MS, IFLA_CAN_RESTART, IFLA_CAN_BERR_COUNTER, + IFLA_CAN_DATA_BITTIMING, + IFLA_CAN_DATA_BITTIMING_CONST, __IFLA_CAN_MAX }; diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 38dbafaa5341..fd161e91b6d7 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -16,37 +16,97 @@ #include <linux/types.h> #include <linux/if_ether.h> -/* This should work for both 32 and 64 bit userland. */ +/* All structures exposed to userland should be defined such that they + * have the same layout for 32-bit and 64-bit userland. + */ + +/** + * struct ethtool_cmd - link control and status + * @cmd: Command number = %ETHTOOL_GSET or %ETHTOOL_SSET + * @supported: Bitmask of %SUPPORTED_* flags for the link modes, + * physical connectors and other link features for which the + * interface supports autonegotiation or auto-detection. + * Read-only. + * @advertising: Bitmask of %ADVERTISED_* flags for the link modes, + * physical connectors and other link features that are + * advertised through autonegotiation or enabled for + * auto-detection. + * @speed: Low bits of the speed + * @duplex: Duplex mode; one of %DUPLEX_* + * @port: Physical connector type; one of %PORT_* + * @phy_address: MDIO address of PHY (transceiver); 0 or 255 if not + * applicable. For clause 45 PHYs this is the PRTAD. + * @transceiver: Historically used to distinguish different possible + * PHY types, but not in a consistent way. Deprecated. + * @autoneg: Enable/disable autonegotiation and auto-detection; + * either %AUTONEG_DISABLE or %AUTONEG_ENABLE + * @mdio_support: Bitmask of %ETH_MDIO_SUPPORTS_* flags for the MDIO + * protocols supported by the interface; 0 if unknown. + * Read-only. + * @maxtxpkt: Historically used to report TX IRQ coalescing; now + * obsoleted by &struct ethtool_coalesce. Read-only; deprecated. + * @maxrxpkt: Historically used to report RX IRQ coalescing; now + * obsoleted by &struct ethtool_coalesce. Read-only; deprecated. + * @speed_hi: High bits of the speed + * @eth_tp_mdix: Ethernet twisted-pair MDI(-X) status; one of + * %ETH_TP_MDI_*. If the status is unknown or not applicable, the + * value will be %ETH_TP_MDI_INVALID. Read-only. + * @eth_tp_mdix_ctrl: Ethernet twisted pair MDI(-X) control; one of + * %ETH_TP_MDI_*. If MDI(-X) control is not implemented, reads + * yield %ETH_TP_MDI_INVALID and writes may be ignored or rejected. + * When written successfully, the link should be renegotiated if + * necessary. + * @lp_advertising: Bitmask of %ADVERTISED_* flags for the link modes + * and other link features that the link partner advertised + * through autonegotiation; 0 if unknown or not applicable. + * Read-only. + * + * The link speed in Mbps is split between @speed and @speed_hi. Use + * the ethtool_cmd_speed() and ethtool_cmd_speed_set() functions to + * access it. + * + * If autonegotiation is disabled, the speed and @duplex represent the + * fixed link mode and are writable if the driver supports multiple + * link modes. If it is enabled then they are read-only; if the link + * is up they represent the negotiated link mode; if the link is down, + * the speed is 0, %SPEED_UNKNOWN or the highest enabled speed and + * @duplex is %DUPLEX_UNKNOWN or the best enabled duplex mode. + * + * Some hardware interfaces may have multiple PHYs and/or physical + * connectors fitted or do not allow the driver to detect which are + * fitted. For these interfaces @port and/or @phy_address may be + * writable, possibly dependent on @autoneg being %AUTONEG_DISABLE. + * Otherwise, attempts to write different values may be ignored or + * rejected. + * + * Users should assume that all fields not marked read-only are + * writable and subject to validation by the driver. They should use + * %ETHTOOL_GSET to get the current values before making specific + * changes and then applying them with %ETHTOOL_SSET. + * + * Drivers that implement set_settings() should validate all fields + * other than @cmd that are not described as read-only or deprecated, + * and must ignore all fields described as read-only. + * + * Deprecated fields should be ignored by both users and drivers. + */ struct ethtool_cmd { __u32 cmd; - __u32 supported; /* Features this interface supports */ - __u32 advertising; /* Features this interface advertises */ - __u16 speed; /* The forced speed (lower bits) in - * Mbps. Please use - * ethtool_cmd_speed()/_set() to - * access it */ - __u8 duplex; /* Duplex, half or full */ - __u8 port; /* Which connector port */ - __u8 phy_address; /* MDIO PHY address (PRTAD for clause 45). - * May be read-only or read-write - * depending on the driver. - */ - __u8 transceiver; /* Which transceiver to use */ - __u8 autoneg; /* Enable or disable autonegotiation */ - __u8 mdio_support; /* MDIO protocols supported. Read-only. - * Not set by all drivers. - */ - __u32 maxtxpkt; /* Tx pkts before generating tx int */ - __u32 maxrxpkt; /* Rx pkts before generating rx int */ - __u16 speed_hi; /* The forced speed (upper - * bits) in Mbps. Please use - * ethtool_cmd_speed()/_set() to - * access it */ - __u8 eth_tp_mdix; /* twisted pair MDI-X status */ - __u8 eth_tp_mdix_ctrl; /* twisted pair MDI-X control, when set, - * link should be renegotiated if necessary - */ - __u32 lp_advertising; /* Features the link partner advertises */ + __u32 supported; + __u32 advertising; + __u16 speed; + __u8 duplex; + __u8 port; + __u8 phy_address; + __u8 transceiver; + __u8 autoneg; + __u8 mdio_support; + __u32 maxtxpkt; + __u32 maxrxpkt; + __u16 speed_hi; + __u8 eth_tp_mdix; + __u8 eth_tp_mdix_ctrl; + __u32 lp_advertising; __u32 reserved[2]; }; @@ -79,37 +139,68 @@ static inline __u32 ethtool_cmd_speed(const struct ethtool_cmd *ep) #define ETHTOOL_FWVERS_LEN 32 #define ETHTOOL_BUSINFO_LEN 32 -/* these strings are set to whatever the driver author decides... */ + +/** + * struct ethtool_drvinfo - general driver and device information + * @cmd: Command number = %ETHTOOL_GDRVINFO + * @driver: Driver short name. This should normally match the name + * in its bus driver structure (e.g. pci_driver::name). Must + * not be an empty string. + * @version: Driver version string; may be an empty string + * @fw_version: Firmware version string; may be an empty string + * @bus_info: Device bus address. This should match the dev_name() + * string for the underlying bus device, if there is one. May be + * an empty string. + * @n_priv_flags: Number of flags valid for %ETHTOOL_GPFLAGS and + * %ETHTOOL_SPFLAGS commands; also the number of strings in the + * %ETH_SS_PRIV_FLAGS set + * @n_stats: Number of u64 statistics returned by the %ETHTOOL_GSTATS + * command; also the number of strings in the %ETH_SS_STATS set + * @testinfo_len: Number of results returned by the %ETHTOOL_TEST + * command; also the number of strings in the %ETH_SS_TEST set + * @eedump_len: Size of EEPROM accessible through the %ETHTOOL_GEEPROM + * and %ETHTOOL_SEEPROM commands, in bytes + * @regdump_len: Size of register dump returned by the %ETHTOOL_GREGS + * command, in bytes + * + * Users can use the %ETHTOOL_GSSET_INFO command to get the number of + * strings in any string set (from Linux 2.6.34). + * + * Drivers should set at most @driver, @version, @fw_version and + * @bus_info in their get_drvinfo() implementation. The ethtool + * core fills in the other fields using other driver operations. + */ struct ethtool_drvinfo { __u32 cmd; - char driver[32]; /* driver short name, "tulip", "eepro100" */ - char version[32]; /* driver version string */ - char fw_version[ETHTOOL_FWVERS_LEN]; /* firmware version string */ - char bus_info[ETHTOOL_BUSINFO_LEN]; /* Bus info for this IF. */ - /* For PCI devices, use pci_name(pci_dev). */ + char driver[32]; + char version[32]; + char fw_version[ETHTOOL_FWVERS_LEN]; + char bus_info[ETHTOOL_BUSINFO_LEN]; char reserved1[32]; char reserved2[12]; - /* - * Some struct members below are filled in - * using ops->get_sset_count(). Obtaining - * this info from ethtool_drvinfo is now - * deprecated; Use ETHTOOL_GSSET_INFO - * instead. - */ - __u32 n_priv_flags; /* number of flags valid in ETHTOOL_GPFLAGS */ - __u32 n_stats; /* number of u64's from ETHTOOL_GSTATS */ + __u32 n_priv_flags; + __u32 n_stats; __u32 testinfo_len; - __u32 eedump_len; /* Size of data from ETHTOOL_GEEPROM (bytes) */ - __u32 regdump_len; /* Size of data from ETHTOOL_GREGS (bytes) */ + __u32 eedump_len; + __u32 regdump_len; }; #define SOPASS_MAX 6 -/* wake-on-lan settings */ + +/** + * struct ethtool_wolinfo - Wake-On-Lan configuration + * @cmd: Command number = %ETHTOOL_GWOL or %ETHTOOL_SWOL + * @supported: Bitmask of %WAKE_* flags for supported Wake-On-Lan modes. + * Read-only. + * @wolopts: Bitmask of %WAKE_* flags for enabled Wake-On-Lan modes. + * @sopass: SecureOn(tm) password; meaningful only if %WAKE_MAGICSECURE + * is set in @wolopts. + */ struct ethtool_wolinfo { __u32 cmd; __u32 supported; __u32 wolopts; - __u8 sopass[SOPASS_MAX]; /* SecureOn(tm) password */ + __u8 sopass[SOPASS_MAX]; }; /* for passing single values */ @@ -118,20 +209,51 @@ struct ethtool_value { __u32 data; }; -/* for passing big chunks of data */ +/** + * struct ethtool_regs - hardware register dump + * @cmd: Command number = %ETHTOOL_GREGS + * @version: Dump format version. This is driver-specific and may + * distinguish different chips/revisions. Drivers must use new + * version numbers whenever the dump format changes in an + * incompatible way. + * @len: On entry, the real length of @data. On return, the number of + * bytes used. + * @data: Buffer for the register dump + * + * Users should use %ETHTOOL_GDRVINFO to find the maximum length of + * a register dump for the interface. They must allocate the buffer + * immediately following this structure. + */ struct ethtool_regs { __u32 cmd; - __u32 version; /* driver-specific, indicates different chips/revs */ - __u32 len; /* bytes */ + __u32 version; + __u32 len; __u8 data[0]; }; -/* for passing EEPROM chunks */ +/** + * struct ethtool_eeprom - EEPROM dump + * @cmd: Command number = %ETHTOOL_GEEPROM, %ETHTOOL_GMODULEEEPROM or + * %ETHTOOL_SEEPROM + * @magic: A 'magic cookie' value to guard against accidental changes. + * The value passed in to %ETHTOOL_SEEPROM must match the value + * returned by %ETHTOOL_GEEPROM for the same device. This is + * unused when @cmd is %ETHTOOL_GMODULEEEPROM. + * @offset: Offset within the EEPROM to begin reading/writing, in bytes + * @len: On entry, number of bytes to read/write. On successful + * return, number of bytes actually read/written. In case of + * error, this may indicate at what point the error occurred. + * @data: Buffer to read/write from + * + * Users may use %ETHTOOL_GDRVINFO or %ETHTOOL_GMODULEINFO to find + * the length of an on-board or module EEPROM, respectively. They + * must allocate the buffer immediately following this structure. + */ struct ethtool_eeprom { __u32 cmd; __u32 magic; - __u32 offset; /* in bytes */ - __u32 len; /* in bytes */ + __u32 offset; + __u32 len; __u8 data[0]; }; @@ -229,17 +351,18 @@ struct ethtool_modinfo { * @rate_sample_interval: How often to do adaptive coalescing packet rate * sampling, measured in seconds. Must not be zero. * - * Each pair of (usecs, max_frames) fields specifies this exit - * condition for interrupt coalescing: + * Each pair of (usecs, max_frames) fields specifies that interrupts + * should be coalesced until * (usecs > 0 && time_since_first_completion >= usecs) || * (max_frames > 0 && completed_frames >= max_frames) + * * It is illegal to set both usecs and max_frames to zero as this * would cause interrupts to never be generated. To disable * coalescing, set usecs = 0 and max_frames = 1. * * Some implementations ignore the value of max_frames and use the - * condition: - * time_since_first_completion >= usecs + * condition time_since_first_completion >= usecs + * * This is deprecated. Drivers for hardware that does not support * counting completions should validate that max_frames == !rx_usecs. * @@ -279,22 +402,37 @@ struct ethtool_coalesce { __u32 rate_sample_interval; }; -/* for configuring RX/TX ring parameters */ +/** + * struct ethtool_ringparam - RX/TX ring parameters + * @cmd: Command number = %ETHTOOL_GRINGPARAM or %ETHTOOL_SRINGPARAM + * @rx_max_pending: Maximum supported number of pending entries per + * RX ring. Read-only. + * @rx_mini_max_pending: Maximum supported number of pending entries + * per RX mini ring. Read-only. + * @rx_jumbo_max_pending: Maximum supported number of pending entries + * per RX jumbo ring. Read-only. + * @tx_max_pending: Maximum supported number of pending entries per + * TX ring. Read-only. + * @rx_pending: Current maximum number of pending entries per RX ring + * @rx_mini_pending: Current maximum number of pending entries per RX + * mini ring + * @rx_jumbo_pending: Current maximum number of pending entries per RX + * jumbo ring + * @tx_pending: Current maximum supported number of pending entries + * per TX ring + * + * If the interface does not have separate RX mini and/or jumbo rings, + * @rx_mini_max_pending and/or @rx_jumbo_max_pending will be 0. + * + * There may also be driver-dependent minimum values for the number + * of entries per ring. + */ struct ethtool_ringparam { - __u32 cmd; /* ETHTOOL_{G,S}RINGPARAM */ - - /* Read only attributes. These indicate the maximum number - * of pending RX/TX ring entries the driver will allow the - * user to set. - */ + __u32 cmd; __u32 rx_max_pending; __u32 rx_mini_max_pending; __u32 rx_jumbo_max_pending; __u32 tx_max_pending; - - /* Values changeable by the user. The valid values are - * in the range 1 to the "*_max_pending" counterpart above. - */ __u32 rx_pending; __u32 rx_mini_pending; __u32 rx_jumbo_pending; @@ -329,51 +467,96 @@ struct ethtool_channels { __u32 combined_count; }; -/* for configuring link flow control parameters */ +/** + * struct ethtool_pauseparam - Ethernet pause (flow control) parameters + * @cmd: Command number = %ETHTOOL_GPAUSEPARAM or %ETHTOOL_SPAUSEPARAM + * @autoneg: Flag to enable autonegotiation of pause frame use + * @rx_pause: Flag to enable reception of pause frames + * @tx_pause: Flag to enable transmission of pause frames + * + * Drivers should reject a non-zero setting of @autoneg when + * autoneogotiation is disabled (or not supported) for the link. + * + * If the link is autonegotiated, drivers should use + * mii_advertise_flowctrl() or similar code to set the advertised + * pause frame capabilities based on the @rx_pause and @tx_pause flags, + * even if @autoneg is zero. They should also allow the advertised + * pause frame capabilities to be controlled directly through the + * advertising field of &struct ethtool_cmd. + * + * If @autoneg is non-zero, the MAC is configured to send and/or + * receive pause frames according to the result of autonegotiation. + * Otherwise, it is configured directly based on the @rx_pause and + * @tx_pause flags. + */ struct ethtool_pauseparam { - __u32 cmd; /* ETHTOOL_{G,S}PAUSEPARAM */ - - /* If the link is being auto-negotiated (via ethtool_cmd.autoneg - * being true) the user may set 'autoneg' here non-zero to have the - * pause parameters be auto-negotiated too. In such a case, the - * {rx,tx}_pause values below determine what capabilities are - * advertised. - * - * If 'autoneg' is zero or the link is not being auto-negotiated, - * then {rx,tx}_pause force the driver to use/not-use pause - * flow control. - */ + __u32 cmd; __u32 autoneg; __u32 rx_pause; __u32 tx_pause; }; #define ETH_GSTRING_LEN 32 + +/** + * enum ethtool_stringset - string set ID + * @ETH_SS_TEST: Self-test result names, for use with %ETHTOOL_TEST + * @ETH_SS_STATS: Statistic names, for use with %ETHTOOL_GSTATS + * @ETH_SS_PRIV_FLAGS: Driver private flag names, for use with + * %ETHTOOL_GPFLAGS and %ETHTOOL_SPFLAGS + * @ETH_SS_NTUPLE_FILTERS: Previously used with %ETHTOOL_GRXNTUPLE; + * now deprecated + * @ETH_SS_FEATURES: Device feature names + */ enum ethtool_stringset { ETH_SS_TEST = 0, ETH_SS_STATS, ETH_SS_PRIV_FLAGS, - ETH_SS_NTUPLE_FILTERS, /* Do not use, GRXNTUPLE is now deprecated */ + ETH_SS_NTUPLE_FILTERS, ETH_SS_FEATURES, }; -/* for passing string sets for data tagging */ +/** + * struct ethtool_gstrings - string set for data tagging + * @cmd: Command number = %ETHTOOL_GSTRINGS + * @string_set: String set ID; one of &enum ethtool_stringset + * @len: On return, the number of strings in the string set + * @data: Buffer for strings. Each string is null-padded to a size of + * %ETH_GSTRING_LEN. + * + * Users must use %ETHTOOL_GSSET_INFO to find the number of strings in + * the string set. They must allocate a buffer of the appropriate + * size immediately following this structure. + */ struct ethtool_gstrings { - __u32 cmd; /* ETHTOOL_GSTRINGS */ - __u32 string_set; /* string set id e.c. ETH_SS_TEST, etc*/ - __u32 len; /* number of strings in the string set */ + __u32 cmd; + __u32 string_set; + __u32 len; __u8 data[0]; }; +/** + * struct ethtool_sset_info - string set information + * @cmd: Command number = %ETHTOOL_GSSET_INFO + * @sset_mask: On entry, a bitmask of string sets to query, with bits + * numbered according to &enum ethtool_stringset. On return, a + * bitmask of those string sets queried that are supported. + * @data: Buffer for string set sizes. On return, this contains the + * size of each string set that was queried and supported, in + * order of ID. + * + * Example: The user passes in @sset_mask = 0x7 (sets 0, 1, 2) and on + * return @sset_mask == 0x6 (sets 1, 2). Then @data[0] contains the + * size of set 1 and @data[1] contains the size of set 2. + * + * Users must allocate a buffer of the appropriate size (4 * number of + * sets queried) immediately following this structure. + */ struct ethtool_sset_info { - __u32 cmd; /* ETHTOOL_GSSET_INFO */ + __u32 cmd; __u32 reserved; - __u64 sset_mask; /* input: each bit selects an sset to query */ - /* output: each bit a returned sset */ - __u32 data[0]; /* ETH_SS_xxx count, in order, based on bits - in sset_mask. One bit implies one - __u32, two bits implies two - __u32's, etc. */ + __u64 sset_mask; + __u32 data[0]; }; /** @@ -393,24 +576,58 @@ enum ethtool_test_flags { ETH_TEST_FL_EXTERNAL_LB_DONE = (1 << 3), }; -/* for requesting NIC test and getting results*/ +/** + * struct ethtool_test - device self-test invocation + * @cmd: Command number = %ETHTOOL_TEST + * @flags: A bitmask of flags from &enum ethtool_test_flags. Some + * flags may be set by the user on entry; others may be set by + * the driver on return. + * @len: On return, the number of test results + * @data: Array of test results + * + * Users must use %ETHTOOL_GSSET_INFO or %ETHTOOL_GDRVINFO to find the + * number of test results that will be returned. They must allocate a + * buffer of the appropriate size (8 * number of results) immediately + * following this structure. + */ struct ethtool_test { - __u32 cmd; /* ETHTOOL_TEST */ - __u32 flags; /* ETH_TEST_FL_xxx */ + __u32 cmd; + __u32 flags; __u32 reserved; - __u32 len; /* result length, in number of u64 elements */ + __u32 len; __u64 data[0]; }; -/* for dumping NIC-specific statistics */ +/** + * struct ethtool_stats - device-specific statistics + * @cmd: Command number = %ETHTOOL_GSTATS + * @n_stats: On return, the number of statistics + * @data: Array of statistics + * + * Users must use %ETHTOOL_GSSET_INFO or %ETHTOOL_GDRVINFO to find the + * number of statistics that will be returned. They must allocate a + * buffer of the appropriate size (8 * number of statistics) + * immediately following this structure. + */ struct ethtool_stats { - __u32 cmd; /* ETHTOOL_GSTATS */ - __u32 n_stats; /* number of u64's being returned */ + __u32 cmd; + __u32 n_stats; __u64 data[0]; }; +/** + * struct ethtool_perm_addr - permanent hardware address + * @cmd: Command number = %ETHTOOL_GPERMADDR + * @size: On entry, the size of the buffer. On return, the size of the + * address. The command fails if the buffer is too small. + * @data: Buffer for the address + * + * Users must allocate the buffer immediately following this structure. + * A buffer size of %MAX_ADDR_LEN should be sufficient for any address + * type. + */ struct ethtool_perm_addr { - __u32 cmd; /* ETHTOOL_GPERMADDR */ + __u32 cmd; __u32 size; __u8 data[0]; }; @@ -593,7 +810,7 @@ struct ethtool_rx_flow_spec { * %ETHTOOL_SRXCLSRLINS may add the rule at any suitable unused * location, and may remove a rule at a later location (lower * priority) that matches exactly the same set of flows. The special - * values are: %RX_CLS_LOC_ANY, selecting any location; + * values are %RX_CLS_LOC_ANY, selecting any location; * %RX_CLS_LOC_FIRST, selecting the first suitable location (maximum * priority); and %RX_CLS_LOC_LAST, selecting the last suitable * location (minimum priority). Additional special values may be @@ -704,9 +921,6 @@ struct ethtool_flash { * for %ETHTOOL_GET_DUMP_FLAG command * @data: data collected for get dump data operation */ - -#define ETH_FW_DUMP_DISABLE 0 - struct ethtool_dump { __u32 cmd; __u32 version; @@ -715,6 +929,8 @@ struct ethtool_dump { __u8 data[0]; }; +#define ETH_FW_DUMP_DISABLE 0 + /* for returning and changing feature sets */ /** @@ -734,8 +950,9 @@ struct ethtool_get_features_block { /** * struct ethtool_gfeatures - command to get state of device's features * @cmd: command number = %ETHTOOL_GFEATURES - * @size: in: number of elements in the features[] array; - * out: number of elements in features[] needed to hold all features + * @size: On entry, the number of elements in the features[] array; + * on return, the number of elements in features[] needed to hold + * all features * @features: state of features */ struct ethtool_gfeatures { @@ -905,7 +1122,6 @@ enum ethtool_sfeatures_retval_bits { #define SPARC_ETH_GSET ETHTOOL_GSET #define SPARC_ETH_SSET ETHTOOL_SSET -/* Indicates what features are supported by the interface. */ #define SUPPORTED_10baseT_Half (1 << 0) #define SUPPORTED_10baseT_Full (1 << 1) #define SUPPORTED_100baseT_Half (1 << 2) @@ -934,7 +1150,6 @@ enum ethtool_sfeatures_retval_bits { #define SUPPORTED_40000baseSR4_Full (1 << 25) #define SUPPORTED_40000baseLR4_Full (1 << 26) -/* Indicates what features are advertised by the interface. */ #define ADVERTISED_10baseT_Half (1 << 0) #define ADVERTISED_10baseT_Full (1 << 1) #define ADVERTISED_100baseT_Half (1 << 2) @@ -999,9 +1214,7 @@ enum ethtool_sfeatures_retval_bits { #define XCVR_DUMMY2 0x03 #define XCVR_DUMMY3 0x04 -/* Enable or disable autonegotiation. If this is set to enable, - * the forced link modes above are completely ignored. - */ +/* Enable or disable autonegotiation. */ #define AUTONEG_DISABLE 0x00 #define AUTONEG_ENABLE 0x01 diff --git a/include/uapi/linux/if.h b/include/uapi/linux/if.h index d758163b0e43..9cf2394f0bcf 100644 --- a/include/uapi/linux/if.h +++ b/include/uapi/linux/if.h @@ -27,65 +27,91 @@ #define IFALIASZ 256 #include <linux/hdlc/ioctl.h> -/* Standard interface flags (netdevice->flags). */ -#define IFF_UP 0x1 /* interface is up */ -#define IFF_BROADCAST 0x2 /* broadcast address valid */ -#define IFF_DEBUG 0x4 /* turn on debugging */ -#define IFF_LOOPBACK 0x8 /* is a loopback net */ -#define IFF_POINTOPOINT 0x10 /* interface is has p-p link */ -#define IFF_NOTRAILERS 0x20 /* avoid use of trailers */ -#define IFF_RUNNING 0x40 /* interface RFC2863 OPER_UP */ -#define IFF_NOARP 0x80 /* no ARP protocol */ -#define IFF_PROMISC 0x100 /* receive all packets */ -#define IFF_ALLMULTI 0x200 /* receive all multicast packets*/ - -#define IFF_MASTER 0x400 /* master of a load balancer */ -#define IFF_SLAVE 0x800 /* slave of a load balancer */ - -#define IFF_MULTICAST 0x1000 /* Supports multicast */ - -#define IFF_PORTSEL 0x2000 /* can set media type */ -#define IFF_AUTOMEDIA 0x4000 /* auto media select active */ -#define IFF_DYNAMIC 0x8000 /* dialup device with changing addresses*/ - -#define IFF_LOWER_UP 0x10000 /* driver signals L1 up */ -#define IFF_DORMANT 0x20000 /* driver signals dormant */ +/** + * enum net_device_flags - &struct net_device flags + * + * These are the &struct net_device flags, they can be set by drivers, the + * kernel and some can be triggered by userspace. Userspace can query and + * set these flags using userspace utilities but there is also a sysfs + * entry available for all dev flags which can be queried and set. These flags + * are shared for all types of net_devices. The sysfs entries are available + * via /sys/class/net/<dev>/flags. Flags which can be toggled through sysfs + * are annotated below, note that only a few flags can be toggled and some + * other flags are always always preserved from the original net_device flags + * even if you try to set them via sysfs. Flags which are always preserved + * are kept under the flag grouping @IFF_VOLATILE. Flags which are volatile + * are annotated below as such. + * + * You should have a pretty good reason to be extending these flags. + * + * @IFF_UP: interface is up. Can be toggled through sysfs. + * @IFF_BROADCAST: broadcast address valid. Volatile. + * @IFF_DEBUG: turn on debugging. Can be toggled through sysfs. + * @IFF_LOOPBACK: is a loopback net. Volatile. + * @IFF_POINTOPOINT: interface is has p-p link. Volatile. + * @IFF_NOTRAILERS: avoid use of trailers. Can be toggled through sysfs. + * Volatile. + * @IFF_RUNNING: interface RFC2863 OPER_UP. Volatile. + * @IFF_NOARP: no ARP protocol. Can be toggled through sysfs. Volatile. + * @IFF_PROMISC: receive all packets. Can be toggled through sysfs. + * @IFF_ALLMULTI: receive all multicast packets. Can be toggled through + * sysfs. + * @IFF_MASTER: master of a load balancer. Volatile. + * @IFF_SLAVE: slave of a load balancer. Volatile. + * @IFF_MULTICAST: Supports multicast. Can be toggled through sysfs. + * @IFF_PORTSEL: can set media type. Can be toggled through sysfs. + * @IFF_AUTOMEDIA: auto media select active. Can be toggled through sysfs. + * @IFF_DYNAMIC: dialup device with changing addresses. Can be toggled + * through sysfs. + * @IFF_LOWER_UP: driver signals L1 up. Volatile. + * @IFF_DORMANT: driver signals dormant. Volatile. + * @IFF_ECHO: echo sent packets. Volatile. + */ +enum net_device_flags { + IFF_UP = 1<<0, /* sysfs */ + IFF_BROADCAST = 1<<1, /* volatile */ + IFF_DEBUG = 1<<2, /* sysfs */ + IFF_LOOPBACK = 1<<3, /* volatile */ + IFF_POINTOPOINT = 1<<4, /* volatile */ + IFF_NOTRAILERS = 1<<5, /* sysfs */ + IFF_RUNNING = 1<<6, /* volatile */ + IFF_NOARP = 1<<7, /* sysfs */ + IFF_PROMISC = 1<<8, /* sysfs */ + IFF_ALLMULTI = 1<<9, /* sysfs */ + IFF_MASTER = 1<<10, /* volatile */ + IFF_SLAVE = 1<<11, /* volatile */ + IFF_MULTICAST = 1<<12, /* sysfs */ + IFF_PORTSEL = 1<<13, /* sysfs */ + IFF_AUTOMEDIA = 1<<14, /* sysfs */ + IFF_DYNAMIC = 1<<15, /* sysfs */ + IFF_LOWER_UP = 1<<16, /* volatile */ + IFF_DORMANT = 1<<17, /* volatile */ + IFF_ECHO = 1<<18, /* volatile */ +}; -#define IFF_ECHO 0x40000 /* echo sent packets */ +#define IFF_UP IFF_UP +#define IFF_BROADCAST IFF_BROADCAST +#define IFF_DEBUG IFF_DEBUG +#define IFF_LOOPBACK IFF_LOOPBACK +#define IFF_POINTOPOINT IFF_POINTOPOINT +#define IFF_NOTRAILERS IFF_NOTRAILERS +#define IFF_RUNNING IFF_RUNNING +#define IFF_NOARP IFF_NOARP +#define IFF_PROMISC IFF_PROMISC +#define IFF_ALLMULTI IFF_ALLMULTI +#define IFF_MASTER IFF_MASTER +#define IFF_SLAVE IFF_SLAVE +#define IFF_MULTICAST IFF_MULTICAST +#define IFF_PORTSEL IFF_PORTSEL +#define IFF_AUTOMEDIA IFF_AUTOMEDIA +#define IFF_DYNAMIC IFF_DYNAMIC +#define IFF_LOWER_UP IFF_LOWER_UP +#define IFF_DORMANT IFF_DORMANT +#define IFF_ECHO IFF_ECHO #define IFF_VOLATILE (IFF_LOOPBACK|IFF_POINTOPOINT|IFF_BROADCAST|IFF_ECHO|\ IFF_MASTER|IFF_SLAVE|IFF_RUNNING|IFF_LOWER_UP|IFF_DORMANT) -/* Private (from user) interface flags (netdevice->priv_flags). */ -#define IFF_802_1Q_VLAN 0x1 /* 802.1Q VLAN device. */ -#define IFF_EBRIDGE 0x2 /* Ethernet bridging device. */ -#define IFF_SLAVE_INACTIVE 0x4 /* bonding slave not the curr. active */ -#define IFF_MASTER_8023AD 0x8 /* bonding master, 802.3ad. */ -#define IFF_MASTER_ALB 0x10 /* bonding master, balance-alb. */ -#define IFF_BONDING 0x20 /* bonding master or slave */ -#define IFF_SLAVE_NEEDARP 0x40 /* need ARPs for validation */ -#define IFF_ISATAP 0x80 /* ISATAP interface (RFC4214) */ -#define IFF_MASTER_ARPMON 0x100 /* bonding master, ARP mon in use */ -#define IFF_WAN_HDLC 0x200 /* WAN HDLC device */ -#define IFF_XMIT_DST_RELEASE 0x400 /* dev_hard_start_xmit() is allowed to - * release skb->dst - */ -#define IFF_DONT_BRIDGE 0x800 /* disallow bridging this ether dev */ -#define IFF_DISABLE_NETPOLL 0x1000 /* disable netpoll at run-time */ -#define IFF_MACVLAN_PORT 0x2000 /* device used as macvlan port */ -#define IFF_BRIDGE_PORT 0x4000 /* device used as bridge port */ -#define IFF_OVS_DATAPATH 0x8000 /* device used as Open vSwitch - * datapath port */ -#define IFF_TX_SKB_SHARING 0x10000 /* The interface supports sharing - * skbs on transmit */ -#define IFF_UNICAST_FLT 0x20000 /* Supports unicast filtering */ -#define IFF_TEAM_PORT 0x40000 /* device used as team port */ -#define IFF_SUPP_NOFCS 0x80000 /* device supports sending custom FCS */ -#define IFF_LIVE_ADDR_CHANGE 0x100000 /* device supports hardware address - * change when it's running */ -#define IFF_MACVLAN 0x200000 /* Macvlan device */ - - #define IF_GET_IFACE 0x0001 /* for querying only */ #define IF_GET_PROTO 0x0002 diff --git a/include/uapi/linux/if_ether.h b/include/uapi/linux/if_ether.h index 2ce0f6a78fa5..750ba67e0dc3 100644 --- a/include/uapi/linux/if_ether.h +++ b/include/uapi/linux/if_ether.h @@ -68,11 +68,11 @@ #define ETH_P_SLOW 0x8809 /* Slow Protocol. See 802.3ad 43B */ #define ETH_P_WCCP 0x883E /* Web-cache coordination protocol * defined in draft-wilson-wrec-wccp-v2-00.txt */ -#define ETH_P_PPP_DISC 0x8863 /* PPPoE discovery messages */ -#define ETH_P_PPP_SES 0x8864 /* PPPoE session messages */ #define ETH_P_MPLS_UC 0x8847 /* MPLS Unicast traffic */ #define ETH_P_MPLS_MC 0x8848 /* MPLS Multicast traffic */ #define ETH_P_ATMMPOA 0x884c /* MultiProtocol Over ATM */ +#define ETH_P_PPP_DISC 0x8863 /* PPPoE discovery messages */ +#define ETH_P_PPP_SES 0x8864 /* PPPoE session messages */ #define ETH_P_LINK_CTL 0x886c /* HPNA, wlan link local tunnel */ #define ETH_P_ATMFATE 0x8884 /* Frame-based ATM Transport * over Ethernet @@ -89,6 +89,7 @@ #define ETH_P_FCOE 0x8906 /* Fibre Channel over Ethernet */ #define ETH_P_TDLS 0x890D /* TDLS */ #define ETH_P_FIP 0x8914 /* FCoE Initialization Protocol */ +#define ETH_P_80221 0x8917 /* IEEE 802.21 Media Independent Handover Protocol */ #define ETH_P_QINQ1 0x9100 /* deprecated QinQ VLAN [ NOT AN OFFICIALLY REGISTERED ID ] */ #define ETH_P_QINQ2 0x9200 /* deprecated QinQ VLAN [ NOT AN OFFICIALLY REGISTERED ID ] */ #define ETH_P_QINQ3 0x9300 /* deprecated QinQ VLAN [ NOT AN OFFICIALLY REGISTERED ID ] */ diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h index 393c5de09d42..c33a65e3d62c 100644 --- a/include/uapi/linux/in.h +++ b/include/uapi/linux/in.h @@ -120,6 +120,10 @@ struct in_addr { * this socket to prevent accepting spoofed ones. */ #define IP_PMTUDISC_INTERFACE 4 +/* weaker version of IP_PMTUDISC_INTERFACE, which allos packets to get + * fragmented if they exeed the interface mtu + */ +#define IP_PMTUDISC_OMIT 5 #define IP_MULTICAST_IF 32 #define IP_MULTICAST_TTL 33 diff --git a/include/uapi/linux/in6.h b/include/uapi/linux/in6.h index 633b93cac1ed..0d8e0f0342dc 100644 --- a/include/uapi/linux/in6.h +++ b/include/uapi/linux/in6.h @@ -128,22 +128,13 @@ struct in6_flowlabel_req { * IPV6 extension headers */ #if __UAPI_DEF_IPPROTO_V6 -enum { - IPPROTO_HOPOPTS = 0, /* IPv6 hop-by-hop options */ -#define IPPROTO_HOPOPTS IPPROTO_HOPOPTS - IPPROTO_ROUTING = 43, /* IPv6 routing header */ -#define IPPROTO_ROUTING IPPROTO_ROUTING - IPPROTO_FRAGMENT = 44, /* IPv6 fragmentation header */ -#define IPPROTO_FRAGMENT IPPROTO_FRAGMENT - IPPROTO_ICMPV6 = 58, /* ICMPv6 */ -#define IPPROTO_ICMPV6 IPPROTO_ICMPV6 - IPPROTO_NONE = 59, /* IPv6 no next header */ -#define IPPROTO_NONE IPPROTO_NONE - IPPROTO_DSTOPTS = 60, /* IPv6 destination options */ -#define IPPROTO_DSTOPTS IPPROTO_DSTOPTS - IPPROTO_MH = 135, /* IPv6 mobility header */ -#define IPPROTO_MH IPPROTO_MH -}; +#define IPPROTO_HOPOPTS 0 /* IPv6 hop-by-hop options */ +#define IPPROTO_ROUTING 43 /* IPv6 routing header */ +#define IPPROTO_FRAGMENT 44 /* IPv6 fragmentation header */ +#define IPPROTO_ICMPV6 58 /* ICMPv6 */ +#define IPPROTO_NONE 59 /* IPv6 no next header */ +#define IPPROTO_DSTOPTS 60 /* IPv6 destination options */ +#define IPPROTO_MH 135 /* IPv6 mobility header */ #endif /* __UAPI_DEF_IPPROTO_V6 */ /* @@ -194,6 +185,10 @@ enum { * also see comments on IP_PMTUDISC_INTERFACE */ #define IPV6_PMTUDISC_INTERFACE 4 +/* weaker version of IPV6_PMTUDISC_INTERFACE, which allows packets to + * get fragmented if they exceed the interface mtu + */ +#define IPV6_PMTUDISC_OMIT 5 /* Flowlabel */ #define IPV6_FLOWLABEL_MGR 32 diff --git a/include/uapi/linux/mic_ioctl.h b/include/uapi/linux/mic_ioctl.h index 7fabba5059cf..feb0b4c0814c 100644 --- a/include/uapi/linux/mic_ioctl.h +++ b/include/uapi/linux/mic_ioctl.h @@ -39,7 +39,7 @@ struct mic_copy_desc { #else struct iovec *iov; #endif - int iovcnt; + __u32 iovcnt; __u8 vr_idx; __u8 update_used; __u32 out_len; diff --git a/include/uapi/linux/mpls.h b/include/uapi/linux/mpls.h new file mode 100644 index 000000000000..bc9abfe88c9a --- /dev/null +++ b/include/uapi/linux/mpls.h @@ -0,0 +1,34 @@ +#ifndef _UAPI_MPLS_H +#define _UAPI_MPLS_H + +#include <linux/types.h> +#include <asm/byteorder.h> + +/* Reference: RFC 5462, RFC 3032 + * + * 0 1 2 3 + * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * | Label | TC |S| TTL | + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * + * Label: Label Value, 20 bits + * TC: Traffic Class field, 3 bits + * S: Bottom of Stack, 1 bit + * TTL: Time to Live, 8 bits + */ + +struct mpls_label { + __be32 entry; +}; + +#define MPLS_LS_LABEL_MASK 0xFFFFF000 +#define MPLS_LS_LABEL_SHIFT 12 +#define MPLS_LS_TC_MASK 0x00000E00 +#define MPLS_LS_TC_SHIFT 9 +#define MPLS_LS_S_MASK 0x00000100 +#define MPLS_LS_S_SHIFT 8 +#define MPLS_LS_TTL_MASK 0x000000FF +#define MPLS_LS_TTL_SHIFT 0 + +#endif /* _UAPI_MPLS_H */ diff --git a/include/uapi/linux/pfkeyv2.h b/include/uapi/linux/pfkeyv2.h index 0b80c806631f..ada7f0171ccc 100644 --- a/include/uapi/linux/pfkeyv2.h +++ b/include/uapi/linux/pfkeyv2.h @@ -235,6 +235,18 @@ struct sadb_x_kmaddress { } __attribute__((packed)); /* sizeof(struct sadb_x_kmaddress) == 8 */ +/* To specify the SA dump filter */ +struct sadb_x_filter { + __u16 sadb_x_filter_len; + __u16 sadb_x_filter_exttype; + __u32 sadb_x_filter_saddr[4]; + __u32 sadb_x_filter_daddr[4]; + __u16 sadb_x_filter_family; + __u8 sadb_x_filter_splen; + __u8 sadb_x_filter_dplen; +} __attribute__((packed)); +/* sizeof(struct sadb_x_filter) == 40 */ + /* Message types */ #define SADB_RESERVED 0 #define SADB_GETSPI 1 @@ -358,7 +370,8 @@ struct sadb_x_kmaddress { #define SADB_X_EXT_SEC_CTX 24 /* Used with MIGRATE to pass @ to IKE for negotiation */ #define SADB_X_EXT_KMADDRESS 25 -#define SADB_EXT_MAX 25 +#define SADB_X_EXT_FILTER 26 +#define SADB_EXT_MAX 26 /* Identity Extension values */ #define SADB_IDENTTYPE_RESERVED 0 diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h index bbaba22f2d1b..df40137f33dd 100644 --- a/include/uapi/linux/snmp.h +++ b/include/uapi/linux/snmp.h @@ -252,6 +252,7 @@ enum LINUX_MIB_TCPCHALLENGEACK, /* TCPChallengeACK */ LINUX_MIB_TCPSYNCHALLENGE, /* TCPSYNChallenge */ LINUX_MIB_TCPFASTOPENACTIVE, /* TCPFastOpenActive */ + LINUX_MIB_TCPFASTOPENACTIVEFAIL, /* TCPFastOpenActiveFail */ LINUX_MIB_TCPFASTOPENPASSIVE, /* TCPFastOpenPassive*/ LINUX_MIB_TCPFASTOPENPASSIVEFAIL, /* TCPFastOpenPassiveFail */ LINUX_MIB_TCPFASTOPENLISTENOVERFLOW, /* TCPFastOpenListenOverflow */ @@ -259,6 +260,11 @@ enum LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES, /* TCPSpuriousRtxHostQueues */ LINUX_MIB_BUSYPOLLRXPACKETS, /* BusyPollRxPackets */ LINUX_MIB_TCPAUTOCORKING, /* TCPAutoCorking */ + LINUX_MIB_TCPFROMZEROWINDOWADV, /* TCPFromZeroWindowAdv */ + LINUX_MIB_TCPTOZEROWINDOWADV, /* TCPToZeroWindowAdv */ + LINUX_MIB_TCPWANTZEROWINDOWADV, /* TCPWantZeroWindowAdv */ + LINUX_MIB_TCPSYNRETRANS, /* TCPSynRetrans */ + LINUX_MIB_TCPORIGDATASENT, /* TCPOrigDataSent */ __LINUX_MIB_MAX }; diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index 377f1e59411d..3b9718328d8b 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -186,6 +186,9 @@ struct tcp_info { __u32 tcpi_rcv_space; __u32 tcpi_total_retrans; + + __u64 tcpi_pacing_rate; + __u64 tcpi_max_pacing_rate; }; /* for TCP_MD5SIG socket option */ diff --git a/include/uapi/linux/tcp_metrics.h b/include/uapi/linux/tcp_metrics.h index 54a37b13f2c4..93533926035c 100644 --- a/include/uapi/linux/tcp_metrics.h +++ b/include/uapi/linux/tcp_metrics.h @@ -11,12 +11,15 @@ #define TCP_METRICS_GENL_VERSION 0x1 enum tcp_metric_index { - TCP_METRIC_RTT, - TCP_METRIC_RTTVAR, + TCP_METRIC_RTT, /* in ms units */ + TCP_METRIC_RTTVAR, /* in ms units */ TCP_METRIC_SSTHRESH, TCP_METRIC_CWND, TCP_METRIC_REORDERING, + TCP_METRIC_RTT_US, /* in usec units */ + TCP_METRIC_RTTVAR_US, /* in usec units */ + /* Always last. */ __TCP_METRIC_MAX, }; diff --git a/include/uapi/linux/xfrm.h b/include/uapi/linux/xfrm.h index a8cd6a4a2970..6550c679584f 100644 --- a/include/uapi/linux/xfrm.h +++ b/include/uapi/linux/xfrm.h @@ -298,6 +298,8 @@ enum xfrm_attr_type_t { XFRMA_TFCPAD, /* __u32 */ XFRMA_REPLAY_ESN_VAL, /* struct xfrm_replay_esn */ XFRMA_SA_EXTRA_FLAGS, /* __u32 */ + XFRMA_PROTO, /* __u8 */ + XFRMA_FILTER, /* struct xfrm_filter */ __XFRMA_MAX #define XFRMA_MAX (__XFRMA_MAX - 1) @@ -474,6 +476,14 @@ struct xfrm_user_mapping { __be16 new_sport; }; +struct xfrm_filter { + xfrm_address_t saddr; + xfrm_address_t daddr; + __u16 family; + __u8 splen; + __u8 dplen; +}; + #ifndef __KERNEL__ /* backwards compatibility for userspace */ #define XFRMGRP_ACQUIRE 1 diff --git a/include/uapi/xen/Kbuild b/include/uapi/xen/Kbuild index 61257cb14653..5c459628e8c7 100644 --- a/include/uapi/xen/Kbuild +++ b/include/uapi/xen/Kbuild @@ -1,3 +1,5 @@ # UAPI Header export list header-y += evtchn.h +header-y += gntalloc.h +header-y += gntdev.h header-y += privcmd.h diff --git a/include/xen/gntalloc.h b/include/uapi/xen/gntalloc.h index 76bd58065f4f..76bd58065f4f 100644 --- a/include/xen/gntalloc.h +++ b/include/uapi/xen/gntalloc.h diff --git a/include/xen/gntdev.h b/include/uapi/xen/gntdev.h index 5304bd3c84c5..5304bd3c84c5 100644 --- a/include/xen/gntdev.h +++ b/include/uapi/xen/gntdev.h diff --git a/include/xen/interface/io/blkif.h b/include/xen/interface/io/blkif.h index ae665ac59c36..32ec05a6572f 100644 --- a/include/xen/interface/io/blkif.h +++ b/include/xen/interface/io/blkif.h @@ -113,13 +113,13 @@ typedef uint64_t blkif_sector_t; * it's less than the number provided by the backend. The indirect_grefs field * in blkif_request_indirect should be filled by the frontend with the * grant references of the pages that are holding the indirect segments. - * This pages are filled with an array of blkif_request_segment_aligned - * that hold the information about the segments. The number of indirect - * pages to use is determined by the maximum number of segments - * a indirect request contains. Every indirect page can contain a maximum - * of 512 segments (PAGE_SIZE/sizeof(blkif_request_segment_aligned)), - * so to calculate the number of indirect pages to use we have to do - * ceil(indirect_segments/512). + * These pages are filled with an array of blkif_request_segment that hold the + * information about the segments. The number of indirect pages to use is + * determined by the number of segments an indirect request contains. Every + * indirect page can contain a maximum of + * (PAGE_SIZE / sizeof(struct blkif_request_segment)) segments, so to + * calculate the number of indirect pages to use we have to do + * ceil(indirect_segments / (PAGE_SIZE / sizeof(struct blkif_request_segment))). * * If a backend does not recognize BLKIF_OP_INDIRECT, it should *not* * create the "feature-max-indirect-segments" node! @@ -135,13 +135,12 @@ typedef uint64_t blkif_sector_t; #define BLKIF_MAX_INDIRECT_PAGES_PER_REQUEST 8 -struct blkif_request_segment_aligned { - grant_ref_t gref; /* reference to I/O buffer frame */ - /* @first_sect: first sector in frame to transfer (inclusive). */ - /* @last_sect: last sector in frame to transfer (inclusive). */ - uint8_t first_sect, last_sect; - uint16_t _pad; /* padding to make it 8 bytes, so it's cache-aligned */ -} __attribute__((__packed__)); +struct blkif_request_segment { + grant_ref_t gref; /* reference to I/O buffer frame */ + /* @first_sect: first sector in frame to transfer (inclusive). */ + /* @last_sect: last sector in frame to transfer (inclusive). */ + uint8_t first_sect, last_sect; +}; struct blkif_request_rw { uint8_t nr_segments; /* number of segments */ @@ -151,12 +150,7 @@ struct blkif_request_rw { #endif uint64_t id; /* private guest value, echoed in resp */ blkif_sector_t sector_number;/* start sector idx on disk (r/w only) */ - struct blkif_request_segment { - grant_ref_t gref; /* reference to I/O buffer frame */ - /* @first_sect: first sector in frame to transfer (inclusive). */ - /* @last_sect: last sector in frame to transfer (inclusive). */ - uint8_t first_sect, last_sect; - } seg[BLKIF_MAX_SEGMENTS_PER_REQUEST]; + struct blkif_request_segment seg[BLKIF_MAX_SEGMENTS_PER_REQUEST]; } __attribute__((__packed__)); struct blkif_request_discard { diff --git a/include/xen/interface/xencomm.h b/include/xen/interface/xencomm.h deleted file mode 100644 index ac45e0712afa..000000000000 --- a/include/xen/interface/xencomm.h +++ /dev/null @@ -1,41 +0,0 @@ -/* - * Permission is hereby granted, free of charge, to any person obtaining a copy - * of this software and associated documentation files (the "Software"), to - * deal in the Software without restriction, including without limitation the - * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or - * sell copies of the Software, and to permit persons to whom the Software is - * furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * 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. - * - * Copyright (C) IBM Corp. 2006 - */ - -#ifndef _XEN_XENCOMM_H_ -#define _XEN_XENCOMM_H_ - -/* A xencomm descriptor is a scatter/gather list containing physical - * addresses corresponding to a virtually contiguous memory area. The - * hypervisor translates these physical addresses to machine addresses to copy - * to and from the virtually contiguous area. - */ - -#define XENCOMM_MAGIC 0x58434F4D /* 'XCOM' */ -#define XENCOMM_INVALID (~0UL) - -struct xencomm_desc { - uint32_t magic; - uint32_t nr_addrs; /* the number of entries in address[] */ - uint64_t address[0]; -}; - -#endif /* _XEN_XENCOMM_H_ */ diff --git a/include/xen/xencomm.h b/include/xen/xencomm.h deleted file mode 100644 index e43b039be112..000000000000 --- a/include/xen/xencomm.h +++ /dev/null @@ -1,77 +0,0 @@ -/* - * 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. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - * - * Copyright (C) IBM Corp. 2006 - * - * Authors: Hollis Blanchard <hollisb@us.ibm.com> - * Jerone Young <jyoung5@us.ibm.com> - */ - -#ifndef _LINUX_XENCOMM_H_ -#define _LINUX_XENCOMM_H_ - -#include <xen/interface/xencomm.h> - -#define XENCOMM_MINI_ADDRS 3 -struct xencomm_mini { - struct xencomm_desc _desc; - uint64_t address[XENCOMM_MINI_ADDRS]; -}; - -/* To avoid additionnal virt to phys conversion, an opaque structure is - presented. */ -struct xencomm_handle; - -extern void xencomm_free(struct xencomm_handle *desc); -extern struct xencomm_handle *xencomm_map(void *ptr, unsigned long bytes); -extern struct xencomm_handle *__xencomm_map_no_alloc(void *ptr, - unsigned long bytes, struct xencomm_mini *xc_area); - -#if 0 -#define XENCOMM_MINI_ALIGNED(xc_desc, n) \ - struct xencomm_mini xc_desc ## _base[(n)] \ - __attribute__((__aligned__(sizeof(struct xencomm_mini)))); \ - struct xencomm_mini *xc_desc = &xc_desc ## _base[0]; -#else -/* - * gcc bug workaround: - * http://gcc.gnu.org/bugzilla/show_bug.cgi?id=16660 - * gcc doesn't handle properly stack variable with - * __attribute__((__align__(sizeof(struct xencomm_mini)))) - */ -#define XENCOMM_MINI_ALIGNED(xc_desc, n) \ - unsigned char xc_desc ## _base[((n) + 1 ) * \ - sizeof(struct xencomm_mini)]; \ - struct xencomm_mini *xc_desc = (struct xencomm_mini *) \ - ((unsigned long)xc_desc ## _base + \ - (sizeof(struct xencomm_mini) - \ - ((unsigned long)xc_desc ## _base) % \ - sizeof(struct xencomm_mini))); -#endif -#define xencomm_map_no_alloc(ptr, bytes) \ - ({ XENCOMM_MINI_ALIGNED(xc_desc, 1); \ - __xencomm_map_no_alloc(ptr, bytes, xc_desc); }) - -/* provided by architecture code: */ -extern unsigned long xencomm_vtop(unsigned long vaddr); - -static inline void *xencomm_pa(void *ptr) -{ - return (void *)xencomm_vtop((unsigned long)ptr); -} - -#define xen_guest_handle(hnd) ((hnd).p) - -#endif /* _LINUX_XENCOMM_H_ */ diff --git a/ipc/mq_sysctl.c b/ipc/mq_sysctl.c index 383d638340b8..5bb8bfe67149 100644 --- a/ipc/mq_sysctl.c +++ b/ipc/mq_sysctl.c @@ -22,6 +22,16 @@ static void *get_mq(ctl_table *table) return which; } +static int proc_mq_dointvec(ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + struct ctl_table mq_table; + memcpy(&mq_table, table, sizeof(mq_table)); + mq_table.data = get_mq(table); + + return proc_dointvec(&mq_table, write, buffer, lenp, ppos); +} + static int proc_mq_dointvec_minmax(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { @@ -33,12 +43,10 @@ static int proc_mq_dointvec_minmax(ctl_table *table, int write, lenp, ppos); } #else +#define proc_mq_dointvec NULL #define proc_mq_dointvec_minmax NULL #endif -static int msg_queues_limit_min = MIN_QUEUESMAX; -static int msg_queues_limit_max = HARD_QUEUESMAX; - static int msg_max_limit_min = MIN_MSGMAX; static int msg_max_limit_max = HARD_MSGMAX; @@ -51,9 +59,7 @@ static ctl_table mq_sysctls[] = { .data = &init_ipc_ns.mq_queues_max, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_mq_dointvec_minmax, - .extra1 = &msg_queues_limit_min, - .extra2 = &msg_queues_limit_max, + .proc_handler = proc_mq_dointvec, }, { .procname = "msg_max", diff --git a/ipc/mqueue.c b/ipc/mqueue.c index ccf1f9fd263a..c3b31179122c 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -433,9 +433,9 @@ static int mqueue_create(struct inode *dir, struct dentry *dentry, error = -EACCES; goto out_unlock; } - if (ipc_ns->mq_queues_count >= HARD_QUEUESMAX || - (ipc_ns->mq_queues_count >= ipc_ns->mq_queues_max && - !capable(CAP_SYS_RESOURCE))) { + + if (ipc_ns->mq_queues_count >= ipc_ns->mq_queues_max && + !capable(CAP_SYS_RESOURCE)) { error = -ENOSPC; goto out_unlock; } diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c index 67ccf0e7cca9..135944a7b28a 100644 --- a/kernel/audit_tree.c +++ b/kernel/audit_tree.c @@ -916,7 +916,7 @@ static int audit_tree_handle_event(struct fsnotify_group *group, struct fsnotify_mark *inode_mark, struct fsnotify_mark *vfsmount_mark, u32 mask, void *data, int data_type, - const unsigned char *file_name) + const unsigned char *file_name, u32 cookie) { return 0; } diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c index 2596fac5dcb4..70b4554d2fbe 100644 --- a/kernel/audit_watch.c +++ b/kernel/audit_watch.c @@ -471,7 +471,7 @@ static int audit_watch_handle_event(struct fsnotify_group *group, struct fsnotify_mark *inode_mark, struct fsnotify_mark *vfsmount_mark, u32 mask, void *data, int data_type, - const unsigned char *dname) + const unsigned char *dname, u32 cookie) { struct inode *inode; struct audit_parent *parent; diff --git a/kernel/cgroup.c b/kernel/cgroup.c index e2f46ba37f72..105f273b6f86 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -886,7 +886,9 @@ static void cgroup_diput(struct dentry *dentry, struct inode *inode) * per-subsystem and moved to css->id so that lookups are * successful until the target css is released. */ + mutex_lock(&cgroup_mutex); idr_remove(&cgrp->root->cgroup_idr, cgrp->id); + mutex_unlock(&cgroup_mutex); cgrp->id = -1; call_rcu(&cgrp->rcu_head, cgroup_free_rcu); @@ -1566,10 +1568,10 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type, mutex_lock(&cgroup_mutex); mutex_lock(&cgroup_root_mutex); - root_cgrp->id = idr_alloc(&root->cgroup_idr, root_cgrp, - 0, 1, GFP_KERNEL); - if (root_cgrp->id < 0) + ret = idr_alloc(&root->cgroup_idr, root_cgrp, 0, 1, GFP_KERNEL); + if (ret < 0) goto unlock_drop; + root_cgrp->id = ret; /* Check for name clashes with existing mounts */ ret = -EBUSY; @@ -2763,10 +2765,7 @@ static int cgroup_cfts_commit(struct cftype *cfts, bool is_add) */ update_before = cgroup_serial_nr_next; - mutex_unlock(&cgroup_mutex); - /* add/rm files for all cgroups created before */ - rcu_read_lock(); css_for_each_descendant_pre(css, cgroup_css(root, ss)) { struct cgroup *cgrp = css->cgroup; @@ -2775,23 +2774,19 @@ static int cgroup_cfts_commit(struct cftype *cfts, bool is_add) inode = cgrp->dentry->d_inode; dget(cgrp->dentry); - rcu_read_unlock(); - dput(prev); prev = cgrp->dentry; + mutex_unlock(&cgroup_mutex); mutex_lock(&inode->i_mutex); mutex_lock(&cgroup_mutex); if (cgrp->serial_nr < update_before && !cgroup_is_dead(cgrp)) ret = cgroup_addrm_files(cgrp, cfts, is_add); - mutex_unlock(&cgroup_mutex); mutex_unlock(&inode->i_mutex); - - rcu_read_lock(); if (ret) break; } - rcu_read_unlock(); + mutex_unlock(&cgroup_mutex); dput(prev); deactivate_super(sb); return ret; @@ -2910,9 +2905,14 @@ static void cgroup_enable_task_cg_lists(void) * We should check if the process is exiting, otherwise * it will race with cgroup_exit() in that the list * entry won't be deleted though the process has exited. + * Do it while holding siglock so that we don't end up + * racing against cgroup_exit(). */ + spin_lock_irq(&p->sighand->siglock); if (!(p->flags & PF_EXITING) && list_empty(&p->cg_list)) list_add(&p->cg_list, &task_css_set(p)->tasks); + spin_unlock_irq(&p->sighand->siglock); + task_unlock(p); } while_each_thread(g, p); read_unlock(&tasklist_lock); @@ -4158,7 +4158,7 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry, struct cgroup *cgrp; struct cgroup_name *name; struct cgroupfs_root *root = parent->root; - int ssid, err = 0; + int ssid, err; struct cgroup_subsys *ss; struct super_block *sb = root->sb; @@ -4168,19 +4168,13 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry, return -ENOMEM; name = cgroup_alloc_name(dentry); - if (!name) + if (!name) { + err = -ENOMEM; goto err_free_cgrp; + } rcu_assign_pointer(cgrp->name, name); /* - * Temporarily set the pointer to NULL, so idr_find() won't return - * a half-baked cgroup. - */ - cgrp->id = idr_alloc(&root->cgroup_idr, NULL, 1, 0, GFP_KERNEL); - if (cgrp->id < 0) - goto err_free_name; - - /* * Only live parents can have children. Note that the liveliness * check isn't strictly necessary because cgroup_mkdir() and * cgroup_rmdir() are fully synchronized by i_mutex; however, do it @@ -4189,7 +4183,17 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry, */ if (!cgroup_lock_live_group(parent)) { err = -ENODEV; - goto err_free_id; + goto err_free_name; + } + + /* + * Temporarily set the pointer to NULL, so idr_find() won't return + * a half-baked cgroup. + */ + cgrp->id = idr_alloc(&root->cgroup_idr, NULL, 1, 0, GFP_KERNEL); + if (cgrp->id < 0) { + err = -ENOMEM; + goto err_unlock; } /* Grab a reference on the superblock so the hierarchy doesn't @@ -4221,7 +4225,7 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry, */ err = cgroup_create_file(dentry, S_IFDIR | mode, sb); if (err < 0) - goto err_unlock; + goto err_free_id; lockdep_assert_held(&dentry->d_inode->i_mutex); cgrp->serial_nr = cgroup_serial_nr_next++; @@ -4257,12 +4261,12 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry, return 0; -err_unlock: - mutex_unlock(&cgroup_mutex); - /* Release the reference count that we took on the superblock */ - deactivate_super(sb); err_free_id: idr_remove(&root->cgroup_idr, cgrp->id); + /* Release the reference count that we took on the superblock */ + deactivate_super(sb); +err_unlock: + mutex_unlock(&cgroup_mutex); err_free_name: kfree(rcu_dereference_raw(cgrp->name)); err_free_cgrp: diff --git a/kernel/events/core.c b/kernel/events/core.c index 56003c6edfd3..fa0b2d4ad83c 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -7856,14 +7856,14 @@ static void perf_pmu_rotate_stop(struct pmu *pmu) static void __perf_event_exit_context(void *__info) { struct perf_event_context *ctx = __info; - struct perf_event *event, *tmp; + struct perf_event *event; perf_pmu_rotate_stop(ctx->pmu); - list_for_each_entry_safe(event, tmp, &ctx->pinned_groups, group_entry) - __perf_remove_from_context(event); - list_for_each_entry_safe(event, tmp, &ctx->flexible_groups, group_entry) + rcu_read_lock(); + list_for_each_entry_rcu(event, &ctx->event_list, event_entry) __perf_remove_from_context(event); + rcu_read_unlock(); } static void perf_event_exit_cpu_context(int cpu) @@ -7887,11 +7887,11 @@ static void perf_event_exit_cpu(int cpu) { struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu); + perf_event_exit_cpu_context(cpu); + mutex_lock(&swhash->hlist_mutex); swevent_hlist_release(swhash); mutex_unlock(&swhash->hlist_mutex); - - perf_event_exit_cpu_context(cpu); } #else static inline void perf_event_exit_cpu(int cpu) { } diff --git a/kernel/irq/devres.c b/kernel/irq/devres.c index bd8e788d71e0..1ef0606797c9 100644 --- a/kernel/irq/devres.c +++ b/kernel/irq/devres.c @@ -73,6 +73,51 @@ int devm_request_threaded_irq(struct device *dev, unsigned int irq, EXPORT_SYMBOL(devm_request_threaded_irq); /** + * devm_request_any_context_irq - allocate an interrupt line for a managed device + * @dev: device to request interrupt for + * @irq: Interrupt line to allocate + * @handler: Function to be called when the IRQ occurs + * @thread_fn: function to be called in a threaded interrupt context. NULL + * for devices which handle everything in @handler + * @irqflags: Interrupt type flags + * @devname: An ascii name for the claiming device + * @dev_id: A cookie passed back to the handler function + * + * Except for the extra @dev argument, this function takes the + * same arguments and performs the same function as + * request_any_context_irq(). IRQs requested with this function will be + * automatically freed on driver detach. + * + * If an IRQ allocated with this function needs to be freed + * separately, devm_free_irq() must be used. + */ +int devm_request_any_context_irq(struct device *dev, unsigned int irq, + irq_handler_t handler, unsigned long irqflags, + const char *devname, void *dev_id) +{ + struct irq_devres *dr; + int rc; + + dr = devres_alloc(devm_irq_release, sizeof(struct irq_devres), + GFP_KERNEL); + if (!dr) + return -ENOMEM; + + rc = request_any_context_irq(irq, handler, irqflags, devname, dev_id); + if (rc) { + devres_free(dr); + return rc; + } + + dr->irq = irq; + dr->dev_id = dev_id; + devres_add(dev, dr); + + return 0; +} +EXPORT_SYMBOL(devm_request_any_context_irq); + +/** * devm_free_irq - free an interrupt * @dev: device to free interrupt for * @irq: Interrupt line to free diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index 192a302d6cfd..8ab8e9390297 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -274,6 +274,7 @@ struct irq_desc *irq_to_desc(unsigned int irq) { return (irq < NR_IRQS) ? irq_desc + irq : NULL; } +EXPORT_SYMBOL(irq_to_desc); static void free_desc(unsigned int irq) { diff --git a/kernel/power/console.c b/kernel/power/console.c index eacb8bd8cab4..aba9c545a0e3 100644 --- a/kernel/power/console.c +++ b/kernel/power/console.c @@ -9,6 +9,7 @@ #include <linux/kbd_kern.h> #include <linux/vt.h> #include <linux/module.h> +#include <linux/slab.h> #include "power.h" #define SUSPEND_CONSOLE (MAX_NR_CONSOLES-1) diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index b1d255f04135..4dae9cbe9259 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -1076,7 +1076,6 @@ static int syslog_print_all(char __user *buf, int size, bool clear) next_seq = log_next_seq; len = 0; - prev = 0; while (len >= 0 && seq < next_seq) { struct printk_log *msg = log_from_idx(idx); int textlen; @@ -2788,7 +2787,6 @@ bool kmsg_dump_get_buffer(struct kmsg_dumper *dumper, bool syslog, next_idx = idx; l = 0; - prev = 0; while (seq < dumper->next_seq) { struct printk_log *msg = log_from_idx(idx); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index b46131ef6aab..6edbef296ece 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1952,7 +1952,7 @@ static int dl_overflow(struct task_struct *p, int policy, { struct dl_bw *dl_b = dl_bw_of(task_cpu(p)); - u64 period = attr->sched_period; + u64 period = attr->sched_period ?: attr->sched_deadline; u64 runtime = attr->sched_runtime; u64 new_bw = dl_policy(policy) ? to_ratio(period, runtime) : 0; int cpus, err = -1; @@ -3661,13 +3661,14 @@ SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param) * @pid: the pid in question. * @uattr: structure containing the extended parameters. */ -SYSCALL_DEFINE2(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr) +SYSCALL_DEFINE3(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr, + unsigned int, flags) { struct sched_attr attr; struct task_struct *p; int retval; - if (!uattr || pid < 0) + if (!uattr || pid < 0 || flags) return -EINVAL; if (sched_copy_attr(uattr, &attr)) @@ -3786,7 +3787,7 @@ static int sched_read_attr(struct sched_attr __user *uattr, attr->size = usize; } - ret = copy_to_user(uattr, attr, usize); + ret = copy_to_user(uattr, attr, attr->size); if (ret) return -EFAULT; @@ -3804,8 +3805,8 @@ err_size: * @uattr: structure containing the extended parameters. * @size: sizeof(attr) for fwd/bwd comp. */ -SYSCALL_DEFINE3(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr, - unsigned int, size) +SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr, + unsigned int, size, unsigned int, flags) { struct sched_attr attr = { .size = sizeof(struct sched_attr), @@ -3814,7 +3815,7 @@ SYSCALL_DEFINE3(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr, int retval; if (!uattr || pid < 0 || size > PAGE_SIZE || - size < SCHED_ATTR_SIZE_VER0) + size < SCHED_ATTR_SIZE_VER0 || flags) return -EINVAL; rcu_read_lock(); @@ -7422,6 +7423,7 @@ static int sched_dl_global_constraints(void) u64 period = global_rt_period(); u64 new_bw = to_ratio(period, runtime); int cpu, ret = 0; + unsigned long flags; /* * Here we want to check the bandwidth not being set to some @@ -7435,10 +7437,10 @@ static int sched_dl_global_constraints(void) for_each_possible_cpu(cpu) { struct dl_bw *dl_b = dl_bw_of(cpu); - raw_spin_lock(&dl_b->lock); + raw_spin_lock_irqsave(&dl_b->lock, flags); if (new_bw < dl_b->total_bw) ret = -EBUSY; - raw_spin_unlock(&dl_b->lock); + raw_spin_unlock_irqrestore(&dl_b->lock, flags); if (ret) break; @@ -7451,6 +7453,7 @@ static void sched_dl_do_global(void) { u64 new_bw = -1; int cpu; + unsigned long flags; def_dl_bandwidth.dl_period = global_rt_period(); def_dl_bandwidth.dl_runtime = global_rt_runtime(); @@ -7464,9 +7467,9 @@ static void sched_dl_do_global(void) for_each_possible_cpu(cpu) { struct dl_bw *dl_b = dl_bw_of(cpu); - raw_spin_lock(&dl_b->lock); + raw_spin_lock_irqsave(&dl_b->lock, flags); dl_b->bw = new_bw; - raw_spin_unlock(&dl_b->lock); + raw_spin_unlock_irqrestore(&dl_b->lock, flags); } } @@ -7475,7 +7478,8 @@ static int sched_rt_global_validate(void) if (sysctl_sched_rt_period <= 0) return -EINVAL; - if (sysctl_sched_rt_runtime > sysctl_sched_rt_period) + if ((sysctl_sched_rt_runtime != RUNTIME_INF) && + (sysctl_sched_rt_runtime > sysctl_sched_rt_period)) return -EINVAL; return 0; diff --git a/kernel/sched/cpudeadline.c b/kernel/sched/cpudeadline.c index 045fc74e3f09..5b9bb42b2d47 100644 --- a/kernel/sched/cpudeadline.c +++ b/kernel/sched/cpudeadline.c @@ -70,7 +70,7 @@ static void cpudl_heapify(struct cpudl *cp, int idx) static void cpudl_change_key(struct cpudl *cp, int idx, u64 new_dl) { - WARN_ON(idx > num_present_cpus() || idx == IDX_INVALID); + WARN_ON(idx == IDX_INVALID || !cpu_present(idx)); if (dl_time_before(new_dl, cp->elements[idx].dl)) { cp->elements[idx].dl = new_dl; @@ -117,7 +117,7 @@ int cpudl_find(struct cpudl *cp, struct task_struct *p, } out: - WARN_ON(best_cpu > num_present_cpus() && best_cpu != -1); + WARN_ON(best_cpu != -1 && !cpu_present(best_cpu)); return best_cpu; } @@ -137,7 +137,7 @@ void cpudl_set(struct cpudl *cp, int cpu, u64 dl, int is_valid) int old_idx, new_cpu; unsigned long flags; - WARN_ON(cpu > num_present_cpus()); + WARN_ON(!cpu_present(cpu)); raw_spin_lock_irqsave(&cp->lock, flags); old_idx = cp->cpu_to_idx[cpu]; diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 0dd5e0971a07..6e79b3faa4cd 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -121,7 +121,7 @@ static inline void dl_clear_overload(struct rq *rq) static void update_dl_migration(struct dl_rq *dl_rq) { - if (dl_rq->dl_nr_migratory && dl_rq->dl_nr_total > 1) { + if (dl_rq->dl_nr_migratory && dl_rq->dl_nr_running > 1) { if (!dl_rq->overloaded) { dl_set_overload(rq_of_dl_rq(dl_rq)); dl_rq->overloaded = 1; @@ -135,9 +135,7 @@ static void update_dl_migration(struct dl_rq *dl_rq) static void inc_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq) { struct task_struct *p = dl_task_of(dl_se); - dl_rq = &rq_of_dl_rq(dl_rq)->dl; - dl_rq->dl_nr_total++; if (p->nr_cpus_allowed > 1) dl_rq->dl_nr_migratory++; @@ -147,9 +145,7 @@ static void inc_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq) static void dec_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq) { struct task_struct *p = dl_task_of(dl_se); - dl_rq = &rq_of_dl_rq(dl_rq)->dl; - dl_rq->dl_nr_total--; if (p->nr_cpus_allowed > 1) dl_rq->dl_nr_migratory--; @@ -566,6 +562,8 @@ int dl_runtime_exceeded(struct rq *rq, struct sched_dl_entity *dl_se) return 1; } +extern bool sched_rt_bandwidth_account(struct rt_rq *rt_rq); + /* * Update the current task's runtime statistics (provided it is still * a -deadline task and has not been removed from the dl_rq). @@ -629,11 +627,13 @@ static void update_curr_dl(struct rq *rq) struct rt_rq *rt_rq = &rq->rt; raw_spin_lock(&rt_rq->rt_runtime_lock); - rt_rq->rt_time += delta_exec; /* * We'll let actual RT tasks worry about the overflow here, we - * have our own CBS to keep us inline -- see above. + * have our own CBS to keep us inline; only account when RT + * bandwidth is relevant. */ + if (sched_rt_bandwidth_account(rt_rq)) + rt_rq->rt_time += delta_exec; raw_spin_unlock(&rt_rq->rt_runtime_lock); } } @@ -717,6 +717,7 @@ void inc_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq) WARN_ON(!dl_prio(prio)); dl_rq->dl_nr_running++; + inc_nr_running(rq_of_dl_rq(dl_rq)); inc_dl_deadline(dl_rq, deadline); inc_dl_migration(dl_se, dl_rq); @@ -730,6 +731,7 @@ void dec_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq) WARN_ON(!dl_prio(prio)); WARN_ON(!dl_rq->dl_nr_running); dl_rq->dl_nr_running--; + dec_nr_running(rq_of_dl_rq(dl_rq)); dec_dl_deadline(dl_rq, dl_se->deadline); dec_dl_migration(dl_se, dl_rq); @@ -836,8 +838,6 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags) if (!task_current(rq, p) && p->nr_cpus_allowed > 1) enqueue_pushable_dl_task(rq, p); - - inc_nr_running(rq); } static void __dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags) @@ -850,8 +850,6 @@ static void dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags) { update_curr_dl(rq); __dequeue_task_dl(rq, p, flags); - - dec_nr_running(rq); } /* diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 966cc2bfcb77..9b4c4f320130 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -1757,6 +1757,8 @@ void task_numa_work(struct callback_head *work) start = end; if (pages <= 0) goto out; + + cond_resched(); } while (end != vma->vm_end); } @@ -6999,15 +7001,15 @@ static void switched_from_fair(struct rq *rq, struct task_struct *p) struct cfs_rq *cfs_rq = cfs_rq_of(se); /* - * Ensure the task's vruntime is normalized, so that when its + * Ensure the task's vruntime is normalized, so that when it's * switched back to the fair class the enqueue_entity(.flags=0) will * do the right thing. * - * If it was on_rq, then the dequeue_entity(.flags=0) will already - * have normalized the vruntime, if it was !on_rq, then only when + * If it's on_rq, then the dequeue_entity(.flags=0) will already + * have normalized the vruntime, if it's !on_rq, then only when * the task is sleeping will it still have non-normalized vruntime. */ - if (!se->on_rq && p->state != TASK_RUNNING) { + if (!p->on_rq && p->state != TASK_RUNNING) { /* * Fix up our vruntime so that the current sleep doesn't * cause 'unlimited' sleep bonus. diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index a2740b775b45..1999021042c7 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -538,6 +538,14 @@ static inline struct rt_bandwidth *sched_rt_bandwidth(struct rt_rq *rt_rq) #endif /* CONFIG_RT_GROUP_SCHED */ +bool sched_rt_bandwidth_account(struct rt_rq *rt_rq) +{ + struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq); + + return (hrtimer_active(&rt_b->rt_period_timer) || + rt_rq->rt_time < rt_b->rt_runtime); +} + #ifdef CONFIG_SMP /* * We ran out of runtime, see if we can borrow some from our neighbours. diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index c2119fd20f8b..f964add50f38 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -462,7 +462,6 @@ struct dl_rq { } earliest_dl; unsigned long dl_nr_migratory; - unsigned long dl_nr_total; int overloaded; /* diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c index 7a925ba456fb..a6a5bf53e86d 100644 --- a/kernel/time/jiffies.c +++ b/kernel/time/jiffies.c @@ -51,7 +51,13 @@ * HZ shrinks, so values greater than 8 overflow 32bits when * HZ=100. */ +#if HZ < 34 +#define JIFFIES_SHIFT 6 +#elif HZ < 67 +#define JIFFIES_SHIFT 7 +#else #define JIFFIES_SHIFT 8 +#endif static cycle_t jiffies_read(struct clocksource *cs) { diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c index 0abb36464281..4d23dc4d8139 100644 --- a/kernel/time/sched_clock.c +++ b/kernel/time/sched_clock.c @@ -116,20 +116,42 @@ static enum hrtimer_restart sched_clock_poll(struct hrtimer *hrt) void __init sched_clock_register(u64 (*read)(void), int bits, unsigned long rate) { + u64 res, wrap, new_mask, new_epoch, cyc, ns; + u32 new_mult, new_shift; + ktime_t new_wrap_kt; unsigned long r; - u64 res, wrap; char r_unit; if (cd.rate > rate) return; WARN_ON(!irqs_disabled()); - read_sched_clock = read; - sched_clock_mask = CLOCKSOURCE_MASK(bits); - cd.rate = rate; /* calculate the mult/shift to convert counter ticks to ns. */ - clocks_calc_mult_shift(&cd.mult, &cd.shift, rate, NSEC_PER_SEC, 3600); + clocks_calc_mult_shift(&new_mult, &new_shift, rate, NSEC_PER_SEC, 3600); + + new_mask = CLOCKSOURCE_MASK(bits); + + /* calculate how many ns until we wrap */ + wrap = clocks_calc_max_nsecs(new_mult, new_shift, 0, new_mask); + new_wrap_kt = ns_to_ktime(wrap - (wrap >> 3)); + + /* update epoch for new counter and update epoch_ns from old counter*/ + new_epoch = read(); + cyc = read_sched_clock(); + ns = cd.epoch_ns + cyc_to_ns((cyc - cd.epoch_cyc) & sched_clock_mask, + cd.mult, cd.shift); + + raw_write_seqcount_begin(&cd.seq); + read_sched_clock = read; + sched_clock_mask = new_mask; + cd.rate = rate; + cd.wrap_kt = new_wrap_kt; + cd.mult = new_mult; + cd.shift = new_shift; + cd.epoch_cyc = new_epoch; + cd.epoch_ns = ns; + raw_write_seqcount_end(&cd.seq); r = rate; if (r >= 4000000) { @@ -141,22 +163,12 @@ void __init sched_clock_register(u64 (*read)(void), int bits, } else r_unit = ' '; - /* calculate how many ns until we wrap */ - wrap = clocks_calc_max_nsecs(cd.mult, cd.shift, 0, sched_clock_mask); - cd.wrap_kt = ns_to_ktime(wrap - (wrap >> 3)); - /* calculate the ns resolution of this counter */ - res = cyc_to_ns(1ULL, cd.mult, cd.shift); + res = cyc_to_ns(1ULL, new_mult, new_shift); + pr_info("sched_clock: %u bits at %lu%cHz, resolution %lluns, wraps every %lluns\n", bits, r, r_unit, res, wrap); - update_sched_clock(); - - /* - * Ensure that sched_clock() starts off at 0ns - */ - cd.epoch_ns = 0; - /* Enable IRQ time accounting if we have a fast enough sched_clock */ if (irqtime > 0 || (irqtime == -1 && rate >= 1000000)) enable_sched_clock_irqtime(); diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index 43780ab5e279..98977a57ac72 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -756,6 +756,7 @@ out: static void tick_broadcast_clear_oneshot(int cpu) { cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask); + cpumask_clear_cpu(cpu, tick_broadcast_pending_mask); } static void tick_broadcast_init_next_event(struct cpumask *mask, diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 294b8a271a04..fc4da2d97f9b 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -2397,6 +2397,13 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, write &= RB_WRITE_MASK; tail = write - length; + /* + * If this is the first commit on the page, then it has the same + * timestamp as the page itself. + */ + if (!tail) + delta = 0; + /* See if we shot pass the end of this buffer page */ if (unlikely(write > BUF_PAGE_SIZE)) return rb_move_tail(cpu_buffer, length, tail, diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c index 240fb62cf394..dd06439b9c84 100644 --- a/kernel/user_namespace.c +++ b/kernel/user_namespace.c @@ -225,7 +225,7 @@ static u32 map_id_up(struct uid_gid_map *map, u32 id) * * When there is no mapping defined for the user-namespace uid * pair INVALID_UID is returned. Callers are expected to test - * for and handle handle INVALID_UID being returned. INVALID_UID + * for and handle INVALID_UID being returned. INVALID_UID * may be tested for using uid_valid(). */ kuid_t make_kuid(struct user_namespace *ns, uid_t uid) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 82ef9f3b7473..193e977a10ea 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -1851,6 +1851,12 @@ static void destroy_worker(struct worker *worker) if (worker->flags & WORKER_IDLE) pool->nr_idle--; + /* + * Once WORKER_DIE is set, the kworker may destroy itself at any + * point. Pin to ensure the task stays until we're done with it. + */ + get_task_struct(worker->task); + list_del_init(&worker->entry); worker->flags |= WORKER_DIE; @@ -1859,6 +1865,7 @@ static void destroy_worker(struct worker *worker) spin_unlock_irq(&pool->lock); kthread_stop(worker->task); + put_task_struct(worker->task); kfree(worker); spin_lock_irq(&pool->lock); diff --git a/lib/dma-debug.c b/lib/dma-debug.c index 2defd1308b04..98f2d7e91a91 100644 --- a/lib/dma-debug.c +++ b/lib/dma-debug.c @@ -424,111 +424,134 @@ void debug_dma_dump_mappings(struct device *dev) EXPORT_SYMBOL(debug_dma_dump_mappings); /* - * For each page mapped (initial page in the case of - * dma_alloc_coherent/dma_map_{single|page}, or each page in a - * scatterlist) insert into this tree using the pfn as the key. At + * For each mapping (initial cacheline in the case of + * dma_alloc_coherent/dma_map_page, initial cacheline in each page of a + * scatterlist, or the cacheline specified in dma_map_single) insert + * into this tree using the cacheline as the key. At * dma_unmap_{single|sg|page} or dma_free_coherent delete the entry. If - * the pfn already exists at insertion time add a tag as a reference + * the entry already exists at insertion time add a tag as a reference * count for the overlapping mappings. For now, the overlap tracking - * just ensures that 'unmaps' balance 'maps' before marking the pfn - * idle, but we should also be flagging overlaps as an API violation. + * just ensures that 'unmaps' balance 'maps' before marking the + * cacheline idle, but we should also be flagging overlaps as an API + * violation. * * Memory usage is mostly constrained by the maximum number of available * dma-debug entries in that we need a free dma_debug_entry before - * inserting into the tree. In the case of dma_map_{single|page} and - * dma_alloc_coherent there is only one dma_debug_entry and one pfn to - * track per event. dma_map_sg(), on the other hand, - * consumes a single dma_debug_entry, but inserts 'nents' entries into - * the tree. + * inserting into the tree. In the case of dma_map_page and + * dma_alloc_coherent there is only one dma_debug_entry and one + * dma_active_cacheline entry to track per event. dma_map_sg(), on the + * other hand, consumes a single dma_debug_entry, but inserts 'nents' + * entries into the tree. * * At any time debug_dma_assert_idle() can be called to trigger a - * warning if the given page is in the active set. + * warning if any cachelines in the given page are in the active set. */ -static RADIX_TREE(dma_active_pfn, GFP_NOWAIT); +static RADIX_TREE(dma_active_cacheline, GFP_NOWAIT); static DEFINE_SPINLOCK(radix_lock); -#define ACTIVE_PFN_MAX_OVERLAP ((1 << RADIX_TREE_MAX_TAGS) - 1) +#define ACTIVE_CACHELINE_MAX_OVERLAP ((1 << RADIX_TREE_MAX_TAGS) - 1) +#define CACHELINE_PER_PAGE_SHIFT (PAGE_SHIFT - L1_CACHE_SHIFT) +#define CACHELINES_PER_PAGE (1 << CACHELINE_PER_PAGE_SHIFT) -static int active_pfn_read_overlap(unsigned long pfn) +static phys_addr_t to_cacheline_number(struct dma_debug_entry *entry) +{ + return (entry->pfn << CACHELINE_PER_PAGE_SHIFT) + + (entry->offset >> L1_CACHE_SHIFT); +} + +static int active_cacheline_read_overlap(phys_addr_t cln) { int overlap = 0, i; for (i = RADIX_TREE_MAX_TAGS - 1; i >= 0; i--) - if (radix_tree_tag_get(&dma_active_pfn, pfn, i)) + if (radix_tree_tag_get(&dma_active_cacheline, cln, i)) overlap |= 1 << i; return overlap; } -static int active_pfn_set_overlap(unsigned long pfn, int overlap) +static int active_cacheline_set_overlap(phys_addr_t cln, int overlap) { int i; - if (overlap > ACTIVE_PFN_MAX_OVERLAP || overlap < 0) + if (overlap > ACTIVE_CACHELINE_MAX_OVERLAP || overlap < 0) return overlap; for (i = RADIX_TREE_MAX_TAGS - 1; i >= 0; i--) if (overlap & 1 << i) - radix_tree_tag_set(&dma_active_pfn, pfn, i); + radix_tree_tag_set(&dma_active_cacheline, cln, i); else - radix_tree_tag_clear(&dma_active_pfn, pfn, i); + radix_tree_tag_clear(&dma_active_cacheline, cln, i); return overlap; } -static void active_pfn_inc_overlap(unsigned long pfn) +static void active_cacheline_inc_overlap(phys_addr_t cln) { - int overlap = active_pfn_read_overlap(pfn); + int overlap = active_cacheline_read_overlap(cln); - overlap = active_pfn_set_overlap(pfn, ++overlap); + overlap = active_cacheline_set_overlap(cln, ++overlap); /* If we overflowed the overlap counter then we're potentially * leaking dma-mappings. Otherwise, if maps and unmaps are * balanced then this overflow may cause false negatives in - * debug_dma_assert_idle() as the pfn may be marked idle + * debug_dma_assert_idle() as the cacheline may be marked idle * prematurely. */ - WARN_ONCE(overlap > ACTIVE_PFN_MAX_OVERLAP, - "DMA-API: exceeded %d overlapping mappings of pfn %lx\n", - ACTIVE_PFN_MAX_OVERLAP, pfn); + WARN_ONCE(overlap > ACTIVE_CACHELINE_MAX_OVERLAP, + "DMA-API: exceeded %d overlapping mappings of cacheline %pa\n", + ACTIVE_CACHELINE_MAX_OVERLAP, &cln); } -static int active_pfn_dec_overlap(unsigned long pfn) +static int active_cacheline_dec_overlap(phys_addr_t cln) { - int overlap = active_pfn_read_overlap(pfn); + int overlap = active_cacheline_read_overlap(cln); - return active_pfn_set_overlap(pfn, --overlap); + return active_cacheline_set_overlap(cln, --overlap); } -static int active_pfn_insert(struct dma_debug_entry *entry) +static int active_cacheline_insert(struct dma_debug_entry *entry) { + phys_addr_t cln = to_cacheline_number(entry); unsigned long flags; int rc; + /* If the device is not writing memory then we don't have any + * concerns about the cpu consuming stale data. This mitigates + * legitimate usages of overlapping mappings. + */ + if (entry->direction == DMA_TO_DEVICE) + return 0; + spin_lock_irqsave(&radix_lock, flags); - rc = radix_tree_insert(&dma_active_pfn, entry->pfn, entry); + rc = radix_tree_insert(&dma_active_cacheline, cln, entry); if (rc == -EEXIST) - active_pfn_inc_overlap(entry->pfn); + active_cacheline_inc_overlap(cln); spin_unlock_irqrestore(&radix_lock, flags); return rc; } -static void active_pfn_remove(struct dma_debug_entry *entry) +static void active_cacheline_remove(struct dma_debug_entry *entry) { + phys_addr_t cln = to_cacheline_number(entry); unsigned long flags; + /* ...mirror the insert case */ + if (entry->direction == DMA_TO_DEVICE) + return; + spin_lock_irqsave(&radix_lock, flags); /* since we are counting overlaps the final put of the - * entry->pfn will occur when the overlap count is 0. - * active_pfn_dec_overlap() returns -1 in that case + * cacheline will occur when the overlap count is 0. + * active_cacheline_dec_overlap() returns -1 in that case */ - if (active_pfn_dec_overlap(entry->pfn) < 0) - radix_tree_delete(&dma_active_pfn, entry->pfn); + if (active_cacheline_dec_overlap(cln) < 0) + radix_tree_delete(&dma_active_cacheline, cln); spin_unlock_irqrestore(&radix_lock, flags); } /** * debug_dma_assert_idle() - assert that a page is not undergoing dma - * @page: page to lookup in the dma_active_pfn tree + * @page: page to lookup in the dma_active_cacheline tree * * Place a call to this routine in cases where the cpu touching the page * before the dma completes (page is dma_unmapped) will lead to data @@ -536,22 +559,38 @@ static void active_pfn_remove(struct dma_debug_entry *entry) */ void debug_dma_assert_idle(struct page *page) { + static struct dma_debug_entry *ents[CACHELINES_PER_PAGE]; + struct dma_debug_entry *entry = NULL; + void **results = (void **) &ents; + unsigned int nents, i; unsigned long flags; - struct dma_debug_entry *entry; + phys_addr_t cln; if (!page) return; + cln = (phys_addr_t) page_to_pfn(page) << CACHELINE_PER_PAGE_SHIFT; spin_lock_irqsave(&radix_lock, flags); - entry = radix_tree_lookup(&dma_active_pfn, page_to_pfn(page)); + nents = radix_tree_gang_lookup(&dma_active_cacheline, results, cln, + CACHELINES_PER_PAGE); + for (i = 0; i < nents; i++) { + phys_addr_t ent_cln = to_cacheline_number(ents[i]); + + if (ent_cln == cln) { + entry = ents[i]; + break; + } else if (ent_cln >= cln + CACHELINES_PER_PAGE) + break; + } spin_unlock_irqrestore(&radix_lock, flags); if (!entry) return; + cln = to_cacheline_number(entry); err_printk(entry->dev, entry, - "DMA-API: cpu touching an active dma mapped page " - "[pfn=0x%lx]\n", entry->pfn); + "DMA-API: cpu touching an active dma mapped cacheline [cln=%pa]\n", + &cln); } /* @@ -568,9 +607,9 @@ static void add_dma_entry(struct dma_debug_entry *entry) hash_bucket_add(bucket, entry); put_hash_bucket(bucket, &flags); - rc = active_pfn_insert(entry); + rc = active_cacheline_insert(entry); if (rc == -ENOMEM) { - pr_err("DMA-API: pfn tracking ENOMEM, dma-debug disabled\n"); + pr_err("DMA-API: cacheline tracking ENOMEM, dma-debug disabled\n"); global_disable = true; } @@ -631,7 +670,7 @@ static void dma_entry_free(struct dma_debug_entry *entry) { unsigned long flags; - active_pfn_remove(entry); + active_cacheline_remove(entry); /* * add to beginning of the list - this way the entries are diff --git a/lib/percpu_ida.c b/lib/percpu_ida.c index 7be235f1a70b..93d145e5539c 100644 --- a/lib/percpu_ida.c +++ b/lib/percpu_ida.c @@ -54,9 +54,7 @@ static inline void move_tags(unsigned *dst, unsigned *dst_nr, /* * Try to steal tags from a remote cpu's percpu freelist. * - * We first check how many percpu freelists have tags - we don't steal tags - * unless enough percpu freelists have tags on them that it's possible more than - * half the total tags could be stuck on remote percpu freelists. + * We first check how many percpu freelists have tags * * Then we iterate through the cpus until we find some tags - we don't attempt * to find the "best" cpu to steal from, to keep cacheline bouncing to a @@ -69,8 +67,7 @@ static inline void steal_tags(struct percpu_ida *pool, struct percpu_ida_cpu *remote; for (cpus_have_tags = cpumask_weight(&pool->cpus_have_tags); - cpus_have_tags * pool->percpu_max_size > pool->nr_tags / 2; - cpus_have_tags--) { + cpus_have_tags; cpus_have_tags--) { cpu = cpumask_next(cpu, &pool->cpus_have_tags); if (cpu >= nr_cpu_ids) { diff --git a/lib/radix-tree.c b/lib/radix-tree.c index 7811ed3b4e70..bd4a8dfdf0b8 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -1253,8 +1253,10 @@ unsigned long radix_tree_locate_item(struct radix_tree_root *root, void *item) node = indirect_to_ptr(node); max_index = radix_tree_maxindex(node->height); - if (cur_index > max_index) + if (cur_index > max_index) { + rcu_read_unlock(); break; + } cur_index = __locate(node, item, cur_index, &found_index); rcu_read_unlock(); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 82166bf974e1..1546655a2d78 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1166,8 +1166,10 @@ alloc: } else { ret = do_huge_pmd_wp_page_fallback(mm, vma, address, pmd, orig_pmd, page, haddr); - if (ret & VM_FAULT_OOM) + if (ret & VM_FAULT_OOM) { split_huge_page(page); + ret |= VM_FAULT_FALLBACK; + } put_page(page); } count_vm_event(THP_FAULT_FALLBACK); @@ -1179,9 +1181,10 @@ alloc: if (page) { split_huge_page(page); put_page(page); - } + } else + split_huge_page_pmd(vma, address, pmd); + ret |= VM_FAULT_FALLBACK; count_vm_event(THP_FAULT_FALLBACK); - ret |= VM_FAULT_OOM; goto out; } @@ -1545,6 +1548,7 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, entry = pmd_mknonnuma(entry); entry = pmd_modify(entry, newprot); ret = HPAGE_PMD_NR; + set_pmd_at(mm, addr, pmd, entry); BUG_ON(pmd_write(entry)); } else { struct page *page = pmd_page(*pmd); @@ -1557,16 +1561,10 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, */ if (!is_huge_zero_page(page) && !pmd_numa(*pmd)) { - entry = *pmd; - entry = pmd_mknuma(entry); + pmdp_set_numa(mm, addr, pmd); ret = HPAGE_PMD_NR; } } - - /* Set PMD if cleared earlier */ - if (ret == HPAGE_PMD_NR) - set_pmd_at(mm, addr, pmd, entry); - spin_unlock(ptl); } @@ -1963,7 +1961,7 @@ out: return ret; } -#define VM_NO_THP (VM_SPECIAL|VM_MIXEDMAP|VM_HUGETLB|VM_SHARED|VM_MAYSHARE) +#define VM_NO_THP (VM_SPECIAL | VM_HUGETLB | VM_SHARED | VM_MAYSHARE) int hugepage_madvise(struct vm_area_struct *vma, unsigned long *vm_flags, int advice) @@ -444,7 +444,7 @@ static void break_cow(struct rmap_item *rmap_item) static struct page *page_trans_compound_anon(struct page *page) { if (PageTransCompound(page)) { - struct page *head = compound_trans_head(page); + struct page *head = compound_head(page); /* * head may actually be splitted and freed from under * us but it's ok here. diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 53385cd4e6f0..5b6b0039f725 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1127,8 +1127,8 @@ skip_node: * skipping css reference should be safe. */ if (next_css) { - if ((next_css->flags & CSS_ONLINE) && - (next_css == &root->css || css_tryget(next_css))) + if ((next_css == &root->css) || + ((next_css->flags & CSS_ONLINE) && css_tryget(next_css))) return mem_cgroup_from_css(next_css); prev_css = next_css; @@ -1687,7 +1687,7 @@ void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p) * protects memcg_name and makes sure that parallel ooms do not * interleave */ - static DEFINE_SPINLOCK(oom_info_lock); + static DEFINE_MUTEX(oom_info_lock); struct cgroup *task_cgrp; struct cgroup *mem_cgrp; static char memcg_name[PATH_MAX]; @@ -1698,7 +1698,7 @@ void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p) if (!p) return; - spin_lock(&oom_info_lock); + mutex_lock(&oom_info_lock); rcu_read_lock(); mem_cgrp = memcg->css.cgroup; @@ -1767,7 +1767,7 @@ done: pr_cont("\n"); } - spin_unlock(&oom_info_lock); + mutex_unlock(&oom_info_lock); } /* @@ -6595,6 +6595,7 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css) { struct mem_cgroup *memcg = mem_cgroup_from_css(css); struct mem_cgroup_event *event, *tmp; + struct cgroup_subsys_state *iter; /* * Unregister events and notify userspace. @@ -6611,7 +6612,14 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css) kmem_cgroup_css_offline(memcg); mem_cgroup_invalidate_reclaim_iterators(memcg); - mem_cgroup_reparent_charges(memcg); + + /* + * This requires that offlining is serialized. Right now that is + * guaranteed because css_killed_work_fn() holds the cgroup_mutex. + */ + css_for_each_descendant_post(iter, css) + mem_cgroup_reparent_charges(mem_cgroup_from_css(iter)); + mem_cgroup_destroy_all_caches(memcg); vmpressure_cleanup(&memcg->vmpressure); } diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 4f08a2d61487..90002ea43638 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -945,8 +945,10 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn, * to it. Similarly, page lock is shifted. */ if (hpage != p) { - put_page(hpage); - get_page(p); + if (!(flags & MF_COUNT_INCREASED)) { + put_page(hpage); + get_page(p); + } lock_page(p); unlock_page(hpage); *hpagep = p; @@ -1649,7 +1651,7 @@ int soft_offline_page(struct page *page, int flags) { int ret; unsigned long pfn = page_to_pfn(page); - struct page *hpage = compound_trans_head(page); + struct page *hpage = compound_head(page); if (PageHWPoison(page)) { pr_info("soft offline: %#lx page already poisoned\n", pfn); diff --git a/mm/memory.c b/mm/memory.c index be6a0c0d4ae0..22dfa617bddb 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3348,6 +3348,7 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma, if (ret & VM_FAULT_LOCKED) unlock_page(vmf.page); ret = VM_FAULT_HWPOISON; + page_cache_release(vmf.page); goto uncharge_out; } @@ -3703,7 +3704,6 @@ static int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, if (unlikely(is_vm_hugetlb_page(vma))) return hugetlb_fault(mm, vma, address, flags); -retry: pgd = pgd_offset(mm, address); pud = pud_alloc(mm, pgd, address); if (!pud) @@ -3741,20 +3741,13 @@ retry: if (dirty && !pmd_write(orig_pmd)) { ret = do_huge_pmd_wp_page(mm, vma, address, pmd, orig_pmd); - /* - * If COW results in an oom, the huge pmd will - * have been split, so retry the fault on the - * pte for a smaller charge. - */ - if (unlikely(ret & VM_FAULT_OOM)) - goto retry; - return ret; + if (!(ret & VM_FAULT_FALLBACK)) + return ret; } else { huge_pmd_set_accessed(mm, vma, address, pmd, orig_pmd, dirty); + return 0; } - - return 0; } } diff --git a/mm/mprotect.c b/mm/mprotect.c index 7332c1785744..769a67a15803 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -58,36 +58,27 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, if (pte_numa(ptent)) ptent = pte_mknonnuma(ptent); ptent = pte_modify(ptent, newprot); + /* + * Avoid taking write faults for pages we + * know to be dirty. + */ + if (dirty_accountable && pte_dirty(ptent)) + ptent = pte_mkwrite(ptent); + ptep_modify_prot_commit(mm, addr, pte, ptent); updated = true; } else { struct page *page; - ptent = *pte; page = vm_normal_page(vma, addr, oldpte); if (page && !PageKsm(page)) { if (!pte_numa(oldpte)) { - ptent = pte_mknuma(ptent); - set_pte_at(mm, addr, pte, ptent); + ptep_set_numa(mm, addr, pte); updated = true; } } } - - /* - * Avoid taking write faults for pages we know to be - * dirty. - */ - if (dirty_accountable && pte_dirty(ptent)) { - ptent = pte_mkwrite(ptent); - updated = true; - } - if (updated) pages++; - - /* Only !prot_numa always clears the pte */ - if (!prot_numa) - ptep_modify_prot_commit(mm, addr, pte, ptent); } else if (IS_ENABLED(CONFIG_MIGRATION) && !pte_file(oldpte)) { swp_entry_t entry = pte_to_swp_entry(oldpte); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index e3758a09a009..3bac76ae4b30 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -369,9 +369,11 @@ void prep_compound_page(struct page *page, unsigned long order) __SetPageHead(page); for (i = 1; i < nr_pages; i++) { struct page *p = page + i; - __SetPageTail(p); set_page_count(p, 0); p->first_page = page; + /* Make sure p->first_page is always valid for PageTail() */ + smp_wmb(); + __SetPageTail(p); } } @@ -1236,6 +1238,15 @@ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp) } local_irq_restore(flags); } +static bool gfp_thisnode_allocation(gfp_t gfp_mask) +{ + return (gfp_mask & GFP_THISNODE) == GFP_THISNODE; +} +#else +static bool gfp_thisnode_allocation(gfp_t gfp_mask) +{ + return false; +} #endif /* @@ -1572,7 +1583,13 @@ again: get_pageblock_migratetype(page)); } - __mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order)); + /* + * NOTE: GFP_THISNODE allocations do not partake in the kswapd + * aging protocol, so they can't be fair. + */ + if (!gfp_thisnode_allocation(gfp_flags)) + __mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order)); + __count_zone_vm_events(PGALLOC, zone, 1 << order); zone_statistics(preferred_zone, zone, gfp_flags); local_irq_restore(flags); @@ -1944,8 +1961,12 @@ zonelist_scan: * ultimately fall back to remote zones that do not * partake in the fairness round-robin cycle of this * zonelist. + * + * NOTE: GFP_THISNODE allocations do not partake in + * the kswapd aging protocol, so they can't be fair. */ - if (alloc_flags & ALLOC_WMARK_LOW) { + if ((alloc_flags & ALLOC_WMARK_LOW) && + !gfp_thisnode_allocation(gfp_mask)) { if (zone_page_state(zone, NR_ALLOC_BATCH) <= 0) continue; if (!zone_local(preferred_zone, zone)) @@ -2501,8 +2522,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, * allowed per node queues are empty and that nodes are * over allocated. */ - if (IS_ENABLED(CONFIG_NUMA) && - (gfp_mask & GFP_THISNODE) == GFP_THISNODE) + if (gfp_thisnode_allocation(gfp_mask)) goto nopage; restart: diff --git a/mm/slub.c b/mm/slub.c index 7e3e0458bce4..25f14ad8f817 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1004,21 +1004,19 @@ static inline void slab_free_hook(struct kmem_cache *s, void *x) static void add_full(struct kmem_cache *s, struct kmem_cache_node *n, struct page *page) { - lockdep_assert_held(&n->list_lock); - if (!(s->flags & SLAB_STORE_USER)) return; + lockdep_assert_held(&n->list_lock); list_add(&page->lru, &n->full); } static void remove_full(struct kmem_cache *s, struct kmem_cache_node *n, struct page *page) { - lockdep_assert_held(&n->list_lock); - if (!(s->flags & SLAB_STORE_USER)) return; + lockdep_assert_held(&n->list_lock); list_del(&page->lru); } @@ -1520,11 +1518,9 @@ static void discard_slab(struct kmem_cache *s, struct page *page) /* * Management of partially allocated slabs. */ -static inline void add_partial(struct kmem_cache_node *n, - struct page *page, int tail) +static inline void +__add_partial(struct kmem_cache_node *n, struct page *page, int tail) { - lockdep_assert_held(&n->list_lock); - n->nr_partial++; if (tail == DEACTIVATE_TO_TAIL) list_add_tail(&page->lru, &n->partial); @@ -1532,15 +1528,27 @@ static inline void add_partial(struct kmem_cache_node *n, list_add(&page->lru, &n->partial); } -static inline void remove_partial(struct kmem_cache_node *n, - struct page *page) +static inline void add_partial(struct kmem_cache_node *n, + struct page *page, int tail) { lockdep_assert_held(&n->list_lock); + __add_partial(n, page, tail); +} +static inline void +__remove_partial(struct kmem_cache_node *n, struct page *page) +{ list_del(&page->lru); n->nr_partial--; } +static inline void remove_partial(struct kmem_cache_node *n, + struct page *page) +{ + lockdep_assert_held(&n->list_lock); + __remove_partial(n, page); +} + /* * Remove slab from the partial list, freeze it and * return the pointer to the freelist. @@ -2906,12 +2914,10 @@ static void early_kmem_cache_node_alloc(int node) inc_slabs_node(kmem_cache_node, node, page->objects); /* - * the lock is for lockdep's sake, not for any actual - * race protection + * No locks need to be taken here as it has just been + * initialized and there is no concurrent access. */ - spin_lock(&n->list_lock); - add_partial(n, page, DEACTIVATE_TO_HEAD); - spin_unlock(&n->list_lock); + __add_partial(n, page, DEACTIVATE_TO_HEAD); } static void free_kmem_cache_nodes(struct kmem_cache *s) @@ -3197,7 +3203,7 @@ static void free_partial(struct kmem_cache *s, struct kmem_cache_node *n) list_for_each_entry_safe(page, h, &n->partial, lru) { if (!page->inuse) { - remove_partial(n, page); + __remove_partial(n, page); discard_slab(s, page); } else { list_slab_objects(s, page, diff --git a/mm/swap.c b/mm/swap.c index b31ba67d440a..0092097b3f4c 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -98,7 +98,7 @@ static void put_compound_page(struct page *page) } /* __split_huge_page_refcount can run under us */ - page_head = compound_trans_head(page); + page_head = compound_head(page); /* * THP can not break up slab pages so avoid taking @@ -253,7 +253,7 @@ bool __get_page_tail(struct page *page) */ unsigned long flags; bool got; - struct page *page_head = compound_trans_head(page); + struct page *page_head = compound_head(page); /* Ref to put_compound_page() comment. */ if (!__compound_tail_refcounted(page_head)) { diff --git a/mm/vmpressure.c b/mm/vmpressure.c index 196970a4541f..d4042e75f7c7 100644 --- a/mm/vmpressure.c +++ b/mm/vmpressure.c @@ -19,6 +19,7 @@ #include <linux/mm.h> #include <linux/vmstat.h> #include <linux/eventfd.h> +#include <linux/slab.h> #include <linux/swap.h> #include <linux/printk.h> #include <linux/vmpressure.h> diff --git a/net/8021q/vlan.h b/net/8021q/vlan.h index 5704ed9c3a23..9d010a09ab98 100644 --- a/net/8021q/vlan.h +++ b/net/8021q/vlan.h @@ -38,9 +38,9 @@ struct vlan_info { static inline unsigned int vlan_proto_idx(__be16 proto) { switch (proto) { - case __constant_htons(ETH_P_8021Q): + case htons(ETH_P_8021Q): return VLAN_PROTO_8021Q; - case __constant_htons(ETH_P_8021AD): + case htons(ETH_P_8021AD): return VLAN_PROTO_8021AD; default: BUG(); diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c index 6ee48aac776f..35b3c192d7b9 100644 --- a/net/8021q/vlan_core.c +++ b/net/8021q/vlan_core.c @@ -22,11 +22,11 @@ bool vlan_do_receive(struct sk_buff **skbp) return false; skb->dev = vlan_dev; - if (skb->pkt_type == PACKET_OTHERHOST) { + if (unlikely(skb->pkt_type == PACKET_OTHERHOST)) { /* Our lower layer thinks this is not local, let's make sure. * This allows the VLAN to have a different MAC than the * underlying device, and still route correctly. */ - if (ether_addr_equal(eth_hdr(skb)->h_dest, vlan_dev->dev_addr)) + if (ether_addr_equal_64bits(eth_hdr(skb)->h_dest, vlan_dev->dev_addr)) skb->pkt_type = PACKET_HOST; } diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index de51c48c4393..566adbf5c506 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -556,7 +556,7 @@ static const struct net_device_ops vlan_netdev_ops; static int vlan_dev_init(struct net_device *dev) { struct net_device *real_dev = vlan_dev_priv(dev)->real_dev; - int subclass = 0, i; + int subclass = 0; netif_carrier_off(dev); @@ -606,17 +606,10 @@ static int vlan_dev_init(struct net_device *dev) vlan_dev_set_lockdep_class(dev, subclass); - vlan_dev_priv(dev)->vlan_pcpu_stats = alloc_percpu(struct vlan_pcpu_stats); + vlan_dev_priv(dev)->vlan_pcpu_stats = netdev_alloc_pcpu_stats(struct vlan_pcpu_stats); if (!vlan_dev_priv(dev)->vlan_pcpu_stats) return -ENOMEM; - for_each_possible_cpu(i) { - struct vlan_pcpu_stats *vlan_stat; - vlan_stat = per_cpu_ptr(vlan_dev_priv(dev)->vlan_pcpu_stats, i); - u64_stats_init(&vlan_stat->syncp); - } - - return 0; } diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c index c7e634af8516..8ac8a5cc2143 100644 --- a/net/8021q/vlan_netlink.c +++ b/net/8021q/vlan_netlink.c @@ -56,8 +56,8 @@ static int vlan_validate(struct nlattr *tb[], struct nlattr *data[]) if (data[IFLA_VLAN_PROTOCOL]) { switch (nla_get_be16(data[IFLA_VLAN_PROTOCOL])) { - case __constant_htons(ETH_P_8021Q): - case __constant_htons(ETH_P_8021AD): + case htons(ETH_P_8021Q): + case htons(ETH_P_8021AD): break; default: return -EPROTONOSUPPORT; diff --git a/net/9p/client.c b/net/9p/client.c index a5e4d2dcb03e..9186550d77a6 100644 --- a/net/9p/client.c +++ b/net/9p/client.c @@ -204,7 +204,7 @@ free_and_return: return ret; } -struct p9_fcall *p9_fcall_alloc(int alloc_msize) +static struct p9_fcall *p9_fcall_alloc(int alloc_msize) { struct p9_fcall *fc; fc = kmalloc(sizeof(struct p9_fcall) + alloc_msize, GFP_NOFS); diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c index cd1e1ede73a4..ac2666c1d011 100644 --- a/net/9p/trans_virtio.c +++ b/net/9p/trans_virtio.c @@ -340,7 +340,10 @@ static int p9_get_mapped_pages(struct virtio_chan *chan, int count = nr_pages; while (nr_pages) { s = rest_of_page(data); - pages[index++] = kmap_to_page(data); + if (is_vmalloc_addr(data)) + pages[index++] = vmalloc_to_page(data); + else + pages[index++] = kmap_to_page(data); data += s; nr_pages--; } diff --git a/net/appletalk/aarp.c b/net/appletalk/aarp.c index d27b86dfb0e9..d1c55d8dd0a2 100644 --- a/net/appletalk/aarp.c +++ b/net/appletalk/aarp.c @@ -926,7 +926,7 @@ static struct aarp_entry *iter_next(struct aarp_iter_state *iter, loff_t *pos) struct aarp_entry *entry; rescan: - while(ct < AARP_HASH_SIZE) { + while (ct < AARP_HASH_SIZE) { for (entry = table[ct]; entry; entry = entry->next) { if (!pos || ++off == *pos) { iter->table = table; @@ -995,7 +995,7 @@ static const char *dt2str(unsigned long ticks) { static char buf[32]; - sprintf(buf, "%ld.%02ld", ticks / HZ, ((ticks % HZ) * 100 ) / HZ); + sprintf(buf, "%ld.%02ld", ticks / HZ, ((ticks % HZ) * 100) / HZ); return buf; } diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c index 02806c6b2ff3..786ee2f83d5f 100644 --- a/net/appletalk/ddp.c +++ b/net/appletalk/ddp.c @@ -293,7 +293,7 @@ static int atif_probe_device(struct atalk_iface *atif) /* Perform AARP probing for a proxy address */ static int atif_proxy_probe_device(struct atalk_iface *atif, - struct atalk_addr* proxy_addr) + struct atalk_addr *proxy_addr) { int netrange = ntohs(atif->nets.nr_lastnet) - ntohs(atif->nets.nr_firstnet) + 1; @@ -581,7 +581,7 @@ out: } /* Delete a route. Find it and discard it */ -static int atrtr_delete(struct atalk_addr * addr) +static int atrtr_delete(struct atalk_addr *addr) { struct atalk_route **r = &atalk_routes; int retval = 0; @@ -936,11 +936,11 @@ static unsigned long atalk_sum_skb(const struct sk_buff *skb, int offset, int i, copy; /* checksum stuff in header space */ - if ( (copy = start - offset) > 0) { + if ((copy = start - offset) > 0) { if (copy > len) copy = len; sum = atalk_sum_partial(skb->data + offset, copy, sum); - if ( (len -= copy) == 0) + if ((len -= copy) == 0) return sum; offset += copy; @@ -1151,7 +1151,7 @@ static int atalk_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) goto out; at->src_net = addr->sat_addr.s_net = ap->s_net; - at->src_node = addr->sat_addr.s_node= ap->s_node; + at->src_node = addr->sat_addr.s_node = ap->s_node; } else { err = -EADDRNOTAVAIL; if (!atalk_find_interface(addr->sat_addr.s_net, @@ -1790,53 +1790,53 @@ static int atalk_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) void __user *argp = (void __user *)arg; switch (cmd) { - /* Protocol layer */ - case TIOCOUTQ: { - long amount = sk->sk_sndbuf - sk_wmem_alloc_get(sk); + /* Protocol layer */ + case TIOCOUTQ: { + long amount = sk->sk_sndbuf - sk_wmem_alloc_get(sk); - if (amount < 0) - amount = 0; - rc = put_user(amount, (int __user *)argp); - break; - } - case TIOCINQ: { - /* - * These two are safe on a single CPU system as only - * user tasks fiddle here - */ - struct sk_buff *skb = skb_peek(&sk->sk_receive_queue); - long amount = 0; + if (amount < 0) + amount = 0; + rc = put_user(amount, (int __user *)argp); + break; + } + case TIOCINQ: { + /* + * These two are safe on a single CPU system as only + * user tasks fiddle here + */ + struct sk_buff *skb = skb_peek(&sk->sk_receive_queue); + long amount = 0; - if (skb) - amount = skb->len - sizeof(struct ddpehdr); - rc = put_user(amount, (int __user *)argp); - break; - } - case SIOCGSTAMP: - rc = sock_get_timestamp(sk, argp); - break; - case SIOCGSTAMPNS: - rc = sock_get_timestampns(sk, argp); - break; - /* Routing */ - case SIOCADDRT: - case SIOCDELRT: - rc = -EPERM; - if (capable(CAP_NET_ADMIN)) - rc = atrtr_ioctl(cmd, argp); - break; - /* Interface */ - case SIOCGIFADDR: - case SIOCSIFADDR: - case SIOCGIFBRDADDR: - case SIOCATALKDIFADDR: - case SIOCDIFADDR: - case SIOCSARP: /* proxy AARP */ - case SIOCDARP: /* proxy AARP */ - rtnl_lock(); - rc = atif_ioctl(cmd, argp); - rtnl_unlock(); - break; + if (skb) + amount = skb->len - sizeof(struct ddpehdr); + rc = put_user(amount, (int __user *)argp); + break; + } + case SIOCGSTAMP: + rc = sock_get_timestamp(sk, argp); + break; + case SIOCGSTAMPNS: + rc = sock_get_timestampns(sk, argp); + break; + /* Routing */ + case SIOCADDRT: + case SIOCDELRT: + rc = -EPERM; + if (capable(CAP_NET_ADMIN)) + rc = atrtr_ioctl(cmd, argp); + break; + /* Interface */ + case SIOCGIFADDR: + case SIOCSIFADDR: + case SIOCGIFBRDADDR: + case SIOCATALKDIFADDR: + case SIOCDIFADDR: + case SIOCSARP: /* proxy AARP */ + case SIOCDARP: /* proxy AARP */ + rtnl_lock(); + rc = atif_ioctl(cmd, argp); + rtnl_unlock(); + break; } return rc; diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index 512159bf607f..8323bced8e5b 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -241,19 +241,19 @@ batadv_iv_ogm_orig_get(struct batadv_priv *bat_priv, const uint8_t *addr) size = bat_priv->num_ifaces * sizeof(uint8_t); orig_node->bat_iv.bcast_own_sum = kzalloc(size, GFP_ATOMIC); if (!orig_node->bat_iv.bcast_own_sum) - goto free_bcast_own; + goto free_orig_node; hash_added = batadv_hash_add(bat_priv->orig_hash, batadv_compare_orig, batadv_choose_orig, orig_node, &orig_node->hash_entry); if (hash_added != 0) - goto free_bcast_own; + goto free_orig_node; return orig_node; -free_bcast_own: - kfree(orig_node->bat_iv.bcast_own); free_orig_node: + /* free twice, as batadv_orig_node_new sets refcount to 2 */ + batadv_orig_node_free_ref(orig_node); batadv_orig_node_free_ref(orig_node); return NULL; @@ -266,7 +266,7 @@ batadv_iv_ogm_neigh_new(struct batadv_hard_iface *hard_iface, struct batadv_orig_node *orig_neigh) { struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); - struct batadv_neigh_node *neigh_node; + struct batadv_neigh_node *neigh_node, *tmp_neigh_node; neigh_node = batadv_neigh_node_new(hard_iface, neigh_addr, orig_node); if (!neigh_node) @@ -281,14 +281,24 @@ batadv_iv_ogm_neigh_new(struct batadv_hard_iface *hard_iface, neigh_node->orig_node = orig_neigh; neigh_node->if_incoming = hard_iface; - batadv_dbg(BATADV_DBG_BATMAN, bat_priv, - "Creating new neighbor %pM for orig_node %pM on interface %s\n", - neigh_addr, orig_node->orig, hard_iface->net_dev->name); - spin_lock_bh(&orig_node->neigh_list_lock); - hlist_add_head_rcu(&neigh_node->list, &orig_node->neigh_list); + tmp_neigh_node = batadv_neigh_node_get(orig_node, hard_iface, + neigh_addr); + if (!tmp_neigh_node) { + hlist_add_head_rcu(&neigh_node->list, &orig_node->neigh_list); + } else { + kfree(neigh_node); + batadv_hardif_free_ref(hard_iface); + neigh_node = tmp_neigh_node; + } spin_unlock_bh(&orig_node->neigh_list_lock); + if (!tmp_neigh_node) + batadv_dbg(BATADV_DBG_BATMAN, bat_priv, + "Creating new neighbor %pM for orig_node %pM on interface %s\n", + neigh_addr, orig_node->orig, + hard_iface->net_dev->name); + out: return neigh_node; } diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c index 55cf2260d295..d7fafc1009a0 100644 --- a/net/batman-adv/gateway_client.c +++ b/net/batman-adv/gateway_client.c @@ -389,8 +389,6 @@ out: batadv_neigh_ifinfo_free_ref(router_gw_tq); if (router_orig_tq) batadv_neigh_ifinfo_free_ref(router_orig_tq); - - return; } /** diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index 3d417d3641c6..b851cc580853 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -241,7 +241,7 @@ int batadv_hardif_min_mtu(struct net_device *soft_iface) { struct batadv_priv *bat_priv = netdev_priv(soft_iface); const struct batadv_hard_iface *hard_iface; - int min_mtu = ETH_DATA_LEN; + int min_mtu = INT_MAX; rcu_read_lock(); list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) { @@ -256,8 +256,6 @@ int batadv_hardif_min_mtu(struct net_device *soft_iface) } rcu_read_unlock(); - atomic_set(&bat_priv->packet_size_max, min_mtu); - if (atomic_read(&bat_priv->fragmentation) == 0) goto out; @@ -268,13 +266,21 @@ int batadv_hardif_min_mtu(struct net_device *soft_iface) min_mtu = min_t(int, min_mtu, BATADV_FRAG_MAX_FRAG_SIZE); min_mtu -= sizeof(struct batadv_frag_packet); min_mtu *= BATADV_FRAG_MAX_FRAGMENTS; - atomic_set(&bat_priv->packet_size_max, min_mtu); - - /* with fragmentation enabled we can fragment external packets easily */ - min_mtu = min_t(int, min_mtu, ETH_DATA_LEN); out: - return min_mtu - batadv_max_header_len(); + /* report to the other components the maximum amount of bytes that + * batman-adv can send over the wire (without considering the payload + * overhead). For example, this value is used by TT to compute the + * maximum local table table size + */ + atomic_set(&bat_priv->packet_size_max, min_mtu); + + /* the real soft-interface MTU is computed by removing the payload + * overhead from the maximum amount of bytes that was just computed. + * + * However batman-adv does not support MTUs bigger than ETH_DATA_LEN + */ + return min_t(int, min_mtu - batadv_max_header_len(), ETH_DATA_LEN); } /* adjusts the MTU if a new interface with a smaller MTU appeared. */ diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index 6df12a2e3605..853941629dc1 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -458,6 +458,42 @@ out: } /** + * batadv_neigh_node_get - retrieve a neighbour from the list + * @orig_node: originator which the neighbour belongs to + * @hard_iface: the interface where this neighbour is connected to + * @addr: the address of the neighbour + * + * Looks for and possibly returns a neighbour belonging to this originator list + * which is connected through the provided hard interface. + * Returns NULL if the neighbour is not found. + */ +struct batadv_neigh_node * +batadv_neigh_node_get(const struct batadv_orig_node *orig_node, + const struct batadv_hard_iface *hard_iface, + const uint8_t *addr) +{ + struct batadv_neigh_node *tmp_neigh_node, *res = NULL; + + rcu_read_lock(); + hlist_for_each_entry_rcu(tmp_neigh_node, &orig_node->neigh_list, list) { + if (!batadv_compare_eth(tmp_neigh_node->addr, addr)) + continue; + + if (tmp_neigh_node->if_incoming != hard_iface) + continue; + + if (!atomic_inc_not_zero(&tmp_neigh_node->refcount)) + continue; + + res = tmp_neigh_node; + break; + } + rcu_read_unlock(); + + return res; +} + +/** * batadv_orig_ifinfo_free_rcu - free the orig_ifinfo object * @rcu: rcu pointer of the orig_ifinfo object */ diff --git a/net/batman-adv/originator.h b/net/batman-adv/originator.h index 37be290f63f6..db3a9ed734cb 100644 --- a/net/batman-adv/originator.h +++ b/net/batman-adv/originator.h @@ -29,6 +29,10 @@ void batadv_orig_node_free_ref_now(struct batadv_orig_node *orig_node); struct batadv_orig_node *batadv_orig_node_new(struct batadv_priv *bat_priv, const uint8_t *addr); struct batadv_neigh_node * +batadv_neigh_node_get(const struct batadv_orig_node *orig_node, + const struct batadv_hard_iface *hard_iface, + const uint8_t *addr); +struct batadv_neigh_node * batadv_neigh_node_new(struct batadv_hard_iface *hard_iface, const uint8_t *neigh_addr, struct batadv_orig_node *orig_node); diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index 1ed9f7c9ecea..a953d5b196a3 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -688,7 +688,7 @@ static int batadv_check_unicast_ttvn(struct batadv_priv *bat_priv, int is_old_ttvn; /* check if there is enough data before accessing it */ - if (pskb_may_pull(skb, hdr_len + ETH_HLEN) < 0) + if (!pskb_may_pull(skb, hdr_len + ETH_HLEN)) return 0; /* create a copy of the skb (in case of for re-routing) to modify it. */ @@ -918,6 +918,8 @@ int batadv_recv_unicast_tvlv(struct sk_buff *skb, if (ret != NET_RX_SUCCESS) ret = batadv_route_unicast_packet(skb, recv_if); + else + consume_skb(skb); return ret; } diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c index 579f5f00a385..843febd1e519 100644 --- a/net/batman-adv/send.c +++ b/net/batman-adv/send.c @@ -254,9 +254,9 @@ static int batadv_send_skb_unicast(struct batadv_priv *bat_priv, struct batadv_orig_node *orig_node, unsigned short vid) { - struct ethhdr *ethhdr = (struct ethhdr *)skb->data; + struct ethhdr *ethhdr; struct batadv_unicast_packet *unicast_packet; - int ret = NET_XMIT_DROP; + int ret = NET_XMIT_DROP, hdr_size; if (!orig_node) goto out; @@ -265,12 +265,16 @@ static int batadv_send_skb_unicast(struct batadv_priv *bat_priv, case BATADV_UNICAST: if (!batadv_send_skb_prepare_unicast(skb, orig_node)) goto out; + + hdr_size = sizeof(*unicast_packet); break; case BATADV_UNICAST_4ADDR: if (!batadv_send_skb_prepare_unicast_4addr(bat_priv, skb, orig_node, packet_subtype)) goto out; + + hdr_size = sizeof(struct batadv_unicast_4addr_packet); break; default: /* this function supports UNICAST and UNICAST_4ADDR only. It @@ -279,6 +283,7 @@ static int batadv_send_skb_unicast(struct batadv_priv *bat_priv, goto out; } + ethhdr = (struct ethhdr *)(skb->data + hdr_size); unicast_packet = (struct batadv_unicast_packet *)skb->data; /* inform the destination node that we are still missing a correct route diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index b6071f675a3e..959dde721c46 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -1975,6 +1975,7 @@ static uint32_t batadv_tt_global_crc(struct batadv_priv *bat_priv, struct hlist_head *head; uint32_t i, crc_tmp, crc = 0; uint8_t flags; + __be16 tmp_vid; for (i = 0; i < hash->size; i++) { head = &hash->table[i]; @@ -2011,8 +2012,11 @@ static uint32_t batadv_tt_global_crc(struct batadv_priv *bat_priv, orig_node)) continue; - crc_tmp = crc32c(0, &tt_common->vid, - sizeof(tt_common->vid)); + /* use network order to read the VID: this ensures that + * every node reads the bytes in the same order. + */ + tmp_vid = htons(tt_common->vid); + crc_tmp = crc32c(0, &tmp_vid, sizeof(tmp_vid)); /* compute the CRC on flags that have to be kept in sync * among nodes @@ -2046,6 +2050,7 @@ static uint32_t batadv_tt_local_crc(struct batadv_priv *bat_priv, struct hlist_head *head; uint32_t i, crc_tmp, crc = 0; uint8_t flags; + __be16 tmp_vid; for (i = 0; i < hash->size; i++) { head = &hash->table[i]; @@ -2064,8 +2069,11 @@ static uint32_t batadv_tt_local_crc(struct batadv_priv *bat_priv, if (tt_common->flags & BATADV_TT_CLIENT_NEW) continue; - crc_tmp = crc32c(0, &tt_common->vid, - sizeof(tt_common->vid)); + /* use network order to read the VID: this ensures that + * every node reads the bytes in the same order. + */ + tmp_vid = htons(tt_common->vid); + crc_tmp = crc32c(0, &tmp_vid, sizeof(tmp_vid)); /* compute the CRC on flags that have to be kept in sync * among nodes @@ -2262,6 +2270,7 @@ static bool batadv_tt_global_check_crc(struct batadv_orig_node *orig_node, { struct batadv_tvlv_tt_vlan_data *tt_vlan_tmp; struct batadv_orig_node_vlan *vlan; + uint32_t crc; int i; /* check if each received CRC matches the locally stored one */ @@ -2281,7 +2290,10 @@ static bool batadv_tt_global_check_crc(struct batadv_orig_node *orig_node, if (!vlan) return false; - if (vlan->tt.crc != ntohl(tt_vlan_tmp->crc)) + crc = vlan->tt.crc; + batadv_orig_node_vlan_free_ref(vlan); + + if (crc != ntohl(tt_vlan_tmp->crc)) return false; } @@ -3218,7 +3230,6 @@ static void batadv_tt_update_orig(struct batadv_priv *bat_priv, spin_lock_bh(&orig_node->tt_lock); - tt_change = (struct batadv_tvlv_tt_change *)tt_buff; batadv_tt_update_changes(bat_priv, orig_node, tt_num_changes, ttvn, tt_change); diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c index adb3ea04adaa..73492b91105a 100644 --- a/net/bluetooth/6lowpan.c +++ b/net/bluetooth/6lowpan.c @@ -27,7 +27,7 @@ #include "6lowpan.h" -#include "../ieee802154/6lowpan.h" /* for the compression support */ +#include <net/6lowpan.h> /* for the compression support */ #define IFACE_NAME_TEMPLATE "bt%d" #define EUI64_ADDR_LEN 8 diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c index 292e619db896..d9fb93451442 100644 --- a/net/bluetooth/hidp/core.c +++ b/net/bluetooth/hidp/core.c @@ -430,6 +430,16 @@ static void hidp_del_timer(struct hidp_session *session) del_timer(&session->timer); } +static void hidp_process_report(struct hidp_session *session, + int type, const u8 *data, int len, int intr) +{ + if (len > HID_MAX_BUFFER_SIZE) + len = HID_MAX_BUFFER_SIZE; + + memcpy(session->input_buf, data, len); + hid_input_report(session->hid, type, session->input_buf, len, intr); +} + static void hidp_process_handshake(struct hidp_session *session, unsigned char param) { @@ -502,7 +512,8 @@ static int hidp_process_data(struct hidp_session *session, struct sk_buff *skb, hidp_input_report(session, skb); if (session->hid) - hid_input_report(session->hid, HID_INPUT_REPORT, skb->data, skb->len, 0); + hidp_process_report(session, HID_INPUT_REPORT, + skb->data, skb->len, 0); break; case HIDP_DATA_RTYPE_OTHER: @@ -584,7 +595,8 @@ static void hidp_recv_intr_frame(struct hidp_session *session, hidp_input_report(session, skb); if (session->hid) { - hid_input_report(session->hid, HID_INPUT_REPORT, skb->data, skb->len, 1); + hidp_process_report(session, HID_INPUT_REPORT, + skb->data, skb->len, 1); BT_DBG("report len %d", skb->len); } } else { diff --git a/net/bluetooth/hidp/hidp.h b/net/bluetooth/hidp/hidp.h index ab5241400cf7..8798492a6e99 100644 --- a/net/bluetooth/hidp/hidp.h +++ b/net/bluetooth/hidp/hidp.h @@ -24,6 +24,7 @@ #define __HIDP_H #include <linux/types.h> +#include <linux/hid.h> #include <linux/kref.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/l2cap.h> @@ -179,6 +180,9 @@ struct hidp_session { /* Used in hidp_output_raw_report() */ int output_report_success; /* boolean */ + + /* temporary input buffer */ + u8 input_buf[HID_MAX_BUFFER_SIZE]; }; /* HIDP init defines */ diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index e4401a531afb..b063050b63e2 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -88,18 +88,11 @@ out: static int br_dev_init(struct net_device *dev) { struct net_bridge *br = netdev_priv(dev); - int i; - br->stats = alloc_percpu(struct pcpu_sw_netstats); + br->stats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); if (!br->stats) return -ENOMEM; - for_each_possible_cpu(i) { - struct pcpu_sw_netstats *br_dev_stats; - br_dev_stats = per_cpu_ptr(br->stats, i); - u64_stats_init(&br_dev_stats->syncp); - } - return 0; } @@ -187,8 +180,7 @@ static int br_set_mac_address(struct net_device *dev, void *p) spin_lock_bh(&br->lock); if (!ether_addr_equal(dev->dev_addr, addr->sa_data)) { - memcpy(dev->dev_addr, addr->sa_data, ETH_ALEN); - br_fdb_change_mac_address(br, addr->sa_data); + /* Mac address will be changed in br_stp_change_bridge_id(). */ br_stp_change_bridge_id(br, addr->sa_data); } spin_unlock_bh(&br->lock); @@ -226,6 +218,33 @@ static void br_netpoll_cleanup(struct net_device *dev) br_netpoll_disable(p); } +static int __br_netpoll_enable(struct net_bridge_port *p, gfp_t gfp) +{ + struct netpoll *np; + int err; + + np = kzalloc(sizeof(*p->np), gfp); + if (!np) + return -ENOMEM; + + err = __netpoll_setup(np, p->dev, gfp); + if (err) { + kfree(np); + return err; + } + + p->np = np; + return err; +} + +int br_netpoll_enable(struct net_bridge_port *p, gfp_t gfp) +{ + if (!p->br->dev->npinfo) + return 0; + + return __br_netpoll_enable(p, gfp); +} + static int br_netpoll_setup(struct net_device *dev, struct netpoll_info *ni, gfp_t gfp) { @@ -236,7 +255,7 @@ static int br_netpoll_setup(struct net_device *dev, struct netpoll_info *ni, list_for_each_entry(p, &br->port_list, list) { if (!p->dev) continue; - err = br_netpoll_enable(p, gfp); + err = __br_netpoll_enable(p, gfp); if (err) goto fail; } @@ -249,28 +268,6 @@ fail: goto out; } -int br_netpoll_enable(struct net_bridge_port *p, gfp_t gfp) -{ - struct netpoll *np; - int err; - - if (!p->br->dev->npinfo) - return 0; - - np = kzalloc(sizeof(*p->np), gfp); - if (!np) - return -ENOMEM; - - err = __netpoll_setup(np, p->dev, gfp); - if (err) { - kfree(np); - return err; - } - - p->np = np; - return err; -} - void br_netpoll_disable(struct net_bridge_port *p) { struct netpoll *np = p->np; @@ -370,7 +367,7 @@ void br_dev_setup(struct net_device *dev) br->bridge_id.prio[0] = 0x80; br->bridge_id.prio[1] = 0x00; - memcpy(br->group_addr, eth_reserved_addr_base, ETH_ALEN); + ether_addr_copy(br->group_addr, eth_reserved_addr_base); br->stp_enabled = BR_NO_STP; br->group_fwd_mask = BR_GROUPFWD_DEFAULT; diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index c5f5a4a933f4..9203d5a1943f 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -27,6 +27,9 @@ #include "br_private.h" static struct kmem_cache *br_fdb_cache __read_mostly; +static struct net_bridge_fdb_entry *fdb_find(struct hlist_head *head, + const unsigned char *addr, + __u16 vid); static int fdb_insert(struct net_bridge *br, struct net_bridge_port *source, const unsigned char *addr, u16 vid); static void fdb_notify(struct net_bridge *br, @@ -89,11 +92,57 @@ static void fdb_delete(struct net_bridge *br, struct net_bridge_fdb_entry *f) call_rcu(&f->rcu, fdb_rcu_free); } +/* Delete a local entry if no other port had the same address. */ +static void fdb_delete_local(struct net_bridge *br, + const struct net_bridge_port *p, + struct net_bridge_fdb_entry *f) +{ + const unsigned char *addr = f->addr.addr; + u16 vid = f->vlan_id; + struct net_bridge_port *op; + + /* Maybe another port has same hw addr? */ + list_for_each_entry(op, &br->port_list, list) { + if (op != p && ether_addr_equal(op->dev->dev_addr, addr) && + (!vid || nbp_vlan_find(op, vid))) { + f->dst = op; + f->added_by_user = 0; + return; + } + } + + /* Maybe bridge device has same hw addr? */ + if (p && ether_addr_equal(br->dev->dev_addr, addr) && + (!vid || br_vlan_find(br, vid))) { + f->dst = NULL; + f->added_by_user = 0; + return; + } + + fdb_delete(br, f); +} + +void br_fdb_find_delete_local(struct net_bridge *br, + const struct net_bridge_port *p, + const unsigned char *addr, u16 vid) +{ + struct hlist_head *head = &br->hash[br_mac_hash(addr, vid)]; + struct net_bridge_fdb_entry *f; + + spin_lock_bh(&br->hash_lock); + f = fdb_find(head, addr, vid); + if (f && f->is_local && !f->added_by_user && f->dst == p) + fdb_delete_local(br, p, f); + spin_unlock_bh(&br->hash_lock); +} + void br_fdb_changeaddr(struct net_bridge_port *p, const unsigned char *newaddr) { struct net_bridge *br = p->br; - bool no_vlan = (nbp_get_vlan_info(p) == NULL) ? true : false; + struct net_port_vlans *pv = nbp_get_vlan_info(p); + bool no_vlan = !pv; int i; + u16 vid; spin_lock_bh(&br->hash_lock); @@ -104,38 +153,34 @@ void br_fdb_changeaddr(struct net_bridge_port *p, const unsigned char *newaddr) struct net_bridge_fdb_entry *f; f = hlist_entry(h, struct net_bridge_fdb_entry, hlist); - if (f->dst == p && f->is_local) { - /* maybe another port has same hw addr? */ - struct net_bridge_port *op; - u16 vid = f->vlan_id; - list_for_each_entry(op, &br->port_list, list) { - if (op != p && - ether_addr_equal(op->dev->dev_addr, - f->addr.addr) && - nbp_vlan_find(op, vid)) { - f->dst = op; - goto insert; - } - } - + if (f->dst == p && f->is_local && !f->added_by_user) { /* delete old one */ - fdb_delete(br, f); -insert: - /* insert new address, may fail if invalid - * address or dup. - */ - fdb_insert(br, p, newaddr, vid); + fdb_delete_local(br, p, f); /* if this port has no vlan information * configured, we can safely be done at * this point. */ if (no_vlan) - goto done; + goto insert; } } } +insert: + /* insert new address, may fail if invalid address or dup. */ + fdb_insert(br, p, newaddr, 0); + + if (no_vlan) + goto done; + + /* Now add entries for every VLAN configured on the port. + * This function runs under RTNL so the bitmap will not change + * from under us. + */ + for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) + fdb_insert(br, p, newaddr, vid); + done: spin_unlock_bh(&br->hash_lock); } @@ -146,10 +191,12 @@ void br_fdb_change_mac_address(struct net_bridge *br, const u8 *newaddr) struct net_port_vlans *pv; u16 vid = 0; + spin_lock_bh(&br->hash_lock); + /* If old entry was unassociated with any port, then delete it. */ f = __br_fdb_get(br, br->dev->dev_addr, 0); if (f && f->is_local && !f->dst) - fdb_delete(br, f); + fdb_delete_local(br, NULL, f); fdb_insert(br, NULL, newaddr, 0); @@ -159,14 +206,16 @@ void br_fdb_change_mac_address(struct net_bridge *br, const u8 *newaddr) */ pv = br_get_vlan_info(br); if (!pv) - return; + goto out; for_each_set_bit_from(vid, pv->vlan_bitmap, VLAN_N_VID) { f = __br_fdb_get(br, br->dev->dev_addr, vid); if (f && f->is_local && !f->dst) - fdb_delete(br, f); + fdb_delete_local(br, NULL, f); fdb_insert(br, NULL, newaddr, vid); } +out: + spin_unlock_bh(&br->hash_lock); } void br_fdb_cleanup(unsigned long _data) @@ -235,25 +284,11 @@ void br_fdb_delete_by_port(struct net_bridge *br, if (f->is_static && !do_all) continue; - /* - * if multiple ports all have the same device address - * then when one port is deleted, assign - * the local entry to other port - */ - if (f->is_local) { - struct net_bridge_port *op; - list_for_each_entry(op, &br->port_list, list) { - if (op != p && - ether_addr_equal(op->dev->dev_addr, - f->addr.addr)) { - f->dst = op; - goto skip_delete; - } - } - } - fdb_delete(br, f); - skip_delete: ; + if (f->is_local) + fdb_delete_local(br, p, f); + else + fdb_delete(br, f); } } spin_unlock_bh(&br->hash_lock); @@ -397,6 +432,7 @@ static struct net_bridge_fdb_entry *fdb_create(struct hlist_head *head, fdb->vlan_id = vid; fdb->is_local = 0; fdb->is_static = 0; + fdb->added_by_user = 0; fdb->updated = fdb->used = jiffies; hlist_add_head_rcu(&fdb->hlist, head); } @@ -447,7 +483,7 @@ int br_fdb_insert(struct net_bridge *br, struct net_bridge_port *source, } void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source, - const unsigned char *addr, u16 vid) + const unsigned char *addr, u16 vid, bool added_by_user) { struct hlist_head *head = &br->hash[br_mac_hash(addr, vid)]; struct net_bridge_fdb_entry *fdb; @@ -473,13 +509,18 @@ void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source, /* fastpath: update of existing entry */ fdb->dst = source; fdb->updated = jiffies; + if (unlikely(added_by_user)) + fdb->added_by_user = 1; } } else { spin_lock(&br->hash_lock); if (likely(!fdb_find(head, addr, vid))) { fdb = fdb_create(head, source, addr, vid); - if (fdb) + if (fdb) { + if (unlikely(added_by_user)) + fdb->added_by_user = 1; fdb_notify(br, fdb, RTM_NEWNEIGH); + } } /* else we lose race and someone else inserts * it first, don't bother updating @@ -647,6 +688,7 @@ static int fdb_add_entry(struct net_bridge_port *source, const __u8 *addr, modified = true; } + fdb->added_by_user = 1; fdb->used = jiffies; if (modified) { @@ -664,7 +706,7 @@ static int __br_fdb_add(struct ndmsg *ndm, struct net_bridge_port *p, if (ndm->ndm_flags & NTF_USE) { rcu_read_lock(); - br_fdb_update(p->br, p, addr, vid); + br_fdb_update(p->br, p, addr, vid, true); rcu_read_unlock(); } else { spin_lock_bh(&p->br->hash_lock); @@ -749,8 +791,7 @@ out: return err; } -int fdb_delete_by_addr(struct net_bridge *br, const u8 *addr, - u16 vlan) +static int fdb_delete_by_addr(struct net_bridge *br, const u8 *addr, u16 vlan) { struct hlist_head *head = &br->hash[br_mac_hash(addr, vlan)]; struct net_bridge_fdb_entry *fdb; diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index cffe1d666ba1..54d207d3a31c 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -389,6 +389,9 @@ int br_add_if(struct net_bridge *br, struct net_device *dev) if (br->dev->needed_headroom < dev->needed_headroom) br->dev->needed_headroom = dev->needed_headroom; + if (br_fdb_insert(br, p, dev->dev_addr, 0)) + netdev_err(dev, "failed insert local address bridge forwarding table\n"); + spin_lock_bh(&br->lock); changed_addr = br_stp_recalculate_bridge_id(br); @@ -404,9 +407,6 @@ int br_add_if(struct net_bridge *br, struct net_device *dev) dev_set_mtu(br->dev, br_min_mtu(br)); - if (br_fdb_insert(br, p, dev->dev_addr, 0)) - netdev_err(dev, "failed insert local address bridge forwarding table\n"); - kobject_uevent(&p->kobj, KOBJ_ADD); return 0; diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index bf8dc7d308d6..28d544627422 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -77,7 +77,7 @@ int br_handle_frame_finish(struct sk_buff *skb) /* insert into forwarding database after filtering to avoid spoofing */ br = p->br; if (p->flags & BR_LEARNING) - br_fdb_update(br, p, eth_hdr(skb)->h_source, vid); + br_fdb_update(br, p, eth_hdr(skb)->h_source, vid, false); if (!is_broadcast_ether_addr(dest) && is_multicast_ether_addr(dest) && br_multicast_rcv(br, p, skb, vid)) @@ -148,7 +148,7 @@ static int br_handle_local_finish(struct sk_buff *skb) br_vlan_get_tag(skb, &vid); if (p->flags & BR_LEARNING) - br_fdb_update(p->br, p, eth_hdr(skb)->h_source, vid); + br_fdb_update(p->br, p, eth_hdr(skb)->h_source, vid, false); return 0; /* process further */ } diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index ef66365b7354..c97c3c8ccdfb 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -363,7 +363,7 @@ static struct sk_buff *br_ip4_multicast_alloc_query(struct net_bridge *br, skb_reset_mac_header(skb); eth = eth_hdr(skb); - memcpy(eth->h_source, br->dev->dev_addr, ETH_ALEN); + ether_addr_copy(eth->h_source, br->dev->dev_addr); eth->h_dest[0] = 1; eth->h_dest[1] = 0; eth->h_dest[2] = 0x5e; @@ -433,7 +433,7 @@ static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br, skb_reset_mac_header(skb); eth = eth_hdr(skb); - memcpy(eth->h_source, br->dev->dev_addr, ETH_ALEN); + ether_addr_copy(eth->h_source, br->dev->dev_addr); eth->h_proto = htons(ETH_P_IPV6); skb_put(skb, sizeof(*eth)); diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c index b008c59a92c4..80e1b0f60a30 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -167,7 +167,7 @@ void br_netfilter_rtable_init(struct net_bridge *br) rt->dst.dev = br->dev; rt->dst.path = &rt->dst; dst_init_metrics(&rt->dst, br_dst_default_metrics, true); - rt->dst.flags = DST_NOXFRM | DST_NOPEER | DST_FAKE_RTABLE; + rt->dst.flags = DST_NOXFRM | DST_FAKE_RTABLE; rt->dst.ops = &fake_dst_ops; } @@ -506,7 +506,7 @@ bridged_dnat: 1); return 0; } - memcpy(eth_hdr(skb)->h_dest, dev->dev_addr, ETH_ALEN); + ether_addr_copy(eth_hdr(skb)->h_dest, dev->dev_addr); skb->pkt_type = PACKET_HOST; } } else { diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index fcd12333c59b..e1ca1dc916a4 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -46,12 +46,12 @@ typedef __u16 port_id; struct bridge_id { unsigned char prio[2]; - unsigned char addr[6]; + unsigned char addr[ETH_ALEN]; }; struct mac_addr { - unsigned char addr[6]; + unsigned char addr[ETH_ALEN]; }; struct br_ip @@ -104,6 +104,7 @@ struct net_bridge_fdb_entry mac_addr addr; unsigned char is_local; unsigned char is_static; + unsigned char added_by_user; __u16 vlan_id; }; @@ -370,6 +371,9 @@ static inline void br_netpoll_disable(struct net_bridge_port *p) int br_fdb_init(void); void br_fdb_fini(void); void br_fdb_flush(struct net_bridge *br); +void br_fdb_find_delete_local(struct net_bridge *br, + const struct net_bridge_port *p, + const unsigned char *addr, u16 vid); void br_fdb_changeaddr(struct net_bridge_port *p, const unsigned char *newaddr); void br_fdb_change_mac_address(struct net_bridge *br, const u8 *newaddr); void br_fdb_cleanup(unsigned long arg); @@ -383,8 +387,7 @@ int br_fdb_fillbuf(struct net_bridge *br, void *buf, unsigned long count, int br_fdb_insert(struct net_bridge *br, struct net_bridge_port *source, const unsigned char *addr, u16 vid); void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source, - const unsigned char *addr, u16 vid); -int fdb_delete_by_addr(struct net_bridge *br, const u8 *addr, u16 vid); + const unsigned char *addr, u16 vid, bool added_by_user); int br_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr); @@ -584,6 +587,7 @@ struct sk_buff *br_handle_vlan(struct net_bridge *br, int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags); int br_vlan_delete(struct net_bridge *br, u16 vid); void br_vlan_flush(struct net_bridge *br); +bool br_vlan_find(struct net_bridge *br, u16 vid); int br_vlan_filter_toggle(struct net_bridge *br, unsigned long val); int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags); int nbp_vlan_delete(struct net_bridge_port *port, u16 vid); @@ -665,6 +669,11 @@ static inline void br_vlan_flush(struct net_bridge *br) { } +static inline bool br_vlan_find(struct net_bridge *br, u16 vid) +{ + return false; +} + static inline int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags) { return -EOPNOTSUPP; diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c index 656a6f3e40de..189ba1e7d851 100644 --- a/net/bridge/br_stp_if.c +++ b/net/bridge/br_stp_if.c @@ -194,6 +194,8 @@ void br_stp_change_bridge_id(struct net_bridge *br, const unsigned char *addr) wasroot = br_is_root_bridge(br); + br_fdb_change_mac_address(br, addr); + memcpy(oldaddr, br->bridge_id.addr, ETH_ALEN); memcpy(br->bridge_id.addr, addr, ETH_ALEN); memcpy(br->dev->dev_addr, addr, ETH_ALEN); diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index 4ca4d0a0151c..8249ca764c79 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -275,9 +275,7 @@ int br_vlan_delete(struct net_bridge *br, u16 vid) if (!pv) return -EINVAL; - spin_lock_bh(&br->hash_lock); - fdb_delete_by_addr(br, br->dev->dev_addr, vid); - spin_unlock_bh(&br->hash_lock); + br_fdb_find_delete_local(br, NULL, br->dev->dev_addr, vid); __vlan_del(pv, vid); return 0; @@ -295,6 +293,25 @@ void br_vlan_flush(struct net_bridge *br) __vlan_flush(pv); } +bool br_vlan_find(struct net_bridge *br, u16 vid) +{ + struct net_port_vlans *pv; + bool found = false; + + rcu_read_lock(); + pv = rcu_dereference(br->vlan_info); + + if (!pv) + goto out; + + if (test_bit(vid, pv->vlan_bitmap)) + found = true; + +out: + rcu_read_unlock(); + return found; +} + int br_vlan_filter_toggle(struct net_bridge *br, unsigned long val) { if (!rtnl_trylock()) @@ -359,9 +376,7 @@ int nbp_vlan_delete(struct net_bridge_port *port, u16 vid) if (!pv) return -EINVAL; - spin_lock_bh(&port->br->hash_lock); - fdb_delete_by_addr(port->br, port->dev->dev_addr, vid); - spin_unlock_bh(&port->br->hash_lock); + br_fdb_find_delete_local(port->br, port, port->dev->dev_addr, vid); return __vlan_del(pv, vid); } diff --git a/net/bridge/netfilter/ebt_among.c b/net/bridge/netfilter/ebt_among.c index 3fb3c848affe..9024283d2bca 100644 --- a/net/bridge/netfilter/ebt_among.c +++ b/net/bridge/netfilter/ebt_among.c @@ -28,7 +28,7 @@ static bool ebt_mac_wormhash_contains(const struct ebt_mac_wormhash *wh, uint32_t cmp[2] = { 0, 0 }; int key = ((const unsigned char *)mac)[5]; - memcpy(((char *) cmp) + 2, mac, ETH_ALEN); + ether_addr_copy(((char *) cmp) + 2, mac); start = wh->table[key]; limit = wh->table[key + 1]; if (ip) { diff --git a/net/bridge/netfilter/ebt_dnat.c b/net/bridge/netfilter/ebt_dnat.c index c59f7bfae6e2..4e0b0c359325 100644 --- a/net/bridge/netfilter/ebt_dnat.c +++ b/net/bridge/netfilter/ebt_dnat.c @@ -22,7 +22,7 @@ ebt_dnat_tg(struct sk_buff *skb, const struct xt_action_param *par) if (!skb_make_writable(skb, 0)) return EBT_DROP; - memcpy(eth_hdr(skb)->h_dest, info->mac, ETH_ALEN); + ether_addr_copy(eth_hdr(skb)->h_dest, info->mac); return info->target; } diff --git a/net/bridge/netfilter/ebt_redirect.c b/net/bridge/netfilter/ebt_redirect.c index 46624bb6d9be..203964997a51 100644 --- a/net/bridge/netfilter/ebt_redirect.c +++ b/net/bridge/netfilter/ebt_redirect.c @@ -25,10 +25,10 @@ ebt_redirect_tg(struct sk_buff *skb, const struct xt_action_param *par) if (par->hooknum != NF_BR_BROUTING) /* rcu_read_lock()ed by nf_hook_slow */ - memcpy(eth_hdr(skb)->h_dest, - br_port_get_rcu(par->in)->br->dev->dev_addr, ETH_ALEN); + ether_addr_copy(eth_hdr(skb)->h_dest, + br_port_get_rcu(par->in)->br->dev->dev_addr); else - memcpy(eth_hdr(skb)->h_dest, par->in->dev_addr, ETH_ALEN); + ether_addr_copy(eth_hdr(skb)->h_dest, par->in->dev_addr); skb->pkt_type = PACKET_HOST; return info->target; } diff --git a/net/bridge/netfilter/ebt_snat.c b/net/bridge/netfilter/ebt_snat.c index 0f6b118d6cb2..e56ccd060d26 100644 --- a/net/bridge/netfilter/ebt_snat.c +++ b/net/bridge/netfilter/ebt_snat.c @@ -24,7 +24,7 @@ ebt_snat_tg(struct sk_buff *skb, const struct xt_action_param *par) if (!skb_make_writable(skb, 0)) return EBT_DROP; - memcpy(eth_hdr(skb)->h_source, info->mac, ETH_ALEN); + ether_addr_copy(eth_hdr(skb)->h_source, info->mac); if (!(info->target & NAT_ARP_BIT) && eth_hdr(skb)->h_proto == htons(ETH_P_ARP)) { const struct arphdr *ap; diff --git a/net/caif/caif_dev.c b/net/caif/caif_dev.c index 4dca159435cf..edbca468fa73 100644 --- a/net/caif/caif_dev.c +++ b/net/caif/caif_dev.c @@ -22,6 +22,7 @@ #include <net/pkt_sched.h> #include <net/caif/caif_device.h> #include <net/caif/caif_layer.h> +#include <net/caif/caif_dev.h> #include <net/caif/cfpkt.h> #include <net/caif/cfcnfg.h> #include <net/caif/cfserl.h> diff --git a/net/caif/cfsrvl.c b/net/caif/cfsrvl.c index 353f793d1b3b..a6e115463052 100644 --- a/net/caif/cfsrvl.c +++ b/net/caif/cfsrvl.c @@ -15,6 +15,7 @@ #include <net/caif/caif_layer.h> #include <net/caif/cfsrvl.h> #include <net/caif/cfpkt.h> +#include <net/caif/caif_dev.h> #define SRVL_CTRL_PKT_SIZE 1 #define SRVL_FLOW_OFF 0x81 diff --git a/net/can/af_can.c b/net/can/af_can.c index d249874a366d..a27f8aad9e99 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -57,6 +57,7 @@ #include <linux/skbuff.h> #include <linux/can.h> #include <linux/can/core.h> +#include <linux/can/skb.h> #include <linux/ratelimit.h> #include <net/net_namespace.h> #include <net/sock.h> @@ -290,7 +291,7 @@ int can_send(struct sk_buff *skb, int loop) return -ENOMEM; } - newskb->sk = skb->sk; + can_skb_set_owner(newskb, skb->sk); newskb->ip_summed = CHECKSUM_UNNECESSARY; newskb->pkt_type = PACKET_BROADCAST; } diff --git a/net/can/bcm.c b/net/can/bcm.c index 3fc737b214c7..dcb75c0e66c1 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -268,7 +268,7 @@ static void bcm_can_tx(struct bcm_op *op) /* send with loopback */ skb->dev = dev; - skb->sk = op->sk; + can_skb_set_owner(skb, op->sk); can_send(skb, 1); /* update statistics */ @@ -1223,7 +1223,7 @@ static int bcm_tx_send(struct msghdr *msg, int ifindex, struct sock *sk) can_skb_prv(skb)->ifindex = dev->ifindex; skb->dev = dev; - skb->sk = sk; + can_skb_set_owner(skb, sk); err = can_send(skb, 1); /* send with loopback */ dev_put(dev); diff --git a/net/can/raw.c b/net/can/raw.c index 07d72d852324..081e81fd017f 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -121,13 +121,9 @@ static void raw_rcv(struct sk_buff *oskb, void *data) if (!ro->recv_own_msgs && oskb->sk == sk) return; - /* do not pass frames with DLC > 8 to a legacy socket */ - if (!ro->fd_frames) { - struct canfd_frame *cfd = (struct canfd_frame *)oskb->data; - - if (unlikely(cfd->len > CAN_MAX_DLEN)) - return; - } + /* do not pass non-CAN2.0 frames to a legacy socket */ + if (!ro->fd_frames && oskb->len != CAN_MTU) + return; /* clone the given skb to be able to enqueue it into the rcv queue */ skb = skb_clone(oskb, GFP_ATOMIC); @@ -715,6 +711,7 @@ static int raw_sendmsg(struct kiocb *iocb, struct socket *sock, skb->dev = dev; skb->sk = sk; + skb->priority = sk->sk_priority; err = can_send(skb, ro->loopback); @@ -737,9 +734,7 @@ static int raw_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t size, int flags) { struct sock *sk = sock->sk; - struct raw_sock *ro = raw_sk(sk); struct sk_buff *skb; - int rxmtu; int err = 0; int noblock; @@ -750,20 +745,10 @@ static int raw_recvmsg(struct kiocb *iocb, struct socket *sock, if (!skb) return err; - /* - * when serving a legacy socket the DLC <= 8 is already checked inside - * raw_rcv(). Now check if we need to pass a canfd_frame to a legacy - * socket and cut the possible CANFD_MTU/CAN_MTU length to CAN_MTU - */ - if (!ro->fd_frames) - rxmtu = CAN_MTU; - else - rxmtu = skb->len; - - if (size < rxmtu) + if (size < skb->len) msg->msg_flags |= MSG_TRUNC; else - size = rxmtu; + size = skb->len; err = memcpy_toiovec(msg->msg_iov, skb->data, size); if (err < 0) { diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 0676f2b199d6..82750f915865 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -2082,7 +2082,6 @@ bad: pr_err("osdc handle_map corrupt msg\n"); ceph_msg_dump(msg); up_write(&osdc->map_sem); - return; } /* @@ -2281,7 +2280,6 @@ done_err: bad: pr_err("osdc handle_watch_notify corrupt msg\n"); - return; } /* diff --git a/net/core/dev.c b/net/core/dev.c index 3721db716350..587f9fb85d73 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2420,7 +2420,7 @@ EXPORT_SYMBOL(netdev_rx_csum_fault); * 2. No high memory really exists on this machine. */ -static int illegal_highdma(struct net_device *dev, struct sk_buff *skb) +static int illegal_highdma(const struct net_device *dev, struct sk_buff *skb) { #ifdef CONFIG_HIGHMEM int i; @@ -2495,34 +2495,36 @@ static int dev_gso_segment(struct sk_buff *skb, netdev_features_t features) } static netdev_features_t harmonize_features(struct sk_buff *skb, - netdev_features_t features) + const struct net_device *dev, + netdev_features_t features) { if (skb->ip_summed != CHECKSUM_NONE && !can_checksum_protocol(features, skb_network_protocol(skb))) { features &= ~NETIF_F_ALL_CSUM; - } else if (illegal_highdma(skb->dev, skb)) { + } else if (illegal_highdma(dev, skb)) { features &= ~NETIF_F_SG; } return features; } -netdev_features_t netif_skb_features(struct sk_buff *skb) +netdev_features_t netif_skb_dev_features(struct sk_buff *skb, + const struct net_device *dev) { __be16 protocol = skb->protocol; - netdev_features_t features = skb->dev->features; + netdev_features_t features = dev->features; - if (skb_shinfo(skb)->gso_segs > skb->dev->gso_max_segs) + if (skb_shinfo(skb)->gso_segs > dev->gso_max_segs) features &= ~NETIF_F_GSO_MASK; if (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 if (!vlan_tx_tag_present(skb)) { - return harmonize_features(skb, features); + return harmonize_features(skb, dev, features); } - features &= (skb->dev->vlan_features | NETIF_F_HW_VLAN_CTAG_TX | + 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)) @@ -2530,9 +2532,9 @@ netdev_features_t netif_skb_features(struct sk_buff *skb) NETIF_F_GEN_CSUM | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX; - return harmonize_features(skb, features); + return harmonize_features(skb, dev, features); } -EXPORT_SYMBOL(netif_skb_features); +EXPORT_SYMBOL(netif_skb_dev_features); int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq) @@ -2803,7 +2805,7 @@ EXPORT_SYMBOL(dev_loopback_xmit); * the BH enable code must have IRQs enabled so that it will not deadlock. * --BLG */ -int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv) +static int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv) { struct net_device *dev = skb->dev; struct netdev_queue *txq; @@ -3493,11 +3495,11 @@ EXPORT_SYMBOL_GPL(netdev_rx_handler_unregister); static bool skb_pfmemalloc_protocol(struct sk_buff *skb) { switch (skb->protocol) { - case __constant_htons(ETH_P_ARP): - case __constant_htons(ETH_P_IP): - case __constant_htons(ETH_P_IPV6): - case __constant_htons(ETH_P_8021Q): - case __constant_htons(ETH_P_8021AD): + case htons(ETH_P_ARP): + case htons(ETH_P_IP): + case htons(ETH_P_IPV6): + case htons(ETH_P_8021Q): + case htons(ETH_P_8021AD): return true; default: return false; @@ -4637,7 +4639,7 @@ struct net_device *netdev_master_upper_dev_get_rcu(struct net_device *dev) } EXPORT_SYMBOL(netdev_master_upper_dev_get_rcu); -int netdev_adjacent_sysfs_add(struct net_device *dev, +static int netdev_adjacent_sysfs_add(struct net_device *dev, struct net_device *adj_dev, struct list_head *dev_list) { @@ -4647,7 +4649,7 @@ int netdev_adjacent_sysfs_add(struct net_device *dev, return sysfs_create_link(&(dev->dev.kobj), &(adj_dev->dev.kobj), linkname); } -void netdev_adjacent_sysfs_del(struct net_device *dev, +static void netdev_adjacent_sysfs_del(struct net_device *dev, char *name, struct list_head *dev_list) { diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index f409e0bd35c0..185c341fafbd 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -745,6 +745,13 @@ static int fib_rules_event(struct notifier_block *this, unsigned long event, attach_rules(&ops->rules_list, dev); break; + case NETDEV_CHANGENAME: + list_for_each_entry(ops, &net->rules_ops, list) { + detach_rules(&ops->rules_list, dev); + attach_rules(&ops->rules_list, dev); + } + break; + case NETDEV_UNREGISTER: list_for_each_entry(ops, &net->rules_ops, list) detach_rules(&ops->rules_list, dev); diff --git a/net/core/flow.c b/net/core/flow.c index dfa602ceb8cd..31cfb365e0c6 100644 --- a/net/core/flow.c +++ b/net/core/flow.c @@ -24,6 +24,7 @@ #include <net/flow.h> #include <linux/atomic.h> #include <linux/security.h> +#include <net/net_namespace.h> struct flow_cache_entry { union { @@ -38,37 +39,14 @@ struct flow_cache_entry { struct flow_cache_object *object; }; -struct flow_cache_percpu { - struct hlist_head *hash_table; - int hash_count; - u32 hash_rnd; - int hash_rnd_recalc; - struct tasklet_struct flush_tasklet; -}; - struct flow_flush_info { struct flow_cache *cache; atomic_t cpuleft; struct completion completion; }; -struct flow_cache { - u32 hash_shift; - struct flow_cache_percpu __percpu *percpu; - struct notifier_block hotcpu_notifier; - int low_watermark; - int high_watermark; - struct timer_list rnd_timer; -}; - -atomic_t flow_cache_genid = ATOMIC_INIT(0); -EXPORT_SYMBOL(flow_cache_genid); -static struct flow_cache flow_cache_global; static struct kmem_cache *flow_cachep __read_mostly; -static DEFINE_SPINLOCK(flow_cache_gc_lock); -static LIST_HEAD(flow_cache_gc_list); - #define flow_cache_hash_size(cache) (1 << (cache)->hash_shift) #define FLOW_HASH_RND_PERIOD (10 * 60 * HZ) @@ -84,16 +62,18 @@ static void flow_cache_new_hashrnd(unsigned long arg) add_timer(&fc->rnd_timer); } -static int flow_entry_valid(struct flow_cache_entry *fle) +static int flow_entry_valid(struct flow_cache_entry *fle, + struct netns_xfrm *xfrm) { - if (atomic_read(&flow_cache_genid) != fle->genid) + if (atomic_read(&xfrm->flow_cache_genid) != fle->genid) return 0; if (fle->object && !fle->object->ops->check(fle->object)) return 0; return 1; } -static void flow_entry_kill(struct flow_cache_entry *fle) +static void flow_entry_kill(struct flow_cache_entry *fle, + struct netns_xfrm *xfrm) { if (fle->object) fle->object->ops->delete(fle->object); @@ -104,26 +84,28 @@ static void flow_cache_gc_task(struct work_struct *work) { struct list_head gc_list; struct flow_cache_entry *fce, *n; + struct netns_xfrm *xfrm = container_of(work, struct netns_xfrm, + flow_cache_gc_work); INIT_LIST_HEAD(&gc_list); - spin_lock_bh(&flow_cache_gc_lock); - list_splice_tail_init(&flow_cache_gc_list, &gc_list); - spin_unlock_bh(&flow_cache_gc_lock); + spin_lock_bh(&xfrm->flow_cache_gc_lock); + list_splice_tail_init(&xfrm->flow_cache_gc_list, &gc_list); + spin_unlock_bh(&xfrm->flow_cache_gc_lock); list_for_each_entry_safe(fce, n, &gc_list, u.gc_list) - flow_entry_kill(fce); + flow_entry_kill(fce, xfrm); } -static DECLARE_WORK(flow_cache_gc_work, flow_cache_gc_task); static void flow_cache_queue_garbage(struct flow_cache_percpu *fcp, - int deleted, struct list_head *gc_list) + int deleted, struct list_head *gc_list, + struct netns_xfrm *xfrm) { if (deleted) { fcp->hash_count -= deleted; - spin_lock_bh(&flow_cache_gc_lock); - list_splice_tail(gc_list, &flow_cache_gc_list); - spin_unlock_bh(&flow_cache_gc_lock); - schedule_work(&flow_cache_gc_work); + spin_lock_bh(&xfrm->flow_cache_gc_lock); + list_splice_tail(gc_list, &xfrm->flow_cache_gc_list); + spin_unlock_bh(&xfrm->flow_cache_gc_lock); + schedule_work(&xfrm->flow_cache_gc_work); } } @@ -135,6 +117,8 @@ static void __flow_cache_shrink(struct flow_cache *fc, struct hlist_node *tmp; LIST_HEAD(gc_list); int i, deleted = 0; + struct netns_xfrm *xfrm = container_of(fc, struct netns_xfrm, + flow_cache_global); for (i = 0; i < flow_cache_hash_size(fc); i++) { int saved = 0; @@ -142,7 +126,7 @@ static void __flow_cache_shrink(struct flow_cache *fc, hlist_for_each_entry_safe(fle, tmp, &fcp->hash_table[i], u.hlist) { if (saved < shrink_to && - flow_entry_valid(fle)) { + flow_entry_valid(fle, xfrm)) { saved++; } else { deleted++; @@ -152,7 +136,7 @@ static void __flow_cache_shrink(struct flow_cache *fc, } } - flow_cache_queue_garbage(fcp, deleted, &gc_list); + flow_cache_queue_garbage(fcp, deleted, &gc_list, xfrm); } static void flow_cache_shrink(struct flow_cache *fc, @@ -208,7 +192,7 @@ struct flow_cache_object * flow_cache_lookup(struct net *net, const struct flowi *key, u16 family, u8 dir, flow_resolve_t resolver, void *ctx) { - struct flow_cache *fc = &flow_cache_global; + struct flow_cache *fc = &net->xfrm.flow_cache_global; struct flow_cache_percpu *fcp; struct flow_cache_entry *fle, *tfle; struct flow_cache_object *flo; @@ -258,7 +242,7 @@ flow_cache_lookup(struct net *net, const struct flowi *key, u16 family, u8 dir, hlist_add_head(&fle->u.hlist, &fcp->hash_table[hash]); fcp->hash_count++; } - } else if (likely(fle->genid == atomic_read(&flow_cache_genid))) { + } else if (likely(fle->genid == atomic_read(&net->xfrm.flow_cache_genid))) { flo = fle->object; if (!flo) goto ret_object; @@ -279,7 +263,7 @@ nocache: } flo = resolver(net, key, family, dir, flo, ctx); if (fle) { - fle->genid = atomic_read(&flow_cache_genid); + fle->genid = atomic_read(&net->xfrm.flow_cache_genid); if (!IS_ERR(flo)) fle->object = flo; else @@ -303,12 +287,14 @@ static void flow_cache_flush_tasklet(unsigned long data) struct hlist_node *tmp; LIST_HEAD(gc_list); int i, deleted = 0; + struct netns_xfrm *xfrm = container_of(fc, struct netns_xfrm, + flow_cache_global); fcp = this_cpu_ptr(fc->percpu); for (i = 0; i < flow_cache_hash_size(fc); i++) { hlist_for_each_entry_safe(fle, tmp, &fcp->hash_table[i], u.hlist) { - if (flow_entry_valid(fle)) + if (flow_entry_valid(fle, xfrm)) continue; deleted++; @@ -317,7 +303,7 @@ static void flow_cache_flush_tasklet(unsigned long data) } } - flow_cache_queue_garbage(fcp, deleted, &gc_list); + flow_cache_queue_garbage(fcp, deleted, &gc_list, xfrm); if (atomic_dec_and_test(&info->cpuleft)) complete(&info->completion); @@ -351,10 +337,9 @@ static void flow_cache_flush_per_cpu(void *data) tasklet_schedule(tasklet); } -void flow_cache_flush(void) +void flow_cache_flush(struct net *net) { struct flow_flush_info info; - static DEFINE_MUTEX(flow_flush_sem); cpumask_var_t mask; int i, self; @@ -365,8 +350,8 @@ void flow_cache_flush(void) /* Don't want cpus going down or up during this. */ get_online_cpus(); - mutex_lock(&flow_flush_sem); - info.cache = &flow_cache_global; + mutex_lock(&net->xfrm.flow_flush_sem); + info.cache = &net->xfrm.flow_cache_global; for_each_online_cpu(i) if (!flow_cache_percpu_empty(info.cache, i)) cpumask_set_cpu(i, mask); @@ -386,21 +371,23 @@ void flow_cache_flush(void) wait_for_completion(&info.completion); done: - mutex_unlock(&flow_flush_sem); + mutex_unlock(&net->xfrm.flow_flush_sem); put_online_cpus(); free_cpumask_var(mask); } static void flow_cache_flush_task(struct work_struct *work) { - flow_cache_flush(); -} + struct netns_xfrm *xfrm = container_of(work, struct netns_xfrm, + flow_cache_gc_work); + struct net *net = container_of(xfrm, struct net, xfrm); -static DECLARE_WORK(flow_cache_flush_work, flow_cache_flush_task); + flow_cache_flush(net); +} -void flow_cache_flush_deferred(void) +void flow_cache_flush_deferred(struct net *net) { - schedule_work(&flow_cache_flush_work); + schedule_work(&net->xfrm.flow_cache_flush_work); } static int flow_cache_cpu_prepare(struct flow_cache *fc, int cpu) @@ -425,7 +412,8 @@ static int flow_cache_cpu(struct notifier_block *nfb, unsigned long action, void *hcpu) { - struct flow_cache *fc = container_of(nfb, struct flow_cache, hotcpu_notifier); + struct flow_cache *fc = container_of(nfb, struct flow_cache, + hotcpu_notifier); int res, cpu = (unsigned long) hcpu; struct flow_cache_percpu *fcp = per_cpu_ptr(fc->percpu, cpu); @@ -444,9 +432,20 @@ static int flow_cache_cpu(struct notifier_block *nfb, return NOTIFY_OK; } -static int __init flow_cache_init(struct flow_cache *fc) +int flow_cache_init(struct net *net) { int i; + struct flow_cache *fc = &net->xfrm.flow_cache_global; + + if (!flow_cachep) + flow_cachep = kmem_cache_create("flow_cache", + sizeof(struct flow_cache_entry), + 0, SLAB_PANIC, NULL); + spin_lock_init(&net->xfrm.flow_cache_gc_lock); + INIT_LIST_HEAD(&net->xfrm.flow_cache_gc_list); + INIT_WORK(&net->xfrm.flow_cache_gc_work, flow_cache_gc_task); + INIT_WORK(&net->xfrm.flow_cache_flush_work, flow_cache_flush_task); + mutex_init(&net->xfrm.flow_flush_sem); fc->hash_shift = 10; fc->low_watermark = 2 * flow_cache_hash_size(fc); @@ -484,14 +483,23 @@ err: return -ENOMEM; } +EXPORT_SYMBOL(flow_cache_init); -static int __init flow_cache_init_global(void) +void flow_cache_fini(struct net *net) { - flow_cachep = kmem_cache_create("flow_cache", - sizeof(struct flow_cache_entry), - 0, SLAB_PANIC, NULL); + int i; + struct flow_cache *fc = &net->xfrm.flow_cache_global; - return flow_cache_init(&flow_cache_global); -} + del_timer_sync(&fc->rnd_timer); + unregister_hotcpu_notifier(&fc->hotcpu_notifier); -module_init(flow_cache_init_global); + for_each_possible_cpu(i) { + struct flow_cache_percpu *fcp = per_cpu_ptr(fc->percpu, i); + kfree(fcp->hash_table); + fcp->hash_table = NULL; + } + + free_percpu(fc->percpu); + fc->percpu = NULL; +} +EXPORT_SYMBOL(flow_cache_fini); diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 87577d447554..80201bf69d59 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -61,7 +61,7 @@ bool skb_flow_dissect(const struct sk_buff *skb, struct flow_keys *flow) again: switch (proto) { - case __constant_htons(ETH_P_IP): { + case htons(ETH_P_IP): { const struct iphdr *iph; struct iphdr _iph; ip: @@ -77,7 +77,7 @@ ip: iph_to_flow_copy_addrs(flow, iph); break; } - case __constant_htons(ETH_P_IPV6): { + case htons(ETH_P_IPV6): { const struct ipv6hdr *iph; struct ipv6hdr _iph; ipv6: @@ -91,8 +91,8 @@ ipv6: nhoff += sizeof(struct ipv6hdr); break; } - case __constant_htons(ETH_P_8021AD): - case __constant_htons(ETH_P_8021Q): { + case htons(ETH_P_8021AD): + case htons(ETH_P_8021Q): { const struct vlan_hdr *vlan; struct vlan_hdr _vlan; @@ -104,7 +104,7 @@ ipv6: nhoff += sizeof(*vlan); goto again; } - case __constant_htons(ETH_P_PPP_SES): { + case htons(ETH_P_PPP_SES): { struct { struct pppoe_hdr hdr; __be16 proto; @@ -115,9 +115,9 @@ ipv6: proto = hdr->proto; nhoff += PPPOE_SES_HLEN; switch (proto) { - case __constant_htons(PPP_IP): + case htons(PPP_IP): goto ip; - case __constant_htons(PPP_IPV6): + case htons(PPP_IPV6): goto ipv6; default: return false; @@ -323,17 +323,6 @@ u32 __skb_get_poff(const struct sk_buff *skb) return poff; } -static inline u16 dev_cap_txqueue(struct net_device *dev, u16 queue_index) -{ - if (unlikely(queue_index >= dev->real_num_tx_queues)) { - net_warn_ratelimited("%s selects TX queue %d, but real number of TX queues is %d\n", - dev->name, queue_index, - dev->real_num_tx_queues); - return 0; - } - return queue_index; -} - static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb) { #ifdef CONFIG_XPS @@ -372,7 +361,7 @@ static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb) #endif } -u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb) +static u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb) { struct sock *sk = skb->sk; int queue_index = sk_tx_queue_get(sk); @@ -392,7 +381,6 @@ u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb) return queue_index; } -EXPORT_SYMBOL(__netdev_pick_tx); struct netdev_queue *netdev_pick_tx(struct net_device *dev, struct sk_buff *skb, @@ -403,13 +391,13 @@ struct netdev_queue *netdev_pick_tx(struct net_device *dev, if (dev->real_num_tx_queues != 1) { const struct net_device_ops *ops = dev->netdev_ops; if (ops->ndo_select_queue) - queue_index = ops->ndo_select_queue(dev, skb, - accel_priv); + queue_index = ops->ndo_select_queue(dev, skb, accel_priv, + __netdev_pick_tx); else queue_index = __netdev_pick_tx(dev, skb); if (!accel_priv) - queue_index = dev_cap_txqueue(dev, queue_index); + queue_index = netdev_cap_txqueue(dev, queue_index); } skb_set_queue_mapping(skb, queue_index); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index b9e9e0d38672..8f8a96ef9f3f 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -766,9 +766,6 @@ static void neigh_periodic_work(struct work_struct *work) nht = rcu_dereference_protected(tbl->nht, lockdep_is_held(&tbl->lock)); - if (atomic_read(&tbl->entries) < tbl->gc_thresh1) - goto out; - /* * periodically recompute ReachableTime from random function */ @@ -781,6 +778,9 @@ static void neigh_periodic_work(struct work_struct *work) neigh_rand_reach_time(NEIGH_VAR(p, BASE_REACHABLE_TIME)); } + if (atomic_read(&tbl->entries) < tbl->gc_thresh1) + goto out; + for (i = 0 ; i < (1 << nht->hash_shift); i++) { np = &nht->hash_buckets[i]; @@ -836,10 +836,10 @@ out: static __inline__ int neigh_max_probes(struct neighbour *n) { struct neigh_parms *p = n->parms; - return (n->nud_state & NUD_PROBE) ? - NEIGH_VAR(p, UCAST_PROBES) : - NEIGH_VAR(p, UCAST_PROBES) + NEIGH_VAR(p, APP_PROBES) + - NEIGH_VAR(p, MCAST_PROBES); + 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; } static void neigh_invalidate(struct neighbour *neigh) @@ -945,6 +945,7 @@ static void neigh_timer_handler(unsigned long arg) neigh->nud_state = NUD_FAILED; notify = 1; neigh_invalidate(neigh); + goto out; } if (neigh->nud_state & NUD_IN_TIMER) { @@ -3046,7 +3047,7 @@ int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p, if (!t) goto err; - for (i = 0; i < ARRAY_SIZE(t->neigh_vars); i++) { + for (i = 0; i < NEIGH_VAR_GC_INTERVAL; i++) { t->neigh_vars[i].data += (long) p; t->neigh_vars[i].extra1 = dev; t->neigh_vars[i].extra2 = p; diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 93886246a0b4..daed9a64c6f6 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -104,6 +104,7 @@ static ssize_t netdev_store(struct device *dev, struct device_attribute *attr, } NETDEVICE_SHOW_RO(dev_id, fmt_hex); +NETDEVICE_SHOW_RO(dev_port, fmt_dec); NETDEVICE_SHOW_RO(addr_assign_type, fmt_dec); NETDEVICE_SHOW_RO(addr_len, fmt_dec); NETDEVICE_SHOW_RO(iflink, fmt_dec); @@ -373,6 +374,7 @@ static struct attribute *net_class_attrs[] = { &dev_attr_netdev_group.attr, &dev_attr_type.attr, &dev_attr_dev_id.attr, + &dev_attr_dev_port.attr, &dev_attr_iflink.attr, &dev_attr_ifindex.attr, &dev_attr_addr_assign_type.attr, @@ -996,15 +998,12 @@ static struct attribute_group dql_group = { #endif /* CONFIG_BQL */ #ifdef CONFIG_XPS -static inline unsigned int get_netdev_queue_index(struct netdev_queue *queue) +static 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; + unsigned int i; + i = queue - dev->_tx; BUG_ON(i >= dev->num_tx_queues); return i; diff --git a/net/core/netpoll.c b/net/core/netpoll.c index c03f3dec4763..a664f7829a6d 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -948,6 +948,7 @@ int netpoll_parse_options(struct netpoll *np, char *opt) { char *cur=opt, *delim; int ipv6; + bool ipversion_set = false; if (*cur != '@') { if ((delim = strchr(cur, '@')) == NULL) @@ -960,6 +961,7 @@ int netpoll_parse_options(struct netpoll *np, char *opt) cur++; if (*cur != '/') { + ipversion_set = true; if ((delim = strchr(cur, '/')) == NULL) goto parse_failed; *delim = 0; @@ -1002,7 +1004,7 @@ int netpoll_parse_options(struct netpoll *np, char *opt) ipv6 = netpoll_parse_ip_addr(cur, &np->remote_ip); if (ipv6 < 0) goto parse_failed; - else if (np->ipv6 != (bool)ipv6) + else if (ipversion_set && np->ipv6 != (bool)ipv6) goto parse_failed; else np->ipv6 = (bool)ipv6; diff --git a/net/core/pktgen.c b/net/core/pktgen.c index fdac61cac1bd..d0dac57291af 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -476,23 +476,22 @@ static int pgctrl_show(struct seq_file *seq, void *v) static ssize_t pgctrl_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { - int err = 0; char data[128]; struct pktgen_net *pn = net_generic(current->nsproxy->net_ns, pg_net_id); - if (!capable(CAP_NET_ADMIN)) { - err = -EPERM; - goto out; - } + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + + if (count == 0) + return -EINVAL; if (count > sizeof(data)) count = sizeof(data); - if (copy_from_user(data, buf, count)) { - err = -EFAULT; - goto out; - } - data[count - 1] = 0; /* Make string */ + if (copy_from_user(data, buf, count)) + return -EFAULT; + + data[count - 1] = 0; /* Strip trailing '\n' and terminate string */ if (!strcmp(data, "stop")) pktgen_stop_all_threads_ifs(pn); @@ -506,10 +505,7 @@ static ssize_t pgctrl_write(struct file *file, const char __user *buf, else pr_warning("Unknown command: %s\n", data); - err = count; - -out: - return err; + return count; } static int pgctrl_open(struct inode *inode, struct file *file) @@ -1251,7 +1247,13 @@ static ssize_t pktgen_if_write(struct file *file, "Flag -:%s:- unknown\nAvailable flags, (prepend ! to un-set flag):\n%s", f, "IPSRC_RND, IPDST_RND, UDPSRC_RND, UDPDST_RND, " - "MACSRC_RND, MACDST_RND, TXSIZE_RND, IPV6, MPLS_RND, VID_RND, SVID_RND, FLOW_SEQ, IPSEC, NODE_ALLOC\n"); + "MACSRC_RND, MACDST_RND, TXSIZE_RND, IPV6, " + "MPLS_RND, VID_RND, SVID_RND, FLOW_SEQ, " + "QUEUE_MAP_RND, QUEUE_MAP_CPU, UDPCSUM, " +#ifdef CONFIG_XFRM + "IPSEC, " +#endif + "NODE_ALLOC\n"); return count; } sprintf(pg_result, "OK: flags=0x%x", pkt_dev->flags); diff --git a/net/core/request_sock.c b/net/core/request_sock.c index 4425148d2b51..467f326126e0 100644 --- a/net/core/request_sock.c +++ b/net/core/request_sock.c @@ -221,5 +221,4 @@ void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req, out: spin_unlock_bh(&fastopenq->lock); sock_put(lsk); - return; } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 393b1bc9a618..fc122fdb266a 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -374,7 +374,7 @@ static size_t rtnl_link_get_slave_info_data_size(const struct net_device *dev) if (!master_dev) return 0; ops = master_dev->rtnl_link_ops; - if (!ops->get_slave_size) + if (!ops || !ops->get_slave_size) return 0; /* IFLA_INFO_SLAVE_DATA + nested data */ return nla_total_size(sizeof(struct nlattr)) + @@ -1121,56 +1121,7 @@ nla_put_failure: return -EMSGSIZE; } -static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) -{ - struct net *net = sock_net(skb->sk); - int h, s_h; - int idx = 0, s_idx; - struct net_device *dev; - struct hlist_head *head; - struct nlattr *tb[IFLA_MAX+1]; - u32 ext_filter_mask = 0; - - s_h = cb->args[0]; - s_idx = cb->args[1]; - - rcu_read_lock(); - cb->seq = net->dev_base_seq; - - if (nlmsg_parse(cb->nlh, sizeof(struct ifinfomsg), tb, IFLA_MAX, - ifla_policy) >= 0) { - - if (tb[IFLA_EXT_MASK]) - ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]); - } - - for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { - idx = 0; - head = &net->dev_index_head[h]; - hlist_for_each_entry_rcu(dev, head, index_hlist) { - if (idx < s_idx) - goto cont; - if (rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, 0, - NLM_F_MULTI, - ext_filter_mask) <= 0) - goto out; - - nl_dump_check_consistent(cb, nlmsg_hdr(skb)); -cont: - idx++; - } - } -out: - rcu_read_unlock(); - cb->args[1] = idx; - cb->args[0] = h; - - return skb->len; -} - -const struct nla_policy ifla_policy[IFLA_MAX+1] = { +static const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_IFNAME] = { .type = NLA_STRING, .len = IFNAMSIZ-1 }, [IFLA_ADDRESS] = { .type = NLA_BINARY, .len = MAX_ADDR_LEN }, [IFLA_BROADCAST] = { .type = NLA_BINARY, .len = MAX_ADDR_LEN }, @@ -1197,7 +1148,6 @@ const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_NUM_RX_QUEUES] = { .type = NLA_U32 }, [IFLA_PHYS_PORT_ID] = { .type = NLA_BINARY, .len = MAX_PHYS_PORT_ID_LEN }, }; -EXPORT_SYMBOL(ifla_policy); static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = { [IFLA_INFO_KIND] = { .type = NLA_STRING }, @@ -1235,6 +1185,61 @@ static const struct nla_policy ifla_port_policy[IFLA_PORT_MAX+1] = { [IFLA_PORT_RESPONSE] = { .type = NLA_U16, }, }; +static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct net *net = sock_net(skb->sk); + int h, s_h; + int idx = 0, s_idx; + struct net_device *dev; + struct hlist_head *head; + struct nlattr *tb[IFLA_MAX+1]; + u32 ext_filter_mask = 0; + + s_h = cb->args[0]; + s_idx = cb->args[1]; + + rcu_read_lock(); + cb->seq = net->dev_base_seq; + + if (nlmsg_parse(cb->nlh, sizeof(struct ifinfomsg), tb, IFLA_MAX, + ifla_policy) >= 0) { + + if (tb[IFLA_EXT_MASK]) + ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]); + } + + for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { + idx = 0; + head = &net->dev_index_head[h]; + hlist_for_each_entry_rcu(dev, head, index_hlist) { + if (idx < s_idx) + goto cont; + if (rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, 0, + NLM_F_MULTI, + ext_filter_mask) <= 0) + goto out; + + nl_dump_check_consistent(cb, nlmsg_hdr(skb)); +cont: + idx++; + } + } +out: + rcu_read_unlock(); + cb->args[1] = idx; + cb->args[0] = h; + + return skb->len; +} + +int rtnl_nla_parse_ifla(struct nlattr **tb, const struct nlattr *head, int len) +{ + return nla_parse(tb, IFLA_MAX, head, len, ifla_policy); +} +EXPORT_SYMBOL(rtnl_nla_parse_ifla); + struct net *rtnl_link_get_net(struct net *src_net, struct nlattr *tb[]) { struct net *net; @@ -1963,16 +1968,21 @@ replay: dev->ifindex = ifm->ifi_index; - if (ops->newlink) + if (ops->newlink) { err = ops->newlink(net, dev, tb, data); - else + /* Drivers should call free_netdev() in ->destructor + * and unregister it on failure so that device could be + * finally freed in rtnl_unlock. + */ + if (err < 0) + goto out; + } else { err = register_netdevice(dev); - - if (err < 0) { - free_netdev(dev); - goto out; + if (err < 0) { + free_netdev(dev); + goto out; + } } - err = rtnl_configure_link(dev, ifm); if (err < 0) unregister_netdevice(dev); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 5976ef0846bd..465a01c97c76 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -707,9 +707,6 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old) new->mark = old->mark; new->skb_iif = old->skb_iif; __nf_copy(new, old); -#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) - new->nf_trace = old->nf_trace; -#endif #ifdef CONFIG_NET_SCHED new->tc_index = old->tc_index; #ifdef CONFIG_NET_CLS_ACT @@ -3281,6 +3278,32 @@ __skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len) return elt; } +/* As compared with skb_to_sgvec, skb_to_sgvec_nomark only map skb to given + * sglist without mark the sg which contain last skb data as the end. + * So the caller can mannipulate sg list as will when padding new data after + * the first call without calling sg_unmark_end to expend sg list. + * + * Scenario to use skb_to_sgvec_nomark: + * 1. sg_init_table + * 2. skb_to_sgvec_nomark(payload1) + * 3. skb_to_sgvec_nomark(payload2) + * + * This is equivalent to: + * 1. sg_init_table + * 2. skb_to_sgvec(payload1) + * 3. sg_unmark_end + * 4. skb_to_sgvec(payload2) + * + * When mapping mutilple payload conditionally, skb_to_sgvec_nomark + * is more preferable. + */ +int skb_to_sgvec_nomark(struct sk_buff *skb, struct scatterlist *sg, + int offset, int len) +{ + return __skb_to_sgvec(skb, sg, offset, len); +} +EXPORT_SYMBOL_GPL(skb_to_sgvec_nomark); + int skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len) { int nsg = __skb_to_sgvec(skb, sg, offset, len); diff --git a/net/core/sock.c b/net/core/sock.c index 0c127dcdf6a8..5b6a9431b017 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1775,7 +1775,9 @@ struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len, while (order) { if (npages >= 1 << order) { page = alloc_pages(sk->sk_allocation | - __GFP_COMP | __GFP_NOWARN, + __GFP_COMP | + __GFP_NOWARN | + __GFP_NORETRY, order); if (page) goto fill_page; @@ -1845,7 +1847,7 @@ bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t prio) gfp_t gfp = prio; if (order) - gfp |= __GFP_COMP | __GFP_NOWARN; + gfp |= __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY; pfrag->page = alloc_pages(gfp, order); if (likely(pfrag->page)) { pfrag->offset = 0; diff --git a/net/dccp/ccids/lib/tfrc.c b/net/dccp/ccids/lib/tfrc.c index c073b81a1f3e..62b5828acde0 100644 --- a/net/dccp/ccids/lib/tfrc.c +++ b/net/dccp/ccids/lib/tfrc.c @@ -8,7 +8,7 @@ #include "tfrc.h" #ifdef CONFIG_IP_DCCP_TFRC_DEBUG -static bool tfrc_debug; +bool tfrc_debug; module_param(tfrc_debug, bool, 0644); MODULE_PARM_DESC(tfrc_debug, "Enable TFRC debug messages"); #endif diff --git a/net/dccp/ccids/lib/tfrc.h b/net/dccp/ccids/lib/tfrc.h index a3d8f7c76ae0..40ee7d62b652 100644 --- a/net/dccp/ccids/lib/tfrc.h +++ b/net/dccp/ccids/lib/tfrc.h @@ -21,6 +21,7 @@ #include "packet_history.h" #ifdef CONFIG_IP_DCCP_TFRC_DEBUG +extern bool tfrc_debug; #define tfrc_pr_debug(format, a...) DCCP_PR_DEBUG(tfrc_debug, format, ##a) #else #define tfrc_pr_debug(format, a...) diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index 2954dcbca832..4c04848953bd 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -2104,8 +2104,6 @@ static struct notifier_block dn_dev_notifier = { .notifier_call = dn_device_event, }; -extern int dn_route_rcv(struct sk_buff *, struct net_device *, struct packet_type *, struct net_device *); - static struct packet_type dn_dix_packet_type __read_mostly = { .type = cpu_to_be16(ETH_P_DNA_RT), .func = dn_route_rcv, @@ -2353,9 +2351,6 @@ static const struct proto_ops dn_proto_ops = { .sendpage = sock_no_sendpage, }; -void dn_register_sysctl(void); -void dn_unregister_sysctl(void); - MODULE_DESCRIPTION("The Linux DECnet Network Protocol"); MODULE_AUTHOR("Linux DECnet Project Team"); MODULE_LICENSE("GPL"); diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c index cac505f166d5..e5302b7f7ca9 100644 --- a/net/hsr/hsr_device.c +++ b/net/hsr/hsr_device.c @@ -209,7 +209,7 @@ static int slave_xmit(struct sk_buff *skb, struct hsr_priv *hsr_priv, /* Address substitution (IEC62439-3 pp 26, 50): replace mac * address of outgoing frame with that of the outgoing slave's. */ - memcpy(hsr_ethhdr->ethhdr.h_source, skb->dev->dev_addr, ETH_ALEN); + ether_addr_copy(hsr_ethhdr->ethhdr.h_source, skb->dev->dev_addr); return dev_queue_xmit(skb); } @@ -346,7 +346,7 @@ static void send_hsr_supervision_frame(struct net_device *hsr_dev, u8 type) /* Payload: MacAddressA */ hsr_sp = (typeof(hsr_sp)) skb_put(skb, sizeof(*hsr_sp)); - memcpy(hsr_sp->MacAddressA, hsr_dev->dev_addr, ETH_ALEN); + ether_addr_copy(hsr_sp->MacAddressA, hsr_dev->dev_addr); dev_queue_xmit(skb); return; @@ -493,7 +493,7 @@ static int check_slave_ok(struct net_device *dev) /* Default multicast address for HSR Supervision frames */ -static const unsigned char def_multicast_addr[ETH_ALEN] = { +static const unsigned char def_multicast_addr[ETH_ALEN] __aligned(2) = { 0x01, 0x15, 0x4e, 0x00, 0x01, 0x00 }; @@ -519,7 +519,7 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], hsr_priv->announce_timer.function = hsr_announce; hsr_priv->announce_timer.data = (unsigned long) hsr_priv; - memcpy(hsr_priv->sup_multicast_addr, def_multicast_addr, ETH_ALEN); + ether_addr_copy(hsr_priv->sup_multicast_addr, def_multicast_addr); hsr_priv->sup_multicast_addr[ETH_ALEN - 1] = multicast_spec; /* FIXME: should I modify the value of these? @@ -547,7 +547,7 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], hsr_dev->features |= NETIF_F_VLAN_CHALLENGED; /* Set hsr_dev's MAC address to that of mac_slave1 */ - memcpy(hsr_dev->dev_addr, hsr_priv->slave[0]->dev_addr, ETH_ALEN); + ether_addr_copy(hsr_dev->dev_addr, hsr_priv->slave[0]->dev_addr); /* Set required header length */ for (i = 0; i < HSR_MAX_SLAVE; i++) { diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c index 327060c6c874..83e58449366a 100644 --- a/net/hsr/hsr_framereg.c +++ b/net/hsr/hsr_framereg.c @@ -108,8 +108,8 @@ int hsr_create_self_node(struct list_head *self_node_db, if (!node) return -ENOMEM; - memcpy(node->MacAddressA, addr_a, ETH_ALEN); - memcpy(node->MacAddressB, addr_b, ETH_ALEN); + ether_addr_copy(node->MacAddressA, addr_a); + ether_addr_copy(node->MacAddressB, addr_b); rcu_read_lock(); oldnode = list_first_or_null_rcu(self_node_db, @@ -199,7 +199,7 @@ struct node_entry *hsr_merge_node(struct hsr_priv *hsr_priv, /* Node is known, but frame was received from an unknown * address. Node is PICS_SUBS capable; merge its AddrB. */ - memcpy(node->MacAddressB, hsr_ethsup->ethhdr.h_source, ETH_ALEN); + ether_addr_copy(node->MacAddressB, hsr_ethsup->ethhdr.h_source); node->AddrB_if = dev_idx; return node; } @@ -208,8 +208,8 @@ struct node_entry *hsr_merge_node(struct hsr_priv *hsr_priv, if (!node) return NULL; - memcpy(node->MacAddressA, hsr_sp->MacAddressA, ETH_ALEN); - memcpy(node->MacAddressB, hsr_ethsup->ethhdr.h_source, ETH_ALEN); + ether_addr_copy(node->MacAddressA, hsr_sp->MacAddressA); + ether_addr_copy(node->MacAddressB, hsr_ethsup->ethhdr.h_source); if (!ether_addr_equal(hsr_sp->MacAddressA, hsr_ethsup->ethhdr.h_source)) node->AddrB_if = dev_idx; else @@ -250,7 +250,7 @@ void hsr_addr_subst_source(struct hsr_priv *hsr_priv, struct sk_buff *skb) rcu_read_lock(); node = find_node_by_AddrB(&hsr_priv->node_db, ethhdr->h_source); if (node) - memcpy(ethhdr->h_source, node->MacAddressA, ETH_ALEN); + ether_addr_copy(ethhdr->h_source, node->MacAddressA); rcu_read_unlock(); } @@ -272,7 +272,7 @@ void hsr_addr_subst_dest(struct hsr_priv *hsr_priv, struct ethhdr *ethhdr, rcu_read_lock(); node = find_node_by_AddrA(&hsr_priv->node_db, ethhdr->h_dest); if (node && (node->AddrB_if == dev_idx)) - memcpy(ethhdr->h_dest, node->MacAddressB, ETH_ALEN); + ether_addr_copy(ethhdr->h_dest, node->MacAddressB); rcu_read_unlock(); } @@ -297,7 +297,7 @@ static bool seq_nr_after(u16 a, u16 b) void hsr_register_frame_in(struct node_entry *node, enum hsr_dev_idx dev_idx) { - if ((dev_idx < 0) || (dev_idx >= HSR_MAX_DEV)) { + if ((dev_idx < 0) || (dev_idx >= HSR_MAX_SLAVE)) { WARN_ONCE(1, "%s: Invalid dev_idx (%d)\n", __func__, dev_idx); return; } @@ -428,13 +428,13 @@ void *hsr_get_next_node(struct hsr_priv *hsr_priv, void *_pos, node = list_first_or_null_rcu(&hsr_priv->node_db, struct node_entry, mac_list); if (node) - memcpy(addr, node->MacAddressA, ETH_ALEN); + ether_addr_copy(addr, node->MacAddressA); return node; } node = _pos; list_for_each_entry_continue_rcu(node, &hsr_priv->node_db, mac_list) { - memcpy(addr, node->MacAddressA, ETH_ALEN); + ether_addr_copy(addr, node->MacAddressA); return node; } @@ -462,7 +462,7 @@ int hsr_get_node_data(struct hsr_priv *hsr_priv, return -ENOENT; /* No such entry */ } - memcpy(addr_b, node->MacAddressB, ETH_ALEN); + ether_addr_copy(addr_b, node->MacAddressB); tdiff = jiffies - node->time_in[HSR_DEV_SLAVE_A]; if (node->time_in_stale[HSR_DEV_SLAVE_A]) diff --git a/net/hsr/hsr_main.c b/net/hsr/hsr_main.c index af68dd83a4e3..10010c543edf 100644 --- a/net/hsr/hsr_main.c +++ b/net/hsr/hsr_main.c @@ -138,8 +138,8 @@ static int hsr_netdev_notify(struct notifier_block *nb, unsigned long event, break; if (dev == hsr_priv->slave[0]) - memcpy(hsr_priv->dev->dev_addr, - hsr_priv->slave[0]->dev_addr, ETH_ALEN); + ether_addr_copy(hsr_priv->dev->dev_addr, + hsr_priv->slave[0]->dev_addr); /* Make sure we recognize frames from ourselves in hsr_rcv() */ res = hsr_create_self_node(&hsr_priv->self_node_db, diff --git a/net/ieee802154/6lowpan_iphc.c b/net/ieee802154/6lowpan_iphc.c index 860aa2d445ba..211b5686d719 100644 --- a/net/ieee802154/6lowpan_iphc.c +++ b/net/ieee802154/6lowpan_iphc.c @@ -54,11 +54,10 @@ #include <linux/if_arp.h> #include <linux/module.h> #include <linux/netdevice.h> +#include <net/6lowpan.h> #include <net/ipv6.h> #include <net/af_ieee802154.h> -#include "6lowpan.h" - /* * Uncompress address function for source and * destination address(non-multicast). diff --git a/net/ieee802154/6lowpan.c b/net/ieee802154/6lowpan_rtnl.c index 48b25c0af4d0..48a8f52b5991 100644 --- a/net/ieee802154/6lowpan.c +++ b/net/ieee802154/6lowpan_rtnl.c @@ -1,10 +1,8 @@ -/* - * Copyright 2011, Siemens AG +/* Copyright 2011, Siemens AG * written by Alexander Smirnov <alex.bluesman.smirnov@gmail.com> */ -/* - * Based on patches from Jon Smirl <jonsmirl@gmail.com> +/* Based on patches from Jon Smirl <jonsmirl@gmail.com> * Copyright (c) 2011 Jon Smirl <jonsmirl@gmail.com> * * This program is free software; you can redistribute it and/or modify @@ -15,10 +13,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. */ /* Jon's code is based on 6lowpan implementation for Contiki which is: @@ -58,9 +52,10 @@ #include <net/af_ieee802154.h> #include <net/ieee802154.h> #include <net/ieee802154_netdev.h> +#include <net/6lowpan.h> #include <net/ipv6.h> -#include "6lowpan.h" +#include "reassembly.h" static LIST_HEAD(lowpan_devices); @@ -68,7 +63,7 @@ static LIST_HEAD(lowpan_devices); struct lowpan_dev_info { struct net_device *real_dev; /* real WPAN device ptr */ struct mutex dev_list_mtx; /* mutex for list ops */ - unsigned short fragment_tag; + __be16 fragment_tag; }; struct lowpan_dev_record { @@ -76,18 +71,6 @@ struct lowpan_dev_record { struct list_head list; }; -struct lowpan_fragment { - struct sk_buff *skb; /* skb to be assembled */ - u16 length; /* length to be assemled */ - u32 bytes_rcv; /* bytes received */ - u16 tag; /* current fragment tag */ - struct timer_list timer; /* assembling timer */ - struct list_head list; /* fragments list */ -}; - -static LIST_HEAD(lowpan_fragments); -static DEFINE_SPINLOCK(flist_lock); - static inline struct lowpan_dev_info *lowpan_dev_info(const struct net_device *dev) { @@ -106,7 +89,6 @@ static int lowpan_header_create(struct sk_buff *skb, unsigned short type, const void *_daddr, const void *_saddr, unsigned int len) { - struct ipv6hdr *hdr; const u8 *saddr = _saddr; const u8 *daddr = _daddr; struct ieee802154_addr sa, da; @@ -117,8 +99,6 @@ static int lowpan_header_create(struct sk_buff *skb, if (type != ETH_P_IPV6) return 0; - hdr = ipv6_hdr(skb); - if (!saddr) saddr = dev->dev_addr; @@ -127,13 +107,11 @@ static int lowpan_header_create(struct sk_buff *skb, lowpan_header_compress(skb, dev, type, daddr, saddr, len); - /* - * NOTE1: I'm still unsure about the fact that compression and WPAN + /* NOTE1: I'm still unsure about the fact that compression and WPAN * header are created here and not later in the xmit. So wait for * an opinion of net maintainers. */ - /* - * NOTE2: to be absolutely correct, we must derive PANid information + /* NOTE2: to be absolutely correct, we must derive PANid information * from MAC subif of the 'dev' and 'real_dev' network devices, but * this isn't implemented in mainline yet, so currently we assign 0xff */ @@ -148,8 +126,7 @@ static int lowpan_header_create(struct sk_buff *skb, /* intra-PAN communications */ da.pan_id = ieee802154_mlme_ops(dev)->get_pan_id(dev); - /* - * if the destination address is the broadcast address, use the + /* if the destination address is the broadcast address, use the * corresponding short address */ if (lowpan_is_addr_broadcast(daddr)) { @@ -191,69 +168,6 @@ static int lowpan_give_skb_to_devices(struct sk_buff *skb, return stat; } -static void lowpan_fragment_timer_expired(unsigned long entry_addr) -{ - struct lowpan_fragment *entry = (struct lowpan_fragment *)entry_addr; - - pr_debug("timer expired for frame with tag %d\n", entry->tag); - - list_del(&entry->list); - dev_kfree_skb(entry->skb); - kfree(entry); -} - -static struct lowpan_fragment * -lowpan_alloc_new_frame(struct sk_buff *skb, u16 len, u16 tag) -{ - struct lowpan_fragment *frame; - - frame = kzalloc(sizeof(struct lowpan_fragment), - GFP_ATOMIC); - if (!frame) - goto frame_err; - - INIT_LIST_HEAD(&frame->list); - - frame->length = len; - frame->tag = tag; - - /* allocate buffer for frame assembling */ - frame->skb = netdev_alloc_skb_ip_align(skb->dev, frame->length + - sizeof(struct ipv6hdr)); - - if (!frame->skb) - goto skb_err; - - frame->skb->priority = skb->priority; - - /* reserve headroom for uncompressed ipv6 header */ - skb_reserve(frame->skb, sizeof(struct ipv6hdr)); - skb_put(frame->skb, frame->length); - - /* copy the first control block to keep a - * trace of the link-layer addresses in case - * of a link-local compressed address - */ - memcpy(frame->skb->cb, skb->cb, sizeof(skb->cb)); - - init_timer(&frame->timer); - /* time out is the same as for ipv6 - 60 sec */ - frame->timer.expires = jiffies + LOWPAN_FRAG_TIMEOUT; - frame->timer.data = (unsigned long)frame; - frame->timer.function = lowpan_fragment_timer_expired; - - add_timer(&frame->timer); - - list_add_tail(&frame->list, &lowpan_fragments); - - return frame; - -skb_err: - kfree(frame); -frame_err: - return NULL; -} - static int process_data(struct sk_buff *skb) { u8 iphc0, iphc1; @@ -267,94 +181,6 @@ static int process_data(struct sk_buff *skb) if (lowpan_fetch_skb_u8(skb, &iphc0)) goto drop; - /* fragments assembling */ - switch (iphc0 & LOWPAN_DISPATCH_MASK) { - case LOWPAN_DISPATCH_FRAG1: - case LOWPAN_DISPATCH_FRAGN: - { - struct lowpan_fragment *frame; - /* slen stores the rightmost 8 bits of the 11 bits length */ - u8 slen, offset = 0; - u16 len, tag; - bool found = false; - - if (lowpan_fetch_skb_u8(skb, &slen) || /* frame length */ - lowpan_fetch_skb_u16(skb, &tag)) /* fragment tag */ - goto drop; - - /* adds the 3 MSB to the 8 LSB to retrieve the 11 bits length */ - len = ((iphc0 & 7) << 8) | slen; - - if ((iphc0 & LOWPAN_DISPATCH_MASK) == LOWPAN_DISPATCH_FRAG1) { - pr_debug("%s received a FRAG1 packet (tag: %d, " - "size of the entire IP packet: %d)", - __func__, tag, len); - } else { /* FRAGN */ - if (lowpan_fetch_skb_u8(skb, &offset)) - goto unlock_and_drop; - pr_debug("%s received a FRAGN packet (tag: %d, " - "size of the entire IP packet: %d, " - "offset: %d)", __func__, tag, len, offset * 8); - } - - /* - * check if frame assembling with the same tag is - * already in progress - */ - spin_lock_bh(&flist_lock); - - list_for_each_entry(frame, &lowpan_fragments, list) - if (frame->tag == tag) { - found = true; - break; - } - - /* alloc new frame structure */ - if (!found) { - pr_debug("%s first fragment received for tag %d, " - "begin packet reassembly", __func__, tag); - frame = lowpan_alloc_new_frame(skb, len, tag); - if (!frame) - goto unlock_and_drop; - } - - /* if payload fits buffer, copy it */ - if (likely((offset * 8 + skb->len) <= frame->length)) - skb_copy_to_linear_data_offset(frame->skb, offset * 8, - skb->data, skb->len); - else - goto unlock_and_drop; - - frame->bytes_rcv += skb->len; - - /* frame assembling complete */ - if ((frame->bytes_rcv == frame->length) && - frame->timer.expires > jiffies) { - /* if timer haven't expired - first of all delete it */ - del_timer_sync(&frame->timer); - list_del(&frame->list); - spin_unlock_bh(&flist_lock); - - pr_debug("%s successfully reassembled fragment " - "(tag %d)", __func__, tag); - - dev_kfree_skb(skb); - skb = frame->skb; - kfree(frame); - - if (lowpan_fetch_skb_u8(skb, &iphc0)) - goto drop; - - break; - } - spin_unlock_bh(&flist_lock); - - return kfree_skb(skb), 0; - } - default: - break; - } - if (lowpan_fetch_skb_u8(skb, &iphc1)) goto drop; @@ -367,8 +193,6 @@ static int process_data(struct sk_buff *skb) IEEE802154_ADDR_LEN, iphc0, iphc1, lowpan_give_skb_to_devices); -unlock_and_drop: - spin_unlock_bh(&flist_lock); drop: kfree_skb(skb); return -EINVAL; @@ -389,7 +213,7 @@ static int lowpan_set_address(struct net_device *dev, void *p) static int lowpan_fragment_xmit(struct sk_buff *skb, u8 *head, - int mlen, int plen, int offset, int type) + int mlen, int plen, int offset, int type) { struct sk_buff *frag; int hlen; @@ -425,51 +249,68 @@ lowpan_fragment_xmit(struct sk_buff *skb, u8 *head, static int lowpan_skb_fragmentation(struct sk_buff *skb, struct net_device *dev) { - int err, header_length, payload_length, tag, offset = 0; + int err; + u16 dgram_offset, dgram_size, payload_length, header_length, + lowpan_size, frag_plen, offset; + __be16 tag; u8 head[5]; header_length = skb->mac_len; payload_length = skb->len - header_length; tag = lowpan_dev_info(dev)->fragment_tag++; + lowpan_size = skb_network_header_len(skb); + dgram_size = lowpan_uncompress_size(skb, &dgram_offset) - + header_length; /* first fragment header */ - head[0] = LOWPAN_DISPATCH_FRAG1 | ((payload_length >> 8) & 0x7); - head[1] = payload_length & 0xff; - head[2] = tag >> 8; - head[3] = tag & 0xff; + head[0] = LOWPAN_DISPATCH_FRAG1 | ((dgram_size >> 8) & 0x7); + head[1] = dgram_size & 0xff; + memcpy(head + 2, &tag, sizeof(tag)); - err = lowpan_fragment_xmit(skb, head, header_length, LOWPAN_FRAG_SIZE, - 0, LOWPAN_DISPATCH_FRAG1); + /* calc the nearest payload length(divided to 8) for first fragment + * which fits into a IEEE802154_MTU + */ + frag_plen = round_down(IEEE802154_MTU - header_length - + LOWPAN_FRAG1_HEAD_SIZE - lowpan_size - + IEEE802154_MFR_SIZE, 8); + err = lowpan_fragment_xmit(skb, head, header_length, + frag_plen + lowpan_size, 0, + LOWPAN_DISPATCH_FRAG1); if (err) { pr_debug("%s unable to send FRAG1 packet (tag: %d)", __func__, tag); goto exit; } - offset = LOWPAN_FRAG_SIZE; + offset = lowpan_size + frag_plen; + dgram_offset += frag_plen; /* next fragment header */ head[0] &= ~LOWPAN_DISPATCH_FRAG1; head[0] |= LOWPAN_DISPATCH_FRAGN; + frag_plen = round_down(IEEE802154_MTU - header_length - + LOWPAN_FRAGN_HEAD_SIZE - IEEE802154_MFR_SIZE, 8); + while (payload_length - offset > 0) { - int len = LOWPAN_FRAG_SIZE; + int len = frag_plen; - head[4] = offset / 8; + head[4] = dgram_offset >> 3; if (payload_length - offset < len) len = payload_length - offset; - err = lowpan_fragment_xmit(skb, head, header_length, - len, offset, LOWPAN_DISPATCH_FRAGN); + err = lowpan_fragment_xmit(skb, head, header_length, len, + offset, LOWPAN_DISPATCH_FRAGN); if (err) { - pr_debug("%s unable to send a subsequent FRAGN packet " - "(tag: %d, offset: %d", __func__, tag, offset); + pr_debug("%s unable to send a FRAGN packet. (tag: %d, offset: %d)\n", + __func__, tag, offset); goto exit; } offset += len; + dgram_offset += len; } exit: @@ -533,7 +374,27 @@ static struct header_ops lowpan_header_ops = { .create = lowpan_header_create, }; +static struct lock_class_key lowpan_tx_busylock; +static struct lock_class_key lowpan_netdev_xmit_lock_key; + +static void lowpan_set_lockdep_class_one(struct net_device *dev, + struct netdev_queue *txq, + void *_unused) +{ + lockdep_set_class(&txq->_xmit_lock, + &lowpan_netdev_xmit_lock_key); +} + + +static int lowpan_dev_init(struct net_device *dev) +{ + netdev_for_each_tx_queue(dev, lowpan_set_lockdep_class_one, NULL); + dev->qdisc_tx_busylock = &lowpan_tx_busylock; + return 0; +} + static const struct net_device_ops lowpan_netdev_ops = { + .ndo_init = lowpan_dev_init, .ndo_start_xmit = lowpan_xmit, .ndo_set_mac_address = lowpan_set_address, }; @@ -577,44 +438,53 @@ static int lowpan_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { struct sk_buff *local_skb; + int ret; if (!netif_running(dev)) - goto drop; + goto drop_skb; if (dev->type != ARPHRD_IEEE802154) - goto drop; + goto drop_skb; + + local_skb = skb_clone(skb, GFP_ATOMIC); + if (!local_skb) + goto drop_skb; + + kfree_skb(skb); /* check that it's our buffer */ if (skb->data[0] == LOWPAN_DISPATCH_IPV6) { - /* Copy the packet so that the IPv6 header is - * properly aligned. - */ - local_skb = skb_copy_expand(skb, NET_SKB_PAD - 1, - skb_tailroom(skb), GFP_ATOMIC); - if (!local_skb) - goto drop; - local_skb->protocol = htons(ETH_P_IPV6); local_skb->pkt_type = PACKET_HOST; /* Pull off the 1-byte of 6lowpan header. */ skb_pull(local_skb, 1); - lowpan_give_skb_to_devices(local_skb, NULL); - - kfree_skb(local_skb); - kfree_skb(skb); + ret = lowpan_give_skb_to_devices(local_skb, NULL); + if (ret == NET_RX_DROP) + goto drop; } else { switch (skb->data[0] & 0xe0) { case LOWPAN_DISPATCH_IPHC: /* ipv6 datagram */ + ret = process_data(local_skb); + if (ret == NET_RX_DROP) + goto drop; + break; case LOWPAN_DISPATCH_FRAG1: /* first fragment header */ + ret = lowpan_frag_rcv(local_skb, LOWPAN_DISPATCH_FRAG1); + if (ret == 1) { + ret = process_data(local_skb); + if (ret == NET_RX_DROP) + goto drop; + } + break; case LOWPAN_DISPATCH_FRAGN: /* next fragments headers */ - local_skb = skb_clone(skb, GFP_ATOMIC); - if (!local_skb) - goto drop; - process_data(local_skb); - - kfree_skb(skb); + ret = lowpan_frag_rcv(local_skb, LOWPAN_DISPATCH_FRAGN); + if (ret == 1) { + ret = process_data(local_skb); + if (ret == NET_RX_DROP) + goto drop; + } break; default: break; @@ -622,9 +492,9 @@ static int lowpan_rcv(struct sk_buff *skb, struct net_device *dev, } return NET_RX_SUCCESS; - -drop: +drop_skb: kfree_skb(skb); +drop: return NET_RX_DROP; } @@ -648,10 +518,9 @@ static int lowpan_newlink(struct net *src_net, struct net_device *dev, } lowpan_dev_info(dev)->real_dev = real_dev; - lowpan_dev_info(dev)->fragment_tag = 0; mutex_init(&lowpan_dev_info(dev)->dev_list_mtx); - entry = kzalloc(sizeof(struct lowpan_dev_record), GFP_KERNEL); + entry = kzalloc(sizeof(*entry), GFP_KERNEL); if (!entry) { dev_put(real_dev); lowpan_dev_info(dev)->real_dev = NULL; @@ -744,7 +613,7 @@ static struct notifier_block lowpan_dev_notifier = { }; static struct packet_type lowpan_packet_type = { - .type = __constant_htons(ETH_P_IEEE802154), + .type = htons(ETH_P_IEEE802154), .func = lowpan_rcv, }; @@ -752,43 +621,40 @@ static int __init lowpan_init_module(void) { int err = 0; - err = lowpan_netlink_init(); + err = lowpan_net_frag_init(); if (err < 0) goto out; + err = lowpan_netlink_init(); + if (err < 0) + goto out_frag; + dev_add_pack(&lowpan_packet_type); err = register_netdevice_notifier(&lowpan_dev_notifier); - if (err < 0) { - dev_remove_pack(&lowpan_packet_type); - lowpan_netlink_fini(); - } + if (err < 0) + goto out_pack; + + return 0; + +out_pack: + dev_remove_pack(&lowpan_packet_type); + lowpan_netlink_fini(); +out_frag: + lowpan_net_frag_exit(); out: return err; } static void __exit lowpan_cleanup_module(void) { - struct lowpan_fragment *frame, *tframe; - lowpan_netlink_fini(); dev_remove_pack(&lowpan_packet_type); - unregister_netdevice_notifier(&lowpan_dev_notifier); + lowpan_net_frag_exit(); - /* Now 6lowpan packet_type is removed, so no new fragments are - * expected on RX, therefore that's the time to clean incomplete - * fragments. - */ - spin_lock_bh(&flist_lock); - list_for_each_entry_safe(frame, tframe, &lowpan_fragments, list) { - del_timer_sync(&frame->timer); - list_del(&frame->list); - dev_kfree_skb(frame->skb); - kfree(frame); - } - spin_unlock_bh(&flist_lock); + unregister_netdevice_notifier(&lowpan_dev_notifier); } module_init(lowpan_init_module); diff --git a/net/ieee802154/Kconfig b/net/ieee802154/Kconfig index 9c9879d5ea64..8af1330b3137 100644 --- a/net/ieee802154/Kconfig +++ b/net/ieee802154/Kconfig @@ -15,7 +15,7 @@ config IEEE802154_6LOWPAN depends on IEEE802154 && IPV6 select 6LOWPAN_IPHC ---help--- - IPv6 compression over IEEE 802.15.4. + IPv6 compression over IEEE 802.15.4. config 6LOWPAN_IPHC tristate diff --git a/net/ieee802154/Makefile b/net/ieee802154/Makefile index e8f05885ced6..b113fc4be3e0 100644 --- a/net/ieee802154/Makefile +++ b/net/ieee802154/Makefile @@ -2,5 +2,6 @@ obj-$(CONFIG_IEEE802154) += ieee802154.o af_802154.o obj-$(CONFIG_IEEE802154_6LOWPAN) += 6lowpan.o obj-$(CONFIG_6LOWPAN_IPHC) += 6lowpan_iphc.o +6lowpan-y := 6lowpan_rtnl.o reassembly.o ieee802154-y := netlink.o nl-mac.o nl-phy.o nl_policy.o wpan-class.o af_802154-y := af_ieee802154.o raw.o dgram.o diff --git a/net/ieee802154/af_ieee802154.c b/net/ieee802154/af_ieee802154.c index 40e606f3788f..a56ab9c47278 100644 --- a/net/ieee802154/af_ieee802154.c +++ b/net/ieee802154/af_ieee802154.c @@ -326,7 +326,7 @@ drop: static struct packet_type ieee802154_packet_type = { - .type = __constant_htons(ETH_P_IEEE802154), + .type = htons(ETH_P_IEEE802154), .func = ieee802154_rcv, }; diff --git a/net/ieee802154/ieee802154.h b/net/ieee802154/ieee802154.h index cee4425b9956..6cbc8965be91 100644 --- a/net/ieee802154/ieee802154.h +++ b/net/ieee802154/ieee802154.h @@ -53,6 +53,7 @@ int ieee802154_list_phy(struct sk_buff *skb, struct genl_info *info); int ieee802154_dump_phy(struct sk_buff *skb, struct netlink_callback *cb); int ieee802154_add_iface(struct sk_buff *skb, struct genl_info *info); int ieee802154_del_iface(struct sk_buff *skb, struct genl_info *info); +int ieee802154_set_phyparams(struct sk_buff *skb, struct genl_info *info); enum ieee802154_mcgrp_ids { IEEE802154_COORD_MCGRP, diff --git a/net/ieee802154/netlink.c b/net/ieee802154/netlink.c index 43f1b2bf469f..67c151bf4b91 100644 --- a/net/ieee802154/netlink.c +++ b/net/ieee802154/netlink.c @@ -115,6 +115,7 @@ static const struct genl_ops ieee8021154_ops[] = { ieee802154_dump_phy), IEEE802154_OP(IEEE802154_ADD_IFACE, ieee802154_add_iface), IEEE802154_OP(IEEE802154_DEL_IFACE, ieee802154_del_iface), + IEEE802154_OP(IEEE802154_SET_PHYPARAMS, ieee802154_set_phyparams), /* see nl-mac.c */ IEEE802154_OP(IEEE802154_ASSOCIATE_REQ, ieee802154_associate_req), IEEE802154_OP(IEEE802154_ASSOCIATE_RESP, ieee802154_associate_resp), diff --git a/net/ieee802154/nl-phy.c b/net/ieee802154/nl-phy.c index 89b265aea151..222310a07762 100644 --- a/net/ieee802154/nl-phy.c +++ b/net/ieee802154/nl-phy.c @@ -55,7 +55,15 @@ static int ieee802154_nl_fill_phy(struct sk_buff *msg, u32 portid, mutex_lock(&phy->pib_lock); if (nla_put_string(msg, IEEE802154_ATTR_PHY_NAME, wpan_phy_name(phy)) || nla_put_u8(msg, IEEE802154_ATTR_PAGE, phy->current_page) || - nla_put_u8(msg, IEEE802154_ATTR_CHANNEL, phy->current_channel)) + nla_put_u8(msg, IEEE802154_ATTR_CHANNEL, phy->current_channel) || + nla_put_s8(msg, IEEE802154_ATTR_TXPOWER, phy->transmit_power) || + nla_put_u8(msg, IEEE802154_ATTR_LBT_ENABLED, phy->lbt) || + nla_put_u8(msg, IEEE802154_ATTR_CCA_MODE, phy->cca_mode) || + nla_put_s32(msg, IEEE802154_ATTR_CCA_ED_LEVEL, phy->cca_ed_level) || + nla_put_u8(msg, IEEE802154_ATTR_CSMA_RETRIES, phy->csma_retries) || + nla_put_u8(msg, IEEE802154_ATTR_CSMA_MIN_BE, phy->min_be) || + nla_put_u8(msg, IEEE802154_ATTR_CSMA_MAX_BE, phy->max_be) || + nla_put_s8(msg, IEEE802154_ATTR_FRAME_RETRIES, phy->frame_retries)) goto nla_put_failure; for (i = 0; i < 32; i++) { if (phy->channels_supported[i]) @@ -354,3 +362,193 @@ out_dev: return rc; } + +static int phy_set_txpower(struct wpan_phy *phy, struct genl_info *info) +{ + int txpower = nla_get_s8(info->attrs[IEEE802154_ATTR_TXPOWER]); + int rc; + + rc = phy->set_txpower(phy, txpower); + if (rc < 0) + return rc; + + phy->transmit_power = txpower; + + return 0; +} + +static int phy_set_lbt(struct wpan_phy *phy, struct genl_info *info) +{ + u8 on = !!nla_get_u8(info->attrs[IEEE802154_ATTR_LBT_ENABLED]); + int rc; + + rc = phy->set_lbt(phy, on); + if (rc < 0) + return rc; + + phy->lbt = on; + + return 0; +} + +static int phy_set_cca_mode(struct wpan_phy *phy, struct genl_info *info) +{ + u8 mode = nla_get_u8(info->attrs[IEEE802154_ATTR_CCA_MODE]); + int rc; + + if (mode > 3) + return -EINVAL; + + rc = phy->set_cca_mode(phy, mode); + if (rc < 0) + return rc; + + phy->cca_mode = mode; + + return 0; +} + +static int phy_set_cca_ed_level(struct wpan_phy *phy, struct genl_info *info) +{ + s32 level = nla_get_s32(info->attrs[IEEE802154_ATTR_CCA_ED_LEVEL]); + int rc; + + rc = phy->set_cca_ed_level(phy, level); + if (rc < 0) + return rc; + + phy->cca_ed_level = level; + + return 0; +} + +static int phy_set_csma_params(struct wpan_phy *phy, struct genl_info *info) +{ + int rc; + u8 min_be = phy->min_be; + u8 max_be = phy->max_be; + u8 retries = phy->csma_retries; + + if (info->attrs[IEEE802154_ATTR_CSMA_RETRIES]) + retries = nla_get_u8(info->attrs[IEEE802154_ATTR_CSMA_RETRIES]); + if (info->attrs[IEEE802154_ATTR_CSMA_MIN_BE]) + min_be = nla_get_u8(info->attrs[IEEE802154_ATTR_CSMA_MIN_BE]); + if (info->attrs[IEEE802154_ATTR_CSMA_MAX_BE]) + max_be = nla_get_u8(info->attrs[IEEE802154_ATTR_CSMA_MAX_BE]); + + if (retries > 5 || max_be < 3 || max_be > 8 || min_be > max_be) + return -EINVAL; + + rc = phy->set_csma_params(phy, min_be, max_be, retries); + if (rc < 0) + return rc; + + phy->min_be = min_be; + phy->max_be = max_be; + phy->csma_retries = retries; + + return 0; +} + +static int phy_set_frame_retries(struct wpan_phy *phy, struct genl_info *info) +{ + s8 retries = nla_get_s8(info->attrs[IEEE802154_ATTR_FRAME_RETRIES]); + int rc; + + if (retries < -1 || retries > 7) + return -EINVAL; + + rc = phy->set_frame_retries(phy, retries); + if (rc < 0) + return rc; + + phy->frame_retries = retries; + + return 0; +} + +int ieee802154_set_phyparams(struct sk_buff *skb, struct genl_info *info) +{ + struct wpan_phy *phy; + const char *name; + int rc = -ENOTSUPP; + + pr_debug("%s\n", __func__); + + if (!info->attrs[IEEE802154_ATTR_PHY_NAME] && + !info->attrs[IEEE802154_ATTR_LBT_ENABLED] && + !info->attrs[IEEE802154_ATTR_CCA_MODE] && + !info->attrs[IEEE802154_ATTR_CCA_ED_LEVEL] && + !info->attrs[IEEE802154_ATTR_CSMA_RETRIES] && + !info->attrs[IEEE802154_ATTR_CSMA_MIN_BE] && + !info->attrs[IEEE802154_ATTR_CSMA_MAX_BE] && + !info->attrs[IEEE802154_ATTR_FRAME_RETRIES]) + return -EINVAL; + + name = nla_data(info->attrs[IEEE802154_ATTR_PHY_NAME]); + if (name[nla_len(info->attrs[IEEE802154_ATTR_PHY_NAME]) - 1] != '\0') + return -EINVAL; /* phy name should be null-terminated */ + + phy = wpan_phy_find(name); + if (!phy) + return -ENODEV; + + if ((!phy->set_txpower && info->attrs[IEEE802154_ATTR_TXPOWER]) || + (!phy->set_lbt && info->attrs[IEEE802154_ATTR_LBT_ENABLED]) || + (!phy->set_cca_mode && info->attrs[IEEE802154_ATTR_CCA_MODE]) || + (!phy->set_cca_ed_level && + info->attrs[IEEE802154_ATTR_CCA_ED_LEVEL])) + goto out; + + mutex_lock(&phy->pib_lock); + + if (info->attrs[IEEE802154_ATTR_TXPOWER]) { + rc = phy_set_txpower(phy, info); + if (rc < 0) + goto error; + } + + if (info->attrs[IEEE802154_ATTR_LBT_ENABLED]) { + rc = phy_set_lbt(phy, info); + if (rc < 0) + goto error; + } + + if (info->attrs[IEEE802154_ATTR_CCA_MODE]) { + rc = phy_set_cca_mode(phy, info); + if (rc < 0) + goto error; + } + + if (info->attrs[IEEE802154_ATTR_CCA_ED_LEVEL]) { + rc = phy_set_cca_ed_level(phy, info); + if (rc < 0) + goto error; + } + + if (info->attrs[IEEE802154_ATTR_CSMA_RETRIES] || + info->attrs[IEEE802154_ATTR_CSMA_MIN_BE] || + info->attrs[IEEE802154_ATTR_CSMA_MAX_BE]) { + rc = phy_set_csma_params(phy, info); + if (rc < 0) + goto error; + } + + if (info->attrs[IEEE802154_ATTR_FRAME_RETRIES]) { + rc = phy_set_frame_retries(phy, info); + if (rc < 0) + goto error; + } + + mutex_unlock(&phy->pib_lock); + + wpan_phy_put(phy); + + return 0; + +error: + mutex_unlock(&phy->pib_lock); +out: + wpan_phy_put(phy); + return rc; +} diff --git a/net/ieee802154/nl_policy.c b/net/ieee802154/nl_policy.c index 6adda4d46f95..fd7be5e45cef 100644 --- a/net/ieee802154/nl_policy.c +++ b/net/ieee802154/nl_policy.c @@ -52,5 +52,15 @@ const struct nla_policy ieee802154_policy[IEEE802154_ATTR_MAX + 1] = { [IEEE802154_ATTR_DURATION] = { .type = NLA_U8, }, [IEEE802154_ATTR_ED_LIST] = { .len = 27 }, [IEEE802154_ATTR_CHANNEL_PAGE_LIST] = { .len = 32 * 4, }, + + [IEEE802154_ATTR_TXPOWER] = { .type = NLA_S8, }, + [IEEE802154_ATTR_LBT_ENABLED] = { .type = NLA_U8, }, + [IEEE802154_ATTR_CCA_MODE] = { .type = NLA_U8, }, + [IEEE802154_ATTR_CCA_ED_LEVEL] = { .type = NLA_S32, }, + [IEEE802154_ATTR_CSMA_RETRIES] = { .type = NLA_U8, }, + [IEEE802154_ATTR_CSMA_MIN_BE] = { .type = NLA_U8, }, + [IEEE802154_ATTR_CSMA_MAX_BE] = { .type = NLA_U8, }, + + [IEEE802154_ATTR_FRAME_RETRIES] = { .type = NLA_S8, }, }; diff --git a/net/ieee802154/reassembly.c b/net/ieee802154/reassembly.c new file mode 100644 index 000000000000..f4ac95778977 --- /dev/null +++ b/net/ieee802154/reassembly.c @@ -0,0 +1,565 @@ +/* 6LoWPAN fragment reassembly + * + * + * Authors: + * Alexander Aring <aar@pengutronix.de> + * + * Based on: net/ipv6/reassembly.c + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#define pr_fmt(fmt) "6LoWPAN: " fmt + +#include <linux/net.h> +#include <linux/list.h> +#include <linux/netdevice.h> +#include <linux/random.h> +#include <linux/jhash.h> +#include <linux/skbuff.h> +#include <linux/slab.h> +#include <linux/export.h> + +#include <net/ieee802154_netdev.h> +#include <net/6lowpan.h> +#include <net/ipv6.h> +#include <net/inet_frag.h> + +#include "reassembly.h" + +static struct inet_frags lowpan_frags; + +static int lowpan_frag_reasm(struct lowpan_frag_queue *fq, + struct sk_buff *prev, struct net_device *dev); + +static unsigned int lowpan_hash_frag(__be16 tag, u16 d_size, + const struct ieee802154_addr *saddr, + const struct ieee802154_addr *daddr) +{ + u32 c; + + net_get_random_once(&lowpan_frags.rnd, sizeof(lowpan_frags.rnd)); + c = jhash_3words(ieee802154_addr_hash(saddr), + ieee802154_addr_hash(daddr), + (__force u32)(tag + (d_size << 16)), + lowpan_frags.rnd); + + return c & (INETFRAGS_HASHSZ - 1); +} + +static unsigned int lowpan_hashfn(struct inet_frag_queue *q) +{ + struct lowpan_frag_queue *fq; + + fq = container_of(q, struct lowpan_frag_queue, q); + return lowpan_hash_frag(fq->tag, fq->d_size, &fq->saddr, &fq->daddr); +} + +bool lowpan_frag_match(struct inet_frag_queue *q, void *a) +{ + struct lowpan_frag_queue *fq; + struct lowpan_create_arg *arg = a; + + fq = container_of(q, struct lowpan_frag_queue, q); + return fq->tag == arg->tag && fq->d_size == arg->d_size && + ieee802154_addr_addr_equal(&fq->saddr, arg->src) && + ieee802154_addr_addr_equal(&fq->daddr, arg->dst); +} +EXPORT_SYMBOL(lowpan_frag_match); + +void lowpan_frag_init(struct inet_frag_queue *q, void *a) +{ + struct lowpan_frag_queue *fq; + struct lowpan_create_arg *arg = a; + + fq = container_of(q, struct lowpan_frag_queue, q); + + fq->tag = arg->tag; + fq->d_size = arg->d_size; + fq->saddr = *arg->src; + fq->daddr = *arg->dst; +} +EXPORT_SYMBOL(lowpan_frag_init); + +void lowpan_expire_frag_queue(struct frag_queue *fq, struct inet_frags *frags) +{ + spin_lock(&fq->q.lock); + + if (fq->q.last_in & INET_FRAG_COMPLETE) + goto out; + + inet_frag_kill(&fq->q, frags); +out: + spin_unlock(&fq->q.lock); + inet_frag_put(&fq->q, frags); +} +EXPORT_SYMBOL(lowpan_expire_frag_queue); + +static void lowpan_frag_expire(unsigned long data) +{ + struct frag_queue *fq; + struct net *net; + + fq = container_of((struct inet_frag_queue *)data, struct frag_queue, q); + net = container_of(fq->q.net, struct net, ieee802154_lowpan.frags); + + lowpan_expire_frag_queue(fq, &lowpan_frags); +} + +static inline struct lowpan_frag_queue * +fq_find(struct net *net, const struct ieee802154_frag_info *frag_info, + const struct ieee802154_addr *src, const struct ieee802154_addr *dst) +{ + struct inet_frag_queue *q; + struct lowpan_create_arg arg; + unsigned int hash; + + arg.tag = frag_info->d_tag; + arg.d_size = frag_info->d_size; + arg.src = src; + arg.dst = dst; + + read_lock(&lowpan_frags.lock); + hash = lowpan_hash_frag(frag_info->d_tag, frag_info->d_size, src, dst); + + q = inet_frag_find(&net->ieee802154_lowpan.frags, + &lowpan_frags, &arg, hash); + if (IS_ERR_OR_NULL(q)) { + inet_frag_maybe_warn_overflow(q, pr_fmt()); + return NULL; + } + return container_of(q, struct lowpan_frag_queue, q); +} + +static int lowpan_frag_queue(struct lowpan_frag_queue *fq, + struct sk_buff *skb, const u8 frag_type) +{ + struct sk_buff *prev, *next; + struct net_device *dev; + int end, offset; + + if (fq->q.last_in & INET_FRAG_COMPLETE) + goto err; + + offset = mac_cb(skb)->frag_info.d_offset << 3; + end = mac_cb(skb)->frag_info.d_size; + + /* Is this the final fragment? */ + if (offset + skb->len == end) { + /* If we already have some bits beyond end + * or have different end, the segment is corrupted. + */ + if (end < fq->q.len || + ((fq->q.last_in & INET_FRAG_LAST_IN) && end != fq->q.len)) + goto err; + fq->q.last_in |= INET_FRAG_LAST_IN; + fq->q.len = end; + } else { + if (end > fq->q.len) { + /* Some bits beyond end -> corruption. */ + if (fq->q.last_in & INET_FRAG_LAST_IN) + goto err; + fq->q.len = end; + } + } + + /* Find out which fragments are in front and at the back of us + * in the chain of fragments so far. We must know where to put + * this fragment, right? + */ + prev = fq->q.fragments_tail; + if (!prev || mac_cb(prev)->frag_info.d_offset < + mac_cb(skb)->frag_info.d_offset) { + next = NULL; + goto found; + } + prev = NULL; + for (next = fq->q.fragments; next != NULL; next = next->next) { + if (mac_cb(next)->frag_info.d_offset >= + mac_cb(skb)->frag_info.d_offset) + break; /* bingo! */ + prev = next; + } + +found: + /* Insert this fragment in the chain of fragments. */ + skb->next = next; + if (!next) + fq->q.fragments_tail = skb; + if (prev) + prev->next = skb; + else + fq->q.fragments = skb; + + dev = skb->dev; + if (dev) + skb->dev = NULL; + + fq->q.stamp = skb->tstamp; + if (frag_type == LOWPAN_DISPATCH_FRAG1) { + /* Calculate uncomp. 6lowpan header to estimate full size */ + fq->q.meat += lowpan_uncompress_size(skb, NULL); + fq->q.last_in |= INET_FRAG_FIRST_IN; + } else { + fq->q.meat += skb->len; + } + add_frag_mem_limit(&fq->q, skb->truesize); + + if (fq->q.last_in == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && + fq->q.meat == fq->q.len) { + int res; + unsigned long orefdst = skb->_skb_refdst; + + skb->_skb_refdst = 0UL; + res = lowpan_frag_reasm(fq, prev, dev); + skb->_skb_refdst = orefdst; + return res; + } + + inet_frag_lru_move(&fq->q); + return -1; +err: + kfree_skb(skb); + return -1; +} + +/* Check if this packet is complete. + * Returns NULL on failure by any reason, and pointer + * to current nexthdr field in reassembled frame. + * + * It is called with locked fq, and caller must check that + * queue is eligible for reassembly i.e. it is not COMPLETE, + * the last and the first frames arrived and all the bits are here. + */ +static int lowpan_frag_reasm(struct lowpan_frag_queue *fq, struct sk_buff *prev, + struct net_device *dev) +{ + struct sk_buff *fp, *head = fq->q.fragments; + int sum_truesize; + + inet_frag_kill(&fq->q, &lowpan_frags); + + /* Make the one we just received the head. */ + if (prev) { + head = prev->next; + fp = skb_clone(head, GFP_ATOMIC); + + if (!fp) + goto out_oom; + + fp->next = head->next; + if (!fp->next) + fq->q.fragments_tail = fp; + prev->next = fp; + + skb_morph(head, fq->q.fragments); + head->next = fq->q.fragments->next; + + consume_skb(fq->q.fragments); + fq->q.fragments = head; + } + + /* Head of list must not be cloned. */ + if (skb_unclone(head, GFP_ATOMIC)) + goto out_oom; + + /* If the first fragment is fragmented itself, we split + * it to two chunks: the first with data and paged part + * and the second, holding only fragments. + */ + if (skb_has_frag_list(head)) { + struct sk_buff *clone; + int i, plen = 0; + + clone = alloc_skb(0, GFP_ATOMIC); + if (!clone) + goto out_oom; + clone->next = head->next; + head->next = clone; + skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list; + skb_frag_list_init(head); + for (i = 0; i < skb_shinfo(head)->nr_frags; i++) + plen += skb_frag_size(&skb_shinfo(head)->frags[i]); + clone->len = head->data_len - plen; + clone->data_len = clone->len; + head->data_len -= clone->len; + head->len -= clone->len; + add_frag_mem_limit(&fq->q, clone->truesize); + } + + WARN_ON(head == NULL); + + sum_truesize = head->truesize; + for (fp = head->next; fp;) { + bool headstolen; + int delta; + struct sk_buff *next = fp->next; + + sum_truesize += fp->truesize; + if (skb_try_coalesce(head, fp, &headstolen, &delta)) { + kfree_skb_partial(fp, headstolen); + } else { + if (!skb_shinfo(head)->frag_list) + skb_shinfo(head)->frag_list = fp; + head->data_len += fp->len; + head->len += fp->len; + head->truesize += fp->truesize; + } + fp = next; + } + sub_frag_mem_limit(&fq->q, sum_truesize); + + head->next = NULL; + head->dev = dev; + head->tstamp = fq->q.stamp; + + fq->q.fragments = NULL; + fq->q.fragments_tail = NULL; + + return 1; +out_oom: + net_dbg_ratelimited("lowpan_frag_reasm: no memory for reassembly\n"); + return -1; +} + +static int lowpan_get_frag_info(struct sk_buff *skb, const u8 frag_type, + struct ieee802154_frag_info *frag_info) +{ + bool fail; + u8 pattern = 0, low = 0; + + fail = lowpan_fetch_skb(skb, &pattern, 1); + fail |= lowpan_fetch_skb(skb, &low, 1); + frag_info->d_size = (pattern & 7) << 8 | low; + fail |= lowpan_fetch_skb(skb, &frag_info->d_tag, 2); + + if (frag_type == LOWPAN_DISPATCH_FRAGN) { + fail |= lowpan_fetch_skb(skb, &frag_info->d_offset, 1); + } else { + skb_reset_network_header(skb); + frag_info->d_offset = 0; + } + + if (unlikely(fail)) + return -EIO; + + return 0; +} + +int lowpan_frag_rcv(struct sk_buff *skb, const u8 frag_type) +{ + struct lowpan_frag_queue *fq; + struct net *net = dev_net(skb->dev); + struct ieee802154_frag_info *frag_info = &mac_cb(skb)->frag_info; + int err; + + err = lowpan_get_frag_info(skb, frag_type, frag_info); + if (err < 0) + goto err; + + if (frag_info->d_size > net->ieee802154_lowpan.max_dsize) + goto err; + + inet_frag_evictor(&net->ieee802154_lowpan.frags, &lowpan_frags, false); + + fq = fq_find(net, frag_info, &mac_cb(skb)->sa, &mac_cb(skb)->da); + if (fq != NULL) { + int ret; + spin_lock(&fq->q.lock); + ret = lowpan_frag_queue(fq, skb, frag_type); + spin_unlock(&fq->q.lock); + + inet_frag_put(&fq->q, &lowpan_frags); + return ret; + } + +err: + kfree_skb(skb); + return -1; +} +EXPORT_SYMBOL(lowpan_frag_rcv); + +#ifdef CONFIG_SYSCTL +static struct ctl_table lowpan_frags_ns_ctl_table[] = { + { + .procname = "6lowpanfrag_high_thresh", + .data = &init_net.ieee802154_lowpan.frags.high_thresh, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, + { + .procname = "6lowpanfrag_low_thresh", + .data = &init_net.ieee802154_lowpan.frags.low_thresh, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, + { + .procname = "6lowpanfrag_time", + .data = &init_net.ieee802154_lowpan.frags.timeout, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + { + .procname = "6lowpanfrag_max_datagram_size", + .data = &init_net.ieee802154_lowpan.max_dsize, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, + { } +}; + +static struct ctl_table lowpan_frags_ctl_table[] = { + { + .procname = "6lowpanfrag_secret_interval", + .data = &lowpan_frags.secret_interval, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + { } +}; + +static int __net_init lowpan_frags_ns_sysctl_register(struct net *net) +{ + struct ctl_table *table; + struct ctl_table_header *hdr; + + table = lowpan_frags_ns_ctl_table; + if (!net_eq(net, &init_net)) { + table = kmemdup(table, sizeof(lowpan_frags_ns_ctl_table), + GFP_KERNEL); + if (table == NULL) + goto err_alloc; + + table[0].data = &net->ieee802154_lowpan.frags.high_thresh; + table[1].data = &net->ieee802154_lowpan.frags.low_thresh; + table[2].data = &net->ieee802154_lowpan.frags.timeout; + table[3].data = &net->ieee802154_lowpan.max_dsize; + + /* Don't export sysctls to unprivileged users */ + if (net->user_ns != &init_user_ns) + table[0].procname = NULL; + } + + hdr = register_net_sysctl(net, "net/ieee802154/6lowpan", table); + if (hdr == NULL) + goto err_reg; + + net->ieee802154_lowpan.sysctl.frags_hdr = hdr; + return 0; + +err_reg: + if (!net_eq(net, &init_net)) + kfree(table); +err_alloc: + return -ENOMEM; +} + +static void __net_exit lowpan_frags_ns_sysctl_unregister(struct net *net) +{ + struct ctl_table *table; + + table = net->ieee802154_lowpan.sysctl.frags_hdr->ctl_table_arg; + unregister_net_sysctl_table(net->ieee802154_lowpan.sysctl.frags_hdr); + if (!net_eq(net, &init_net)) + kfree(table); +} + +static struct ctl_table_header *lowpan_ctl_header; + +static int lowpan_frags_sysctl_register(void) +{ + lowpan_ctl_header = register_net_sysctl(&init_net, + "net/ieee802154/6lowpan", + lowpan_frags_ctl_table); + return lowpan_ctl_header == NULL ? -ENOMEM : 0; +} + +static void lowpan_frags_sysctl_unregister(void) +{ + unregister_net_sysctl_table(lowpan_ctl_header); +} +#else +static inline int lowpan_frags_ns_sysctl_register(struct net *net) +{ + return 0; +} + +static inline void lowpan_frags_ns_sysctl_unregister(struct net *net) +{ +} + +static inline int lowpan_frags_sysctl_register(void) +{ + return 0; +} + +static inline void lowpan_frags_sysctl_unregister(void) +{ +} +#endif + +static int __net_init lowpan_frags_init_net(struct net *net) +{ + net->ieee802154_lowpan.frags.high_thresh = IPV6_FRAG_HIGH_THRESH; + net->ieee802154_lowpan.frags.low_thresh = IPV6_FRAG_LOW_THRESH; + net->ieee802154_lowpan.frags.timeout = IPV6_FRAG_TIMEOUT; + net->ieee802154_lowpan.max_dsize = 0xFFFF; + + inet_frags_init_net(&net->ieee802154_lowpan.frags); + + return lowpan_frags_ns_sysctl_register(net); +} + +static void __net_exit lowpan_frags_exit_net(struct net *net) +{ + lowpan_frags_ns_sysctl_unregister(net); + inet_frags_exit_net(&net->ieee802154_lowpan.frags, &lowpan_frags); +} + +static struct pernet_operations lowpan_frags_ops = { + .init = lowpan_frags_init_net, + .exit = lowpan_frags_exit_net, +}; + +int __init lowpan_net_frag_init(void) +{ + int ret; + + ret = lowpan_frags_sysctl_register(); + if (ret) + return ret; + + ret = register_pernet_subsys(&lowpan_frags_ops); + if (ret) + goto err_pernet; + + lowpan_frags.hashfn = lowpan_hashfn; + lowpan_frags.constructor = lowpan_frag_init; + lowpan_frags.destructor = NULL; + lowpan_frags.skb_free = NULL; + lowpan_frags.qsize = sizeof(struct frag_queue); + lowpan_frags.match = lowpan_frag_match; + lowpan_frags.frag_expire = lowpan_frag_expire; + lowpan_frags.secret_interval = 10 * 60 * HZ; + inet_frags_init(&lowpan_frags); + + return ret; +err_pernet: + lowpan_frags_sysctl_unregister(); + return ret; +} + +void lowpan_net_frag_exit(void) +{ + inet_frags_fini(&lowpan_frags); + lowpan_frags_sysctl_unregister(); + unregister_pernet_subsys(&lowpan_frags_ops); +} diff --git a/net/ieee802154/reassembly.h b/net/ieee802154/reassembly.h new file mode 100644 index 000000000000..055518b9da2d --- /dev/null +++ b/net/ieee802154/reassembly.h @@ -0,0 +1,66 @@ +#ifndef __IEEE802154_6LOWPAN_REASSEMBLY_H__ +#define __IEEE802154_6LOWPAN_REASSEMBLY_H__ + +#include <net/inet_frag.h> + +struct lowpan_create_arg { + __be16 tag; + u16 d_size; + const struct ieee802154_addr *src; + const struct ieee802154_addr *dst; +}; + +/* Equivalent of ipv4 struct ip + */ +struct lowpan_frag_queue { + struct inet_frag_queue q; + + __be16 tag; + u16 d_size; + struct ieee802154_addr saddr; + struct ieee802154_addr daddr; +}; + +static inline u32 ieee802154_addr_hash(const struct ieee802154_addr *a) +{ + switch (a->addr_type) { + case IEEE802154_ADDR_LONG: + return (__force u32)((((u32 *)a->hwaddr))[0] ^ + ((u32 *)(a->hwaddr))[1]); + case IEEE802154_ADDR_SHORT: + return (__force u32)(a->short_addr); + default: + return 0; + } +} + +static inline bool ieee802154_addr_addr_equal(const struct ieee802154_addr *a1, + const struct ieee802154_addr *a2) +{ + if (a1->pan_id != a2->pan_id) + return false; + + if (a1->addr_type != a2->addr_type) + return false; + + switch (a1->addr_type) { + case IEEE802154_ADDR_LONG: + if (memcmp(a1->hwaddr, a2->hwaddr, IEEE802154_ADDR_LEN)) + return false; + break; + case IEEE802154_ADDR_SHORT: + if (a1->short_addr != a2->short_addr) + return false; + break; + default: + return false; + } + + return true; +} + +int lowpan_frag_rcv(struct sk_buff *skb, const u8 frag_type); +void lowpan_net_frag_exit(void); +int lowpan_net_frag_init(void); + +#endif /* __IEEE802154_6LOWPAN_REASSEMBLY_H__ */ diff --git a/net/ieee802154/wpan-class.c b/net/ieee802154/wpan-class.c index 4dd37615a749..edd0962d55f9 100644 --- a/net/ieee802154/wpan-class.c +++ b/net/ieee802154/wpan-class.c @@ -44,9 +44,7 @@ static DEVICE_ATTR_RO(name); MASTER_SHOW(current_channel, "%d"); MASTER_SHOW(current_page, "%d"); -MASTER_SHOW_COMPLEX(transmit_power, "%d +- %d dB", - ((signed char) (phy->transmit_power << 2)) >> 2, - (phy->transmit_power >> 6) ? (phy->transmit_power >> 6) * 3 : 1); +MASTER_SHOW(transmit_power, "%d +- 1 dB"); MASTER_SHOW(cca_mode, "%d"); static ssize_t channels_supported_show(struct device *dev, @@ -171,6 +169,12 @@ struct wpan_phy *wpan_phy_alloc(size_t priv_size) phy->current_channel = -1; /* not initialised */ phy->current_page = 0; /* for compatibility */ + /* defaults per 802.15.4-2011 */ + phy->min_be = 3; + phy->max_be = 5; + phy->csma_retries = 4; + phy->frame_retries = -1; /* for compatibility, actual default is 3 */ + return phy; out: diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index f8c49ce5b283..f032688d20d3 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -55,4 +55,4 @@ obj-$(CONFIG_MEMCG_KMEM) += tcp_memcontrol.o obj-$(CONFIG_NETLABEL) += cipso_ipv4.o obj-$(CONFIG_XFRM) += xfrm4_policy.o xfrm4_state.o xfrm4_input.o \ - xfrm4_output.o + xfrm4_output.o xfrm4_protocol.o diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index ecd2c3f245ce..19ab78aca547 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1296,8 +1296,11 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb, segs = ERR_PTR(-EPROTONOSUPPORT); - /* Note : following gso_segment() might change skb->encapsulation */ - udpfrag = !skb->encapsulation && proto == IPPROTO_UDP; + if (skb->encapsulation && + skb_shinfo(skb)->gso_type & (SKB_GSO_SIT|SKB_GSO_IPIP)) + udpfrag = proto == IPPROTO_UDP && encap; + else + udpfrag = proto == IPPROTO_UDP && !skb->encapsulation; ops = rcu_dereference(inet_offloads[proto]); if (likely(ops && ops->callbacks.gso_segment)) diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c index 717902669d2f..a2afa89513a0 100644 --- a/net/ipv4/ah4.c +++ b/net/ipv4/ah4.c @@ -155,6 +155,10 @@ static int ah_output(struct xfrm_state *x, struct sk_buff *skb) struct iphdr *iph, *top_iph; struct ip_auth_hdr *ah; struct ah_data *ahp; + int seqhi_len = 0; + __be32 *seqhi; + int sglists = 0; + struct scatterlist *seqhisg; ahp = x->data; ahash = ahp->ahash; @@ -167,14 +171,19 @@ static int ah_output(struct xfrm_state *x, struct sk_buff *skb) ah = ip_auth_hdr(skb); ihl = ip_hdrlen(skb); + if (x->props.flags & XFRM_STATE_ESN) { + sglists = 1; + seqhi_len = sizeof(*seqhi); + } err = -ENOMEM; - iph = ah_alloc_tmp(ahash, nfrags, ihl); + iph = ah_alloc_tmp(ahash, nfrags + sglists, ihl + seqhi_len); if (!iph) goto out; - - icv = ah_tmp_icv(ahash, iph, ihl); + seqhi = (__be32 *)((char *)iph + ihl); + icv = ah_tmp_icv(ahash, seqhi, seqhi_len); req = ah_tmp_req(ahash, icv); sg = ah_req_sg(ahash, req); + seqhisg = sg + nfrags; memset(ah->auth_data, 0, ahp->icv_trunc_len); @@ -210,10 +219,15 @@ static int ah_output(struct xfrm_state *x, struct sk_buff *skb) ah->spi = x->id.spi; ah->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.low); - sg_init_table(sg, nfrags); - skb_to_sgvec(skb, sg, 0, skb->len); + sg_init_table(sg, nfrags + sglists); + skb_to_sgvec_nomark(skb, sg, 0, skb->len); - ahash_request_set_crypt(req, sg, icv, skb->len); + if (x->props.flags & XFRM_STATE_ESN) { + /* Attach seqhi sg right after packet payload */ + *seqhi = htonl(XFRM_SKB_CB(skb)->seq.output.hi); + sg_set_buf(seqhisg, seqhi, seqhi_len); + } + ahash_request_set_crypt(req, sg, icv, skb->len + seqhi_len); ahash_request_set_callback(req, 0, ah_output_done, skb); AH_SKB_CB(skb)->tmp = iph; @@ -295,6 +309,10 @@ static int ah_input(struct xfrm_state *x, struct sk_buff *skb) struct ip_auth_hdr *ah; struct ah_data *ahp; int err = -ENOMEM; + int seqhi_len = 0; + __be32 *seqhi; + int sglists = 0; + struct scatterlist *seqhisg; if (!pskb_may_pull(skb, sizeof(*ah))) goto out; @@ -335,14 +353,22 @@ static int ah_input(struct xfrm_state *x, struct sk_buff *skb) iph = ip_hdr(skb); ihl = ip_hdrlen(skb); - work_iph = ah_alloc_tmp(ahash, nfrags, ihl + ahp->icv_trunc_len); + if (x->props.flags & XFRM_STATE_ESN) { + sglists = 1; + seqhi_len = sizeof(*seqhi); + } + + work_iph = ah_alloc_tmp(ahash, nfrags + sglists, ihl + + ahp->icv_trunc_len + seqhi_len); if (!work_iph) goto out; - auth_data = ah_tmp_auth(work_iph, ihl); + seqhi = (__be32 *)((char *)work_iph + ihl); + auth_data = ah_tmp_auth(seqhi, seqhi_len); icv = ah_tmp_icv(ahash, auth_data, ahp->icv_trunc_len); req = ah_tmp_req(ahash, icv); sg = ah_req_sg(ahash, req); + seqhisg = sg + nfrags; memcpy(work_iph, iph, ihl); memcpy(auth_data, ah->auth_data, ahp->icv_trunc_len); @@ -361,10 +387,15 @@ static int ah_input(struct xfrm_state *x, struct sk_buff *skb) skb_push(skb, ihl); - sg_init_table(sg, nfrags); - skb_to_sgvec(skb, sg, 0, skb->len); + sg_init_table(sg, nfrags + sglists); + skb_to_sgvec_nomark(skb, sg, 0, skb->len); - ahash_request_set_crypt(req, sg, icv, skb->len); + if (x->props.flags & XFRM_STATE_ESN) { + /* Attach seqhi sg right after packet payload */ + *seqhi = XFRM_SKB_CB(skb)->seq.input.hi; + sg_set_buf(seqhisg, seqhi, seqhi_len); + } + ahash_request_set_crypt(req, sg, icv, skb->len + seqhi_len); ahash_request_set_callback(req, 0, ah_input_done, skb); AH_SKB_CB(skb)->tmp = work_iph; @@ -397,7 +428,7 @@ out: return err; } -static void ah4_err(struct sk_buff *skb, u32 info) +static int ah4_err(struct sk_buff *skb, u32 info) { struct net *net = dev_net(skb->dev); const struct iphdr *iph = (const struct iphdr *)skb->data; @@ -407,23 +438,25 @@ static void ah4_err(struct sk_buff *skb, u32 info) switch (icmp_hdr(skb)->type) { case ICMP_DEST_UNREACH: if (icmp_hdr(skb)->code != ICMP_FRAG_NEEDED) - return; + return 0; case ICMP_REDIRECT: break; default: - return; + return 0; } x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr, ah->spi, IPPROTO_AH, AF_INET); if (!x) - return; + return 0; if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_AH, 0); else ipv4_redirect(skb, net, 0, 0, IPPROTO_AH, 0); xfrm_state_put(x); + + return 0; } static int ah_init_state(struct xfrm_state *x) @@ -505,6 +538,10 @@ static void ah_destroy(struct xfrm_state *x) kfree(ahp); } +static int ah4_rcv_cb(struct sk_buff *skb, int err) +{ + return 0; +} static const struct xfrm_type ah_type = { @@ -518,11 +555,12 @@ static const struct xfrm_type ah_type = .output = ah_output }; -static const struct net_protocol ah4_protocol = { +static struct xfrm4_protocol ah4_protocol = { .handler = xfrm4_rcv, + .input_handler = xfrm_input, + .cb_handler = ah4_rcv_cb, .err_handler = ah4_err, - .no_policy = 1, - .netns_ok = 1, + .priority = 0, }; static int __init ah4_init(void) @@ -531,7 +569,7 @@ static int __init ah4_init(void) pr_info("%s: can't add xfrm type\n", __func__); return -EAGAIN; } - if (inet_add_protocol(&ah4_protocol, IPPROTO_AH) < 0) { + if (xfrm4_protocol_register(&ah4_protocol, IPPROTO_AH) < 0) { pr_info("%s: can't add protocol\n", __func__); xfrm_unregister_type(&ah_type, AF_INET); return -EAGAIN; @@ -541,7 +579,7 @@ static int __init ah4_init(void) static void __exit ah4_fini(void) { - if (inet_del_protocol(&ah4_protocol, IPPROTO_AH) < 0) + if (xfrm4_protocol_deregister(&ah4_protocol, IPPROTO_AH) < 0) pr_info("%s: can't remove protocol\n", __func__); if (xfrm_unregister_type(&ah_type, AF_INET) < 0) pr_info("%s: can't remove xfrm type\n", __func__); diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index ac2dff3c2c1c..bdbf68bb2e2d 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1443,7 +1443,8 @@ static size_t inet_nlmsg_size(void) + nla_total_size(4) /* IFA_LOCAL */ + nla_total_size(4) /* IFA_BROADCAST */ + nla_total_size(IFNAMSIZ) /* IFA_LABEL */ - + nla_total_size(4); /* IFA_FLAGS */ + + nla_total_size(4) /* IFA_FLAGS */ + + nla_total_size(sizeof(struct ifa_cacheinfo)); /* IFA_CACHEINFO */ } static inline u32 cstamp_delta(unsigned long cstamp) diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 7785b28061ac..360b565918c4 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -473,7 +473,7 @@ static u32 esp4_get_mtu(struct xfrm_state *x, int mtu) net_adj) & ~(blksize - 1)) + net_adj - 2; } -static void esp4_err(struct sk_buff *skb, u32 info) +static int esp4_err(struct sk_buff *skb, u32 info) { struct net *net = dev_net(skb->dev); const struct iphdr *iph = (const struct iphdr *)skb->data; @@ -483,23 +483,25 @@ static void esp4_err(struct sk_buff *skb, u32 info) switch (icmp_hdr(skb)->type) { case ICMP_DEST_UNREACH: if (icmp_hdr(skb)->code != ICMP_FRAG_NEEDED) - return; + return 0; case ICMP_REDIRECT: break; default: - return; + return 0; } x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr, esph->spi, IPPROTO_ESP, AF_INET); if (!x) - return; + return 0; if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_ESP, 0); else ipv4_redirect(skb, net, 0, 0, IPPROTO_ESP, 0); xfrm_state_put(x); + + return 0; } static void esp_destroy(struct xfrm_state *x) @@ -672,6 +674,11 @@ error: return err; } +static int esp4_rcv_cb(struct sk_buff *skb, int err) +{ + return 0; +} + static const struct xfrm_type esp_type = { .description = "ESP4", @@ -685,11 +692,12 @@ static const struct xfrm_type esp_type = .output = esp_output }; -static const struct net_protocol esp4_protocol = { +static struct xfrm4_protocol esp4_protocol = { .handler = xfrm4_rcv, + .input_handler = xfrm_input, + .cb_handler = esp4_rcv_cb, .err_handler = esp4_err, - .no_policy = 1, - .netns_ok = 1, + .priority = 0, }; static int __init esp4_init(void) @@ -698,7 +706,7 @@ static int __init esp4_init(void) pr_info("%s: can't add xfrm type\n", __func__); return -EAGAIN; } - if (inet_add_protocol(&esp4_protocol, IPPROTO_ESP) < 0) { + if (xfrm4_protocol_register(&esp4_protocol, IPPROTO_ESP) < 0) { pr_info("%s: can't add protocol\n", __func__); xfrm_unregister_type(&esp_type, AF_INET); return -EAGAIN; @@ -708,7 +716,7 @@ static int __init esp4_init(void) static void __exit esp4_fini(void) { - if (inet_del_protocol(&esp4_protocol, IPPROTO_ESP) < 0) + if (xfrm4_protocol_deregister(&esp4_protocol, IPPROTO_ESP) < 0) pr_info("%s: can't remove protocol\n", __func__); if (xfrm_unregister_type(&esp_type, AF_INET) < 0) pr_info("%s: can't remove xfrm type\n", __func__); diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index e9f1217a8afd..be8abe73bb9f 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -39,6 +39,71 @@ #include <net/route.h> #include <net/xfrm.h> +static bool ip_may_fragment(const struct sk_buff *skb) +{ + return unlikely((ip_hdr(skb)->frag_off & htons(IP_DF)) == 0) || + !skb->local_df; +} + +static bool ip_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu) +{ + if (skb->len <= mtu || skb->local_df) + return false; + + if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu) + return false; + + return true; +} + +static bool ip_gso_exceeds_dst_mtu(const struct sk_buff *skb) +{ + unsigned int mtu; + + if (skb->local_df || !skb_is_gso(skb)) + return false; + + mtu = ip_dst_mtu_maybe_forward(skb_dst(skb), true); + + /* if seglen > mtu, do software segmentation for IP fragmentation on + * output. DF bit cannot be set since ip_forward would have sent + * icmp error. + */ + return skb_gso_network_seglen(skb) > mtu; +} + +/* called if GSO skb needs to be fragmented on forward */ +static int ip_forward_finish_gso(struct sk_buff *skb) +{ + struct dst_entry *dst = skb_dst(skb); + netdev_features_t features; + struct sk_buff *segs; + int ret = 0; + + features = netif_skb_dev_features(skb, dst->dev); + segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK); + if (IS_ERR(segs)) { + kfree_skb(skb); + return -ENOMEM; + } + + consume_skb(skb); + + do { + struct sk_buff *nskb = segs->next; + int err; + + segs->next = NULL; + err = dst_output(segs); + + if (err && ret == 0) + ret = err; + segs = nskb; + } while (segs); + + return ret; +} + static int ip_forward_finish(struct sk_buff *skb) { struct ip_options *opt = &(IPCB(skb)->opt); @@ -49,6 +114,9 @@ static int ip_forward_finish(struct sk_buff *skb) if (unlikely(opt->optlen)) ip_forward_options(skb); + if (ip_gso_exceeds_dst_mtu(skb)) + return ip_forward_finish_gso(skb); + return dst_output(skb); } @@ -59,6 +127,10 @@ int ip_forward(struct sk_buff *skb) struct rtable *rt; /* Route we use */ struct ip_options *opt = &(IPCB(skb)->opt); + /* that should never happen */ + if (skb->pkt_type != PACKET_HOST) + goto drop; + if (skb_warn_if_lro(skb)) goto drop; @@ -68,9 +140,6 @@ int ip_forward(struct sk_buff *skb) if (IPCB(skb)->opt.router_alert && ip_call_ra_chain(skb)) return NET_RX_SUCCESS; - if (skb->pkt_type != PACKET_HOST) - goto drop; - skb_forward_csum(skb); /* @@ -91,8 +160,7 @@ int ip_forward(struct sk_buff *skb) IPCB(skb)->flags |= IPSKB_FORWARDED; mtu = ip_dst_mtu_maybe_forward(&rt->dst, true); - if (unlikely(skb->len > mtu && !skb_is_gso(skb) && - (ip_hdr(skb)->frag_off & htons(IP_DF))) && !skb->local_df) { + if (!ip_may_fragment(skb) && ip_exceeds_mtu(skb, mtu)) { IP_INC_STATS(dev_net(rt->dst.dev), IPSTATS_MIB_FRAGFAILS); icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 8971780aec7c..1a0755fea491 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -422,9 +422,6 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from) to->tc_index = from->tc_index; #endif nf_copy(to, from); -#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) - to->nf_trace = from->nf_trace; -#endif #if defined(CONFIG_IP_VS) || defined(CONFIG_IP_VS_MODULE) to->ipvs_property = from->ipvs_property; #endif @@ -449,7 +446,6 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) __be16 not_last_frag; struct rtable *rt = skb_rtable(skb); int err = 0; - bool forwarding = IPCB(skb)->flags & IPSKB_FORWARDED; dev = rt->dst.dev; @@ -459,7 +455,7 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) iph = ip_hdr(skb); - mtu = ip_dst_mtu_maybe_forward(&rt->dst, forwarding); + mtu = ip_skb_dst_mtu(skb); if (unlikely(((iph->frag_off & htons(IP_DF)) && !skb->local_df) || (IPCB(skb)->frag_max_size && IPCB(skb)->frag_max_size > mtu))) { @@ -825,8 +821,7 @@ static int __ip_append_data(struct sock *sk, fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0); maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen; - maxnonfragsize = (inet->pmtudisc >= IP_PMTUDISC_DO) ? - mtu : 0xFFFF; + maxnonfragsize = ip_sk_local_df(sk) ? 0xFFFF : mtu; if (cork->length + length > maxnonfragsize - fragheaderlen) { ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport, @@ -1149,8 +1144,7 @@ ssize_t ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page, fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0); maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen; - maxnonfragsize = (inet->pmtudisc >= IP_PMTUDISC_DO) ? - mtu : 0xFFFF; + maxnonfragsize = ip_sk_local_df(sk) ? 0xFFFF : mtu; if (cork->length + size > maxnonfragsize - fragheaderlen) { ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport, @@ -1311,8 +1305,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk, * to fragment the frame generated here. No matter, what transforms * how transforms change size of the packet, it will come out. */ - if (inet->pmtudisc < IP_PMTUDISC_DO) - skb->local_df = 1; + skb->local_df = ip_sk_local_df(sk); /* DF bit is set when we want to see DF on outgoing frames. * If local_df is set too, we still allow to fragment this frame diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 580dd96666e0..64741b938632 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -186,7 +186,8 @@ void ip_cmsg_recv(struct msghdr *msg, struct sk_buff *skb) } EXPORT_SYMBOL(ip_cmsg_recv); -int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc) +int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc, + bool allow_ipv6) { int err, val; struct cmsghdr *cmsg; @@ -194,6 +195,22 @@ int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc) for (cmsg = CMSG_FIRSTHDR(msg); cmsg; cmsg = CMSG_NXTHDR(msg, cmsg)) { if (!CMSG_OK(msg, cmsg)) return -EINVAL; +#if defined(CONFIG_IPV6) + if (allow_ipv6 && + cmsg->cmsg_level == SOL_IPV6 && + cmsg->cmsg_type == IPV6_PKTINFO) { + struct in6_pktinfo *src_info; + + if (cmsg->cmsg_len < CMSG_LEN(sizeof(*src_info))) + return -EINVAL; + src_info = (struct in6_pktinfo *)CMSG_DATA(cmsg); + if (!ipv6_addr_v4mapped(&src_info->ipi6_addr)) + return -EINVAL; + ipc->oif = src_info->ipi6_ifindex; + ipc->addr = src_info->ipi6_addr.s6_addr32[3]; + continue; + } +#endif if (cmsg->cmsg_level != SOL_IP) continue; switch (cmsg->cmsg_type) { @@ -626,7 +643,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, inet->nodefrag = val ? 1 : 0; break; case IP_MTU_DISCOVER: - if (val < IP_PMTUDISC_DONT || val > IP_PMTUDISC_INTERFACE) + if (val < IP_PMTUDISC_DONT || val > IP_PMTUDISC_OMIT) goto e_inval; inet->pmtudisc = val; break; diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index bd28f386bd02..66aaf506fbef 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -93,83 +93,32 @@ static void tunnel_dst_reset(struct ip_tunnel *t) tunnel_dst_set(t, NULL); } -static void tunnel_dst_reset_all(struct ip_tunnel *t) +void ip_tunnel_dst_reset_all(struct ip_tunnel *t) { int i; for_each_possible_cpu(i) __tunnel_dst_set(per_cpu_ptr(t->dst_cache, i), NULL); } +EXPORT_SYMBOL(ip_tunnel_dst_reset_all); -static struct dst_entry *tunnel_dst_get(struct ip_tunnel *t) +static struct rtable *tunnel_rtable_get(struct ip_tunnel *t, u32 cookie) { struct dst_entry *dst; rcu_read_lock(); dst = rcu_dereference(this_cpu_ptr(t->dst_cache)->dst); - if (dst) + if (dst) { + if (dst->obsolete && dst->ops->check(dst, cookie) == NULL) { + rcu_read_unlock(); + tunnel_dst_reset(t); + return NULL; + } dst_hold(dst); - rcu_read_unlock(); - return dst; -} - -static struct dst_entry *tunnel_dst_check(struct ip_tunnel *t, u32 cookie) -{ - struct dst_entry *dst = tunnel_dst_get(t); - - if (dst && dst->obsolete && dst->ops->check(dst, cookie) == NULL) { - tunnel_dst_reset(t); - return NULL; } - - return dst; -} - -/* Often modified stats are per cpu, other are shared (netdev->stats) */ -struct rtnl_link_stats64 *ip_tunnel_get_stats64(struct net_device *dev, - struct rtnl_link_stats64 *tot) -{ - int i; - - for_each_possible_cpu(i) { - const struct pcpu_sw_netstats *tstats = - per_cpu_ptr(dev->tstats, i); - u64 rx_packets, rx_bytes, tx_packets, tx_bytes; - unsigned int start; - - do { - start = u64_stats_fetch_begin_bh(&tstats->syncp); - rx_packets = tstats->rx_packets; - tx_packets = tstats->tx_packets; - rx_bytes = tstats->rx_bytes; - tx_bytes = tstats->tx_bytes; - } while (u64_stats_fetch_retry_bh(&tstats->syncp, start)); - - tot->rx_packets += rx_packets; - tot->tx_packets += tx_packets; - tot->rx_bytes += rx_bytes; - tot->tx_bytes += tx_bytes; - } - - tot->multicast = dev->stats.multicast; - - tot->rx_crc_errors = dev->stats.rx_crc_errors; - tot->rx_fifo_errors = dev->stats.rx_fifo_errors; - tot->rx_length_errors = dev->stats.rx_length_errors; - tot->rx_frame_errors = dev->stats.rx_frame_errors; - tot->rx_errors = dev->stats.rx_errors; - - tot->tx_fifo_errors = dev->stats.tx_fifo_errors; - tot->tx_carrier_errors = dev->stats.tx_carrier_errors; - tot->tx_dropped = dev->stats.tx_dropped; - tot->tx_aborted_errors = dev->stats.tx_aborted_errors; - tot->tx_errors = dev->stats.tx_errors; - - tot->collisions = dev->stats.collisions; - - return tot; + rcu_read_unlock(); + return (struct rtable *)dst; } -EXPORT_SYMBOL_GPL(ip_tunnel_get_stats64); static bool ip_tunnel_key_match(const struct ip_tunnel_parm *p, __be16 flags, __be32 key) @@ -286,13 +235,17 @@ static struct hlist_head *ip_bucket(struct ip_tunnel_net *itn, { unsigned int h; __be32 remote; + __be32 i_key = parms->i_key; if (parms->iph.daddr && !ipv4_is_multicast(parms->iph.daddr)) remote = parms->iph.daddr; else remote = 0; - h = ip_tunnel_hash(parms->i_key, remote); + if (!(parms->i_flags & TUNNEL_KEY) && (parms->i_flags & VTI_ISVTI)) + i_key = 0; + + h = ip_tunnel_hash(i_key, remote); return &itn->tunnels[h]; } @@ -449,7 +402,7 @@ static struct ip_tunnel *ip_tunnel_create(struct net *net, fbt = netdev_priv(itn->fb_tunnel_dev); dev = __ip_tunnel_create(net, itn->fb_tunnel_dev->rtnl_link_ops, parms); if (IS_ERR(dev)) - return NULL; + return ERR_CAST(dev); dev->mtu = ip_tunnel_bind_dev(dev); @@ -584,7 +537,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi4 fl4; u8 tos, ttl; __be16 df; - struct rtable *rt = NULL; /* Route to the other host */ + struct rtable *rt; /* Route to the other host */ unsigned int max_headroom; /* The extra header space needed */ __be32 dst; int err; @@ -657,8 +610,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, init_tunnel_flow(&fl4, protocol, dst, tnl_params->saddr, tunnel->parms.o_key, RT_TOS(tos), tunnel->parms.link); - if (connected) - rt = (struct rtable *)tunnel_dst_check(tunnel, 0); + rt = connected ? tunnel_rtable_get(tunnel, 0) : NULL; if (!rt) { rt = ip_route_output_key(tunnel->net, &fl4); @@ -766,7 +718,7 @@ static void ip_tunnel_update(struct ip_tunnel_net *itn, if (set_mtu) dev->mtu = mtu; } - tunnel_dst_reset_all(t); + ip_tunnel_dst_reset_all(t); netdev_state_change(dev); } @@ -803,9 +755,13 @@ int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd) t = ip_tunnel_find(itn, p, itn->fb_tunnel_dev->type); - if (!t && (cmd == SIOCADDTUNNEL)) + if (!t && (cmd == SIOCADDTUNNEL)) { t = ip_tunnel_create(net, itn, p); - + if (IS_ERR(t)) { + err = PTR_ERR(t); + break; + } + } if (dev != itn->fb_tunnel_dev && cmd == SIOCCHGTUNNEL) { if (t != NULL) { if (t->dev != dev) { @@ -832,8 +788,9 @@ int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd) if (t) { err = 0; ip_tunnel_update(itn, t, dev, p, true); - } else - err = (cmd == SIOCADDTUNNEL ? -ENOBUFS : -ENOENT); + } else { + err = -ENOENT; + } break; case SIOCDELTUNNEL: @@ -1048,19 +1005,13 @@ int ip_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct iphdr *iph = &tunnel->parms.iph; - int i, err; + int err; dev->destructor = ip_tunnel_dev_free; - dev->tstats = alloc_percpu(struct pcpu_sw_netstats); + dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); if (!dev->tstats) return -ENOMEM; - for_each_possible_cpu(i) { - struct pcpu_sw_netstats *ipt_stats; - ipt_stats = per_cpu_ptr(dev->tstats, i); - u64_stats_init(&ipt_stats->syncp); - } - tunnel->dst_cache = alloc_percpu(struct ip_tunnel_dst); if (!tunnel->dst_cache) { free_percpu(dev->tstats); @@ -1095,7 +1046,7 @@ void ip_tunnel_uninit(struct net_device *dev) if (itn->fb_tunnel_dev != dev) ip_tunnel_del(netdev_priv(dev)); - tunnel_dst_reset_all(tunnel); + ip_tunnel_dst_reset_all(tunnel); } EXPORT_SYMBOL_GPL(ip_tunnel_uninit); diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 6156f4ef5e91..6f847dd56dbc 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -108,7 +108,6 @@ int iptunnel_pull_header(struct sk_buff *skb, int hdr_len, __be16 inner_proto) nf_reset(skb); secpath_reset(skb); skb_clear_hash_if_not_l4(skb); - skb_dst_drop(skb); skb->vlan_tci = 0; skb_set_queue_mapping(skb, 0); skb->pkt_type = PACKET_HOST; @@ -148,3 +147,49 @@ error: return ERR_PTR(err); } EXPORT_SYMBOL_GPL(iptunnel_handle_offloads); + +/* Often modified stats are per cpu, other are shared (netdev->stats) */ +struct rtnl_link_stats64 *ip_tunnel_get_stats64(struct net_device *dev, + struct rtnl_link_stats64 *tot) +{ + int i; + + for_each_possible_cpu(i) { + const struct pcpu_sw_netstats *tstats = + per_cpu_ptr(dev->tstats, i); + u64 rx_packets, rx_bytes, tx_packets, tx_bytes; + unsigned int start; + + do { + start = u64_stats_fetch_begin_bh(&tstats->syncp); + rx_packets = tstats->rx_packets; + tx_packets = tstats->tx_packets; + rx_bytes = tstats->rx_bytes; + tx_bytes = tstats->tx_bytes; + } while (u64_stats_fetch_retry_bh(&tstats->syncp, start)); + + tot->rx_packets += rx_packets; + tot->tx_packets += tx_packets; + tot->rx_bytes += rx_bytes; + tot->tx_bytes += tx_bytes; + } + + tot->multicast = dev->stats.multicast; + + tot->rx_crc_errors = dev->stats.rx_crc_errors; + tot->rx_fifo_errors = dev->stats.rx_fifo_errors; + tot->rx_length_errors = dev->stats.rx_length_errors; + tot->rx_frame_errors = dev->stats.rx_frame_errors; + tot->rx_errors = dev->stats.rx_errors; + + tot->tx_fifo_errors = dev->stats.tx_fifo_errors; + tot->tx_carrier_errors = dev->stats.tx_carrier_errors; + tot->tx_dropped = dev->stats.tx_dropped; + tot->tx_aborted_errors = dev->stats.tx_aborted_errors; + tot->tx_errors = dev->stats.tx_errors; + + tot->collisions = dev->stats.collisions; + + return tot; +} +EXPORT_SYMBOL_GPL(ip_tunnel_get_stats64); diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 48eafae51769..687ddef4e574 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -34,6 +34,7 @@ #include <linux/init.h> #include <linux/netfilter_ipv4.h> #include <linux/if_ether.h> +#include <linux/icmpv6.h> #include <net/sock.h> #include <net/ip.h> @@ -49,8 +50,8 @@ static struct rtnl_link_ops vti_link_ops __read_mostly; static int vti_net_id __read_mostly; static int vti_tunnel_init(struct net_device *dev); -/* We dont digest the packet therefore let the packet pass */ -static int vti_rcv(struct sk_buff *skb) +static int vti_input(struct sk_buff *skb, int nexthdr, __be32 spi, + int encap_type) { struct ip_tunnel *tunnel; const struct iphdr *iph = ip_hdr(skb); @@ -60,79 +61,120 @@ static int vti_rcv(struct sk_buff *skb) tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY, iph->saddr, iph->daddr, 0); if (tunnel != NULL) { - struct pcpu_sw_netstats *tstats; - u32 oldmark = skb->mark; - int ret; - - - /* temporarily mark the skb with the tunnel o_key, to - * only match policies with this mark. - */ - skb->mark = be32_to_cpu(tunnel->parms.o_key); - ret = xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb); - skb->mark = oldmark; - if (!ret) - return -1; - - tstats = this_cpu_ptr(tunnel->dev->tstats); - u64_stats_update_begin(&tstats->syncp); - tstats->rx_packets++; - tstats->rx_bytes += skb->len; - u64_stats_update_end(&tstats->syncp); - - secpath_reset(skb); - skb->dev = tunnel->dev; + if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) + goto drop; + + XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = tunnel; + skb->mark = be32_to_cpu(tunnel->parms.i_key); + + return xfrm_input(skb, nexthdr, spi, encap_type); + } + + return -EINVAL; +drop: + kfree_skb(skb); + return 0; +} + +static int vti_rcv(struct sk_buff *skb) +{ + XFRM_SPI_SKB_CB(skb)->family = AF_INET; + XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr); + + return vti_input(skb, ip_hdr(skb)->protocol, 0, 0); +} + +static int vti_rcv_cb(struct sk_buff *skb, int err) +{ + unsigned short family; + struct net_device *dev; + struct pcpu_sw_netstats *tstats; + struct xfrm_state *x; + struct ip_tunnel *tunnel = XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4; + + if (!tunnel) return 1; + + dev = tunnel->dev; + + if (err) { + dev->stats.rx_errors++; + dev->stats.rx_dropped++; + + return 0; } - return -1; + x = xfrm_input_state(skb); + family = x->inner_mode->afinfo->family; + + if (!xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family)) + return -EPERM; + + skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(skb->dev))); + skb->dev = dev; + + tstats = this_cpu_ptr(dev->tstats); + + u64_stats_update_begin(&tstats->syncp); + tstats->rx_packets++; + tstats->rx_bytes += skb->len; + u64_stats_update_end(&tstats->syncp); + + return 0; } -/* This function assumes it is being called from dev_queue_xmit() - * and that skb is filled properly by that function. - */ +static bool vti_state_check(const struct xfrm_state *x, __be32 dst, __be32 src) +{ + xfrm_address_t *daddr = (xfrm_address_t *)&dst; + xfrm_address_t *saddr = (xfrm_address_t *)&src; -static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) + /* if there is no transform then this tunnel is not functional. + * Or if the xfrm is not mode tunnel. + */ + if (!x || x->props.mode != XFRM_MODE_TUNNEL || + x->props.family != AF_INET) + return false; + + if (!dst) + return xfrm_addr_equal(saddr, &x->props.saddr, AF_INET); + + if (!xfrm_state_addr_check(x, daddr, saddr, AF_INET)) + return false; + + return true; +} + +static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev, + struct flowi *fl) { struct ip_tunnel *tunnel = netdev_priv(dev); - struct iphdr *tiph = &tunnel->parms.iph; - u8 tos; - struct rtable *rt; /* Route to the other host */ + struct ip_tunnel_parm *parms = &tunnel->parms; + struct dst_entry *dst = skb_dst(skb); struct net_device *tdev; /* Device to other host */ - struct iphdr *old_iph = ip_hdr(skb); - __be32 dst = tiph->daddr; - struct flowi4 fl4; int err; - if (skb->protocol != htons(ETH_P_IP)) - goto tx_error; - - tos = old_iph->tos; + if (!dst) { + dev->stats.tx_carrier_errors++; + goto tx_error_icmp; + } - memset(&fl4, 0, sizeof(fl4)); - flowi4_init_output(&fl4, tunnel->parms.link, - be32_to_cpu(tunnel->parms.o_key), RT_TOS(tos), - RT_SCOPE_UNIVERSE, - IPPROTO_IPIP, 0, - dst, tiph->saddr, 0, 0); - rt = ip_route_output_key(dev_net(dev), &fl4); - if (IS_ERR(rt)) { + dst_hold(dst); + dst = xfrm_lookup(tunnel->net, dst, fl, NULL, 0); + if (IS_ERR(dst)) { dev->stats.tx_carrier_errors++; goto tx_error_icmp; } - /* if there is no transform then this tunnel is not functional. - * Or if the xfrm is not mode tunnel. - */ - if (!rt->dst.xfrm || - rt->dst.xfrm->props.mode != XFRM_MODE_TUNNEL) { + + if (!vti_state_check(dst->xfrm, parms->iph.daddr, parms->iph.saddr)) { dev->stats.tx_carrier_errors++; - ip_rt_put(rt); + dst_release(dst); goto tx_error_icmp; } - tdev = rt->dst.dev; + + tdev = dst->dev; if (tdev == dev) { - ip_rt_put(rt); + dst_release(dst); dev->stats.collisions++; goto tx_error; } @@ -146,10 +188,8 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) tunnel->err_count = 0; } - memset(IPCB(skb), 0, sizeof(*IPCB(skb))); - skb_dst_drop(skb); - skb_dst_set(skb, &rt->dst); - nf_reset(skb); + skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(dev))); + skb_dst_set(skb, dst); skb->dev = skb_dst(skb)->dev; err = dst_output(skb); @@ -166,6 +206,95 @@ tx_error: return NETDEV_TX_OK; } +/* This function assumes it is being called from dev_queue_xmit() + * and that skb is filled properly by that function. + */ +static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct ip_tunnel *tunnel = netdev_priv(dev); + struct flowi fl; + + memset(&fl, 0, sizeof(fl)); + + skb->mark = be32_to_cpu(tunnel->parms.o_key); + + switch (skb->protocol) { + case htons(ETH_P_IP): + xfrm_decode_session(skb, &fl, AF_INET); + memset(IPCB(skb), 0, sizeof(*IPCB(skb))); + break; + case htons(ETH_P_IPV6): + xfrm_decode_session(skb, &fl, AF_INET6); + memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); + break; + default: + dev->stats.tx_errors++; + dev_kfree_skb(skb); + return NETDEV_TX_OK; + } + + return vti_xmit(skb, dev, &fl); +} + +static int vti4_err(struct sk_buff *skb, u32 info) +{ + __be32 spi; + struct xfrm_state *x; + struct ip_tunnel *tunnel; + struct ip_esp_hdr *esph; + struct ip_auth_hdr *ah ; + struct ip_comp_hdr *ipch; + struct net *net = dev_net(skb->dev); + const struct iphdr *iph = (const struct iphdr *)skb->data; + int protocol = iph->protocol; + struct ip_tunnel_net *itn = net_generic(net, vti_net_id); + + tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY, + iph->daddr, iph->saddr, 0); + if (!tunnel) + return -1; + + switch (protocol) { + case IPPROTO_ESP: + esph = (struct ip_esp_hdr *)(skb->data+(iph->ihl<<2)); + spi = esph->spi; + break; + case IPPROTO_AH: + ah = (struct ip_auth_hdr *)(skb->data+(iph->ihl<<2)); + spi = ah->spi; + break; + case IPPROTO_COMP: + ipch = (struct ip_comp_hdr *)(skb->data+(iph->ihl<<2)); + spi = htonl(ntohs(ipch->cpi)); + break; + default: + return 0; + } + + switch (icmp_hdr(skb)->type) { + case ICMP_DEST_UNREACH: + if (icmp_hdr(skb)->code != ICMP_FRAG_NEEDED) + return 0; + case ICMP_REDIRECT: + break; + default: + return 0; + } + + x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr, + spi, protocol, AF_INET); + if (!x) + return 0; + + if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) + ipv4_update_pmtu(skb, net, info, 0, 0, protocol, 0); + else + ipv4_redirect(skb, net, 0, 0, protocol, 0); + xfrm_state_put(x); + + return 0; +} + static int vti_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { @@ -181,12 +310,13 @@ vti_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) return -EINVAL; } + p.i_flags |= VTI_ISVTI; err = ip_tunnel_ioctl(dev, &p, cmd); if (err) return err; if (cmd != SIOCDELTUNNEL) { - p.i_flags |= GRE_KEY | VTI_ISVTI; + p.i_flags |= GRE_KEY; p.o_flags |= GRE_KEY; } @@ -224,7 +354,6 @@ static int vti_tunnel_init(struct net_device *dev) dev->flags = IFF_NOARP; dev->iflink = 0; dev->addr_len = 4; - dev->features |= NETIF_F_NETNS_LOCAL; dev->features |= NETIF_F_LLTX; dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; @@ -241,9 +370,28 @@ static void __net_init vti_fb_tunnel_init(struct net_device *dev) iph->ihl = 5; } -static struct xfrm_tunnel_notifier vti_handler __read_mostly = { +static struct xfrm4_protocol vti_esp4_protocol __read_mostly = { .handler = vti_rcv, - .priority = 1, + .input_handler = vti_input, + .cb_handler = vti_rcv_cb, + .err_handler = vti4_err, + .priority = 100, +}; + +static struct xfrm4_protocol vti_ah4_protocol __read_mostly = { + .handler = vti_rcv, + .input_handler = vti_input, + .cb_handler = vti_rcv_cb, + .err_handler = vti4_err, + .priority = 100, +}; + +static struct xfrm4_protocol vti_ipcomp4_protocol __read_mostly = { + .handler = vti_rcv, + .input_handler = vti_input, + .cb_handler = vti_rcv_cb, + .err_handler = vti4_err, + .priority = 100, }; static int __net_init vti_init_net(struct net *net) @@ -287,6 +435,8 @@ static void vti_netlink_parms(struct nlattr *data[], if (!data) return; + parms->i_flags = VTI_ISVTI; + if (data[IFLA_VTI_LINK]) parms->link = nla_get_u32(data[IFLA_VTI_LINK]); @@ -382,10 +532,31 @@ static int __init vti_init(void) err = register_pernet_device(&vti_net_ops); if (err < 0) return err; - err = xfrm4_mode_tunnel_input_register(&vti_handler); + err = xfrm4_protocol_register(&vti_esp4_protocol, IPPROTO_ESP); + if (err < 0) { + unregister_pernet_device(&vti_net_ops); + pr_info("vti init: can't register tunnel\n"); + + return err; + } + + err = xfrm4_protocol_register(&vti_ah4_protocol, IPPROTO_AH); + if (err < 0) { + xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP); + unregister_pernet_device(&vti_net_ops); + pr_info("vti init: can't register tunnel\n"); + + return err; + } + + err = xfrm4_protocol_register(&vti_ipcomp4_protocol, IPPROTO_COMP); if (err < 0) { + xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH); + xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP); unregister_pernet_device(&vti_net_ops); pr_info("vti init: can't register tunnel\n"); + + return err; } err = rtnl_link_register(&vti_link_ops); @@ -395,7 +566,9 @@ static int __init vti_init(void) return err; rtnl_link_failed: - xfrm4_mode_tunnel_input_deregister(&vti_handler); + xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP); + xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH); + xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP); unregister_pernet_device(&vti_net_ops); return err; } @@ -403,8 +576,13 @@ rtnl_link_failed: static void __exit vti_fini(void) { rtnl_link_unregister(&vti_link_ops); - if (xfrm4_mode_tunnel_input_deregister(&vti_handler)) + if (xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP)) pr_info("vti close: can't deregister tunnel\n"); + if (xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH)) + pr_info("vti close: can't deregister tunnel\n"); + if (xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP)) + pr_info("vti close: can't deregister tunnel\n"); + unregister_pernet_device(&vti_net_ops); } diff --git a/net/ipv4/ipcomp.c b/net/ipv4/ipcomp.c index 826be4cb482a..c0855d50a3fa 100644 --- a/net/ipv4/ipcomp.c +++ b/net/ipv4/ipcomp.c @@ -23,7 +23,7 @@ #include <net/protocol.h> #include <net/sock.h> -static void ipcomp4_err(struct sk_buff *skb, u32 info) +static int ipcomp4_err(struct sk_buff *skb, u32 info) { struct net *net = dev_net(skb->dev); __be32 spi; @@ -34,24 +34,26 @@ static void ipcomp4_err(struct sk_buff *skb, u32 info) switch (icmp_hdr(skb)->type) { case ICMP_DEST_UNREACH: if (icmp_hdr(skb)->code != ICMP_FRAG_NEEDED) - return; + return 0; case ICMP_REDIRECT: break; default: - return; + return 0; } spi = htonl(ntohs(ipch->cpi)); x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr, spi, IPPROTO_COMP, AF_INET); if (!x) - return; + return 0; if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_COMP, 0); else ipv4_redirect(skb, net, 0, 0, IPPROTO_COMP, 0); xfrm_state_put(x); + + return 0; } /* We always hold one tunnel user reference to indicate a tunnel */ @@ -147,6 +149,11 @@ out: return err; } +static int ipcomp4_rcv_cb(struct sk_buff *skb, int err) +{ + return 0; +} + static const struct xfrm_type ipcomp_type = { .description = "IPCOMP4", .owner = THIS_MODULE, @@ -157,11 +164,12 @@ static const struct xfrm_type ipcomp_type = { .output = ipcomp_output }; -static const struct net_protocol ipcomp4_protocol = { +static struct xfrm4_protocol ipcomp4_protocol = { .handler = xfrm4_rcv, + .input_handler = xfrm_input, + .cb_handler = ipcomp4_rcv_cb, .err_handler = ipcomp4_err, - .no_policy = 1, - .netns_ok = 1, + .priority = 0, }; static int __init ipcomp4_init(void) @@ -170,7 +178,7 @@ static int __init ipcomp4_init(void) pr_info("%s: can't add xfrm type\n", __func__); return -EAGAIN; } - if (inet_add_protocol(&ipcomp4_protocol, IPPROTO_COMP) < 0) { + if (xfrm4_protocol_register(&ipcomp4_protocol, IPPROTO_COMP) < 0) { pr_info("%s: can't add protocol\n", __func__); xfrm_unregister_type(&ipcomp_type, AF_INET); return -EAGAIN; @@ -180,7 +188,7 @@ static int __init ipcomp4_init(void) static void __exit ipcomp4_fini(void) { - if (inet_del_protocol(&ipcomp4_protocol, IPPROTO_COMP) < 0) + if (xfrm4_protocol_deregister(&ipcomp4_protocol, IPPROTO_COMP) < 0) pr_info("%s: can't remove protocol\n", __func__); if (xfrm_unregister_type(&ipcomp_type, AF_INET) < 0) pr_info("%s: can't remove xfrm type\n", __func__); diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index efa1138fa523..b3e86ea7b71b 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -273,7 +273,7 @@ static int __init ic_open_devs(void) msleep(1); - if time_before(jiffies, next_msg) + if (time_before(jiffies, next_msg)) continue; elapsed = jiffies_to_msecs(jiffies - start); diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index 81c6910cfa92..a26ce035e3fa 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -61,6 +61,11 @@ config NFT_CHAIN_NAT_IPV4 packet transformations such as the source, destination address and source and destination ports. +config NFT_REJECT_IPV4 + depends on NF_TABLES_IPV4 + default NFT_REJECT + tristate + config NF_TABLES_ARP depends on NF_TABLES tristate "ARP nf_tables support" diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile index c16be9d58420..90b82405331e 100644 --- a/net/ipv4/netfilter/Makefile +++ b/net/ipv4/netfilter/Makefile @@ -30,6 +30,7 @@ obj-$(CONFIG_NF_NAT_PROTO_GRE) += nf_nat_proto_gre.o obj-$(CONFIG_NF_TABLES_IPV4) += nf_tables_ipv4.o obj-$(CONFIG_NFT_CHAIN_ROUTE_IPV4) += nft_chain_route_ipv4.o obj-$(CONFIG_NFT_CHAIN_NAT_IPV4) += nft_chain_nat_ipv4.o +obj-$(CONFIG_NFT_REJECT_IPV4) += nft_reject_ipv4.o obj-$(CONFIG_NF_TABLES_ARP) += nf_tables_arp.o # generic IP tables diff --git a/net/ipv4/netfilter/nf_nat_h323.c b/net/ipv4/netfilter/nf_nat_h323.c index 9eea059dd621..574f7ebba0b6 100644 --- a/net/ipv4/netfilter/nf_nat_h323.c +++ b/net/ipv4/netfilter/nf_nat_h323.c @@ -229,7 +229,10 @@ static int nat_rtp_rtcp(struct sk_buff *skb, struct nf_conn *ct, ret = nf_ct_expect_related(rtcp_exp); if (ret == 0) break; - else if (ret != -EBUSY) { + else if (ret == -EBUSY) { + nf_ct_unexpect_related(rtp_exp); + continue; + } else if (ret < 0) { nf_ct_unexpect_related(rtp_exp); nated_port = 0; break; diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic.c b/net/ipv4/netfilter/nf_nat_snmp_basic.c index d551e31b416e..7c676671329d 100644 --- a/net/ipv4/netfilter/nf_nat_snmp_basic.c +++ b/net/ipv4/netfilter/nf_nat_snmp_basic.c @@ -1198,8 +1198,8 @@ static int snmp_translate(struct nf_conn *ct, map.to = NOCT1(&ct->tuplehash[!dir].tuple.dst.u3.ip); } else { /* DNAT replies */ - map.from = NOCT1(&ct->tuplehash[dir].tuple.src.u3.ip); - map.to = NOCT1(&ct->tuplehash[!dir].tuple.dst.u3.ip); + map.from = NOCT1(&ct->tuplehash[!dir].tuple.src.u3.ip); + map.to = NOCT1(&ct->tuplehash[dir].tuple.dst.u3.ip); } if (map.from == map.to) diff --git a/net/ipv4/netfilter/nft_reject_ipv4.c b/net/ipv4/netfilter/nft_reject_ipv4.c new file mode 100644 index 000000000000..e79718a382f2 --- /dev/null +++ b/net/ipv4/netfilter/nft_reject_ipv4.c @@ -0,0 +1,75 @@ +/* + * Copyright (c) 2008-2009 Patrick McHardy <kaber@trash.net> + * Copyright (c) 2013 Eric Leblond <eric@regit.org> + * + * 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. + * + * Development of this code funded by Astaro AG (http://www.astaro.com/) + */ + +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/netlink.h> +#include <linux/netfilter.h> +#include <linux/netfilter/nf_tables.h> +#include <net/netfilter/nf_tables.h> +#include <net/icmp.h> +#include <net/netfilter/ipv4/nf_reject.h> +#include <net/netfilter/nft_reject.h> + +void nft_reject_ipv4_eval(const struct nft_expr *expr, + struct nft_data data[NFT_REG_MAX + 1], + const struct nft_pktinfo *pkt) +{ + struct nft_reject *priv = nft_expr_priv(expr); + + switch (priv->type) { + case NFT_REJECT_ICMP_UNREACH: + nf_send_unreach(pkt->skb, priv->icmp_code); + break; + case NFT_REJECT_TCP_RST: + nf_send_reset(pkt->skb, pkt->ops->hooknum); + break; + } + + data[NFT_REG_VERDICT].verdict = NF_DROP; +} +EXPORT_SYMBOL_GPL(nft_reject_ipv4_eval); + +static struct nft_expr_type nft_reject_ipv4_type; +static const struct nft_expr_ops nft_reject_ipv4_ops = { + .type = &nft_reject_ipv4_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_reject)), + .eval = nft_reject_ipv4_eval, + .init = nft_reject_init, + .dump = nft_reject_dump, +}; + +static struct nft_expr_type nft_reject_ipv4_type __read_mostly = { + .family = NFPROTO_IPV4, + .name = "reject", + .ops = &nft_reject_ipv4_ops, + .policy = nft_reject_policy, + .maxattr = NFTA_REJECT_MAX, + .owner = THIS_MODULE, +}; + +static int __init nft_reject_ipv4_module_init(void) +{ + return nft_register_expr(&nft_reject_ipv4_type); +} + +static void __exit nft_reject_ipv4_module_exit(void) +{ + nft_unregister_expr(&nft_reject_ipv4_type); +} + +module_init(nft_reject_ipv4_module_init); +module_exit(nft_reject_ipv4_module_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); +MODULE_ALIAS_NFT_AF_EXPR(AF_INET, "reject"); diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 2d11c094296e..f4b19e5dde54 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -727,7 +727,7 @@ static int ping_v4_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m sock_tx_timestamp(sk, &ipc.tx_flags); if (msg->msg_controllen) { - err = ip_cmsg_send(sock_net(sk), msg, &ipc); + err = ip_cmsg_send(sock_net(sk), msg, &ipc, false); if (err) return err; if (ipc.opt) diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index a6c8a80ec9d6..ad737fad6d8b 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -273,6 +273,7 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPChallengeACK", LINUX_MIB_TCPCHALLENGEACK), SNMP_MIB_ITEM("TCPSYNChallenge", LINUX_MIB_TCPSYNCHALLENGE), SNMP_MIB_ITEM("TCPFastOpenActive", LINUX_MIB_TCPFASTOPENACTIVE), + SNMP_MIB_ITEM("TCPFastOpenActiveFail", LINUX_MIB_TCPFASTOPENACTIVEFAIL), SNMP_MIB_ITEM("TCPFastOpenPassive", LINUX_MIB_TCPFASTOPENPASSIVE), SNMP_MIB_ITEM("TCPFastOpenPassiveFail", LINUX_MIB_TCPFASTOPENPASSIVEFAIL), SNMP_MIB_ITEM("TCPFastOpenListenOverflow", LINUX_MIB_TCPFASTOPENLISTENOVERFLOW), @@ -280,6 +281,11 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPSpuriousRtxHostQueues", LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES), SNMP_MIB_ITEM("BusyPollRxPackets", LINUX_MIB_BUSYPOLLRXPACKETS), SNMP_MIB_ITEM("TCPAutoCorking", LINUX_MIB_TCPAUTOCORKING), + SNMP_MIB_ITEM("TCPFromZeroWindowAdv", LINUX_MIB_TCPFROMZEROWINDOWADV), + SNMP_MIB_ITEM("TCPToZeroWindowAdv", LINUX_MIB_TCPTOZEROWINDOWADV), + SNMP_MIB_ITEM("TCPWantZeroWindowAdv", LINUX_MIB_TCPWANTZEROWINDOWADV), + SNMP_MIB_ITEM("TCPSynRetrans", LINUX_MIB_TCPSYNRETRANS), + SNMP_MIB_ITEM("TCPOrigDataSent", LINUX_MIB_TCPORIGDATASENT), SNMP_MIB_SENTINEL }; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index c04518f4850a..a9dbe58bdfe7 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -524,7 +524,7 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, ipc.oif = sk->sk_bound_dev_if; if (msg->msg_controllen) { - err = ip_cmsg_send(sock_net(sk), msg, &ipc); + err = ip_cmsg_send(sock_net(sk), msg, &ipc, false); if (err) goto out; if (ipc.opt) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 25071b48921c..11e4384daaf9 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -697,7 +697,6 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw, out_unlock: spin_unlock_bh(&fnhe_lock); - return; } static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flowi4 *fl4, @@ -1597,6 +1596,7 @@ static int __mkroute_input(struct sk_buff *skb, rth->rt_gateway = 0; rth->rt_uses_gateway = 0; INIT_LIST_HEAD(&rth->rt_uncached); + RT_CACHE_STAT_INC(in_slow_tot); rth->dst.input = ip_forward; rth->dst.output = ip_output; @@ -1695,10 +1695,11 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, fl4.daddr = daddr; fl4.saddr = saddr; err = fib_lookup(net, &fl4, &res); - if (err != 0) + if (err != 0) { + if (!IN_DEV_FORWARD(in_dev)) + err = -EHOSTUNREACH; goto no_route; - - RT_CACHE_STAT_INC(in_slow_tot); + } if (res.type == RTN_BROADCAST) goto brd_input; @@ -1712,8 +1713,10 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, goto local_input; } - if (!IN_DEV_FORWARD(in_dev)) + if (!IN_DEV_FORWARD(in_dev)) { + err = -EHOSTUNREACH; goto no_route; + } if (res.type != RTN_UNICAST) goto martian_destination; @@ -1768,6 +1771,7 @@ local_input: rth->rt_gateway = 0; rth->rt_uses_gateway = 0; INIT_LIST_HEAD(&rth->rt_uncached); + RT_CACHE_STAT_INC(in_slow_tot); if (res.type == RTN_UNREACHABLE) { rth->dst.input= ip_error; rth->dst.error= -err; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 4475b3bb494d..4bd6d52eeffb 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -387,7 +387,7 @@ void tcp_init_sock(struct sock *sk) INIT_LIST_HEAD(&tp->tsq_node); icsk->icsk_rto = TCP_TIMEOUT_INIT; - tp->mdev = TCP_TIMEOUT_INIT; + tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT); /* So many TCP implementations out there (incorrectly) count the * initial SYN frame in their delayed-ACK and congestion control @@ -1044,7 +1044,8 @@ void tcp_free_fastopen_req(struct tcp_sock *tp) } } -static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *size) +static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, + int *copied, size_t size) { struct tcp_sock *tp = tcp_sk(sk); int err, flags; @@ -1059,11 +1060,12 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *size) if (unlikely(tp->fastopen_req == NULL)) return -ENOBUFS; tp->fastopen_req->data = msg; + tp->fastopen_req->size = size; flags = (msg->msg_flags & MSG_DONTWAIT) ? O_NONBLOCK : 0; err = __inet_stream_connect(sk->sk_socket, msg->msg_name, msg->msg_namelen, flags); - *size = tp->fastopen_req->copied; + *copied = tp->fastopen_req->copied; tcp_free_fastopen_req(tp); return err; } @@ -1083,7 +1085,7 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, flags = msg->msg_flags; if (flags & MSG_FASTOPEN) { - err = tcp_sendmsg_fastopen(sk, msg, &copied_syn); + err = tcp_sendmsg_fastopen(sk, msg, &copied_syn, size); if (err == -EINPROGRESS && copied_syn > 0) goto out; else if (err) @@ -2229,7 +2231,7 @@ adjudge_to_death: /* This is a (useful) BSD violating of the RFC. There is a * problem with TCP as specified in that the other end could * keep a socket open forever with no application left this end. - * We use a 3 minute timeout (about the same as BSD) then kill + * We use a 1 minute timeout (about the same as BSD) then kill * our end. If they send after that then tough - BUT: long enough * that we won't make the old 4*rto = almost no time - whoops * reset mistake. @@ -2339,7 +2341,7 @@ int tcp_disconnect(struct sock *sk, int flags) sk->sk_shutdown = 0; sock_reset_flag(sk, SOCK_DONE); - tp->srtt = 0; + tp->srtt_us = 0; if ((tp->write_seq += tp->max_window + 2) == 0) tp->write_seq = 1; icsk->icsk_backoff = 0; @@ -2783,8 +2785,8 @@ void tcp_get_info(const struct sock *sk, struct tcp_info *info) info->tcpi_pmtu = icsk->icsk_pmtu_cookie; info->tcpi_rcv_ssthresh = tp->rcv_ssthresh; - info->tcpi_rtt = jiffies_to_usecs(tp->srtt)>>3; - info->tcpi_rttvar = jiffies_to_usecs(tp->mdev)>>2; + info->tcpi_rtt = tp->srtt_us >> 3; + info->tcpi_rttvar = tp->mdev_us >> 2; info->tcpi_snd_ssthresh = tp->snd_ssthresh; info->tcpi_snd_cwnd = tp->snd_cwnd; info->tcpi_advmss = tp->advmss; @@ -2794,6 +2796,11 @@ void tcp_get_info(const struct sock *sk, struct tcp_info *info) info->tcpi_rcv_space = tp->rcvq_space.space; info->tcpi_total_retrans = tp->total_retrans; + + info->tcpi_pacing_rate = sk->sk_pacing_rate != ~0U ? + sk->sk_pacing_rate : ~0ULL; + info->tcpi_max_pacing_rate = sk->sk_max_pacing_rate != ~0U ? + sk->sk_max_pacing_rate : ~0ULL; } EXPORT_SYMBOL_GPL(tcp_get_info); diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index ad37bf18ae4b..2b9464c93b88 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -290,8 +290,7 @@ bool tcp_is_cwnd_limited(const struct sock *sk, u32 in_flight) left = tp->snd_cwnd - in_flight; if (sk_can_gso(sk) && left * sysctl_tcp_tso_win_divisor < tp->snd_cwnd && - left * tp->mss_cache < sk->sk_gso_max_size && - left < sk->sk_gso_max_segs) + left < tp->xmit_size_goal_segs) return true; return left <= tcp_max_tso_deferred_mss(tp); } @@ -362,21 +361,12 @@ u32 tcp_reno_ssthresh(struct sock *sk) } EXPORT_SYMBOL_GPL(tcp_reno_ssthresh); -/* Lower bound on congestion window with halving. */ -u32 tcp_reno_min_cwnd(const struct sock *sk) -{ - const struct tcp_sock *tp = tcp_sk(sk); - return tp->snd_ssthresh/2; -} -EXPORT_SYMBOL_GPL(tcp_reno_min_cwnd); - struct tcp_congestion_ops tcp_reno = { .flags = TCP_CONG_NON_RESTRICTED, .name = "reno", .owner = THIS_MODULE, .ssthresh = tcp_reno_ssthresh, .cong_avoid = tcp_reno_cong_avoid, - .min_cwnd = tcp_reno_min_cwnd, }; /* Initial congestion control used (until SYN) @@ -388,6 +378,5 @@ struct tcp_congestion_ops tcp_init_congestion_ops = { .owner = THIS_MODULE, .ssthresh = tcp_reno_ssthresh, .cong_avoid = tcp_reno_cong_avoid, - .min_cwnd = tcp_reno_min_cwnd, }; EXPORT_SYMBOL_GPL(tcp_init_congestion_ops); diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index 828e4c3ffbaf..8bf224516ba2 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -476,10 +476,6 @@ static int __init cubictcp_register(void) /* divide by bic_scale and by constant Srtt (100ms) */ do_div(cube_factor, bic_scale * 10); - /* hystart needs ms clock resolution */ - if (hystart && HZ < 1000) - cubictcp.flags |= TCP_CONG_RTT_STAMP; - return tcp_register_congestion_control(&cubictcp); } diff --git a/net/ipv4/tcp_highspeed.c b/net/ipv4/tcp_highspeed.c index 8ed9305dfdf4..8b9e7bad77c0 100644 --- a/net/ipv4/tcp_highspeed.c +++ b/net/ipv4/tcp_highspeed.c @@ -162,7 +162,6 @@ static struct tcp_congestion_ops tcp_highspeed __read_mostly = { .init = hstcp_init, .ssthresh = hstcp_ssthresh, .cong_avoid = hstcp_cong_avoid, - .min_cwnd = tcp_reno_min_cwnd, .owner = THIS_MODULE, .name = "highspeed" diff --git a/net/ipv4/tcp_hybla.c b/net/ipv4/tcp_hybla.c index 478fe82611bf..a15a799bf768 100644 --- a/net/ipv4/tcp_hybla.c +++ b/net/ipv4/tcp_hybla.c @@ -21,7 +21,7 @@ struct hybla { u32 rho2; /* Rho * Rho, integer part */ u32 rho_3ls; /* Rho parameter, <<3 */ u32 rho2_7ls; /* Rho^2, <<7 */ - u32 minrtt; /* Minimum smoothed round trip time value seen */ + u32 minrtt_us; /* Minimum smoothed round trip time value seen */ }; /* Hybla reference round trip time (default= 1/40 sec = 25 ms), in ms */ @@ -35,7 +35,9 @@ static inline void hybla_recalc_param (struct sock *sk) { struct hybla *ca = inet_csk_ca(sk); - ca->rho_3ls = max_t(u32, tcp_sk(sk)->srtt / msecs_to_jiffies(rtt0), 8); + ca->rho_3ls = max_t(u32, + tcp_sk(sk)->srtt_us / (rtt0 * USEC_PER_MSEC), + 8U); ca->rho = ca->rho_3ls >> 3; ca->rho2_7ls = (ca->rho_3ls * ca->rho_3ls) << 1; ca->rho2 = ca->rho2_7ls >> 7; @@ -59,7 +61,7 @@ static void hybla_init(struct sock *sk) hybla_recalc_param(sk); /* set minimum rtt as this is the 1st ever seen */ - ca->minrtt = tp->srtt; + ca->minrtt_us = tp->srtt_us; tp->snd_cwnd = ca->rho; } @@ -94,9 +96,9 @@ static void hybla_cong_avoid(struct sock *sk, u32 ack, u32 acked, int is_slowstart = 0; /* Recalculate rho only if this srtt is the lowest */ - if (tp->srtt < ca->minrtt){ + if (tp->srtt_us < ca->minrtt_us) { hybla_recalc_param(sk); - ca->minrtt = tp->srtt; + ca->minrtt_us = tp->srtt_us; } if (!tcp_is_cwnd_limited(sk, in_flight)) @@ -166,7 +168,6 @@ static void hybla_cong_avoid(struct sock *sk, u32 ack, u32 acked, static struct tcp_congestion_ops tcp_hybla __read_mostly = { .init = hybla_init, .ssthresh = tcp_reno_ssthresh, - .min_cwnd = tcp_reno_min_cwnd, .cong_avoid = hybla_cong_avoid, .set_state = hybla_state, diff --git a/net/ipv4/tcp_illinois.c b/net/ipv4/tcp_illinois.c index e498a62b8f97..863d105e3015 100644 --- a/net/ipv4/tcp_illinois.c +++ b/net/ipv4/tcp_illinois.c @@ -325,10 +325,8 @@ static void tcp_illinois_info(struct sock *sk, u32 ext, } static struct tcp_congestion_ops tcp_illinois __read_mostly = { - .flags = TCP_CONG_RTT_STAMP, .init = tcp_illinois_init, .ssthresh = tcp_illinois_ssthresh, - .min_cwnd = tcp_reno_min_cwnd, .cong_avoid = tcp_illinois_cong_avoid, .set_state = tcp_illinois_state, .get_info = tcp_illinois_info, diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 65cf90e063d5..e1661f46fd19 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -667,10 +667,11 @@ static void tcp_event_data_recv(struct sock *sk, struct sk_buff *skb) * To save cycles in the RFC 1323 implementation it was better to break * it up into three procedures. -- erics */ -static void tcp_rtt_estimator(struct sock *sk, const __u32 mrtt) +static void tcp_rtt_estimator(struct sock *sk, long mrtt_us) { struct tcp_sock *tp = tcp_sk(sk); - long m = mrtt; /* RTT */ + long m = mrtt_us; /* RTT */ + u32 srtt = tp->srtt_us; /* The following amusing code comes from Jacobson's * article in SIGCOMM '88. Note that rtt and mdev @@ -688,14 +689,12 @@ static void tcp_rtt_estimator(struct sock *sk, const __u32 mrtt) * does not matter how to _calculate_ it. Seems, it was trap * that VJ failed to avoid. 8) */ - if (m == 0) - m = 1; - if (tp->srtt != 0) { - m -= (tp->srtt >> 3); /* m is now error in rtt est */ - tp->srtt += m; /* rtt = 7/8 rtt + 1/8 new */ + if (srtt != 0) { + m -= (srtt >> 3); /* m is now error in rtt est */ + srtt += m; /* rtt = 7/8 rtt + 1/8 new */ if (m < 0) { m = -m; /* m is now abs(error) */ - m -= (tp->mdev >> 2); /* similar update on mdev */ + m -= (tp->mdev_us >> 2); /* similar update on mdev */ /* This is similar to one of Eifel findings. * Eifel blocks mdev updates when rtt decreases. * This solution is a bit different: we use finer gain @@ -707,27 +706,29 @@ static void tcp_rtt_estimator(struct sock *sk, const __u32 mrtt) if (m > 0) m >>= 3; } else { - m -= (tp->mdev >> 2); /* similar update on mdev */ + m -= (tp->mdev_us >> 2); /* similar update on mdev */ } - tp->mdev += m; /* mdev = 3/4 mdev + 1/4 new */ - if (tp->mdev > tp->mdev_max) { - tp->mdev_max = tp->mdev; - if (tp->mdev_max > tp->rttvar) - tp->rttvar = tp->mdev_max; + tp->mdev_us += m; /* mdev = 3/4 mdev + 1/4 new */ + if (tp->mdev_us > tp->mdev_max_us) { + tp->mdev_max_us = tp->mdev_us; + if (tp->mdev_max_us > tp->rttvar_us) + tp->rttvar_us = tp->mdev_max_us; } if (after(tp->snd_una, tp->rtt_seq)) { - if (tp->mdev_max < tp->rttvar) - tp->rttvar -= (tp->rttvar - tp->mdev_max) >> 2; + if (tp->mdev_max_us < tp->rttvar_us) + tp->rttvar_us -= (tp->rttvar_us - tp->mdev_max_us) >> 2; tp->rtt_seq = tp->snd_nxt; - tp->mdev_max = tcp_rto_min(sk); + tp->mdev_max_us = tcp_rto_min_us(sk); } } else { /* no previous measure. */ - tp->srtt = m << 3; /* take the measured time to be rtt */ - tp->mdev = m << 1; /* make sure rto = 3*rtt */ - tp->mdev_max = tp->rttvar = max(tp->mdev, tcp_rto_min(sk)); + srtt = m << 3; /* take the measured time to be rtt */ + tp->mdev_us = m << 1; /* make sure rto = 3*rtt */ + tp->rttvar_us = max(tp->mdev_us, tcp_rto_min_us(sk)); + tp->mdev_max_us = tp->rttvar_us; tp->rtt_seq = tp->snd_nxt; } + tp->srtt_us = max(1U, srtt); } /* Set the sk_pacing_rate to allow proper sizing of TSO packets. @@ -742,18 +743,12 @@ static void tcp_update_pacing_rate(struct sock *sk) u64 rate; /* set sk_pacing_rate to 200 % of current rate (mss * cwnd / srtt) */ - rate = (u64)tp->mss_cache * 2 * (HZ << 3); + rate = (u64)tp->mss_cache * 2 * (USEC_PER_SEC << 3); rate *= max(tp->snd_cwnd, tp->packets_out); - /* Correction for small srtt : minimum srtt being 8 (1 jiffy << 3), - * be conservative and assume srtt = 1 (125 us instead of 1.25 ms) - * We probably need usec resolution in the future. - * Note: This also takes care of possible srtt=0 case, - * when tcp_rtt_estimator() was not yet called. - */ - if (tp->srtt > 8 + 2) - do_div(rate, tp->srtt); + if (likely(tp->srtt_us)) + do_div(rate, tp->srtt_us); /* ACCESS_ONCE() is needed because sch_fq fetches sk_pacing_rate * without any lock. We want to make sure compiler wont store @@ -1120,10 +1115,10 @@ static bool tcp_check_dsack(struct sock *sk, const struct sk_buff *ack_skb, } struct tcp_sacktag_state { - int reord; - int fack_count; - int flag; - s32 rtt; /* RTT measured by SACKing never-retransmitted data */ + int reord; + int fack_count; + long rtt_us; /* RTT measured by SACKing never-retransmitted data */ + int flag; }; /* Check if skb is fully within the SACK block. In presence of GSO skbs, @@ -1184,7 +1179,8 @@ static int tcp_match_skb_to_sack(struct sock *sk, struct sk_buff *skb, static u8 tcp_sacktag_one(struct sock *sk, struct tcp_sacktag_state *state, u8 sacked, u32 start_seq, u32 end_seq, - int dup_sack, int pcount, u32 xmit_time) + int dup_sack, int pcount, + const struct skb_mstamp *xmit_time) { struct tcp_sock *tp = tcp_sk(sk); int fack_count = state->fack_count; @@ -1225,8 +1221,13 @@ static u8 tcp_sacktag_one(struct sock *sk, if (!after(end_seq, tp->high_seq)) state->flag |= FLAG_ORIG_SACK_ACKED; /* Pick the earliest sequence sacked for RTT */ - if (state->rtt < 0) - state->rtt = tcp_time_stamp - xmit_time; + if (state->rtt_us < 0) { + struct skb_mstamp now; + + skb_mstamp_get(&now); + state->rtt_us = skb_mstamp_us_delta(&now, + xmit_time); + } } if (sacked & TCPCB_LOST) { @@ -1285,7 +1286,7 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, */ tcp_sacktag_one(sk, state, TCP_SKB_CB(skb)->sacked, start_seq, end_seq, dup_sack, pcount, - TCP_SKB_CB(skb)->when); + &skb->skb_mstamp); if (skb == tp->lost_skb_hint) tp->lost_cnt_hint += pcount; @@ -1563,7 +1564,7 @@ static struct sk_buff *tcp_sacktag_walk(struct sk_buff *skb, struct sock *sk, TCP_SKB_CB(skb)->end_seq, dup_sack, tcp_skb_pcount(skb), - TCP_SKB_CB(skb)->when); + &skb->skb_mstamp); if (!before(TCP_SKB_CB(skb)->seq, tcp_highest_sack_seq(tp))) @@ -1620,7 +1621,7 @@ static int tcp_sack_cache_ok(const struct tcp_sock *tp, const struct tcp_sack_bl static int tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb, - u32 prior_snd_una, s32 *sack_rtt) + u32 prior_snd_una, long *sack_rtt_us) { struct tcp_sock *tp = tcp_sk(sk); const unsigned char *ptr = (skb_transport_header(ack_skb) + @@ -1638,7 +1639,7 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb, state.flag = 0; state.reord = tp->packets_out; - state.rtt = -1; + state.rtt_us = -1L; if (!tp->sacked_out) { if (WARN_ON(tp->fackets_out)) @@ -1822,7 +1823,7 @@ out: WARN_ON((int)tp->retrans_out < 0); WARN_ON((int)tcp_packets_in_flight(tp) < 0); #endif - *sack_rtt = state.rtt; + *sack_rtt_us = state.rtt_us; return state.flag; } @@ -1943,8 +1944,9 @@ void tcp_enter_loss(struct sock *sk, int how) if (skb == tcp_send_head(sk)) break; - if (TCP_SKB_CB(skb)->sacked & TCPCB_RETRANS) + if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) tp->undo_marker = 0; + TCP_SKB_CB(skb)->sacked &= (~TCPCB_TAGBITS)|TCPCB_SACKED_ACKED; if (!(TCP_SKB_CB(skb)->sacked&TCPCB_SACKED_ACKED) || how) { TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_ACKED; @@ -2032,10 +2034,12 @@ static bool tcp_pause_early_retransmit(struct sock *sk, int flag) * available, or RTO is scheduled to fire first. */ if (sysctl_tcp_early_retrans < 2 || sysctl_tcp_early_retrans > 3 || - (flag & FLAG_ECE) || !tp->srtt) + (flag & FLAG_ECE) || !tp->srtt_us) return false; - delay = max_t(unsigned long, (tp->srtt >> 5), msecs_to_jiffies(2)); + delay = max(usecs_to_jiffies(tp->srtt_us >> 5), + msecs_to_jiffies(2)); + if (!time_after(inet_csk(sk)->icsk_timeout, (jiffies + delay))) return false; @@ -2882,7 +2886,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const int acked, } static inline bool tcp_ack_update_rtt(struct sock *sk, const int flag, - s32 seq_rtt, s32 sack_rtt) + long seq_rtt_us, long sack_rtt_us) { const struct tcp_sock *tp = tcp_sk(sk); @@ -2892,10 +2896,10 @@ static inline bool tcp_ack_update_rtt(struct sock *sk, const int flag, * is acked (RFC6298). */ if (flag & FLAG_RETRANS_DATA_ACKED) - seq_rtt = -1; + seq_rtt_us = -1L; - if (seq_rtt < 0) - seq_rtt = sack_rtt; + if (seq_rtt_us < 0) + seq_rtt_us = sack_rtt_us; /* RTTM Rule: A TSecr value received in a segment is used to * update the averaged RTT measurement only if the segment @@ -2903,14 +2907,14 @@ static inline bool tcp_ack_update_rtt(struct sock *sk, const int flag, * left edge of the send window. * See draft-ietf-tcplw-high-performance-00, section 3.3. */ - if (seq_rtt < 0 && tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr && + if (seq_rtt_us < 0 && tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr && flag & FLAG_ACKED) - seq_rtt = tcp_time_stamp - tp->rx_opt.rcv_tsecr; + seq_rtt_us = jiffies_to_usecs(tcp_time_stamp - tp->rx_opt.rcv_tsecr); - if (seq_rtt < 0) + if (seq_rtt_us < 0) return false; - tcp_rtt_estimator(sk, seq_rtt); + tcp_rtt_estimator(sk, seq_rtt_us); tcp_set_rto(sk); /* RFC6298: only reset backoff on valid RTT measurement. */ @@ -2922,16 +2926,16 @@ static inline bool tcp_ack_update_rtt(struct sock *sk, const int flag, static void tcp_synack_rtt_meas(struct sock *sk, const u32 synack_stamp) { struct tcp_sock *tp = tcp_sk(sk); - s32 seq_rtt = -1; + long seq_rtt_us = -1L; if (synack_stamp && !tp->total_retrans) - seq_rtt = tcp_time_stamp - synack_stamp; + seq_rtt_us = jiffies_to_usecs(tcp_time_stamp - synack_stamp); /* If the ACK acks both the SYNACK and the (Fast Open'd) data packets * sent in SYN_RECV, SYNACK RTT is the smooth RTT computed in tcp_ack() */ - if (!tp->srtt) - tcp_ack_update_rtt(sk, FLAG_SYN_ACKED, seq_rtt, -1); + if (!tp->srtt_us) + tcp_ack_update_rtt(sk, FLAG_SYN_ACKED, seq_rtt_us, -1L); } static void tcp_cong_avoid(struct sock *sk, u32 ack, u32 acked, u32 in_flight) @@ -3020,26 +3024,27 @@ static u32 tcp_tso_acked(struct sock *sk, struct sk_buff *skb) * arrived at the other end. */ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, - u32 prior_snd_una, s32 sack_rtt) + u32 prior_snd_una, long sack_rtt_us) { - struct tcp_sock *tp = tcp_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); - struct sk_buff *skb; - u32 now = tcp_time_stamp; + struct skb_mstamp first_ackt, last_ackt, now; + struct tcp_sock *tp = tcp_sk(sk); + u32 prior_sacked = tp->sacked_out; + u32 reord = tp->packets_out; bool fully_acked = true; - int flag = 0; + long ca_seq_rtt_us = -1L; + long seq_rtt_us = -1L; + struct sk_buff *skb; u32 pkts_acked = 0; - u32 reord = tp->packets_out; - u32 prior_sacked = tp->sacked_out; - s32 seq_rtt = -1; - s32 ca_seq_rtt = -1; - ktime_t last_ackt = net_invalid_timestamp(); bool rtt_update; + int flag = 0; + + first_ackt.v64 = 0; while ((skb = tcp_write_queue_head(sk)) && skb != tcp_send_head(sk)) { struct tcp_skb_cb *scb = TCP_SKB_CB(skb); - u32 acked_pcount; u8 sacked = scb->sacked; + u32 acked_pcount; /* Determine how many packets and what bytes were acked, tso and else */ if (after(scb->end_seq, tp->snd_una)) { @@ -3061,11 +3066,11 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, tp->retrans_out -= acked_pcount; flag |= FLAG_RETRANS_DATA_ACKED; } else { - ca_seq_rtt = now - scb->when; - last_ackt = skb->tstamp; - if (seq_rtt < 0) { - seq_rtt = ca_seq_rtt; - } + last_ackt = skb->skb_mstamp; + WARN_ON_ONCE(last_ackt.v64 == 0); + if (!first_ackt.v64) + first_ackt = last_ackt; + if (!(sacked & TCPCB_SACKED_ACKED)) reord = min(pkts_acked, reord); if (!after(scb->end_seq, tp->high_seq)) @@ -3111,7 +3116,13 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, if (skb && (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)) flag |= FLAG_SACK_RENEGING; - rtt_update = tcp_ack_update_rtt(sk, flag, seq_rtt, sack_rtt); + skb_mstamp_get(&now); + if (first_ackt.v64) { + seq_rtt_us = skb_mstamp_us_delta(&now, &first_ackt); + ca_seq_rtt_us = skb_mstamp_us_delta(&now, &last_ackt); + } + + rtt_update = tcp_ack_update_rtt(sk, flag, seq_rtt_us, sack_rtt_us); if (flag & FLAG_ACKED) { const struct tcp_congestion_ops *ca_ops @@ -3139,25 +3150,11 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, tp->fackets_out -= min(pkts_acked, tp->fackets_out); - if (ca_ops->pkts_acked) { - s32 rtt_us = -1; - - /* Is the ACK triggering packet unambiguous? */ - if (!(flag & FLAG_RETRANS_DATA_ACKED)) { - /* High resolution needed and available? */ - if (ca_ops->flags & TCP_CONG_RTT_STAMP && - !ktime_equal(last_ackt, - net_invalid_timestamp())) - rtt_us = ktime_us_delta(ktime_get_real(), - last_ackt); - else if (ca_seq_rtt >= 0) - rtt_us = jiffies_to_usecs(ca_seq_rtt); - } + if (ca_ops->pkts_acked) + ca_ops->pkts_acked(sk, pkts_acked, ca_seq_rtt_us); - ca_ops->pkts_acked(sk, pkts_acked, rtt_us); - } - } else if (skb && rtt_update && sack_rtt >= 0 && - sack_rtt > (s32)(now - TCP_SKB_CB(skb)->when)) { + } else if (skb && rtt_update && sack_rtt_us >= 0 && + sack_rtt_us > skb_mstamp_us_delta(&now, &skb->skb_mstamp)) { /* Do not re-arm RTO if the sack RTT is measured from data sent * after when the head was last (re)transmitted. Otherwise the * timeout may continue to extend in loss recovery. @@ -3367,12 +3364,12 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) u32 ack_seq = TCP_SKB_CB(skb)->seq; u32 ack = TCP_SKB_CB(skb)->ack_seq; bool is_dupack = false; - u32 prior_in_flight, prior_cwnd = tp->snd_cwnd, prior_rtt = tp->srtt; + u32 prior_in_flight; u32 prior_fackets; int prior_packets = tp->packets_out; const int prior_unsacked = tp->packets_out - tp->sacked_out; int acked = 0; /* Number of packets newly acked */ - s32 sack_rtt = -1; + long sack_rtt_us = -1L; /* If the ack is older than previous acks * then we can probably ignore it. @@ -3430,7 +3427,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) if (TCP_SKB_CB(skb)->sacked) flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una, - &sack_rtt); + &sack_rtt_us); if (TCP_ECN_rcv_ecn_echo(tp, tcp_hdr(skb))) flag |= FLAG_ECE; @@ -3449,7 +3446,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) /* See if we can take anything off of the retransmit queue. */ acked = tp->packets_out; - flag |= tcp_clean_rtx_queue(sk, prior_fackets, prior_snd_una, sack_rtt); + flag |= tcp_clean_rtx_queue(sk, prior_fackets, prior_snd_una, + sack_rtt_us); acked -= tp->packets_out; /* Advance cwnd if state allows */ @@ -3472,8 +3470,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) if (icsk->icsk_pending == ICSK_TIME_RETRANS) tcp_schedule_loss_probe(sk); - if (tp->srtt != prior_rtt || tp->snd_cwnd != prior_cwnd) - tcp_update_pacing_rate(sk); + tcp_update_pacing_rate(sk); return 1; no_queue: @@ -3502,7 +3499,7 @@ old_ack: */ if (TCP_SKB_CB(skb)->sacked) { flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una, - &sack_rtt); + &sack_rtt_us); tcp_fastretrans_alert(sk, acked, prior_unsacked, is_dupack, flag); } @@ -5398,9 +5395,12 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack, break; } tcp_rearm_rto(sk); + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPFASTOPENACTIVEFAIL); return true; } tp->syn_data_acked = tp->syn_data; + if (tp->syn_data_acked) + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPFASTOPENACTIVE); return false; } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 3cf976510497..c4f1d9a76c44 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -435,7 +435,7 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) break; icsk->icsk_backoff--; - inet_csk(sk)->icsk_rto = (tp->srtt ? __tcp_set_rto(tp) : + inet_csk(sk)->icsk_rto = (tp->srtt_us ? __tcp_set_rto(tp) : TCP_TIMEOUT_INIT) << icsk->icsk_backoff; tcp_bound_rto(sk); @@ -854,8 +854,10 @@ static int tcp_v4_rtx_synack(struct sock *sk, struct request_sock *req) { int res = tcp_v4_send_synack(sk, NULL, req, 0); - if (!res) + if (!res) { TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS); + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPSYNRETRANS); + } return res; } diff --git a/net/ipv4/tcp_lp.c b/net/ipv4/tcp_lp.c index 991d62a2f9bb..c9aecae31327 100644 --- a/net/ipv4/tcp_lp.c +++ b/net/ipv4/tcp_lp.c @@ -315,11 +315,9 @@ static void tcp_lp_pkts_acked(struct sock *sk, u32 num_acked, s32 rtt_us) } static struct tcp_congestion_ops tcp_lp __read_mostly = { - .flags = TCP_CONG_RTT_STAMP, .init = tcp_lp_init, .ssthresh = tcp_reno_ssthresh, .cong_avoid = tcp_lp_cong_avoid, - .min_cwnd = tcp_reno_min_cwnd, .pkts_acked = tcp_lp_pkts_acked, .owner = THIS_MODULE, diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index d547075d8300..dcaf72f10216 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -33,6 +33,11 @@ struct tcp_fastopen_metrics { struct tcp_fastopen_cookie cookie; }; +/* TCP_METRIC_MAX includes 2 extra fields for userspace compatibility + * Kernel only stores RTT and RTTVAR in usec resolution + */ +#define TCP_METRIC_MAX_KERNEL (TCP_METRIC_MAX - 2) + struct tcp_metrics_block { struct tcp_metrics_block __rcu *tcpm_next; struct inetpeer_addr tcpm_saddr; @@ -41,7 +46,7 @@ struct tcp_metrics_block { u32 tcpm_ts; u32 tcpm_ts_stamp; u32 tcpm_lock; - u32 tcpm_vals[TCP_METRIC_MAX + 1]; + u32 tcpm_vals[TCP_METRIC_MAX_KERNEL + 1]; struct tcp_fastopen_metrics tcpm_fastopen; struct rcu_head rcu_head; @@ -59,12 +64,6 @@ static u32 tcp_metric_get(struct tcp_metrics_block *tm, return tm->tcpm_vals[idx]; } -static u32 tcp_metric_get_jiffies(struct tcp_metrics_block *tm, - enum tcp_metric_index idx) -{ - return msecs_to_jiffies(tm->tcpm_vals[idx]); -} - static void tcp_metric_set(struct tcp_metrics_block *tm, enum tcp_metric_index idx, u32 val) @@ -72,13 +71,6 @@ static void tcp_metric_set(struct tcp_metrics_block *tm, tm->tcpm_vals[idx] = val; } -static void tcp_metric_set_msecs(struct tcp_metrics_block *tm, - enum tcp_metric_index idx, - u32 val) -{ - tm->tcpm_vals[idx] = jiffies_to_msecs(val); -} - static bool addr_same(const struct inetpeer_addr *a, const struct inetpeer_addr *b) { @@ -101,9 +93,11 @@ struct tcpm_hash_bucket { static DEFINE_SPINLOCK(tcp_metrics_lock); -static void tcpm_suck_dst(struct tcp_metrics_block *tm, struct dst_entry *dst, +static void tcpm_suck_dst(struct tcp_metrics_block *tm, + const struct dst_entry *dst, bool fastopen_clear) { + u32 msval; u32 val; tm->tcpm_stamp = jiffies; @@ -121,8 +115,11 @@ static void tcpm_suck_dst(struct tcp_metrics_block *tm, struct dst_entry *dst, val |= 1 << TCP_METRIC_REORDERING; tm->tcpm_lock = val; - tm->tcpm_vals[TCP_METRIC_RTT] = dst_metric_raw(dst, RTAX_RTT); - tm->tcpm_vals[TCP_METRIC_RTTVAR] = dst_metric_raw(dst, RTAX_RTTVAR); + msval = dst_metric_raw(dst, RTAX_RTT); + tm->tcpm_vals[TCP_METRIC_RTT] = msval * USEC_PER_MSEC; + + msval = dst_metric_raw(dst, RTAX_RTTVAR); + tm->tcpm_vals[TCP_METRIC_RTTVAR] = msval * USEC_PER_MSEC; tm->tcpm_vals[TCP_METRIC_SSTHRESH] = dst_metric_raw(dst, RTAX_SSTHRESH); tm->tcpm_vals[TCP_METRIC_CWND] = dst_metric_raw(dst, RTAX_CWND); tm->tcpm_vals[TCP_METRIC_REORDERING] = dst_metric_raw(dst, RTAX_REORDERING); @@ -384,7 +381,7 @@ void tcp_update_metrics(struct sock *sk) dst_confirm(dst); rcu_read_lock(); - if (icsk->icsk_backoff || !tp->srtt) { + if (icsk->icsk_backoff || !tp->srtt_us) { /* This session failed to estimate rtt. Why? * Probably, no packets returned in time. Reset our * results. @@ -399,8 +396,8 @@ void tcp_update_metrics(struct sock *sk) if (!tm) goto out_unlock; - rtt = tcp_metric_get_jiffies(tm, TCP_METRIC_RTT); - m = rtt - tp->srtt; + rtt = tcp_metric_get(tm, TCP_METRIC_RTT); + m = rtt - tp->srtt_us; /* If newly calculated rtt larger than stored one, store new * one. Otherwise, use EWMA. Remember, rtt overestimation is @@ -408,10 +405,10 @@ void tcp_update_metrics(struct sock *sk) */ if (!tcp_metric_locked(tm, TCP_METRIC_RTT)) { if (m <= 0) - rtt = tp->srtt; + rtt = tp->srtt_us; else rtt -= (m >> 3); - tcp_metric_set_msecs(tm, TCP_METRIC_RTT, rtt); + tcp_metric_set(tm, TCP_METRIC_RTT, rtt); } if (!tcp_metric_locked(tm, TCP_METRIC_RTTVAR)) { @@ -422,16 +419,16 @@ void tcp_update_metrics(struct sock *sk) /* Scale deviation to rttvar fixed point */ m >>= 1; - if (m < tp->mdev) - m = tp->mdev; + if (m < tp->mdev_us) + m = tp->mdev_us; - var = tcp_metric_get_jiffies(tm, TCP_METRIC_RTTVAR); + var = tcp_metric_get(tm, TCP_METRIC_RTTVAR); if (m >= var) var = m; else var -= (var - m) >> 2; - tcp_metric_set_msecs(tm, TCP_METRIC_RTTVAR, var); + tcp_metric_set(tm, TCP_METRIC_RTTVAR, var); } if (tcp_in_initial_slowstart(tp)) { @@ -528,7 +525,7 @@ void tcp_init_metrics(struct sock *sk) tp->reordering = val; } - crtt = tcp_metric_get_jiffies(tm, TCP_METRIC_RTT); + crtt = tcp_metric_get(tm, TCP_METRIC_RTT); rcu_read_unlock(); reset: /* The initial RTT measurement from the SYN/SYN-ACK is not ideal @@ -551,18 +548,20 @@ reset: * to low value, and then abruptly stops to do it and starts to delay * ACKs, wait for troubles. */ - if (crtt > tp->srtt) { + if (crtt > tp->srtt_us) { /* Set RTO like tcp_rtt_estimator(), but from cached RTT. */ - crtt >>= 3; + crtt /= 8 * USEC_PER_MSEC; inet_csk(sk)->icsk_rto = crtt + max(2 * crtt, tcp_rto_min(sk)); - } else if (tp->srtt == 0) { + } else if (tp->srtt_us == 0) { /* RFC6298: 5.7 We've failed to get a valid RTT sample from * 3WHS. This is most likely due to retransmission, * including spurious one. Reset the RTO back to 3secs * from the more aggressive 1sec to avoid more spurious * retransmission. */ - tp->mdev = tp->mdev_max = tp->rttvar = TCP_TIMEOUT_FALLBACK; + tp->rttvar_us = jiffies_to_usecs(TCP_TIMEOUT_FALLBACK); + tp->mdev_us = tp->mdev_max_us = tp->rttvar_us; + inet_csk(sk)->icsk_rto = TCP_TIMEOUT_FALLBACK; } /* Cut cwnd down to 1 per RFC5681 if SYN or SYN-ACK has been @@ -809,10 +808,26 @@ static int tcp_metrics_fill_info(struct sk_buff *msg, nest = nla_nest_start(msg, TCP_METRICS_ATTR_VALS); if (!nest) goto nla_put_failure; - for (i = 0; i < TCP_METRIC_MAX + 1; i++) { - if (!tm->tcpm_vals[i]) + for (i = 0; i < TCP_METRIC_MAX_KERNEL + 1; i++) { + u32 val = tm->tcpm_vals[i]; + + if (!val) continue; - if (nla_put_u32(msg, i + 1, tm->tcpm_vals[i]) < 0) + if (i == TCP_METRIC_RTT) { + if (nla_put_u32(msg, TCP_METRIC_RTT_US + 1, + val) < 0) + goto nla_put_failure; + n++; + val = max(val / 1000, 1U); + } + if (i == TCP_METRIC_RTTVAR) { + if (nla_put_u32(msg, TCP_METRIC_RTTVAR_US + 1, + val) < 0) + goto nla_put_failure; + n++; + val = max(val / 1000, 1U); + } + if (nla_put_u32(msg, i + 1, val) < 0) goto nla_put_failure; n++; } diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 7a436c517e44..ca788ada5bd3 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -398,8 +398,8 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, tcp_init_wl(newtp, treq->rcv_isn); - newtp->srtt = 0; - newtp->mdev = TCP_TIMEOUT_INIT; + newtp->srtt_us = 0; + newtp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT); newicsk->icsk_rto = TCP_TIMEOUT_INIT; newtp->packets_out = 0; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 03d26b85eab8..5a163de5e142 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -86,6 +86,9 @@ static void tcp_event_new_data_sent(struct sock *sk, const struct sk_buff *skb) icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) { tcp_rearm_rto(sk); } + + NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPORIGDATASENT, + tcp_skb_pcount(skb)); } /* SND.NXT, if window was not shrunk. @@ -269,6 +272,7 @@ EXPORT_SYMBOL(tcp_select_initial_window); static u16 tcp_select_window(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); + u32 old_win = tp->rcv_wnd; u32 cur_win = tcp_receive_window(tp); u32 new_win = __tcp_select_window(sk); @@ -281,6 +285,9 @@ static u16 tcp_select_window(struct sock *sk) * * Relax Will Robinson. */ + if (new_win == 0) + NET_INC_STATS(sock_net(sk), + LINUX_MIB_TCPWANTZEROWINDOWADV); new_win = ALIGN(cur_win, 1 << tp->rx_opt.rcv_wscale); } tp->rcv_wnd = new_win; @@ -298,8 +305,14 @@ static u16 tcp_select_window(struct sock *sk) new_win >>= tp->rx_opt.rcv_wscale; /* If we advertise zero window, disable fast path. */ - if (new_win == 0) + if (new_win == 0) { tp->pred_flags = 0; + if (old_win) + NET_INC_STATS(sock_net(sk), + LINUX_MIB_TCPTOZEROWINDOWADV); + } else if (old_win == 0) { + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFROMZEROWINDOWADV); + } return new_win; } @@ -698,7 +711,8 @@ static void tcp_tsq_handler(struct sock *sk) if ((1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_FIN_WAIT1 | TCPF_CLOSING | TCPF_CLOSE_WAIT | TCPF_LAST_ACK)) - tcp_write_xmit(sk, tcp_current_mss(sk), 0, 0, GFP_ATOMIC); + tcp_write_xmit(sk, tcp_current_mss(sk), tcp_sk(sk)->nonagle, + 0, GFP_ATOMIC); } /* * One tasklet per cpu tries to send more skbs. @@ -855,16 +869,12 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, if (clone_it) { const struct sk_buff *fclone = skb + 1; - /* If congestion control is doing timestamping, we must - * take such a timestamp before we potentially clone/copy. - */ - if (icsk->icsk_ca_ops->flags & TCP_CONG_RTT_STAMP) - __net_timestamp(skb); + skb_mstamp_get(&skb->skb_mstamp); if (unlikely(skb->fclone == SKB_FCLONE_ORIG && fclone->fclone == SKB_FCLONE_CLONE)) - NET_INC_STATS_BH(sock_net(sk), - LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES); + NET_INC_STATS(sock_net(sk), + LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES); if (unlikely(skb_cloned(skb))) skb = pskb_copy(skb, gfp_mask); @@ -872,6 +882,8 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, skb = skb_clone(skb, gfp_mask); if (unlikely(!skb)) return -ENOBUFS; + /* Our usage of tstamp should remain private */ + skb->tstamp.tv64 = 0; } inet = inet_sk(sk); @@ -1904,7 +1916,15 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, if (atomic_read(&sk->sk_wmem_alloc) > limit) { set_bit(TSQ_THROTTLED, &tp->tsq_flags); - break; + /* It is possible TX completion already happened + * before we set TSQ_THROTTLED, so we must + * test again the condition. + * We abuse smp_mb__after_clear_bit() because + * there is no smp_mb__after_set_bit() yet + */ + smp_mb__after_clear_bit(); + if (atomic_read(&sk->sk_wmem_alloc) > limit) + break; } limit = mss_now; @@ -1955,7 +1975,7 @@ bool tcp_schedule_loss_probe(struct sock *sk) struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); u32 timeout, tlp_time_stamp, rto_time_stamp; - u32 rtt = tp->srtt >> 3; + u32 rtt = usecs_to_jiffies(tp->srtt_us >> 3); if (WARN_ON(icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS)) return false; @@ -1977,7 +1997,7 @@ bool tcp_schedule_loss_probe(struct sock *sk) /* Schedule a loss probe in 2*RTT for SACK capable connections * in Open state, that are either limited by cwnd or application. */ - if (sysctl_tcp_early_retrans < 3 || !rtt || !tp->packets_out || + if (sysctl_tcp_early_retrans < 3 || !tp->srtt_us || !tp->packets_out || !tcp_is_sack(tp) || inet_csk(sk)->icsk_ca_state != TCP_CA_Open) return false; @@ -2062,7 +2082,6 @@ rearm_timer: if (likely(!err)) NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPLOSSPROBES); - return; } /* Push out any pending frames which were held back due to @@ -2160,7 +2179,8 @@ u32 __tcp_select_window(struct sock *sk) */ int mss = icsk->icsk_ack.rcv_mss; int free_space = tcp_space(sk); - int full_space = min_t(int, tp->window_clamp, tcp_full_space(sk)); + int allowed_space = tcp_full_space(sk); + int full_space = min_t(int, tp->window_clamp, allowed_space); int window; if (mss > full_space) @@ -2173,7 +2193,19 @@ u32 __tcp_select_window(struct sock *sk) tp->rcv_ssthresh = min(tp->rcv_ssthresh, 4U * tp->advmss); - if (free_space < mss) + /* free_space might become our new window, make sure we don't + * increase it due to wscale. + */ + free_space = round_down(free_space, 1 << tp->rx_opt.rcv_wscale); + + /* if free space is less than mss estimate, or is below 1/16th + * of the maximum allowed, try to move to zero-window, else + * tcp_clamp_window() will grow rcv buf up to tcp_rmem[2], and + * new incoming data is dropped due to memory limits. + * With large window, mss test triggers way too late in order + * to announce zero window in time before rmem limit kicks in. + */ + if (free_space < (allowed_space >> 4) || free_space < mss) return 0; } @@ -2328,6 +2360,7 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); unsigned int cur_mss; + int err; /* Inconslusive MTU probe */ if (icsk->icsk_mtup.probe_size) { @@ -2391,11 +2424,15 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) skb_headroom(skb) >= 0xFFFF)) { struct sk_buff *nskb = __pskb_copy(skb, MAX_TCP_HEADER, GFP_ATOMIC); - return nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) : - -ENOBUFS; + err = nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) : + -ENOBUFS; } else { - return tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC); + err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC); } + + if (likely(!err)) + TCP_SKB_CB(skb)->sacked |= TCPCB_EVER_RETRANS; + return err; } int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) @@ -2406,7 +2443,8 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) if (err == 0) { /* Update global TCP statistics. */ TCP_INC_STATS(sock_net(sk), TCP_MIB_RETRANSSEGS); - + if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN) + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPSYNRETRANS); tp->total_retrans++; #if FASTRETRANS_DEBUG > 0 @@ -2899,7 +2937,12 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) space = __tcp_mtu_to_mss(sk, inet_csk(sk)->icsk_pmtu_cookie) - MAX_TCP_OPTION_SPACE; - syn_data = skb_copy_expand(syn, skb_headroom(syn), space, + space = min_t(size_t, space, fo->size); + + /* limit to order-0 allocations */ + space = min_t(size_t, space, SKB_MAX_HEAD(MAX_TCP_HEADER)); + + syn_data = skb_copy_expand(syn, MAX_TCP_HEADER, space, sk->sk_allocation); if (syn_data == NULL) goto fallback; @@ -2929,9 +2972,15 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) tcp_connect_queue_skb(sk, data); fo->copied = data->len; + /* syn_data is about to be sent, we need to take current time stamps + * for the packets that are in write queue : SYN packet and DATA + */ + skb_mstamp_get(&syn->skb_mstamp); + data->skb_mstamp = syn->skb_mstamp; + if (tcp_transmit_skb(sk, syn_data, 0, sk->sk_allocation) == 0) { tp->syn_data = (fo->copied > 0); - NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENACTIVE); + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPORIGDATASENT); goto done; } syn_data = NULL; @@ -3019,8 +3068,9 @@ void tcp_send_delayed_ack(struct sock *sk) * Do not use inet_csk(sk)->icsk_rto here, use results of rtt measurements * directly. */ - if (tp->srtt) { - int rtt = max(tp->srtt >> 3, TCP_DELACK_MIN); + if (tp->srtt_us) { + int rtt = max_t(int, usecs_to_jiffies(tp->srtt_us >> 3), + TCP_DELACK_MIN); if (rtt < max_ato) max_ato = rtt; diff --git a/net/ipv4/tcp_probe.c b/net/ipv4/tcp_probe.c index 1f2d37613c9e..3b66610d4156 100644 --- a/net/ipv4/tcp_probe.c +++ b/net/ipv4/tcp_probe.c @@ -154,7 +154,7 @@ static void jtcp_rcv_established(struct sock *sk, struct sk_buff *skb, p->snd_wnd = tp->snd_wnd; p->rcv_wnd = tp->rcv_wnd; p->ssthresh = tcp_current_ssthresh(sk); - p->srtt = tp->srtt >> 3; + p->srtt = tp->srtt_us >> 3; tcp_probe.head = (tcp_probe.head + 1) & (bufsize - 1); } diff --git a/net/ipv4/tcp_scalable.c b/net/ipv4/tcp_scalable.c index 19ea6c2951f3..0ac50836da4d 100644 --- a/net/ipv4/tcp_scalable.c +++ b/net/ipv4/tcp_scalable.c @@ -39,7 +39,6 @@ static u32 tcp_scalable_ssthresh(struct sock *sk) static struct tcp_congestion_ops tcp_scalable __read_mostly = { .ssthresh = tcp_scalable_ssthresh, .cong_avoid = tcp_scalable_cong_avoid, - .min_cwnd = tcp_reno_min_cwnd, .owner = THIS_MODULE, .name = "scalable", diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 64f0354c84c7..286227abed10 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -165,6 +165,9 @@ static int tcp_write_timeout(struct sock *sk) dst_negative_advice(sk); if (tp->syn_fastopen || tp->syn_data) tcp_fastopen_cache_set(sk, 0, NULL, true); + if (tp->syn_data) + NET_INC_STATS_BH(sock_net(sk), + LINUX_MIB_TCPFASTOPENACTIVEFAIL); } retry_until = icsk->icsk_syn_retries ? : sysctl_tcp_syn_retries; syn_set = true; diff --git a/net/ipv4/tcp_vegas.c b/net/ipv4/tcp_vegas.c index 06cae62bf208..48539fff6357 100644 --- a/net/ipv4/tcp_vegas.c +++ b/net/ipv4/tcp_vegas.c @@ -306,11 +306,9 @@ void tcp_vegas_get_info(struct sock *sk, u32 ext, struct sk_buff *skb) EXPORT_SYMBOL_GPL(tcp_vegas_get_info); static struct tcp_congestion_ops tcp_vegas __read_mostly = { - .flags = TCP_CONG_RTT_STAMP, .init = tcp_vegas_init, .ssthresh = tcp_reno_ssthresh, .cong_avoid = tcp_vegas_cong_avoid, - .min_cwnd = tcp_reno_min_cwnd, .pkts_acked = tcp_vegas_pkts_acked, .set_state = tcp_vegas_state, .cwnd_event = tcp_vegas_cwnd_event, diff --git a/net/ipv4/tcp_veno.c b/net/ipv4/tcp_veno.c index 326475a94865..1b8e28fcd7e1 100644 --- a/net/ipv4/tcp_veno.c +++ b/net/ipv4/tcp_veno.c @@ -203,7 +203,6 @@ static u32 tcp_veno_ssthresh(struct sock *sk) } static struct tcp_congestion_ops tcp_veno __read_mostly = { - .flags = TCP_CONG_RTT_STAMP, .init = tcp_veno_init, .ssthresh = tcp_veno_ssthresh, .cong_avoid = tcp_veno_cong_avoid, diff --git a/net/ipv4/tcp_westwood.c b/net/ipv4/tcp_westwood.c index 76a1e23259e1..b94a04ae2ed5 100644 --- a/net/ipv4/tcp_westwood.c +++ b/net/ipv4/tcp_westwood.c @@ -276,7 +276,6 @@ static struct tcp_congestion_ops tcp_westwood __read_mostly = { .init = tcp_westwood_init, .ssthresh = tcp_reno_ssthresh, .cong_avoid = tcp_reno_cong_avoid, - .min_cwnd = tcp_westwood_bw_rttmin, .cwnd_event = tcp_westwood_event, .get_info = tcp_westwood_info, .pkts_acked = tcp_westwood_pkts_acked, diff --git a/net/ipv4/tcp_yeah.c b/net/ipv4/tcp_yeah.c index 1a8d271f994d..5ede0e727945 100644 --- a/net/ipv4/tcp_yeah.c +++ b/net/ipv4/tcp_yeah.c @@ -227,11 +227,9 @@ static u32 tcp_yeah_ssthresh(struct sock *sk) { } static struct tcp_congestion_ops tcp_yeah __read_mostly = { - .flags = TCP_CONG_RTT_STAMP, .init = tcp_yeah_init, .ssthresh = tcp_yeah_ssthresh, .cong_avoid = tcp_yeah_cong_avoid, - .min_cwnd = tcp_reno_min_cwnd, .set_state = tcp_vegas_state, .cwnd_event = tcp_vegas_cwnd_event, .get_info = tcp_vegas_get_info, diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 77bd16fa9f34..4468e1adc094 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -931,7 +931,8 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, sock_tx_timestamp(sk, &ipc.tx_flags); if (msg->msg_controllen) { - err = ip_cmsg_send(sock_net(sk), msg, &ipc); + err = ip_cmsg_send(sock_net(sk), msg, &ipc, + sk->sk_family == AF_INET6); if (err) return err; if (ipc.opt) diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 25f5cee3a08a..88b4023ecfcf 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -17,6 +17,8 @@ static DEFINE_SPINLOCK(udp_offload_lock); static struct udp_offload_priv __rcu *udp_offload_base __read_mostly; +#define udp_deref_protected(X) rcu_dereference_protected(X, lockdep_is_held(&udp_offload_lock)) + struct udp_offload_priv { struct udp_offload *offload; struct rcu_head rcu; @@ -100,8 +102,7 @@ out: int udp_add_offload(struct udp_offload *uo) { - struct udp_offload_priv __rcu **head = &udp_offload_base; - struct udp_offload_priv *new_offload = kzalloc(sizeof(*new_offload), GFP_KERNEL); + struct udp_offload_priv *new_offload = kzalloc(sizeof(*new_offload), GFP_ATOMIC); if (!new_offload) return -ENOMEM; @@ -109,8 +110,8 @@ int udp_add_offload(struct udp_offload *uo) new_offload->offload = uo; spin_lock(&udp_offload_lock); - rcu_assign_pointer(new_offload->next, rcu_dereference(*head)); - rcu_assign_pointer(*head, new_offload); + new_offload->next = udp_offload_base; + rcu_assign_pointer(udp_offload_base, new_offload); spin_unlock(&udp_offload_lock); return 0; @@ -130,12 +131,12 @@ void udp_del_offload(struct udp_offload *uo) spin_lock(&udp_offload_lock); - uo_priv = rcu_dereference(*head); + uo_priv = udp_deref_protected(*head); for (; uo_priv != NULL; - uo_priv = rcu_dereference(*head)) { - + uo_priv = udp_deref_protected(*head)) { if (uo_priv->offload == uo) { - rcu_assign_pointer(*head, rcu_dereference(uo_priv->next)); + rcu_assign_pointer(*head, + udp_deref_protected(uo_priv->next)); goto unlock; } head = &uo_priv->next; diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c index 1f12c8b45864..aac6197b7a71 100644 --- a/net/ipv4/xfrm4_input.c +++ b/net/ipv4/xfrm4_input.c @@ -37,15 +37,6 @@ drop: return NET_RX_DROP; } -int xfrm4_rcv_encap(struct sk_buff *skb, int nexthdr, __be32 spi, - int encap_type) -{ - XFRM_SPI_SKB_CB(skb)->family = AF_INET; - XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr); - return xfrm_input(skb, nexthdr, spi, encap_type); -} -EXPORT_SYMBOL(xfrm4_rcv_encap); - int xfrm4_transport_finish(struct sk_buff *skb, int async) { struct iphdr *iph = ip_hdr(skb); diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c index 31b18152528f..05f2b484954f 100644 --- a/net/ipv4/xfrm4_mode_tunnel.c +++ b/net/ipv4/xfrm4_mode_tunnel.c @@ -15,65 +15,6 @@ #include <net/ip.h> #include <net/xfrm.h> -/* Informational hook. The decap is still done here. */ -static struct xfrm_tunnel_notifier __rcu *rcv_notify_handlers __read_mostly; -static DEFINE_MUTEX(xfrm4_mode_tunnel_input_mutex); - -int xfrm4_mode_tunnel_input_register(struct xfrm_tunnel_notifier *handler) -{ - struct xfrm_tunnel_notifier __rcu **pprev; - struct xfrm_tunnel_notifier *t; - int ret = -EEXIST; - int priority = handler->priority; - - mutex_lock(&xfrm4_mode_tunnel_input_mutex); - - for (pprev = &rcv_notify_handlers; - (t = rcu_dereference_protected(*pprev, - lockdep_is_held(&xfrm4_mode_tunnel_input_mutex))) != NULL; - pprev = &t->next) { - if (t->priority > priority) - break; - if (t->priority == priority) - goto err; - - } - - handler->next = *pprev; - rcu_assign_pointer(*pprev, handler); - - ret = 0; - -err: - mutex_unlock(&xfrm4_mode_tunnel_input_mutex); - return ret; -} -EXPORT_SYMBOL_GPL(xfrm4_mode_tunnel_input_register); - -int xfrm4_mode_tunnel_input_deregister(struct xfrm_tunnel_notifier *handler) -{ - struct xfrm_tunnel_notifier __rcu **pprev; - struct xfrm_tunnel_notifier *t; - int ret = -ENOENT; - - mutex_lock(&xfrm4_mode_tunnel_input_mutex); - for (pprev = &rcv_notify_handlers; - (t = rcu_dereference_protected(*pprev, - lockdep_is_held(&xfrm4_mode_tunnel_input_mutex))) != NULL; - pprev = &t->next) { - if (t == handler) { - *pprev = handler->next; - ret = 0; - break; - } - } - mutex_unlock(&xfrm4_mode_tunnel_input_mutex); - synchronize_net(); - - return ret; -} -EXPORT_SYMBOL_GPL(xfrm4_mode_tunnel_input_deregister); - static inline void ipip_ecn_decapsulate(struct sk_buff *skb) { struct iphdr *inner_iph = ipip_hdr(skb); @@ -127,14 +68,8 @@ static int xfrm4_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb) return 0; } -#define for_each_input_rcu(head, handler) \ - for (handler = rcu_dereference(head); \ - handler != NULL; \ - handler = rcu_dereference(handler->next)) - static int xfrm4_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb) { - struct xfrm_tunnel_notifier *handler; int err = -EINVAL; if (XFRM_MODE_SKB_CB(skb)->protocol != IPPROTO_IPIP) @@ -143,9 +78,6 @@ static int xfrm4_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb) if (!pskb_may_pull(skb, sizeof(struct iphdr))) goto out; - for_each_input_rcu(rcv_notify_handlers, handler) - handler->handler(skb); - err = skb_unclone(skb, GFP_ATOMIC); if (err) goto out; diff --git a/net/ipv4/xfrm4_protocol.c b/net/ipv4/xfrm4_protocol.c new file mode 100644 index 000000000000..cdc09efca442 --- /dev/null +++ b/net/ipv4/xfrm4_protocol.c @@ -0,0 +1,275 @@ +/* xfrm4_protocol.c - Generic xfrm protocol multiplexer. + * + * Copyright (C) 2013 secunet Security Networks AG + * + * Author: + * Steffen Klassert <steffen.klassert@secunet.com> + * + * Based on: + * net/ipv4/tunnel4.c + * + * 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 <linux/init.h> +#include <linux/mutex.h> +#include <linux/skbuff.h> +#include <net/icmp.h> +#include <net/ip.h> +#include <net/protocol.h> +#include <net/xfrm.h> + +static struct xfrm4_protocol __rcu *esp4_handlers __read_mostly; +static struct xfrm4_protocol __rcu *ah4_handlers __read_mostly; +static struct xfrm4_protocol __rcu *ipcomp4_handlers __read_mostly; +static DEFINE_MUTEX(xfrm4_protocol_mutex); + +static inline struct xfrm4_protocol __rcu **proto_handlers(u8 protocol) +{ + switch (protocol) { + case IPPROTO_ESP: + return &esp4_handlers; + case IPPROTO_AH: + return &ah4_handlers; + case IPPROTO_COMP: + return &ipcomp4_handlers; + } + + return NULL; +} + +#define for_each_protocol_rcu(head, handler) \ + for (handler = rcu_dereference(head); \ + handler != NULL; \ + handler = rcu_dereference(handler->next)) \ + +int xfrm4_rcv_cb(struct sk_buff *skb, u8 protocol, int err) +{ + int ret; + struct xfrm4_protocol *handler; + + for_each_protocol_rcu(*proto_handlers(protocol), handler) + if ((ret = handler->cb_handler(skb, err)) <= 0) + return ret; + + return 0; +} +EXPORT_SYMBOL(xfrm4_rcv_cb); + +int xfrm4_rcv_encap(struct sk_buff *skb, int nexthdr, __be32 spi, + int encap_type) +{ + int ret; + struct xfrm4_protocol *handler; + + XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL; + XFRM_SPI_SKB_CB(skb)->family = AF_INET; + XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr); + + for_each_protocol_rcu(*proto_handlers(nexthdr), handler) + if ((ret = handler->input_handler(skb, nexthdr, spi, encap_type)) != -EINVAL) + return ret; + + icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); + + kfree_skb(skb); + return 0; +} +EXPORT_SYMBOL(xfrm4_rcv_encap); + +static int xfrm4_esp_rcv(struct sk_buff *skb) +{ + int ret; + struct xfrm4_protocol *handler; + + XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL; + + for_each_protocol_rcu(esp4_handlers, handler) + if ((ret = handler->handler(skb)) != -EINVAL) + return ret; + + icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); + + kfree_skb(skb); + return 0; +} + +static void xfrm4_esp_err(struct sk_buff *skb, u32 info) +{ + struct xfrm4_protocol *handler; + + for_each_protocol_rcu(esp4_handlers, handler) + if (!handler->err_handler(skb, info)) + break; +} + +static int xfrm4_ah_rcv(struct sk_buff *skb) +{ + int ret; + struct xfrm4_protocol *handler; + + XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL; + + for_each_protocol_rcu(ah4_handlers, handler) + if ((ret = handler->handler(skb)) != -EINVAL) + return ret;; + + icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); + + kfree_skb(skb); + return 0; +} + +static void xfrm4_ah_err(struct sk_buff *skb, u32 info) +{ + struct xfrm4_protocol *handler; + + for_each_protocol_rcu(ah4_handlers, handler) + if (!handler->err_handler(skb, info)) + break; +} + +static int xfrm4_ipcomp_rcv(struct sk_buff *skb) +{ + int ret; + struct xfrm4_protocol *handler; + + XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL; + + for_each_protocol_rcu(ipcomp4_handlers, handler) + if ((ret = handler->handler(skb)) != -EINVAL) + return ret; + + icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); + + kfree_skb(skb); + return 0; +} + +static void xfrm4_ipcomp_err(struct sk_buff *skb, u32 info) +{ + struct xfrm4_protocol *handler; + + for_each_protocol_rcu(ipcomp4_handlers, handler) + if (!handler->err_handler(skb, info)) + break; +} + +static const struct net_protocol esp4_protocol = { + .handler = xfrm4_esp_rcv, + .err_handler = xfrm4_esp_err, + .no_policy = 1, + .netns_ok = 1, +}; + +static const struct net_protocol ah4_protocol = { + .handler = xfrm4_ah_rcv, + .err_handler = xfrm4_ah_err, + .no_policy = 1, + .netns_ok = 1, +}; + +static const struct net_protocol ipcomp4_protocol = { + .handler = xfrm4_ipcomp_rcv, + .err_handler = xfrm4_ipcomp_err, + .no_policy = 1, + .netns_ok = 1, +}; + +static inline const struct net_protocol *netproto(unsigned char protocol) +{ + switch (protocol) { + case IPPROTO_ESP: + return &esp4_protocol; + case IPPROTO_AH: + return &ah4_protocol; + case IPPROTO_COMP: + return &ipcomp4_protocol; + } + + return NULL; +} + +int xfrm4_protocol_register(struct xfrm4_protocol *handler, + unsigned char protocol) +{ + struct xfrm4_protocol __rcu **pprev; + struct xfrm4_protocol *t; + bool add_netproto = false; + + int ret = -EEXIST; + int priority = handler->priority; + + mutex_lock(&xfrm4_protocol_mutex); + + if (!rcu_dereference_protected(*proto_handlers(protocol), + lockdep_is_held(&xfrm4_protocol_mutex))) + add_netproto = true; + + for (pprev = proto_handlers(protocol); + (t = rcu_dereference_protected(*pprev, + lockdep_is_held(&xfrm4_protocol_mutex))) != NULL; + pprev = &t->next) { + if (t->priority < priority) + break; + if (t->priority == priority) + goto err; + } + + handler->next = *pprev; + rcu_assign_pointer(*pprev, handler); + + ret = 0; + +err: + mutex_unlock(&xfrm4_protocol_mutex); + + if (add_netproto) { + if (inet_add_protocol(netproto(protocol), protocol)) { + pr_err("%s: can't add protocol\n", __func__); + ret = -EAGAIN; + } + } + + return ret; +} +EXPORT_SYMBOL(xfrm4_protocol_register); + +int xfrm4_protocol_deregister(struct xfrm4_protocol *handler, + unsigned char protocol) +{ + struct xfrm4_protocol __rcu **pprev; + struct xfrm4_protocol *t; + int ret = -ENOENT; + + mutex_lock(&xfrm4_protocol_mutex); + + for (pprev = proto_handlers(protocol); + (t = rcu_dereference_protected(*pprev, + lockdep_is_held(&xfrm4_protocol_mutex))) != NULL; + pprev = &t->next) { + if (t == handler) { + *pprev = handler->next; + ret = 0; + break; + } + } + + if (!rcu_dereference_protected(*proto_handlers(protocol), + lockdep_is_held(&xfrm4_protocol_mutex))) { + if (inet_del_protocol(netproto(protocol), protocol) < 0) { + pr_err("%s: can't remove protocol\n", __func__); + ret = -EAGAIN; + } + } + + mutex_unlock(&xfrm4_protocol_mutex); + + synchronize_net(); + + return ret; +} +EXPORT_SYMBOL(xfrm4_protocol_deregister); diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig index d92e5586783e..438a73aa777c 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -138,6 +138,7 @@ config INET6_XFRM_MODE_ROUTEOPTIMIZATION config IPV6_VTI tristate "Virtual (secure) IPv6: tunneling" select IPV6_TUNNEL + select NET_IP_TUNNEL depends on INET6_XFRM_MODE_TUNNEL ---help--- Tunneling means encapsulating data of one protocol type within diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index ad235690684c..fdbfeca36d63 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -2783,6 +2783,8 @@ static void addrconf_gre_config(struct net_device *dev) ipv6_addr_set(&addr, htonl(0xFE800000), 0, 0, 0); if (!ipv6_generate_eui64(addr.s6_addr + 8, dev)) addrconf_add_linklocal(idev, &addr); + else + addrconf_prefix_route(&addr, 64, dev, 0, 0); } #endif diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c index b30ad3741b46..731e1e1722d9 100644 --- a/net/ipv6/addrlabel.c +++ b/net/ipv6/addrlabel.c @@ -6,7 +6,7 @@ */ /* * Author: - * YOSHIFUJI Hideaki @ USAGI/WIDE Project <yoshfuji@linux-ipv6.org> + * YOSHIFUJI Hideaki @ USAGI/WIDE Project <yoshfuji@linux-ipv6.org> */ #include <linux/kernel.h> @@ -22,14 +22,13 @@ #if 0 #define ADDRLABEL(x...) printk(x) #else -#define ADDRLABEL(x...) do { ; } while(0) +#define ADDRLABEL(x...) do { ; } while (0) #endif /* * Policy Table */ -struct ip6addrlbl_entry -{ +struct ip6addrlbl_entry { #ifdef CONFIG_NET_NS struct net *lbl_net; #endif @@ -88,39 +87,39 @@ static const __net_initconst struct ip6addrlbl_init_table { /* ::/0 */ .prefix = &in6addr_any, .label = 1, - },{ /* fc00::/7 */ - .prefix = &(struct in6_addr){{{ 0xfc }}}, + }, { /* fc00::/7 */ + .prefix = &(struct in6_addr){ { { 0xfc } } } , .prefixlen = 7, .label = 5, - },{ /* fec0::/10 */ - .prefix = &(struct in6_addr){{{ 0xfe, 0xc0 }}}, + }, { /* fec0::/10 */ + .prefix = &(struct in6_addr){ { { 0xfe, 0xc0 } } }, .prefixlen = 10, .label = 11, - },{ /* 2002::/16 */ - .prefix = &(struct in6_addr){{{ 0x20, 0x02 }}}, + }, { /* 2002::/16 */ + .prefix = &(struct in6_addr){ { { 0x20, 0x02 } } }, .prefixlen = 16, .label = 2, - },{ /* 3ffe::/16 */ - .prefix = &(struct in6_addr){{{ 0x3f, 0xfe }}}, + }, { /* 3ffe::/16 */ + .prefix = &(struct in6_addr){ { { 0x3f, 0xfe } } }, .prefixlen = 16, .label = 12, - },{ /* 2001::/32 */ - .prefix = &(struct in6_addr){{{ 0x20, 0x01 }}}, + }, { /* 2001::/32 */ + .prefix = &(struct in6_addr){ { { 0x20, 0x01 } } }, .prefixlen = 32, .label = 6, - },{ /* 2001:10::/28 */ - .prefix = &(struct in6_addr){{{ 0x20, 0x01, 0x00, 0x10 }}}, + }, { /* 2001:10::/28 */ + .prefix = &(struct in6_addr){ { { 0x20, 0x01, 0x00, 0x10 } } }, .prefixlen = 28, .label = 7, - },{ /* ::ffff:0:0 */ - .prefix = &(struct in6_addr){{{ [10] = 0xff, [11] = 0xff }}}, + }, { /* ::ffff:0:0 */ + .prefix = &(struct in6_addr){ { { [10] = 0xff, [11] = 0xff } } }, .prefixlen = 96, .label = 4, - },{ /* ::/96 */ + }, { /* ::/96 */ .prefix = &in6addr_any, .prefixlen = 96, .label = 3, - },{ /* ::1/128 */ + }, { /* ::1/128 */ .prefix = &in6addr_loopback, .prefixlen = 128, .label = 0, @@ -441,7 +440,7 @@ static int ip6addrlbl_newdel(struct sk_buff *skb, struct nlmsghdr *nlh) if (label == IPV6_ADDR_LABEL_DEFAULT) return -EINVAL; - switch(nlh->nlmsg_type) { + switch (nlh->nlmsg_type) { case RTM_NEWADDRLABEL: if (ifal->ifal_index && !__dev_get_by_index(net, ifal->ifal_index)) @@ -505,12 +504,13 @@ static int ip6addrlbl_dump(struct sk_buff *skb, struct netlink_callback *cb) hlist_for_each_entry_rcu(p, &ip6addrlbl_table.head, list) { if (idx >= s_idx && net_eq(ip6addrlbl_net(p), net)) { - if ((err = ip6addrlbl_fill(skb, p, - ip6addrlbl_table.seq, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - RTM_NEWADDRLABEL, - NLM_F_MULTI)) <= 0) + err = ip6addrlbl_fill(skb, p, + ip6addrlbl_table.seq, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + RTM_NEWADDRLABEL, + NLM_F_MULTI); + if (err <= 0) break; } idx++; @@ -527,7 +527,7 @@ static inline int ip6addrlbl_msgsize(void) + nla_total_size(4); /* IFAL_LABEL */ } -static int ip6addrlbl_get(struct sk_buff *in_skb, struct nlmsghdr* nlh) +static int ip6addrlbl_get(struct sk_buff *in_skb, struct nlmsghdr *nlh) { struct net *net = sock_net(in_skb->sk); struct ifaddrlblmsg *ifal; @@ -568,7 +568,8 @@ static int ip6addrlbl_get(struct sk_buff *in_skb, struct nlmsghdr* nlh) goto out; } - if (!(skb = nlmsg_new(ip6addrlbl_msgsize(), GFP_KERNEL))) { + skb = nlmsg_new(ip6addrlbl_msgsize(), GFP_KERNEL); + if (!skb) { ip6addrlbl_put(p); return -ENOBUFS; } diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index 81e496a2e008..6c5f0949e0ab 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -346,6 +346,10 @@ static int ah6_output(struct xfrm_state *x, struct sk_buff *skb) struct ip_auth_hdr *ah; struct ah_data *ahp; struct tmp_ext *iph_ext; + int seqhi_len = 0; + __be32 *seqhi; + int sglists = 0; + struct scatterlist *seqhisg; ahp = x->data; ahash = ahp->ahash; @@ -359,15 +363,22 @@ static int ah6_output(struct xfrm_state *x, struct sk_buff *skb) if (extlen) extlen += sizeof(*iph_ext); + if (x->props.flags & XFRM_STATE_ESN) { + sglists = 1; + seqhi_len = sizeof(*seqhi); + } err = -ENOMEM; - iph_base = ah_alloc_tmp(ahash, nfrags, IPV6HDR_BASELEN + extlen); + iph_base = ah_alloc_tmp(ahash, nfrags + sglists, IPV6HDR_BASELEN + + extlen + seqhi_len); if (!iph_base) goto out; iph_ext = ah_tmp_ext(iph_base); - icv = ah_tmp_icv(ahash, iph_ext, extlen); + seqhi = (__be32 *)((char *)iph_ext + extlen); + icv = ah_tmp_icv(ahash, seqhi, seqhi_len); req = ah_tmp_req(ahash, icv); sg = ah_req_sg(ahash, req); + seqhisg = sg + nfrags; ah = ip_auth_hdr(skb); memset(ah->auth_data, 0, ahp->icv_trunc_len); @@ -411,10 +422,15 @@ static int ah6_output(struct xfrm_state *x, struct sk_buff *skb) ah->spi = x->id.spi; ah->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.low); - sg_init_table(sg, nfrags); - skb_to_sgvec(skb, sg, 0, skb->len); + sg_init_table(sg, nfrags + sglists); + skb_to_sgvec_nomark(skb, sg, 0, skb->len); - ahash_request_set_crypt(req, sg, icv, skb->len); + if (x->props.flags & XFRM_STATE_ESN) { + /* Attach seqhi sg right after packet payload */ + *seqhi = htonl(XFRM_SKB_CB(skb)->seq.output.hi); + sg_set_buf(seqhisg, seqhi, seqhi_len); + } + ahash_request_set_crypt(req, sg, icv, skb->len + seqhi_len); ahash_request_set_callback(req, 0, ah6_output_done, skb); AH_SKB_CB(skb)->tmp = iph_base; @@ -514,6 +530,10 @@ static int ah6_input(struct xfrm_state *x, struct sk_buff *skb) int nexthdr; int nfrags; int err = -ENOMEM; + int seqhi_len = 0; + __be32 *seqhi; + int sglists = 0; + struct scatterlist *seqhisg; if (!pskb_may_pull(skb, sizeof(struct ip_auth_hdr))) goto out; @@ -550,14 +570,22 @@ static int ah6_input(struct xfrm_state *x, struct sk_buff *skb) skb_push(skb, hdr_len); - work_iph = ah_alloc_tmp(ahash, nfrags, hdr_len + ahp->icv_trunc_len); + if (x->props.flags & XFRM_STATE_ESN) { + sglists = 1; + seqhi_len = sizeof(*seqhi); + } + + work_iph = ah_alloc_tmp(ahash, nfrags + sglists, hdr_len + + ahp->icv_trunc_len + seqhi_len); if (!work_iph) goto out; - auth_data = ah_tmp_auth(work_iph, hdr_len); - icv = ah_tmp_icv(ahash, auth_data, ahp->icv_trunc_len); + auth_data = ah_tmp_auth((u8 *)work_iph, hdr_len); + seqhi = (__be32 *)(auth_data + ahp->icv_trunc_len); + icv = ah_tmp_icv(ahash, seqhi, seqhi_len); req = ah_tmp_req(ahash, icv); sg = ah_req_sg(ahash, req); + seqhisg = sg + nfrags; memcpy(work_iph, ip6h, hdr_len); memcpy(auth_data, ah->auth_data, ahp->icv_trunc_len); @@ -572,10 +600,16 @@ static int ah6_input(struct xfrm_state *x, struct sk_buff *skb) ip6h->flow_lbl[2] = 0; ip6h->hop_limit = 0; - sg_init_table(sg, nfrags); - skb_to_sgvec(skb, sg, 0, skb->len); + sg_init_table(sg, nfrags + sglists); + skb_to_sgvec_nomark(skb, sg, 0, skb->len); + + if (x->props.flags & XFRM_STATE_ESN) { + /* Attach seqhi sg right after packet payload */ + *seqhi = XFRM_SKB_CB(skb)->seq.input.hi; + sg_set_buf(seqhisg, seqhi, seqhi_len); + } - ahash_request_set_crypt(req, sg, icv, skb->len); + ahash_request_set_crypt(req, sg, icv, skb->len + seqhi_len); ahash_request_set_callback(req, 0, ah6_input_done, skb); AH_SKB_CB(skb)->tmp = work_iph; diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c index 140748debc4a..8af3eb57f438 100644 --- a/net/ipv6/exthdrs_core.c +++ b/net/ipv6/exthdrs_core.c @@ -212,7 +212,7 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset, found = (nexthdr == target); if ((!ipv6_ext_hdr(nexthdr)) || nexthdr == NEXTHDR_NONE) { - if (target < 0) + if (target < 0 || found) break; return -ENOENT; } diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index f81f59686f21..f2610e157660 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -414,7 +414,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) addr_type = ipv6_addr_type(&hdr->daddr); if (ipv6_chk_addr(net, &hdr->daddr, skb->dev, 0) || - ipv6_anycast_destination(skb)) + ipv6_chk_acast_addr_src(net, skb->dev, &hdr->daddr)) saddr = &hdr->daddr; /* diff --git a/net/ipv6/ip6_checksum.c b/net/ipv6/ip6_checksum.c index 72d198b8e4d2..ee7a97f510cb 100644 --- a/net/ipv6/ip6_checksum.c +++ b/net/ipv6/ip6_checksum.c @@ -79,7 +79,9 @@ int udp6_csum_init(struct sk_buff *skb, struct udphdr *uh, int proto) /* RFC 2460 section 8.1 says that we SHOULD log this error. Well, it is reasonable. */ - LIMIT_NETDEBUG(KERN_INFO "IPv6: udp checksum is 0\n"); + LIMIT_NETDEBUG(KERN_INFO "IPv6: udp checksum is 0 for [%pI6c]:%u->[%pI6c]:%u\n", + &ipv6_hdr(skb)->saddr, ntohs(uh->source), + &ipv6_hdr(skb)->daddr, ntohs(uh->dest)); return 1; } if (skb->ip_summed == CHECKSUM_COMPLETE && diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index dfa41bb4e0dc..0961b5ef866d 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -15,9 +15,7 @@ #include <linux/socket.h> #include <linux/net.h> #include <linux/netdevice.h> -#include <linux/if_arp.h> #include <linux/in6.h> -#include <linux/route.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/slab.h> @@ -28,12 +26,8 @@ #include <net/sock.h> #include <net/ipv6.h> -#include <net/ndisc.h> -#include <net/protocol.h> -#include <net/ip6_route.h> #include <net/addrconf.h> #include <net/rawv6.h> -#include <net/icmp.h> #include <net/transp_v6.h> #include <asm/uaccess.h> diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index f3ffb43f59c0..c98338b81d30 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1454,7 +1454,6 @@ static void ip6gre_netlink_parms(struct nlattr *data[], static int ip6gre_tap_init(struct net_device *dev) { struct ip6_tnl *tunnel; - int i; tunnel = netdev_priv(dev); @@ -1464,16 +1463,10 @@ static int ip6gre_tap_init(struct net_device *dev) ip6gre_tnl_link_config(tunnel, 1); - dev->tstats = alloc_percpu(struct pcpu_sw_netstats); + dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); if (!dev->tstats) return -ENOMEM; - for_each_possible_cpu(i) { - struct pcpu_sw_netstats *ip6gre_tap_stats; - ip6gre_tap_stats = per_cpu_ptr(dev->tstats, i); - u64_stats_init(&ip6gre_tap_stats->syncp); - } - return 0; } diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index 1e8683b135bb..59f95affceb0 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -89,7 +89,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, unsigned int unfrag_ip6hlen; u8 *prevhdr; int offset = 0; - bool tunnel; + bool encap, udpfrag; int nhoff; if (unlikely(skb_shinfo(skb)->gso_type & @@ -110,8 +110,8 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h)))) goto out; - tunnel = SKB_GSO_CB(skb)->encap_level > 0; - if (tunnel) + encap = SKB_GSO_CB(skb)->encap_level > 0; + if (encap) features = skb->dev->hw_enc_features & netif_skb_features(skb); SKB_GSO_CB(skb)->encap_level += sizeof(*ipv6h); @@ -121,6 +121,12 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, proto = ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr); + if (skb->encapsulation && + skb_shinfo(skb)->gso_type & (SKB_GSO_SIT|SKB_GSO_IPIP)) + udpfrag = proto == IPPROTO_UDP && encap; + else + udpfrag = proto == IPPROTO_UDP && !skb->encapsulation; + ops = rcu_dereference(inet6_offloads[proto]); if (likely(ops && ops->callbacks.gso_segment)) { skb_reset_transport_header(skb); @@ -133,13 +139,9 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, for (skb = segs; skb; skb = skb->next) { ipv6h = (struct ipv6hdr *)(skb_mac_header(skb) + nhoff); ipv6h->payload_len = htons(skb->len - nhoff - sizeof(*ipv6h)); - if (tunnel) { - skb_reset_inner_headers(skb); - skb->encapsulation = 1; - } skb->network_header = (u8 *)ipv6h - skb->head; - if (!tunnel && proto == IPPROTO_UDP) { + if (udpfrag) { unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr); fptr = (struct frag_hdr *)((u8 *)ipv6h + unfrag_ip6hlen); fptr->frag_off = htons(offset); @@ -148,6 +150,8 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, offset += (ntohs(ipv6h->payload_len) - sizeof(struct frag_hdr)); } + if (encap) + skb_reset_inner_headers(skb); } out: diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index ef02b26ccf81..90dd551fdd3c 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -342,6 +342,20 @@ static unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst) return mtu; } +static bool ip6_pkt_too_big(const struct sk_buff *skb, unsigned int mtu) +{ + if (skb->len <= mtu || skb->local_df) + return false; + + if (IP6CB(skb)->frag_max_size && IP6CB(skb)->frag_max_size > mtu) + return true; + + if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu) + return false; + + return true; +} + int ip6_forward(struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); @@ -353,6 +367,9 @@ int ip6_forward(struct sk_buff *skb) if (net->ipv6.devconf_all->forwarding == 0) goto error; + if (skb->pkt_type != PACKET_HOST) + goto drop; + if (skb_warn_if_lro(skb)) goto drop; @@ -362,9 +379,6 @@ int ip6_forward(struct sk_buff *skb) goto drop; } - if (skb->pkt_type != PACKET_HOST) - goto drop; - skb_forward_csum(skb); /* @@ -466,8 +480,7 @@ int ip6_forward(struct sk_buff *skb) if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; - if ((!skb->local_df && skb->len > mtu && !skb_is_gso(skb)) || - (IP6CB(skb)->frag_max_size && IP6CB(skb)->frag_max_size > mtu)) { + if (ip6_pkt_too_big(skb, mtu)) { /* Again, force OUTPUT device used as source address */ skb->dev = dst->dev; icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); @@ -517,9 +530,6 @@ static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from) to->tc_index = from->tc_index; #endif nf_copy(to, from); -#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) - to->nf_trace = from->nf_trace; -#endif skb_copy_secmark(to, from); } @@ -1221,8 +1231,10 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, sizeof(struct frag_hdr) : 0) + rt->rt6i_nfheader_len; - maxnonfragsize = (np->pmtudisc >= IPV6_PMTUDISC_DO) ? - mtu : sizeof(struct ipv6hdr) + IPV6_MAXPLEN; + if (ip6_sk_local_df(sk)) + maxnonfragsize = sizeof(struct ipv6hdr) + IPV6_MAXPLEN; + else + maxnonfragsize = mtu; /* dontfrag active */ if ((cork->length + length > mtu - headersize) && dontfrag && @@ -1530,8 +1542,7 @@ int ip6_push_pending_frames(struct sock *sk) } /* Allow local fragmentation. */ - if (np->pmtudisc < IPV6_PMTUDISC_DO) - skb->local_df = 1; + skb->local_df = ip6_sk_local_df(sk); *final_dst = fl6->daddr; __skb_pull(skb, skb_network_header_len(skb)); diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 5db8d310f9c0..8ad59f4811df 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1502,19 +1502,12 @@ static inline int ip6_tnl_dev_init_gen(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); - int i; t->dev = dev; t->net = dev_net(dev); - dev->tstats = alloc_percpu(struct pcpu_sw_netstats); + dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); if (!dev->tstats) return -ENOMEM; - - for_each_possible_cpu(i) { - struct pcpu_sw_netstats *ip6_tnl_stats; - ip6_tnl_stats = per_cpu_ptr(dev->tstats, i); - u64_stats_init(&ip6_tnl_stats->syncp); - } return 0; } diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index 2d19272b8cee..864914399391 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -731,18 +731,12 @@ static void vti6_dev_setup(struct net_device *dev) static inline int vti6_dev_init_gen(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); - int i; t->dev = dev; t->net = dev_net(dev); - dev->tstats = alloc_percpu(struct pcpu_sw_netstats); + dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); if (!dev->tstats) return -ENOMEM; - for_each_possible_cpu(i) { - struct pcpu_sw_netstats *stats; - stats = per_cpu_ptr(dev->tstats, i); - u64_stats_init(&stats->syncp); - } return 0; } diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 0a00f449de5e..edb58aff4ae7 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -722,7 +722,7 @@ done: case IPV6_MTU_DISCOVER: if (optlen < sizeof(int)) goto e_inval; - if (val < IPV6_PMTUDISC_DONT || val > IPV6_PMTUDISC_INTERFACE) + if (val < IPV6_PMTUDISC_DONT || val > IPV6_PMTUDISC_OMIT) goto e_inval; np->pmtudisc = val; retv = 0; diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig index 35750df744dc..4bff1f297e39 100644 --- a/net/ipv6/netfilter/Kconfig +++ b/net/ipv6/netfilter/Kconfig @@ -50,6 +50,11 @@ config NFT_CHAIN_NAT_IPV6 packet transformations such as the source, destination address and source and destination ports. +config NFT_REJECT_IPV6 + depends on NF_TABLES_IPV6 + default NFT_REJECT + tristate + config IP6_NF_IPTABLES tristate "IP6 tables support (required for filtering)" depends on INET && IPV6 diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile index d1b4928f34f7..70d3dd66f2cd 100644 --- a/net/ipv6/netfilter/Makefile +++ b/net/ipv6/netfilter/Makefile @@ -27,6 +27,7 @@ obj-$(CONFIG_NF_DEFRAG_IPV6) += nf_defrag_ipv6.o obj-$(CONFIG_NF_TABLES_IPV6) += nf_tables_ipv6.o obj-$(CONFIG_NFT_CHAIN_ROUTE_IPV6) += nft_chain_route_ipv6.o obj-$(CONFIG_NFT_CHAIN_NAT_IPV6) += nft_chain_nat_ipv6.o +obj-$(CONFIG_NFT_REJECT_IPV6) += nft_reject_ipv6.o # matches obj-$(CONFIG_IP6_NF_MATCH_AH) += ip6t_ah.o diff --git a/net/ipv6/netfilter/nft_reject_ipv6.c b/net/ipv6/netfilter/nft_reject_ipv6.c new file mode 100644 index 000000000000..0bc19fa87821 --- /dev/null +++ b/net/ipv6/netfilter/nft_reject_ipv6.c @@ -0,0 +1,76 @@ +/* + * Copyright (c) 2008-2009 Patrick McHardy <kaber@trash.net> + * Copyright (c) 2013 Eric Leblond <eric@regit.org> + * + * 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. + * + * Development of this code funded by Astaro AG (http://www.astaro.com/) + */ + +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/netlink.h> +#include <linux/netfilter.h> +#include <linux/netfilter/nf_tables.h> +#include <net/netfilter/nf_tables.h> +#include <net/netfilter/nft_reject.h> +#include <net/netfilter/ipv6/nf_reject.h> + +void nft_reject_ipv6_eval(const struct nft_expr *expr, + struct nft_data data[NFT_REG_MAX + 1], + const struct nft_pktinfo *pkt) +{ + struct nft_reject *priv = nft_expr_priv(expr); + struct net *net = dev_net((pkt->in != NULL) ? pkt->in : pkt->out); + + switch (priv->type) { + case NFT_REJECT_ICMP_UNREACH: + nf_send_unreach6(net, pkt->skb, priv->icmp_code, + pkt->ops->hooknum); + break; + case NFT_REJECT_TCP_RST: + nf_send_reset6(net, pkt->skb, pkt->ops->hooknum); + break; + } + + data[NFT_REG_VERDICT].verdict = NF_DROP; +} +EXPORT_SYMBOL_GPL(nft_reject_ipv6_eval); + +static struct nft_expr_type nft_reject_ipv6_type; +static const struct nft_expr_ops nft_reject_ipv6_ops = { + .type = &nft_reject_ipv6_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_reject)), + .eval = nft_reject_ipv6_eval, + .init = nft_reject_init, + .dump = nft_reject_dump, +}; + +static struct nft_expr_type nft_reject_ipv6_type __read_mostly = { + .family = NFPROTO_IPV6, + .name = "reject", + .ops = &nft_reject_ipv6_ops, + .policy = nft_reject_policy, + .maxattr = NFTA_REJECT_MAX, + .owner = THIS_MODULE, +}; + +static int __init nft_reject_ipv6_module_init(void) +{ + return nft_register_expr(&nft_reject_ipv6_type); +} + +static void __exit nft_reject_ipv6_module_exit(void) +{ + nft_unregister_expr(&nft_reject_ipv6_type); +} + +module_init(nft_reject_ipv6_module_init); +module_exit(nft_reject_ipv6_module_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); +MODULE_ALIAS_NFT_AF_EXPR(AF_INET6, "reject"); diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c index 827f795209cf..d1b35d377e62 100644 --- a/net/ipv6/output_core.c +++ b/net/ipv6/output_core.c @@ -13,7 +13,7 @@ void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt) int old, new; #if IS_ENABLED(CONFIG_IPV6) - if (rt && !(rt->dst.flags & DST_NOPEER)) { + if (rt) { struct inet_peer *peer; struct net *net; diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index fb9beb78f00b..587bbdcb22b4 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -135,6 +135,7 @@ int ping_v6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, fl6.flowi6_proto = IPPROTO_ICMPV6; fl6.saddr = np->saddr; fl6.daddr = *daddr; + fl6.flowi6_mark = sk->sk_mark; fl6.fl6_icmp_type = user_icmph.icmp6_type; fl6.fl6_icmp_code = user_icmph.icmp6_code; security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 3dfbcf1dcb1c..1693c8d885f0 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -475,6 +475,7 @@ static void ipip6_tunnel_uninit(struct net_device *dev) ipip6_tunnel_unlink(sitn, tunnel); ipip6_tunnel_del_prl(tunnel, NULL); } + ip_tunnel_dst_reset_all(tunnel); dev_put(dev); } @@ -1082,6 +1083,7 @@ static void ipip6_tunnel_update(struct ip_tunnel *t, struct ip_tunnel_parm *p) t->parms.link = p->link; ipip6_tunnel_bind_dev(t->dev); } + ip_tunnel_dst_reset_all(t); netdev_state_change(t->dev); } @@ -1112,6 +1114,7 @@ static int ipip6_tunnel_update_6rd(struct ip_tunnel *t, t->ip6rd.relay_prefix = relay_prefix; t->ip6rd.prefixlen = ip6rd->prefixlen; t->ip6rd.relay_prefixlen = ip6rd->relay_prefixlen; + ip_tunnel_dst_reset_all(t); netdev_state_change(t->dev); return 0; } @@ -1271,6 +1274,7 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) err = ipip6_tunnel_add_prl(t, &prl, cmd == SIOCCHGPRL); break; } + ip_tunnel_dst_reset_all(t); netdev_state_change(dev); break; @@ -1326,6 +1330,9 @@ static const struct net_device_ops ipip6_netdev_ops = { static void ipip6_dev_free(struct net_device *dev) { + struct ip_tunnel *tunnel = netdev_priv(dev); + + free_percpu(tunnel->dst_cache); free_percpu(dev->tstats); free_netdev(dev); } @@ -1356,7 +1363,6 @@ static void ipip6_tunnel_setup(struct net_device *dev) static int ipip6_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); - int i; tunnel->dev = dev; tunnel->net = dev_net(dev); @@ -1365,14 +1371,14 @@ static int ipip6_tunnel_init(struct net_device *dev) memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4); ipip6_tunnel_bind_dev(dev); - dev->tstats = alloc_percpu(struct pcpu_sw_netstats); + dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); if (!dev->tstats) return -ENOMEM; - for_each_possible_cpu(i) { - struct pcpu_sw_netstats *ipip6_tunnel_stats; - ipip6_tunnel_stats = per_cpu_ptr(dev->tstats, i); - u64_stats_init(&ipip6_tunnel_stats->syncp); + tunnel->dst_cache = alloc_percpu(struct ip_tunnel_dst); + if (!tunnel->dst_cache) { + free_percpu(dev->tstats); + return -ENOMEM; } return 0; @@ -1384,7 +1390,6 @@ static int __net_init ipip6_fb_tunnel_init(struct net_device *dev) struct iphdr *iph = &tunnel->parms.iph; struct net *net = dev_net(dev); struct sit_net *sitn = net_generic(net, sit_net_id); - int i; tunnel->dev = dev; tunnel->net = dev_net(dev); @@ -1395,14 +1400,14 @@ static int __net_init ipip6_fb_tunnel_init(struct net_device *dev) iph->ihl = 5; iph->ttl = 64; - dev->tstats = alloc_percpu(struct pcpu_sw_netstats); + dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); if (!dev->tstats) return -ENOMEM; - for_each_possible_cpu(i) { - struct pcpu_sw_netstats *ipip6_fb_stats; - ipip6_fb_stats = per_cpu_ptr(dev->tstats, i); - u64_stats_init(&ipip6_fb_stats->syncp); + tunnel->dst_cache = alloc_percpu(struct ip_tunnel_dst); + if (!tunnel->dst_cache) { + free_percpu(dev->tstats); + return -ENOMEM; } dev_hold(dev); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 889079b2ea85..3277680186b4 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -501,8 +501,10 @@ static int tcp_v6_rtx_synack(struct sock *sk, struct request_sock *req) int res; res = tcp_v6_send_synack(sk, NULL, &fl6, req, 0); - if (!res) + if (!res) { TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS); + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPSYNRETRANS); + } return res; } diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index e7359f9eaa8d..b261ee8b83fc 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -113,7 +113,7 @@ 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; - ipv6_select_ident(fptr, (struct rt6_info *)skb_dst(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/ipx/af_ipx.c b/net/ipx/af_ipx.c index 994e28bfb32e..41e4e93cb3aa 100644 --- a/net/ipx/af_ipx.c +++ b/net/ipx/af_ipx.c @@ -52,18 +52,12 @@ #include <net/p8022.h> #include <net/psnap.h> #include <net/sock.h> +#include <net/datalink.h> #include <net/tcp_states.h> +#include <net/net_namespace.h> #include <asm/uaccess.h> -#ifdef CONFIG_SYSCTL -extern void ipx_register_sysctl(void); -extern void ipx_unregister_sysctl(void); -#else -#define ipx_register_sysctl() -#define ipx_unregister_sysctl() -#endif - /* Configuration Variables */ static unsigned char ipxcfg_max_hops = 16; static char ipxcfg_auto_select_primary; @@ -84,15 +78,6 @@ DEFINE_SPINLOCK(ipx_interfaces_lock); struct ipx_interface *ipx_primary_net; struct ipx_interface *ipx_internal_net; -extern int ipxrtr_add_route(__be32 network, struct ipx_interface *intrfc, - unsigned char *node); -extern void ipxrtr_del_routes(struct ipx_interface *intrfc); -extern int ipxrtr_route_packet(struct sock *sk, struct sockaddr_ipx *usipx, - struct iovec *iov, size_t len, int noblock); -extern int ipxrtr_route_skb(struct sk_buff *skb); -extern struct ipx_route *ipxrtr_lookup(__be32 net); -extern int ipxrtr_ioctl(unsigned int cmd, void __user *arg); - struct ipx_interface *ipx_interfaces_head(void) { struct ipx_interface *rc = NULL; @@ -1383,6 +1368,7 @@ static int ipx_release(struct socket *sock) goto out; lock_sock(sk); + sk->sk_shutdown = SHUTDOWN_MASK; if (!sock_flag(sk, SOCK_DEAD)) sk->sk_state_change(sk); @@ -1806,8 +1792,11 @@ static int ipx_recvmsg(struct kiocb *iocb, struct socket *sock, skb = skb_recv_datagram(sk, flags & ~MSG_DONTWAIT, flags & MSG_DONTWAIT, &rc); - if (!skb) + if (!skb) { + if (rc == -EAGAIN && (sk->sk_shutdown & RCV_SHUTDOWN)) + rc = 0; goto out; + } ipx = ipx_hdr(skb); copied = ntohs(ipx->ipx_pktsize) - sizeof(struct ipxhdr); @@ -1937,6 +1926,26 @@ static int ipx_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long } #endif +static int ipx_shutdown(struct socket *sock, int mode) +{ + struct sock *sk = sock->sk; + + if (mode < SHUT_RD || mode > SHUT_RDWR) + return -EINVAL; + /* This maps: + * SHUT_RD (0) -> RCV_SHUTDOWN (1) + * SHUT_WR (1) -> SEND_SHUTDOWN (2) + * SHUT_RDWR (2) -> SHUTDOWN_MASK (3) + */ + ++mode; + + lock_sock(sk); + sk->sk_shutdown |= mode; + release_sock(sk); + sk->sk_state_change(sk); + + return 0; +} /* * Socket family declarations @@ -1963,7 +1972,7 @@ static const struct proto_ops ipx_dgram_ops = { .compat_ioctl = ipx_compat_ioctl, #endif .listen = sock_no_listen, - .shutdown = sock_no_shutdown, /* FIXME: support shutdown */ + .shutdown = ipx_shutdown, .setsockopt = ipx_setsockopt, .getsockopt = ipx_getsockopt, .sendmsg = ipx_sendmsg, @@ -1986,9 +1995,6 @@ static struct notifier_block ipx_dev_notifier = { .notifier_call = ipxitf_device_event, }; -extern struct datalink_proto *make_EII_client(void); -extern void destroy_EII_client(struct datalink_proto *); - static const unsigned char ipx_8022_type = 0xE0; static const unsigned char ipx_snap_id[5] = { 0x0, 0x0, 0x0, 0x81, 0x37 }; static const char ipx_EII_err_msg[] __initconst = diff --git a/net/ipx/ipx_route.c b/net/ipx/ipx_route.c index 30f4519b092f..c1f03185c5e1 100644 --- a/net/ipx/ipx_route.c +++ b/net/ipx/ipx_route.c @@ -20,15 +20,11 @@ DEFINE_RWLOCK(ipx_routes_lock); extern struct ipx_interface *ipx_internal_net; -extern __be16 ipx_cksum(struct ipxhdr *packet, int length); extern struct ipx_interface *ipxitf_find_using_net(__be32 net); extern int ipxitf_demux_socket(struct ipx_interface *intrfc, struct sk_buff *skb, int copy); extern int ipxitf_demux_socket(struct ipx_interface *intrfc, struct sk_buff *skb, int copy); -extern int ipxitf_send(struct ipx_interface *intrfc, struct sk_buff *skb, - char *node); -extern struct ipx_interface *ipxitf_find_using_net(__be32 net); struct ipx_route *ipxrtr_lookup(__be32 net) { diff --git a/net/key/af_key.c b/net/key/af_key.c index 1a04c1329362..a50d979b5926 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -365,6 +365,7 @@ static const u8 sadb_ext_min_len[] = { [SADB_X_EXT_NAT_T_OA] = (u8) sizeof(struct sadb_address), [SADB_X_EXT_SEC_CTX] = (u8) sizeof(struct sadb_x_sec_ctx), [SADB_X_EXT_KMADDRESS] = (u8) sizeof(struct sadb_x_kmaddress), + [SADB_X_EXT_FILTER] = (u8) sizeof(struct sadb_x_filter), }; /* Verify sadb_address_{len,prefixlen} against sa_family. */ @@ -1798,6 +1799,7 @@ static void pfkey_dump_sa_done(struct pfkey_sock *pfk) static int pfkey_dump(struct sock *sk, struct sk_buff *skb, const struct sadb_msg *hdr, void * const *ext_hdrs) { u8 proto; + struct xfrm_filter *filter = NULL; struct pfkey_sock *pfk = pfkey_sk(sk); if (pfk->dump.dump != NULL) @@ -1807,11 +1809,27 @@ static int pfkey_dump(struct sock *sk, struct sk_buff *skb, const struct sadb_ms if (proto == 0) return -EINVAL; + if (ext_hdrs[SADB_X_EXT_FILTER - 1]) { + struct sadb_x_filter *xfilter = ext_hdrs[SADB_X_EXT_FILTER - 1]; + + filter = kmalloc(sizeof(*filter), GFP_KERNEL); + if (filter == NULL) + return -ENOMEM; + + memcpy(&filter->saddr, &xfilter->sadb_x_filter_saddr, + sizeof(xfrm_address_t)); + memcpy(&filter->daddr, &xfilter->sadb_x_filter_daddr, + sizeof(xfrm_address_t)); + filter->family = xfilter->sadb_x_filter_family; + filter->splen = xfilter->sadb_x_filter_splen; + filter->dplen = xfilter->sadb_x_filter_dplen; + } + pfk->dump.msg_version = hdr->sadb_msg_version; pfk->dump.msg_portid = hdr->sadb_msg_pid; pfk->dump.dump = pfkey_dump_sa; pfk->dump.done = pfkey_dump_sa_done; - xfrm_state_walk_init(&pfk->dump.u.state, proto); + xfrm_state_walk_init(&pfk->dump.u.state, proto, filter); return pfkey_do_dump(pfk); } @@ -3059,6 +3077,24 @@ static u32 get_acqseq(void) return res; } +static bool pfkey_is_alive(const struct km_event *c) +{ + struct netns_pfkey *net_pfkey = net_generic(c->net, pfkey_net_id); + struct sock *sk; + bool is_alive = false; + + rcu_read_lock(); + sk_for_each_rcu(sk, &net_pfkey->table) { + if (pfkey_sk(sk)->registered) { + is_alive = true; + break; + } + } + rcu_read_unlock(); + + return is_alive; +} + static int pfkey_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_policy *xp) { struct sk_buff *skb; @@ -3784,6 +3820,7 @@ static struct xfrm_mgr pfkeyv2_mgr = .new_mapping = pfkey_send_new_mapping, .notify_policy = pfkey_send_policy_notify, .migrate = pfkey_send_migrate, + .is_alive = pfkey_is_alive, }; static int __net_init pfkey_net_init(struct net *net) diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 735d0f60c83a..dcab9ddc4388 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -1131,7 +1131,7 @@ static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, /* Queue the packet to IP for output */ skb->local_df = 1; #if IS_ENABLED(CONFIG_IPV6) - if (skb->sk->sk_family == PF_INET6 && !tunnel->v4mapped) + if (tunnel->sock->sk_family == PF_INET6 && !tunnel->v4mapped) error = inet6_csk_xmit(skb, NULL); else #endif @@ -1151,23 +1151,6 @@ static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, return 0; } -/* Automatically called when the skb is freed. - */ -static void l2tp_sock_wfree(struct sk_buff *skb) -{ - sock_put(skb->sk); -} - -/* For data skbs that we transmit, we associate with the tunnel socket - * but don't do accounting. - */ -static inline void l2tp_skb_set_owner_w(struct sk_buff *skb, struct sock *sk) -{ - sock_hold(sk); - skb->sk = sk; - skb->destructor = l2tp_sock_wfree; -} - #if IS_ENABLED(CONFIG_IPV6) static void l2tp_xmit_ipv6_csum(struct sock *sk, struct sk_buff *skb, int udp_len) @@ -1221,7 +1204,6 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len return NET_XMIT_DROP; } - skb_orphan(skb); /* Setup L2TP header */ session->build_header(session, __skb_push(skb, hdr_len)); @@ -1287,8 +1269,6 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len break; } - l2tp_skb_set_owner_w(skb, sk); - l2tp_xmit_core(session, skb, fl, data_len); out_unlock: bh_unlock_sock(sk); @@ -1809,8 +1789,6 @@ void l2tp_session_free(struct l2tp_session *session) } kfree(session); - - return; } EXPORT_SYMBOL_GPL(l2tp_session_free); diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index be5fadf34739..ec40bc344be6 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -454,13 +454,11 @@ static void pppol2tp_session_close(struct l2tp_session *session) BUG_ON(session->magic != L2TP_SESSION_MAGIC); - if (sock) { inet_shutdown(sock, 2); /* Don't let the session go away before our socket does */ l2tp_session_inc_refcount(session); } - return; } /* Really kill the session socket. (Called from sock_put() if @@ -474,7 +472,6 @@ static void pppol2tp_session_destruct(struct sock *sk) BUG_ON(session->magic != L2TP_SESSION_MAGIC); l2tp_session_dec_refcount(session); } - return; } /* Called when the PPPoX socket (session) is closed. diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index be198f42f1f7..b8d331e7d883 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -1054,7 +1054,8 @@ static void ieee80211_uninit(struct net_device *dev) static u16 ieee80211_netdev_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv) + void *accel_priv, + select_queue_fallback_t fallback) { return ieee80211_select_queue(IEEE80211_DEV_TO_SUB_IF(dev), skb); } @@ -1072,7 +1073,8 @@ static const struct net_device_ops ieee80211_dataif_ops = { static u16 ieee80211_monitor_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv) + void *accel_priv, + select_queue_fallback_t fallback) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; diff --git a/net/mac802154/ieee802154_dev.c b/net/mac802154/ieee802154_dev.c index 52ae6646a411..b75bb01e5c6b 100644 --- a/net/mac802154/ieee802154_dev.c +++ b/net/mac802154/ieee802154_dev.c @@ -165,6 +165,67 @@ err: return ERR_PTR(err); } +static int mac802154_set_txpower(struct wpan_phy *phy, int db) +{ + struct mac802154_priv *priv = wpan_phy_priv(phy); + + if (!priv->ops->set_txpower) + return -ENOTSUPP; + + return priv->ops->set_txpower(&priv->hw, db); +} + +static int mac802154_set_lbt(struct wpan_phy *phy, bool on) +{ + struct mac802154_priv *priv = wpan_phy_priv(phy); + + if (!priv->ops->set_lbt) + return -ENOTSUPP; + + return priv->ops->set_lbt(&priv->hw, on); +} + +static int mac802154_set_cca_mode(struct wpan_phy *phy, u8 mode) +{ + struct mac802154_priv *priv = wpan_phy_priv(phy); + + if (!priv->ops->set_cca_mode) + return -ENOTSUPP; + + return priv->ops->set_cca_mode(&priv->hw, mode); +} + +static int mac802154_set_cca_ed_level(struct wpan_phy *phy, s32 level) +{ + struct mac802154_priv *priv = wpan_phy_priv(phy); + + if (!priv->ops->set_cca_ed_level) + return -ENOTSUPP; + + return priv->ops->set_cca_ed_level(&priv->hw, level); +} + +static int mac802154_set_csma_params(struct wpan_phy *phy, u8 min_be, + u8 max_be, u8 retries) +{ + struct mac802154_priv *priv = wpan_phy_priv(phy); + + if (!priv->ops->set_csma_params) + return -ENOTSUPP; + + return priv->ops->set_csma_params(&priv->hw, min_be, max_be, retries); +} + +static int mac802154_set_frame_retries(struct wpan_phy *phy, s8 retries) +{ + struct mac802154_priv *priv = wpan_phy_priv(phy); + + if (!priv->ops->set_frame_retries) + return -ENOTSUPP; + + return priv->ops->set_frame_retries(&priv->hw, retries); +} + struct ieee802154_dev * ieee802154_alloc_device(size_t priv_data_len, struct ieee802154_ops *ops) { @@ -242,6 +303,12 @@ int ieee802154_register_device(struct ieee802154_dev *dev) priv->phy->add_iface = mac802154_add_iface; priv->phy->del_iface = mac802154_del_iface; + priv->phy->set_txpower = mac802154_set_txpower; + priv->phy->set_lbt = mac802154_set_lbt; + priv->phy->set_cca_mode = mac802154_set_cca_mode; + priv->phy->set_cca_ed_level = mac802154_set_cca_ed_level; + priv->phy->set_csma_params = mac802154_set_csma_params; + priv->phy->set_frame_retries = mac802154_set_frame_retries; rc = wpan_phy_register(priv->phy); if (rc < 0) diff --git a/net/mac802154/mib.c b/net/mac802154/mib.c index 8ded97cf1c33..f48f40c1da1a 100644 --- a/net/mac802154/mib.c +++ b/net/mac802154/mib.c @@ -62,8 +62,6 @@ static void hw_addr_notify(struct work_struct *work) pr_debug("failed changed mask %lx\n", nw->changed); kfree(nw); - - return; } static void set_hw_addr_filt(struct net_device *dev, unsigned long changed) @@ -79,8 +77,6 @@ static void set_hw_addr_filt(struct net_device *dev, unsigned long changed) work->dev = dev; work->changed = changed; queue_work(priv->hw->dev_workqueue, &work->work); - - return; } void mac802154_dev_set_short_addr(struct net_device *dev, u16 val) diff --git a/net/mac802154/rx.c b/net/mac802154/rx.c index 38548ec2098f..03855b0677cc 100644 --- a/net/mac802154/rx.c +++ b/net/mac802154/rx.c @@ -80,7 +80,6 @@ mac802154_subif_rx(struct ieee802154_dev *hw, struct sk_buff *skb, u8 lqi) mac802154_wpans_rx(priv, skb); out: dev_kfree_skb(skb); - return; } static void mac802154_rx_worker(struct work_struct *work) diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index c37467562fd0..e9410d17619d 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -513,7 +513,6 @@ config NFT_QUEUE config NFT_REJECT depends on NF_TABLES - depends on NF_TABLES_IPV6 || !NF_TABLES_IPV6 default m if NETFILTER_ADVANCED=n tristate "Netfilter nf_tables reject support" help @@ -521,6 +520,11 @@ config NFT_REJECT explicitly deny and notify via TCP reset/ICMP informational errors unallowed traffic. +config NFT_REJECT_INET + depends on NF_TABLES_INET + default NFT_REJECT + tristate + config NFT_COMPAT depends on NF_TABLES depends on NETFILTER_XTABLES diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index ee9c4de5f8ed..bffdad774da7 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -79,6 +79,7 @@ obj-$(CONFIG_NFT_LIMIT) += nft_limit.o obj-$(CONFIG_NFT_NAT) += nft_nat.o obj-$(CONFIG_NFT_QUEUE) += nft_queue.o obj-$(CONFIG_NFT_REJECT) += nft_reject.o +obj-$(CONFIG_NFT_REJECT_INET) += nft_reject_inet.o obj-$(CONFIG_NFT_RBTREE) += nft_rbtree.o obj-$(CONFIG_NFT_HASH) += nft_hash.o obj-$(CONFIG_NFT_COUNTER) += nft_counter.o diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index 59a1a85bcb3e..a8eb0a89326a 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -871,11 +871,11 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p, cp->protocol = p->protocol; ip_vs_addr_set(p->af, &cp->caddr, p->caddr); cp->cport = p->cport; - ip_vs_addr_set(p->af, &cp->vaddr, p->vaddr); - cp->vport = p->vport; - /* proto should only be IPPROTO_IP if d_addr is a fwmark */ + /* proto should only be IPPROTO_IP if p->vaddr is a fwmark */ ip_vs_addr_set(p->protocol == IPPROTO_IP ? AF_UNSPEC : p->af, - &cp->daddr, daddr); + &cp->vaddr, p->vaddr); + cp->vport = p->vport; + ip_vs_addr_set(p->af, &cp->daddr, daddr); cp->dport = dport; cp->flags = flags; cp->fwmark = fwmark; diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 8824ed0ccc9c..356bef519fe5 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -312,6 +312,21 @@ static void death_by_timeout(unsigned long ul_conntrack) nf_ct_delete((struct nf_conn *)ul_conntrack, 0, 0); } +static inline bool +nf_ct_key_equal(struct nf_conntrack_tuple_hash *h, + const struct nf_conntrack_tuple *tuple, + u16 zone) +{ + struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h); + + /* A conntrack can be recreated with the equal tuple, + * so we need to check that the conntrack is confirmed + */ + return nf_ct_tuple_equal(tuple, &h->tuple) && + nf_ct_zone(ct) == zone && + nf_ct_is_confirmed(ct); +} + /* * Warning : * - Caller must take a reference on returned object @@ -333,8 +348,7 @@ ____nf_conntrack_find(struct net *net, u16 zone, local_bh_disable(); begin: hlist_nulls_for_each_entry_rcu(h, n, &net->ct.hash[bucket], hnnode) { - if (nf_ct_tuple_equal(tuple, &h->tuple) && - nf_ct_zone(nf_ct_tuplehash_to_ctrack(h)) == zone) { + if (nf_ct_key_equal(h, tuple, zone)) { NF_CT_STAT_INC(net, found); local_bh_enable(); return h; @@ -372,8 +386,7 @@ begin: !atomic_inc_not_zero(&ct->ct_general.use))) h = NULL; else { - if (unlikely(!nf_ct_tuple_equal(tuple, &h->tuple) || - nf_ct_zone(ct) != zone)) { + if (unlikely(!nf_ct_key_equal(h, tuple, zone))) { nf_ct_put(ct); goto begin; } @@ -435,7 +448,9 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct) goto out; add_timer(&ct->timeout); - nf_conntrack_get(&ct->ct_general); + smp_wmb(); + /* The caller holds a reference to this object */ + atomic_set(&ct->ct_general.use, 2); __nf_conntrack_hash_insert(ct, hash, repl_hash); NF_CT_STAT_INC(net, insert); spin_unlock_bh(&nf_conntrack_lock); @@ -449,6 +464,21 @@ out: } EXPORT_SYMBOL_GPL(nf_conntrack_hash_check_insert); +/* deletion from this larval template list happens via nf_ct_put() */ +void nf_conntrack_tmpl_insert(struct net *net, struct nf_conn *tmpl) +{ + __set_bit(IPS_TEMPLATE_BIT, &tmpl->status); + __set_bit(IPS_CONFIRMED_BIT, &tmpl->status); + nf_conntrack_get(&tmpl->ct_general); + + spin_lock_bh(&nf_conntrack_lock); + /* Overload tuple linked list to put us in template list. */ + hlist_nulls_add_head_rcu(&tmpl->tuplehash[IP_CT_DIR_ORIGINAL].hnnode, + &net->ct.tmpl); + spin_unlock_bh(&nf_conntrack_lock); +} +EXPORT_SYMBOL_GPL(nf_conntrack_tmpl_insert); + /* Confirm a connection given skb; places it in hash table */ int __nf_conntrack_confirm(struct sk_buff *skb) @@ -720,11 +750,10 @@ __nf_conntrack_alloc(struct net *net, u16 zone, nf_ct_zone->id = zone; } #endif - /* - * changes to lookup keys must be done before setting refcnt to 1 + /* Because we use RCU lookups, we set ct_general.use to zero before + * this is inserted in any list. */ - smp_wmb(); - atomic_set(&ct->ct_general.use, 1); + atomic_set(&ct->ct_general.use, 0); return ct; #ifdef CONFIG_NF_CONNTRACK_ZONES @@ -748,6 +777,11 @@ void nf_conntrack_free(struct nf_conn *ct) { struct net *net = nf_ct_net(ct); + /* A freed object has refcnt == 0, that's + * the golden rule for SLAB_DESTROY_BY_RCU + */ + NF_CT_ASSERT(atomic_read(&ct->ct_general.use) == 0); + nf_ct_ext_destroy(ct); nf_ct_ext_free(ct); kmem_cache_free(net->ct.nf_conntrack_cachep, ct); @@ -843,6 +877,9 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, NF_CT_STAT_INC(net, new); } + /* Now it is inserted into the unconfirmed list, bump refcount */ + nf_conntrack_get(&ct->ct_general); + /* Overload tuple linked list to put us in unconfirmed list. */ hlist_nulls_add_head_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode, &net->ct.unconfirmed); diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index bb322d0beb48..b9f0e0374322 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -1310,27 +1310,22 @@ ctnetlink_change_status(struct nf_conn *ct, const struct nlattr * const cda[]) } static int -ctnetlink_change_nat(struct nf_conn *ct, const struct nlattr * const cda[]) +ctnetlink_setup_nat(struct nf_conn *ct, const struct nlattr * const cda[]) { #ifdef CONFIG_NF_NAT_NEEDED int ret; - if (cda[CTA_NAT_DST]) { - ret = ctnetlink_parse_nat_setup(ct, - NF_NAT_MANIP_DST, - cda[CTA_NAT_DST]); - if (ret < 0) - return ret; - } - if (cda[CTA_NAT_SRC]) { - ret = ctnetlink_parse_nat_setup(ct, - NF_NAT_MANIP_SRC, - cda[CTA_NAT_SRC]); - if (ret < 0) - return ret; - } - return 0; + ret = ctnetlink_parse_nat_setup(ct, NF_NAT_MANIP_DST, + cda[CTA_NAT_DST]); + if (ret < 0) + return ret; + + ret = ctnetlink_parse_nat_setup(ct, NF_NAT_MANIP_SRC, + cda[CTA_NAT_SRC]); + return ret; #else + if (!cda[CTA_NAT_DST] && !cda[CTA_NAT_SRC]) + return 0; return -EOPNOTSUPP; #endif } @@ -1659,11 +1654,9 @@ ctnetlink_create_conntrack(struct net *net, u16 zone, goto err2; } - if (cda[CTA_NAT_SRC] || cda[CTA_NAT_DST]) { - err = ctnetlink_change_nat(ct, cda); - if (err < 0) - goto err2; - } + err = ctnetlink_setup_nat(ct, cda); + if (err < 0) + goto err2; nf_ct_acct_ext_add(ct, GFP_ATOMIC); nf_ct_tstamp_ext_add(ct, GFP_ATOMIC); diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index d3f5cd6dd962..52ca952b802c 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -432,15 +432,15 @@ nf_nat_setup_info(struct nf_conn *ct, } EXPORT_SYMBOL(nf_nat_setup_info); -unsigned int -nf_nat_alloc_null_binding(struct nf_conn *ct, unsigned int hooknum) +static unsigned int +__nf_nat_alloc_null_binding(struct nf_conn *ct, enum nf_nat_manip_type manip) { /* Force range to this IP; let proto decide mapping for * per-proto parts (hence not IP_NAT_RANGE_PROTO_SPECIFIED). * Use reply in case it's already been mangled (eg local packet). */ union nf_inet_addr ip = - (HOOK2MANIP(hooknum) == NF_NAT_MANIP_SRC ? + (manip == NF_NAT_MANIP_SRC ? ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3 : ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3); struct nf_nat_range range = { @@ -448,7 +448,13 @@ nf_nat_alloc_null_binding(struct nf_conn *ct, unsigned int hooknum) .min_addr = ip, .max_addr = ip, }; - return nf_nat_setup_info(ct, &range, HOOK2MANIP(hooknum)); + return nf_nat_setup_info(ct, &range, manip); +} + +unsigned int +nf_nat_alloc_null_binding(struct nf_conn *ct, unsigned int hooknum) +{ + return __nf_nat_alloc_null_binding(ct, HOOK2MANIP(hooknum)); } EXPORT_SYMBOL_GPL(nf_nat_alloc_null_binding); @@ -702,9 +708,9 @@ static const struct nla_policy nat_nla_policy[CTA_NAT_MAX+1] = { static int nfnetlink_parse_nat(const struct nlattr *nat, - const struct nf_conn *ct, struct nf_nat_range *range) + const struct nf_conn *ct, struct nf_nat_range *range, + const struct nf_nat_l3proto *l3proto) { - const struct nf_nat_l3proto *l3proto; struct nlattr *tb[CTA_NAT_MAX+1]; int err; @@ -714,38 +720,46 @@ nfnetlink_parse_nat(const struct nlattr *nat, if (err < 0) return err; - rcu_read_lock(); - l3proto = __nf_nat_l3proto_find(nf_ct_l3num(ct)); - if (l3proto == NULL) { - err = -EAGAIN; - goto out; - } err = l3proto->nlattr_to_range(tb, range); if (err < 0) - goto out; + return err; if (!tb[CTA_NAT_PROTO]) - goto out; + return 0; - err = nfnetlink_parse_nat_proto(tb[CTA_NAT_PROTO], ct, range); -out: - rcu_read_unlock(); - return err; + return nfnetlink_parse_nat_proto(tb[CTA_NAT_PROTO], ct, range); } +/* This function is called under rcu_read_lock() */ static int nfnetlink_parse_nat_setup(struct nf_conn *ct, enum nf_nat_manip_type manip, const struct nlattr *attr) { struct nf_nat_range range; + const struct nf_nat_l3proto *l3proto; int err; - err = nfnetlink_parse_nat(attr, ct, &range); + /* Should not happen, restricted to creating new conntracks + * via ctnetlink. + */ + if (WARN_ON_ONCE(nf_nat_initialized(ct, manip))) + return -EEXIST; + + /* Make sure that L3 NAT is there by when we call nf_nat_setup_info to + * attach the null binding, otherwise this may oops. + */ + l3proto = __nf_nat_l3proto_find(nf_ct_l3num(ct)); + if (l3proto == NULL) + return -EAGAIN; + + /* No NAT information has been passed, allocate the null-binding */ + if (attr == NULL) + return __nf_nat_alloc_null_binding(ct, manip); + + err = nfnetlink_parse_nat(attr, ct, &range, l3proto); if (err < 0) return err; - if (nf_nat_initialized(ct, manip)) - return -EEXIST; return nf_nat_setup_info(ct, &range, manip); } diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c index 9858e3e51a3a..52e20c9a46a5 100644 --- a/net/netfilter/nf_synproxy_core.c +++ b/net/netfilter/nf_synproxy_core.c @@ -363,9 +363,8 @@ static int __net_init synproxy_net_init(struct net *net) goto err2; if (!nfct_synproxy_ext_add(ct)) goto err2; - __set_bit(IPS_TEMPLATE_BIT, &ct->status); - __set_bit(IPS_CONFIRMED_BIT, &ct->status); + nf_conntrack_tmpl_insert(net, ct); snet->tmpl = ct; snet->stats = alloc_percpu(struct synproxy_stats); @@ -390,7 +389,7 @@ static void __net_exit synproxy_net_exit(struct net *net) { struct synproxy_net *snet = synproxy_pernet(net); - nf_conntrack_free(snet->tmpl); + nf_ct_put(snet->tmpl); synproxy_proc_exit(net); free_percpu(snet->stats); } diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 117bbaaddde6..adce01e8bb57 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1008,10 +1008,8 @@ notify: return 0; } -static void nf_tables_rcu_chain_destroy(struct rcu_head *head) +static void nf_tables_chain_destroy(struct nft_chain *chain) { - struct nft_chain *chain = container_of(head, struct nft_chain, rcu_head); - BUG_ON(chain->use > 0); if (chain->flags & NFT_BASE_CHAIN) { @@ -1045,7 +1043,7 @@ static int nf_tables_delchain(struct sock *nlsk, struct sk_buff *skb, if (IS_ERR(chain)) return PTR_ERR(chain); - if (!list_empty(&chain->rules)) + if (!list_empty(&chain->rules) || chain->use > 0) return -EBUSY; list_del(&chain->list); @@ -1059,7 +1057,9 @@ static int nf_tables_delchain(struct sock *nlsk, struct sk_buff *skb, family); /* Make sure all rule references are gone before this is released */ - call_rcu(&chain->rcu_head, nf_tables_rcu_chain_destroy); + synchronize_rcu(); + + nf_tables_chain_destroy(chain); return 0; } @@ -1114,35 +1114,45 @@ void nft_unregister_expr(struct nft_expr_type *type) } EXPORT_SYMBOL_GPL(nft_unregister_expr); -static const struct nft_expr_type *__nft_expr_type_get(struct nlattr *nla) +static const struct nft_expr_type *__nft_expr_type_get(u8 family, + struct nlattr *nla) { const struct nft_expr_type *type; list_for_each_entry(type, &nf_tables_expressions, list) { - if (!nla_strcmp(nla, type->name)) + if (!nla_strcmp(nla, type->name) && + (!type->family || type->family == family)) return type; } return NULL; } -static const struct nft_expr_type *nft_expr_type_get(struct nlattr *nla) +static const struct nft_expr_type *nft_expr_type_get(u8 family, + struct nlattr *nla) { const struct nft_expr_type *type; if (nla == NULL) return ERR_PTR(-EINVAL); - type = __nft_expr_type_get(nla); + type = __nft_expr_type_get(family, nla); if (type != NULL && try_module_get(type->owner)) return type; #ifdef CONFIG_MODULES if (type == NULL) { nfnl_unlock(NFNL_SUBSYS_NFTABLES); + request_module("nft-expr-%u-%.*s", family, + nla_len(nla), (char *)nla_data(nla)); + nfnl_lock(NFNL_SUBSYS_NFTABLES); + if (__nft_expr_type_get(family, nla)) + return ERR_PTR(-EAGAIN); + + nfnl_unlock(NFNL_SUBSYS_NFTABLES); request_module("nft-expr-%.*s", nla_len(nla), (char *)nla_data(nla)); nfnl_lock(NFNL_SUBSYS_NFTABLES); - if (__nft_expr_type_get(nla)) + if (__nft_expr_type_get(family, nla)) return ERR_PTR(-EAGAIN); } #endif @@ -1193,7 +1203,7 @@ static int nf_tables_expr_parse(const struct nft_ctx *ctx, if (err < 0) return err; - type = nft_expr_type_get(tb[NFTA_EXPR_NAME]); + type = nft_expr_type_get(ctx->afi->family, tb[NFTA_EXPR_NAME]); if (IS_ERR(type)) return PTR_ERR(type); @@ -1521,9 +1531,8 @@ err: return err; } -static void nf_tables_rcu_rule_destroy(struct rcu_head *head) +static void nf_tables_rule_destroy(struct nft_rule *rule) { - struct nft_rule *rule = container_of(head, struct nft_rule, rcu_head); struct nft_expr *expr; /* @@ -1538,11 +1547,6 @@ static void nf_tables_rcu_rule_destroy(struct rcu_head *head) kfree(rule); } -static void nf_tables_rule_destroy(struct nft_rule *rule) -{ - call_rcu(&rule->rcu_head, nf_tables_rcu_rule_destroy); -} - #define NFT_RULE_MAXEXPRS 128 static struct nft_expr_info *info; @@ -1809,9 +1813,6 @@ static int nf_tables_commit(struct sk_buff *skb) synchronize_rcu(); list_for_each_entry_safe(rupd, tmp, &net->nft.commit_list, list) { - /* Delete this rule from the dirty list */ - list_del(&rupd->list); - /* This rule was inactive in the past and just became active. * Clear the next bit of the genmask since its meaning has * changed, now it is the future. @@ -1822,6 +1823,7 @@ static int nf_tables_commit(struct sk_buff *skb) rupd->chain, rupd->rule, NFT_MSG_NEWRULE, 0, rupd->family); + list_del(&rupd->list); kfree(rupd); continue; } @@ -1831,7 +1833,15 @@ static int nf_tables_commit(struct sk_buff *skb) nf_tables_rule_notify(skb, rupd->nlh, rupd->table, rupd->chain, rupd->rule, NFT_MSG_DELRULE, 0, rupd->family); + } + + /* Make sure we don't see any packet traversing old rules */ + synchronize_rcu(); + + /* Now we can safely release unused old rules */ + list_for_each_entry_safe(rupd, tmp, &net->nft.commit_list, list) { nf_tables_rule_destroy(rupd->rule); + list_del(&rupd->list); kfree(rupd); } @@ -1844,20 +1854,26 @@ static int nf_tables_abort(struct sk_buff *skb) struct nft_rule_trans *rupd, *tmp; list_for_each_entry_safe(rupd, tmp, &net->nft.commit_list, list) { - /* Delete all rules from the dirty list */ - list_del(&rupd->list); - if (!nft_rule_is_active_next(net, rupd->rule)) { nft_rule_clear(net, rupd->rule); + list_del(&rupd->list); kfree(rupd); continue; } /* This rule is inactive, get rid of it */ list_del_rcu(&rupd->rule->list); + } + + /* Make sure we don't see any packet accessing aborted rules */ + synchronize_rcu(); + + list_for_each_entry_safe(rupd, tmp, &net->nft.commit_list, list) { nf_tables_rule_destroy(rupd->rule); + list_del(&rupd->list); kfree(rupd); } + return 0; } @@ -1943,6 +1959,9 @@ static int nft_ctx_init_from_setattr(struct nft_ctx *ctx, } if (nla[NFTA_SET_TABLE] != NULL) { + if (afi == NULL) + return -EAFNOSUPPORT; + table = nf_tables_table_lookup(afi, nla[NFTA_SET_TABLE]); if (IS_ERR(table)) return PTR_ERR(table); @@ -1989,13 +2008,13 @@ static int nf_tables_set_alloc_name(struct nft_ctx *ctx, struct nft_set *set, if (!sscanf(i->name, name, &tmp)) continue; - if (tmp < 0 || tmp > BITS_PER_LONG * PAGE_SIZE) + if (tmp < 0 || tmp >= BITS_PER_BYTE * PAGE_SIZE) continue; set_bit(tmp, inuse); } - n = find_first_zero_bit(inuse, BITS_PER_LONG * PAGE_SIZE); + n = find_first_zero_bit(inuse, BITS_PER_BYTE * PAGE_SIZE); free_page((unsigned long)inuse); } @@ -2428,6 +2447,8 @@ static int nf_tables_delset(struct sock *nlsk, struct sk_buff *skb, struct nft_ctx ctx; int err; + if (nfmsg->nfgen_family == NFPROTO_UNSPEC) + return -EAFNOSUPPORT; if (nla[NFTA_SET_TABLE] == NULL) return -EINVAL; @@ -2435,9 +2456,6 @@ static int nf_tables_delset(struct sock *nlsk, struct sk_buff *skb, if (err < 0) return err; - if (nfmsg->nfgen_family == NFPROTO_UNSPEC) - return -EAFNOSUPPORT; - set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_NAME]); if (IS_ERR(set)) return PTR_ERR(set); @@ -2723,6 +2741,9 @@ static int nft_add_set_elem(const struct nft_ctx *ctx, struct nft_set *set, if (nla[NFTA_SET_ELEM_DATA] == NULL && !(elem.flags & NFT_SET_ELEM_INTERVAL_END)) return -EINVAL; + if (nla[NFTA_SET_ELEM_DATA] != NULL && + elem.flags & NFT_SET_ELEM_INTERVAL_END) + return -EINVAL; } else { if (nla[NFTA_SET_ELEM_DATA] != NULL) return -EINVAL; @@ -2977,6 +2998,9 @@ 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) + return 0; + switch (elem->data.verdict) { case NFT_JUMP: case NFT_GOTO: diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c index 0d879fcb8763..90998a6ff8b9 100644 --- a/net/netfilter/nf_tables_core.c +++ b/net/netfilter/nf_tables_core.c @@ -103,9 +103,9 @@ static struct nf_loginfo trace_loginfo = { }, }; -static inline void nft_trace_packet(const struct nft_pktinfo *pkt, - const struct nft_chain *chain, - int rulenum, enum nft_trace type) +static void nft_trace_packet(const struct nft_pktinfo *pkt, + const struct nft_chain *chain, + int rulenum, enum nft_trace type) { struct net *net = dev_net(pkt->in ? pkt->in : pkt->out); diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 917052e20602..46e275403838 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -226,6 +226,7 @@ static int nft_ct_init_validate_get(const struct nft_expr *expr, if (tb[NFTA_CT_DIRECTION] != NULL) return -EINVAL; break; + case NFT_CT_L3PROTOCOL: case NFT_CT_PROTOCOL: case NFT_CT_SRC: case NFT_CT_DST: @@ -311,8 +312,19 @@ static int nft_ct_get_dump(struct sk_buff *skb, const struct nft_expr *expr) goto nla_put_failure; if (nla_put_be32(skb, NFTA_CT_KEY, htonl(priv->key))) goto nla_put_failure; - if (nla_put_u8(skb, NFTA_CT_DIRECTION, priv->dir)) - goto nla_put_failure; + + switch (priv->key) { + case NFT_CT_PROTOCOL: + case NFT_CT_SRC: + case NFT_CT_DST: + case NFT_CT_PROTO_SRC: + case NFT_CT_PROTO_DST: + if (nla_put_u8(skb, NFTA_CT_DIRECTION, priv->dir)) + goto nla_put_failure; + default: + break; + } + return 0; nla_put_failure: diff --git a/net/netfilter/nft_log.c b/net/netfilter/nft_log.c index 5af790123ad8..26c5154e05f3 100644 --- a/net/netfilter/nft_log.c +++ b/net/netfilter/nft_log.c @@ -23,7 +23,6 @@ static const char *nft_log_null_prefix = ""; struct nft_log { struct nf_loginfo loginfo; char *prefix; - int family; }; static void nft_log_eval(const struct nft_expr *expr, @@ -33,7 +32,7 @@ static void nft_log_eval(const struct nft_expr *expr, const struct nft_log *priv = nft_expr_priv(expr); struct net *net = dev_net(pkt->in ? pkt->in : pkt->out); - nf_log_packet(net, priv->family, pkt->ops->hooknum, pkt->skb, pkt->in, + nf_log_packet(net, pkt->ops->pf, pkt->ops->hooknum, pkt->skb, pkt->in, pkt->out, &priv->loginfo, "%s", priv->prefix); } @@ -52,8 +51,6 @@ static int nft_log_init(const struct nft_ctx *ctx, struct nf_loginfo *li = &priv->loginfo; const struct nlattr *nla; - priv->family = ctx->afi->family; - nla = tb[NFTA_LOG_PREFIX]; if (nla != NULL) { priv->prefix = kmalloc(nla_len(nla) + 1, GFP_KERNEL); diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index 8a6116b75b5a..bb4ef4cccb6e 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -16,6 +16,7 @@ #include <linux/netfilter.h> #include <linux/netfilter/nf_tables.h> #include <net/netfilter/nf_tables.h> +#include <net/netfilter/nf_tables_core.h> struct nft_lookup { struct nft_set *set; diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index e8254ad2e5a9..425cf39af890 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -116,7 +116,7 @@ static void nft_meta_get_eval(const struct nft_expr *expr, skb->sk->sk_socket->file->f_cred->fsgid); read_unlock_bh(&skb->sk->sk_callback_lock); break; -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID case NFT_META_RTCLASSID: { const struct dst_entry *dst = skb_dst(skb); @@ -199,7 +199,7 @@ static int nft_meta_init_validate_get(uint32_t key) case NFT_META_OIFTYPE: case NFT_META_SKUID: case NFT_META_SKGID: -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID case NFT_META_RTCLASSID: #endif #ifdef CONFIG_NETWORK_SECMARK diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index a2aeb318678f..85daa84bfdfe 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -135,7 +135,8 @@ nft_payload_select_ops(const struct nft_ctx *ctx, if (len == 0 || len > FIELD_SIZEOF(struct nft_data, data)) return ERR_PTR(-EINVAL); - if (len <= 4 && IS_ALIGNED(offset, len) && base != NFT_PAYLOAD_LL_HEADER) + if (len <= 4 && is_power_of_2(len) && IS_ALIGNED(offset, len) && + base != NFT_PAYLOAD_LL_HEADER) return &nft_payload_fast_ops; else return &nft_payload_ops; diff --git a/net/netfilter/nft_queue.c b/net/netfilter/nft_queue.c index cbea473d69e9..e8ae2f6bf232 100644 --- a/net/netfilter/nft_queue.c +++ b/net/netfilter/nft_queue.c @@ -25,7 +25,6 @@ struct nft_queue { u16 queuenum; u16 queues_total; u16 flags; - u8 family; }; static void nft_queue_eval(const struct nft_expr *expr, @@ -43,7 +42,7 @@ static void nft_queue_eval(const struct nft_expr *expr, queue = priv->queuenum + cpu % priv->queues_total; } else { queue = nfqueue_hash(pkt->skb, queue, - priv->queues_total, priv->family, + priv->queues_total, pkt->ops->pf, jhash_initval); } } @@ -71,7 +70,6 @@ static int nft_queue_init(const struct nft_ctx *ctx, return -EINVAL; init_hashrandom(&jhash_initval); - priv->family = ctx->afi->family; priv->queuenum = ntohs(nla_get_be16(tb[NFTA_QUEUE_NUM])); if (tb[NFTA_QUEUE_TOTAL] != NULL) diff --git a/net/netfilter/nft_rbtree.c b/net/netfilter/nft_rbtree.c index ca0c1b231bfe..e21d69d13506 100644 --- a/net/netfilter/nft_rbtree.c +++ b/net/netfilter/nft_rbtree.c @@ -69,8 +69,10 @@ 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) + if (set->flags & NFT_SET_MAP && + !(rbe->flags & NFT_SET_ELEM_INTERVAL_END)) nft_data_uninit(rbe->data, set->dtype); + kfree(rbe); } @@ -108,7 +110,8 @@ static int nft_rbtree_insert(const struct nft_set *set, int err; size = sizeof(*rbe); - if (set->flags & NFT_SET_MAP) + if (set->flags & NFT_SET_MAP && + !(elem->flags & NFT_SET_ELEM_INTERVAL_END)) size += sizeof(rbe->data[0]); rbe = kzalloc(size, GFP_KERNEL); @@ -117,7 +120,8 @@ static int nft_rbtree_insert(const struct nft_set *set, rbe->flags = elem->flags; nft_data_copy(&rbe->key, &elem->key); - if (set->flags & NFT_SET_MAP) + if (set->flags & NFT_SET_MAP && + !(rbe->flags & NFT_SET_ELEM_INTERVAL_END)) nft_data_copy(rbe->data, &elem->data); err = __nft_rbtree_insert(set, rbe); @@ -153,7 +157,8 @@ static int nft_rbtree_get(const struct nft_set *set, struct nft_set_elem *elem) parent = parent->rb_right; else { elem->cookie = rbe; - if (set->flags & NFT_SET_MAP) + if (set->flags & NFT_SET_MAP && + !(rbe->flags & NFT_SET_ELEM_INTERVAL_END)) nft_data_copy(&elem->data, rbe->data); elem->flags = rbe->flags; return 0; @@ -177,7 +182,8 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx, rbe = rb_entry(node, struct nft_rbtree_elem, node); nft_data_copy(&elem.key, &rbe->key); - if (set->flags & NFT_SET_MAP) + if (set->flags & NFT_SET_MAP && + !(rbe->flags & NFT_SET_ELEM_INTERVAL_END)) nft_data_copy(&elem.data, rbe->data); elem.flags = rbe->flags; diff --git a/net/netfilter/nft_reject.c b/net/netfilter/nft_reject.c index 5e204711d704..f3448c296446 100644 --- a/net/netfilter/nft_reject.c +++ b/net/netfilter/nft_reject.c @@ -16,65 +16,23 @@ #include <linux/netfilter.h> #include <linux/netfilter/nf_tables.h> #include <net/netfilter/nf_tables.h> -#include <net/icmp.h> -#include <net/netfilter/ipv4/nf_reject.h> +#include <net/netfilter/nft_reject.h> -#if IS_ENABLED(CONFIG_NF_TABLES_IPV6) -#include <net/netfilter/ipv6/nf_reject.h> -#endif - -struct nft_reject { - enum nft_reject_types type:8; - u8 icmp_code; - u8 family; -}; - -static void nft_reject_eval(const struct nft_expr *expr, - struct nft_data data[NFT_REG_MAX + 1], - const struct nft_pktinfo *pkt) -{ - struct nft_reject *priv = nft_expr_priv(expr); -#if IS_ENABLED(CONFIG_NF_TABLES_IPV6) - struct net *net = dev_net((pkt->in != NULL) ? pkt->in : pkt->out); -#endif - switch (priv->type) { - case NFT_REJECT_ICMP_UNREACH: - if (priv->family == NFPROTO_IPV4) - nf_send_unreach(pkt->skb, priv->icmp_code); -#if IS_ENABLED(CONFIG_NF_TABLES_IPV6) - else if (priv->family == NFPROTO_IPV6) - nf_send_unreach6(net, pkt->skb, priv->icmp_code, - pkt->ops->hooknum); -#endif - break; - case NFT_REJECT_TCP_RST: - if (priv->family == NFPROTO_IPV4) - nf_send_reset(pkt->skb, pkt->ops->hooknum); -#if IS_ENABLED(CONFIG_NF_TABLES_IPV6) - else if (priv->family == NFPROTO_IPV6) - nf_send_reset6(net, pkt->skb, pkt->ops->hooknum); -#endif - break; - } - - data[NFT_REG_VERDICT].verdict = NF_DROP; -} - -static const struct nla_policy nft_reject_policy[NFTA_REJECT_MAX + 1] = { +const struct nla_policy nft_reject_policy[NFTA_REJECT_MAX + 1] = { [NFTA_REJECT_TYPE] = { .type = NLA_U32 }, [NFTA_REJECT_ICMP_CODE] = { .type = NLA_U8 }, }; +EXPORT_SYMBOL_GPL(nft_reject_policy); -static int nft_reject_init(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nlattr * const tb[]) +int nft_reject_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) { struct nft_reject *priv = nft_expr_priv(expr); if (tb[NFTA_REJECT_TYPE] == NULL) return -EINVAL; - priv->family = ctx->afi->family; priv->type = ntohl(nla_get_be32(tb[NFTA_REJECT_TYPE])); switch (priv->type) { case NFT_REJECT_ICMP_UNREACH: @@ -89,8 +47,9 @@ static int nft_reject_init(const struct nft_ctx *ctx, return 0; } +EXPORT_SYMBOL_GPL(nft_reject_init); -static int nft_reject_dump(struct sk_buff *skb, const struct nft_expr *expr) +int nft_reject_dump(struct sk_buff *skb, const struct nft_expr *expr) { const struct nft_reject *priv = nft_expr_priv(expr); @@ -109,37 +68,7 @@ static int nft_reject_dump(struct sk_buff *skb, const struct nft_expr *expr) nla_put_failure: return -1; } - -static struct nft_expr_type nft_reject_type; -static const struct nft_expr_ops nft_reject_ops = { - .type = &nft_reject_type, - .size = NFT_EXPR_SIZE(sizeof(struct nft_reject)), - .eval = nft_reject_eval, - .init = nft_reject_init, - .dump = nft_reject_dump, -}; - -static struct nft_expr_type nft_reject_type __read_mostly = { - .name = "reject", - .ops = &nft_reject_ops, - .policy = nft_reject_policy, - .maxattr = NFTA_REJECT_MAX, - .owner = THIS_MODULE, -}; - -static int __init nft_reject_module_init(void) -{ - return nft_register_expr(&nft_reject_type); -} - -static void __exit nft_reject_module_exit(void) -{ - nft_unregister_expr(&nft_reject_type); -} - -module_init(nft_reject_module_init); -module_exit(nft_reject_module_exit); +EXPORT_SYMBOL_GPL(nft_reject_dump); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); -MODULE_ALIAS_NFT_EXPR("reject"); diff --git a/net/netfilter/nft_reject_inet.c b/net/netfilter/nft_reject_inet.c new file mode 100644 index 000000000000..b718a52a4654 --- /dev/null +++ b/net/netfilter/nft_reject_inet.c @@ -0,0 +1,63 @@ +/* + * Copyright (c) 2014 Patrick McHardy <kaber@trash.net> + * + * 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 <linux/kernel.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/netlink.h> +#include <linux/netfilter.h> +#include <linux/netfilter/nf_tables.h> +#include <net/netfilter/nf_tables.h> +#include <net/netfilter/nft_reject.h> + +static void nft_reject_inet_eval(const struct nft_expr *expr, + struct nft_data data[NFT_REG_MAX + 1], + const struct nft_pktinfo *pkt) +{ + switch (pkt->ops->pf) { + case NFPROTO_IPV4: + return nft_reject_ipv4_eval(expr, data, pkt); + case NFPROTO_IPV6: + return nft_reject_ipv6_eval(expr, data, pkt); + } +} + +static struct nft_expr_type nft_reject_inet_type; +static const struct nft_expr_ops nft_reject_inet_ops = { + .type = &nft_reject_inet_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_reject)), + .eval = nft_reject_inet_eval, + .init = nft_reject_init, + .dump = nft_reject_dump, +}; + +static struct nft_expr_type nft_reject_inet_type __read_mostly = { + .family = NFPROTO_INET, + .name = "reject", + .ops = &nft_reject_inet_ops, + .policy = nft_reject_policy, + .maxattr = NFTA_REJECT_MAX, + .owner = THIS_MODULE, +}; + +static int __init nft_reject_inet_module_init(void) +{ + return nft_register_expr(&nft_reject_inet_type); +} + +static void __exit nft_reject_inet_module_exit(void) +{ + nft_unregister_expr(&nft_reject_inet_type); +} + +module_init(nft_reject_inet_module_init); +module_exit(nft_reject_inet_module_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); +MODULE_ALIAS_NFT_AF_EXPR(1, "reject"); diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c index 5929be622c5c..75747aecdebe 100644 --- a/net/netfilter/xt_CT.c +++ b/net/netfilter/xt_CT.c @@ -228,12 +228,7 @@ static int xt_ct_tg_check(const struct xt_tgchk_param *par, goto err3; } - __set_bit(IPS_TEMPLATE_BIT, &ct->status); - __set_bit(IPS_CONFIRMED_BIT, &ct->status); - - /* Overload tuple linked list to put us in template list. */ - hlist_nulls_add_head_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode, - &par->net->ct.tmpl); + nf_conntrack_tmpl_insert(par->net, ct); out: info->ct = ct; return 0; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index fdf51353cf78..c2d585c4f7c5 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1460,7 +1460,7 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr, if (nlk->netlink_bind && nlk->groups[0]) { int i; - for (i=0; i<nlk->ngroups; i++) { + for (i = 0; i < nlk->ngroups; i++) { if (test_bit(i, nlk->groups)) nlk->netlink_bind(i); } @@ -1489,8 +1489,8 @@ static int netlink_connect(struct socket *sock, struct sockaddr *addr, if (addr->sa_family != AF_NETLINK) return -EINVAL; - /* Only superuser is allowed to send multicasts */ - if (nladdr->nl_groups && !netlink_capable(sock, NL_CFG_F_NONROOT_SEND)) + if ((nladdr->nl_groups || nladdr->nl_pid) && + !netlink_capable(sock, NL_CFG_F_NONROOT_SEND)) return -EPERM; if (!nlk->portid) @@ -2343,6 +2343,11 @@ static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock, } #endif + /* Record the max length of recvmsg() calls for future allocations */ + nlk->max_recvmsg_len = max(nlk->max_recvmsg_len, len); + nlk->max_recvmsg_len = min_t(size_t, nlk->max_recvmsg_len, + 16384); + copied = data_skb->len; if (len < copied) { msg->msg_flags |= MSG_TRUNC; @@ -2549,7 +2554,7 @@ __nlmsg_put(struct sk_buff *skb, u32 portid, u32 seq, int type, int len, int fla struct nlmsghdr *nlh; int size = nlmsg_msg_size(len); - nlh = (struct nlmsghdr*)skb_put(skb, NLMSG_ALIGN(size)); + nlh = (struct nlmsghdr *)skb_put(skb, NLMSG_ALIGN(size)); nlh->nlmsg_type = type; nlh->nlmsg_len = size; nlh->nlmsg_flags = flags; @@ -2587,7 +2592,27 @@ static int netlink_dump(struct sock *sk) if (!netlink_rx_is_mmaped(sk) && atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf) goto errout_skb; - skb = netlink_alloc_skb(sk, alloc_size, nlk->portid, GFP_KERNEL); + + /* NLMSG_GOODSIZE is small to avoid high order allocations being + * required, but it makes sense to _attempt_ a 16K bytes allocation + * to reduce number of system calls on dump operations, if user + * ever provided a big enough buffer. + */ + if (alloc_size < nlk->max_recvmsg_len) { + skb = netlink_alloc_skb(sk, + nlk->max_recvmsg_len, + nlk->portid, + GFP_KERNEL | + __GFP_NOWARN | + __GFP_NORETRY); + /* available room should be exact amount to avoid MSG_TRUNC */ + if (skb) + skb_reserve(skb, skb_tailroom(skb) - + nlk->max_recvmsg_len); + } + if (!skb) + skb = netlink_alloc_skb(sk, alloc_size, nlk->portid, + GFP_KERNEL); if (!skb) goto errout_skb; netlink_skb_set_owner_r(skb, sk); diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h index acbd774eeb7c..ed13a790b00e 100644 --- a/net/netlink/af_netlink.h +++ b/net/netlink/af_netlink.h @@ -31,6 +31,7 @@ struct netlink_sock { u32 ngroups; unsigned long *groups; unsigned long state; + size_t max_recvmsg_len; wait_queue_head_t wait; bool cb_running; struct netlink_callback cb; diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index df4692826ead..36f8872cb072 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -55,6 +55,7 @@ #include "datapath.h" #include "flow.h" +#include "flow_table.h" #include "flow_netlink.h" #include "vport-internal_dev.h" #include "vport-netdev.h" @@ -160,7 +161,6 @@ static void destroy_dp_rcu(struct rcu_head *rcu) { struct datapath *dp = container_of(rcu, struct datapath, rcu); - ovs_flow_tbl_destroy(&dp->table); free_percpu(dp->stats_percpu); release_net(ovs_dp_get_net(dp)); kfree(dp->ports); @@ -256,10 +256,10 @@ void ovs_dp_process_received_packet(struct vport *p, struct sk_buff *skb) out: /* Update datapath statistics. */ - u64_stats_update_begin(&stats->sync); + u64_stats_update_begin(&stats->syncp); (*stats_counter)++; stats->n_mask_hit += n_mask_hit; - u64_stats_update_end(&stats->sync); + u64_stats_update_end(&stats->syncp); } static struct genl_family dp_packet_genl_family = { @@ -295,9 +295,9 @@ int ovs_dp_upcall(struct datapath *dp, struct sk_buff *skb, err: stats = this_cpu_ptr(dp->stats_percpu); - u64_stats_update_begin(&stats->sync); + u64_stats_update_begin(&stats->syncp); stats->n_lost++; - u64_stats_update_end(&stats->sync); + u64_stats_update_end(&stats->syncp); return err; } @@ -466,6 +466,14 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb, skb_zerocopy(user_skb, skb, skb->len, hlen); + /* Pad OVS_PACKET_ATTR_PACKET if linear copy was performed */ + if (!(dp->user_features & OVS_DP_F_UNALIGNED)) { + size_t plen = NLA_ALIGN(user_skb->len) - user_skb->len; + + if (plen > 0) + memset(skb_put(user_skb, plen), 0, plen); + } + ((struct nlmsghdr *) user_skb->data)->nlmsg_len = user_skb->len; err = genlmsg_unicast(ovs_dp_get_net(dp), user_skb, upcall_info->portid); @@ -598,9 +606,9 @@ static void get_dp_stats(struct datapath *dp, struct ovs_dp_stats *stats, percpu_stats = per_cpu_ptr(dp->stats_percpu, i); do { - start = u64_stats_fetch_begin_bh(&percpu_stats->sync); + start = u64_stats_fetch_begin_bh(&percpu_stats->syncp); local_stats = *percpu_stats; - } while (u64_stats_fetch_retry_bh(&percpu_stats->sync, start)); + } while (u64_stats_fetch_retry_bh(&percpu_stats->syncp, start)); stats->n_hit += local_stats.n_hit; stats->n_missed += local_stats.n_missed; @@ -852,11 +860,8 @@ static int ovs_flow_cmd_new_or_set(struct sk_buff *skb, struct genl_info *info) goto err_unlock_ovs; /* The unmasked key has to be the same for flow updates. */ - error = -EINVAL; - if (!ovs_flow_cmp_unmasked_key(flow, &match)) { - OVS_NLERR("Flow modification message rejected, unmasked key does not match.\n"); + if (!ovs_flow_cmp_unmasked_key(flow, &match)) goto err_unlock_ovs; - } /* Update actions. */ old_acts = ovsl_dereference(flow->sf_acts); @@ -1079,6 +1084,7 @@ static size_t ovs_dp_cmd_msg_size(void) msgsize += nla_total_size(IFNAMSIZ); msgsize += nla_total_size(sizeof(struct ovs_dp_stats)); msgsize += nla_total_size(sizeof(struct ovs_dp_megaflow_stats)); + msgsize += nla_total_size(sizeof(u32)); /* OVS_DP_ATTR_USER_FEATURES */ return msgsize; } @@ -1209,18 +1215,12 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info) if (err) goto err_free_dp; - dp->stats_percpu = alloc_percpu(struct dp_stats_percpu); + dp->stats_percpu = netdev_alloc_pcpu_stats(struct dp_stats_percpu); if (!dp->stats_percpu) { err = -ENOMEM; goto err_destroy_table; } - for_each_possible_cpu(i) { - struct dp_stats_percpu *dpath_stats; - dpath_stats = per_cpu_ptr(dp->stats_percpu, i); - u64_stats_init(&dpath_stats->sync); - } - dp->ports = kmalloc(DP_VPORT_HASH_BUCKETS * sizeof(struct hlist_head), GFP_KERNEL); if (!dp->ports) { @@ -1279,7 +1279,7 @@ err_destroy_ports_array: err_destroy_percpu: free_percpu(dp->stats_percpu); err_destroy_table: - ovs_flow_tbl_destroy(&dp->table); + ovs_flow_tbl_destroy(&dp->table, false); err_free_dp: release_net(ovs_dp_get_net(dp)); kfree(dp); @@ -1306,10 +1306,13 @@ static void __dp_destroy(struct datapath *dp) list_del_rcu(&dp->list_node); /* OVSP_LOCAL is datapath internal port. We need to make sure that - * all port in datapath are destroyed first before freeing datapath. + * all ports in datapath are destroyed first before freeing datapath. */ ovs_dp_detach_port(ovs_vport_ovsl(dp, OVSP_LOCAL)); + /* RCU destroy the flow table */ + ovs_flow_tbl_destroy(&dp->table, true); + call_rcu(&dp->rcu, destroy_dp_rcu); } diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h index 6be9fbb5e9cb..05317380fc03 100644 --- a/net/openvswitch/datapath.h +++ b/net/openvswitch/datapath.h @@ -55,7 +55,7 @@ struct dp_stats_percpu { u64 n_missed; u64 n_lost; u64 n_mask_hit; - struct u64_stats_sync sync; + struct u64_stats_sync syncp; }; /** diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c index c58a0fe3c889..3c268b3d71c3 100644 --- a/net/openvswitch/flow_table.c +++ b/net/openvswitch/flow_table.c @@ -153,29 +153,29 @@ static void rcu_free_flow_callback(struct rcu_head *rcu) flow_free(flow); } -static void flow_mask_del_ref(struct sw_flow_mask *mask, bool deferred) -{ - if (!mask) - return; - - BUG_ON(!mask->ref_count); - mask->ref_count--; - - if (!mask->ref_count) { - list_del_rcu(&mask->list); - if (deferred) - kfree_rcu(mask, rcu); - else - kfree(mask); - } -} - void ovs_flow_free(struct sw_flow *flow, bool deferred) { if (!flow) return; - flow_mask_del_ref(flow->mask, deferred); + if (flow->mask) { + struct sw_flow_mask *mask = flow->mask; + + /* ovs-lock is required to protect mask-refcount and + * mask list. + */ + ASSERT_OVSL(); + BUG_ON(!mask->ref_count); + mask->ref_count--; + + if (!mask->ref_count) { + list_del_rcu(&mask->list); + if (deferred) + kfree_rcu(mask, rcu); + else + kfree(mask); + } + } if (deferred) call_rcu(&flow->rcu, rcu_free_flow_callback); @@ -188,26 +188,9 @@ static void free_buckets(struct flex_array *buckets) flex_array_free(buckets); } + static void __table_instance_destroy(struct table_instance *ti) { - int i; - - if (ti->keep_flows) - goto skip_flows; - - for (i = 0; i < ti->n_buckets; i++) { - struct sw_flow *flow; - struct hlist_head *head = flex_array_get(ti->buckets, i); - struct hlist_node *n; - int ver = ti->node_ver; - - hlist_for_each_entry_safe(flow, n, head, hash_node[ver]) { - hlist_del(&flow->hash_node[ver]); - ovs_flow_free(flow, false); - } - } - -skip_flows: free_buckets(ti->buckets); kfree(ti); } @@ -258,20 +241,38 @@ static void flow_tbl_destroy_rcu_cb(struct rcu_head *rcu) static void table_instance_destroy(struct table_instance *ti, bool deferred) { + int i; + if (!ti) return; + if (ti->keep_flows) + goto skip_flows; + + for (i = 0; i < ti->n_buckets; i++) { + struct sw_flow *flow; + struct hlist_head *head = flex_array_get(ti->buckets, i); + struct hlist_node *n; + int ver = ti->node_ver; + + hlist_for_each_entry_safe(flow, n, head, hash_node[ver]) { + hlist_del_rcu(&flow->hash_node[ver]); + ovs_flow_free(flow, deferred); + } + } + +skip_flows: if (deferred) call_rcu(&ti->rcu, flow_tbl_destroy_rcu_cb); else __table_instance_destroy(ti); } -void ovs_flow_tbl_destroy(struct flow_table *table) +void ovs_flow_tbl_destroy(struct flow_table *table, bool deferred) { struct table_instance *ti = ovsl_dereference(table->ti); - table_instance_destroy(ti, false); + table_instance_destroy(ti, deferred); } struct sw_flow *ovs_flow_tbl_dump_next(struct table_instance *ti, @@ -504,16 +505,11 @@ static struct sw_flow_mask *mask_alloc(void) mask = kmalloc(sizeof(*mask), GFP_KERNEL); if (mask) - mask->ref_count = 0; + mask->ref_count = 1; return mask; } -static void mask_add_ref(struct sw_flow_mask *mask) -{ - mask->ref_count++; -} - static bool mask_equal(const struct sw_flow_mask *a, const struct sw_flow_mask *b) { @@ -554,9 +550,11 @@ static int flow_mask_insert(struct flow_table *tbl, struct sw_flow *flow, mask->key = new->key; mask->range = new->range; list_add_rcu(&mask->list, &tbl->mask_list); + } else { + BUG_ON(!mask->ref_count); + mask->ref_count++; } - mask_add_ref(mask); flow->mask = mask; return 0; } diff --git a/net/openvswitch/flow_table.h b/net/openvswitch/flow_table.h index 1996e34c0fd8..baaeb101924d 100644 --- a/net/openvswitch/flow_table.h +++ b/net/openvswitch/flow_table.h @@ -60,7 +60,7 @@ void ovs_flow_free(struct sw_flow *, bool deferred); int ovs_flow_tbl_init(struct flow_table *); int ovs_flow_tbl_count(struct flow_table *table); -void ovs_flow_tbl_destroy(struct flow_table *table); +void ovs_flow_tbl_destroy(struct flow_table *table, bool deferred); int ovs_flow_tbl_flush(struct flow_table *flow_table); int ovs_flow_tbl_insert(struct flow_table *table, struct sw_flow *flow, diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c index 208dd9a26dd1..3b4db3220456 100644 --- a/net/openvswitch/vport.c +++ b/net/openvswitch/vport.c @@ -121,7 +121,6 @@ struct vport *ovs_vport_alloc(int priv_size, const struct vport_ops *ops, { struct vport *vport; size_t alloc_size; - int i; alloc_size = sizeof(struct vport); if (priv_size) { @@ -139,19 +138,12 @@ struct vport *ovs_vport_alloc(int priv_size, const struct vport_ops *ops, vport->ops = ops; INIT_HLIST_NODE(&vport->dp_hash_node); - vport->percpu_stats = alloc_percpu(struct pcpu_sw_netstats); + vport->percpu_stats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); if (!vport->percpu_stats) { kfree(vport); return ERR_PTR(-ENOMEM); } - for_each_possible_cpu(i) { - struct pcpu_sw_netstats *vport_stats; - vport_stats = per_cpu_ptr(vport->percpu_stats, i); - u64_stats_init(&vport_stats->syncp); - } - - spin_lock_init(&vport->stats_lock); return vport; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 6a2bb37506c5..292304404fda 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -308,11 +308,27 @@ static bool packet_use_direct_xmit(const struct packet_sock *po) return po->xmit == packet_direct_xmit; } -static u16 packet_pick_tx_queue(struct net_device *dev) +static u16 __packet_pick_tx_queue(struct net_device *dev, struct sk_buff *skb) { return (u16) raw_smp_processor_id() % dev->real_num_tx_queues; } +static void packet_pick_tx_queue(struct net_device *dev, struct sk_buff *skb) +{ + const struct net_device_ops *ops = dev->netdev_ops; + u16 queue_index; + + if (ops->ndo_select_queue) { + queue_index = ops->ndo_select_queue(dev, skb, NULL, + __packet_pick_tx_queue); + queue_index = netdev_cap_txqueue(dev, queue_index); + } else { + queue_index = __packet_pick_tx_queue(dev, skb); + } + + skb_set_queue_mapping(skb, queue_index); +} + /* register_prot_hook must be invoked with the po->bind_lock held, * or from a context in which asynchronous accesses to the packet * socket is not possible (packet_create()). @@ -2241,8 +2257,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) if (unlikely(!(dev->flags & IFF_UP))) goto out_put; - reserve = dev->hard_header_len; - + reserve = dev->hard_header_len + VLAN_HLEN; size_max = po->tx_ring.frame_size - (po->tp_hdrlen - sizeof(struct sockaddr_ll)); @@ -2269,8 +2284,19 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) goto out_status; tp_len = tpacket_fill_skb(po, skb, ph, dev, size_max, proto, - addr, hlen); + addr, hlen); + if (tp_len > dev->mtu + dev->hard_header_len) { + struct ethhdr *ehdr; + /* Earlier code assumed this would be a VLAN pkt, + * double-check this now that we have the actual + * packet in hand. + */ + skb_reset_mac_header(skb); + ehdr = eth_hdr(skb); + if (ehdr->h_proto != htons(ETH_P_8021Q)) + tp_len = -EMSGSIZE; + } if (unlikely(tp_len < 0)) { if (po->tp_loss) { __packet_set_status(po, ph, @@ -2285,7 +2311,8 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) } } - skb_set_queue_mapping(skb, packet_pick_tx_queue(dev)); + packet_pick_tx_queue(dev, skb); + skb->destructor = tpacket_destruct_skb; __packet_set_status(po, ph, TP_STATUS_SENDING); packet_inc_pending(&po->tx_ring); @@ -2499,7 +2526,8 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) skb->dev = dev; skb->priority = sk->sk_priority; skb->mark = sk->sk_mark; - skb_set_queue_mapping(skb, packet_pick_tx_queue(dev)); + + packet_pick_tx_queue(dev, skb); if (po->has_vnet_hdr) { if (vnet_hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) { @@ -3786,7 +3814,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, */ if (!tx_ring) init_prb_bdqc(po, rb, pg_vec, req_u, tx_ring); - break; + break; default: break; } diff --git a/net/rxrpc/Makefile b/net/rxrpc/Makefile index d1c3429b69ed..ec126f91276b 100644 --- a/net/rxrpc/Makefile +++ b/net/rxrpc/Makefile @@ -20,9 +20,8 @@ af-rxrpc-y := \ ar-skbuff.o \ ar-transport.o -ifeq ($(CONFIG_PROC_FS),y) -af-rxrpc-y += ar-proc.o -endif +af-rxrpc-$(CONFIG_PROC_FS) += ar-proc.o +af-rxrpc-$(CONFIG_SYSCTL) += sysctl.o obj-$(CONFIG_AF_RXRPC) += af-rxrpc.o diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index e61aa6001c65..7b1670489638 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -838,6 +838,12 @@ static int __init af_rxrpc_init(void) goto error_key_type_s; } + ret = rxrpc_sysctl_init(); + if (ret < 0) { + printk(KERN_CRIT "RxRPC: Cannot register sysctls\n"); + goto error_sysctls; + } + #ifdef CONFIG_PROC_FS proc_create("rxrpc_calls", 0, init_net.proc_net, &rxrpc_call_seq_fops); proc_create("rxrpc_conns", 0, init_net.proc_net, @@ -845,6 +851,8 @@ static int __init af_rxrpc_init(void) #endif return 0; +error_sysctls: + unregister_key_type(&key_type_rxrpc_s); error_key_type_s: unregister_key_type(&key_type_rxrpc); error_key_type: @@ -865,6 +873,7 @@ error_call_jar: static void __exit af_rxrpc_exit(void) { _enter(""); + rxrpc_sysctl_exit(); unregister_key_type(&key_type_rxrpc_s); unregister_key_type(&key_type_rxrpc); sock_unregister(PF_RXRPC); diff --git a/net/rxrpc/ar-ack.c b/net/rxrpc/ar-ack.c index cd97a0ce48d8..c6be17a959a6 100644 --- a/net/rxrpc/ar-ack.c +++ b/net/rxrpc/ar-ack.c @@ -19,7 +19,49 @@ #include <net/af_rxrpc.h> #include "ar-internal.h" -static unsigned int rxrpc_ack_defer = 1; +/* + * How long to wait before scheduling ACK generation after seeing a + * packet with RXRPC_REQUEST_ACK set (in jiffies). + */ +unsigned rxrpc_requested_ack_delay = 1; + +/* + * How long to wait before scheduling an ACK with subtype DELAY (in jiffies). + * + * We use this when we've received new data packets. If those packets aren't + * all consumed within this time we will send a DELAY ACK if an ACK was not + * requested to let the sender know it doesn't need to resend. + */ +unsigned rxrpc_soft_ack_delay = 1 * HZ; + +/* + * How long to wait before scheduling an ACK with subtype IDLE (in jiffies). + * + * We use this when we've consumed some previously soft-ACK'd packets when + * further packets aren't immediately received to decide when to send an IDLE + * ACK let the other end know that it can free up its Tx buffer space. + */ +unsigned rxrpc_idle_ack_delay = 0.5 * HZ; + +/* + * Receive window size in packets. This indicates the maximum number of + * unconsumed received packets we're willing to retain in memory. Once this + * limit is hit, we should generate an EXCEEDS_WINDOW ACK and discard further + * packets. + */ +unsigned rxrpc_rx_window_size = 32; + +/* + * Maximum Rx MTU size. This indicates to the sender the size of jumbo packet + * made by gluing normal packets together that we're willing to handle. + */ +unsigned rxrpc_rx_mtu = 5692; + +/* + * The maximum number of fragments in a received jumbo packet that we tell the + * sender that we're willing to handle. + */ +unsigned rxrpc_rx_jumbo_max = 4; static const char *rxrpc_acks(u8 reason) { @@ -82,24 +124,23 @@ void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason, switch (ack_reason) { case RXRPC_ACK_DELAY: _debug("run delay timer"); - call->ack_timer.expires = jiffies + rxrpc_ack_timeout * HZ; - add_timer(&call->ack_timer); - return; + expiry = rxrpc_soft_ack_delay; + goto run_timer; case RXRPC_ACK_IDLE: if (!immediate) { _debug("run defer timer"); - expiry = 1; + expiry = rxrpc_idle_ack_delay; goto run_timer; } goto cancel_timer; case RXRPC_ACK_REQUESTED: - if (!rxrpc_ack_defer) + expiry = rxrpc_requested_ack_delay; + if (!expiry) goto cancel_timer; if (!immediate || serial == cpu_to_be32(1)) { _debug("run defer timer"); - expiry = rxrpc_ack_defer; goto run_timer; } @@ -1174,11 +1215,11 @@ send_ACK: mtu = call->conn->trans->peer->if_mtu; mtu -= call->conn->trans->peer->hdrsize; ackinfo.maxMTU = htonl(mtu); - ackinfo.rwind = htonl(32); + ackinfo.rwind = htonl(rxrpc_rx_window_size); /* permit the peer to send us jumbo packets if it wants to */ - ackinfo.rxMTU = htonl(5692); - ackinfo.jumbo_max = htonl(4); + ackinfo.rxMTU = htonl(rxrpc_rx_mtu); + ackinfo.jumbo_max = htonl(rxrpc_rx_jumbo_max); hdr.serial = htonl(atomic_inc_return(&call->conn->serial)); _proto("Tx ACK %%%u { m=%hu f=#%u p=#%u s=%%%u r=%s n=%u }", diff --git a/net/rxrpc/ar-call.c b/net/rxrpc/ar-call.c index a3bbb360a3f9..a9e05db0f5d5 100644 --- a/net/rxrpc/ar-call.c +++ b/net/rxrpc/ar-call.c @@ -12,10 +12,22 @@ #include <linux/slab.h> #include <linux/module.h> #include <linux/circ_buf.h> +#include <linux/hashtable.h> +#include <linux/spinlock_types.h> #include <net/sock.h> #include <net/af_rxrpc.h> #include "ar-internal.h" +/* + * Maximum lifetime of a call (in jiffies). + */ +unsigned rxrpc_max_call_lifetime = 60 * HZ; + +/* + * Time till dead call expires after last use (in jiffies). + */ +unsigned rxrpc_dead_call_expiry = 2 * HZ; + const char *const rxrpc_call_states[] = { [RXRPC_CALL_CLIENT_SEND_REQUEST] = "ClSndReq", [RXRPC_CALL_CLIENT_AWAIT_REPLY] = "ClAwtRpl", @@ -38,8 +50,6 @@ const char *const rxrpc_call_states[] = { struct kmem_cache *rxrpc_call_jar; LIST_HEAD(rxrpc_calls); DEFINE_RWLOCK(rxrpc_call_lock); -static unsigned int rxrpc_call_max_lifetime = 60; -static unsigned int rxrpc_dead_call_timeout = 2; static void rxrpc_destroy_call(struct work_struct *work); static void rxrpc_call_life_expired(unsigned long _call); @@ -47,6 +57,145 @@ static void rxrpc_dead_call_expired(unsigned long _call); static void rxrpc_ack_time_expired(unsigned long _call); static void rxrpc_resend_time_expired(unsigned long _call); +static DEFINE_SPINLOCK(rxrpc_call_hash_lock); +static DEFINE_HASHTABLE(rxrpc_call_hash, 10); + +/* + * Hash function for rxrpc_call_hash + */ +static unsigned long rxrpc_call_hashfunc( + u8 clientflag, + __be32 cid, + __be32 call_id, + __be32 epoch, + __be16 service_id, + sa_family_t proto, + void *localptr, + unsigned int addr_size, + const u8 *peer_addr) +{ + const u16 *p; + unsigned int i; + unsigned long key; + u32 hcid = ntohl(cid); + + _enter(""); + + key = (unsigned long)localptr; + /* We just want to add up the __be32 values, so forcing the + * cast should be okay. + */ + key += (__force u32)epoch; + key += (__force u16)service_id; + key += (__force u32)call_id; + key += (hcid & RXRPC_CIDMASK) >> RXRPC_CIDSHIFT; + key += hcid & RXRPC_CHANNELMASK; + key += clientflag; + key += proto; + /* Step through the peer address in 16-bit portions for speed */ + for (i = 0, p = (const u16 *)peer_addr; i < addr_size >> 1; i++, p++) + key += *p; + _leave(" key = 0x%lx", key); + return key; +} + +/* + * Add a call to the hashtable + */ +static void rxrpc_call_hash_add(struct rxrpc_call *call) +{ + unsigned long key; + unsigned int addr_size = 0; + + _enter(""); + switch (call->proto) { + case AF_INET: + addr_size = sizeof(call->peer_ip.ipv4_addr); + break; + case AF_INET6: + addr_size = sizeof(call->peer_ip.ipv6_addr); + break; + default: + break; + } + key = rxrpc_call_hashfunc(call->in_clientflag, call->cid, + call->call_id, call->epoch, + call->service_id, call->proto, + call->conn->trans->local, addr_size, + call->peer_ip.ipv6_addr); + /* Store the full key in the call */ + call->hash_key = key; + spin_lock(&rxrpc_call_hash_lock); + hash_add_rcu(rxrpc_call_hash, &call->hash_node, key); + spin_unlock(&rxrpc_call_hash_lock); + _leave(""); +} + +/* + * Remove a call from the hashtable + */ +static void rxrpc_call_hash_del(struct rxrpc_call *call) +{ + _enter(""); + spin_lock(&rxrpc_call_hash_lock); + hash_del_rcu(&call->hash_node); + spin_unlock(&rxrpc_call_hash_lock); + _leave(""); +} + +/* + * Find a call in the hashtable and return it, or NULL if it + * isn't there. + */ +struct rxrpc_call *rxrpc_find_call_hash( + u8 clientflag, + __be32 cid, + __be32 call_id, + __be32 epoch, + __be16 service_id, + void *localptr, + sa_family_t proto, + const u8 *peer_addr) +{ + unsigned long key; + unsigned int addr_size = 0; + struct rxrpc_call *call = NULL; + struct rxrpc_call *ret = NULL; + + _enter(""); + switch (proto) { + case AF_INET: + addr_size = sizeof(call->peer_ip.ipv4_addr); + break; + case AF_INET6: + addr_size = sizeof(call->peer_ip.ipv6_addr); + break; + default: + break; + } + + key = rxrpc_call_hashfunc(clientflag, cid, call_id, epoch, + service_id, proto, localptr, addr_size, + peer_addr); + hash_for_each_possible_rcu(rxrpc_call_hash, call, hash_node, key) { + if (call->hash_key == key && + call->call_id == call_id && + call->cid == cid && + call->in_clientflag == clientflag && + call->service_id == service_id && + call->proto == proto && + call->local == localptr && + memcmp(call->peer_ip.ipv6_addr, peer_addr, + addr_size) == 0 && + call->epoch == epoch) { + ret = call; + break; + } + } + _leave(" = %p", ret); + return ret; +} + /* * allocate a new call */ @@ -91,7 +240,7 @@ static struct rxrpc_call *rxrpc_alloc_call(gfp_t gfp) call->rx_data_expect = 1; call->rx_data_eaten = 0; call->rx_first_oos = 0; - call->ackr_win_top = call->rx_data_eaten + 1 + RXRPC_MAXACKS; + call->ackr_win_top = call->rx_data_eaten + 1 + rxrpc_rx_window_size; call->creation_jif = jiffies; return call; } @@ -128,11 +277,31 @@ static struct rxrpc_call *rxrpc_alloc_client_call( return ERR_PTR(ret); } + /* Record copies of information for hashtable lookup */ + call->proto = rx->proto; + call->local = trans->local; + switch (call->proto) { + case AF_INET: + call->peer_ip.ipv4_addr = + trans->peer->srx.transport.sin.sin_addr.s_addr; + break; + case AF_INET6: + memcpy(call->peer_ip.ipv6_addr, + trans->peer->srx.transport.sin6.sin6_addr.in6_u.u6_addr8, + sizeof(call->peer_ip.ipv6_addr)); + break; + } + call->epoch = call->conn->epoch; + call->service_id = call->conn->service_id; + call->in_clientflag = call->conn->in_clientflag; + /* Add the new call to the hashtable */ + rxrpc_call_hash_add(call); + spin_lock(&call->conn->trans->peer->lock); list_add(&call->error_link, &call->conn->trans->peer->error_targets); spin_unlock(&call->conn->trans->peer->lock); - call->lifetimer.expires = jiffies + rxrpc_call_max_lifetime * HZ; + call->lifetimer.expires = jiffies + rxrpc_max_call_lifetime; add_timer(&call->lifetimer); _leave(" = %p", call); @@ -320,9 +489,12 @@ struct rxrpc_call *rxrpc_incoming_call(struct rxrpc_sock *rx, parent = *p; call = rb_entry(parent, struct rxrpc_call, conn_node); - if (call_id < call->call_id) + /* The tree is sorted in order of the __be32 value without + * turning it into host order. + */ + if ((__force u32)call_id < (__force u32)call->call_id) p = &(*p)->rb_left; - else if (call_id > call->call_id) + else if ((__force u32)call_id > (__force u32)call->call_id) p = &(*p)->rb_right; else goto old_call; @@ -347,9 +519,31 @@ struct rxrpc_call *rxrpc_incoming_call(struct rxrpc_sock *rx, list_add_tail(&call->link, &rxrpc_calls); write_unlock_bh(&rxrpc_call_lock); + /* Record copies of information for hashtable lookup */ + call->proto = rx->proto; + call->local = conn->trans->local; + switch (call->proto) { + case AF_INET: + call->peer_ip.ipv4_addr = + conn->trans->peer->srx.transport.sin.sin_addr.s_addr; + break; + case AF_INET6: + memcpy(call->peer_ip.ipv6_addr, + conn->trans->peer->srx.transport.sin6.sin6_addr.in6_u.u6_addr8, + sizeof(call->peer_ip.ipv6_addr)); + break; + default: + break; + } + call->epoch = conn->epoch; + call->service_id = conn->service_id; + call->in_clientflag = conn->in_clientflag; + /* Add the new call to the hashtable */ + rxrpc_call_hash_add(call); + _net("CALL incoming %d on CONN %d", call->debug_id, call->conn->debug_id); - call->lifetimer.expires = jiffies + rxrpc_call_max_lifetime * HZ; + call->lifetimer.expires = jiffies + rxrpc_max_call_lifetime; add_timer(&call->lifetimer); _leave(" = %p {%d} [new]", call, call->debug_id); return call; @@ -533,7 +727,7 @@ void rxrpc_release_call(struct rxrpc_call *call) del_timer_sync(&call->resend_timer); del_timer_sync(&call->ack_timer); del_timer_sync(&call->lifetimer); - call->deadspan.expires = jiffies + rxrpc_dead_call_timeout * HZ; + call->deadspan.expires = jiffies + rxrpc_dead_call_expiry; add_timer(&call->deadspan); _leave(""); @@ -665,6 +859,9 @@ static void rxrpc_cleanup_call(struct rxrpc_call *call) rxrpc_put_connection(call->conn); } + /* Remove the call from the hash */ + rxrpc_call_hash_del(call); + if (call->acks_window) { _debug("kill Tx window %d", CIRC_CNT(call->acks_head, call->acks_tail, diff --git a/net/rxrpc/ar-connection.c b/net/rxrpc/ar-connection.c index 7bf5b5b9e8b9..6631f4f1e39b 100644 --- a/net/rxrpc/ar-connection.c +++ b/net/rxrpc/ar-connection.c @@ -18,11 +18,15 @@ #include <net/af_rxrpc.h> #include "ar-internal.h" +/* + * Time till a connection expires after last use (in seconds). + */ +unsigned rxrpc_connection_expiry = 10 * 60; + static void rxrpc_connection_reaper(struct work_struct *work); LIST_HEAD(rxrpc_connections); DEFINE_RWLOCK(rxrpc_connection_lock); -static unsigned long rxrpc_connection_timeout = 10 * 60; static DECLARE_DELAYED_WORK(rxrpc_connection_reap, rxrpc_connection_reaper); /* @@ -862,7 +866,7 @@ static void rxrpc_connection_reaper(struct work_struct *work) spin_lock(&conn->trans->client_lock); write_lock(&conn->trans->conn_lock); - reap_time = conn->put_time + rxrpc_connection_timeout; + reap_time = conn->put_time + rxrpc_connection_expiry; if (atomic_read(&conn->usage) > 0) { ; @@ -916,7 +920,7 @@ void __exit rxrpc_destroy_all_connections(void) { _enter(""); - rxrpc_connection_timeout = 0; + rxrpc_connection_expiry = 0; cancel_delayed_work(&rxrpc_connection_reap); rxrpc_queue_delayed_work(&rxrpc_connection_reap, 0); diff --git a/net/rxrpc/ar-error.c b/net/rxrpc/ar-error.c index a9206087b4d7..db57458c824c 100644 --- a/net/rxrpc/ar-error.c +++ b/net/rxrpc/ar-error.c @@ -83,6 +83,7 @@ void rxrpc_UDP_error_report(struct sock *sk) if (mtu == 0) { /* they didn't give us a size, estimate one */ + mtu = peer->if_mtu; if (mtu > 1500) { mtu >>= 1; if (mtu < 1500) diff --git a/net/rxrpc/ar-input.c b/net/rxrpc/ar-input.c index 529572f18d1f..73742647c135 100644 --- a/net/rxrpc/ar-input.c +++ b/net/rxrpc/ar-input.c @@ -25,8 +25,6 @@ #include <net/net_namespace.h> #include "ar-internal.h" -unsigned long rxrpc_ack_timeout = 1; - const char *rxrpc_pkts[] = { "?00", "DATA", "ACK", "BUSY", "ABORT", "ACKALL", "CHALL", "RESP", "DEBUG", @@ -349,8 +347,7 @@ void rxrpc_fast_process_packet(struct rxrpc_call *call, struct sk_buff *skb) * it */ if (sp->hdr.flags & RXRPC_REQUEST_ACK) { _proto("ACK Requested on %%%u", serial); - rxrpc_propose_ACK(call, RXRPC_ACK_REQUESTED, sp->hdr.serial, - !(sp->hdr.flags & RXRPC_MORE_PACKETS)); + rxrpc_propose_ACK(call, RXRPC_ACK_REQUESTED, sp->hdr.serial, false); } switch (sp->hdr.type) { @@ -526,36 +523,38 @@ protocol_error: * post an incoming packet to the appropriate call/socket to deal with * - must get rid of the sk_buff, either by freeing it or by queuing it */ -static void rxrpc_post_packet_to_call(struct rxrpc_connection *conn, +static void rxrpc_post_packet_to_call(struct rxrpc_call *call, struct sk_buff *skb) { struct rxrpc_skb_priv *sp; - struct rxrpc_call *call; - struct rb_node *p; - __be32 call_id; - - _enter("%p,%p", conn, skb); - read_lock_bh(&conn->lock); + _enter("%p,%p", call, skb); sp = rxrpc_skb(skb); - /* look at extant calls by channel number first */ - call = conn->channels[ntohl(sp->hdr.cid) & RXRPC_CHANNELMASK]; - if (!call || call->call_id != sp->hdr.callNumber) - goto call_not_extant; - _debug("extant call [%d]", call->state); - ASSERTCMP(call->conn, ==, conn); read_lock(&call->state_lock); switch (call->state) { case RXRPC_CALL_LOCALLY_ABORTED: - if (!test_and_set_bit(RXRPC_CALL_ABORT, &call->events)) + if (!test_and_set_bit(RXRPC_CALL_ABORT, &call->events)) { rxrpc_queue_call(call); + goto free_unlock; + } case RXRPC_CALL_REMOTELY_ABORTED: case RXRPC_CALL_NETWORK_ERROR: case RXRPC_CALL_DEAD: + goto dead_call; + case RXRPC_CALL_COMPLETE: + case RXRPC_CALL_CLIENT_FINAL_ACK: + /* complete server call */ + if (call->conn->in_clientflag) + goto dead_call; + /* resend last packet of a completed call */ + _debug("final ack again"); + rxrpc_get_call(call); + set_bit(RXRPC_CALL_ACK_FINAL, &call->events); + rxrpc_queue_call(call); goto free_unlock; default: break; @@ -563,7 +562,6 @@ static void rxrpc_post_packet_to_call(struct rxrpc_connection *conn, read_unlock(&call->state_lock); rxrpc_get_call(call); - read_unlock_bh(&conn->lock); if (sp->hdr.type == RXRPC_PACKET_TYPE_DATA && sp->hdr.flags & RXRPC_JUMBO_PACKET) @@ -574,78 +572,16 @@ static void rxrpc_post_packet_to_call(struct rxrpc_connection *conn, rxrpc_put_call(call); goto done; -call_not_extant: - /* search the completed calls in case what we're dealing with is - * there */ - _debug("call not extant"); - - call_id = sp->hdr.callNumber; - p = conn->calls.rb_node; - while (p) { - call = rb_entry(p, struct rxrpc_call, conn_node); - - if (call_id < call->call_id) - p = p->rb_left; - else if (call_id > call->call_id) - p = p->rb_right; - else - goto found_completed_call; - } - dead_call: - /* it's a either a really old call that we no longer remember or its a - * new incoming call */ - read_unlock_bh(&conn->lock); - - if (sp->hdr.flags & RXRPC_CLIENT_INITIATED && - sp->hdr.seq == cpu_to_be32(1)) { - _debug("incoming call"); - skb_queue_tail(&conn->trans->local->accept_queue, skb); - rxrpc_queue_work(&conn->trans->local->acceptor); - goto done; - } - - _debug("dead call"); - skb->priority = RX_CALL_DEAD; - rxrpc_reject_packet(conn->trans->local, skb); - goto done; - - /* resend last packet of a completed call - * - client calls may have been aborted or ACK'd - * - server calls may have been aborted - */ -found_completed_call: - _debug("completed call"); - - if (atomic_read(&call->usage) == 0) - goto dead_call; - - /* synchronise any state changes */ - read_lock(&call->state_lock); - ASSERTIFCMP(call->state != RXRPC_CALL_CLIENT_FINAL_ACK, - call->state, >=, RXRPC_CALL_COMPLETE); - - if (call->state == RXRPC_CALL_LOCALLY_ABORTED || - call->state == RXRPC_CALL_REMOTELY_ABORTED || - call->state == RXRPC_CALL_DEAD) { - read_unlock(&call->state_lock); - goto dead_call; - } - - if (call->conn->in_clientflag) { - read_unlock(&call->state_lock); - goto dead_call; /* complete server call */ + if (sp->hdr.type != RXRPC_PACKET_TYPE_ABORT) { + skb->priority = RX_CALL_DEAD; + rxrpc_reject_packet(call->conn->trans->local, skb); + goto unlock; } - - _debug("final ack again"); - rxrpc_get_call(call); - set_bit(RXRPC_CALL_ACK_FINAL, &call->events); - rxrpc_queue_call(call); - free_unlock: - read_unlock(&call->state_lock); - read_unlock_bh(&conn->lock); rxrpc_free_skb(skb); +unlock: + read_unlock(&call->state_lock); done: _leave(""); } @@ -664,17 +600,42 @@ static void rxrpc_post_packet_to_conn(struct rxrpc_connection *conn, rxrpc_queue_conn(conn); } +static struct rxrpc_connection *rxrpc_conn_from_local(struct rxrpc_local *local, + struct sk_buff *skb, + struct rxrpc_skb_priv *sp) +{ + struct rxrpc_peer *peer; + struct rxrpc_transport *trans; + struct rxrpc_connection *conn; + + peer = rxrpc_find_peer(local, ip_hdr(skb)->saddr, + udp_hdr(skb)->source); + if (IS_ERR(peer)) + goto cant_find_conn; + + trans = rxrpc_find_transport(local, peer); + rxrpc_put_peer(peer); + if (!trans) + goto cant_find_conn; + + conn = rxrpc_find_connection(trans, &sp->hdr); + rxrpc_put_transport(trans); + if (!conn) + goto cant_find_conn; + + return conn; +cant_find_conn: + return NULL; +} + /* * handle data received on the local endpoint * - may be called in interrupt context */ void rxrpc_data_ready(struct sock *sk, int count) { - struct rxrpc_connection *conn; - struct rxrpc_transport *trans; struct rxrpc_skb_priv *sp; struct rxrpc_local *local; - struct rxrpc_peer *peer; struct sk_buff *skb; int ret; @@ -749,27 +710,34 @@ void rxrpc_data_ready(struct sock *sk, int count) (sp->hdr.callNumber == 0 || sp->hdr.seq == 0)) goto bad_message; - peer = rxrpc_find_peer(local, ip_hdr(skb)->saddr, udp_hdr(skb)->source); - if (IS_ERR(peer)) - goto cant_route_call; + if (sp->hdr.callNumber == 0) { + /* This is a connection-level packet. These should be + * fairly rare, so the extra overhead of looking them up the + * old-fashioned way doesn't really hurt */ + struct rxrpc_connection *conn; - trans = rxrpc_find_transport(local, peer); - rxrpc_put_peer(peer); - if (!trans) - goto cant_route_call; + conn = rxrpc_conn_from_local(local, skb, sp); + if (!conn) + goto cant_route_call; - conn = rxrpc_find_connection(trans, &sp->hdr); - rxrpc_put_transport(trans); - if (!conn) - goto cant_route_call; - - _debug("CONN %p {%d}", conn, conn->debug_id); - - if (sp->hdr.callNumber == 0) + _debug("CONN %p {%d}", conn, conn->debug_id); rxrpc_post_packet_to_conn(conn, skb); - else - rxrpc_post_packet_to_call(conn, skb); - rxrpc_put_connection(conn); + rxrpc_put_connection(conn); + } else { + struct rxrpc_call *call; + u8 in_clientflag = 0; + + if (sp->hdr.flags & RXRPC_CLIENT_INITIATED) + in_clientflag = RXRPC_CLIENT_INITIATED; + call = rxrpc_find_call_hash(in_clientflag, sp->hdr.cid, + sp->hdr.callNumber, sp->hdr.epoch, + sp->hdr.serviceId, local, AF_INET, + (u8 *)&ip_hdr(skb)->saddr); + if (call) + rxrpc_post_packet_to_call(call, skb); + else + goto cant_route_call; + } rxrpc_put_local(local); return; @@ -790,8 +758,10 @@ cant_route_call: skb->priority = RX_CALL_DEAD; } - _debug("reject"); - rxrpc_reject_packet(local, skb); + if (sp->hdr.type != RXRPC_PACKET_TYPE_ABORT) { + _debug("reject type %d",sp->hdr.type); + rxrpc_reject_packet(local, skb); + } rxrpc_put_local(local); _leave(" [no call]"); return; diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 5f43675ee1df..c831d44b0841 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -396,9 +396,20 @@ struct rxrpc_call { #define RXRPC_ACKR_WINDOW_ASZ DIV_ROUND_UP(RXRPC_MAXACKS, BITS_PER_LONG) unsigned long ackr_window[RXRPC_ACKR_WINDOW_ASZ + 1]; + struct hlist_node hash_node; + unsigned long hash_key; /* Full hash key */ + u8 in_clientflag; /* Copy of conn->in_clientflag for hashing */ + struct rxrpc_local *local; /* Local endpoint. Used for hashing. */ + sa_family_t proto; /* Frame protocol */ /* the following should all be in net order */ __be32 cid; /* connection ID + channel index */ __be32 call_id; /* call ID on connection */ + __be32 epoch; /* epoch of this connection */ + __be16 service_id; /* service ID */ + union { /* Peer IP address for hashing */ + __be32 ipv4_addr; + __u8 ipv6_addr[16]; /* Anticipates eventual IPv6 support */ + } peer_ip; }; /* @@ -433,6 +444,13 @@ int rxrpc_reject_call(struct rxrpc_sock *); /* * ar-ack.c */ +extern unsigned rxrpc_requested_ack_delay; +extern unsigned rxrpc_soft_ack_delay; +extern unsigned rxrpc_idle_ack_delay; +extern unsigned rxrpc_rx_window_size; +extern unsigned rxrpc_rx_mtu; +extern unsigned rxrpc_rx_jumbo_max; + void __rxrpc_propose_ACK(struct rxrpc_call *, u8, __be32, bool); void rxrpc_propose_ACK(struct rxrpc_call *, u8, __be32, bool); void rxrpc_process_call(struct work_struct *); @@ -440,10 +458,14 @@ void rxrpc_process_call(struct work_struct *); /* * ar-call.c */ +extern unsigned rxrpc_max_call_lifetime; +extern unsigned rxrpc_dead_call_expiry; extern struct kmem_cache *rxrpc_call_jar; extern struct list_head rxrpc_calls; extern rwlock_t rxrpc_call_lock; +struct rxrpc_call *rxrpc_find_call_hash(u8, __be32, __be32, __be32, + __be16, void *, sa_family_t, const u8 *); struct rxrpc_call *rxrpc_get_client_call(struct rxrpc_sock *, struct rxrpc_transport *, struct rxrpc_conn_bundle *, @@ -460,6 +482,7 @@ void __exit rxrpc_destroy_all_calls(void); /* * ar-connection.c */ +extern unsigned rxrpc_connection_expiry; extern struct list_head rxrpc_connections; extern rwlock_t rxrpc_connection_lock; @@ -493,7 +516,6 @@ void rxrpc_UDP_error_handler(struct work_struct *); /* * ar-input.c */ -extern unsigned long rxrpc_ack_timeout; extern const char *rxrpc_pkts[]; void rxrpc_data_ready(struct sock *, int); @@ -504,6 +526,7 @@ void rxrpc_fast_process_packet(struct rxrpc_call *, struct sk_buff *); * ar-local.c */ extern rwlock_t rxrpc_local_lock; + struct rxrpc_local *rxrpc_lookup_local(struct sockaddr_rxrpc *); void rxrpc_put_local(struct rxrpc_local *); void __exit rxrpc_destroy_all_locals(void); @@ -522,7 +545,7 @@ int rxrpc_get_server_data_key(struct rxrpc_connection *, const void *, time_t, /* * ar-output.c */ -extern int rxrpc_resend_timeout; +extern unsigned rxrpc_resend_timeout; int rxrpc_send_packet(struct rxrpc_transport *, struct sk_buff *); int rxrpc_client_sendmsg(struct kiocb *, struct rxrpc_sock *, @@ -572,6 +595,8 @@ void rxrpc_packet_destructor(struct sk_buff *); /* * ar-transport.c */ +extern unsigned rxrpc_transport_expiry; + struct rxrpc_transport *rxrpc_get_transport(struct rxrpc_local *, struct rxrpc_peer *, gfp_t); void rxrpc_put_transport(struct rxrpc_transport *); @@ -580,6 +605,17 @@ struct rxrpc_transport *rxrpc_find_transport(struct rxrpc_local *, struct rxrpc_peer *); /* + * sysctl.c + */ +#ifdef CONFIG_SYSCTL +extern int __init rxrpc_sysctl_init(void); +extern void rxrpc_sysctl_exit(void); +#else +static inline int __init rxrpc_sysctl_init(void) { return 0; } +static inline void rxrpc_sysctl_exit(void) {} +#endif + +/* * debug tracing */ extern unsigned int rxrpc_debug; diff --git a/net/rxrpc/ar-output.c b/net/rxrpc/ar-output.c index d0e8f1c1898a..0b4b9a79f5ab 100644 --- a/net/rxrpc/ar-output.c +++ b/net/rxrpc/ar-output.c @@ -18,7 +18,10 @@ #include <net/af_rxrpc.h> #include "ar-internal.h" -int rxrpc_resend_timeout = 4; +/* + * Time till packet resend (in jiffies). + */ +unsigned rxrpc_resend_timeout = 4 * HZ; static int rxrpc_send_data(struct kiocb *iocb, struct rxrpc_sock *rx, @@ -487,7 +490,7 @@ static void rxrpc_queue_packet(struct rxrpc_call *call, struct sk_buff *skb, ntohl(sp->hdr.serial), ntohl(sp->hdr.seq)); sp->need_resend = false; - sp->resend_at = jiffies + rxrpc_resend_timeout * HZ; + sp->resend_at = jiffies + rxrpc_resend_timeout; if (!test_and_set_bit(RXRPC_CALL_RUN_RTIMER, &call->flags)) { _debug("run timer"); call->resend_timer.expires = sp->resend_at; @@ -666,6 +669,7 @@ static int rxrpc_send_data(struct kiocb *iocb, /* add the packet to the send queue if it's now full */ if (sp->remain <= 0 || (segment == 0 && !more)) { struct rxrpc_connection *conn = call->conn; + uint32_t seq; size_t pad; /* pad out if we're using security */ @@ -678,11 +682,12 @@ static int rxrpc_send_data(struct kiocb *iocb, memset(skb_put(skb, pad), 0, pad); } + seq = atomic_inc_return(&call->sequence); + sp->hdr.epoch = conn->epoch; sp->hdr.cid = call->cid; sp->hdr.callNumber = call->call_id; - sp->hdr.seq = - htonl(atomic_inc_return(&call->sequence)); + sp->hdr.seq = htonl(seq); sp->hdr.serial = htonl(atomic_inc_return(&conn->serial)); sp->hdr.type = RXRPC_PACKET_TYPE_DATA; @@ -697,6 +702,8 @@ static int rxrpc_send_data(struct kiocb *iocb, else if (CIRC_SPACE(call->acks_head, call->acks_tail, call->acks_winsz) > 1) sp->hdr.flags |= RXRPC_MORE_PACKETS; + if (more && seq & 1) + sp->hdr.flags |= RXRPC_REQUEST_ACK; ret = rxrpc_secure_packet( call, skb, skb->mark, diff --git a/net/rxrpc/ar-recvmsg.c b/net/rxrpc/ar-recvmsg.c index 34b5490dde65..e9aaa65c0778 100644 --- a/net/rxrpc/ar-recvmsg.c +++ b/net/rxrpc/ar-recvmsg.c @@ -180,16 +180,7 @@ int rxrpc_recvmsg(struct kiocb *iocb, struct socket *sock, if (copy > len - copied) copy = len - copied; - if (skb->ip_summed == CHECKSUM_UNNECESSARY || - skb->ip_summed == CHECKSUM_PARTIAL) { - ret = skb_copy_datagram_iovec(skb, offset, - msg->msg_iov, copy); - } else { - ret = skb_copy_and_csum_datagram_iovec(skb, offset, - msg->msg_iov); - if (ret == -EINVAL) - goto csum_copy_error; - } + ret = skb_copy_datagram_iovec(skb, offset, msg->msg_iov, copy); if (ret < 0) goto copy_error; @@ -348,20 +339,6 @@ copy_error: _leave(" = %d", ret); return ret; -csum_copy_error: - _debug("csum error"); - release_sock(&rx->sk); - if (continue_call) - rxrpc_put_call(continue_call); - rxrpc_kill_skb(skb); - if (!(flags & MSG_PEEK)) { - if (skb_dequeue(&rx->sk.sk_receive_queue) != skb) - BUG(); - } - skb_kill_datagram(&rx->sk, skb, flags); - rxrpc_put_call(call); - return -EAGAIN; - wait_interrupted: ret = sock_intr_errno(timeo); wait_error: diff --git a/net/rxrpc/ar-skbuff.c b/net/rxrpc/ar-skbuff.c index de755e04d29c..4cfab49e329d 100644 --- a/net/rxrpc/ar-skbuff.c +++ b/net/rxrpc/ar-skbuff.c @@ -83,9 +83,14 @@ static void rxrpc_hard_ACK_data(struct rxrpc_call *call, rxrpc_request_final_ACK(call); } else if (atomic_dec_and_test(&call->ackr_not_idle) && test_and_clear_bit(RXRPC_CALL_TX_SOFT_ACK, &call->flags)) { + /* We previously soft-ACK'd some received packets that have now + * been consumed, so send a hard-ACK if no more packets are + * immediately forthcoming to allow the transmitter to free up + * its Tx bufferage. + */ _debug("send Rx idle ACK"); __rxrpc_propose_ACK(call, RXRPC_ACK_IDLE, sp->hdr.serial, - true); + false); } spin_unlock_bh(&call->lock); diff --git a/net/rxrpc/ar-transport.c b/net/rxrpc/ar-transport.c index 92df566930b9..1976dec84f29 100644 --- a/net/rxrpc/ar-transport.c +++ b/net/rxrpc/ar-transport.c @@ -17,11 +17,15 @@ #include <net/af_rxrpc.h> #include "ar-internal.h" +/* + * Time after last use at which transport record is cleaned up. + */ +unsigned rxrpc_transport_expiry = 3600 * 24; + static void rxrpc_transport_reaper(struct work_struct *work); static LIST_HEAD(rxrpc_transports); static DEFINE_RWLOCK(rxrpc_transport_lock); -static unsigned long rxrpc_transport_timeout = 3600 * 24; static DECLARE_DELAYED_WORK(rxrpc_transport_reap, rxrpc_transport_reaper); /* @@ -235,7 +239,7 @@ static void rxrpc_transport_reaper(struct work_struct *work) if (likely(atomic_read(&trans->usage) > 0)) continue; - reap_time = trans->put_time + rxrpc_transport_timeout; + reap_time = trans->put_time + rxrpc_transport_expiry; if (reap_time <= now) list_move_tail(&trans->link, &graveyard); else if (reap_time < earliest) @@ -271,7 +275,7 @@ void __exit rxrpc_destroy_all_transports(void) { _enter(""); - rxrpc_transport_timeout = 0; + rxrpc_transport_expiry = 0; cancel_delayed_work(&rxrpc_transport_reap); rxrpc_queue_delayed_work(&rxrpc_transport_reap, 0); diff --git a/net/rxrpc/sysctl.c b/net/rxrpc/sysctl.c new file mode 100644 index 000000000000..50a98a910eb1 --- /dev/null +++ b/net/rxrpc/sysctl.c @@ -0,0 +1,146 @@ +/* sysctls for configuring RxRPC operating parameters + * + * Copyright (C) 2014 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ + +#include <linux/sysctl.h> +#include <net/sock.h> +#include <net/af_rxrpc.h> +#include "ar-internal.h" + +static struct ctl_table_header *rxrpc_sysctl_reg_table; +static const unsigned zero = 0; +static const unsigned one = 1; +static const unsigned four = 4; +static const unsigned n_65535 = 65535; +static const unsigned n_max_acks = RXRPC_MAXACKS; + +/* + * RxRPC operating parameters. + * + * See Documentation/networking/rxrpc.txt and the variable definitions for more + * information on the individual parameters. + */ +static struct ctl_table rxrpc_sysctl_table[] = { + /* Values measured in milliseconds */ + { + .procname = "req_ack_delay", + .data = &rxrpc_requested_ack_delay, + .maxlen = sizeof(unsigned), + .mode = 0644, + .proc_handler = proc_dointvec_ms_jiffies, + .extra1 = (void *)&zero, + }, + { + .procname = "soft_ack_delay", + .data = &rxrpc_soft_ack_delay, + .maxlen = sizeof(unsigned), + .mode = 0644, + .proc_handler = proc_dointvec_ms_jiffies, + .extra1 = (void *)&one, + }, + { + .procname = "idle_ack_delay", + .data = &rxrpc_idle_ack_delay, + .maxlen = sizeof(unsigned), + .mode = 0644, + .proc_handler = proc_dointvec_ms_jiffies, + .extra1 = (void *)&one, + }, + { + .procname = "resend_timeout", + .data = &rxrpc_resend_timeout, + .maxlen = sizeof(unsigned), + .mode = 0644, + .proc_handler = proc_dointvec_ms_jiffies, + .extra1 = (void *)&one, + }, + + /* Values measured in seconds but used in jiffies */ + { + .procname = "max_call_lifetime", + .data = &rxrpc_max_call_lifetime, + .maxlen = sizeof(unsigned), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + .extra1 = (void *)&one, + }, + { + .procname = "dead_call_expiry", + .data = &rxrpc_dead_call_expiry, + .maxlen = sizeof(unsigned), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + .extra1 = (void *)&one, + }, + + /* Values measured in seconds */ + { + .procname = "connection_expiry", + .data = &rxrpc_connection_expiry, + .maxlen = sizeof(unsigned), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = (void *)&one, + }, + { + .procname = "transport_expiry", + .data = &rxrpc_transport_expiry, + .maxlen = sizeof(unsigned), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = (void *)&one, + }, + + /* Non-time values */ + { + .procname = "rx_window_size", + .data = &rxrpc_rx_window_size, + .maxlen = sizeof(unsigned), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = (void *)&one, + .extra2 = (void *)&n_max_acks, + }, + { + .procname = "rx_mtu", + .data = &rxrpc_rx_mtu, + .maxlen = sizeof(unsigned), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = (void *)&one, + .extra1 = (void *)&n_65535, + }, + { + .procname = "rx_jumbo_max", + .data = &rxrpc_rx_jumbo_max, + .maxlen = sizeof(unsigned), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = (void *)&one, + .extra2 = (void *)&four, + }, + + { } +}; + +int __init rxrpc_sysctl_init(void) +{ + rxrpc_sysctl_reg_table = register_net_sysctl(&init_net, "net/rxrpc", + rxrpc_sysctl_table); + if (!rxrpc_sysctl_reg_table) + return -ENOMEM; + return 0; +} + +void rxrpc_sysctl_exit(void) +{ + if (rxrpc_sysctl_reg_table) + unregister_net_sysctl_table(rxrpc_sysctl_reg_table); +} diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 72bdc7166345..8a5ba5add4bc 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -27,8 +27,11 @@ #include <net/act_api.h> #include <net/netlink.h> -void tcf_hash_destroy(struct tcf_common *p, struct tcf_hashinfo *hinfo) +void tcf_hash_destroy(struct tc_action *a) { + struct tcf_common *p = a->priv; + struct tcf_hashinfo *hinfo = a->ops->hinfo; + spin_lock_bh(&hinfo->lock); hlist_del(&p->tcfc_head); spin_unlock_bh(&hinfo->lock); @@ -42,18 +45,22 @@ void tcf_hash_destroy(struct tcf_common *p, struct tcf_hashinfo *hinfo) } EXPORT_SYMBOL(tcf_hash_destroy); -int tcf_hash_release(struct tcf_common *p, int bind, - struct tcf_hashinfo *hinfo) +int tcf_hash_release(struct tc_action *a, int bind) { + struct tcf_common *p = a->priv; int ret = 0; if (p) { if (bind) p->tcfc_bindcnt--; + else if (p->tcfc_bindcnt > 0) + return -EPERM; p->tcfc_refcnt--; if (p->tcfc_bindcnt <= 0 && p->tcfc_refcnt <= 0) { - tcf_hash_destroy(p, hinfo); + if (a->ops->cleanup) + a->ops->cleanup(a, bind); + tcf_hash_destroy(a); ret = 1; } } @@ -118,6 +125,7 @@ static int tcf_del_walker(struct sk_buff *skb, struct tc_action *a) struct tcf_common *p; struct nlattr *nest; int i = 0, n_i = 0; + int ret = -EINVAL; nest = nla_nest_start(skb, a->order); if (nest == NULL) @@ -127,10 +135,13 @@ static int tcf_del_walker(struct sk_buff *skb, struct tc_action *a) for (i = 0; i < (hinfo->hmask + 1); i++) { head = &hinfo->htab[tcf_hash(i, hinfo->hmask)]; hlist_for_each_entry_safe(p, n, head, tcfc_head) { - if (ACT_P_DELETED == tcf_hash_release(p, 0, hinfo)) { + a->priv = p; + ret = tcf_hash_release(a, 0); + if (ret == ACT_P_DELETED) { module_put(a->ops->owner); n_i++; - } + } else if (ret < 0) + goto nla_put_failure; } } if (nla_put_u32(skb, TCA_FCNT, n_i)) @@ -140,7 +151,7 @@ static int tcf_del_walker(struct sk_buff *skb, struct tc_action *a) return n_i; nla_put_failure: nla_nest_cancel(skb, nest); - return -EINVAL; + return ret; } static int tcf_generic_walker(struct sk_buff *skb, struct netlink_callback *cb, @@ -198,7 +209,7 @@ int tcf_hash_search(struct tc_action *a, u32 index) } EXPORT_SYMBOL(tcf_hash_search); -struct tcf_common *tcf_hash_check(u32 index, struct tc_action *a, int bind) +int tcf_hash_check(u32 index, struct tc_action *a, int bind) { struct tcf_hashinfo *hinfo = a->ops->hinfo; struct tcf_common *p = NULL; @@ -207,19 +218,30 @@ struct tcf_common *tcf_hash_check(u32 index, struct tc_action *a, int bind) p->tcfc_bindcnt++; p->tcfc_refcnt++; a->priv = p; + return 1; } - return p; + return 0; } EXPORT_SYMBOL(tcf_hash_check); -struct tcf_common *tcf_hash_create(u32 index, struct nlattr *est, - struct tc_action *a, int size, int bind) +void tcf_hash_cleanup(struct tc_action *a, struct nlattr *est) +{ + struct tcf_common *pc = a->priv; + if (est) + gen_kill_estimator(&pc->tcfc_bstats, + &pc->tcfc_rate_est); + kfree_rcu(pc, tcfc_rcu); +} +EXPORT_SYMBOL(tcf_hash_cleanup); + +int tcf_hash_create(u32 index, struct nlattr *est, struct tc_action *a, + int size, int bind) { struct tcf_hashinfo *hinfo = a->ops->hinfo; struct tcf_common *p = kzalloc(size, GFP_KERNEL); if (unlikely(!p)) - return ERR_PTR(-ENOMEM); + return -ENOMEM; p->tcfc_refcnt = 1; if (bind) p->tcfc_bindcnt = 1; @@ -234,17 +256,19 @@ struct tcf_common *tcf_hash_create(u32 index, struct nlattr *est, &p->tcfc_lock, est); if (err) { kfree(p); - return ERR_PTR(err); + return err; } } a->priv = (void *) p; - return p; + return 0; } EXPORT_SYMBOL(tcf_hash_create); -void tcf_hash_insert(struct tcf_common *p, struct tcf_hashinfo *hinfo) +void tcf_hash_insert(struct tc_action *a) { + struct tcf_common *p = a->priv; + struct tcf_hashinfo *hinfo = a->ops->hinfo; unsigned int h = tcf_hash(p->tcfc_index, hinfo->hmask); spin_lock_bh(&hinfo->lock); @@ -256,12 +280,13 @@ EXPORT_SYMBOL(tcf_hash_insert); static LIST_HEAD(act_base); static DEFINE_RWLOCK(act_mod_lock); -int tcf_register_action(struct tc_action_ops *act) +int tcf_register_action(struct tc_action_ops *act, unsigned int mask) { struct tc_action_ops *a; + int err; - /* Must supply act, dump, cleanup and init */ - if (!act->act || !act->dump || !act->cleanup || !act->init) + /* Must supply act, dump and init */ + if (!act->act || !act->dump || !act->init) return -EINVAL; /* Supply defaults */ @@ -270,10 +295,21 @@ int tcf_register_action(struct tc_action_ops *act) if (!act->walk) act->walk = tcf_generic_walker; + act->hinfo = kmalloc(sizeof(struct tcf_hashinfo), GFP_KERNEL); + if (!act->hinfo) + return -ENOMEM; + err = tcf_hashinfo_init(act->hinfo, mask); + if (err) { + kfree(act->hinfo); + return err; + } + write_lock(&act_mod_lock); list_for_each_entry(a, &act_base, head) { if (act->type == a->type || (strcmp(act->kind, a->kind) == 0)) { write_unlock(&act_mod_lock); + tcf_hashinfo_destroy(act->hinfo); + kfree(act->hinfo); return -EEXIST; } } @@ -292,6 +328,8 @@ int tcf_unregister_action(struct tc_action_ops *act) list_for_each_entry(a, &act_base, head) { if (a == act) { list_del(&act->head); + tcf_hashinfo_destroy(act->hinfo); + kfree(act->hinfo); err = 0; break; } @@ -368,16 +406,21 @@ exec_done: } EXPORT_SYMBOL(tcf_action_exec); -void tcf_action_destroy(struct list_head *actions, int bind) +int tcf_action_destroy(struct list_head *actions, int bind) { struct tc_action *a, *tmp; + int ret = 0; list_for_each_entry_safe(a, tmp, actions, list) { - if (a->ops->cleanup(a, bind) == ACT_P_DELETED) + ret = tcf_hash_release(a, bind); + if (ret == ACT_P_DELETED) module_put(a->ops->owner); + else if (ret < 0) + return ret; list_del(&a->list); kfree(a); } + return ret; } int @@ -642,6 +685,20 @@ act_get_notify(struct net *net, u32 portid, struct nlmsghdr *n, return rtnl_unicast(skb, net, portid); } +static struct tc_action *create_a(int i) +{ + struct tc_action *act; + + act = kzalloc(sizeof(*act), GFP_KERNEL); + if (act == NULL) { + pr_debug("create_a: failed to alloc!\n"); + return NULL; + } + act->order = i; + INIT_LIST_HEAD(&act->list); + return act; +} + static struct tc_action * tcf_action_get_1(struct nlattr *nla, struct nlmsghdr *n, u32 portid) { @@ -661,11 +718,10 @@ tcf_action_get_1(struct nlattr *nla, struct nlmsghdr *n, u32 portid) index = nla_get_u32(tb[TCA_ACT_INDEX]); err = -ENOMEM; - a = kzalloc(sizeof(struct tc_action), GFP_KERNEL); + a = create_a(0); if (a == NULL) goto err_out; - INIT_LIST_HEAD(&a->list); err = -EINVAL; a->ops = tc_lookup_action(tb[TCA_ACT_KIND]); if (a->ops == NULL) /* could happen in batch of actions */ @@ -695,20 +751,6 @@ static void cleanup_a(struct list_head *actions) } } -static struct tc_action *create_a(int i) -{ - struct tc_action *act; - - act = kzalloc(sizeof(*act), GFP_KERNEL); - if (act == NULL) { - pr_debug("create_a: failed to alloc!\n"); - return NULL; - } - act->order = i; - INIT_LIST_HEAD(&act->list); - return act; -} - static int tca_action_flush(struct net *net, struct nlattr *nla, struct nlmsghdr *n, u32 portid) { @@ -720,18 +762,12 @@ static int tca_action_flush(struct net *net, struct nlattr *nla, struct nlattr *nest; struct nlattr *tb[TCA_ACT_MAX + 1]; struct nlattr *kind; - struct tc_action *a = create_a(0); + struct tc_action a; int err = -ENOMEM; - if (a == NULL) { - pr_debug("tca_action_flush: couldnt create tc_action\n"); - return err; - } - skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) { pr_debug("tca_action_flush: failed skb alloc\n"); - kfree(a); return err; } @@ -743,8 +779,10 @@ static int tca_action_flush(struct net *net, struct nlattr *nla, err = -EINVAL; kind = tb[TCA_ACT_KIND]; - a->ops = tc_lookup_action(kind); - if (a->ops == NULL) /*some idjot trying to flush unknown action */ + memset(&a, 0, sizeof(struct tc_action)); + INIT_LIST_HEAD(&a.list); + a.ops = tc_lookup_action(kind); + if (a.ops == NULL) /*some idjot trying to flush unknown action */ goto err_out; nlh = nlmsg_put(skb, portid, n->nlmsg_seq, RTM_DELACTION, sizeof(*t), 0); @@ -759,7 +797,7 @@ static int tca_action_flush(struct net *net, struct nlattr *nla, if (nest == NULL) goto out_module_put; - err = a->ops->walk(skb, &dcb, RTM_DELACTION, a); + err = a.ops->walk(skb, &dcb, RTM_DELACTION, &a); if (err < 0) goto out_module_put; if (err == 0) @@ -769,8 +807,7 @@ static int tca_action_flush(struct net *net, struct nlattr *nla, nlh->nlmsg_len = skb_tail_pointer(skb) - b; nlh->nlmsg_flags |= NLM_F_ROOT; - module_put(a->ops->owner); - kfree(a); + module_put(a.ops->owner); err = rtnetlink_send(skb, net, portid, RTNLGRP_TC, n->nlmsg_flags & NLM_F_ECHO); if (err > 0) @@ -779,11 +816,10 @@ static int tca_action_flush(struct net *net, struct nlattr *nla, return err; out_module_put: - module_put(a->ops->owner); + module_put(a.ops->owner); err_out: noflush_out: kfree_skb(skb); - kfree(a); return err; } @@ -805,7 +841,11 @@ tcf_del_notify(struct net *net, struct nlmsghdr *n, struct list_head *actions, } /* now do the delete */ - tcf_action_destroy(actions, 0); + ret = tcf_action_destroy(actions, 0); + if (ret < 0) { + kfree_skb(skb); + return ret; + } ret = rtnetlink_send(skb, net, portid, RTNLGRP_TC, n->nlmsg_flags & NLM_F_ECHO); diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index 2210187c45c2..edbf40dac709 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -37,7 +37,6 @@ #include <net/tc_act/tc_csum.h> #define CSUM_TAB_MASK 15 -static struct tcf_hashinfo csum_hash_info; static const struct nla_policy csum_policy[TCA_CSUM_MAX + 1] = { [TCA_CSUM_PARMS] = { .len = sizeof(struct tc_csum), }, @@ -48,7 +47,6 @@ static int tcf_csum_init(struct net *n, struct nlattr *nla, struct nlattr *est, { struct nlattr *tb[TCA_CSUM_MAX + 1]; struct tc_csum *parm; - struct tcf_common *pc; struct tcf_csum *p; int ret = 0, err; @@ -63,38 +61,31 @@ static int tcf_csum_init(struct net *n, struct nlattr *nla, struct nlattr *est, return -EINVAL; parm = nla_data(tb[TCA_CSUM_PARMS]); - pc = tcf_hash_check(parm->index, a, bind); - if (!pc) { - pc = tcf_hash_create(parm->index, est, a, sizeof(*p), bind); - if (IS_ERR(pc)) - return PTR_ERR(pc); + if (!tcf_hash_check(parm->index, a, bind)) { + ret = tcf_hash_create(parm->index, est, a, sizeof(*p), bind); + if (ret) + return ret; ret = ACT_P_CREATED; } else { if (bind)/* dont override defaults */ return 0; - tcf_hash_release(pc, bind, a->ops->hinfo); + tcf_hash_release(a, bind); if (!ovr) return -EEXIST; } - p = to_tcf_csum(pc); + p = to_tcf_csum(a); spin_lock_bh(&p->tcf_lock); p->tcf_action = parm->action; p->update_flags = parm->update_flags; spin_unlock_bh(&p->tcf_lock); if (ret == ACT_P_CREATED) - tcf_hash_insert(pc, a->ops->hinfo); + tcf_hash_insert(a); return ret; } -static int tcf_csum_cleanup(struct tc_action *a, int bind) -{ - struct tcf_csum *p = a->priv; - return tcf_hash_release(&p->common, bind, &csum_hash_info); -} - /** * tcf_csum_skb_nextlayer - Get next layer pointer * @skb: sk_buff to use @@ -569,12 +560,10 @@ nla_put_failure: static struct tc_action_ops act_csum_ops = { .kind = "csum", - .hinfo = &csum_hash_info, .type = TCA_ACT_CSUM, .owner = THIS_MODULE, .act = tcf_csum, .dump = tcf_csum_dump, - .cleanup = tcf_csum_cleanup, .init = tcf_csum_init, }; @@ -583,11 +572,7 @@ MODULE_LICENSE("GPL"); static int __init csum_init_module(void) { - int err = tcf_hashinfo_init(&csum_hash_info, CSUM_TAB_MASK); - if (err) - return err; - - return tcf_register_action(&act_csum_ops); + return tcf_register_action(&act_csum_ops, CSUM_TAB_MASK); } static void __exit csum_cleanup_module(void) diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c index a0eed30d5811..d6bcbd9f7791 100644 --- a/net/sched/act_gact.c +++ b/net/sched/act_gact.c @@ -24,7 +24,6 @@ #include <net/tc_act/tc_gact.h> #define GACT_TAB_MASK 15 -static struct tcf_hashinfo gact_hash_info; #ifdef CONFIG_GACT_PROB static int gact_net_rand(struct tcf_gact *gact) @@ -57,7 +56,6 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla, struct nlattr *tb[TCA_GACT_MAX + 1]; struct tc_gact *parm; struct tcf_gact *gact; - struct tcf_common *pc; int ret = 0; int err; #ifdef CONFIG_GACT_PROB @@ -86,21 +84,20 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla, } #endif - pc = tcf_hash_check(parm->index, a, bind); - if (!pc) { - pc = tcf_hash_create(parm->index, est, a, sizeof(*gact), bind); - if (IS_ERR(pc)) - return PTR_ERR(pc); + if (!tcf_hash_check(parm->index, a, bind)) { + ret = tcf_hash_create(parm->index, est, a, sizeof(*gact), bind); + if (ret) + return ret; ret = ACT_P_CREATED; } else { if (bind)/* dont override defaults */ return 0; - tcf_hash_release(pc, bind, a->ops->hinfo); + tcf_hash_release(a, bind); if (!ovr) return -EEXIST; } - gact = to_gact(pc); + gact = to_gact(a); spin_lock_bh(&gact->tcf_lock); gact->tcf_action = parm->action; @@ -113,19 +110,10 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla, #endif spin_unlock_bh(&gact->tcf_lock); if (ret == ACT_P_CREATED) - tcf_hash_insert(pc, a->ops->hinfo); + tcf_hash_insert(a); return ret; } -static int tcf_gact_cleanup(struct tc_action *a, int bind) -{ - struct tcf_gact *gact = a->priv; - - if (gact) - return tcf_hash_release(&gact->common, bind, a->ops->hinfo); - return 0; -} - static int tcf_gact(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { @@ -191,12 +179,10 @@ nla_put_failure: static struct tc_action_ops act_gact_ops = { .kind = "gact", - .hinfo = &gact_hash_info, .type = TCA_ACT_GACT, .owner = THIS_MODULE, .act = tcf_gact, .dump = tcf_gact_dump, - .cleanup = tcf_gact_cleanup, .init = tcf_gact_init, }; @@ -206,21 +192,17 @@ MODULE_LICENSE("GPL"); static int __init gact_init_module(void) { - int err = tcf_hashinfo_init(&gact_hash_info, GACT_TAB_MASK); - if (err) - return err; #ifdef CONFIG_GACT_PROB pr_info("GACT probability on\n"); #else pr_info("GACT probability NOT on\n"); #endif - return tcf_register_action(&act_gact_ops); + return tcf_register_action(&act_gact_ops, GACT_TAB_MASK); } static void __exit gact_cleanup_module(void) { tcf_unregister_action(&act_gact_ops); - tcf_hashinfo_destroy(&gact_hash_info); } module_init(gact_init_module); diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index 0a6d62174027..8a64a0734aee 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -29,7 +29,6 @@ #define IPT_TAB_MASK 15 -static struct tcf_hashinfo ipt_hash_info; static int ipt_init_target(struct xt_entry_target *t, char *table, unsigned int hook) { @@ -69,22 +68,12 @@ static void ipt_destroy_target(struct xt_entry_target *t) module_put(par.target->me); } -static int tcf_ipt_release(struct tcf_ipt *ipt, int bind) +static void tcf_ipt_release(struct tc_action *a, int bind) { - int ret = 0; - if (ipt) { - if (bind) - ipt->tcf_bindcnt--; - ipt->tcf_refcnt--; - if (ipt->tcf_bindcnt <= 0 && ipt->tcf_refcnt <= 0) { - ipt_destroy_target(ipt->tcfi_t); - kfree(ipt->tcfi_tname); - kfree(ipt->tcfi_t); - tcf_hash_destroy(&ipt->common, &ipt_hash_info); - ret = ACT_P_DELETED; - } - } - return ret; + struct tcf_ipt *ipt = to_ipt(a); + ipt_destroy_target(ipt->tcfi_t); + kfree(ipt->tcfi_tname); + kfree(ipt->tcfi_t); } static const struct nla_policy ipt_policy[TCA_IPT_MAX + 1] = { @@ -99,7 +88,6 @@ static int tcf_ipt_init(struct net *net, struct nlattr *nla, struct nlattr *est, { struct nlattr *tb[TCA_IPT_MAX + 1]; struct tcf_ipt *ipt; - struct tcf_common *pc; struct xt_entry_target *td, *t; char *tname; int ret = 0, err; @@ -125,21 +113,20 @@ static int tcf_ipt_init(struct net *net, struct nlattr *nla, struct nlattr *est, if (tb[TCA_IPT_INDEX] != NULL) index = nla_get_u32(tb[TCA_IPT_INDEX]); - pc = tcf_hash_check(index, a, bind); - if (!pc) { - pc = tcf_hash_create(index, est, a, sizeof(*ipt), bind); - if (IS_ERR(pc)) - return PTR_ERR(pc); + if (!tcf_hash_check(index, a, bind) ) { + ret = tcf_hash_create(index, est, a, sizeof(*ipt), bind); + if (ret) + return ret; ret = ACT_P_CREATED; } else { if (bind)/* dont override defaults */ return 0; - tcf_ipt_release(to_ipt(pc), bind); + tcf_hash_release(a, bind); if (!ovr) return -EEXIST; } - ipt = to_ipt(pc); + ipt = to_ipt(a); hook = nla_get_u32(tb[TCA_IPT_HOOK]); @@ -170,7 +157,7 @@ static int tcf_ipt_init(struct net *net, struct nlattr *nla, struct nlattr *est, ipt->tcfi_hook = hook; spin_unlock_bh(&ipt->tcf_lock); if (ret == ACT_P_CREATED) - tcf_hash_insert(pc, a->ops->hinfo); + tcf_hash_insert(a); return ret; err3: @@ -178,21 +165,11 @@ err3: err2: kfree(tname); err1: - if (ret == ACT_P_CREATED) { - if (est) - gen_kill_estimator(&pc->tcfc_bstats, - &pc->tcfc_rate_est); - kfree_rcu(pc, tcfc_rcu); - } + if (ret == ACT_P_CREATED) + tcf_hash_cleanup(a, est); return err; } -static int tcf_ipt_cleanup(struct tc_action *a, int bind) -{ - struct tcf_ipt *ipt = a->priv; - return tcf_ipt_release(ipt, bind); -} - static int tcf_ipt(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { @@ -284,23 +261,21 @@ nla_put_failure: static struct tc_action_ops act_ipt_ops = { .kind = "ipt", - .hinfo = &ipt_hash_info, .type = TCA_ACT_IPT, .owner = THIS_MODULE, .act = tcf_ipt, .dump = tcf_ipt_dump, - .cleanup = tcf_ipt_cleanup, + .cleanup = tcf_ipt_release, .init = tcf_ipt_init, }; static struct tc_action_ops act_xt_ops = { .kind = "xt", - .hinfo = &ipt_hash_info, .type = TCA_ACT_XT, .owner = THIS_MODULE, .act = tcf_ipt, .dump = tcf_ipt_dump, - .cleanup = tcf_ipt_cleanup, + .cleanup = tcf_ipt_release, .init = tcf_ipt_init, }; @@ -311,20 +286,16 @@ MODULE_ALIAS("act_xt"); static int __init ipt_init_module(void) { - int ret1, ret2, err; - err = tcf_hashinfo_init(&ipt_hash_info, IPT_TAB_MASK); - if (err) - return err; + int ret1, ret2; - ret1 = tcf_register_action(&act_xt_ops); + ret1 = tcf_register_action(&act_xt_ops, IPT_TAB_MASK); if (ret1 < 0) printk("Failed to load xt action\n"); - ret2 = tcf_register_action(&act_ipt_ops); + ret2 = tcf_register_action(&act_ipt_ops, IPT_TAB_MASK); if (ret2 < 0) printk("Failed to load ipt action\n"); if (ret1 < 0 && ret2 < 0) { - tcf_hashinfo_destroy(&ipt_hash_info); return ret1; } else return 0; @@ -334,7 +305,6 @@ static void __exit ipt_cleanup_module(void) { tcf_unregister_action(&act_xt_ops); tcf_unregister_action(&act_ipt_ops); - tcf_hashinfo_destroy(&ipt_hash_info); } module_init(ipt_init_module); diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 0b2c6d39d396..4f912c0e225b 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -31,23 +31,13 @@ #define MIRRED_TAB_MASK 7 static LIST_HEAD(mirred_list); -static struct tcf_hashinfo mirred_hash_info; -static int tcf_mirred_release(struct tcf_mirred *m, int bind) +static void tcf_mirred_release(struct tc_action *a, int bind) { - if (m) { - if (bind) - m->tcf_bindcnt--; - m->tcf_refcnt--; - if (!m->tcf_bindcnt && m->tcf_refcnt <= 0) { - list_del(&m->tcfm_list); - if (m->tcfm_dev) - dev_put(m->tcfm_dev); - tcf_hash_destroy(&m->common, &mirred_hash_info); - return 1; - } - } - return 0; + struct tcf_mirred *m = to_mirred(a); + list_del(&m->tcfm_list); + if (m->tcfm_dev) + dev_put(m->tcfm_dev); } static const struct nla_policy mirred_policy[TCA_MIRRED_MAX + 1] = { @@ -61,7 +51,6 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, struct nlattr *tb[TCA_MIRRED_MAX + 1]; struct tc_mirred *parm; struct tcf_mirred *m; - struct tcf_common *pc; struct net_device *dev; int ret, ok_push = 0; @@ -101,21 +90,20 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, dev = NULL; } - pc = tcf_hash_check(parm->index, a, bind); - if (!pc) { + if (!tcf_hash_check(parm->index, a, bind)) { if (dev == NULL) return -EINVAL; - pc = tcf_hash_create(parm->index, est, a, sizeof(*m), bind); - if (IS_ERR(pc)) - return PTR_ERR(pc); + ret = tcf_hash_create(parm->index, est, a, sizeof(*m), bind); + if (ret) + return ret; ret = ACT_P_CREATED; } else { if (!ovr) { - tcf_mirred_release(to_mirred(pc), bind); + tcf_hash_release(a, bind); return -EEXIST; } } - m = to_mirred(pc); + m = to_mirred(a); spin_lock_bh(&m->tcf_lock); m->tcf_action = parm->action; @@ -131,21 +119,12 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, spin_unlock_bh(&m->tcf_lock); if (ret == ACT_P_CREATED) { list_add(&m->tcfm_list, &mirred_list); - tcf_hash_insert(pc, a->ops->hinfo); + tcf_hash_insert(a); } return ret; } -static int tcf_mirred_cleanup(struct tc_action *a, int bind) -{ - struct tcf_mirred *m = a->priv; - - if (m) - return tcf_mirred_release(m, bind); - return 0; -} - static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { @@ -254,12 +233,11 @@ static struct notifier_block mirred_device_notifier = { static struct tc_action_ops act_mirred_ops = { .kind = "mirred", - .hinfo = &mirred_hash_info, .type = TCA_ACT_MIRRED, .owner = THIS_MODULE, .act = tcf_mirred, .dump = tcf_mirred_dump, - .cleanup = tcf_mirred_cleanup, + .cleanup = tcf_mirred_release, .init = tcf_mirred_init, }; @@ -273,19 +251,13 @@ static int __init mirred_init_module(void) if (err) return err; - err = tcf_hashinfo_init(&mirred_hash_info, MIRRED_TAB_MASK); - if (err) { - unregister_netdevice_notifier(&mirred_device_notifier); - return err; - } pr_info("Mirror/redirect action on\n"); - return tcf_register_action(&act_mirred_ops); + return tcf_register_action(&act_mirred_ops, MIRRED_TAB_MASK); } static void __exit mirred_cleanup_module(void) { tcf_unregister_action(&act_mirred_ops); - tcf_hashinfo_destroy(&mirred_hash_info); unregister_netdevice_notifier(&mirred_device_notifier); } diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c index 81f0404bb335..270a030d5fd0 100644 --- a/net/sched/act_nat.c +++ b/net/sched/act_nat.c @@ -31,8 +31,6 @@ #define NAT_TAB_MASK 15 -static struct tcf_hashinfo nat_hash_info; - static const struct nla_policy nat_policy[TCA_NAT_MAX + 1] = { [TCA_NAT_PARMS] = { .len = sizeof(struct tc_nat) }, }; @@ -44,7 +42,6 @@ static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_nat *parm; int ret = 0, err; struct tcf_nat *p; - struct tcf_common *pc; if (nla == NULL) return -EINVAL; @@ -57,20 +54,19 @@ static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est, return -EINVAL; parm = nla_data(tb[TCA_NAT_PARMS]); - pc = tcf_hash_check(parm->index, a, bind); - if (!pc) { - pc = tcf_hash_create(parm->index, est, a, sizeof(*p), bind); - if (IS_ERR(pc)) - return PTR_ERR(pc); + if (!tcf_hash_check(parm->index, a, bind)) { + ret = tcf_hash_create(parm->index, est, a, sizeof(*p), bind); + if (ret) + return ret; ret = ACT_P_CREATED; } else { if (bind) return 0; - tcf_hash_release(pc, bind, a->ops->hinfo); + tcf_hash_release(a, bind); if (!ovr) return -EEXIST; } - p = to_tcf_nat(pc); + p = to_tcf_nat(a); spin_lock_bh(&p->tcf_lock); p->old_addr = parm->old_addr; @@ -82,18 +78,11 @@ static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est, spin_unlock_bh(&p->tcf_lock); if (ret == ACT_P_CREATED) - tcf_hash_insert(pc, a->ops->hinfo); + tcf_hash_insert(a); return ret; } -static int tcf_nat_cleanup(struct tc_action *a, int bind) -{ - struct tcf_nat *p = a->priv; - - return tcf_hash_release(&p->common, bind, &nat_hash_info); -} - static int tcf_nat(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { @@ -293,12 +282,10 @@ nla_put_failure: static struct tc_action_ops act_nat_ops = { .kind = "nat", - .hinfo = &nat_hash_info, .type = TCA_ACT_NAT, .owner = THIS_MODULE, .act = tcf_nat, .dump = tcf_nat_dump, - .cleanup = tcf_nat_cleanup, .init = tcf_nat_init, }; @@ -307,16 +294,12 @@ MODULE_LICENSE("GPL"); static int __init nat_init_module(void) { - int err = tcf_hashinfo_init(&nat_hash_info, NAT_TAB_MASK); - if (err) - return err; - return tcf_register_action(&act_nat_ops); + return tcf_register_action(&act_nat_ops, NAT_TAB_MASK); } static void __exit nat_cleanup_module(void) { tcf_unregister_action(&act_nat_ops); - tcf_hashinfo_destroy(&nat_hash_info); } module_init(nat_init_module); diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index be3f0f6875bb..5f9bcb2e080b 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -25,8 +25,6 @@ #define PEDIT_TAB_MASK 15 -static struct tcf_hashinfo pedit_hash_info; - static const struct nla_policy pedit_policy[TCA_PEDIT_MAX + 1] = { [TCA_PEDIT_PARMS] = { .len = sizeof(struct tc_pedit) }, }; @@ -39,7 +37,6 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, struct tc_pedit *parm; int ret = 0, err; struct tcf_pedit *p; - struct tcf_common *pc; struct tc_pedit_key *keys = NULL; int ksize; @@ -57,26 +54,22 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, if (nla_len(tb[TCA_PEDIT_PARMS]) < sizeof(*parm) + ksize) return -EINVAL; - pc = tcf_hash_check(parm->index, a, bind); - if (!pc) { + if (!tcf_hash_check(parm->index, a, bind)) { if (!parm->nkeys) return -EINVAL; - pc = tcf_hash_create(parm->index, est, a, sizeof(*p), bind); - if (IS_ERR(pc)) - return PTR_ERR(pc); - p = to_pedit(pc); + ret = tcf_hash_create(parm->index, est, a, sizeof(*p), bind); + if (ret) + return ret; + p = to_pedit(a); keys = kmalloc(ksize, GFP_KERNEL); if (keys == NULL) { - if (est) - gen_kill_estimator(&pc->tcfc_bstats, - &pc->tcfc_rate_est); - kfree_rcu(pc, tcfc_rcu); + tcf_hash_cleanup(a, est); return -ENOMEM; } ret = ACT_P_CREATED; } else { - p = to_pedit(pc); - tcf_hash_release(pc, bind, a->ops->hinfo); + p = to_pedit(a); + tcf_hash_release(a, bind); if (bind) return 0; if (!ovr) @@ -100,22 +93,15 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, memcpy(p->tcfp_keys, parm->keys, ksize); spin_unlock_bh(&p->tcf_lock); if (ret == ACT_P_CREATED) - tcf_hash_insert(pc, a->ops->hinfo); + tcf_hash_insert(a); return ret; } -static int tcf_pedit_cleanup(struct tc_action *a, int bind) +static void tcf_pedit_cleanup(struct tc_action *a, int bind) { struct tcf_pedit *p = a->priv; - - if (p) { - struct tc_pedit_key *keys = p->tcfp_keys; - if (tcf_hash_release(&p->common, bind, &pedit_hash_info)) { - kfree(keys); - return 1; - } - } - return 0; + struct tc_pedit_key *keys = p->tcfp_keys; + kfree(keys); } static int tcf_pedit(struct sk_buff *skb, const struct tc_action *a, @@ -230,7 +216,6 @@ nla_put_failure: static struct tc_action_ops act_pedit_ops = { .kind = "pedit", - .hinfo = &pedit_hash_info, .type = TCA_ACT_PEDIT, .owner = THIS_MODULE, .act = tcf_pedit, @@ -245,15 +230,11 @@ MODULE_LICENSE("GPL"); static int __init pedit_init_module(void) { - int err = tcf_hashinfo_init(&pedit_hash_info, PEDIT_TAB_MASK); - if (err) - return err; - return tcf_register_action(&act_pedit_ops); + return tcf_register_action(&act_pedit_ops, PEDIT_TAB_MASK); } static void __exit pedit_cleanup_module(void) { - tcf_hashinfo_destroy(&pedit_hash_info); tcf_unregister_action(&act_pedit_ops); } diff --git a/net/sched/act_police.c b/net/sched/act_police.c index 1778209a332f..0566e4606a4a 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -41,7 +41,6 @@ struct tcf_police { container_of(pc, struct tcf_police, common) #define POL_TAB_MASK 15 -static struct tcf_hashinfo police_hash_info; /* old policer structure from before tc actions */ struct tc_police_compat { @@ -234,7 +233,7 @@ override: police->tcfp_t_c = ktime_to_ns(ktime_get()); police->tcf_index = parm->index ? parm->index : - tcf_hash_new_index(a->ops->hinfo); + tcf_hash_new_index(hinfo); h = tcf_hash(police->tcf_index, POL_TAB_MASK); spin_lock_bh(&hinfo->lock); hlist_add_head(&police->tcf_head, &hinfo->htab[h]); @@ -253,14 +252,6 @@ failure: return err; } -static int tcf_act_police_cleanup(struct tc_action *a, int bind) -{ - struct tcf_police *p = a->priv; - if (p) - return tcf_hash_release(&p->common, bind, &police_hash_info); - return 0; -} - static int tcf_act_police(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { @@ -357,12 +348,10 @@ MODULE_LICENSE("GPL"); static struct tc_action_ops act_police_ops = { .kind = "police", - .hinfo = &police_hash_info, .type = TCA_ID_POLICE, .owner = THIS_MODULE, .act = tcf_act_police, .dump = tcf_act_police_dump, - .cleanup = tcf_act_police_cleanup, .init = tcf_act_police_locate, .walk = tcf_act_police_walker }; @@ -370,19 +359,12 @@ static struct tc_action_ops act_police_ops = { static int __init police_init_module(void) { - int err = tcf_hashinfo_init(&police_hash_info, POL_TAB_MASK); - if (err) - return err; - err = tcf_register_action(&act_police_ops); - if (err) - tcf_hashinfo_destroy(&police_hash_info); - return err; + return tcf_register_action(&act_police_ops, POL_TAB_MASK); } static void __exit police_cleanup_module(void) { - tcf_hashinfo_destroy(&police_hash_info); tcf_unregister_action(&act_police_ops); } diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c index 8ef2f1fcbfba..992c2317ce88 100644 --- a/net/sched/act_simple.c +++ b/net/sched/act_simple.c @@ -25,7 +25,6 @@ #include <net/tc_act/tc_defact.h> #define SIMP_TAB_MASK 7 -static struct tcf_hashinfo simp_hash_info; #define SIMP_MAX_DATA 32 static int tcf_simp(struct sk_buff *skb, const struct tc_action *a, @@ -47,20 +46,10 @@ static int tcf_simp(struct sk_buff *skb, const struct tc_action *a, return d->tcf_action; } -static int tcf_simp_release(struct tcf_defact *d, int bind) +static void tcf_simp_release(struct tc_action *a, int bind) { - int ret = 0; - if (d) { - if (bind) - d->tcf_bindcnt--; - d->tcf_refcnt--; - if (d->tcf_bindcnt <= 0 && d->tcf_refcnt <= 0) { - kfree(d->tcfd_defdata); - tcf_hash_destroy(&d->common, &simp_hash_info); - ret = 1; - } - } - return ret; + struct tcf_defact *d = to_defact(a); + kfree(d->tcfd_defdata); } static int alloc_defdata(struct tcf_defact *d, char *defdata) @@ -94,7 +83,6 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla, struct nlattr *tb[TCA_DEF_MAX + 1]; struct tc_defact *parm; struct tcf_defact *d; - struct tcf_common *pc; char *defdata; int ret = 0, err; @@ -114,29 +102,25 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla, parm = nla_data(tb[TCA_DEF_PARMS]); defdata = nla_data(tb[TCA_DEF_DATA]); - pc = tcf_hash_check(parm->index, a, bind); - if (!pc) { - pc = tcf_hash_create(parm->index, est, a, sizeof(*d), bind); - if (IS_ERR(pc)) - return PTR_ERR(pc); + if (!tcf_hash_check(parm->index, a, bind)) { + ret = tcf_hash_create(parm->index, est, a, sizeof(*d), bind); + if (ret) + return ret; - d = to_defact(pc); + d = to_defact(a); ret = alloc_defdata(d, defdata); if (ret < 0) { - if (est) - gen_kill_estimator(&pc->tcfc_bstats, - &pc->tcfc_rate_est); - kfree_rcu(pc, tcfc_rcu); + tcf_hash_cleanup(a, est); return ret; } d->tcf_action = parm->action; ret = ACT_P_CREATED; } else { - d = to_defact(pc); + d = to_defact(a); if (bind) return 0; - tcf_simp_release(d, bind); + tcf_hash_release(a, bind); if (!ovr) return -EEXIST; @@ -144,19 +128,10 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla, } if (ret == ACT_P_CREATED) - tcf_hash_insert(pc, a->ops->hinfo); + tcf_hash_insert(a); return ret; } -static int tcf_simp_cleanup(struct tc_action *a, int bind) -{ - struct tcf_defact *d = a->priv; - - if (d) - return tcf_simp_release(d, bind); - return 0; -} - static int tcf_simp_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) { @@ -187,12 +162,11 @@ nla_put_failure: static struct tc_action_ops act_simp_ops = { .kind = "simple", - .hinfo = &simp_hash_info, .type = TCA_ACT_SIMP, .owner = THIS_MODULE, .act = tcf_simp, .dump = tcf_simp_dump, - .cleanup = tcf_simp_cleanup, + .cleanup = tcf_simp_release, .init = tcf_simp_init, }; @@ -202,23 +176,15 @@ MODULE_LICENSE("GPL"); static int __init simp_init_module(void) { - int err, ret; - err = tcf_hashinfo_init(&simp_hash_info, SIMP_TAB_MASK); - if (err) - return err; - - ret = tcf_register_action(&act_simp_ops); + int ret; + ret = tcf_register_action(&act_simp_ops, SIMP_TAB_MASK); if (!ret) pr_info("Simple TC action Loaded\n"); - else - tcf_hashinfo_destroy(&simp_hash_info); - return ret; } static void __exit simp_cleanup_module(void) { - tcf_hashinfo_destroy(&simp_hash_info); tcf_unregister_action(&act_simp_ops); } diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index 98725080b5aa..fcfeeaf838be 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -28,7 +28,6 @@ #include <net/tc_act/tc_skbedit.h> #define SKBEDIT_TAB_MASK 15 -static struct tcf_hashinfo skbedit_hash_info; static int tcf_skbedit(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) @@ -65,7 +64,6 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, struct nlattr *tb[TCA_SKBEDIT_MAX + 1]; struct tc_skbedit *parm; struct tcf_skbedit *d; - struct tcf_common *pc; u32 flags = 0, *priority = NULL, *mark = NULL; u16 *queue_mapping = NULL; int ret = 0, err; @@ -100,19 +98,18 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, parm = nla_data(tb[TCA_SKBEDIT_PARMS]); - pc = tcf_hash_check(parm->index, a, bind); - if (!pc) { - pc = tcf_hash_create(parm->index, est, a, sizeof(*d), bind); - if (IS_ERR(pc)) - return PTR_ERR(pc); + if (!tcf_hash_check(parm->index, a, bind)) { + ret = tcf_hash_create(parm->index, est, a, sizeof(*d), bind); + if (ret) + return ret; - d = to_skbedit(pc); + d = to_skbedit(a); ret = ACT_P_CREATED; } else { - d = to_skbedit(pc); + d = to_skbedit(a); if (bind) return 0; - tcf_hash_release(pc, bind, a->ops->hinfo); + tcf_hash_release(a, bind); if (!ovr) return -EEXIST; } @@ -132,19 +129,10 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, spin_unlock_bh(&d->tcf_lock); if (ret == ACT_P_CREATED) - tcf_hash_insert(pc, a->ops->hinfo); + tcf_hash_insert(a); return ret; } -static int tcf_skbedit_cleanup(struct tc_action *a, int bind) -{ - struct tcf_skbedit *d = a->priv; - - if (d) - return tcf_hash_release(&d->common, bind, &skbedit_hash_info); - return 0; -} - static int tcf_skbedit_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) { @@ -186,12 +174,10 @@ nla_put_failure: static struct tc_action_ops act_skbedit_ops = { .kind = "skbedit", - .hinfo = &skbedit_hash_info, .type = TCA_ACT_SKBEDIT, .owner = THIS_MODULE, .act = tcf_skbedit, .dump = tcf_skbedit_dump, - .cleanup = tcf_skbedit_cleanup, .init = tcf_skbedit_init, }; @@ -201,15 +187,11 @@ MODULE_LICENSE("GPL"); static int __init skbedit_init_module(void) { - int err = tcf_hashinfo_init(&skbedit_hash_info, SKBEDIT_TAB_MASK); - if (err) - return err; - return tcf_register_action(&act_skbedit_ops); + return tcf_register_action(&act_skbedit_ops, SKBEDIT_TAB_MASK); } static void __exit skbedit_cleanup_module(void) { - tcf_hashinfo_destroy(&skbedit_hash_info); tcf_unregister_action(&act_skbedit_ops); } diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 1313145e3b86..0a99d7ced71e 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1303,6 +1303,7 @@ static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid, struct gnet_dump d; struct qdisc_size_table *stab; + cond_resched(); nlh = nlmsg_put(skb, portid, seq, event, sizeof(*tcm), flags); if (!nlh) goto out_nlmsg_trim; @@ -1434,9 +1435,9 @@ static int tc_dump_qdisc(struct sk_buff *skb, struct netlink_callback *cb) s_idx = cb->args[0]; s_q_idx = q_idx = cb->args[1]; - rcu_read_lock(); idx = 0; - for_each_netdev_rcu(net, dev) { + ASSERT_RTNL(); + for_each_netdev(net, dev) { struct netdev_queue *dev_queue; if (idx < s_idx) @@ -1459,8 +1460,6 @@ cont: } done: - rcu_read_unlock(); - cb->args[0] = idx; cb->args[1] = q_idx; @@ -1617,6 +1616,7 @@ static int tc_fill_tclass(struct sk_buff *skb, struct Qdisc *q, struct gnet_dump d; const struct Qdisc_class_ops *cl_ops = q->ops->cl_ops; + cond_resched(); nlh = nlmsg_put(skb, portid, seq, event, sizeof(*tcm), flags); if (!nlh) goto out_nlmsg_trim; diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index 08ef7a42c0e4..21e251766eb1 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -601,6 +601,7 @@ static int fq_resize(struct Qdisc *sch, u32 log) { struct fq_sched_data *q = qdisc_priv(sch); struct rb_root *array; + void *old_fq_root; u32 idx; if (q->fq_root && log == q->fq_trees_log) @@ -615,13 +616,19 @@ static int fq_resize(struct Qdisc *sch, u32 log) for (idx = 0; idx < (1U << log); idx++) array[idx] = RB_ROOT; - if (q->fq_root) { - fq_rehash(q, q->fq_root, q->fq_trees_log, array, log); - fq_free(q->fq_root); - } + sch_tree_lock(sch); + + old_fq_root = q->fq_root; + if (old_fq_root) + fq_rehash(q, old_fq_root, q->fq_trees_log, array, log); + q->fq_root = array; q->fq_trees_log = log; + sch_tree_unlock(sch); + + fq_free(old_fq_root); + return 0; } @@ -697,9 +704,11 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt) q->flow_refill_delay = usecs_to_jiffies(usecs_delay); } - if (!err) + if (!err) { + sch_tree_unlock(sch); err = fq_resize(sch, fq_log); - + sch_tree_lock(sch); + } while (sch->q.qlen > sch->limit) { struct sk_buff *skb = fq_dequeue(sch); diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 722e137df244..9f949abcacef 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -1062,12 +1062,13 @@ static int htb_init(struct Qdisc *sch, struct nlattr *opt) static int htb_dump(struct Qdisc *sch, struct sk_buff *skb) { - spinlock_t *root_lock = qdisc_root_sleeping_lock(sch); struct htb_sched *q = qdisc_priv(sch); struct nlattr *nest; struct tc_htb_glob gopt; - spin_lock_bh(root_lock); + /* Its safe to not acquire qdisc lock. As we hold RTNL, + * no change can happen on the qdisc parameters. + */ gopt.direct_pkts = q->direct_pkts; gopt.version = HTB_VER; @@ -1081,13 +1082,10 @@ static int htb_dump(struct Qdisc *sch, struct sk_buff *skb) if (nla_put(skb, TCA_HTB_INIT, sizeof(gopt), &gopt) || nla_put_u32(skb, TCA_HTB_DIRECT_QLEN, q->direct_qlen)) goto nla_put_failure; - nla_nest_end(skb, nest); - spin_unlock_bh(root_lock); - return skb->len; + return nla_nest_end(skb, nest); nla_put_failure: - spin_unlock_bh(root_lock); nla_nest_cancel(skb, nest); return -1; } @@ -1096,11 +1094,12 @@ static int htb_dump_class(struct Qdisc *sch, unsigned long arg, struct sk_buff *skb, struct tcmsg *tcm) { struct htb_class *cl = (struct htb_class *)arg; - spinlock_t *root_lock = qdisc_root_sleeping_lock(sch); struct nlattr *nest; struct tc_htb_opt opt; - spin_lock_bh(root_lock); + /* Its safe to not acquire qdisc lock. As we hold RTNL, + * no change can happen on the class parameters. + */ tcm->tcm_parent = cl->parent ? cl->parent->common.classid : TC_H_ROOT; tcm->tcm_handle = cl->common.classid; if (!cl->level && cl->un.leaf.q) @@ -1128,12 +1127,9 @@ static int htb_dump_class(struct Qdisc *sch, unsigned long arg, nla_put_u64(skb, TCA_HTB_CEIL64, cl->ceil.rate_bytes_ps)) goto nla_put_failure; - nla_nest_end(skb, nest); - spin_unlock_bh(root_lock); - return skb->len; + return nla_nest_end(skb, nest); nla_put_failure: - spin_unlock_bh(root_lock); nla_nest_cancel(skb, nest); return -1; } diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index de1059af6da1..f1669a00f571 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -117,6 +117,11 @@ struct netem_sched_data { LOST_IN_BURST_PERIOD, } _4_state_model; + enum { + GOOD_STATE = 1, + BAD_STATE, + } GE_state_model; + /* Correlated Loss Generation models */ struct clgstate { /* state of the Markov chain */ @@ -272,15 +277,15 @@ static bool loss_gilb_ell(struct netem_sched_data *q) struct clgstate *clg = &q->clg; switch (clg->state) { - case 1: + case GOOD_STATE: if (prandom_u32() < clg->a1) - clg->state = 2; + clg->state = BAD_STATE; if (prandom_u32() < clg->a4) return true; break; - case 2: + case BAD_STATE: if (prandom_u32() < clg->a2) - clg->state = 1; + clg->state = GOOD_STATE; if (prandom_u32() > clg->a3) return true; } @@ -689,9 +694,8 @@ static int get_dist_table(struct Qdisc *sch, const struct nlattr *attr) return 0; } -static void get_correlation(struct Qdisc *sch, const struct nlattr *attr) +static void get_correlation(struct netem_sched_data *q, const struct nlattr *attr) { - struct netem_sched_data *q = qdisc_priv(sch); const struct tc_netem_corr *c = nla_data(attr); init_crandom(&q->delay_cor, c->delay_corr); @@ -699,27 +703,24 @@ static void get_correlation(struct Qdisc *sch, const struct nlattr *attr) init_crandom(&q->dup_cor, c->dup_corr); } -static void get_reorder(struct Qdisc *sch, const struct nlattr *attr) +static void get_reorder(struct netem_sched_data *q, const struct nlattr *attr) { - struct netem_sched_data *q = qdisc_priv(sch); const struct tc_netem_reorder *r = nla_data(attr); q->reorder = r->probability; init_crandom(&q->reorder_cor, r->correlation); } -static void get_corrupt(struct Qdisc *sch, const struct nlattr *attr) +static void get_corrupt(struct netem_sched_data *q, const struct nlattr *attr) { - struct netem_sched_data *q = qdisc_priv(sch); const struct tc_netem_corrupt *r = nla_data(attr); q->corrupt = r->probability; init_crandom(&q->corrupt_cor, r->correlation); } -static void get_rate(struct Qdisc *sch, const struct nlattr *attr) +static void get_rate(struct netem_sched_data *q, const struct nlattr *attr) { - struct netem_sched_data *q = qdisc_priv(sch); const struct tc_netem_rate *r = nla_data(attr); q->rate = r->rate; @@ -732,9 +733,8 @@ static void get_rate(struct Qdisc *sch, const struct nlattr *attr) q->cell_size_reciprocal = (struct reciprocal_value) { 0 }; } -static int get_loss_clg(struct Qdisc *sch, const struct nlattr *attr) +static int get_loss_clg(struct netem_sched_data *q, const struct nlattr *attr) { - struct netem_sched_data *q = qdisc_priv(sch); const struct nlattr *la; int rem; @@ -752,7 +752,7 @@ static int get_loss_clg(struct Qdisc *sch, const struct nlattr *attr) q->loss_model = CLG_4_STATES; - q->clg.state = 1; + q->clg.state = TX_IN_GAP_PERIOD; q->clg.a1 = gi->p13; q->clg.a2 = gi->p31; q->clg.a3 = gi->p32; @@ -770,7 +770,7 @@ static int get_loss_clg(struct Qdisc *sch, const struct nlattr *attr) } q->loss_model = CLG_GILB_ELL; - q->clg.state = 1; + q->clg.state = GOOD_STATE; q->clg.a1 = ge->p; q->clg.a2 = ge->r; q->clg.a3 = ge->h; @@ -821,6 +821,8 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt) struct netem_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_NETEM_MAX + 1]; struct tc_netem_qopt *qopt; + struct clgstate old_clg; + int old_loss_model = CLG_RANDOM; int ret; if (opt == NULL) @@ -831,6 +833,33 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt) if (ret < 0) return ret; + /* backup q->clg and q->loss_model */ + old_clg = q->clg; + old_loss_model = q->loss_model; + + if (tb[TCA_NETEM_LOSS]) { + ret = get_loss_clg(q, tb[TCA_NETEM_LOSS]); + if (ret) { + q->loss_model = old_loss_model; + return ret; + } + } else { + q->loss_model = CLG_RANDOM; + } + + if (tb[TCA_NETEM_DELAY_DIST]) { + ret = get_dist_table(sch, tb[TCA_NETEM_DELAY_DIST]); + if (ret) { + /* recover clg and loss_model, in case of + * q->clg and q->loss_model were modified + * in get_loss_clg() + */ + q->clg = old_clg; + q->loss_model = old_loss_model; + return ret; + } + } + sch->limit = qopt->limit; q->latency = qopt->latency; @@ -848,22 +877,16 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt) q->reorder = ~0; if (tb[TCA_NETEM_CORR]) - get_correlation(sch, tb[TCA_NETEM_CORR]); - - if (tb[TCA_NETEM_DELAY_DIST]) { - ret = get_dist_table(sch, tb[TCA_NETEM_DELAY_DIST]); - if (ret) - return ret; - } + get_correlation(q, tb[TCA_NETEM_CORR]); if (tb[TCA_NETEM_REORDER]) - get_reorder(sch, tb[TCA_NETEM_REORDER]); + get_reorder(q, tb[TCA_NETEM_REORDER]); if (tb[TCA_NETEM_CORRUPT]) - get_corrupt(sch, tb[TCA_NETEM_CORRUPT]); + get_corrupt(q, tb[TCA_NETEM_CORRUPT]); if (tb[TCA_NETEM_RATE]) - get_rate(sch, tb[TCA_NETEM_RATE]); + get_rate(q, tb[TCA_NETEM_RATE]); if (tb[TCA_NETEM_RATE64]) q->rate = max_t(u64, q->rate, @@ -872,10 +895,6 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt) if (tb[TCA_NETEM_ECN]) q->ecn = nla_get_u32(tb[TCA_NETEM_ECN]); - q->loss_model = CLG_RANDOM; - if (tb[TCA_NETEM_LOSS]) - ret = get_loss_clg(sch, tb[TCA_NETEM_LOSS]); - return ret; } diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c index a255d0200a59..fefeeb73f15f 100644 --- a/net/sched/sch_pie.c +++ b/net/sched/sch_pie.c @@ -15,6 +15,11 @@ * * ECN support is added by Naeem Khademi <naeemk@ifi.uio.no> * University of Oslo, Norway. + * + * References: + * IETF draft submission: http://tools.ietf.org/html/draft-pan-aqm-pie-00 + * IEEE Conference on High Performance Switching and Routing 2013 : + * "PIE: A * Lightweight Control Scheme to Address the Bufferbloat Problem" */ #include <linux/module.h> @@ -36,7 +41,7 @@ struct pie_params { psched_time_t target; /* user specified target delay in pschedtime */ u32 tupdate; /* timer frequency (in jiffies) */ u32 limit; /* number of packets that can be enqueued */ - u32 alpha; /* alpha and beta are between -4 and 4 */ + u32 alpha; /* alpha and beta are between 0 and 32 */ u32 beta; /* and are used for shift relative to 1 */ bool ecn; /* true if ecn is enabled */ bool bytemode; /* to scale drop early prob based on pkt size */ @@ -326,10 +331,16 @@ static void calculate_probability(struct Qdisc *sch) if (qdelay == 0 && qlen != 0) update_prob = false; - /* Add ranges for alpha and beta, more aggressive for high dropping - * mode and gentle steps for light dropping mode - * In light dropping mode, take gentle steps; in medium dropping mode, - * take medium steps; in high dropping mode, take big steps. + /* In the algorithm, alpha and beta are between 0 and 2 with typical + * value for alpha as 0.125. In this implementation, we use values 0-32 + * passed from user space to represent this. Also, alpha and beta have + * unit of HZ and need to be scaled before they can used to update + * probability. alpha/beta are updated locally below by 1) scaling them + * appropriately 2) scaling down by 16 to come to 0-2 range. + * Please see paper for details. + * + * We scale alpha and beta differently depending on whether we are in + * light, medium or high dropping mode. */ if (q->vars.prob < MAX_PROB / 100) { alpha = diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c index 1cb413fead89..87a02bfa707b 100644 --- a/net/sched/sch_tbf.c +++ b/net/sched/sch_tbf.c @@ -101,12 +101,11 @@ struct tbf_sched_data { /* Parameters */ u32 limit; /* Maximal length of backlog: bytes */ + u32 max_size; s64 buffer; /* Token bucket depth/rate: MUST BE >= MTU/B */ s64 mtu; - u32 max_size; struct psched_ratecfg rate; struct psched_ratecfg peak; - bool peak_present; /* Variables */ s64 tokens; /* Current number of B tokens */ @@ -222,6 +221,11 @@ static unsigned int tbf_drop(struct Qdisc *sch) return len; } +static bool tbf_peak_present(const struct tbf_sched_data *q) +{ + return q->peak.rate_bytes_ps; +} + static struct sk_buff *tbf_dequeue(struct Qdisc *sch) { struct tbf_sched_data *q = qdisc_priv(sch); @@ -238,7 +242,7 @@ static struct sk_buff *tbf_dequeue(struct Qdisc *sch) now = ktime_to_ns(ktime_get()); toks = min_t(s64, now - q->t_c, q->buffer); - if (q->peak_present) { + if (tbf_peak_present(q)) { ptoks = toks + q->ptokens; if (ptoks > q->mtu) ptoks = q->mtu; @@ -334,18 +338,6 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt) qdisc_put_rtab(qdisc_get_rtab(&qopt->peakrate, tb[TCA_TBF_PTAB])); - if (q->qdisc != &noop_qdisc) { - err = fifo_set_limit(q->qdisc, qopt->limit); - if (err) - goto done; - } else if (qopt->limit > 0) { - child = fifo_create_dflt(sch, &bfifo_qdisc_ops, qopt->limit); - if (IS_ERR(child)) { - err = PTR_ERR(child); - goto done; - } - } - buffer = min_t(u64, PSCHED_TICKS2NS(qopt->buffer), ~0U); mtu = min_t(u64, PSCHED_TICKS2NS(qopt->mtu), ~0U); @@ -378,6 +370,8 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt) } else { max_size = min_t(u64, max_size, psched_ns_t2l(&peak, mtu)); } + } else { + memset(&peak, 0, sizeof(peak)); } if (max_size < psched_mtu(qdisc_dev(sch))) @@ -390,6 +384,18 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt) goto done; } + if (q->qdisc != &noop_qdisc) { + err = fifo_set_limit(q->qdisc, qopt->limit); + if (err) + goto done; + } else if (qopt->limit > 0) { + child = fifo_create_dflt(sch, &bfifo_qdisc_ops, qopt->limit); + if (IS_ERR(child)) { + err = PTR_ERR(child); + goto done; + } + } + sch_tree_lock(sch); if (child) { qdisc_tree_decrease_qlen(q->qdisc, q->qdisc->q.qlen); @@ -410,12 +416,7 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt) q->ptokens = q->mtu; memcpy(&q->rate, &rate, sizeof(struct psched_ratecfg)); - if (qopt->peakrate.rate) { - memcpy(&q->peak, &peak, sizeof(struct psched_ratecfg)); - q->peak_present = true; - } else { - q->peak_present = false; - } + memcpy(&q->peak, &peak, sizeof(struct psched_ratecfg)); sch_tree_unlock(sch); err = 0; @@ -458,7 +459,7 @@ static int tbf_dump(struct Qdisc *sch, struct sk_buff *skb) opt.limit = q->limit; psched_ratecfg_getrate(&opt.rate, &q->rate); - if (q->peak_present) + if (tbf_peak_present(q)) psched_ratecfg_getrate(&opt.peakrate, &q->peak); else memset(&opt.peakrate, 0, sizeof(opt.peakrate)); @@ -469,7 +470,7 @@ static int tbf_dump(struct Qdisc *sch, struct sk_buff *skb) if (q->rate.rate_bytes_ps >= (1ULL << 32) && nla_put_u64(skb, TCA_TBF_RATE64, q->rate.rate_bytes_ps)) goto nla_put_failure; - if (q->peak_present && + if (tbf_peak_present(q) && q->peak.rate_bytes_ps >= (1ULL << 32) && nla_put_u64(skb, TCA_TBF_PRATE64, q->peak.rate_bytes_ps)) goto nla_put_failure; diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 5ae609200674..4f6d6f9d1274 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -1239,78 +1239,106 @@ void sctp_assoc_update(struct sctp_association *asoc, } /* Update the retran path for sending a retransmitted packet. - * Round-robin through the active transports, else round-robin - * through the inactive transports as this is the next best thing - * we can try. + * See also RFC4960, 6.4. Multi-Homed SCTP Endpoints: + * + * When there is outbound data to send and the primary path + * becomes inactive (e.g., due to failures), or where the + * SCTP user explicitly requests to send data to an + * inactive destination transport address, before reporting + * an error to its ULP, the SCTP endpoint should try to send + * the data to an alternate active destination transport + * address if one exists. + * + * When retransmitting data that timed out, if the endpoint + * is multihomed, it should consider each source-destination + * address pair in its retransmission selection policy. + * When retransmitting timed-out data, the endpoint should + * attempt to pick the most divergent source-destination + * pair from the original source-destination pair to which + * the packet was transmitted. + * + * Note: Rules for picking the most divergent source-destination + * pair are an implementation decision and are not specified + * within this document. + * + * Our basic strategy is to round-robin transports in priorities + * according to sctp_state_prio_map[] e.g., if no such + * transport with state SCTP_ACTIVE exists, round-robin through + * SCTP_UNKNOWN, etc. You get the picture. */ -void sctp_assoc_update_retran_path(struct sctp_association *asoc) +static const u8 sctp_trans_state_to_prio_map[] = { + [SCTP_ACTIVE] = 3, /* best case */ + [SCTP_UNKNOWN] = 2, + [SCTP_PF] = 1, + [SCTP_INACTIVE] = 0, /* worst case */ +}; + +static u8 sctp_trans_score(const struct sctp_transport *trans) { - struct sctp_transport *t, *next; - struct list_head *head = &asoc->peer.transport_addr_list; - struct list_head *pos; + return sctp_trans_state_to_prio_map[trans->state]; +} - if (asoc->peer.transport_count == 1) - return; +static struct sctp_transport *sctp_trans_elect_best(struct sctp_transport *curr, + struct sctp_transport *best) +{ + if (best == NULL) + return curr; - /* Find the next transport in a round-robin fashion. */ - t = asoc->peer.retran_path; - pos = &t->transports; - next = NULL; + return sctp_trans_score(curr) > sctp_trans_score(best) ? curr : best; +} - while (1) { - /* Skip the head. */ - if (pos->next == head) - pos = head->next; - else - pos = pos->next; +void sctp_assoc_update_retran_path(struct sctp_association *asoc) +{ + struct sctp_transport *trans = asoc->peer.retran_path; + struct sctp_transport *trans_next = NULL; - t = list_entry(pos, struct sctp_transport, transports); + /* We're done as we only have the one and only path. */ + if (asoc->peer.transport_count == 1) + return; + /* If active_path and retran_path are the same and active, + * then this is the only active path. Use it. + */ + if (asoc->peer.active_path == asoc->peer.retran_path && + asoc->peer.active_path->state == SCTP_ACTIVE) + return; - /* We have exhausted the list, but didn't find any - * other active transports. If so, use the next - * transport. - */ - if (t == asoc->peer.retran_path) { - t = next; + /* Iterate from retran_path's successor back to retran_path. */ + for (trans = list_next_entry(trans, transports); 1; + trans = list_next_entry(trans, transports)) { + /* Manually skip the head element. */ + if (&trans->transports == &asoc->peer.transport_addr_list) + continue; + if (trans->state == SCTP_UNCONFIRMED) + continue; + trans_next = sctp_trans_elect_best(trans, trans_next); + /* Active is good enough for immediate return. */ + if (trans_next->state == SCTP_ACTIVE) break; - } - - /* Try to find an active transport. */ - - if ((t->state == SCTP_ACTIVE) || - (t->state == SCTP_UNKNOWN)) { + /* We've reached the end, time to update path. */ + if (trans == asoc->peer.retran_path) break; - } else { - /* Keep track of the next transport in case - * we don't find any active transport. - */ - if (t->state != SCTP_UNCONFIRMED && !next) - next = t; - } } - if (t) - asoc->peer.retran_path = t; - else - t = asoc->peer.retran_path; + asoc->peer.retran_path = trans_next; - pr_debug("%s: association:%p addr:%pISpc\n", __func__, asoc, - &t->ipaddr.sa); + pr_debug("%s: association:%p updated new path to addr:%pISpc\n", + __func__, asoc, &asoc->peer.retran_path->ipaddr.sa); } -/* Choose the transport for sending retransmit packet. */ -struct sctp_transport *sctp_assoc_choose_alter_transport( - struct sctp_association *asoc, struct sctp_transport *last_sent_to) +struct sctp_transport * +sctp_assoc_choose_alter_transport(struct sctp_association *asoc, + struct sctp_transport *last_sent_to) { /* If this is the first time packet is sent, use the active path, * else use the retran path. If the last packet was sent over the * retran path, update the retran path and use it. */ - if (!last_sent_to) + if (last_sent_to == NULL) { return asoc->peer.active_path; - else { + } else { if (last_sent_to == asoc->peer.retran_path) sctp_assoc_update_retran_path(asoc); + return asoc->peer.retran_path; } } @@ -1367,44 +1395,35 @@ static inline bool sctp_peer_needs_update(struct sctp_association *asoc) return false; } -/* Increase asoc's rwnd by len and send any window update SACK if needed. */ -void sctp_assoc_rwnd_increase(struct sctp_association *asoc, unsigned int len) +/* Update asoc's rwnd for the approximated state in the buffer, + * and check whether SACK needs to be sent. + */ +void sctp_assoc_rwnd_update(struct sctp_association *asoc, bool update_peer) { + int rx_count; struct sctp_chunk *sack; struct timer_list *timer; - if (asoc->rwnd_over) { - if (asoc->rwnd_over >= len) { - asoc->rwnd_over -= len; - } else { - asoc->rwnd += (len - asoc->rwnd_over); - asoc->rwnd_over = 0; - } - } else { - asoc->rwnd += len; - } + if (asoc->ep->rcvbuf_policy) + rx_count = atomic_read(&asoc->rmem_alloc); + else + rx_count = atomic_read(&asoc->base.sk->sk_rmem_alloc); - /* If we had window pressure, start recovering it - * once our rwnd had reached the accumulated pressure - * threshold. The idea is to recover slowly, but up - * to the initial advertised window. - */ - if (asoc->rwnd_press && asoc->rwnd >= asoc->rwnd_press) { - int change = min(asoc->pathmtu, asoc->rwnd_press); - asoc->rwnd += change; - asoc->rwnd_press -= change; - } + if ((asoc->base.sk->sk_rcvbuf - rx_count) > 0) + asoc->rwnd = (asoc->base.sk->sk_rcvbuf - rx_count) >> 1; + else + asoc->rwnd = 0; - pr_debug("%s: asoc:%p rwnd increased by %d to (%u, %u) - %u\n", - __func__, asoc, len, asoc->rwnd, asoc->rwnd_over, - asoc->a_rwnd); + pr_debug("%s: asoc:%p rwnd=%u, rx_count=%d, sk_rcvbuf=%d\n", + __func__, asoc, asoc->rwnd, rx_count, + asoc->base.sk->sk_rcvbuf); /* Send a window update SACK if the rwnd has increased by at least the * minimum of the association's PMTU and half of the receive buffer. * The algorithm used is similar to the one described in * Section 4.2.3.3 of RFC 1122. */ - if (sctp_peer_needs_update(asoc)) { + if (update_peer && sctp_peer_needs_update(asoc)) { asoc->a_rwnd = asoc->rwnd; pr_debug("%s: sending window update SACK- asoc:%p rwnd:%u " @@ -1426,45 +1445,6 @@ void sctp_assoc_rwnd_increase(struct sctp_association *asoc, unsigned int len) } } -/* Decrease asoc's rwnd by len. */ -void sctp_assoc_rwnd_decrease(struct sctp_association *asoc, unsigned int len) -{ - int rx_count; - int over = 0; - - if (unlikely(!asoc->rwnd || asoc->rwnd_over)) - pr_debug("%s: association:%p has asoc->rwnd:%u, " - "asoc->rwnd_over:%u!\n", __func__, asoc, - asoc->rwnd, asoc->rwnd_over); - - if (asoc->ep->rcvbuf_policy) - rx_count = atomic_read(&asoc->rmem_alloc); - else - rx_count = atomic_read(&asoc->base.sk->sk_rmem_alloc); - - /* If we've reached or overflowed our receive buffer, announce - * a 0 rwnd if rwnd would still be positive. Store the - * the potential pressure overflow so that the window can be restored - * back to original value. - */ - if (rx_count >= asoc->base.sk->sk_rcvbuf) - over = 1; - - if (asoc->rwnd >= len) { - asoc->rwnd -= len; - if (over) { - asoc->rwnd_press += asoc->rwnd; - asoc->rwnd = 0; - } - } else { - asoc->rwnd_over = len - asoc->rwnd; - asoc->rwnd = 0; - } - - pr_debug("%s: asoc:%p rwnd decreased by %d to (%u, %u, %u)\n", - __func__, asoc, len, asoc->rwnd, asoc->rwnd_over, - asoc->rwnd_press); -} /* Build the bind address list for the association based on info from the * local endpoint and the remote peer. diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 0f6259a6a932..2b1738ef9394 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -662,6 +662,8 @@ static struct sock *sctp_v6_create_accept_sk(struct sock *sk, */ sctp_v6_to_sk_daddr(&asoc->peer.primary_addr, newsk); + newsk->sk_v6_rcv_saddr = sk->sk_v6_rcv_saddr; + sk_refcnt_debug_inc(newsk); if (newsk->sk_prot->init(newsk)) { diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index bd859154000e..5d6883ff00c3 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -495,11 +495,12 @@ static void sctp_do_8_2_transport_strike(sctp_cmd_seq_t *commands, } /* If the transport error count is greater than the pf_retrans - * threshold, and less than pathmaxrtx, then mark this transport - * as Partially Failed, ee SCTP Quick Failover Draft, secon 5.1, - * point 1 + * threshold, and less than pathmaxrtx, and if the current state + * is not SCTP_UNCONFIRMED, then mark this transport as Partially + * Failed, see SCTP Quick Failover Draft, section 5.1 */ if ((transport->state != SCTP_PF) && + (transport->state != SCTP_UNCONFIRMED) && (asoc->pf_retrans < transport->pathmaxrxt) && (transport->error_count > asoc->pf_retrans)) { diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 483dcd71b3c5..ae65b6b5973a 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -758,6 +758,13 @@ sctp_disposition_t sctp_sf_do_5_1D_ce(struct net *net, struct sctp_chunk auth; sctp_ierror_t ret; + /* Make sure that we and the peer are AUTH capable */ + if (!net->sctp.auth_enable || !new_asoc->peer.auth_capable) { + kfree_skb(chunk->auth_chunk); + sctp_association_free(new_asoc); + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + } + /* set-up our fake chunk so that we can process it */ auth.skb = chunk->auth_chunk; auth.asoc = chunk->asoc; @@ -6176,7 +6183,7 @@ static int sctp_eat_data(const struct sctp_association *asoc, * PMTU. In cases, such as loopback, this might be a rather * large spill over. */ - if ((!chunk->data_accepted) && (!asoc->rwnd || asoc->rwnd_over || + if ((!chunk->data_accepted) && (!asoc->rwnd || (datalen > asoc->rwnd + asoc->frag_point))) { /* If this is the next TSN, consider reneging to make diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 9e91d6e5df63..981aaf8b6ace 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -64,6 +64,7 @@ #include <linux/crypto.h> #include <linux/slab.h> #include <linux/file.h> +#include <linux/compat.h> #include <net/ip.h> #include <net/icmp.h> @@ -1368,11 +1369,19 @@ static int sctp_setsockopt_connectx(struct sock *sk, /* * New (hopefully final) interface for the API. * We use the sctp_getaddrs_old structure so that use-space library - * can avoid any unnecessary allocations. The only defferent part + * can avoid any unnecessary allocations. The only different part * is that we store the actual length of the address buffer into the - * addrs_num structure member. That way we can re-use the existing + * addrs_num structure member. That way we can re-use the existing * code. */ +#ifdef CONFIG_COMPAT +struct compat_sctp_getaddrs_old { + sctp_assoc_t assoc_id; + s32 addr_num; + compat_uptr_t addrs; /* struct sockaddr * */ +}; +#endif + static int sctp_getsockopt_connectx3(struct sock *sk, int len, char __user *optval, int __user *optlen) @@ -1381,16 +1390,30 @@ static int sctp_getsockopt_connectx3(struct sock *sk, int len, sctp_assoc_t assoc_id = 0; int err = 0; - if (len < sizeof(param)) - return -EINVAL; +#ifdef CONFIG_COMPAT + if (is_compat_task()) { + struct compat_sctp_getaddrs_old param32; - if (copy_from_user(¶m, optval, sizeof(param))) - return -EFAULT; + if (len < sizeof(param32)) + return -EINVAL; + if (copy_from_user(¶m32, optval, sizeof(param32))) + return -EFAULT; - err = __sctp_setsockopt_connectx(sk, - (struct sockaddr __user *)param.addrs, - param.addr_num, &assoc_id); + param.assoc_id = param32.assoc_id; + param.addr_num = param32.addr_num; + param.addrs = compat_ptr(param32.addrs); + } else +#endif + { + if (len < sizeof(param)) + return -EINVAL; + if (copy_from_user(¶m, optval, sizeof(param))) + return -EFAULT; + } + err = __sctp_setsockopt_connectx(sk, (struct sockaddr __user *) + param.addrs, param.addr_num, + &assoc_id); if (err == 0 || err == -EINPROGRESS) { if (copy_to_user(optval, &assoc_id, sizeof(assoc_id))) return -EFAULT; @@ -2092,12 +2115,6 @@ static int sctp_recvmsg(struct kiocb *iocb, struct sock *sk, sctp_skb_pull(skb, copied); skb_queue_head(&sk->sk_receive_queue, skb); - /* When only partial message is copied to the user, increase - * rwnd by that amount. If all the data in the skb is read, - * rwnd is updated when the event is freed. - */ - if (!sctp_ulpevent_is_notification(event)) - sctp_assoc_rwnd_increase(event->asoc, copied); goto out; } else if ((event->msg_flags & MSG_NOTIFICATION) || (event->msg_flags & MSG_EOR)) diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index 7135e617ab0f..35c8923b5554 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -151,6 +151,7 @@ static struct ctl_table sctp_net_table[] = { }, { .procname = "cookie_hmac_alg", + .data = &init_net.sctp.sctp_hmac_alg, .maxlen = 8, .mode = 0644, .proc_handler = proc_sctp_do_hmac_alg, @@ -401,15 +402,18 @@ static int proc_sctp_do_rto_max(struct ctl_table *ctl, int write, int sctp_sysctl_net_register(struct net *net) { - struct ctl_table *table; - int i; + struct ctl_table *table = sctp_net_table; + + if (!net_eq(net, &init_net)) { + int i; - table = kmemdup(sctp_net_table, sizeof(sctp_net_table), GFP_KERNEL); - if (!table) - return -ENOMEM; + table = kmemdup(sctp_net_table, sizeof(sctp_net_table), GFP_KERNEL); + if (!table) + return -ENOMEM; - for (i = 0; table[i].data; i++) - table[i].data += (char *)(&net->sctp) - (char *)&init_net.sctp; + for (i = 0; table[i].data; i++) + table[i].data += (char *)(&net->sctp) - (char *)&init_net.sctp; + } net->sctp.sysctl_header = register_net_sysctl(net, "net/sctp", table); return 0; diff --git a/net/sctp/transport.c b/net/sctp/transport.c index d0810dc5f079..1d348d15b33d 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -652,5 +652,4 @@ void sctp_transport_immediate_rtx(struct sctp_transport *t) if (!mod_timer(&t->T3_rtx_timer, jiffies + t->rto)) sctp_transport_hold(t); } - return; } diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c index 85c64658bd0b..8d198ae03606 100644 --- a/net/sctp/ulpevent.c +++ b/net/sctp/ulpevent.c @@ -989,7 +989,7 @@ static void sctp_ulpevent_receive_data(struct sctp_ulpevent *event, skb = sctp_event2skb(event); /* Set the owner and charge rwnd for bytes received. */ sctp_ulpevent_set_owner(event, asoc); - sctp_assoc_rwnd_decrease(asoc, skb_headlen(skb)); + sctp_assoc_rwnd_update(asoc, false); if (!skb->data_len) return; @@ -1011,6 +1011,7 @@ static void sctp_ulpevent_release_data(struct sctp_ulpevent *event) { struct sk_buff *skb, *frag; unsigned int len; + struct sctp_association *asoc; /* Current stack structures assume that the rcv buffer is * per socket. For UDP style sockets this is not true as @@ -1035,8 +1036,11 @@ static void sctp_ulpevent_release_data(struct sctp_ulpevent *event) } done: - sctp_assoc_rwnd_increase(event->asoc, len); + asoc = event->asoc; + sctp_association_hold(asoc); sctp_ulpevent_release_owner(event); + sctp_assoc_rwnd_update(asoc, true); + sctp_association_put(asoc); } static void sctp_ulpevent_release_frag_data(struct sctp_ulpevent *event) diff --git a/net/socket.c b/net/socket.c index 879933aaed4c..840cffb7119b 100644 --- a/net/socket.c +++ b/net/socket.c @@ -593,7 +593,7 @@ void sock_release(struct socket *sock) } if (rcu_dereference_protected(sock->wq, 1)->fasync_list) - printk(KERN_ERR "sock_release: fasync list not empty!\n"); + pr_err("%s: fasync list not empty!\n", __func__); if (test_bit(SOCK_EXTERNALLY_ALLOCATED, &sock->flags)) return; @@ -1265,8 +1265,8 @@ int __sock_create(struct net *net, int family, int type, int protocol, static int warned; if (!warned) { warned = 1; - printk(KERN_INFO "%s uses obsolete (PF_INET,SOCK_PACKET)\n", - current->comm); + pr_info("%s uses obsolete (PF_INET,SOCK_PACKET)\n", + current->comm); } family = PF_PACKET; } @@ -2595,8 +2595,7 @@ int sock_register(const struct net_proto_family *ops) int err; if (ops->family >= NPROTO) { - printk(KERN_CRIT "protocol %d >= NPROTO(%d)\n", ops->family, - NPROTO); + pr_crit("protocol %d >= NPROTO(%d)\n", ops->family, NPROTO); return -ENOBUFS; } @@ -2610,7 +2609,7 @@ int sock_register(const struct net_proto_family *ops) } spin_unlock(&net_family_lock); - printk(KERN_INFO "NET: Registered protocol family %d\n", ops->family); + pr_info("NET: Registered protocol family %d\n", ops->family); return err; } EXPORT_SYMBOL(sock_register); @@ -2638,7 +2637,7 @@ void sock_unregister(int family) synchronize_rcu(); - printk(KERN_INFO "NET: Unregistered protocol family %d\n", family); + pr_info("NET: Unregistered protocol family %d\n", family); } EXPORT_SYMBOL(sock_unregister); diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index 6c0513a7f992..36e431ee1c90 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -108,6 +108,7 @@ struct gss_auth { static DEFINE_SPINLOCK(pipe_version_lock); static struct rpc_wait_queue pipe_version_rpc_waitqueue; static DECLARE_WAIT_QUEUE_HEAD(pipe_version_waitqueue); +static void gss_put_auth(struct gss_auth *gss_auth); static void gss_free_ctx(struct gss_cl_ctx *); static const struct rpc_pipe_ops gss_upcall_ops_v0; @@ -320,6 +321,7 @@ gss_release_msg(struct gss_upcall_msg *gss_msg) if (gss_msg->ctx != NULL) gss_put_ctx(gss_msg->ctx); rpc_destroy_wait_queue(&gss_msg->rpc_waitqueue); + gss_put_auth(gss_msg->auth); kfree(gss_msg); } @@ -498,9 +500,12 @@ gss_alloc_msg(struct gss_auth *gss_auth, default: err = gss_encode_v1_msg(gss_msg, service_name, gss_auth->target_name); if (err) - goto err_free_msg; + goto err_put_pipe_version; }; + kref_get(&gss_auth->kref); return gss_msg; +err_put_pipe_version: + put_pipe_version(gss_auth->net); err_free_msg: kfree(gss_msg); err: @@ -991,6 +996,8 @@ gss_create_new(struct rpc_auth_create_args *args, struct rpc_clnt *clnt) gss_auth->service = gss_pseudoflavor_to_service(gss_auth->mech, flavor); if (gss_auth->service == 0) goto err_put_mech; + if (!gssd_running(gss_auth->net)) + goto err_put_mech; auth = &gss_auth->rpc_auth; auth->au_cslack = GSS_CRED_SLACK >> 2; auth->au_rslack = GSS_VERF_SLACK >> 2; @@ -1062,6 +1069,12 @@ gss_free_callback(struct kref *kref) } static void +gss_put_auth(struct gss_auth *gss_auth) +{ + kref_put(&gss_auth->kref, gss_free_callback); +} + +static void gss_destroy(struct rpc_auth *auth) { struct gss_auth *gss_auth = container_of(auth, @@ -1082,7 +1095,7 @@ gss_destroy(struct rpc_auth *auth) gss_auth->gss_pipe[1] = NULL; rpcauth_destroy_credcache(auth); - kref_put(&gss_auth->kref, gss_free_callback); + gss_put_auth(gss_auth); } /* @@ -1253,7 +1266,7 @@ gss_destroy_nullcred(struct rpc_cred *cred) call_rcu(&cred->cr_rcu, gss_free_cred_callback); if (ctx) gss_put_ctx(ctx); - kref_put(&gss_auth->kref, gss_free_callback); + gss_put_auth(gss_auth); } static void diff --git a/net/sunrpc/backchannel_rqst.c b/net/sunrpc/backchannel_rqst.c index 890a29912d5a..e860d4f7ed2a 100644 --- a/net/sunrpc/backchannel_rqst.c +++ b/net/sunrpc/backchannel_rqst.c @@ -64,7 +64,6 @@ static void xprt_free_allocation(struct rpc_rqst *req) free_page((unsigned long)xbufp->head[0].iov_base); xbufp = &req->rq_snd_buf; free_page((unsigned long)xbufp->head[0].iov_base); - list_del(&req->rq_bc_pa_list); kfree(req); } @@ -168,8 +167,10 @@ out_free: /* * Memory allocation failed, free the temporary list */ - list_for_each_entry_safe(req, tmp, &tmp_list, rq_bc_pa_list) + list_for_each_entry_safe(req, tmp, &tmp_list, rq_bc_pa_list) { + list_del(&req->rq_bc_pa_list); xprt_free_allocation(req); + } dprintk("RPC: setup backchannel transport failed\n"); return -ENOMEM; @@ -198,6 +199,7 @@ void xprt_destroy_backchannel(struct rpc_xprt *xprt, unsigned int max_reqs) xprt_dec_alloc_count(xprt, max_reqs); list_for_each_entry_safe(req, tmp, &xprt->bc_pa_list, rq_bc_pa_list) { dprintk("RPC: req=%p\n", req); + list_del(&req->rq_bc_pa_list); xprt_free_allocation(req); if (--max_reqs == 0) break; diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 80a6640f329b..06c6ff0cb911 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -571,7 +571,7 @@ static void svc_check_conn_limits(struct svc_serv *serv) } } -int svc_alloc_arg(struct svc_rqst *rqstp) +static int svc_alloc_arg(struct svc_rqst *rqstp) { struct svc_serv *serv = rqstp->rq_server; struct xdr_buf *arg; @@ -612,7 +612,7 @@ int svc_alloc_arg(struct svc_rqst *rqstp) return 0; } -struct svc_xprt *svc_get_next_xprt(struct svc_rqst *rqstp, long timeout) +static struct svc_xprt *svc_get_next_xprt(struct svc_rqst *rqstp, long timeout) { struct svc_xprt *xprt; struct svc_pool *pool = rqstp->rq_pool; @@ -691,7 +691,7 @@ struct svc_xprt *svc_get_next_xprt(struct svc_rqst *rqstp, long timeout) return xprt; } -void svc_add_new_temp_xprt(struct svc_serv *serv, struct svc_xprt *newxpt) +static void svc_add_new_temp_xprt(struct svc_serv *serv, struct svc_xprt *newxpt) { spin_lock_bh(&serv->sv_lock); set_bit(XPT_TEMP, &newxpt->xpt_flags); diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 817a1e523969..0addefca8e77 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -510,6 +510,7 @@ static int xs_nospace(struct rpc_task *task) struct rpc_rqst *req = task->tk_rqstp; struct rpc_xprt *xprt = req->rq_xprt; struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); + struct sock *sk = transport->inet; int ret = -EAGAIN; dprintk("RPC: %5u xmit incomplete (%u left of %u)\n", @@ -527,7 +528,7 @@ static int xs_nospace(struct rpc_task *task) * window size */ set_bit(SOCK_NOSPACE, &transport->sock->flags); - transport->inet->sk_write_pending++; + sk->sk_write_pending++; /* ...and wait for more buffer space */ xprt_wait_for_buffer_space(task, xs_nospace_callback); } @@ -537,6 +538,9 @@ static int xs_nospace(struct rpc_task *task) } spin_unlock_bh(&xprt->transport_lock); + + /* Race breaker in case memory is freed before above code is called */ + sk->sk_write_space(sk); return ret; } diff --git a/net/tipc/addr.h b/net/tipc/addr.h index 60b00ab93d74..a74acf9ee804 100644 --- a/net/tipc/addr.h +++ b/net/tipc/addr.h @@ -37,6 +37,8 @@ #ifndef _TIPC_ADDR_H #define _TIPC_ADDR_H +#include "core.h" + #define TIPC_ZONE_MASK 0xff000000u #define TIPC_CLUSTER_MASK 0xfffff000u diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index bf860d9e75af..e0feb7ef1469 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -356,9 +356,9 @@ static void bclink_peek_nack(struct tipc_msg *msg) } /* - * tipc_bclink_send_msg - broadcast a packet to all nodes in cluster + * tipc_bclink_xmit - broadcast a packet to all nodes in cluster */ -int tipc_bclink_send_msg(struct sk_buff *buf) +int tipc_bclink_xmit(struct sk_buff *buf) { int res; @@ -370,7 +370,7 @@ int tipc_bclink_send_msg(struct sk_buff *buf) goto exit; } - res = tipc_link_send_buf(bcl, buf); + res = __tipc_link_xmit(bcl, buf); if (likely(res >= 0)) { bclink_set_last_sent(); bcl->stats.queue_sz_counts++; @@ -399,19 +399,18 @@ static void bclink_accept_pkt(struct tipc_node *node, u32 seqno) */ if (((seqno - tipc_own_addr) % TIPC_MIN_LINK_WIN) == 0) { - tipc_link_send_proto_msg( - node->active_links[node->addr & 1], - STATE_MSG, 0, 0, 0, 0, 0); + tipc_link_proto_xmit(node->active_links[node->addr & 1], + STATE_MSG, 0, 0, 0, 0, 0); bcl->stats.sent_acks++; } } /** - * tipc_bclink_recv_pkt - receive a broadcast packet, and deliver upwards + * tipc_bclink_rcv - receive a broadcast packet, and deliver upwards * * tipc_net_lock is read_locked, no other locks set */ -void tipc_bclink_recv_pkt(struct sk_buff *buf) +void tipc_bclink_rcv(struct sk_buff *buf) { struct tipc_msg *msg = buf_msg(buf); struct tipc_node *node; @@ -468,7 +467,7 @@ receive: spin_unlock_bh(&bc_lock); tipc_node_unlock(node); if (likely(msg_mcast(msg))) - tipc_port_recv_mcast(buf, NULL); + tipc_port_mcast_rcv(buf, NULL); else kfree_skb(buf); } else if (msg_user(msg) == MSG_BUNDLER) { @@ -478,12 +477,12 @@ receive: bcl->stats.recv_bundled += msg_msgcnt(msg); spin_unlock_bh(&bc_lock); tipc_node_unlock(node); - tipc_link_recv_bundle(buf); + tipc_link_bundle_rcv(buf); } else if (msg_user(msg) == MSG_FRAGMENTER) { int ret; - ret = tipc_link_recv_fragment(&node->bclink.reasm_head, - &node->bclink.reasm_tail, - &buf); + ret = tipc_link_frag_rcv(&node->bclink.reasm_head, + &node->bclink.reasm_tail, + &buf); if (ret == LINK_REASM_ERROR) goto unlock; spin_lock_bh(&bc_lock); @@ -503,7 +502,7 @@ receive: bclink_accept_pkt(node, seqno); spin_unlock_bh(&bc_lock); tipc_node_unlock(node); - tipc_named_recv(buf); + tipc_named_rcv(buf); } else { spin_lock_bh(&bc_lock); bclink_accept_pkt(node, seqno); @@ -785,7 +784,6 @@ void tipc_bclink_init(void) bcl->owner = &bclink->node; bcl->max_pkt = MAX_PKT_DEFAULT_MCAST; tipc_link_set_queue_limits(bcl, BCLINK_WIN_DEFAULT); - spin_lock_init(&bcbearer->bearer.lock); bcl->b_ptr = &bcbearer->bearer; bcl->state = WORKING_WORKING; strlcpy(bcl->name, tipc_bclink_name, TIPC_MAX_LINK_NAME); diff --git a/net/tipc/bcast.h b/net/tipc/bcast.h index 6ee587b469fd..a80ef54b818e 100644 --- a/net/tipc/bcast.h +++ b/net/tipc/bcast.h @@ -90,8 +90,8 @@ void tipc_bclink_add_node(u32 addr); void tipc_bclink_remove_node(u32 addr); struct tipc_node *tipc_bclink_retransmit_to(void); void tipc_bclink_acknowledge(struct tipc_node *n_ptr, u32 acked); -int tipc_bclink_send_msg(struct sk_buff *buf); -void tipc_bclink_recv_pkt(struct sk_buff *buf); +int tipc_bclink_xmit(struct sk_buff *buf); +void tipc_bclink_rcv(struct sk_buff *buf); u32 tipc_bclink_get_last_sent(void); u32 tipc_bclink_acks_missing(struct tipc_node *n_ptr); void tipc_bclink_update_link_state(struct tipc_node *n_ptr, u32 last_sent); diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index a38c89969c68..7f1f95c57476 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -51,7 +51,7 @@ static struct tipc_media * const media_info_array[] = { struct tipc_bearer tipc_bearers[MAX_BEARERS]; -static void bearer_disable(struct tipc_bearer *b_ptr); +static void bearer_disable(struct tipc_bearer *b_ptr, bool shutting_down); /** * tipc_media_find - locates specified media object by name @@ -327,12 +327,10 @@ restart: b_ptr->net_plane = bearer_id + 'A'; b_ptr->active = 1; b_ptr->priority = priority; - INIT_LIST_HEAD(&b_ptr->links); - spin_lock_init(&b_ptr->lock); res = tipc_disc_create(b_ptr, &b_ptr->bcast_addr, disc_domain); if (res) { - bearer_disable(b_ptr); + bearer_disable(b_ptr, false); pr_warn("Bearer <%s> rejected, discovery object creation failed\n", name); goto exit; @@ -350,20 +348,9 @@ exit: */ static int tipc_reset_bearer(struct tipc_bearer *b_ptr) { - struct tipc_link *l_ptr; - struct tipc_link *temp_l_ptr; - read_lock_bh(&tipc_net_lock); pr_info("Resetting bearer <%s>\n", b_ptr->name); - spin_lock_bh(&b_ptr->lock); - list_for_each_entry_safe(l_ptr, temp_l_ptr, &b_ptr->links, link_list) { - struct tipc_node *n_ptr = l_ptr->owner; - - spin_lock_bh(&n_ptr->lock); - tipc_link_reset(l_ptr); - spin_unlock_bh(&n_ptr->lock); - } - spin_unlock_bh(&b_ptr->lock); + tipc_link_reset_list(b_ptr->identity); read_unlock_bh(&tipc_net_lock); return 0; } @@ -373,25 +360,14 @@ static int tipc_reset_bearer(struct tipc_bearer *b_ptr) * * Note: This routine assumes caller holds tipc_net_lock. */ -static void bearer_disable(struct tipc_bearer *b_ptr) +static void bearer_disable(struct tipc_bearer *b_ptr, bool shutting_down) { - struct tipc_link *l_ptr; - struct tipc_link *temp_l_ptr; - struct tipc_link_req *temp_req; - pr_info("Disabling bearer <%s>\n", b_ptr->name); - spin_lock_bh(&b_ptr->lock); b_ptr->media->disable_media(b_ptr); - list_for_each_entry_safe(l_ptr, temp_l_ptr, &b_ptr->links, link_list) { - tipc_link_delete(l_ptr); - } - temp_req = b_ptr->link_req; - b_ptr->link_req = NULL; - spin_unlock_bh(&b_ptr->lock); - - if (temp_req) - tipc_disc_delete(temp_req); + tipc_link_delete_list(b_ptr->identity, shutting_down); + if (b_ptr->link_req) + tipc_disc_delete(b_ptr->link_req); memset(b_ptr, 0, sizeof(struct tipc_bearer)); } @@ -406,7 +382,7 @@ int tipc_disable_bearer(const char *name) pr_warn("Attempt to disable unknown bearer <%s>\n", name); res = -EINVAL; } else { - bearer_disable(b_ptr); + bearer_disable(b_ptr, false); res = 0; } write_unlock_bh(&tipc_net_lock); @@ -599,7 +575,7 @@ static int tipc_l2_device_event(struct notifier_block *nb, unsigned long evt, } static struct packet_type tipc_packet_type __read_mostly = { - .type = __constant_htons(ETH_P_TIPC), + .type = htons(ETH_P_TIPC), .func = tipc_l2_rcv_msg, }; @@ -610,8 +586,13 @@ static struct notifier_block notifier = { int tipc_bearer_setup(void) { + int err; + + err = register_netdevice_notifier(¬ifier); + if (err) + return err; dev_add_pack(&tipc_packet_type); - return register_netdevice_notifier(¬ifier); + return 0; } void tipc_bearer_cleanup(void) @@ -626,6 +607,6 @@ void tipc_bearer_stop(void) for (i = 0; i < MAX_BEARERS; i++) { if (tipc_bearers[i].active) - bearer_disable(&tipc_bearers[i]); + bearer_disable(&tipc_bearers[i], true); } } diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h index 4f5db9ad5bf6..425dd8107a8f 100644 --- a/net/tipc/bearer.h +++ b/net/tipc/bearer.h @@ -107,10 +107,8 @@ struct tipc_media { /** * struct tipc_bearer - Generic TIPC bearer structure - * @dev: ptr to associated network device - * @usr_handle: pointer to additional media-specific information about bearer + * @media_ptr: pointer to additional media-specific information about bearer * @mtu: max packet size bearer can support - * @lock: spinlock for controlling access to bearer * @addr: media-specific address associated with bearer * @name: bearer name (format = media:interface) * @media: ptr to media structure associated with bearer @@ -120,7 +118,6 @@ struct tipc_media { * @tolerance: default link tolerance for bearer * @identity: array index of this bearer within TIPC bearer array * @link_req: ptr to (optional) structure making periodic link setup requests - * @links: list of non-congested links associated with bearer * @active: non-zero if bearer structure is represents a bearer * @net_plane: network plane ('A' through 'H') currently associated with bearer * @nodes: indicates which nodes in cluster can be reached through bearer @@ -134,7 +131,6 @@ struct tipc_bearer { u32 mtu; /* initalized by media */ struct tipc_media_addr addr; /* initalized by media */ char name[TIPC_MAX_BEARER_NAME]; - spinlock_t lock; struct tipc_media *media; struct tipc_media_addr bcast_addr; u32 priority; @@ -142,7 +138,6 @@ struct tipc_bearer { u32 tolerance; u32 identity; struct tipc_link_req *link_req; - struct list_head links; int active; char net_plane; struct tipc_node_map nodes; diff --git a/net/tipc/config.c b/net/tipc/config.c index c301a9a592d8..e74eef2e7490 100644 --- a/net/tipc/config.c +++ b/net/tipc/config.c @@ -181,7 +181,7 @@ static struct sk_buff *cfg_set_own_addr(void) if (tipc_own_addr) return tipc_cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED " (cannot change node address once assigned)"); - tipc_core_start_net(addr); + tipc_net_start(addr); return tipc_cfg_reply_none(); } diff --git a/net/tipc/core.c b/net/tipc/core.c index f9e88d8b04ca..e2491b341edb 100644 --- a/net/tipc/core.c +++ b/net/tipc/core.c @@ -1,7 +1,7 @@ /* * net/tipc/core.c: TIPC module code * - * Copyright (c) 2003-2006, Ericsson AB + * Copyright (c) 2003-2006, 2013, Ericsson AB * Copyright (c) 2005-2006, 2010-2013, Wind River Systems * All rights reserved. * @@ -77,37 +77,13 @@ struct sk_buff *tipc_buf_acquire(u32 size) } /** - * tipc_core_stop_net - shut down TIPC networking sub-systems - */ -static void tipc_core_stop_net(void) -{ - tipc_net_stop(); - tipc_bearer_cleanup(); -} - -/** - * start_net - start TIPC networking sub-systems - */ -int tipc_core_start_net(unsigned long addr) -{ - int res; - - tipc_net_start(addr); - res = tipc_bearer_setup(); - if (res < 0) - goto err; - return res; - -err: - tipc_core_stop_net(); - return res; -} - -/** * tipc_core_stop - switch TIPC from SINGLE NODE to NOT RUNNING mode */ static void tipc_core_stop(void) { + tipc_handler_stop(); + tipc_net_stop(); + tipc_bearer_cleanup(); tipc_netlink_stop(); tipc_cfg_stop(); tipc_subscr_stop(); @@ -122,30 +98,65 @@ static void tipc_core_stop(void) */ static int tipc_core_start(void) { - int res; + int err; get_random_bytes(&tipc_random, sizeof(tipc_random)); - res = tipc_handler_start(); - if (!res) - res = tipc_ref_table_init(tipc_max_ports, tipc_random); - if (!res) - res = tipc_nametbl_init(); - if (!res) - res = tipc_netlink_start(); - if (!res) - res = tipc_socket_init(); - if (!res) - res = tipc_register_sysctl(); - if (!res) - res = tipc_subscr_start(); - if (!res) - res = tipc_cfg_init(); - if (res) { - tipc_handler_stop(); - tipc_core_stop(); - } - return res; + err = tipc_handler_start(); + if (err) + goto out_handler; + + err = tipc_ref_table_init(tipc_max_ports, tipc_random); + if (err) + goto out_reftbl; + + err = tipc_nametbl_init(); + if (err) + goto out_nametbl; + + err = tipc_netlink_start(); + if (err) + goto out_netlink; + + err = tipc_socket_init(); + if (err) + goto out_socket; + + err = tipc_register_sysctl(); + if (err) + goto out_sysctl; + + err = tipc_subscr_start(); + if (err) + goto out_subscr; + + err = tipc_cfg_init(); + if (err) + goto out_cfg; + + err = tipc_bearer_setup(); + if (err) + goto out_bearer; + + return 0; +out_bearer: + tipc_cfg_stop(); +out_cfg: + tipc_subscr_stop(); +out_subscr: + tipc_unregister_sysctl(); +out_sysctl: + tipc_socket_stop(); +out_socket: + tipc_netlink_stop(); +out_netlink: + tipc_nametbl_stop(); +out_nametbl: + tipc_ref_table_stop(); +out_reftbl: + tipc_handler_stop(); +out_handler: + return err; } static int __init tipc_init(void) @@ -174,8 +185,6 @@ static int __init tipc_init(void) static void __exit tipc_exit(void) { - tipc_handler_stop(); - tipc_core_stop_net(); tipc_core_stop(); pr_info("Deactivated\n"); } diff --git a/net/tipc/core.h b/net/tipc/core.h index 1ff477b0450d..4dfe137587bb 100644 --- a/net/tipc/core.h +++ b/net/tipc/core.h @@ -90,7 +90,6 @@ extern int tipc_random __read_mostly; /* * Routines available to privileged subsystems */ -int tipc_core_start_net(unsigned long); int tipc_handler_start(void); void tipc_handler_stop(void); int tipc_netlink_start(void); @@ -192,6 +191,7 @@ static inline void k_term_timer(struct timer_list *timer) struct tipc_skb_cb { void *handle; + bool deferred; }; #define TIPC_SKB_CB(__skb) ((struct tipc_skb_cb *)&((__skb)->cb[0])) diff --git a/net/tipc/discover.c b/net/tipc/discover.c index 412ff41b8611..fa94da6db3d4 100644 --- a/net/tipc/discover.c +++ b/net/tipc/discover.c @@ -110,11 +110,11 @@ static void disc_dupl_alert(struct tipc_bearer *b_ptr, u32 node_addr, } /** - * tipc_disc_recv_msg - handle incoming link setup message (request or response) + * tipc_disc_rcv - handle incoming link setup message (request or response) * @buf: buffer containing message * @b_ptr: bearer that message arrived on */ -void tipc_disc_recv_msg(struct sk_buff *buf, struct tipc_bearer *b_ptr) +void tipc_disc_rcv(struct sk_buff *buf, struct tipc_bearer *b_ptr) { struct tipc_node *n_ptr; struct tipc_link *link; diff --git a/net/tipc/discover.h b/net/tipc/discover.h index 75b67c403aa3..b4fc962c3623 100644 --- a/net/tipc/discover.h +++ b/net/tipc/discover.h @@ -44,6 +44,6 @@ int tipc_disc_create(struct tipc_bearer *b_ptr, struct tipc_media_addr *dest, void tipc_disc_delete(struct tipc_link_req *req); void tipc_disc_add_dest(struct tipc_link_req *req); void tipc_disc_remove_dest(struct tipc_link_req *req); -void tipc_disc_recv_msg(struct sk_buff *buf, struct tipc_bearer *b_ptr); +void tipc_disc_rcv(struct sk_buff *buf, struct tipc_bearer *b_ptr); #endif diff --git a/net/tipc/link.c b/net/tipc/link.c index d4b5de41b682..a42f4a1d3cd1 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -77,19 +77,19 @@ static const char *link_unk_evt = "Unknown link event "; static void link_handle_out_of_seq_msg(struct tipc_link *l_ptr, struct sk_buff *buf); -static void link_recv_proto_msg(struct tipc_link *l_ptr, struct sk_buff *buf); -static int tipc_link_tunnel_rcv(struct tipc_link **l_ptr, +static void tipc_link_proto_rcv(struct tipc_link *l_ptr, struct sk_buff *buf); +static int tipc_link_tunnel_rcv(struct tipc_node *n_ptr, struct sk_buff **buf); static void link_set_supervision_props(struct tipc_link *l_ptr, u32 tolerance); -static int link_send_sections_long(struct tipc_port *sender, - struct iovec const *msg_sect, - unsigned int len, u32 destnode); +static int tipc_link_iovec_long_xmit(struct tipc_port *sender, + struct iovec const *msg_sect, + unsigned int len, u32 destnode); static void link_state_event(struct tipc_link *l_ptr, u32 event); static void link_reset_statistics(struct tipc_link *l_ptr); static void link_print(struct tipc_link *l_ptr, const char *str); -static int link_send_long_buf(struct tipc_link *l_ptr, struct sk_buff *buf); -static void tipc_link_send_sync(struct tipc_link *l); -static void tipc_link_recv_sync(struct tipc_node *n, struct sk_buff *buf); +static int tipc_link_frag_xmit(struct tipc_link *l_ptr, struct sk_buff *buf); +static void tipc_link_sync_xmit(struct tipc_link *l); +static void tipc_link_sync_rcv(struct tipc_node *n, struct sk_buff *buf); /* * Simple link routines @@ -147,11 +147,6 @@ int tipc_link_is_active(struct tipc_link *l_ptr) /** * link_timeout - handle expiration of link timer * @l_ptr: pointer to link - * - * This routine must not grab "tipc_net_lock" to avoid a potential deadlock conflict - * with tipc_link_delete(). (There is no risk that the node will be deleted by - * another thread because tipc_link_delete() always cancels the link timer before - * tipc_node_delete() is called.) */ static void link_timeout(struct tipc_link *l_ptr) { @@ -213,8 +208,8 @@ static void link_set_timer(struct tipc_link *l_ptr, u32 time) * Returns pointer to link. */ struct tipc_link *tipc_link_create(struct tipc_node *n_ptr, - struct tipc_bearer *b_ptr, - const struct tipc_media_addr *media_addr) + struct tipc_bearer *b_ptr, + const struct tipc_media_addr *media_addr) { struct tipc_link *l_ptr; struct tipc_msg *msg; @@ -279,41 +274,43 @@ struct tipc_link *tipc_link_create(struct tipc_node *n_ptr, k_init_timer(&l_ptr->timer, (Handler)link_timeout, (unsigned long)l_ptr); - list_add_tail(&l_ptr->link_list, &b_ptr->links); link_state_event(l_ptr, STARTING_EVT); return l_ptr; } -/** - * tipc_link_delete - delete a link - * @l_ptr: pointer to link - * - * Note: 'tipc_net_lock' is write_locked, bearer is locked. - * This routine must not grab the node lock until after link timer cancellation - * to avoid a potential deadlock situation. - */ -void tipc_link_delete(struct tipc_link *l_ptr) -{ - if (!l_ptr) { - pr_err("Attempt to delete non-existent link\n"); - return; - } - k_cancel_timer(&l_ptr->timer); +void tipc_link_delete_list(unsigned int bearer_id, bool shutting_down) +{ + struct tipc_link *l_ptr; + struct tipc_node *n_ptr; - tipc_node_lock(l_ptr->owner); - tipc_link_reset(l_ptr); - tipc_node_detach_link(l_ptr->owner, l_ptr); - tipc_link_purge_queues(l_ptr); - list_del_init(&l_ptr->link_list); - tipc_node_unlock(l_ptr->owner); - k_term_timer(&l_ptr->timer); - kfree(l_ptr); + list_for_each_entry(n_ptr, &tipc_node_list, list) { + spin_lock_bh(&n_ptr->lock); + l_ptr = n_ptr->links[bearer_id]; + if (l_ptr) { + tipc_link_reset(l_ptr); + if (shutting_down || !tipc_node_is_up(n_ptr)) { + tipc_node_detach_link(l_ptr->owner, l_ptr); + tipc_link_reset_fragments(l_ptr); + spin_unlock_bh(&n_ptr->lock); + + /* Nobody else can access this link now: */ + del_timer_sync(&l_ptr->timer); + kfree(l_ptr); + } else { + /* Detach/delete when failover is finished: */ + l_ptr->flags |= LINK_STOPPED; + spin_unlock_bh(&n_ptr->lock); + del_timer_sync(&l_ptr->timer); + } + continue; + } + spin_unlock_bh(&n_ptr->lock); + } } - /** * link_schedule_port - schedule port for deferred sending * @l_ptr: pointer to link @@ -330,8 +327,6 @@ static int link_schedule_port(struct tipc_link *l_ptr, u32 origport, u32 sz) spin_lock_bh(&tipc_port_list_lock); p_ptr = tipc_port_lock(origport); if (p_ptr) { - if (!p_ptr->wakeup) - goto exit; if (!list_empty(&p_ptr->wait_list)) goto exit; p_ptr->congested = 1; @@ -366,7 +361,7 @@ void tipc_link_wakeup_ports(struct tipc_link *l_ptr, int all) list_del_init(&p_ptr->wait_list); spin_lock_bh(p_ptr->lock); p_ptr->congested = 0; - p_ptr->wakeup(p_ptr); + tipc_port_wakeup(p_ptr); win -= p_ptr->waiting_pkts; spin_unlock_bh(p_ptr->lock); } @@ -461,6 +456,19 @@ void tipc_link_reset(struct tipc_link *l_ptr) link_reset_statistics(l_ptr); } +void tipc_link_reset_list(unsigned int bearer_id) +{ + struct tipc_link *l_ptr; + struct tipc_node *n_ptr; + + list_for_each_entry(n_ptr, &tipc_node_list, list) { + spin_lock_bh(&n_ptr->lock); + l_ptr = n_ptr->links[bearer_id]; + if (l_ptr) + tipc_link_reset(l_ptr); + spin_unlock_bh(&n_ptr->lock); + } +} static void link_activate(struct tipc_link *l_ptr) { @@ -479,7 +487,10 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event) struct tipc_link *other; u32 cont_intv = l_ptr->continuity_interval; - if (!l_ptr->started && (event != STARTING_EVT)) + if (l_ptr->flags & LINK_STOPPED) + return; + + if (!(l_ptr->flags & LINK_STARTED) && (event != STARTING_EVT)) return; /* Not yet. */ /* Check whether changeover is going on */ @@ -499,12 +510,12 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event) if (l_ptr->next_in_no != l_ptr->checkpoint) { l_ptr->checkpoint = l_ptr->next_in_no; if (tipc_bclink_acks_missing(l_ptr->owner)) { - tipc_link_send_proto_msg(l_ptr, STATE_MSG, - 0, 0, 0, 0, 0); + tipc_link_proto_xmit(l_ptr, STATE_MSG, + 0, 0, 0, 0, 0); l_ptr->fsm_msg_cnt++; } else if (l_ptr->max_pkt < l_ptr->max_pkt_target) { - tipc_link_send_proto_msg(l_ptr, STATE_MSG, - 1, 0, 0, 0, 0); + tipc_link_proto_xmit(l_ptr, STATE_MSG, + 1, 0, 0, 0, 0); l_ptr->fsm_msg_cnt++; } link_set_timer(l_ptr, cont_intv); @@ -512,7 +523,7 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event) } l_ptr->state = WORKING_UNKNOWN; l_ptr->fsm_msg_cnt = 0; - tipc_link_send_proto_msg(l_ptr, STATE_MSG, 1, 0, 0, 0, 0); + tipc_link_proto_xmit(l_ptr, STATE_MSG, 1, 0, 0, 0, 0); l_ptr->fsm_msg_cnt++; link_set_timer(l_ptr, cont_intv / 4); break; @@ -522,7 +533,8 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event) tipc_link_reset(l_ptr); l_ptr->state = RESET_RESET; l_ptr->fsm_msg_cnt = 0; - tipc_link_send_proto_msg(l_ptr, ACTIVATE_MSG, 0, 0, 0, 0, 0); + tipc_link_proto_xmit(l_ptr, ACTIVATE_MSG, + 0, 0, 0, 0, 0); l_ptr->fsm_msg_cnt++; link_set_timer(l_ptr, cont_intv); break; @@ -544,7 +556,8 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event) tipc_link_reset(l_ptr); l_ptr->state = RESET_RESET; l_ptr->fsm_msg_cnt = 0; - tipc_link_send_proto_msg(l_ptr, ACTIVATE_MSG, 0, 0, 0, 0, 0); + tipc_link_proto_xmit(l_ptr, ACTIVATE_MSG, + 0, 0, 0, 0, 0); l_ptr->fsm_msg_cnt++; link_set_timer(l_ptr, cont_intv); break; @@ -554,14 +567,14 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event) l_ptr->fsm_msg_cnt = 0; l_ptr->checkpoint = l_ptr->next_in_no; if (tipc_bclink_acks_missing(l_ptr->owner)) { - tipc_link_send_proto_msg(l_ptr, STATE_MSG, - 0, 0, 0, 0, 0); + tipc_link_proto_xmit(l_ptr, STATE_MSG, + 0, 0, 0, 0, 0); l_ptr->fsm_msg_cnt++; } link_set_timer(l_ptr, cont_intv); } else if (l_ptr->fsm_msg_cnt < l_ptr->abort_limit) { - tipc_link_send_proto_msg(l_ptr, STATE_MSG, - 1, 0, 0, 0, 0); + tipc_link_proto_xmit(l_ptr, STATE_MSG, + 1, 0, 0, 0, 0); l_ptr->fsm_msg_cnt++; link_set_timer(l_ptr, cont_intv / 4); } else { /* Link has failed */ @@ -570,8 +583,8 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event) tipc_link_reset(l_ptr); l_ptr->state = RESET_UNKNOWN; l_ptr->fsm_msg_cnt = 0; - tipc_link_send_proto_msg(l_ptr, RESET_MSG, - 0, 0, 0, 0, 0); + tipc_link_proto_xmit(l_ptr, RESET_MSG, + 0, 0, 0, 0, 0); l_ptr->fsm_msg_cnt++; link_set_timer(l_ptr, cont_intv); } @@ -591,24 +604,25 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event) l_ptr->state = WORKING_WORKING; l_ptr->fsm_msg_cnt = 0; link_activate(l_ptr); - tipc_link_send_proto_msg(l_ptr, STATE_MSG, 1, 0, 0, 0, 0); + tipc_link_proto_xmit(l_ptr, STATE_MSG, 1, 0, 0, 0, 0); l_ptr->fsm_msg_cnt++; if (l_ptr->owner->working_links == 1) - tipc_link_send_sync(l_ptr); + tipc_link_sync_xmit(l_ptr); link_set_timer(l_ptr, cont_intv); break; case RESET_MSG: l_ptr->state = RESET_RESET; l_ptr->fsm_msg_cnt = 0; - tipc_link_send_proto_msg(l_ptr, ACTIVATE_MSG, 1, 0, 0, 0, 0); + tipc_link_proto_xmit(l_ptr, ACTIVATE_MSG, + 1, 0, 0, 0, 0); l_ptr->fsm_msg_cnt++; link_set_timer(l_ptr, cont_intv); break; case STARTING_EVT: - l_ptr->started = 1; + l_ptr->flags |= LINK_STARTED; /* fall through */ case TIMEOUT_EVT: - tipc_link_send_proto_msg(l_ptr, RESET_MSG, 0, 0, 0, 0, 0); + tipc_link_proto_xmit(l_ptr, RESET_MSG, 0, 0, 0, 0, 0); l_ptr->fsm_msg_cnt++; link_set_timer(l_ptr, cont_intv); break; @@ -626,16 +640,17 @@ static void link_state_event(struct tipc_link *l_ptr, unsigned int event) l_ptr->state = WORKING_WORKING; l_ptr->fsm_msg_cnt = 0; link_activate(l_ptr); - tipc_link_send_proto_msg(l_ptr, STATE_MSG, 1, 0, 0, 0, 0); + tipc_link_proto_xmit(l_ptr, STATE_MSG, 1, 0, 0, 0, 0); l_ptr->fsm_msg_cnt++; if (l_ptr->owner->working_links == 1) - tipc_link_send_sync(l_ptr); + tipc_link_sync_xmit(l_ptr); link_set_timer(l_ptr, cont_intv); break; case RESET_MSG: break; case TIMEOUT_EVT: - tipc_link_send_proto_msg(l_ptr, ACTIVATE_MSG, 0, 0, 0, 0, 0); + tipc_link_proto_xmit(l_ptr, ACTIVATE_MSG, + 0, 0, 0, 0, 0); l_ptr->fsm_msg_cnt++; link_set_timer(l_ptr, cont_intv); break; @@ -721,11 +736,11 @@ static void link_add_chain_to_outqueue(struct tipc_link *l_ptr, } /* - * tipc_link_send_buf() is the 'full path' for messages, called from - * inside TIPC when the 'fast path' in tipc_send_buf + * tipc_link_xmit() is the 'full path' for messages, called from + * inside TIPC when the 'fast path' in tipc_send_xmit * has failed, and from link_send() */ -int tipc_link_send_buf(struct tipc_link *l_ptr, struct sk_buff *buf) +int __tipc_link_xmit(struct tipc_link *l_ptr, struct sk_buff *buf) { struct tipc_msg *msg = buf_msg(buf); u32 size = msg_size(msg); @@ -753,7 +768,7 @@ int tipc_link_send_buf(struct tipc_link *l_ptr, struct sk_buff *buf) /* Fragmentation needed ? */ if (size > max_packet) - return link_send_long_buf(l_ptr, buf); + return tipc_link_frag_xmit(l_ptr, buf); /* Packet can be queued or sent. */ if (likely(!link_congested(l_ptr))) { @@ -797,11 +812,11 @@ int tipc_link_send_buf(struct tipc_link *l_ptr, struct sk_buff *buf) } /* - * tipc_link_send(): same as tipc_link_send_buf(), but the link to use has - * not been selected yet, and the the owner node is not locked + * tipc_link_xmit(): same as __tipc_link_xmit(), but the link to use + * has not been selected yet, and the the owner node is not locked * Called by TIPC internal users, e.g. the name distributor */ -int tipc_link_send(struct sk_buff *buf, u32 dest, u32 selector) +int tipc_link_xmit(struct sk_buff *buf, u32 dest, u32 selector) { struct tipc_link *l_ptr; struct tipc_node *n_ptr; @@ -813,7 +828,7 @@ int tipc_link_send(struct sk_buff *buf, u32 dest, u32 selector) tipc_node_lock(n_ptr); l_ptr = n_ptr->active_links[selector & 1]; if (l_ptr) - res = tipc_link_send_buf(l_ptr, buf); + res = __tipc_link_xmit(l_ptr, buf); else kfree_skb(buf); tipc_node_unlock(n_ptr); @@ -825,14 +840,14 @@ int tipc_link_send(struct sk_buff *buf, u32 dest, u32 selector) } /* - * tipc_link_send_sync - synchronize broadcast link endpoints. + * tipc_link_sync_xmit - synchronize broadcast link endpoints. * * Give a newly added peer node the sequence number where it should * start receiving and acking broadcast packets. * * Called with node locked */ -static void tipc_link_send_sync(struct tipc_link *l) +static void tipc_link_sync_xmit(struct tipc_link *l) { struct sk_buff *buf; struct tipc_msg *msg; @@ -849,14 +864,14 @@ static void tipc_link_send_sync(struct tipc_link *l) } /* - * tipc_link_recv_sync - synchronize broadcast link endpoints. + * tipc_link_sync_rcv - synchronize broadcast link endpoints. * Receive the sequence number where we should start receiving and * acking broadcast packets from a newly added peer node, and open * up for reception of such packets. * * Called with node locked */ -static void tipc_link_recv_sync(struct tipc_node *n, struct sk_buff *buf) +static void tipc_link_sync_rcv(struct tipc_node *n, struct sk_buff *buf) { struct tipc_msg *msg = buf_msg(buf); @@ -866,7 +881,7 @@ static void tipc_link_recv_sync(struct tipc_node *n, struct sk_buff *buf) } /* - * tipc_link_send_names - send name table entries to new neighbor + * tipc_link_names_xmit - send name table entries to new neighbor * * Send routine for bulk delivery of name table messages when contact * with a new neighbor occurs. No link congestion checking is performed @@ -874,7 +889,7 @@ static void tipc_link_recv_sync(struct tipc_node *n, struct sk_buff *buf) * small enough not to require fragmentation. * Called without any locks held. */ -void tipc_link_send_names(struct list_head *message_list, u32 dest) +void tipc_link_names_xmit(struct list_head *message_list, u32 dest) { struct tipc_node *n_ptr; struct tipc_link *l_ptr; @@ -909,13 +924,13 @@ void tipc_link_send_names(struct list_head *message_list, u32 dest) } /* - * link_send_buf_fast: Entry for data messages where the + * tipc_link_xmit_fast: Entry for data messages where the * destination link is known and the header is complete, * inclusive total message length. Very time critical. * Link is locked. Returns user data length. */ -static int link_send_buf_fast(struct tipc_link *l_ptr, struct sk_buff *buf, - u32 *used_max_pkt) +static int tipc_link_xmit_fast(struct tipc_link *l_ptr, struct sk_buff *buf, + u32 *used_max_pkt) { struct tipc_msg *msg = buf_msg(buf); int res = msg_data_sz(msg); @@ -931,18 +946,18 @@ static int link_send_buf_fast(struct tipc_link *l_ptr, struct sk_buff *buf, else *used_max_pkt = l_ptr->max_pkt; } - return tipc_link_send_buf(l_ptr, buf); /* All other cases */ + return __tipc_link_xmit(l_ptr, buf); /* All other cases */ } /* - * tipc_link_send_sections_fast: Entry for messages where the + * tipc_link_iovec_xmit_fast: Entry for messages where the * destination processor is known and the header is complete, * except for total message length. * Returns user data length or errno. */ -int tipc_link_send_sections_fast(struct tipc_port *sender, - struct iovec const *msg_sect, - unsigned int len, u32 destaddr) +int tipc_link_iovec_xmit_fast(struct tipc_port *sender, + struct iovec const *msg_sect, + unsigned int len, u32 destaddr) { struct tipc_msg *hdr = &sender->phdr; struct tipc_link *l_ptr; @@ -968,8 +983,8 @@ again: l_ptr = node->active_links[selector]; if (likely(l_ptr)) { if (likely(buf)) { - res = link_send_buf_fast(l_ptr, buf, - &sender->max_pkt); + res = tipc_link_xmit_fast(l_ptr, buf, + &sender->max_pkt); exit: tipc_node_unlock(node); read_unlock_bh(&tipc_net_lock); @@ -995,24 +1010,21 @@ exit: if ((msg_hdr_sz(hdr) + res) <= sender->max_pkt) goto again; - return link_send_sections_long(sender, msg_sect, len, - destaddr); + return tipc_link_iovec_long_xmit(sender, msg_sect, + len, destaddr); } tipc_node_unlock(node); } read_unlock_bh(&tipc_net_lock); /* Couldn't find a link to the destination node */ - if (buf) - return tipc_reject_msg(buf, TIPC_ERR_NO_NODE); - if (res >= 0) - return tipc_port_reject_sections(sender, hdr, msg_sect, - len, TIPC_ERR_NO_NODE); - return res; + kfree_skb(buf); + tipc_port_iovec_reject(sender, hdr, msg_sect, len, TIPC_ERR_NO_NODE); + return -ENETUNREACH; } /* - * link_send_sections_long(): Entry for long messages where the + * tipc_link_iovec_long_xmit(): Entry for long messages where the * destination node is known and the header is complete, * inclusive total message length. * Link and bearer congestion status have been checked to be ok, @@ -1025,9 +1037,9 @@ exit: * * Returns user data length or errno. */ -static int link_send_sections_long(struct tipc_port *sender, - struct iovec const *msg_sect, - unsigned int len, u32 destaddr) +static int tipc_link_iovec_long_xmit(struct tipc_port *sender, + struct iovec const *msg_sect, + unsigned int len, u32 destaddr) { struct tipc_link *l_ptr; struct tipc_node *node; @@ -1146,8 +1158,9 @@ error: } else { reject: kfree_skb_list(buf_chain); - return tipc_port_reject_sections(sender, hdr, msg_sect, - len, TIPC_ERR_NO_NODE); + tipc_port_iovec_reject(sender, hdr, msg_sect, len, + TIPC_ERR_NO_NODE); + return -ENETUNREACH; } /* Append chain of fragments to send queue & send them */ @@ -1391,6 +1404,12 @@ static int link_recv_buf_validate(struct sk_buff *buf) u32 hdr_size; u32 min_hdr_size; + /* If this packet comes from the defer queue, the skb has already + * been validated + */ + if (unlikely(TIPC_SKB_CB(buf)->deferred)) + return 1; + if (unlikely(buf->len < MIN_H_SIZE)) return 0; @@ -1435,7 +1454,6 @@ void tipc_rcv(struct sk_buff *head, struct tipc_bearer *b_ptr) u32 seq_no; u32 ackd; u32 released = 0; - int type; head = head->next; buf->next = NULL; @@ -1457,9 +1475,9 @@ void tipc_rcv(struct sk_buff *head, struct tipc_bearer *b_ptr) if (unlikely(msg_non_seq(msg))) { if (msg_user(msg) == LINK_CONFIG) - tipc_disc_recv_msg(buf, b_ptr); + tipc_disc_rcv(buf, b_ptr); else - tipc_bclink_recv_pkt(buf); + tipc_bclink_rcv(buf); continue; } @@ -1483,7 +1501,7 @@ void tipc_rcv(struct sk_buff *head, struct tipc_bearer *b_ptr) if ((n_ptr->block_setup & WAIT_PEER_DOWN) && msg_user(msg) == LINK_PROTOCOL && (msg_type(msg) == RESET_MSG || - msg_type(msg) == ACTIVATE_MSG) && + msg_type(msg) == ACTIVATE_MSG) && !msg_redundant_link(msg)) n_ptr->block_setup &= ~WAIT_PEER_DOWN; @@ -1502,7 +1520,6 @@ void tipc_rcv(struct sk_buff *head, struct tipc_bearer *b_ptr) while ((crs != l_ptr->next_out) && less_eq(buf_seqno(crs), ackd)) { struct sk_buff *next = crs->next; - kfree_skb(crs); crs = next; released++; @@ -1515,18 +1532,19 @@ void tipc_rcv(struct sk_buff *head, struct tipc_bearer *b_ptr) /* Try sending any messages link endpoint has pending */ if (unlikely(l_ptr->next_out)) tipc_link_push_queue(l_ptr); + if (unlikely(!list_empty(&l_ptr->waiting_ports))) tipc_link_wakeup_ports(l_ptr, 0); + if (unlikely(++l_ptr->unacked_window >= TIPC_MIN_LINK_WIN)) { l_ptr->stats.sent_acks++; - tipc_link_send_proto_msg(l_ptr, STATE_MSG, 0, 0, 0, 0, 0); + tipc_link_proto_xmit(l_ptr, STATE_MSG, 0, 0, 0, 0, 0); } - /* Now (finally!) process the incoming message */ -protocol_check: + /* Process the incoming packet */ if (unlikely(!link_working_working(l_ptr))) { if (msg_user(msg) == LINK_PROTOCOL) { - link_recv_proto_msg(l_ptr, buf); + tipc_link_proto_rcv(l_ptr, buf); head = link_insert_deferred_queue(l_ptr, head); tipc_node_unlock(n_ptr); continue; @@ -1555,67 +1573,65 @@ protocol_check: l_ptr->next_in_no++; if (unlikely(l_ptr->oldest_deferred_in)) head = link_insert_deferred_queue(l_ptr, head); -deliver: - if (likely(msg_isdata(msg))) { - tipc_node_unlock(n_ptr); - tipc_port_recv_msg(buf); - continue; + + /* Deliver packet/message to correct user: */ + if (unlikely(msg_user(msg) == CHANGEOVER_PROTOCOL)) { + if (!tipc_link_tunnel_rcv(n_ptr, &buf)) { + tipc_node_unlock(n_ptr); + continue; + } + msg = buf_msg(buf); + } else if (msg_user(msg) == MSG_FRAGMENTER) { + int rc; + + l_ptr->stats.recv_fragments++; + rc = tipc_link_frag_rcv(&l_ptr->reasm_head, + &l_ptr->reasm_tail, + &buf); + if (rc == LINK_REASM_COMPLETE) { + l_ptr->stats.recv_fragmented++; + msg = buf_msg(buf); + } else { + if (rc == LINK_REASM_ERROR) + tipc_link_reset(l_ptr); + tipc_node_unlock(n_ptr); + continue; + } } + switch (msg_user(msg)) { - int ret; + case TIPC_LOW_IMPORTANCE: + case TIPC_MEDIUM_IMPORTANCE: + case TIPC_HIGH_IMPORTANCE: + case TIPC_CRITICAL_IMPORTANCE: + tipc_node_unlock(n_ptr); + tipc_port_rcv(buf); + continue; case MSG_BUNDLER: l_ptr->stats.recv_bundles++; l_ptr->stats.recv_bundled += msg_msgcnt(msg); tipc_node_unlock(n_ptr); - tipc_link_recv_bundle(buf); + tipc_link_bundle_rcv(buf); continue; case NAME_DISTRIBUTOR: n_ptr->bclink.recv_permitted = true; tipc_node_unlock(n_ptr); - tipc_named_recv(buf); - continue; - case BCAST_PROTOCOL: - tipc_link_recv_sync(n_ptr, buf); - tipc_node_unlock(n_ptr); + tipc_named_rcv(buf); continue; case CONN_MANAGER: tipc_node_unlock(n_ptr); - tipc_port_recv_proto_msg(buf); - continue; - case MSG_FRAGMENTER: - l_ptr->stats.recv_fragments++; - ret = tipc_link_recv_fragment(&l_ptr->reasm_head, - &l_ptr->reasm_tail, - &buf); - if (ret == LINK_REASM_COMPLETE) { - l_ptr->stats.recv_fragmented++; - msg = buf_msg(buf); - goto deliver; - } - if (ret == LINK_REASM_ERROR) - tipc_link_reset(l_ptr); - tipc_node_unlock(n_ptr); + tipc_port_proto_rcv(buf); continue; - case CHANGEOVER_PROTOCOL: - type = msg_type(msg); - if (tipc_link_tunnel_rcv(&l_ptr, &buf)) { - msg = buf_msg(buf); - seq_no = msg_seqno(msg); - if (type == ORIGINAL_MSG) - goto deliver; - goto protocol_check; - } + case BCAST_PROTOCOL: + tipc_link_sync_rcv(n_ptr, buf); break; default: kfree_skb(buf); - buf = NULL; break; } tipc_node_unlock(n_ptr); - tipc_net_route_msg(buf); continue; unlock_discard: - tipc_node_unlock(n_ptr); discard: kfree_skb(buf); @@ -1682,7 +1698,7 @@ static void link_handle_out_of_seq_msg(struct tipc_link *l_ptr, u32 seq_no = buf_seqno(buf); if (likely(msg_user(buf_msg(buf)) == LINK_PROTOCOL)) { - link_recv_proto_msg(l_ptr, buf); + tipc_link_proto_rcv(l_ptr, buf); return; } @@ -1703,8 +1719,9 @@ static void link_handle_out_of_seq_msg(struct tipc_link *l_ptr, &l_ptr->newest_deferred_in, buf)) { l_ptr->deferred_inqueue_sz++; l_ptr->stats.deferred_recv++; + TIPC_SKB_CB(buf)->deferred = true; if ((l_ptr->deferred_inqueue_sz % 16) == 1) - tipc_link_send_proto_msg(l_ptr, STATE_MSG, 0, 0, 0, 0, 0); + tipc_link_proto_xmit(l_ptr, STATE_MSG, 0, 0, 0, 0, 0); } else l_ptr->stats.duplicates++; } @@ -1712,9 +1729,8 @@ static void link_handle_out_of_seq_msg(struct tipc_link *l_ptr, /* * Send protocol message to the other endpoint. */ -void tipc_link_send_proto_msg(struct tipc_link *l_ptr, u32 msg_typ, - int probe_msg, u32 gap, u32 tolerance, - u32 priority, u32 ack_mtu) +void tipc_link_proto_xmit(struct tipc_link *l_ptr, u32 msg_typ, int probe_msg, + u32 gap, u32 tolerance, u32 priority, u32 ack_mtu) { struct sk_buff *buf = NULL; struct tipc_msg *msg = l_ptr->pmsg; @@ -1813,7 +1829,7 @@ void tipc_link_send_proto_msg(struct tipc_link *l_ptr, u32 msg_typ, * Note that network plane id propagates through the network, and may * change at any time. The node with lowest address rules */ -static void link_recv_proto_msg(struct tipc_link *l_ptr, struct sk_buff *buf) +static void tipc_link_proto_rcv(struct tipc_link *l_ptr, struct sk_buff *buf) { u32 rec_gap = 0; u32 max_pkt_info; @@ -1932,8 +1948,8 @@ static void link_recv_proto_msg(struct tipc_link *l_ptr, struct sk_buff *buf) msg_last_bcast(msg)); if (rec_gap || (msg_probe(msg))) { - tipc_link_send_proto_msg(l_ptr, STATE_MSG, - 0, rec_gap, 0, 0, max_pkt_ack); + tipc_link_proto_xmit(l_ptr, STATE_MSG, 0, rec_gap, 0, + 0, max_pkt_ack); } if (msg_seq_gap(msg)) { l_ptr->stats.recv_nacks++; @@ -1972,7 +1988,7 @@ static void tipc_link_tunnel_xmit(struct tipc_link *l_ptr, } skb_copy_to_linear_data(buf, tunnel_hdr, INT_H_SIZE); skb_copy_to_linear_data_offset(buf, INT_H_SIZE, msg, length); - tipc_link_send_buf(tunnel, buf); + __tipc_link_xmit(tunnel, buf); } @@ -2005,7 +2021,7 @@ void tipc_link_failover_send_queue(struct tipc_link *l_ptr) if (buf) { skb_copy_to_linear_data(buf, &tunnel_hdr, INT_H_SIZE); msg_set_size(&tunnel_hdr, INT_H_SIZE); - tipc_link_send_buf(tunnel, buf); + __tipc_link_xmit(tunnel, buf); } else { pr_warn("%sunable to send changeover msg\n", link_co_err); @@ -2039,7 +2055,7 @@ void tipc_link_failover_send_queue(struct tipc_link *l_ptr) } } -/* tipc_link_dup_send_queue(): A second link has become active. Tunnel a +/* tipc_link_dup_queue_xmit(): A second link has become active. Tunnel a * duplicate of the first link's send queue via the new link. This way, we * are guaranteed that currently queued packets from a socket are delivered * before future traffic from the same socket, even if this is using the @@ -2048,7 +2064,7 @@ void tipc_link_failover_send_queue(struct tipc_link *l_ptr) * and sequence order is preserved per sender/receiver socket pair. * Owner node is locked. */ -void tipc_link_dup_send_queue(struct tipc_link *l_ptr, +void tipc_link_dup_queue_xmit(struct tipc_link *l_ptr, struct tipc_link *tunnel) { struct sk_buff *iter; @@ -2078,7 +2094,7 @@ void tipc_link_dup_send_queue(struct tipc_link *l_ptr, skb_copy_to_linear_data(outbuf, &tunnel_hdr, INT_H_SIZE); skb_copy_to_linear_data_offset(outbuf, INT_H_SIZE, iter->data, length); - tipc_link_send_buf(tunnel, outbuf); + __tipc_link_xmit(tunnel, outbuf); if (!tipc_link_is_up(l_ptr)) return; iter = iter->next; @@ -2105,89 +2121,114 @@ static struct sk_buff *buf_extract(struct sk_buff *skb, u32 from_pos) return eb; } -/* tipc_link_tunnel_rcv(): Receive a tunneled packet, sent - * via other link as result of a failover (ORIGINAL_MSG) or - * a new active link (DUPLICATE_MSG). Failover packets are - * returned to the active link for delivery upwards. + + +/* tipc_link_dup_rcv(): Receive a tunnelled DUPLICATE_MSG packet. + * Owner node is locked. + */ +static void tipc_link_dup_rcv(struct tipc_link *l_ptr, + struct sk_buff *t_buf) +{ + struct sk_buff *buf; + + if (!tipc_link_is_up(l_ptr)) + return; + + buf = buf_extract(t_buf, INT_H_SIZE); + if (buf == NULL) { + pr_warn("%sfailed to extract inner dup pkt\n", link_co_err); + return; + } + + /* Add buffer to deferred queue, if applicable: */ + link_handle_out_of_seq_msg(l_ptr, buf); +} + +/* tipc_link_failover_rcv(): Receive a tunnelled ORIGINAL_MSG packet * Owner node is locked. */ -static int tipc_link_tunnel_rcv(struct tipc_link **l_ptr, - struct sk_buff **buf) +static struct sk_buff *tipc_link_failover_rcv(struct tipc_link *l_ptr, + struct sk_buff *t_buf) { - struct sk_buff *tunnel_buf = *buf; - struct tipc_link *dest_link; + struct tipc_msg *t_msg = buf_msg(t_buf); + struct sk_buff *buf = NULL; struct tipc_msg *msg; - struct tipc_msg *tunnel_msg = buf_msg(tunnel_buf); - u32 msg_typ = msg_type(tunnel_msg); - u32 msg_count = msg_msgcnt(tunnel_msg); - u32 bearer_id = msg_bearer_id(tunnel_msg); - if (bearer_id >= MAX_BEARERS) - goto exit; - dest_link = (*l_ptr)->owner->links[bearer_id]; - if (!dest_link) - goto exit; - if (dest_link == *l_ptr) { - pr_err("Unexpected changeover message on link <%s>\n", - (*l_ptr)->name); - goto exit; - } - *l_ptr = dest_link; - msg = msg_get_wrapped(tunnel_msg); + if (tipc_link_is_up(l_ptr)) + tipc_link_reset(l_ptr); - if (msg_typ == DUPLICATE_MSG) { - if (less(msg_seqno(msg), mod(dest_link->next_in_no))) - goto exit; - *buf = buf_extract(tunnel_buf, INT_H_SIZE); - if (*buf == NULL) { - pr_warn("%sduplicate msg dropped\n", link_co_err); + /* First failover packet? */ + if (l_ptr->exp_msg_count == START_CHANGEOVER) + l_ptr->exp_msg_count = msg_msgcnt(t_msg); + + /* Should there be an inner packet? */ + if (l_ptr->exp_msg_count) { + l_ptr->exp_msg_count--; + buf = buf_extract(t_buf, INT_H_SIZE); + if (buf == NULL) { + pr_warn("%sno inner failover pkt\n", link_co_err); goto exit; } - kfree_skb(tunnel_buf); - return 1; - } + msg = buf_msg(buf); - /* First original message ?: */ - if (tipc_link_is_up(dest_link)) { - pr_info("%s<%s>, changeover initiated by peer\n", link_rst_msg, - dest_link->name); - tipc_link_reset(dest_link); - dest_link->exp_msg_count = msg_count; - if (!msg_count) - goto exit; - } else if (dest_link->exp_msg_count == START_CHANGEOVER) { - dest_link->exp_msg_count = msg_count; - if (!msg_count) + if (less(msg_seqno(msg), l_ptr->reset_checkpoint)) { + kfree_skb(buf); + buf = NULL; goto exit; + } + if (msg_user(msg) == MSG_FRAGMENTER) { + l_ptr->stats.recv_fragments++; + tipc_link_frag_rcv(&l_ptr->reasm_head, + &l_ptr->reasm_tail, + &buf); + } } +exit: + if ((l_ptr->exp_msg_count == 0) && (l_ptr->flags & LINK_STOPPED)) { + tipc_node_detach_link(l_ptr->owner, l_ptr); + kfree(l_ptr); + } + return buf; +} + +/* tipc_link_tunnel_rcv(): Receive a tunnelled packet, sent + * via other link as result of a failover (ORIGINAL_MSG) or + * a new active link (DUPLICATE_MSG). Failover packets are + * returned to the active link for delivery upwards. + * Owner node is locked. + */ +static int tipc_link_tunnel_rcv(struct tipc_node *n_ptr, + struct sk_buff **buf) +{ + struct sk_buff *t_buf = *buf; + struct tipc_link *l_ptr; + struct tipc_msg *t_msg = buf_msg(t_buf); + u32 bearer_id = msg_bearer_id(t_msg); + + *buf = NULL; - /* Receive original message */ - if (dest_link->exp_msg_count == 0) { - pr_warn("%sgot too many tunnelled messages\n", link_co_err); + if (bearer_id >= MAX_BEARERS) goto exit; - } - dest_link->exp_msg_count--; - if (less(msg_seqno(msg), dest_link->reset_checkpoint)) { + + l_ptr = n_ptr->links[bearer_id]; + if (!l_ptr) goto exit; - } else { - *buf = buf_extract(tunnel_buf, INT_H_SIZE); - if (*buf != NULL) { - kfree_skb(tunnel_buf); - return 1; - } else { - pr_warn("%soriginal msg dropped\n", link_co_err); - } - } + + if (msg_type(t_msg) == DUPLICATE_MSG) + tipc_link_dup_rcv(l_ptr, t_buf); + else if (msg_type(t_msg) == ORIGINAL_MSG) + *buf = tipc_link_failover_rcv(l_ptr, t_buf); + else + pr_warn("%sunknown tunnel pkt received\n", link_co_err); exit: - *buf = NULL; - kfree_skb(tunnel_buf); - return 0; + kfree_skb(t_buf); + return *buf != NULL; } /* * Bundler functionality: */ -void tipc_link_recv_bundle(struct sk_buff *buf) +void tipc_link_bundle_rcv(struct sk_buff *buf) { u32 msgcount = msg_msgcnt(buf_msg(buf)); u32 pos = INT_H_SIZE; @@ -2210,11 +2251,11 @@ void tipc_link_recv_bundle(struct sk_buff *buf) */ /* - * link_send_long_buf: Entry for buffers needing fragmentation. + * tipc_link_frag_xmit: Entry for buffers needing fragmentation. * The buffer is complete, inclusive total message length. * Returns user data length. */ -static int link_send_long_buf(struct tipc_link *l_ptr, struct sk_buff *buf) +static int tipc_link_frag_xmit(struct tipc_link *l_ptr, struct sk_buff *buf) { struct sk_buff *buf_chain = NULL; struct sk_buff *buf_chain_tail = (struct sk_buff *)&buf_chain; @@ -2277,12 +2318,11 @@ static int link_send_long_buf(struct tipc_link *l_ptr, struct sk_buff *buf) return dsz; } -/* - * tipc_link_recv_fragment(): Called with node lock on. Returns +/* tipc_link_frag_rcv(): Called with node lock on. Returns * the reassembled buffer if message is complete. */ -int tipc_link_recv_fragment(struct sk_buff **head, struct sk_buff **tail, - struct sk_buff **fbuf) +int tipc_link_frag_rcv(struct sk_buff **head, struct sk_buff **tail, + struct sk_buff **fbuf) { struct sk_buff *frag = *fbuf; struct tipc_msg *msg = buf_msg(frag); @@ -2296,6 +2336,7 @@ int tipc_link_recv_fragment(struct sk_buff **head, struct sk_buff **tail, goto out_free; *head = frag; skb_frag_list_init(*head); + *fbuf = NULL; return 0; } else if (*head && skb_try_coalesce(*head, frag, &headstolen, &delta)) { @@ -2315,10 +2356,12 @@ int tipc_link_recv_fragment(struct sk_buff **head, struct sk_buff **tail, *tail = *head = NULL; return LINK_REASM_COMPLETE; } + *fbuf = NULL; return 0; out_free: pr_warn_ratelimited("Link unable to reassemble fragmented message\n"); kfree_skb(*fbuf); + *fbuf = NULL; return LINK_REASM_ERROR; } @@ -2352,35 +2395,40 @@ void tipc_link_set_queue_limits(struct tipc_link *l_ptr, u32 window) l_ptr->queue_limit[MSG_FRAGMENTER] = 4000; } -/** - * link_find_link - locate link by name - * @name: ptr to link name string - * @node: ptr to area to be filled with ptr to associated node - * +/* tipc_link_find_owner - locate owner node of link by link's name + * @name: pointer to link name string + * @bearer_id: pointer to index in 'node->links' array where the link was found. * Caller must hold 'tipc_net_lock' to ensure node and bearer are not deleted; * this also prevents link deletion. * - * Returns pointer to link (or 0 if invalid link name). + * Returns pointer to node owning the link, or 0 if no matching link is found. */ -static struct tipc_link *link_find_link(const char *name, - struct tipc_node **node) +static struct tipc_node *tipc_link_find_owner(const char *link_name, + unsigned int *bearer_id) { struct tipc_link *l_ptr; struct tipc_node *n_ptr; + struct tipc_node *tmp_n_ptr; + struct tipc_node *found_node = 0; + int i; - list_for_each_entry(n_ptr, &tipc_node_list, list) { + *bearer_id = 0; + list_for_each_entry_safe(n_ptr, tmp_n_ptr, &tipc_node_list, list) { + tipc_node_lock(n_ptr); for (i = 0; i < MAX_BEARERS; i++) { l_ptr = n_ptr->links[i]; - if (l_ptr && !strcmp(l_ptr->name, name)) - goto found; + if (l_ptr && !strcmp(l_ptr->name, link_name)) { + *bearer_id = i; + found_node = n_ptr; + break; + } } + tipc_node_unlock(n_ptr); + if (found_node) + break; } - l_ptr = NULL; - n_ptr = NULL; -found: - *node = n_ptr; - return l_ptr; + return found_node; } /** @@ -2422,32 +2470,33 @@ static int link_cmd_set_value(const char *name, u32 new_value, u16 cmd) struct tipc_link *l_ptr; struct tipc_bearer *b_ptr; struct tipc_media *m_ptr; + int bearer_id; int res = 0; - l_ptr = link_find_link(name, &node); - if (l_ptr) { - /* - * acquire node lock for tipc_link_send_proto_msg(). - * see "TIPC locking policy" in net.c. - */ + node = tipc_link_find_owner(name, &bearer_id); + if (node) { tipc_node_lock(node); - switch (cmd) { - case TIPC_CMD_SET_LINK_TOL: - link_set_supervision_props(l_ptr, new_value); - tipc_link_send_proto_msg(l_ptr, - STATE_MSG, 0, 0, new_value, 0, 0); - break; - case TIPC_CMD_SET_LINK_PRI: - l_ptr->priority = new_value; - tipc_link_send_proto_msg(l_ptr, - STATE_MSG, 0, 0, 0, new_value, 0); - break; - case TIPC_CMD_SET_LINK_WINDOW: - tipc_link_set_queue_limits(l_ptr, new_value); - break; - default: - res = -EINVAL; - break; + l_ptr = node->links[bearer_id]; + + if (l_ptr) { + switch (cmd) { + case TIPC_CMD_SET_LINK_TOL: + link_set_supervision_props(l_ptr, new_value); + tipc_link_proto_xmit(l_ptr, STATE_MSG, 0, 0, + new_value, 0, 0); + break; + case TIPC_CMD_SET_LINK_PRI: + l_ptr->priority = new_value; + tipc_link_proto_xmit(l_ptr, STATE_MSG, 0, 0, + 0, new_value, 0); + break; + case TIPC_CMD_SET_LINK_WINDOW: + tipc_link_set_queue_limits(l_ptr, new_value); + break; + default: + res = -EINVAL; + break; + } } tipc_node_unlock(node); return res; @@ -2542,6 +2591,7 @@ struct sk_buff *tipc_link_cmd_reset_stats(const void *req_tlv_area, int req_tlv_ char *link_name; struct tipc_link *l_ptr; struct tipc_node *node; + unsigned int bearer_id; if (!TLV_CHECK(req_tlv_area, req_tlv_space, TIPC_TLV_LINK_NAME)) return tipc_cfg_reply_error_string(TIPC_CFG_TLV_ERROR); @@ -2552,15 +2602,19 @@ struct sk_buff *tipc_link_cmd_reset_stats(const void *req_tlv_area, int req_tlv_ return tipc_cfg_reply_error_string("link not found"); return tipc_cfg_reply_none(); } - read_lock_bh(&tipc_net_lock); - l_ptr = link_find_link(link_name, &node); - if (!l_ptr) { + node = tipc_link_find_owner(link_name, &bearer_id); + if (!node) { read_unlock_bh(&tipc_net_lock); return tipc_cfg_reply_error_string("link not found"); } - tipc_node_lock(node); + l_ptr = node->links[bearer_id]; + if (!l_ptr) { + tipc_node_unlock(node); + read_unlock_bh(&tipc_net_lock); + return tipc_cfg_reply_error_string("link not found"); + } link_reset_statistics(l_ptr); tipc_node_unlock(node); read_unlock_bh(&tipc_net_lock); @@ -2590,18 +2644,27 @@ static int tipc_link_stats(const char *name, char *buf, const u32 buf_size) struct tipc_node *node; char *status; u32 profile_total = 0; + unsigned int bearer_id; int ret; if (!strcmp(name, tipc_bclink_name)) return tipc_bclink_stats(buf, buf_size); read_lock_bh(&tipc_net_lock); - l = link_find_link(name, &node); - if (!l) { + node = tipc_link_find_owner(name, &bearer_id); + if (!node) { read_unlock_bh(&tipc_net_lock); return 0; } tipc_node_lock(node); + + l = node->links[bearer_id]; + if (!l) { + tipc_node_unlock(node); + read_unlock_bh(&tipc_net_lock); + return 0; + } + s = &l->stats; if (tipc_link_is_active(l)) diff --git a/net/tipc/link.h b/net/tipc/link.h index 3b6aa65b608c..8c0b49b5b2ee 100644 --- a/net/tipc/link.h +++ b/net/tipc/link.h @@ -1,7 +1,7 @@ /* * net/tipc/link.h: Include file for TIPC link code * - * Copyright (c) 1995-2006, Ericsson AB + * Copyright (c) 1995-2006, 2013, Ericsson AB * Copyright (c) 2004-2005, 2010-2011, Wind River Systems * All rights reserved. * @@ -40,27 +40,28 @@ #include "msg.h" #include "node.h" -/* - * Link reassembly status codes +/* Link reassembly status codes */ #define LINK_REASM_ERROR -1 #define LINK_REASM_COMPLETE 1 -/* - * Out-of-range value for link sequence numbers +/* Out-of-range value for link sequence numbers */ #define INVALID_LINK_SEQ 0x10000 -/* - * Link states +/* Link working states */ #define WORKING_WORKING 560810u #define WORKING_UNKNOWN 560811u #define RESET_UNKNOWN 560812u #define RESET_RESET 560813u -/* - * Starting value for maximum packet size negotiation on unicast links +/* Link endpoint execution states + */ +#define LINK_STARTED 0x0001 +#define LINK_STOPPED 0x0002 + +/* Starting value for maximum packet size negotiation on unicast links * (unless bearer MTU is less) */ #define MAX_PKT_DEFAULT 1500 @@ -102,8 +103,7 @@ struct tipc_stats { * @media_addr: media address to use when sending messages over link * @timer: link timer * @owner: pointer to peer node - * @link_list: adjacent links in bearer's list of links - * @started: indicates if link has been started + * @flags: execution state flags for link endpoint instance * @checkpoint: reference point for triggering link continuity checking * @peer_session: link session # being used by peer end of link * @peer_bearer_id: bearer id used by link's peer endpoint @@ -149,10 +149,9 @@ struct tipc_link { struct tipc_media_addr media_addr; struct timer_list timer; struct tipc_node *owner; - struct list_head link_list; /* Management and link supervision data */ - int started; + unsigned int flags; u32 checkpoint; u32 peer_session; u32 peer_bearer_id; @@ -215,10 +214,9 @@ struct tipc_port; struct tipc_link *tipc_link_create(struct tipc_node *n_ptr, struct tipc_bearer *b_ptr, const struct tipc_media_addr *media_addr); -void tipc_link_delete(struct tipc_link *l_ptr); +void tipc_link_delete_list(unsigned int bearer_id, bool shutting_down); void tipc_link_failover_send_queue(struct tipc_link *l_ptr); -void tipc_link_dup_send_queue(struct tipc_link *l_ptr, - struct tipc_link *dest); +void tipc_link_dup_queue_xmit(struct tipc_link *l_ptr, struct tipc_link *dest); void tipc_link_reset_fragments(struct tipc_link *l_ptr); int tipc_link_is_up(struct tipc_link *l_ptr); int tipc_link_is_active(struct tipc_link *l_ptr); @@ -231,23 +229,24 @@ struct sk_buff *tipc_link_cmd_show_stats(const void *req_tlv_area, struct sk_buff *tipc_link_cmd_reset_stats(const void *req_tlv_area, int req_tlv_space); void tipc_link_reset(struct tipc_link *l_ptr); -int tipc_link_send(struct sk_buff *buf, u32 dest, u32 selector); -void tipc_link_send_names(struct list_head *message_list, u32 dest); +void tipc_link_reset_list(unsigned int bearer_id); +int tipc_link_xmit(struct sk_buff *buf, u32 dest, u32 selector); +void tipc_link_names_xmit(struct list_head *message_list, u32 dest); +int __tipc_link_xmit(struct tipc_link *l_ptr, struct sk_buff *buf); int tipc_link_send_buf(struct tipc_link *l_ptr, struct sk_buff *buf); u32 tipc_link_get_max_pkt(u32 dest, u32 selector); -int tipc_link_send_sections_fast(struct tipc_port *sender, - struct iovec const *msg_sect, - unsigned int len, u32 destnode); -void tipc_link_recv_bundle(struct sk_buff *buf); -int tipc_link_recv_fragment(struct sk_buff **reasm_head, - struct sk_buff **reasm_tail, - struct sk_buff **fbuf); -void tipc_link_send_proto_msg(struct tipc_link *l_ptr, u32 msg_typ, int prob, - u32 gap, u32 tolerance, u32 priority, - u32 acked_mtu); +int tipc_link_iovec_xmit_fast(struct tipc_port *sender, + struct iovec const *msg_sect, + unsigned int len, u32 destnode); +void tipc_link_bundle_rcv(struct sk_buff *buf); +int tipc_link_frag_rcv(struct sk_buff **reasm_head, + struct sk_buff **reasm_tail, + struct sk_buff **fbuf); +void tipc_link_proto_xmit(struct tipc_link *l_ptr, u32 msg_typ, int prob, + u32 gap, u32 tolerance, u32 priority, u32 acked_mtu); void tipc_link_push_queue(struct tipc_link *l_ptr); u32 tipc_link_defer_pkt(struct sk_buff **head, struct sk_buff **tail, - struct sk_buff *buf); + struct sk_buff *buf); void tipc_link_wakeup_ports(struct tipc_link *l_ptr, int all); void tipc_link_set_queue_limits(struct tipc_link *l_ptr, u32 window); void tipc_link_retransmit(struct tipc_link *l_ptr, diff --git a/net/tipc/name_distr.c b/net/tipc/name_distr.c index e0d08055754e..893c49a3d98a 100644 --- a/net/tipc/name_distr.c +++ b/net/tipc/name_distr.c @@ -138,7 +138,7 @@ static void named_cluster_distribute(struct sk_buff *buf) if (!buf_copy) break; msg_set_destnode(buf_msg(buf_copy), n_ptr->addr); - tipc_link_send(buf_copy, n_ptr->addr, n_ptr->addr); + tipc_link_xmit(buf_copy, n_ptr->addr, n_ptr->addr); } } @@ -262,7 +262,7 @@ void tipc_named_node_up(unsigned long nodearg) named_distribute(&message_list, node, &publ_zone, max_item_buf); read_unlock_bh(&tipc_nametbl_lock); - tipc_link_send_names(&message_list, node); + tipc_link_names_xmit(&message_list, node); } /** @@ -293,9 +293,9 @@ static void named_purge_publ(struct publication *publ) } /** - * tipc_named_recv - process name table update message sent by another node + * tipc_named_rcv - process name table update message sent by another node */ -void tipc_named_recv(struct sk_buff *buf) +void tipc_named_rcv(struct sk_buff *buf) { struct publication *publ; struct tipc_msg *msg = buf_msg(buf); diff --git a/net/tipc/name_distr.h b/net/tipc/name_distr.h index 1e41bdd4f255..9b312ccfd43e 100644 --- a/net/tipc/name_distr.h +++ b/net/tipc/name_distr.h @@ -42,7 +42,7 @@ void tipc_named_publish(struct publication *publ); void tipc_named_withdraw(struct publication *publ); void tipc_named_node_up(unsigned long node); -void tipc_named_recv(struct sk_buff *buf); +void tipc_named_rcv(struct sk_buff *buf); void tipc_named_reinit(void); #endif diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c index 92a1533af4e0..48302be175ce 100644 --- a/net/tipc/name_table.c +++ b/net/tipc/name_table.c @@ -945,9 +945,6 @@ void tipc_nametbl_stop(void) { u32 i; - if (!table.types) - return; - /* Verify name table is empty, then release it */ write_lock_bh(&tipc_nametbl_lock); for (i = 0; i < TIPC_NAMETBL_SIZE; i++) { diff --git a/net/tipc/net.c b/net/tipc/net.c index 7d305ecc09c2..31b606e3916c 100644 --- a/net/tipc/net.c +++ b/net/tipc/net.c @@ -146,19 +146,19 @@ void tipc_net_route_msg(struct sk_buff *buf) if (tipc_in_scope(dnode, tipc_own_addr)) { if (msg_isdata(msg)) { if (msg_mcast(msg)) - tipc_port_recv_mcast(buf, NULL); + tipc_port_mcast_rcv(buf, NULL); else if (msg_destport(msg)) - tipc_port_recv_msg(buf); + tipc_port_rcv(buf); else net_route_named_msg(buf); return; } switch (msg_user(msg)) { case NAME_DISTRIBUTOR: - tipc_named_recv(buf); + tipc_named_rcv(buf); break; case CONN_MANAGER: - tipc_port_recv_proto_msg(buf); + tipc_port_proto_rcv(buf); break; default: kfree_skb(buf); @@ -168,7 +168,7 @@ void tipc_net_route_msg(struct sk_buff *buf) /* Handle message for another node */ skb_trim(buf, msg_size(msg)); - tipc_link_send(buf, dnode, msg_link_selector(msg)); + tipc_link_xmit(buf, dnode, msg_link_selector(msg)); } void tipc_net_start(u32 addr) diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c index 9f72a6376362..3aaf73de9e2d 100644 --- a/net/tipc/netlink.c +++ b/net/tipc/netlink.c @@ -83,8 +83,6 @@ static struct genl_ops tipc_genl_ops[] = { }, }; -static int tipc_genl_family_registered; - int tipc_netlink_start(void) { int res; @@ -94,16 +92,10 @@ int tipc_netlink_start(void) pr_err("Failed to register netlink interface\n"); return res; } - - tipc_genl_family_registered = 1; return 0; } void tipc_netlink_stop(void) { - if (!tipc_genl_family_registered) - return; - genl_unregister_family(&tipc_genl_family); - tipc_genl_family_registered = 0; } diff --git a/net/tipc/node.c b/net/tipc/node.c index efe4d41bf11b..0b0f6c7da965 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -162,7 +162,7 @@ void tipc_node_link_up(struct tipc_node *n_ptr, struct tipc_link *l_ptr) pr_info("New link <%s> becomes standby\n", l_ptr->name); return; } - tipc_link_dup_send_queue(active[0], l_ptr); + tipc_link_dup_queue_xmit(active[0], l_ptr); if (l_ptr->priority == active[0]->priority) { active[0] = l_ptr; return; @@ -249,9 +249,15 @@ void tipc_node_attach_link(struct tipc_node *n_ptr, struct tipc_link *l_ptr) void tipc_node_detach_link(struct tipc_node *n_ptr, struct tipc_link *l_ptr) { - n_ptr->links[l_ptr->b_ptr->identity] = NULL; - atomic_dec(&tipc_num_links); - n_ptr->link_cnt--; + int i; + + for (i = 0; i < MAX_BEARERS; i++) { + if (l_ptr != n_ptr->links[i]) + continue; + n_ptr->links[i] = NULL; + atomic_dec(&tipc_num_links); + n_ptr->link_cnt--; + } } static void node_established_contact(struct tipc_node *n_ptr) diff --git a/net/tipc/port.c b/net/tipc/port.c index b742b2654525..5c14c7801ee6 100644 --- a/net/tipc/port.c +++ b/net/tipc/port.c @@ -1,7 +1,7 @@ /* * net/tipc/port.c: TIPC port code * - * Copyright (c) 1992-2007, Ericsson AB + * Copyright (c) 1992-2007, 2014, Ericsson AB * Copyright (c) 2004-2008, 2010-2013, Wind River Systems * All rights reserved. * @@ -38,6 +38,7 @@ #include "config.h" #include "port.h" #include "name_table.h" +#include "socket.h" /* Connection management: */ #define PROBING_INTERVAL 3600000 /* [ms] => 1 h */ @@ -54,17 +55,6 @@ static struct sk_buff *port_build_self_abort_msg(struct tipc_port *, u32 err); static struct sk_buff *port_build_peer_abort_msg(struct tipc_port *, u32 err); static void port_timeout(unsigned long ref); - -static u32 port_peernode(struct tipc_port *p_ptr) -{ - return msg_destnode(&p_ptr->phdr); -} - -static u32 port_peerport(struct tipc_port *p_ptr) -{ - return msg_destport(&p_ptr->phdr); -} - /** * tipc_port_peer_msg - verify message was sent by connected port's peer * @@ -76,33 +66,32 @@ int tipc_port_peer_msg(struct tipc_port *p_ptr, struct tipc_msg *msg) u32 peernode; u32 orignode; - if (msg_origport(msg) != port_peerport(p_ptr)) + if (msg_origport(msg) != tipc_port_peerport(p_ptr)) return 0; orignode = msg_orignode(msg); - peernode = port_peernode(p_ptr); + peernode = tipc_port_peernode(p_ptr); return (orignode == peernode) || (!orignode && (peernode == tipc_own_addr)) || (!peernode && (orignode == tipc_own_addr)); } /** - * tipc_multicast - send a multicast message to local and remote destinations + * tipc_port_mcast_xmit - send a multicast message to local and remote + * destinations */ -int tipc_multicast(u32 ref, struct tipc_name_seq const *seq, - struct iovec const *msg_sect, unsigned int len) +int tipc_port_mcast_xmit(struct tipc_port *oport, + struct tipc_name_seq const *seq, + struct iovec const *msg_sect, + unsigned int len) { struct tipc_msg *hdr; struct sk_buff *buf; struct sk_buff *ibuf = NULL; struct tipc_port_list dports = {0, NULL, }; - struct tipc_port *oport = tipc_port_deref(ref); int ext_targets; int res; - if (unlikely(!oport)) - return -EINVAL; - /* Create multicast message */ hdr = &oport->phdr; msg_set_type(hdr, TIPC_MCAST_MSG); @@ -131,7 +120,7 @@ int tipc_multicast(u32 ref, struct tipc_name_seq const *seq, return -ENOMEM; } } - res = tipc_bclink_send_msg(buf); + res = tipc_bclink_xmit(buf); if ((res < 0) && (dports.count != 0)) kfree_skb(ibuf); } else { @@ -140,7 +129,7 @@ int tipc_multicast(u32 ref, struct tipc_name_seq const *seq, if (res >= 0) { if (ibuf) - tipc_port_recv_mcast(ibuf, &dports); + tipc_port_mcast_rcv(ibuf, &dports); } else { tipc_port_list_free(&dports); } @@ -148,11 +137,11 @@ int tipc_multicast(u32 ref, struct tipc_name_seq const *seq, } /** - * tipc_port_recv_mcast - deliver multicast message to all destination ports + * tipc_port_mcast_rcv - deliver multicast message to all destination ports * * If there is no port list, perform a lookup to create one */ -void tipc_port_recv_mcast(struct sk_buff *buf, struct tipc_port_list *dp) +void tipc_port_mcast_rcv(struct sk_buff *buf, struct tipc_port_list *dp) { struct tipc_msg *msg; struct tipc_port_list dports = {0, NULL, }; @@ -176,7 +165,7 @@ void tipc_port_recv_mcast(struct sk_buff *buf, struct tipc_port_list *dp) msg_set_destnode(msg, tipc_own_addr); if (dp->count == 1) { msg_set_destport(msg, dp->ports[0]); - tipc_port_recv_msg(buf); + tipc_port_rcv(buf); tipc_port_list_free(dp); return; } @@ -191,7 +180,7 @@ void tipc_port_recv_mcast(struct sk_buff *buf, struct tipc_port_list *dp) if ((index == 0) && (cnt != 0)) item = item->next; msg_set_destport(buf_msg(b), item->ports[index]); - tipc_port_recv_msg(b); + tipc_port_rcv(b); } } exit: @@ -199,40 +188,32 @@ exit: tipc_port_list_free(dp); } -/** - * tipc_createport - create a generic TIPC port + +void tipc_port_wakeup(struct tipc_port *port) +{ + tipc_sock_wakeup(tipc_port_to_sock(port)); +} + +/* tipc_port_init - intiate TIPC port and lock it * - * Returns pointer to (locked) TIPC port, or NULL if unable to create it + * Returns obtained reference if initialization is successful, zero otherwise */ -struct tipc_port *tipc_createport(struct sock *sk, - u32 (*dispatcher)(struct tipc_port *, - struct sk_buff *), - void (*wakeup)(struct tipc_port *), - const u32 importance) +u32 tipc_port_init(struct tipc_port *p_ptr, + const unsigned int importance) { - struct tipc_port *p_ptr; struct tipc_msg *msg; u32 ref; - p_ptr = kzalloc(sizeof(*p_ptr), GFP_ATOMIC); - if (!p_ptr) { - pr_warn("Port creation failed, no memory\n"); - return NULL; - } ref = tipc_ref_acquire(p_ptr, &p_ptr->lock); if (!ref) { - pr_warn("Port creation failed, ref. table exhausted\n"); - kfree(p_ptr); - return NULL; + pr_warn("Port registration failed, ref. table exhausted\n"); + return 0; } - p_ptr->sk = sk; p_ptr->max_pkt = MAX_PKT_DEFAULT; p_ptr->ref = ref; INIT_LIST_HEAD(&p_ptr->wait_list); INIT_LIST_HEAD(&p_ptr->subscription.nodesub_list); - p_ptr->dispatcher = dispatcher; - p_ptr->wakeup = wakeup; k_init_timer(&p_ptr->timer, (Handler)port_timeout, ref); INIT_LIST_HEAD(&p_ptr->publications); INIT_LIST_HEAD(&p_ptr->port_list); @@ -248,10 +229,10 @@ struct tipc_port *tipc_createport(struct sock *sk, msg_set_origport(msg, ref); list_add_tail(&p_ptr->port_list, &ports); spin_unlock_bh(&tipc_port_list_lock); - return p_ptr; + return ref; } -int tipc_deleteport(struct tipc_port *p_ptr) +void tipc_port_destroy(struct tipc_port *p_ptr) { struct sk_buff *buf = NULL; @@ -272,67 +253,7 @@ int tipc_deleteport(struct tipc_port *p_ptr) list_del(&p_ptr->wait_list); spin_unlock_bh(&tipc_port_list_lock); k_term_timer(&p_ptr->timer); - kfree(p_ptr); tipc_net_route_msg(buf); - return 0; -} - -static int port_unreliable(struct tipc_port *p_ptr) -{ - return msg_src_droppable(&p_ptr->phdr); -} - -int tipc_portunreliable(u32 ref, unsigned int *isunreliable) -{ - struct tipc_port *p_ptr; - - p_ptr = tipc_port_lock(ref); - if (!p_ptr) - return -EINVAL; - *isunreliable = port_unreliable(p_ptr); - tipc_port_unlock(p_ptr); - return 0; -} - -int tipc_set_portunreliable(u32 ref, unsigned int isunreliable) -{ - struct tipc_port *p_ptr; - - p_ptr = tipc_port_lock(ref); - if (!p_ptr) - return -EINVAL; - msg_set_src_droppable(&p_ptr->phdr, (isunreliable != 0)); - tipc_port_unlock(p_ptr); - return 0; -} - -static int port_unreturnable(struct tipc_port *p_ptr) -{ - return msg_dest_droppable(&p_ptr->phdr); -} - -int tipc_portunreturnable(u32 ref, unsigned int *isunrejectable) -{ - struct tipc_port *p_ptr; - - p_ptr = tipc_port_lock(ref); - if (!p_ptr) - return -EINVAL; - *isunrejectable = port_unreturnable(p_ptr); - tipc_port_unlock(p_ptr); - return 0; -} - -int tipc_set_portunreturnable(u32 ref, unsigned int isunrejectable) -{ - struct tipc_port *p_ptr; - - p_ptr = tipc_port_lock(ref); - if (!p_ptr) - return -EINVAL; - msg_set_dest_droppable(&p_ptr->phdr, (isunrejectable != 0)); - tipc_port_unlock(p_ptr); - return 0; } /* @@ -350,8 +271,8 @@ static struct sk_buff *port_build_proto_msg(struct tipc_port *p_ptr, if (buf) { msg = buf_msg(buf); tipc_msg_init(msg, CONN_MANAGER, type, INT_H_SIZE, - port_peernode(p_ptr)); - msg_set_destport(msg, port_peerport(p_ptr)); + tipc_port_peernode(p_ptr)); + msg_set_destport(msg, tipc_port_peerport(p_ptr)); msg_set_origport(msg, p_ptr->ref); msg_set_msgcnt(msg, ack); } @@ -422,17 +343,17 @@ int tipc_reject_msg(struct sk_buff *buf, u32 err) /* send returned message & dispose of rejected message */ src_node = msg_prevnode(msg); if (in_own_node(src_node)) - tipc_port_recv_msg(rbuf); + tipc_port_rcv(rbuf); else - tipc_link_send(rbuf, src_node, msg_link_selector(rmsg)); + tipc_link_xmit(rbuf, src_node, msg_link_selector(rmsg)); exit: kfree_skb(buf); return data_sz; } -int tipc_port_reject_sections(struct tipc_port *p_ptr, struct tipc_msg *hdr, - struct iovec const *msg_sect, unsigned int len, - int err) +int tipc_port_iovec_reject(struct tipc_port *p_ptr, struct tipc_msg *hdr, + struct iovec const *msg_sect, unsigned int len, + int err) { struct sk_buff *buf; int res; @@ -519,7 +440,7 @@ static struct sk_buff *port_build_peer_abort_msg(struct tipc_port *p_ptr, u32 er return buf; } -void tipc_port_recv_proto_msg(struct sk_buff *buf) +void tipc_port_proto_rcv(struct sk_buff *buf) { struct tipc_msg *msg = buf_msg(buf); struct tipc_port *p_ptr; @@ -547,13 +468,12 @@ void tipc_port_recv_proto_msg(struct sk_buff *buf) /* Process protocol message sent by peer */ switch (msg_type(msg)) { case CONN_ACK: - wakeable = tipc_port_congested(p_ptr) && p_ptr->congested && - p_ptr->wakeup; + wakeable = tipc_port_congested(p_ptr) && p_ptr->congested; p_ptr->acked += msg_msgcnt(msg); if (!tipc_port_congested(p_ptr)) { p_ptr->congested = 0; if (wakeable) - p_ptr->wakeup(p_ptr); + tipc_port_wakeup(p_ptr); } break; case CONN_PROBE: @@ -584,8 +504,8 @@ static int port_print(struct tipc_port *p_ptr, char *buf, int len, int full_id) ret = tipc_snprintf(buf, len, "%-10u:", p_ptr->ref); if (p_ptr->connected) { - u32 dport = port_peerport(p_ptr); - u32 destnode = port_peernode(p_ptr); + u32 dport = tipc_port_peerport(p_ptr); + u32 destnode = tipc_port_peernode(p_ptr); ret += tipc_snprintf(buf + ret, len - ret, " connected to <%u.%u.%u:%u>", @@ -673,34 +593,6 @@ void tipc_acknowledge(u32 ref, u32 ack) tipc_net_route_msg(buf); } -int tipc_portimportance(u32 ref, unsigned int *importance) -{ - struct tipc_port *p_ptr; - - p_ptr = tipc_port_lock(ref); - if (!p_ptr) - return -EINVAL; - *importance = (unsigned int)msg_importance(&p_ptr->phdr); - tipc_port_unlock(p_ptr); - return 0; -} - -int tipc_set_portimportance(u32 ref, unsigned int imp) -{ - struct tipc_port *p_ptr; - - if (imp > TIPC_CRITICAL_IMPORTANCE) - return -EINVAL; - - p_ptr = tipc_port_lock(ref); - if (!p_ptr) - return -EINVAL; - msg_set_importance(&p_ptr->phdr, (u32)imp); - tipc_port_unlock(p_ptr); - return 0; -} - - int tipc_publish(struct tipc_port *p_ptr, unsigned int scope, struct tipc_name_seq const *seq) { @@ -760,7 +652,7 @@ int tipc_withdraw(struct tipc_port *p_ptr, unsigned int scope, return res; } -int tipc_connect(u32 ref, struct tipc_portid const *peer) +int tipc_port_connect(u32 ref, struct tipc_portid const *peer) { struct tipc_port *p_ptr; int res; @@ -768,17 +660,17 @@ int tipc_connect(u32 ref, struct tipc_portid const *peer) p_ptr = tipc_port_lock(ref); if (!p_ptr) return -EINVAL; - res = __tipc_connect(ref, p_ptr, peer); + res = __tipc_port_connect(ref, p_ptr, peer); tipc_port_unlock(p_ptr); return res; } /* - * __tipc_connect - connect to a remote peer + * __tipc_port_connect - connect to a remote peer * * Port must be locked. */ -int __tipc_connect(u32 ref, struct tipc_port *p_ptr, +int __tipc_port_connect(u32 ref, struct tipc_port *p_ptr, struct tipc_portid const *peer) { struct tipc_msg *msg; @@ -815,7 +707,7 @@ exit: * * Port must be locked. */ -int __tipc_disconnect(struct tipc_port *tp_ptr) +int __tipc_port_disconnect(struct tipc_port *tp_ptr) { if (tp_ptr->connected) { tp_ptr->connected = 0; @@ -828,10 +720,10 @@ int __tipc_disconnect(struct tipc_port *tp_ptr) } /* - * tipc_disconnect(): Disconnect port form peer. + * tipc_port_disconnect(): Disconnect port form peer. * This is a node local operation. */ -int tipc_disconnect(u32 ref) +int tipc_port_disconnect(u32 ref) { struct tipc_port *p_ptr; int res; @@ -839,15 +731,15 @@ int tipc_disconnect(u32 ref) p_ptr = tipc_port_lock(ref); if (!p_ptr) return -EINVAL; - res = __tipc_disconnect(p_ptr); + res = __tipc_port_disconnect(p_ptr); tipc_port_unlock(p_ptr); return res; } /* - * tipc_shutdown(): Send a SHUTDOWN msg to peer and disconnect + * tipc_port_shutdown(): Send a SHUTDOWN msg to peer and disconnect */ -int tipc_shutdown(u32 ref) +int tipc_port_shutdown(u32 ref) { struct tipc_port *p_ptr; struct sk_buff *buf = NULL; @@ -859,13 +751,13 @@ int tipc_shutdown(u32 ref) buf = port_build_peer_abort_msg(p_ptr, TIPC_CONN_SHUTDOWN); tipc_port_unlock(p_ptr); tipc_net_route_msg(buf); - return tipc_disconnect(ref); + return tipc_port_disconnect(ref); } /** - * tipc_port_recv_msg - receive message from lower layer and deliver to port user + * tipc_port_rcv - receive message from lower layer and deliver to port user */ -int tipc_port_recv_msg(struct sk_buff *buf) +int tipc_port_rcv(struct sk_buff *buf) { struct tipc_port *p_ptr; struct tipc_msg *msg = buf_msg(buf); @@ -882,7 +774,7 @@ int tipc_port_recv_msg(struct sk_buff *buf) /* validate destination & pass to port, otherwise reject message */ p_ptr = tipc_port_lock(destport); if (likely(p_ptr)) { - err = p_ptr->dispatcher(p_ptr, buf); + err = tipc_sk_rcv(&tipc_port_to_sock(p_ptr)->sk, buf); tipc_port_unlock(p_ptr); if (likely(!err)) return dsz; @@ -894,43 +786,43 @@ int tipc_port_recv_msg(struct sk_buff *buf) } /* - * tipc_port_recv_sections(): Concatenate and deliver sectioned - * message for this node. + * tipc_port_iovec_rcv: Concatenate and deliver sectioned + * message for this node. */ -static int tipc_port_recv_sections(struct tipc_port *sender, - struct iovec const *msg_sect, - unsigned int len) +static int tipc_port_iovec_rcv(struct tipc_port *sender, + struct iovec const *msg_sect, + unsigned int len) { struct sk_buff *buf; int res; res = tipc_msg_build(&sender->phdr, msg_sect, len, MAX_MSG_SIZE, &buf); if (likely(buf)) - tipc_port_recv_msg(buf); + tipc_port_rcv(buf); return res; } /** * tipc_send - send message sections on connection */ -int tipc_send(u32 ref, struct iovec const *msg_sect, unsigned int len) +int tipc_send(struct tipc_port *p_ptr, + struct iovec const *msg_sect, + unsigned int len) { - struct tipc_port *p_ptr; u32 destnode; int res; - p_ptr = tipc_port_deref(ref); - if (!p_ptr || !p_ptr->connected) + if (!p_ptr->connected) return -EINVAL; p_ptr->congested = 1; if (!tipc_port_congested(p_ptr)) { - destnode = port_peernode(p_ptr); + destnode = tipc_port_peernode(p_ptr); if (likely(!in_own_node(destnode))) - res = tipc_link_send_sections_fast(p_ptr, msg_sect, - len, destnode); + res = tipc_link_iovec_xmit_fast(p_ptr, msg_sect, len, + destnode); else - res = tipc_port_recv_sections(p_ptr, msg_sect, len); + res = tipc_port_iovec_rcv(p_ptr, msg_sect, len); if (likely(res != -ELINKCONG)) { p_ptr->congested = 0; @@ -939,7 +831,7 @@ int tipc_send(u32 ref, struct iovec const *msg_sect, unsigned int len) return res; } } - if (port_unreliable(p_ptr)) { + if (tipc_port_unreliable(p_ptr)) { p_ptr->congested = 0; return len; } @@ -949,17 +841,18 @@ int tipc_send(u32 ref, struct iovec const *msg_sect, unsigned int len) /** * tipc_send2name - send message sections to port name */ -int tipc_send2name(u32 ref, struct tipc_name const *name, unsigned int domain, - struct iovec const *msg_sect, unsigned int len) +int tipc_send2name(struct tipc_port *p_ptr, + struct tipc_name const *name, + unsigned int domain, + struct iovec const *msg_sect, + unsigned int len) { - struct tipc_port *p_ptr; struct tipc_msg *msg; u32 destnode = domain; u32 destport; int res; - p_ptr = tipc_port_deref(ref); - if (!p_ptr || p_ptr->connected) + if (p_ptr->connected) return -EINVAL; msg = &p_ptr->phdr; @@ -974,39 +867,39 @@ int tipc_send2name(u32 ref, struct tipc_name const *name, unsigned int domain, if (likely(destport || destnode)) { if (likely(in_own_node(destnode))) - res = tipc_port_recv_sections(p_ptr, msg_sect, len); + res = tipc_port_iovec_rcv(p_ptr, msg_sect, len); else if (tipc_own_addr) - res = tipc_link_send_sections_fast(p_ptr, msg_sect, - len, destnode); + res = tipc_link_iovec_xmit_fast(p_ptr, msg_sect, len, + destnode); else - res = tipc_port_reject_sections(p_ptr, msg, msg_sect, - len, TIPC_ERR_NO_NODE); + res = tipc_port_iovec_reject(p_ptr, msg, msg_sect, + len, TIPC_ERR_NO_NODE); if (likely(res != -ELINKCONG)) { if (res > 0) p_ptr->sent++; return res; } - if (port_unreliable(p_ptr)) { + if (tipc_port_unreliable(p_ptr)) return len; - } + return -ELINKCONG; } - return tipc_port_reject_sections(p_ptr, msg, msg_sect, len, - TIPC_ERR_NO_NAME); + return tipc_port_iovec_reject(p_ptr, msg, msg_sect, len, + TIPC_ERR_NO_NAME); } /** * tipc_send2port - send message sections to port identity */ -int tipc_send2port(u32 ref, struct tipc_portid const *dest, - struct iovec const *msg_sect, unsigned int len) +int tipc_send2port(struct tipc_port *p_ptr, + struct tipc_portid const *dest, + struct iovec const *msg_sect, + unsigned int len) { - struct tipc_port *p_ptr; struct tipc_msg *msg; int res; - p_ptr = tipc_port_deref(ref); - if (!p_ptr || p_ptr->connected) + if (p_ptr->connected) return -EINVAL; msg = &p_ptr->phdr; @@ -1017,20 +910,20 @@ int tipc_send2port(u32 ref, struct tipc_portid const *dest, msg_set_hdr_sz(msg, BASIC_H_SIZE); if (in_own_node(dest->node)) - res = tipc_port_recv_sections(p_ptr, msg_sect, len); + res = tipc_port_iovec_rcv(p_ptr, msg_sect, len); else if (tipc_own_addr) - res = tipc_link_send_sections_fast(p_ptr, msg_sect, len, - dest->node); + res = tipc_link_iovec_xmit_fast(p_ptr, msg_sect, len, + dest->node); else - res = tipc_port_reject_sections(p_ptr, msg, msg_sect, len, + res = tipc_port_iovec_reject(p_ptr, msg, msg_sect, len, TIPC_ERR_NO_NODE); if (likely(res != -ELINKCONG)) { if (res > 0) p_ptr->sent++; return res; } - if (port_unreliable(p_ptr)) { + if (tipc_port_unreliable(p_ptr)) return len; - } + return -ELINKCONG; } diff --git a/net/tipc/port.h b/net/tipc/port.h index 34f12bd4074e..a00397393bd1 100644 --- a/net/tipc/port.h +++ b/net/tipc/port.h @@ -1,7 +1,7 @@ /* * net/tipc/port.h: Include file for TIPC port code * - * Copyright (c) 1994-2007, Ericsson AB + * Copyright (c) 1994-2007, 2014, Ericsson AB * Copyright (c) 2004-2007, 2010-2013, Wind River Systems * All rights reserved. * @@ -48,7 +48,6 @@ /** * struct tipc_port - TIPC port structure - * @sk: pointer to socket handle * @lock: pointer to spinlock for controlling access to port * @connected: non-zero if port is currently connected to a peer port * @conn_type: TIPC type used when connection was established @@ -60,8 +59,6 @@ * @ref: unique reference to port in TIPC object registry * @phdr: preformatted message header used when sending messages * @port_list: adjacent ports in TIPC's global list of ports - * @dispatcher: ptr to routine which handles received messages - * @wakeup: ptr to routine to call when port is no longer congested * @wait_list: adjacent ports in list of ports waiting on link congestion * @waiting_pkts: * @sent: # of non-empty messages sent by port @@ -74,7 +71,6 @@ * @subscription: "node down" subscription used to terminate failed connections */ struct tipc_port { - struct sock *sk; spinlock_t *lock; int connected; u32 conn_type; @@ -86,8 +82,6 @@ struct tipc_port { u32 ref; struct tipc_msg phdr; struct list_head port_list; - u32 (*dispatcher)(struct tipc_port *, struct sk_buff *); - void (*wakeup)(struct tipc_port *); struct list_head wait_list; u32 waiting_pkts; u32 sent; @@ -106,68 +100,71 @@ struct tipc_port_list; /* * TIPC port manipulation routines */ -struct tipc_port *tipc_createport(struct sock *sk, - u32 (*dispatcher)(struct tipc_port *, - struct sk_buff *), - void (*wakeup)(struct tipc_port *), - const u32 importance); +u32 tipc_port_init(struct tipc_port *p_ptr, + const unsigned int importance); int tipc_reject_msg(struct sk_buff *buf, u32 err); void tipc_acknowledge(u32 port_ref, u32 ack); -int tipc_deleteport(struct tipc_port *p_ptr); - -int tipc_portimportance(u32 portref, unsigned int *importance); -int tipc_set_portimportance(u32 portref, unsigned int importance); - -int tipc_portunreliable(u32 portref, unsigned int *isunreliable); -int tipc_set_portunreliable(u32 portref, unsigned int isunreliable); - -int tipc_portunreturnable(u32 portref, unsigned int *isunreturnable); -int tipc_set_portunreturnable(u32 portref, unsigned int isunreturnable); +void tipc_port_destroy(struct tipc_port *p_ptr); int tipc_publish(struct tipc_port *p_ptr, unsigned int scope, struct tipc_name_seq const *name_seq); + int tipc_withdraw(struct tipc_port *p_ptr, unsigned int scope, struct tipc_name_seq const *name_seq); -int tipc_connect(u32 portref, struct tipc_portid const *port); +int tipc_port_connect(u32 portref, struct tipc_portid const *port); -int tipc_disconnect(u32 portref); +int tipc_port_disconnect(u32 portref); -int tipc_shutdown(u32 ref); +int tipc_port_shutdown(u32 ref); +void tipc_port_wakeup(struct tipc_port *port); /* * The following routines require that the port be locked on entry */ -int __tipc_disconnect(struct tipc_port *tp_ptr); -int __tipc_connect(u32 ref, struct tipc_port *p_ptr, +int __tipc_port_disconnect(struct tipc_port *tp_ptr); +int __tipc_port_connect(u32 ref, struct tipc_port *p_ptr, struct tipc_portid const *peer); int tipc_port_peer_msg(struct tipc_port *p_ptr, struct tipc_msg *msg); /* * TIPC messaging routines */ -int tipc_port_recv_msg(struct sk_buff *buf); -int tipc_send(u32 portref, struct iovec const *msg_sect, unsigned int len); - -int tipc_send2name(u32 portref, struct tipc_name const *name, u32 domain, - struct iovec const *msg_sect, unsigned int len); +int tipc_port_rcv(struct sk_buff *buf); + +int tipc_send(struct tipc_port *port, + struct iovec const *msg_sect, + unsigned int len); + +int tipc_send2name(struct tipc_port *port, + struct tipc_name const *name, + u32 domain, + struct iovec const *msg_sect, + unsigned int len); + +int tipc_send2port(struct tipc_port *port, + struct tipc_portid const *dest, + struct iovec const *msg_sect, + unsigned int len); + +int tipc_port_mcast_xmit(struct tipc_port *port, + struct tipc_name_seq const *seq, + struct iovec const *msg, + unsigned int len); + +int tipc_port_iovec_reject(struct tipc_port *p_ptr, + struct tipc_msg *hdr, + struct iovec const *msg_sect, + unsigned int len, + int err); -int tipc_send2port(u32 portref, struct tipc_portid const *dest, - struct iovec const *msg_sect, unsigned int len); - -int tipc_multicast(u32 portref, struct tipc_name_seq const *seq, - struct iovec const *msg, unsigned int len); - -int tipc_port_reject_sections(struct tipc_port *p_ptr, struct tipc_msg *hdr, - struct iovec const *msg_sect, unsigned int len, - int err); struct sk_buff *tipc_port_get_ports(void); -void tipc_port_recv_proto_msg(struct sk_buff *buf); -void tipc_port_recv_mcast(struct sk_buff *buf, struct tipc_port_list *dp); +void tipc_port_proto_rcv(struct sk_buff *buf); +void tipc_port_mcast_rcv(struct sk_buff *buf, struct tipc_port_list *dp); void tipc_port_reinit(void); /** @@ -188,14 +185,53 @@ static inline void tipc_port_unlock(struct tipc_port *p_ptr) spin_unlock_bh(p_ptr->lock); } -static inline struct tipc_port *tipc_port_deref(u32 ref) +static inline int tipc_port_congested(struct tipc_port *p_ptr) { - return (struct tipc_port *)tipc_ref_deref(ref); + return (p_ptr->sent - p_ptr->acked) >= (TIPC_FLOW_CONTROL_WIN * 2); } -static inline int tipc_port_congested(struct tipc_port *p_ptr) + +static inline u32 tipc_port_peernode(struct tipc_port *p_ptr) { - return (p_ptr->sent - p_ptr->acked) >= (TIPC_FLOW_CONTROL_WIN * 2); + return msg_destnode(&p_ptr->phdr); +} + +static inline u32 tipc_port_peerport(struct tipc_port *p_ptr) +{ + return msg_destport(&p_ptr->phdr); +} + +static inline bool tipc_port_unreliable(struct tipc_port *port) +{ + return msg_src_droppable(&port->phdr) != 0; +} + +static inline void tipc_port_set_unreliable(struct tipc_port *port, + bool unreliable) +{ + msg_set_src_droppable(&port->phdr, unreliable ? 1 : 0); +} + +static inline bool tipc_port_unreturnable(struct tipc_port *port) +{ + return msg_dest_droppable(&port->phdr) != 0; +} + +static inline void tipc_port_set_unreturnable(struct tipc_port *port, + bool unreturnable) +{ + msg_set_dest_droppable(&port->phdr, unreturnable ? 1 : 0); +} + + +static inline int tipc_port_importance(struct tipc_port *port) +{ + return msg_importance(&port->phdr); +} + +static inline void tipc_port_set_importance(struct tipc_port *port, int imp) +{ + msg_set_importance(&port->phdr, (u32)imp); } #endif diff --git a/net/tipc/ref.c b/net/tipc/ref.c index 2a2a938dc22c..3d4ecd754eee 100644 --- a/net/tipc/ref.c +++ b/net/tipc/ref.c @@ -89,7 +89,7 @@ struct ref_table { static struct ref_table tipc_ref_table; -static DEFINE_RWLOCK(ref_table_lock); +static DEFINE_SPINLOCK(ref_table_lock); /** * tipc_ref_table_init - create reference table for objects @@ -126,9 +126,6 @@ int tipc_ref_table_init(u32 requested_size, u32 start) */ void tipc_ref_table_stop(void) { - if (!tipc_ref_table.entries) - return; - vfree(tipc_ref_table.entries); tipc_ref_table.entries = NULL; } @@ -162,7 +159,7 @@ u32 tipc_ref_acquire(void *object, spinlock_t **lock) } /* take a free entry, if available; otherwise initialize a new entry */ - write_lock_bh(&ref_table_lock); + spin_lock_bh(&ref_table_lock); if (tipc_ref_table.first_free) { index = tipc_ref_table.first_free; entry = &(tipc_ref_table.entries[index]); @@ -178,7 +175,7 @@ u32 tipc_ref_acquire(void *object, spinlock_t **lock) } else { ref = 0; } - write_unlock_bh(&ref_table_lock); + spin_unlock_bh(&ref_table_lock); /* * Grab the lock so no one else can modify this entry @@ -219,7 +216,7 @@ void tipc_ref_discard(u32 ref) index = ref & index_mask; entry = &(tipc_ref_table.entries[index]); - write_lock_bh(&ref_table_lock); + spin_lock_bh(&ref_table_lock); if (!entry->object) { pr_err("Attempt to discard ref. to non-existent obj\n"); @@ -245,7 +242,7 @@ void tipc_ref_discard(u32 ref) tipc_ref_table.last_free = index; exit: - write_unlock_bh(&ref_table_lock); + spin_unlock_bh(&ref_table_lock); } /** @@ -267,20 +264,3 @@ void *tipc_ref_lock(u32 ref) } return NULL; } - - -/** - * tipc_ref_deref - return pointer referenced object (without locking it) - */ -void *tipc_ref_deref(u32 ref) -{ - if (likely(tipc_ref_table.entries)) { - struct reference *entry; - - entry = &tipc_ref_table.entries[ref & - tipc_ref_table.index_mask]; - if (likely(entry->ref == ref)) - return entry->object; - } - return NULL; -} diff --git a/net/tipc/ref.h b/net/tipc/ref.h index 5bc8e7ab84de..d01aa1df63b8 100644 --- a/net/tipc/ref.h +++ b/net/tipc/ref.h @@ -44,6 +44,5 @@ u32 tipc_ref_acquire(void *object, spinlock_t **lock); void tipc_ref_discard(u32 ref); void *tipc_ref_lock(u32 ref); -void *tipc_ref_deref(u32 ref); #endif diff --git a/net/tipc/server.c b/net/tipc/server.c index b635ca347a87..373979789a73 100644 --- a/net/tipc/server.c +++ b/net/tipc/server.c @@ -573,7 +573,6 @@ int tipc_server_start(struct tipc_server *s) kmem_cache_destroy(s->rcvbuf_cache); return ret; } - s->enabled = 1; return ret; } @@ -583,10 +582,6 @@ void tipc_server_stop(struct tipc_server *s) int total = 0; int id; - if (!s->enabled) - return; - - s->enabled = 0; spin_lock_bh(&s->idr_lock); for (id = 0; total < s->idr_in_use; id++) { con = idr_find(&s->conn_idr, id); diff --git a/net/tipc/server.h b/net/tipc/server.h index 98b23f20bc0f..be817b0b547e 100644 --- a/net/tipc/server.h +++ b/net/tipc/server.h @@ -56,7 +56,6 @@ * @name: server name * @imp: message importance * @type: socket type - * @enabled: identify whether server is launched or not */ struct tipc_server { struct idr conn_idr; @@ -74,7 +73,6 @@ struct tipc_server { const char name[TIPC_SERVER_NAME_LEN]; int imp; int type; - int enabled; }; int tipc_conn_sendmsg(struct tipc_server *s, int conid, diff --git a/net/tipc/socket.c b/net/tipc/socket.c index aab4948f0aff..2a89bdb331b5 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -1,7 +1,7 @@ /* * net/tipc/socket.c: TIPC socket API * - * Copyright (c) 2001-2007, 2012 Ericsson AB + * Copyright (c) 2001-2007, 2012-2014, Ericsson AB * Copyright (c) 2004-2008, 2010-2013, Wind River Systems * All rights reserved. * @@ -38,30 +38,17 @@ #include "port.h" #include <linux/export.h> -#include <net/sock.h> #define SS_LISTENING -1 /* socket is listening */ #define SS_READY -2 /* socket is connectionless */ #define CONN_TIMEOUT_DEFAULT 8000 /* default connect timeout = 8s */ -struct tipc_sock { - struct sock sk; - struct tipc_port *p; - struct tipc_portid peer_name; - unsigned int conn_timeout; -}; - -#define tipc_sk(sk) ((struct tipc_sock *)(sk)) -#define tipc_sk_port(sk) (tipc_sk(sk)->p) - static int backlog_rcv(struct sock *sk, struct sk_buff *skb); -static u32 dispatch(struct tipc_port *tport, struct sk_buff *buf); -static void wakeupdispatch(struct tipc_port *tport); static void tipc_data_ready(struct sock *sk, int len); static void tipc_write_space(struct sock *sk); -static int release(struct socket *sock); -static int accept(struct socket *sock, struct socket *new_sock, int flags); +static int tipc_release(struct socket *sock); +static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags); static const struct proto_ops packet_ops; static const struct proto_ops stream_ops; @@ -70,8 +57,6 @@ static const struct proto_ops msg_ops; static struct proto tipc_proto; static struct proto tipc_proto_kern; -static int sockets_enabled; - /* * Revised TIPC socket locking policy: * @@ -117,6 +102,8 @@ static int sockets_enabled; * - port reference */ +#include "socket.h" + /** * advance_rx_queue - discard first buffer in socket receive queue * @@ -152,13 +139,15 @@ static void reject_rx_queue(struct sock *sk) * * Returns 0 on success, errno otherwise */ -static int tipc_sk_create(struct net *net, struct socket *sock, int protocol, - int kern) +static int tipc_sk_create(struct net *net, struct socket *sock, + int protocol, int kern) { const struct proto_ops *ops; socket_state state; struct sock *sk; - struct tipc_port *tp_ptr; + struct tipc_sock *tsk; + struct tipc_port *port; + u32 ref; /* Validate arguments */ if (unlikely(protocol != 0)) @@ -191,10 +180,12 @@ static int tipc_sk_create(struct net *net, struct socket *sock, int protocol, if (sk == NULL) return -ENOMEM; - /* Allocate TIPC port for socket to use */ - tp_ptr = tipc_createport(sk, &dispatch, &wakeupdispatch, - TIPC_LOW_IMPORTANCE); - if (unlikely(!tp_ptr)) { + tsk = tipc_sk(sk); + port = &tsk->port; + + ref = tipc_port_init(port, TIPC_LOW_IMPORTANCE); + if (!ref) { + pr_warn("Socket registration failed, ref. table exhausted\n"); sk_free(sk); return -ENOMEM; } @@ -208,17 +199,14 @@ static int tipc_sk_create(struct net *net, struct socket *sock, int protocol, sk->sk_rcvbuf = sysctl_tipc_rmem[1]; sk->sk_data_ready = tipc_data_ready; sk->sk_write_space = tipc_write_space; - tipc_sk(sk)->p = tp_ptr; tipc_sk(sk)->conn_timeout = CONN_TIMEOUT_DEFAULT; - - spin_unlock_bh(tp_ptr->lock); + tipc_port_unlock(port); if (sock->state == SS_READY) { - tipc_set_portunreturnable(tp_ptr->ref, 1); + tipc_port_set_unreturnable(port, true); if (sock->type == SOCK_DGRAM) - tipc_set_portunreliable(tp_ptr->ref, 1); + tipc_port_set_unreliable(port, true); } - return 0; } @@ -256,7 +244,7 @@ int tipc_sock_create_local(int type, struct socket **res) */ void tipc_sock_release_local(struct socket *sock) { - release(sock); + tipc_release(sock); sock->ops = NULL; sock_release(sock); } @@ -282,7 +270,7 @@ int tipc_sock_accept_local(struct socket *sock, struct socket **newsock, if (ret < 0) return ret; - ret = accept(sock, *newsock, flags); + ret = tipc_accept(sock, *newsock, flags); if (ret < 0) { sock_release(*newsock); return ret; @@ -292,7 +280,7 @@ int tipc_sock_accept_local(struct socket *sock, struct socket **newsock, } /** - * release - destroy a TIPC socket + * tipc_release - destroy a TIPC socket * @sock: socket to destroy * * This routine cleans up any messages that are still queued on the socket. @@ -307,10 +295,11 @@ int tipc_sock_accept_local(struct socket *sock, struct socket **newsock, * * Returns 0 on success, errno otherwise */ -static int release(struct socket *sock) +static int tipc_release(struct socket *sock) { struct sock *sk = sock->sk; - struct tipc_port *tport; + struct tipc_sock *tsk; + struct tipc_port *port; struct sk_buff *buf; int res; @@ -321,7 +310,8 @@ static int release(struct socket *sock) if (sk == NULL) return 0; - tport = tipc_sk_port(sk); + tsk = tipc_sk(sk); + port = &tsk->port; lock_sock(sk); /* @@ -338,17 +328,16 @@ static int release(struct socket *sock) if ((sock->state == SS_CONNECTING) || (sock->state == SS_CONNECTED)) { sock->state = SS_DISCONNECTING; - tipc_disconnect(tport->ref); + tipc_port_disconnect(port->ref); } tipc_reject_msg(buf, TIPC_ERR_NO_PORT); } } - /* - * Delete TIPC port; this ensures no more messages are queued - * (also disconnects an active connection & sends a 'FIN-' to peer) + /* Destroy TIPC port; also disconnects an active connection and + * sends a 'FIN-' to peer. */ - res = tipc_deleteport(tport); + tipc_port_destroy(port); /* Discard any remaining (connection-based) messages in receive queue */ __skb_queue_purge(&sk->sk_receive_queue); @@ -364,7 +353,7 @@ static int release(struct socket *sock) } /** - * bind - associate or disassocate TIPC name(s) with a socket + * tipc_bind - associate or disassocate TIPC name(s) with a socket * @sock: socket structure * @uaddr: socket address describing name(s) and desired operation * @uaddr_len: size of socket address data structure @@ -378,16 +367,17 @@ static int release(struct socket *sock) * NOTE: This routine doesn't need to take the socket lock since it doesn't * access any non-constant socket information. */ -static int bind(struct socket *sock, struct sockaddr *uaddr, int uaddr_len) +static int tipc_bind(struct socket *sock, struct sockaddr *uaddr, + int uaddr_len) { struct sock *sk = sock->sk; struct sockaddr_tipc *addr = (struct sockaddr_tipc *)uaddr; - struct tipc_port *tport = tipc_sk_port(sock->sk); + struct tipc_sock *tsk = tipc_sk(sk); int res = -EINVAL; lock_sock(sk); if (unlikely(!uaddr_len)) { - res = tipc_withdraw(tport, 0, NULL); + res = tipc_withdraw(&tsk->port, 0, NULL); goto exit; } @@ -415,15 +405,15 @@ static int bind(struct socket *sock, struct sockaddr *uaddr, int uaddr_len) } res = (addr->scope > 0) ? - tipc_publish(tport, addr->scope, &addr->addr.nameseq) : - tipc_withdraw(tport, -addr->scope, &addr->addr.nameseq); + tipc_publish(&tsk->port, addr->scope, &addr->addr.nameseq) : + tipc_withdraw(&tsk->port, -addr->scope, &addr->addr.nameseq); exit: release_sock(sk); return res; } /** - * get_name - get port ID of socket or peer socket + * tipc_getname - get port ID of socket or peer socket * @sock: socket structure * @uaddr: area for returned socket address * @uaddr_len: area for returned length of socket address @@ -435,21 +425,21 @@ exit: * accesses socket information that is unchanging (or which changes in * a completely predictable manner). */ -static int get_name(struct socket *sock, struct sockaddr *uaddr, - int *uaddr_len, int peer) +static int tipc_getname(struct socket *sock, struct sockaddr *uaddr, + int *uaddr_len, int peer) { struct sockaddr_tipc *addr = (struct sockaddr_tipc *)uaddr; - struct tipc_sock *tsock = tipc_sk(sock->sk); + struct tipc_sock *tsk = tipc_sk(sock->sk); memset(addr, 0, sizeof(*addr)); if (peer) { if ((sock->state != SS_CONNECTED) && ((peer != 2) || (sock->state != SS_DISCONNECTING))) return -ENOTCONN; - addr->addr.id.ref = tsock->peer_name.ref; - addr->addr.id.node = tsock->peer_name.node; + addr->addr.id.ref = tipc_port_peerport(&tsk->port); + addr->addr.id.node = tipc_port_peernode(&tsk->port); } else { - addr->addr.id.ref = tsock->p->ref; + addr->addr.id.ref = tsk->port.ref; addr->addr.id.node = tipc_own_addr; } @@ -463,7 +453,7 @@ static int get_name(struct socket *sock, struct sockaddr *uaddr, } /** - * poll - read and possibly block on pollmask + * tipc_poll - read and possibly block on pollmask * @file: file structure associated with the socket * @sock: socket for which to calculate the poll bits * @wait: ??? @@ -502,22 +492,23 @@ static int get_name(struct socket *sock, struct sockaddr *uaddr, * imply that the operation will succeed, merely that it should be performed * and will not block. */ -static unsigned int poll(struct file *file, struct socket *sock, - poll_table *wait) +static unsigned int tipc_poll(struct file *file, struct socket *sock, + poll_table *wait) { struct sock *sk = sock->sk; + struct tipc_sock *tsk = tipc_sk(sk); u32 mask = 0; sock_poll_wait(file, sk_sleep(sk), wait); switch ((int)sock->state) { case SS_UNCONNECTED: - if (!tipc_sk_port(sk)->congested) + if (!tsk->port.congested) mask |= POLLOUT; break; case SS_READY: case SS_CONNECTED: - if (!tipc_sk_port(sk)->congested) + if (!tsk->port.congested) mask |= POLLOUT; /* fall thru' */ case SS_CONNECTING: @@ -567,7 +558,7 @@ static int dest_name_check(struct sockaddr_tipc *dest, struct msghdr *m) static int tipc_wait_for_sndmsg(struct socket *sock, long *timeo_p) { struct sock *sk = sock->sk; - struct tipc_port *tport = tipc_sk_port(sk); + struct tipc_sock *tsk = tipc_sk(sk); DEFINE_WAIT(wait); int done; @@ -583,14 +574,15 @@ static int tipc_wait_for_sndmsg(struct socket *sock, long *timeo_p) return sock_intr_errno(*timeo_p); prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); - done = sk_wait_event(sk, timeo_p, !tport->congested); + done = sk_wait_event(sk, timeo_p, !tsk->port.congested); finish_wait(sk_sleep(sk), &wait); } while (!done); return 0; } + /** - * send_msg - send message in connectionless manner + * tipc_sendmsg - send message in connectionless manner * @iocb: if NULL, indicates that socket lock is already held * @sock: socket structure * @m: message to send @@ -603,11 +595,12 @@ static int tipc_wait_for_sndmsg(struct socket *sock, long *timeo_p) * * Returns the number of bytes sent on success, or errno otherwise */ -static int send_msg(struct kiocb *iocb, struct socket *sock, - struct msghdr *m, size_t total_len) +static int tipc_sendmsg(struct kiocb *iocb, struct socket *sock, + struct msghdr *m, size_t total_len) { struct sock *sk = sock->sk; - struct tipc_port *tport = tipc_sk_port(sk); + struct tipc_sock *tsk = tipc_sk(sk); + struct tipc_port *port = &tsk->port; DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name); int needs_conn; long timeo; @@ -634,13 +627,13 @@ static int send_msg(struct kiocb *iocb, struct socket *sock, res = -EISCONN; goto exit; } - if (tport->published) { + if (tsk->port.published) { res = -EOPNOTSUPP; goto exit; } if (dest->addrtype == TIPC_ADDR_NAME) { - tport->conn_type = dest->addr.name.name.type; - tport->conn_instance = dest->addr.name.name.instance; + tsk->port.conn_type = dest->addr.name.name.type; + tsk->port.conn_instance = dest->addr.name.name.instance; } /* Abort any pending connection attempts (very unlikely) */ @@ -653,13 +646,13 @@ static int send_msg(struct kiocb *iocb, struct socket *sock, res = dest_name_check(dest, m); if (res) break; - res = tipc_send2name(tport->ref, + res = tipc_send2name(port, &dest->addr.name.name, dest->addr.name.domain, m->msg_iov, total_len); } else if (dest->addrtype == TIPC_ADDR_ID) { - res = tipc_send2port(tport->ref, + res = tipc_send2port(port, &dest->addr.id, m->msg_iov, total_len); @@ -671,10 +664,10 @@ static int send_msg(struct kiocb *iocb, struct socket *sock, res = dest_name_check(dest, m); if (res) break; - res = tipc_multicast(tport->ref, - &dest->addr.nameseq, - m->msg_iov, - total_len); + res = tipc_port_mcast_xmit(port, + &dest->addr.nameseq, + m->msg_iov, + total_len); } if (likely(res != -ELINKCONG)) { if (needs_conn && (res >= 0)) @@ -695,7 +688,8 @@ exit: static int tipc_wait_for_sndpkt(struct socket *sock, long *timeo_p) { struct sock *sk = sock->sk; - struct tipc_port *tport = tipc_sk_port(sk); + struct tipc_sock *tsk = tipc_sk(sk); + struct tipc_port *port = &tsk->port; DEFINE_WAIT(wait); int done; @@ -714,14 +708,14 @@ static int tipc_wait_for_sndpkt(struct socket *sock, long *timeo_p) prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); done = sk_wait_event(sk, timeo_p, - (!tport->congested || !tport->connected)); + (!port->congested || !port->connected)); finish_wait(sk_sleep(sk), &wait); } while (!done); return 0; } /** - * send_packet - send a connection-oriented message + * tipc_send_packet - send a connection-oriented message * @iocb: if NULL, indicates that socket lock is already held * @sock: socket structure * @m: message to send @@ -731,18 +725,18 @@ static int tipc_wait_for_sndpkt(struct socket *sock, long *timeo_p) * * Returns the number of bytes sent on success, or errno otherwise */ -static int send_packet(struct kiocb *iocb, struct socket *sock, - struct msghdr *m, size_t total_len) +static int tipc_send_packet(struct kiocb *iocb, struct socket *sock, + struct msghdr *m, size_t total_len) { struct sock *sk = sock->sk; - struct tipc_port *tport = tipc_sk_port(sk); + struct tipc_sock *tsk = tipc_sk(sk); DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name); int res = -EINVAL; long timeo; /* Handle implied connection establishment */ if (unlikely(dest)) - return send_msg(iocb, sock, m, total_len); + return tipc_sendmsg(iocb, sock, m, total_len); if (total_len > TIPC_MAX_USER_MSG_SIZE) return -EMSGSIZE; @@ -760,7 +754,7 @@ static int send_packet(struct kiocb *iocb, struct socket *sock, timeo = sock_sndtimeo(sk, m->msg_flags & MSG_DONTWAIT); do { - res = tipc_send(tport->ref, m->msg_iov, total_len); + res = tipc_send(&tsk->port, m->msg_iov, total_len); if (likely(res != -ELINKCONG)) break; res = tipc_wait_for_sndpkt(sock, &timeo); @@ -774,7 +768,7 @@ exit: } /** - * send_stream - send stream-oriented data + * tipc_send_stream - send stream-oriented data * @iocb: (unused) * @sock: socket structure * @m: data to send @@ -785,11 +779,11 @@ exit: * Returns the number of bytes sent on success (or partial success), * or errno if no data sent */ -static int send_stream(struct kiocb *iocb, struct socket *sock, - struct msghdr *m, size_t total_len) +static int tipc_send_stream(struct kiocb *iocb, struct socket *sock, + struct msghdr *m, size_t total_len) { struct sock *sk = sock->sk; - struct tipc_port *tport = tipc_sk_port(sk); + struct tipc_sock *tsk = tipc_sk(sk); struct msghdr my_msg; struct iovec my_iov; struct iovec *curr_iov; @@ -806,7 +800,7 @@ static int send_stream(struct kiocb *iocb, struct socket *sock, /* Handle special cases where there is no connection */ if (unlikely(sock->state != SS_CONNECTED)) { if (sock->state == SS_UNCONNECTED) - res = send_packet(NULL, sock, m, total_len); + res = tipc_send_packet(NULL, sock, m, total_len); else res = sock->state == SS_DISCONNECTING ? -EPIPE : -ENOTCONN; goto exit; @@ -837,21 +831,22 @@ static int send_stream(struct kiocb *iocb, struct socket *sock, my_msg.msg_name = NULL; bytes_sent = 0; - hdr_size = msg_hdr_sz(&tport->phdr); + hdr_size = msg_hdr_sz(&tsk->port.phdr); while (curr_iovlen--) { curr_start = curr_iov->iov_base; curr_left = curr_iov->iov_len; while (curr_left) { - bytes_to_send = tport->max_pkt - hdr_size; + bytes_to_send = tsk->port.max_pkt - hdr_size; if (bytes_to_send > TIPC_MAX_USER_MSG_SIZE) bytes_to_send = TIPC_MAX_USER_MSG_SIZE; if (curr_left < bytes_to_send) bytes_to_send = curr_left; my_iov.iov_base = curr_start; my_iov.iov_len = bytes_to_send; - res = send_packet(NULL, sock, &my_msg, bytes_to_send); + res = tipc_send_packet(NULL, sock, &my_msg, + bytes_to_send); if (res < 0) { if (bytes_sent) res = bytes_sent; @@ -872,27 +867,25 @@ exit: /** * auto_connect - complete connection setup to a remote port - * @sock: socket structure + * @tsk: tipc socket structure * @msg: peer's response message * * Returns 0 on success, errno otherwise */ -static int auto_connect(struct socket *sock, struct tipc_msg *msg) +static int auto_connect(struct tipc_sock *tsk, struct tipc_msg *msg) { - struct tipc_sock *tsock = tipc_sk(sock->sk); - struct tipc_port *p_ptr; + struct tipc_port *port = &tsk->port; + struct socket *sock = tsk->sk.sk_socket; + struct tipc_portid peer; - tsock->peer_name.ref = msg_origport(msg); - tsock->peer_name.node = msg_orignode(msg); - p_ptr = tipc_port_deref(tsock->p->ref); - if (!p_ptr) - return -EINVAL; + peer.ref = msg_origport(msg); + peer.node = msg_orignode(msg); - __tipc_connect(tsock->p->ref, p_ptr, &tsock->peer_name); + __tipc_port_connect(port->ref, port, &peer); if (msg_importance(msg) > TIPC_CRITICAL_IMPORTANCE) return -EINVAL; - msg_set_importance(&p_ptr->phdr, (u32)msg_importance(msg)); + msg_set_importance(&port->phdr, (u32)msg_importance(msg)); sock->state = SS_CONNECTED; return 0; } @@ -1023,7 +1016,7 @@ static int tipc_wait_for_rcvmsg(struct socket *sock, long timeo) } /** - * recv_msg - receive packet-oriented message + * tipc_recvmsg - receive packet-oriented message * @iocb: (unused) * @m: descriptor for message info * @buf_len: total size of user buffer area @@ -1034,11 +1027,12 @@ static int tipc_wait_for_rcvmsg(struct socket *sock, long timeo) * * Returns size of returned message data, errno otherwise */ -static int recv_msg(struct kiocb *iocb, struct socket *sock, - struct msghdr *m, size_t buf_len, int flags) +static int tipc_recvmsg(struct kiocb *iocb, struct socket *sock, + struct msghdr *m, size_t buf_len, int flags) { struct sock *sk = sock->sk; - struct tipc_port *tport = tipc_sk_port(sk); + struct tipc_sock *tsk = tipc_sk(sk); + struct tipc_port *port = &tsk->port; struct sk_buff *buf; struct tipc_msg *msg; long timeo; @@ -1081,7 +1075,7 @@ restart: set_orig_addr(m, msg); /* Capture ancillary data (optional) */ - res = anc_data_recv(m, msg, tport); + res = anc_data_recv(m, msg, port); if (res) goto exit; @@ -1107,8 +1101,8 @@ restart: /* Consume received message (optional) */ if (likely(!(flags & MSG_PEEK))) { if ((sock->state != SS_READY) && - (++tport->conn_unacked >= TIPC_FLOW_CONTROL_WIN)) - tipc_acknowledge(tport->ref, tport->conn_unacked); + (++port->conn_unacked >= TIPC_FLOW_CONTROL_WIN)) + tipc_acknowledge(port->ref, port->conn_unacked); advance_rx_queue(sk); } exit: @@ -1117,7 +1111,7 @@ exit: } /** - * recv_stream - receive stream-oriented data + * tipc_recv_stream - receive stream-oriented data * @iocb: (unused) * @m: descriptor for message info * @buf_len: total size of user buffer area @@ -1128,11 +1122,12 @@ exit: * * Returns size of returned message data, errno otherwise */ -static int recv_stream(struct kiocb *iocb, struct socket *sock, - struct msghdr *m, size_t buf_len, int flags) +static int tipc_recv_stream(struct kiocb *iocb, struct socket *sock, + struct msghdr *m, size_t buf_len, int flags) { struct sock *sk = sock->sk; - struct tipc_port *tport = tipc_sk_port(sk); + struct tipc_sock *tsk = tipc_sk(sk); + struct tipc_port *port = &tsk->port; struct sk_buff *buf; struct tipc_msg *msg; long timeo; @@ -1177,7 +1172,7 @@ restart: /* Optionally capture sender's address & ancillary data of first msg */ if (sz_copied == 0) { set_orig_addr(m, msg); - res = anc_data_recv(m, msg, tport); + res = anc_data_recv(m, msg, port); if (res) goto exit; } @@ -1215,8 +1210,8 @@ restart: /* Consume received message (optional) */ if (likely(!(flags & MSG_PEEK))) { - if (unlikely(++tport->conn_unacked >= TIPC_FLOW_CONTROL_WIN)) - tipc_acknowledge(tport->ref, tport->conn_unacked); + if (unlikely(++port->conn_unacked >= TIPC_FLOW_CONTROL_WIN)) + tipc_acknowledge(port->ref, port->conn_unacked); advance_rx_queue(sk); } @@ -1268,17 +1263,19 @@ static void tipc_data_ready(struct sock *sk, int len) /** * filter_connect - Handle all incoming messages for a connection-based socket - * @tsock: TIPC socket + * @tsk: TIPC socket * @msg: message * * Returns TIPC error status code and socket error status code * once it encounters some errors */ -static u32 filter_connect(struct tipc_sock *tsock, struct sk_buff **buf) +static u32 filter_connect(struct tipc_sock *tsk, struct sk_buff **buf) { - struct socket *sock = tsock->sk.sk_socket; + struct sock *sk = &tsk->sk; + struct tipc_port *port = &tsk->port; + struct socket *sock = sk->sk_socket; struct tipc_msg *msg = buf_msg(*buf); - struct sock *sk = &tsock->sk; + u32 retval = TIPC_ERR_NO_PORT; int res; @@ -1288,10 +1285,10 @@ static u32 filter_connect(struct tipc_sock *tsock, struct sk_buff **buf) switch ((int)sock->state) { case SS_CONNECTED: /* Accept only connection-based messages sent by peer */ - if (msg_connected(msg) && tipc_port_peer_msg(tsock->p, msg)) { + if (msg_connected(msg) && tipc_port_peer_msg(port, msg)) { if (unlikely(msg_errcode(msg))) { sock->state = SS_DISCONNECTING; - __tipc_disconnect(tsock->p); + __tipc_port_disconnect(port); } retval = TIPC_OK; } @@ -1308,7 +1305,7 @@ static u32 filter_connect(struct tipc_sock *tsock, struct sk_buff **buf) if (unlikely(!msg_connected(msg))) break; - res = auto_connect(sock, msg); + res = auto_connect(tsk, msg); if (res) { sock->state = SS_DISCONNECTING; sk->sk_err = -res; @@ -1387,6 +1384,7 @@ static unsigned int rcvbuf_limit(struct sock *sk, struct sk_buff *buf) static u32 filter_rcv(struct sock *sk, struct sk_buff *buf) { struct socket *sock = sk->sk_socket; + struct tipc_sock *tsk = tipc_sk(sk); struct tipc_msg *msg = buf_msg(buf); unsigned int limit = rcvbuf_limit(sk, buf); u32 res = TIPC_OK; @@ -1399,7 +1397,7 @@ static u32 filter_rcv(struct sock *sk, struct sk_buff *buf) if (msg_connected(msg)) return TIPC_ERR_NO_PORT; } else { - res = filter_connect(tipc_sk(sk), &buf); + res = filter_connect(tsk, &buf); if (res != TIPC_OK || buf == NULL) return res; } @@ -1437,17 +1435,16 @@ static int backlog_rcv(struct sock *sk, struct sk_buff *buf) } /** - * dispatch - handle incoming message - * @tport: TIPC port that received message + * tipc_sk_rcv - handle incoming message + * @sk: socket receiving message * @buf: message * * Called with port lock already taken. * * Returns TIPC error status code (TIPC_OK if message is not to be rejected) */ -static u32 dispatch(struct tipc_port *tport, struct sk_buff *buf) +u32 tipc_sk_rcv(struct sock *sk, struct sk_buff *buf) { - struct sock *sk = tport->sk; u32 res; /* @@ -1470,19 +1467,6 @@ static u32 dispatch(struct tipc_port *tport, struct sk_buff *buf) return res; } -/** - * wakeupdispatch - wake up port after congestion - * @tport: port to wakeup - * - * Called with port lock already taken. - */ -static void wakeupdispatch(struct tipc_port *tport) -{ - struct sock *sk = tport->sk; - - sk->sk_write_space(sk); -} - static int tipc_wait_for_connect(struct socket *sock, long *timeo_p) { struct sock *sk = sock->sk; @@ -1506,7 +1490,7 @@ static int tipc_wait_for_connect(struct socket *sock, long *timeo_p) } /** - * connect - establish a connection to another TIPC port + * tipc_connect - establish a connection to another TIPC port * @sock: socket structure * @dest: socket address for destination port * @destlen: size of socket address data structure @@ -1514,8 +1498,8 @@ static int tipc_wait_for_connect(struct socket *sock, long *timeo_p) * * Returns 0 on success, errno otherwise */ -static int connect(struct socket *sock, struct sockaddr *dest, int destlen, - int flags) +static int tipc_connect(struct socket *sock, struct sockaddr *dest, + int destlen, int flags) { struct sock *sk = sock->sk; struct sockaddr_tipc *dst = (struct sockaddr_tipc *)dest; @@ -1556,7 +1540,7 @@ static int connect(struct socket *sock, struct sockaddr *dest, int destlen, if (!timeout) m.msg_flags = MSG_DONTWAIT; - res = send_msg(NULL, sock, &m, 0); + res = tipc_sendmsg(NULL, sock, &m, 0); if ((res < 0) && (res != -EWOULDBLOCK)) goto exit; @@ -1587,13 +1571,13 @@ exit: } /** - * listen - allow socket to listen for incoming connections + * tipc_listen - allow socket to listen for incoming connections * @sock: socket structure * @len: (unused) * * Returns 0 on success, errno otherwise */ -static int listen(struct socket *sock, int len) +static int tipc_listen(struct socket *sock, int len) { struct sock *sk = sock->sk; int res; @@ -1648,20 +1632,20 @@ static int tipc_wait_for_accept(struct socket *sock, long timeo) } /** - * accept - wait for connection request + * tipc_accept - wait for connection request * @sock: listening socket * @newsock: new socket that is to be connected * @flags: file-related flags associated with socket * * Returns 0 on success, errno otherwise */ -static int accept(struct socket *sock, struct socket *new_sock, int flags) +static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags) { struct sock *new_sk, *sk = sock->sk; struct sk_buff *buf; - struct tipc_sock *new_tsock; - struct tipc_port *new_tport; + struct tipc_port *new_port; struct tipc_msg *msg; + struct tipc_portid peer; u32 new_ref; long timeo; int res; @@ -1672,7 +1656,6 @@ static int accept(struct socket *sock, struct socket *new_sock, int flags) res = -EINVAL; goto exit; } - timeo = sock_rcvtimeo(sk, flags & O_NONBLOCK); res = tipc_wait_for_accept(sock, timeo); if (res) @@ -1685,9 +1668,8 @@ static int accept(struct socket *sock, struct socket *new_sock, int flags) goto exit; new_sk = new_sock->sk; - new_tsock = tipc_sk(new_sk); - new_tport = new_tsock->p; - new_ref = new_tport->ref; + new_port = &tipc_sk(new_sk)->port; + new_ref = new_port->ref; msg = buf_msg(buf); /* we lock on new_sk; but lockdep sees the lock on sk */ @@ -1700,15 +1682,15 @@ static int accept(struct socket *sock, struct socket *new_sock, int flags) reject_rx_queue(new_sk); /* Connect new socket to it's peer */ - new_tsock->peer_name.ref = msg_origport(msg); - new_tsock->peer_name.node = msg_orignode(msg); - tipc_connect(new_ref, &new_tsock->peer_name); + peer.ref = msg_origport(msg); + peer.node = msg_orignode(msg); + tipc_port_connect(new_ref, &peer); new_sock->state = SS_CONNECTED; - tipc_set_portimportance(new_ref, msg_importance(msg)); + tipc_port_set_importance(new_port, msg_importance(msg)); if (msg_named(msg)) { - new_tport->conn_type = msg_nametype(msg); - new_tport->conn_instance = msg_nameinst(msg); + new_port->conn_type = msg_nametype(msg); + new_port->conn_instance = msg_nameinst(msg); } /* @@ -1719,21 +1701,20 @@ static int accept(struct socket *sock, struct socket *new_sock, int flags) struct msghdr m = {NULL,}; advance_rx_queue(sk); - send_packet(NULL, new_sock, &m, 0); + tipc_send_packet(NULL, new_sock, &m, 0); } else { __skb_dequeue(&sk->sk_receive_queue); __skb_queue_head(&new_sk->sk_receive_queue, buf); skb_set_owner_r(buf, new_sk); } release_sock(new_sk); - exit: release_sock(sk); return res; } /** - * shutdown - shutdown socket connection + * tipc_shutdown - shutdown socket connection * @sock: socket structure * @how: direction to close (must be SHUT_RDWR) * @@ -1741,10 +1722,11 @@ exit: * * Returns 0 on success, errno otherwise */ -static int shutdown(struct socket *sock, int how) +static int tipc_shutdown(struct socket *sock, int how) { struct sock *sk = sock->sk; - struct tipc_port *tport = tipc_sk_port(sk); + struct tipc_sock *tsk = tipc_sk(sk); + struct tipc_port *port = &tsk->port; struct sk_buff *buf; int res; @@ -1765,10 +1747,10 @@ restart: kfree_skb(buf); goto restart; } - tipc_disconnect(tport->ref); + tipc_port_disconnect(port->ref); tipc_reject_msg(buf, TIPC_CONN_SHUTDOWN); } else { - tipc_shutdown(tport->ref); + tipc_port_shutdown(port->ref); } sock->state = SS_DISCONNECTING; @@ -1794,7 +1776,7 @@ restart: } /** - * setsockopt - set socket option + * tipc_setsockopt - set socket option * @sock: socket structure * @lvl: option level * @opt: option identifier @@ -1806,11 +1788,12 @@ restart: * * Returns 0 on success, errno otherwise */ -static int setsockopt(struct socket *sock, int lvl, int opt, char __user *ov, - unsigned int ol) +static int tipc_setsockopt(struct socket *sock, int lvl, int opt, + char __user *ov, unsigned int ol) { struct sock *sk = sock->sk; - struct tipc_port *tport = tipc_sk_port(sk); + struct tipc_sock *tsk = tipc_sk(sk); + struct tipc_port *port = &tsk->port; u32 value; int res; @@ -1828,16 +1811,16 @@ static int setsockopt(struct socket *sock, int lvl, int opt, char __user *ov, switch (opt) { case TIPC_IMPORTANCE: - res = tipc_set_portimportance(tport->ref, value); + tipc_port_set_importance(port, value); break; case TIPC_SRC_DROPPABLE: if (sock->type != SOCK_STREAM) - res = tipc_set_portunreliable(tport->ref, value); + tipc_port_set_unreliable(port, value); else res = -ENOPROTOOPT; break; case TIPC_DEST_DROPPABLE: - res = tipc_set_portunreturnable(tport->ref, value); + tipc_port_set_unreturnable(port, value); break; case TIPC_CONN_TIMEOUT: tipc_sk(sk)->conn_timeout = value; @@ -1853,7 +1836,7 @@ static int setsockopt(struct socket *sock, int lvl, int opt, char __user *ov, } /** - * getsockopt - get socket option + * tipc_getsockopt - get socket option * @sock: socket structure * @lvl: option level * @opt: option identifier @@ -1865,11 +1848,12 @@ static int setsockopt(struct socket *sock, int lvl, int opt, char __user *ov, * * Returns 0 on success, errno otherwise */ -static int getsockopt(struct socket *sock, int lvl, int opt, char __user *ov, - int __user *ol) +static int tipc_getsockopt(struct socket *sock, int lvl, int opt, + char __user *ov, int __user *ol) { struct sock *sk = sock->sk; - struct tipc_port *tport = tipc_sk_port(sk); + struct tipc_sock *tsk = tipc_sk(sk); + struct tipc_port *port = &tsk->port; int len; u32 value; int res; @@ -1886,13 +1870,13 @@ static int getsockopt(struct socket *sock, int lvl, int opt, char __user *ov, switch (opt) { case TIPC_IMPORTANCE: - res = tipc_portimportance(tport->ref, &value); + value = tipc_port_importance(port); break; case TIPC_SRC_DROPPABLE: - res = tipc_portunreliable(tport->ref, &value); + value = tipc_port_unreliable(port); break; case TIPC_DEST_DROPPABLE: - res = tipc_portunreturnable(tport->ref, &value); + value = tipc_port_unreturnable(port); break; case TIPC_CONN_TIMEOUT: value = tipc_sk(sk)->conn_timeout; @@ -1927,20 +1911,20 @@ static int getsockopt(struct socket *sock, int lvl, int opt, char __user *ov, static const struct proto_ops msg_ops = { .owner = THIS_MODULE, .family = AF_TIPC, - .release = release, - .bind = bind, - .connect = connect, + .release = tipc_release, + .bind = tipc_bind, + .connect = tipc_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, - .getname = get_name, - .poll = poll, + .getname = tipc_getname, + .poll = tipc_poll, .ioctl = sock_no_ioctl, .listen = sock_no_listen, - .shutdown = shutdown, - .setsockopt = setsockopt, - .getsockopt = getsockopt, - .sendmsg = send_msg, - .recvmsg = recv_msg, + .shutdown = tipc_shutdown, + .setsockopt = tipc_setsockopt, + .getsockopt = tipc_getsockopt, + .sendmsg = tipc_sendmsg, + .recvmsg = tipc_recvmsg, .mmap = sock_no_mmap, .sendpage = sock_no_sendpage }; @@ -1948,20 +1932,20 @@ static const struct proto_ops msg_ops = { static const struct proto_ops packet_ops = { .owner = THIS_MODULE, .family = AF_TIPC, - .release = release, - .bind = bind, - .connect = connect, + .release = tipc_release, + .bind = tipc_bind, + .connect = tipc_connect, .socketpair = sock_no_socketpair, - .accept = accept, - .getname = get_name, - .poll = poll, + .accept = tipc_accept, + .getname = tipc_getname, + .poll = tipc_poll, .ioctl = sock_no_ioctl, - .listen = listen, - .shutdown = shutdown, - .setsockopt = setsockopt, - .getsockopt = getsockopt, - .sendmsg = send_packet, - .recvmsg = recv_msg, + .listen = tipc_listen, + .shutdown = tipc_shutdown, + .setsockopt = tipc_setsockopt, + .getsockopt = tipc_getsockopt, + .sendmsg = tipc_send_packet, + .recvmsg = tipc_recvmsg, .mmap = sock_no_mmap, .sendpage = sock_no_sendpage }; @@ -1969,20 +1953,20 @@ static const struct proto_ops packet_ops = { static const struct proto_ops stream_ops = { .owner = THIS_MODULE, .family = AF_TIPC, - .release = release, - .bind = bind, - .connect = connect, + .release = tipc_release, + .bind = tipc_bind, + .connect = tipc_connect, .socketpair = sock_no_socketpair, - .accept = accept, - .getname = get_name, - .poll = poll, + .accept = tipc_accept, + .getname = tipc_getname, + .poll = tipc_poll, .ioctl = sock_no_ioctl, - .listen = listen, - .shutdown = shutdown, - .setsockopt = setsockopt, - .getsockopt = getsockopt, - .sendmsg = send_stream, - .recvmsg = recv_stream, + .listen = tipc_listen, + .shutdown = tipc_shutdown, + .setsockopt = tipc_setsockopt, + .getsockopt = tipc_getsockopt, + .sendmsg = tipc_send_stream, + .recvmsg = tipc_recv_stream, .mmap = sock_no_mmap, .sendpage = sock_no_sendpage }; @@ -2027,8 +2011,6 @@ int tipc_socket_init(void) proto_unregister(&tipc_proto); goto out; } - - sockets_enabled = 1; out: return res; } @@ -2038,10 +2020,6 @@ int tipc_socket_init(void) */ void tipc_socket_stop(void) { - if (!sockets_enabled) - return; - - sockets_enabled = 0; sock_unregister(tipc_family_ops.family); proto_unregister(&tipc_proto); } diff --git a/net/tipc/socket.h b/net/tipc/socket.h new file mode 100644 index 000000000000..74e5c7f195a6 --- /dev/null +++ b/net/tipc/socket.h @@ -0,0 +1,72 @@ +/* net/tipc/socket.h: Include file for TIPC socket code + * + * Copyright (c) 2014, Ericsson AB + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. 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. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef _TIPC_SOCK_H +#define _TIPC_SOCK_H + +#include "port.h" +#include <net/sock.h> + +/** + * struct tipc_sock - TIPC socket structure + * @sk: socket - interacts with 'port' and with user via the socket API + * @port: port - interacts with 'sk' and with the rest of the TIPC stack + * @peer_name: the peer of the connection, if any + * @conn_timeout: the time we can wait for an unresponded setup request + */ + +struct tipc_sock { + struct sock sk; + struct tipc_port port; + unsigned int conn_timeout; +}; + +static inline struct tipc_sock *tipc_sk(const struct sock *sk) +{ + return container_of(sk, struct tipc_sock, sk); +} + +static inline struct tipc_sock *tipc_port_to_sock(const struct tipc_port *port) +{ + return container_of(port, struct tipc_sock, port); +} + +static inline void tipc_sock_wakeup(struct tipc_sock *tsk) +{ + tsk->sk.sk_write_space(&tsk->sk); +} + +u32 tipc_sk_rcv(struct sock *sk, struct sk_buff *buf); + +#endif diff --git a/net/wireless/chan.c b/net/wireless/chan.c index 5946450c5406..cd10c1985074 100644 --- a/net/wireless/chan.c +++ b/net/wireless/chan.c @@ -712,6 +712,4 @@ cfg80211_get_chan_state(struct wireless_dev *wdev, case NUM_NL80211_IFTYPES: WARN_ON(1); } - - return; } diff --git a/net/wireless/util.c b/net/wireless/util.c index 57b3ce7a6b92..2bb685f3e8fc 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -11,6 +11,7 @@ #include <net/ip.h> #include <net/dsfield.h> #include <linux/if_vlan.h> +#include <linux/mpls.h> #include "core.h" #include "rdev-ops.h" @@ -717,6 +718,21 @@ unsigned int cfg80211_classify8021d(struct sk_buff *skb, case htons(ETH_P_IPV6): dscp = ipv6_get_dsfield(ipv6_hdr(skb)) & 0xfc; break; + case htons(ETH_P_MPLS_UC): + case htons(ETH_P_MPLS_MC): { + struct mpls_label mpls_tmp, *mpls; + + mpls = skb_header_pointer(skb, sizeof(struct ethhdr), + sizeof(*mpls), &mpls_tmp); + if (!mpls) + return 0; + + return (ntohl(mpls->entry) & MPLS_LS_TC_MASK) + >> MPLS_LS_TC_SHIFT; + } + case htons(ETH_P_80221): + /* 802.21 is always network control traffic */ + return 7; default: return 0; } diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index 6c7ac016ce3a..4218164f4f5e 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -108,7 +108,7 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) int err; __be32 seq; __be32 seq_hi; - struct xfrm_state *x; + struct xfrm_state *x = NULL; xfrm_address_t *daddr; struct xfrm_mode *inner_mode; unsigned int family; @@ -120,9 +120,14 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) async = 1; x = xfrm_input_state(skb); seq = XFRM_SKB_CB(skb)->seq.input.low; + family = x->outer_mode->afinfo->family; goto resume; } + daddr = (xfrm_address_t *)(skb_network_header(skb) + + XFRM_SPI_SKB_CB(skb)->daddroff); + family = XFRM_SPI_SKB_CB(skb)->family; + /* Allocate new secpath or COW existing one. */ if (!skb->sp || atomic_read(&skb->sp->refcnt) != 1) { struct sec_path *sp; @@ -137,10 +142,6 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) skb->sp = sp; } - daddr = (xfrm_address_t *)(skb_network_header(skb) + - XFRM_SPI_SKB_CB(skb)->daddroff); - family = XFRM_SPI_SKB_CB(skb)->family; - seq = 0; if (!spi && (err = xfrm_parse_spi(skb, nexthdr, &spi, &seq)) != 0) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINHDRERROR); @@ -162,6 +163,11 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) skb->sp->xvec[skb->sp->len++] = x; + if (xfrm_tunnel_check(skb, x, family)) { + XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMODEERROR); + goto drop; + } + spin_lock(&x->lock); if (unlikely(x->km.state == XFRM_STATE_ACQ)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMACQUIREERROR); @@ -201,7 +207,6 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) if (nexthdr == -EINPROGRESS) return 0; - resume: spin_lock(&x->lock); if (nexthdr <= 0) { @@ -263,6 +268,10 @@ resume: } } while (!err); + err = xfrm_rcv_cb(skb, family, x->type->proto, 0); + if (err) + goto drop; + nf_reset(skb); if (decaps) { @@ -276,6 +285,7 @@ resume: drop_unlock: spin_unlock(&x->lock); drop: + xfrm_rcv_cb(skb, family, x && x->type ? x->type->proto : nexthdr, -1); kfree_skb(skb); return 0; } diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 4b98b25793c5..f02f511b7107 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -39,8 +39,6 @@ #define XFRM_QUEUE_TMO_MAX ((unsigned)(60*HZ)) #define XFRM_MAX_QUEUE_LEN 100 -static struct dst_entry *xfrm_policy_sk_bundles; - static DEFINE_SPINLOCK(xfrm_policy_afinfo_lock); static struct xfrm_policy_afinfo __rcu *xfrm_policy_afinfo[NPROTO] __read_mostly; @@ -661,7 +659,7 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl) hlist_add_head(&policy->bydst, chain); xfrm_pol_hold(policy); net->xfrm.policy_count[dir]++; - atomic_inc(&flow_cache_genid); + atomic_inc(&net->xfrm.flow_cache_genid); /* After previous checking, family can either be AF_INET or AF_INET6 */ if (policy->family == AF_INET) @@ -1158,7 +1156,7 @@ static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol, if (hlist_unhashed(&pol->bydst)) return NULL; - hlist_del(&pol->bydst); + hlist_del_init(&pol->bydst); hlist_del(&pol->byidx); list_del(&pol->walk.all); net->xfrm.policy_count[dir]--; @@ -2109,13 +2107,6 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, goto no_transform; } - dst_hold(&xdst->u.dst); - - spin_lock_bh(&net->xfrm.xfrm_policy_sk_bundle_lock); - xdst->u.dst.next = xfrm_policy_sk_bundles; - xfrm_policy_sk_bundles = &xdst->u.dst; - spin_unlock_bh(&net->xfrm.xfrm_policy_sk_bundle_lock); - route = xdst->route; } } @@ -2549,33 +2540,15 @@ static struct dst_entry *xfrm_negative_advice(struct dst_entry *dst) return dst; } -static void __xfrm_garbage_collect(struct net *net) -{ - struct dst_entry *head, *next; - - spin_lock_bh(&net->xfrm.xfrm_policy_sk_bundle_lock); - head = xfrm_policy_sk_bundles; - xfrm_policy_sk_bundles = NULL; - spin_unlock_bh(&net->xfrm.xfrm_policy_sk_bundle_lock); - - while (head) { - next = head->next; - dst_free(head); - head = next; - } -} - void xfrm_garbage_collect(struct net *net) { - flow_cache_flush(); - __xfrm_garbage_collect(net); + flow_cache_flush(net); } EXPORT_SYMBOL(xfrm_garbage_collect); static void xfrm_garbage_collect_deferred(struct net *net) { - flow_cache_flush_deferred(); - __xfrm_garbage_collect(net); + flow_cache_flush_deferred(net); } static void xfrm_init_pmtu(struct dst_entry *dst) @@ -2940,15 +2913,19 @@ static int __net_init xfrm_net_init(struct net *net) rv = xfrm_sysctl_init(net); if (rv < 0) goto out_sysctl; + rv = flow_cache_init(net); + if (rv < 0) + goto out; /* Initialize the per-net locks here */ spin_lock_init(&net->xfrm.xfrm_state_lock); rwlock_init(&net->xfrm.xfrm_policy_lock); - spin_lock_init(&net->xfrm.xfrm_policy_sk_bundle_lock); mutex_init(&net->xfrm.xfrm_cfg_mutex); return 0; +out: + xfrm_sysctl_fini(net); out_sysctl: xfrm_policy_fini(net); out_policy: @@ -2961,6 +2938,7 @@ out_statistics: static void __net_exit xfrm_net_exit(struct net *net) { + flow_cache_fini(net); xfrm_sysctl_fini(net); xfrm_policy_fini(net); xfrm_state_fini(net); diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index a26b7aa79475..06970fee9155 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -161,6 +161,7 @@ static DEFINE_SPINLOCK(xfrm_state_gc_lock); int __xfrm_state_delete(struct xfrm_state *x); int km_query(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_policy *pol); +bool km_is_alive(const struct km_event *c); void km_state_expired(struct xfrm_state *x, int hard, u32 portid); static DEFINE_SPINLOCK(xfrm_type_lock); @@ -788,6 +789,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr, struct xfrm_state *best = NULL; u32 mark = pol->mark.v & pol->mark.m; unsigned short encap_family = tmpl->encap_family; + struct km_event c; to_put = NULL; @@ -832,6 +834,17 @@ found: error = -EEXIST; goto out; } + + c.net = net; + /* If the KMs have no listeners (yet...), avoid allocating an SA + * for each and every packet - garbage collection might not + * handle the flood. + */ + if (!km_is_alive(&c)) { + error = -ESRCH; + goto out; + } + x = xfrm_state_alloc(net); if (x == NULL) { error = -ENOMEM; @@ -1135,10 +1148,9 @@ out: EXPORT_SYMBOL(xfrm_state_add); #ifdef CONFIG_XFRM_MIGRATE -static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig, int *errp) +static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig) { struct net *net = xs_net(orig); - int err = -ENOMEM; struct xfrm_state *x = xfrm_state_alloc(net); if (!x) goto out; @@ -1159,6 +1171,11 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig, int *errp) } x->props.aalgo = orig->props.aalgo; + if (orig->aead) { + x->aead = xfrm_algo_aead_clone(orig->aead); + if (!x->aead) + goto error; + } if (orig->ealg) { x->ealg = xfrm_algo_clone(orig->ealg); if (!x->ealg) @@ -1187,20 +1204,21 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig, int *errp) } if (orig->replay_esn) { - err = xfrm_replay_clone(x, orig); - if (err) + if (xfrm_replay_clone(x, orig)) goto error; } memcpy(&x->mark, &orig->mark, sizeof(x->mark)); - err = xfrm_init_state(x); - if (err) + if (xfrm_init_state(x) < 0) goto error; x->props.flags = orig->props.flags; x->props.extra_flags = orig->props.extra_flags; + x->tfcpad = orig->tfcpad; + x->replay_maxdiff = orig->replay_maxdiff; + x->replay_maxage = orig->replay_maxage; x->curlft.add_time = orig->curlft.add_time; x->km.state = orig->km.state; x->km.seq = orig->km.seq; @@ -1210,16 +1228,15 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig, int *errp) error: xfrm_state_put(x); out: - if (errp) - *errp = err; return NULL; } -/* net->xfrm.xfrm_state_lock is held */ struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *net) { unsigned int h; - struct xfrm_state *x; + struct xfrm_state *x = NULL; + + spin_lock_bh(&net->xfrm.xfrm_state_lock); if (m->reqid) { h = xfrm_dst_hash(net, &m->old_daddr, &m->old_saddr, @@ -1236,7 +1253,7 @@ struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *n m->old_family)) continue; xfrm_state_hold(x); - return x; + break; } } else { h = xfrm_src_hash(net, &m->old_daddr, &m->old_saddr, @@ -1251,11 +1268,13 @@ struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *n m->old_family)) continue; xfrm_state_hold(x); - return x; + break; } } - return NULL; + spin_unlock_bh(&net->xfrm.xfrm_state_lock); + + return x; } EXPORT_SYMBOL(xfrm_migrate_state_find); @@ -1263,9 +1282,8 @@ struct xfrm_state *xfrm_state_migrate(struct xfrm_state *x, struct xfrm_migrate *m) { struct xfrm_state *xc; - int err; - xc = xfrm_state_clone(x, &err); + xc = xfrm_state_clone(x); if (!xc) return NULL; @@ -1278,7 +1296,7 @@ struct xfrm_state *xfrm_state_migrate(struct xfrm_state *x, state is to be updated as it is a part of triplet */ xfrm_state_insert(xc); } else { - if ((err = xfrm_state_add(xc)) < 0) + if (xfrm_state_add(xc) < 0) goto error; } @@ -1451,7 +1469,7 @@ xfrm_state_sort(struct xfrm_state **dst, struct xfrm_state **src, int n, { int err = 0; struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family); - struct net *net = xs_net(*dst); + struct net *net = xs_net(*src); if (!afinfo) return -EAFNOSUPPORT; @@ -1590,6 +1608,23 @@ unlock: } EXPORT_SYMBOL(xfrm_alloc_spi); +static bool __xfrm_state_filter_match(struct xfrm_state *x, + struct xfrm_filter *filter) +{ + if (filter) { + if ((filter->family == AF_INET || + filter->family == AF_INET6) && + x->props.family != filter->family) + return false; + + return addr_match(&x->props.saddr, &filter->saddr, + filter->splen) && + addr_match(&x->id.daddr, &filter->daddr, + filter->dplen); + } + return true; +} + int xfrm_state_walk(struct net *net, struct xfrm_state_walk *walk, int (*func)(struct xfrm_state *, int, void*), void *data) @@ -1612,6 +1647,8 @@ int xfrm_state_walk(struct net *net, struct xfrm_state_walk *walk, state = container_of(x, struct xfrm_state, km); if (!xfrm_id_proto_match(state->id.proto, walk->proto)) continue; + if (!__xfrm_state_filter_match(state, walk->filter)) + continue; err = func(state, walk->seq, data); if (err) { list_move_tail(&walk->all, &x->all); @@ -1630,17 +1667,21 @@ out: } EXPORT_SYMBOL(xfrm_state_walk); -void xfrm_state_walk_init(struct xfrm_state_walk *walk, u8 proto) +void xfrm_state_walk_init(struct xfrm_state_walk *walk, u8 proto, + struct xfrm_filter *filter) { INIT_LIST_HEAD(&walk->all); walk->proto = proto; walk->state = XFRM_STATE_DEAD; walk->seq = 0; + walk->filter = filter; } EXPORT_SYMBOL(xfrm_state_walk_init); void xfrm_state_walk_done(struct xfrm_state_walk *walk, struct net *net) { + kfree(walk->filter); + if (list_empty(&walk->all)) return; @@ -1793,6 +1834,24 @@ int km_report(struct net *net, u8 proto, struct xfrm_selector *sel, xfrm_address } EXPORT_SYMBOL(km_report); +bool km_is_alive(const struct km_event *c) +{ + struct xfrm_mgr *km; + bool is_alive = false; + + rcu_read_lock(); + list_for_each_entry_rcu(km, &xfrm_km_list, list) { + if (km->is_alive && km->is_alive(c)) { + is_alive = true; + break; + } + } + rcu_read_unlock(); + + return is_alive; +} +EXPORT_SYMBOL(km_is_alive); + int xfrm_user_policy(struct sock *sk, int optname, u8 __user *optval, int optlen) { int err; diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 1ae3ec7c18b0..195dbe230b98 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -32,11 +32,6 @@ #include <linux/in6.h> #endif -static inline int aead_len(struct xfrm_algo_aead *alg) -{ - return sizeof(*alg) + ((alg->alg_key_len + 7) / 8); -} - static int verify_one_alg(struct nlattr **attrs, enum xfrm_attr_type_t type) { struct nlattr *rt = attrs[type]; @@ -142,7 +137,8 @@ static inline int verify_replay(struct xfrm_usersa_info *p, if (!rt) return 0; - if (p->id.proto != IPPROTO_ESP) + /* As only ESP and AH support ESN feature. */ + if ((p->id.proto != IPPROTO_ESP) && (p->id.proto != IPPROTO_AH)) return -EINVAL; if (p->replay_window != 0) @@ -886,6 +882,7 @@ static int xfrm_dump_sa_done(struct netlink_callback *cb) return 0; } +static const struct nla_policy xfrma_policy[XFRMA_MAX+1]; static int xfrm_dump_sa(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); @@ -901,8 +898,31 @@ static int xfrm_dump_sa(struct sk_buff *skb, struct netlink_callback *cb) info.nlmsg_flags = NLM_F_MULTI; if (!cb->args[0]) { + struct nlattr *attrs[XFRMA_MAX+1]; + struct xfrm_filter *filter = NULL; + u8 proto = 0; + int err; + cb->args[0] = 1; - xfrm_state_walk_init(walk, 0); + + err = nlmsg_parse(cb->nlh, 0, attrs, XFRMA_MAX, + xfrma_policy); + if (err < 0) + return err; + + if (attrs[XFRMA_FILTER]) { + filter = kmalloc(sizeof(*filter), GFP_KERNEL); + if (filter == NULL) + return -ENOMEM; + + memcpy(filter, nla_data(attrs[XFRMA_FILTER]), + sizeof(*filter)); + } + + if (attrs[XFRMA_PROTO]) + proto = nla_get_u8(attrs[XFRMA_PROTO]); + + xfrm_state_walk_init(walk, proto, filter); } (void) xfrm_state_walk(net, walk, dump_one_state, &info); @@ -2308,6 +2328,8 @@ static const struct nla_policy xfrma_policy[XFRMA_MAX+1] = { [XFRMA_TFCPAD] = { .type = NLA_U32 }, [XFRMA_REPLAY_ESN_VAL] = { .len = sizeof(struct xfrm_replay_state_esn) }, [XFRMA_SA_EXTRA_FLAGS] = { .type = NLA_U32 }, + [XFRMA_PROTO] = { .type = NLA_U8 }, + [XFRMA_FILTER] = { .len = sizeof(struct xfrm_filter) }, }; static const struct xfrm_link { @@ -2981,6 +3003,11 @@ static int xfrm_send_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_MAPPING, GFP_ATOMIC); } +static bool xfrm_is_alive(const struct km_event *c) +{ + return (bool)xfrm_acquire_is_on(c->net); +} + static struct xfrm_mgr netlink_mgr = { .id = "netlink", .notify = xfrm_send_state_notify, @@ -2990,6 +3017,7 @@ static struct xfrm_mgr netlink_mgr = { .report = xfrm_send_report, .migrate = xfrm_send_migrate, .new_mapping = xfrm_send_mapping, + .is_alive = xfrm_is_alive, }; static int __net_init xfrm_user_net_init(struct net *net) diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib index 49392ecbef17..79c059e70860 100644 --- a/scripts/Makefile.lib +++ b/scripts/Makefile.lib @@ -152,6 +152,7 @@ ld_flags = $(LDFLAGS) $(ldflags-y) dtc_cpp_flags = -Wp,-MD,$(depfile).pre.tmp -nostdinc \ -I$(srctree)/arch/$(SRCARCH)/boot/dts \ -I$(srctree)/arch/$(SRCARCH)/boot/dts/include \ + -I$(srctree)/drivers/of/testcase-data \ -undef -D__DTS__ # Finds the multi-part object the current object will be linked into diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index 0ea2a1e24ade..464dcef79b35 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -471,7 +471,7 @@ sub seed_camelcase_includes { $camelcase_seeded = 1; - if (-d ".git") { + if (-e ".git") { my $git_last_include_commit = `git log --no-merges --pretty=format:"%h%n" -1 -- include`; chomp $git_last_include_commit; $camelcase_cache = ".checkpatch-camelcase.git.$git_last_include_commit"; @@ -499,7 +499,7 @@ sub seed_camelcase_includes { return; } - if (-d ".git") { + if (-e ".git") { $files = `git ls-files "include/*.h"`; @include_files = split('\n', $files); } diff --git a/scripts/gen_initramfs_list.sh b/scripts/gen_initramfs_list.sh index ef474098d9f1..17fa901418ae 100644 --- a/scripts/gen_initramfs_list.sh +++ b/scripts/gen_initramfs_list.sh @@ -257,7 +257,7 @@ case "$arg" in && compr="lzop -9 -f" echo "$output_file" | grep -q "\.lz4$" \ && [ -x "`which lz4 2> /dev/null`" ] \ - && compr="lz4 -9 -f" + && compr="lz4 -l -9 -f" echo "$output_file" | grep -q "\.cpio$" && compr="cat" shift ;; diff --git a/scripts/get_maintainer.pl b/scripts/get_maintainer.pl index 9c3986f4140c..41987885bd31 100755 --- a/scripts/get_maintainer.pl +++ b/scripts/get_maintainer.pl @@ -95,7 +95,7 @@ my %VCS_cmds; my %VCS_cmds_git = ( "execute_cmd" => \&git_execute_cmd, - "available" => '(which("git") ne "") && (-d ".git")', + "available" => '(which("git") ne "") && (-e ".git")', "find_signers_cmd" => "git log --no-color --follow --since=\$email_git_since " . '--numstat --no-merges ' . diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c index 10085de886fe..276e84b8a8e5 100644 --- a/scripts/kallsyms.c +++ b/scripts/kallsyms.c @@ -330,8 +330,7 @@ static void write_src(void) printf("\tPTR\t_text + %#llx\n", table[i].addr - _text); else - printf("\tPTR\t_text - %#llx\n", - _text - table[i].addr); + printf("\tPTR\t%#llx\n", table[i].addr); } else { printf("\tPTR\t%#llx\n", table[i].addr); } diff --git a/scripts/mod/file2alias.c b/scripts/mod/file2alias.c index 23708636b05c..25e5cb0aaef6 100644 --- a/scripts/mod/file2alias.c +++ b/scripts/mod/file2alias.c @@ -210,8 +210,8 @@ static void do_usb_entry(void *symval, range_lo < 0x9 ? "[%X-9" : "[%X", range_lo); sprintf(alias + strlen(alias), - range_hi > 0xA ? "a-%X]" : "%X]", - range_lo); + range_hi > 0xA ? "A-%X]" : "%X]", + range_hi); } } if (bcdDevice_initial_digits < (sizeof(bcdDevice_lo) * 2 - 1)) diff --git a/security/selinux/include/xfrm.h b/security/selinux/include/xfrm.h index 48c3cc94c168..dfe3fda7e5f7 100644 --- a/security/selinux/include/xfrm.h +++ b/security/selinux/include/xfrm.h @@ -45,10 +45,11 @@ static inline void selinux_xfrm_notify_policyload(void) { struct net *net; - atomic_inc(&flow_cache_genid); rtnl_lock(); - for_each_net(net) + for_each_net(net) { + atomic_inc(&net->xfrm.flow_cache_genid); rt_genid_bump_all(net); + } rtnl_unlock(); } #else diff --git a/security/selinux/ss/policydb.c b/security/selinux/ss/policydb.c index c0f498842129..9c5cdc2caaef 100644 --- a/security/selinux/ss/policydb.c +++ b/security/selinux/ss/policydb.c @@ -3338,10 +3338,10 @@ static int filename_write_helper(void *key, void *data, void *ptr) if (rc) return rc; - buf[0] = ft->stype; - buf[1] = ft->ttype; - buf[2] = ft->tclass; - buf[3] = otype->otype; + buf[0] = cpu_to_le32(ft->stype); + buf[1] = cpu_to_le32(ft->ttype); + buf[2] = cpu_to_le32(ft->tclass); + buf[3] = cpu_to_le32(otype->otype); rc = put_entry(buf, sizeof(u32), 4, fp); if (rc) diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c index ec4536c8d8d4..dafcf82139e2 100644 --- a/sound/pci/hda/hda_codec.c +++ b/sound/pci/hda/hda_codec.c @@ -932,7 +932,7 @@ int snd_hda_bus_new(struct snd_card *card, } EXPORT_SYMBOL_GPL(snd_hda_bus_new); -#ifdef CONFIG_SND_HDA_GENERIC +#if IS_ENABLED(CONFIG_SND_HDA_GENERIC) #define is_generic_config(codec) \ (codec->modelname && !strcmp(codec->modelname, "generic")) #else @@ -1339,23 +1339,15 @@ get_hda_cvt_setup(struct hda_codec *codec, hda_nid_t nid) /* * Dynamic symbol binding for the codec parsers */ -#ifdef MODULE -#define load_parser_sym(sym) ((int (*)(struct hda_codec *))symbol_request(sym)) -#define unload_parser_addr(addr) symbol_put_addr(addr) -#else -#define load_parser_sym(sym) (sym) -#define unload_parser_addr(addr) do {} while (0) -#endif #define load_parser(codec, sym) \ - ((codec)->parser = load_parser_sym(sym)) + ((codec)->parser = (int (*)(struct hda_codec *))symbol_request(sym)) static void unload_parser(struct hda_codec *codec) { - if (codec->parser) { - unload_parser_addr(codec->parser); - codec->parser = NULL; - } + if (codec->parser) + symbol_put_addr(codec->parser); + codec->parser = NULL; } /* @@ -1570,7 +1562,7 @@ int snd_hda_codec_update_widgets(struct hda_codec *codec) EXPORT_SYMBOL_GPL(snd_hda_codec_update_widgets); -#ifdef CONFIG_SND_HDA_CODEC_HDMI +#if IS_ENABLED(CONFIG_SND_HDA_CODEC_HDMI) /* if all audio out widgets are digital, let's assume the codec as a HDMI/DP */ static bool is_likely_hdmi_codec(struct hda_codec *codec) { @@ -1620,12 +1612,20 @@ int snd_hda_codec_configure(struct hda_codec *codec) patch = codec->preset->patch; if (!patch) { unload_parser(codec); /* to be sure */ - if (is_likely_hdmi_codec(codec)) + if (is_likely_hdmi_codec(codec)) { +#if IS_MODULE(CONFIG_SND_HDA_CODEC_HDMI) patch = load_parser(codec, snd_hda_parse_hdmi_codec); -#ifdef CONFIG_SND_HDA_GENERIC - if (!patch) +#elif IS_BUILTIN(CONFIG_SND_HDA_CODEC_HDMI) + patch = snd_hda_parse_hdmi_codec; +#endif + } + if (!patch) { +#if IS_MODULE(CONFIG_SND_HDA_GENERIC) patch = load_parser(codec, snd_hda_parse_generic_codec); +#elif IS_BUILTIN(CONFIG_SND_HDA_GENERIC) + patch = snd_hda_parse_generic_codec; #endif + } if (!patch) { printk(KERN_ERR "hda-codec: No codec parser is available\n"); return -ENODEV; diff --git a/sound/pci/hda/hda_generic.c b/sound/pci/hda/hda_generic.c index 8321a97d5c05..d9a09bdd09db 100644 --- a/sound/pci/hda/hda_generic.c +++ b/sound/pci/hda/hda_generic.c @@ -3269,7 +3269,7 @@ static int cap_put_caller(struct snd_kcontrol *kcontrol, mutex_unlock(&codec->control_mutex); snd_hda_codec_flush_cache(codec); /* flush the updates */ if (err >= 0 && spec->cap_sync_hook) - spec->cap_sync_hook(codec, ucontrol); + spec->cap_sync_hook(codec, kcontrol, ucontrol); return err; } @@ -3390,7 +3390,7 @@ static int cap_single_sw_put(struct snd_kcontrol *kcontrol, return ret; if (spec->cap_sync_hook) - spec->cap_sync_hook(codec, ucontrol); + spec->cap_sync_hook(codec, kcontrol, ucontrol); return ret; } @@ -3795,7 +3795,7 @@ static int mux_select(struct hda_codec *codec, unsigned int adc_idx, return 0; snd_hda_activate_path(codec, path, true, false); if (spec->cap_sync_hook) - spec->cap_sync_hook(codec, NULL); + spec->cap_sync_hook(codec, NULL, NULL); path_power_down_sync(codec, old_path); return 1; } @@ -5270,7 +5270,7 @@ static void init_input_src(struct hda_codec *codec) } if (spec->cap_sync_hook) - spec->cap_sync_hook(codec, NULL); + spec->cap_sync_hook(codec, NULL, NULL); } /* set right pin controls for digital I/O */ diff --git a/sound/pci/hda/hda_generic.h b/sound/pci/hda/hda_generic.h index 07f767231c9f..c908afbe4d94 100644 --- a/sound/pci/hda/hda_generic.h +++ b/sound/pci/hda/hda_generic.h @@ -274,6 +274,7 @@ struct hda_gen_spec { void (*init_hook)(struct hda_codec *codec); void (*automute_hook)(struct hda_codec *codec); void (*cap_sync_hook)(struct hda_codec *codec, + struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol); /* PCM hooks */ diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index fa2879a21a50..e354ab1ec20f 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -198,7 +198,7 @@ MODULE_DESCRIPTION("Intel HDA driver"); #endif #if defined(CONFIG_PM) && defined(CONFIG_VGA_SWITCHEROO) -#ifdef CONFIG_SND_HDA_CODEC_HDMI +#if IS_ENABLED(CONFIG_SND_HDA_CODEC_HDMI) #define SUPPORT_VGA_SWITCHEROO #endif #endif diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c index 54d14793725a..46ecdbb9053f 100644 --- a/sound/pci/hda/patch_ca0132.c +++ b/sound/pci/hda/patch_ca0132.c @@ -2662,60 +2662,6 @@ static bool dspload_wait_loaded(struct hda_codec *codec) } /* - * PCM stuffs - */ -static void ca0132_setup_stream(struct hda_codec *codec, hda_nid_t nid, - u32 stream_tag, - int channel_id, int format) -{ - unsigned int oldval, newval; - - if (!nid) - return; - - snd_printdd( - "ca0132_setup_stream: NID=0x%x, stream=0x%x, " - "channel=%d, format=0x%x\n", - nid, stream_tag, channel_id, format); - - /* update the format-id if changed */ - oldval = snd_hda_codec_read(codec, nid, 0, - AC_VERB_GET_STREAM_FORMAT, - 0); - if (oldval != format) { - msleep(20); - snd_hda_codec_write(codec, nid, 0, - AC_VERB_SET_STREAM_FORMAT, - format); - } - - oldval = snd_hda_codec_read(codec, nid, 0, AC_VERB_GET_CONV, 0); - newval = (stream_tag << 4) | channel_id; - if (oldval != newval) { - snd_hda_codec_write(codec, nid, 0, - AC_VERB_SET_CHANNEL_STREAMID, - newval); - } -} - -static void ca0132_cleanup_stream(struct hda_codec *codec, hda_nid_t nid) -{ - unsigned int val; - - if (!nid) - return; - - snd_printdd(KERN_INFO "ca0132_cleanup_stream: NID=0x%x\n", nid); - - val = snd_hda_codec_read(codec, nid, 0, AC_VERB_GET_CONV, 0); - if (!val) - return; - - snd_hda_codec_write(codec, nid, 0, AC_VERB_SET_STREAM_FORMAT, 0); - snd_hda_codec_write(codec, nid, 0, AC_VERB_SET_CHANNEL_STREAMID, 0); -} - -/* * PCM callbacks */ static int ca0132_playback_pcm_prepare(struct hda_pcm_stream *hinfo, @@ -2726,7 +2672,7 @@ static int ca0132_playback_pcm_prepare(struct hda_pcm_stream *hinfo, { struct ca0132_spec *spec = codec->spec; - ca0132_setup_stream(codec, spec->dacs[0], stream_tag, 0, format); + snd_hda_codec_setup_stream(codec, spec->dacs[0], stream_tag, 0, format); return 0; } @@ -2745,7 +2691,7 @@ static int ca0132_playback_pcm_cleanup(struct hda_pcm_stream *hinfo, if (spec->effects_switch[PLAY_ENHANCEMENT - EFFECT_START_NID]) msleep(50); - ca0132_cleanup_stream(codec, spec->dacs[0]); + snd_hda_codec_cleanup_stream(codec, spec->dacs[0]); return 0; } @@ -2822,10 +2768,8 @@ static int ca0132_capture_pcm_prepare(struct hda_pcm_stream *hinfo, unsigned int format, struct snd_pcm_substream *substream) { - struct ca0132_spec *spec = codec->spec; - - ca0132_setup_stream(codec, spec->adcs[substream->number], - stream_tag, 0, format); + snd_hda_codec_setup_stream(codec, hinfo->nid, + stream_tag, 0, format); return 0; } @@ -2839,7 +2783,7 @@ static int ca0132_capture_pcm_cleanup(struct hda_pcm_stream *hinfo, if (spec->dsp_state == DSP_DOWNLOADING) return 0; - ca0132_cleanup_stream(codec, hinfo->nid); + snd_hda_codec_cleanup_stream(codec, hinfo->nid); return 0; } @@ -4742,6 +4686,8 @@ static int patch_ca0132(struct hda_codec *codec) return err; codec->patch_ops = ca0132_patch_ops; + codec->pcm_format_first = 1; + codec->no_sticky_stream = 1; return 0; } diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c index 4e0ec146553d..bcf91bea3317 100644 --- a/sound/pci/hda/patch_conexant.c +++ b/sound/pci/hda/patch_conexant.c @@ -3291,7 +3291,8 @@ static void cxt_update_headset_mode(struct hda_codec *codec) } static void cxt_update_headset_mode_hook(struct hda_codec *codec, - struct snd_ctl_elem_value *ucontrol) + struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) { cxt_update_headset_mode(codec); } diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index d9693ca9546f..ec304f3ae3b4 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -708,7 +708,8 @@ static void alc_inv_dmic_sync(struct hda_codec *codec, bool force) } static void alc_inv_dmic_hook(struct hda_codec *codec, - struct snd_ctl_elem_value *ucontrol) + struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) { alc_inv_dmic_sync(codec, false); } @@ -3218,7 +3219,8 @@ static void alc269_fixup_hp_gpio_mute_hook(void *private_data, int enabled) /* turn on/off mic-mute LED per capture hook */ static void alc269_fixup_hp_gpio_mic_mute_hook(struct hda_codec *codec, - struct snd_ctl_elem_value *ucontrol) + struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) { struct alc_spec *spec = codec->spec; unsigned int oldval = spec->gpio_led; @@ -3528,7 +3530,8 @@ static void alc_update_headset_mode(struct hda_codec *codec) } static void alc_update_headset_mode_hook(struct hda_codec *codec, - struct snd_ctl_elem_value *ucontrol) + struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) { alc_update_headset_mode(codec); } @@ -4305,7 +4308,9 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1028, 0x0651, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x0652, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x0653, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1028, 0x0657, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x0658, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1028, 0x065f, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x0662, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x15cc, "Dell X5 Precision", ALC269_FIXUP_DELL2_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x15cd, "Dell X5 Precision", ALC269_FIXUP_DELL2_MIC_NO_PRESENCE), @@ -4314,6 +4319,54 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x1973, "HP Pavilion", ALC269_FIXUP_HP_MUTE_LED_MIC1), SND_PCI_QUIRK(0x103c, 0x1983, "HP Pavilion", ALC269_FIXUP_HP_MUTE_LED_MIC1), SND_PCI_QUIRK(0x103c, 0x218b, "HP", ALC269_FIXUP_LIMIT_INT_MIC_BOOST_MUTE_LED), + /* ALC282 */ + SND_PCI_QUIRK(0x103c, 0x220f, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x2213, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x2266, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x2267, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x2268, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x2269, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x226a, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x226b, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x227a, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x227b, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x229e, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x22a0, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x22b2, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x22b7, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x22bf, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x22c0, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x22c1, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x22c2, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x22cd, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x22ce, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x22cf, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x22d0, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), + /* ALC290 */ + SND_PCI_QUIRK(0x103c, 0x2260, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x2261, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x2262, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x2263, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x2264, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x2265, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x227d, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x227e, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x227f, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x2280, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x2281, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x2282, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x2289, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x228a, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x228b, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x228c, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x228d, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x228e, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x22c5, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x22c6, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x22c7, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x22c8, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x22c3, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x22c4, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), SND_PCI_QUIRK_VENDOR(0x103c, "HP", ALC269_FIXUP_HP_MUTE_LED), SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300), SND_PCI_QUIRK(0x1043, 0x106d, "Asus K53BE", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), @@ -4329,6 +4382,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x8398, "ASUS P1005", ALC269_FIXUP_STEREO_DMIC), SND_PCI_QUIRK(0x1043, 0x83ce, "ASUS P1005", ALC269_FIXUP_STEREO_DMIC), SND_PCI_QUIRK(0x1043, 0x8516, "ASUS X101CH", ALC269_FIXUP_ASUS_X101), + SND_PCI_QUIRK(0x104d, 0x90b5, "Sony VAIO Pro 11", ALC286_FIXUP_SONY_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x104d, 0x90b6, "Sony VAIO Pro 13", ALC286_FIXUP_SONY_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x104d, 0x9073, "Sony VAIO", ALC275_FIXUP_SONY_VAIO_GPIO2), SND_PCI_QUIRK(0x104d, 0x907b, "Sony VAIO", ALC275_FIXUP_SONY_HWEQ), @@ -4434,9 +4488,6 @@ static void alc269_fill_coef(struct hda_codec *codec) if (spec->codec_variant != ALC269_TYPE_ALC269VB) return; - /* ALC271X doesn't seem to support these COEFs (bko#52181) */ - if (!strcmp(codec->chip_name, "ALC271X")) - return; if ((alc_get_coef0(codec) & 0x00ff) < 0x015) { alc_write_coef_idx(codec, 0xf, 0x960b); @@ -5106,6 +5157,7 @@ static const struct snd_pci_quirk alc662_fixup_tbl[] = { SND_PCI_QUIRK(0x1025, 0x038b, "Acer Aspire 8943G", ALC662_FIXUP_ASPIRE), SND_PCI_QUIRK(0x1028, 0x05d8, "Dell", ALC668_FIXUP_DELL_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x05db, "Dell", ALC668_FIXUP_DELL_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1028, 0x060a, "Dell XPS 13", ALC668_FIXUP_DELL_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x0623, "Dell", ALC668_FIXUP_AUTO_MUTE), SND_PCI_QUIRK(0x1028, 0x0624, "Dell", ALC668_FIXUP_AUTO_MUTE), SND_PCI_QUIRK(0x1028, 0x0625, "Dell", ALC668_FIXUP_DELL_MIC_NO_PRESENCE), diff --git a/sound/pci/hda/patch_sigmatel.c b/sound/pci/hda/patch_sigmatel.c index 6998cf29b9bc..3bc29c9b2529 100644 --- a/sound/pci/hda/patch_sigmatel.c +++ b/sound/pci/hda/patch_sigmatel.c @@ -83,6 +83,7 @@ enum { STAC_DELL_M6_BOTH, STAC_DELL_EQ, STAC_ALIENWARE_M17X, + STAC_92HD89XX_HP_FRONT_JACK, STAC_92HD73XX_MODELS }; @@ -97,6 +98,7 @@ enum { STAC_92HD83XXX_HP_LED, STAC_92HD83XXX_HP_INV_LED, STAC_92HD83XXX_HP_MIC_LED, + STAC_HP_LED_GPIO10, STAC_92HD83XXX_HEADSET_JACK, STAC_92HD83XXX_HP, STAC_HP_ENVY_BASS, @@ -194,7 +196,7 @@ struct sigmatel_spec { int default_polarity; unsigned int mic_mute_led_gpio; /* capture mute LED GPIO */ - bool mic_mute_led_on; /* current mic mute state */ + unsigned int mic_enabled; /* current mic mute state (bitmask) */ /* stream */ unsigned int stream_delay; @@ -324,19 +326,26 @@ static void stac_gpio_set(struct hda_codec *codec, unsigned int mask, /* hook for controlling mic-mute LED GPIO */ static void stac_capture_led_hook(struct hda_codec *codec, - struct snd_ctl_elem_value *ucontrol) + struct snd_kcontrol *kcontrol, + struct snd_ctl_elem_value *ucontrol) { struct sigmatel_spec *spec = codec->spec; - bool mute; + unsigned int mask; + bool cur_mute, prev_mute; - if (!ucontrol) + if (!kcontrol || !ucontrol) return; - mute = !(ucontrol->value.integer.value[0] || - ucontrol->value.integer.value[1]); - if (spec->mic_mute_led_on != mute) { - spec->mic_mute_led_on = mute; - if (mute) + mask = 1U << snd_ctl_get_ioffidx(kcontrol, &ucontrol->id); + prev_mute = !spec->mic_enabled; + if (ucontrol->value.integer.value[0] || + ucontrol->value.integer.value[1]) + spec->mic_enabled |= mask; + else + spec->mic_enabled &= ~mask; + cur_mute = !spec->mic_enabled; + if (cur_mute != prev_mute) { + if (cur_mute) spec->gpio_data |= spec->mic_mute_led_gpio; else spec->gpio_data &= ~spec->mic_mute_led_gpio; @@ -1788,6 +1797,12 @@ static const struct hda_pintbl intel_dg45id_pin_configs[] = { {} }; +static const struct hda_pintbl stac92hd89xx_hp_front_jack_pin_configs[] = { + { 0x0a, 0x02214030 }, + { 0x0b, 0x02A19010 }, + {} +}; + static void stac92hd73xx_fixup_ref(struct hda_codec *codec, const struct hda_fixup *fix, int action) { @@ -1906,6 +1921,10 @@ static const struct hda_fixup stac92hd73xx_fixups[] = { [STAC_92HD73XX_NO_JD] = { .type = HDA_FIXUP_FUNC, .v.func = stac92hd73xx_fixup_no_jd, + }, + [STAC_92HD89XX_HP_FRONT_JACK] = { + .type = HDA_FIXUP_PINS, + .v.pins = stac92hd89xx_hp_front_jack_pin_configs, } }; @@ -1966,6 +1985,8 @@ static const struct snd_pci_quirk stac92hd73xx_fixup_tbl[] = { "Alienware M17x", STAC_ALIENWARE_M17X), SND_PCI_QUIRK(PCI_VENDOR_ID_DELL, 0x0490, "Alienware M17x R3", STAC_DELL_EQ), + SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x2b17, + "unknown HP", STAC_92HD89XX_HP_FRONT_JACK), {} /* terminator */ }; @@ -2110,6 +2131,17 @@ static void stac92hd83xxx_fixup_hp_mic_led(struct hda_codec *codec, } } +static void stac92hd83xxx_fixup_hp_led_gpio10(struct hda_codec *codec, + const struct hda_fixup *fix, int action) +{ + struct sigmatel_spec *spec = codec->spec; + + if (action == HDA_FIXUP_ACT_PRE_PROBE) { + spec->gpio_led = 0x10; /* GPIO4 */ + spec->default_polarity = 0; + } +} + static void stac92hd83xxx_fixup_headset_jack(struct hda_codec *codec, const struct hda_fixup *fix, int action) { @@ -2604,6 +2636,12 @@ static const struct hda_fixup stac92hd83xxx_fixups[] = { .chained = true, .chain_id = STAC_92HD83XXX_HP, }, + [STAC_HP_LED_GPIO10] = { + .type = HDA_FIXUP_FUNC, + .v.func = stac92hd83xxx_fixup_hp_led_gpio10, + .chained = true, + .chain_id = STAC_92HD83XXX_HP, + }, [STAC_92HD83XXX_HEADSET_JACK] = { .type = HDA_FIXUP_FUNC, .v.func = stac92hd83xxx_fixup_headset_jack, @@ -2682,6 +2720,8 @@ static const struct snd_pci_quirk stac92hd83xxx_fixup_tbl[] = { "HP", STAC_92HD83XXX_HP_cNB11_INTQUAD), SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x1888, "HP Envy Spectre", STAC_HP_ENVY_BASS), + SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x1899, + "HP Folio 13", STAC_HP_LED_GPIO10), SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x18df, "HP Folio", STAC_HP_BNB13_EQ), SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x18F8, @@ -4462,7 +4502,7 @@ static void stac_setup_gpio(struct hda_codec *codec) if (spec->mic_mute_led_gpio) { spec->gpio_mask |= spec->mic_mute_led_gpio; spec->gpio_dir |= spec->mic_mute_led_gpio; - spec->mic_mute_led_on = true; + spec->mic_enabled = 0; spec->gpio_data |= spec->mic_mute_led_gpio; spec->gen.cap_sync_hook = stac_capture_led_hook; diff --git a/sound/pci/hda/thinkpad_helper.c b/sound/pci/hda/thinkpad_helper.c index 5799fbc24c28..8fe3b8c18ed4 100644 --- a/sound/pci/hda/thinkpad_helper.c +++ b/sound/pci/hda/thinkpad_helper.c @@ -39,6 +39,7 @@ static void update_tpacpi_mute_led(void *private_data, int enabled) } static void update_tpacpi_micmute_led(struct hda_codec *codec, + struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { if (!ucontrol || !led_set_func) diff --git a/sound/soc/blackfin/Kconfig b/sound/soc/blackfin/Kconfig index 54f74f8cbb75..4544d8eb1452 100644 --- a/sound/soc/blackfin/Kconfig +++ b/sound/soc/blackfin/Kconfig @@ -11,7 +11,7 @@ config SND_BF5XX_I2S config SND_BF5XX_SOC_SSM2602 tristate "SoC SSM2602 Audio Codec Add-On Card support" - depends on SND_BF5XX_I2S && (SPI_MASTER || I2C) + depends on SND_BF5XX_I2S && SND_SOC_I2C_AND_SPI select SND_BF5XX_SOC_I2S if !BF60x select SND_BF6XX_SOC_I2S if BF60x select SND_SOC_SSM2602 @@ -21,10 +21,9 @@ config SND_BF5XX_SOC_SSM2602 config SND_SOC_BFIN_EVAL_ADAU1701 tristate "Support for the EVAL-ADAU1701MINIZ board on Blackfin eval boards" - depends on SND_BF5XX_I2S + depends on SND_BF5XX_I2S && I2C select SND_BF5XX_SOC_I2S select SND_SOC_ADAU1701 - select I2C help Say Y if you want to add support for the Analog Devices EVAL-ADAU1701MINIZ board connected to one of the Blackfin evaluation boards like the @@ -45,7 +44,7 @@ config SND_SOC_BFIN_EVAL_ADAU1373 config SND_SOC_BFIN_EVAL_ADAV80X tristate "Support for the EVAL-ADAV80X boards on Blackfin eval boards" - depends on SND_BF5XX_I2S && (SPI_MASTER || I2C) + depends on SND_BF5XX_I2S && SND_SOC_I2C_AND_SPI select SND_BF5XX_SOC_I2S select SND_SOC_ADAV80X help @@ -58,7 +57,7 @@ config SND_SOC_BFIN_EVAL_ADAV80X config SND_BF5XX_SOC_AD1836 tristate "SoC AD1836 Audio support for BF5xx" - depends on SND_BF5XX_I2S + depends on SND_BF5XX_I2S && SPI_MASTER select SND_BF5XX_SOC_I2S select SND_SOC_AD1836 help @@ -66,7 +65,7 @@ config SND_BF5XX_SOC_AD1836 config SND_BF5XX_SOC_AD193X tristate "SoC AD193X Audio support for Blackfin" - depends on SND_BF5XX_I2S + depends on SND_BF5XX_I2S && SND_SOC_I2C_AND_SPI select SND_BF5XX_SOC_I2S select SND_SOC_AD193X help diff --git a/sound/soc/codecs/ad1980.c b/sound/soc/codecs/ad1980.c index 7257a8885f42..34d965a4a040 100644 --- a/sound/soc/codecs/ad1980.c +++ b/sound/soc/codecs/ad1980.c @@ -57,8 +57,8 @@ static const u16 ad1980_reg[] = { static const char *ad1980_rec_sel[] = {"Mic", "CD", "NC", "AUX", "Line", "Stereo Mix", "Mono Mix", "Phone"}; -static const struct soc_enum ad1980_cap_src = - SOC_ENUM_DOUBLE(AC97_REC_SEL, 8, 0, 7, ad1980_rec_sel); +static SOC_ENUM_DOUBLE_DECL(ad1980_cap_src, + AC97_REC_SEL, 8, 0, ad1980_rec_sel); static const struct snd_kcontrol_new ad1980_snd_ac97_controls[] = { SOC_DOUBLE("Master Playback Volume", AC97_MASTER, 8, 0, 31, 1), diff --git a/sound/soc/codecs/da732x.c b/sound/soc/codecs/da732x.c index f295b6569910..f4d965ebc29e 100644 --- a/sound/soc/codecs/da732x.c +++ b/sound/soc/codecs/da732x.c @@ -1268,11 +1268,23 @@ static struct snd_soc_dai_driver da732x_dai[] = { }, }; +static bool da732x_volatile(struct device *dev, unsigned int reg) +{ + switch (reg) { + case DA732X_REG_HPL_DAC_OFF_CNTL: + case DA732X_REG_HPR_DAC_OFF_CNTL: + return true; + default: + return false; + } +} + static const struct regmap_config da732x_regmap = { .reg_bits = 8, .val_bits = 8, .max_register = DA732X_MAX_REG, + .volatile_reg = da732x_volatile, .reg_defaults = da732x_reg_cache, .num_reg_defaults = ARRAY_SIZE(da732x_reg_cache), .cache_type = REGCACHE_RBTREE, diff --git a/sound/soc/codecs/da9055.c b/sound/soc/codecs/da9055.c index 52b79a487ac7..422812613a28 100644 --- a/sound/soc/codecs/da9055.c +++ b/sound/soc/codecs/da9055.c @@ -1523,8 +1523,15 @@ static int da9055_remove(struct i2c_client *client) return 0; } +/* + * DO NOT change the device Ids. The naming is intentionally specific as both + * the CODEC and PMIC parts of this chip are instantiated separately as I2C + * devices (both have configurable I2C addresses, and are to all intents and + * purposes separate). As a result there are specific DA9055 Ids for CODEC + * and PMIC, which must be different to operate together. + */ static const struct i2c_device_id da9055_i2c_id[] = { - { "da9055", 0 }, + { "da9055-codec", 0 }, { } }; MODULE_DEVICE_TABLE(i2c, da9055_i2c_id); @@ -1532,7 +1539,7 @@ MODULE_DEVICE_TABLE(i2c, da9055_i2c_id); /* I2C codec control layer */ static struct i2c_driver da9055_i2c_driver = { .driver = { - .name = "da9055", + .name = "da9055-codec", .owner = THIS_MODULE, }, .probe = da9055_i2c_probe, diff --git a/sound/soc/codecs/isabelle.c b/sound/soc/codecs/isabelle.c index 5839048ec467..cb736ddc446d 100644 --- a/sound/soc/codecs/isabelle.c +++ b/sound/soc/codecs/isabelle.c @@ -140,13 +140,17 @@ static const char *isabelle_rx1_texts[] = {"VRX1", "ARX1"}; static const char *isabelle_rx2_texts[] = {"VRX2", "ARX2"}; static const struct soc_enum isabelle_rx1_enum[] = { - SOC_ENUM_SINGLE(ISABELLE_VOICE_HPF_CFG_REG, 3, 1, isabelle_rx1_texts), - SOC_ENUM_SINGLE(ISABELLE_AUDIO_HPF_CFG_REG, 5, 1, isabelle_rx1_texts), + SOC_ENUM_SINGLE(ISABELLE_VOICE_HPF_CFG_REG, 3, + ARRAY_SIZE(isabelle_rx1_texts), isabelle_rx1_texts), + SOC_ENUM_SINGLE(ISABELLE_AUDIO_HPF_CFG_REG, 5, + ARRAY_SIZE(isabelle_rx1_texts), isabelle_rx1_texts), }; static const struct soc_enum isabelle_rx2_enum[] = { - SOC_ENUM_SINGLE(ISABELLE_VOICE_HPF_CFG_REG, 2, 1, isabelle_rx2_texts), - SOC_ENUM_SINGLE(ISABELLE_AUDIO_HPF_CFG_REG, 4, 1, isabelle_rx2_texts), + SOC_ENUM_SINGLE(ISABELLE_VOICE_HPF_CFG_REG, 2, + ARRAY_SIZE(isabelle_rx2_texts), isabelle_rx2_texts), + SOC_ENUM_SINGLE(ISABELLE_AUDIO_HPF_CFG_REG, 4, + ARRAY_SIZE(isabelle_rx2_texts), isabelle_rx2_texts), }; /* Headset DAC playback switches */ @@ -161,13 +165,17 @@ static const char *isabelle_atx_texts[] = {"AMIC1", "DMIC"}; static const char *isabelle_vtx_texts[] = {"AMIC2", "DMIC"}; static const struct soc_enum isabelle_atx_enum[] = { - SOC_ENUM_SINGLE(ISABELLE_AMIC_CFG_REG, 7, 1, isabelle_atx_texts), - SOC_ENUM_SINGLE(ISABELLE_DMIC_CFG_REG, 0, 1, isabelle_atx_texts), + SOC_ENUM_SINGLE(ISABELLE_AMIC_CFG_REG, 7, + ARRAY_SIZE(isabelle_atx_texts), isabelle_atx_texts), + SOC_ENUM_SINGLE(ISABELLE_DMIC_CFG_REG, 0, + ARRAY_SIZE(isabelle_atx_texts), isabelle_atx_texts), }; static const struct soc_enum isabelle_vtx_enum[] = { - SOC_ENUM_SINGLE(ISABELLE_AMIC_CFG_REG, 6, 1, isabelle_vtx_texts), - SOC_ENUM_SINGLE(ISABELLE_DMIC_CFG_REG, 0, 1, isabelle_vtx_texts), + SOC_ENUM_SINGLE(ISABELLE_AMIC_CFG_REG, 6, + ARRAY_SIZE(isabelle_vtx_texts), isabelle_vtx_texts), + SOC_ENUM_SINGLE(ISABELLE_DMIC_CFG_REG, 0, + ARRAY_SIZE(isabelle_vtx_texts), isabelle_vtx_texts), }; static const struct snd_kcontrol_new atx_mux_controls = @@ -183,17 +191,13 @@ static const char *isabelle_amic1_texts[] = { /* Left analog microphone selection */ static const char *isabelle_amic2_texts[] = {"Sub Mic", "Aux/FM Right"}; -static const struct soc_enum isabelle_amic1_enum[] = { - SOC_ENUM_SINGLE(ISABELLE_AMIC_CFG_REG, 5, - ARRAY_SIZE(isabelle_amic1_texts), - isabelle_amic1_texts), -}; +static SOC_ENUM_SINGLE_DECL(isabelle_amic1_enum, + ISABELLE_AMIC_CFG_REG, 5, + isabelle_amic1_texts); -static const struct soc_enum isabelle_amic2_enum[] = { - SOC_ENUM_SINGLE(ISABELLE_AMIC_CFG_REG, 4, - ARRAY_SIZE(isabelle_amic2_texts), - isabelle_amic2_texts), -}; +static SOC_ENUM_SINGLE_DECL(isabelle_amic2_enum, + ISABELLE_AMIC_CFG_REG, 4, + isabelle_amic2_texts); static const struct snd_kcontrol_new amic1_control = SOC_DAPM_ENUM("Route", isabelle_amic1_enum); @@ -206,16 +210,20 @@ static const char *isabelle_st_audio_texts[] = {"ATX1", "ATX2"}; static const char *isabelle_st_voice_texts[] = {"VTX1", "VTX2"}; static const struct soc_enum isabelle_st_audio_enum[] = { - SOC_ENUM_SINGLE(ISABELLE_ATX_STPGA1_CFG_REG, 7, 1, + SOC_ENUM_SINGLE(ISABELLE_ATX_STPGA1_CFG_REG, 7, + ARRAY_SIZE(isabelle_st_audio_texts), isabelle_st_audio_texts), - SOC_ENUM_SINGLE(ISABELLE_ATX_STPGA2_CFG_REG, 7, 1, + SOC_ENUM_SINGLE(ISABELLE_ATX_STPGA2_CFG_REG, 7, + ARRAY_SIZE(isabelle_st_audio_texts), isabelle_st_audio_texts), }; static const struct soc_enum isabelle_st_voice_enum[] = { - SOC_ENUM_SINGLE(ISABELLE_VTX_STPGA1_CFG_REG, 7, 1, + SOC_ENUM_SINGLE(ISABELLE_VTX_STPGA1_CFG_REG, 7, + ARRAY_SIZE(isabelle_st_voice_texts), isabelle_st_voice_texts), - SOC_ENUM_SINGLE(ISABELLE_VTX2_STPGA2_CFG_REG, 7, 1, + SOC_ENUM_SINGLE(ISABELLE_VTX2_STPGA2_CFG_REG, 7, + ARRAY_SIZE(isabelle_st_voice_texts), isabelle_st_voice_texts), }; diff --git a/sound/soc/codecs/max98090.c b/sound/soc/codecs/max98090.c index 51f9b3d16b41..9f714ea86613 100644 --- a/sound/soc/codecs/max98090.c +++ b/sound/soc/codecs/max98090.c @@ -336,6 +336,7 @@ static bool max98090_readable_register(struct device *dev, unsigned int reg) case M98090_REG_RECORD_TDM_SLOT: case M98090_REG_SAMPLE_RATE: case M98090_REG_DMIC34_BIQUAD_BASE ... M98090_REG_DMIC34_BIQUAD_BASE + 0x0E: + case M98090_REG_REVISION_ID: return true; default: return false; @@ -1769,16 +1770,6 @@ static int max98090_set_bias_level(struct snd_soc_codec *codec, switch (level) { case SND_SOC_BIAS_ON: - if (codec->dapm.bias_level == SND_SOC_BIAS_OFF) { - ret = regcache_sync(max98090->regmap); - - if (ret != 0) { - dev_err(codec->dev, - "Failed to sync cache: %d\n", ret); - return ret; - } - } - if (max98090->jack_state == M98090_JACK_STATE_HEADSET) { /* * Set to normal bias level. @@ -1792,6 +1783,16 @@ static int max98090_set_bias_level(struct snd_soc_codec *codec, break; case SND_SOC_BIAS_STANDBY: + if (codec->dapm.bias_level == SND_SOC_BIAS_OFF) { + ret = regcache_sync(max98090->regmap); + if (ret != 0) { + dev_err(codec->dev, + "Failed to sync cache: %d\n", ret); + return ret; + } + } + break; + case SND_SOC_BIAS_OFF: /* Set internal pull-up to lowest power mode */ snd_soc_update_bits(codec, M98090_REG_JACK_DETECT, diff --git a/sound/soc/codecs/rt5640.c b/sound/soc/codecs/rt5640.c index a3fb41179636..886924934aa5 100644 --- a/sound/soc/codecs/rt5640.c +++ b/sound/soc/codecs/rt5640.c @@ -2093,6 +2093,7 @@ MODULE_DEVICE_TABLE(i2c, rt5640_i2c_id); #ifdef CONFIG_ACPI static struct acpi_device_id rt5640_acpi_match[] = { { "INT33CA", 0 }, + { "10EC5640", 0 }, { }, }; MODULE_DEVICE_TABLE(acpi, rt5640_acpi_match); diff --git a/sound/soc/codecs/sta32x.c b/sound/soc/codecs/sta32x.c index 06edb396e733..2735361a4c3c 100644 --- a/sound/soc/codecs/sta32x.c +++ b/sound/soc/codecs/sta32x.c @@ -187,42 +187,42 @@ static const unsigned int sta32x_limiter_drc_release_tlv[] = { 13, 16, TLV_DB_SCALE_ITEM(-1500, 300, 0), }; -static const struct soc_enum sta32x_drc_ac_enum = - SOC_ENUM_SINGLE(STA32X_CONFD, STA32X_CONFD_DRC_SHIFT, - 2, sta32x_drc_ac); -static const struct soc_enum sta32x_auto_eq_enum = - SOC_ENUM_SINGLE(STA32X_AUTO1, STA32X_AUTO1_AMEQ_SHIFT, - 3, sta32x_auto_eq_mode); -static const struct soc_enum sta32x_auto_gc_enum = - SOC_ENUM_SINGLE(STA32X_AUTO1, STA32X_AUTO1_AMGC_SHIFT, - 4, sta32x_auto_gc_mode); -static const struct soc_enum sta32x_auto_xo_enum = - SOC_ENUM_SINGLE(STA32X_AUTO2, STA32X_AUTO2_XO_SHIFT, - 16, sta32x_auto_xo_mode); -static const struct soc_enum sta32x_preset_eq_enum = - SOC_ENUM_SINGLE(STA32X_AUTO3, STA32X_AUTO3_PEQ_SHIFT, - 32, sta32x_preset_eq_mode); -static const struct soc_enum sta32x_limiter_ch1_enum = - SOC_ENUM_SINGLE(STA32X_C1CFG, STA32X_CxCFG_LS_SHIFT, - 3, sta32x_limiter_select); -static const struct soc_enum sta32x_limiter_ch2_enum = - SOC_ENUM_SINGLE(STA32X_C2CFG, STA32X_CxCFG_LS_SHIFT, - 3, sta32x_limiter_select); -static const struct soc_enum sta32x_limiter_ch3_enum = - SOC_ENUM_SINGLE(STA32X_C3CFG, STA32X_CxCFG_LS_SHIFT, - 3, sta32x_limiter_select); -static const struct soc_enum sta32x_limiter1_attack_rate_enum = - SOC_ENUM_SINGLE(STA32X_L1AR, STA32X_LxA_SHIFT, - 16, sta32x_limiter_attack_rate); -static const struct soc_enum sta32x_limiter2_attack_rate_enum = - SOC_ENUM_SINGLE(STA32X_L2AR, STA32X_LxA_SHIFT, - 16, sta32x_limiter_attack_rate); -static const struct soc_enum sta32x_limiter1_release_rate_enum = - SOC_ENUM_SINGLE(STA32X_L1AR, STA32X_LxR_SHIFT, - 16, sta32x_limiter_release_rate); -static const struct soc_enum sta32x_limiter2_release_rate_enum = - SOC_ENUM_SINGLE(STA32X_L2AR, STA32X_LxR_SHIFT, - 16, sta32x_limiter_release_rate); +static SOC_ENUM_SINGLE_DECL(sta32x_drc_ac_enum, + STA32X_CONFD, STA32X_CONFD_DRC_SHIFT, + sta32x_drc_ac); +static SOC_ENUM_SINGLE_DECL(sta32x_auto_eq_enum, + STA32X_AUTO1, STA32X_AUTO1_AMEQ_SHIFT, + sta32x_auto_eq_mode); +static SOC_ENUM_SINGLE_DECL(sta32x_auto_gc_enum, + STA32X_AUTO1, STA32X_AUTO1_AMGC_SHIFT, + sta32x_auto_gc_mode); +static SOC_ENUM_SINGLE_DECL(sta32x_auto_xo_enum, + STA32X_AUTO2, STA32X_AUTO2_XO_SHIFT, + sta32x_auto_xo_mode); +static SOC_ENUM_SINGLE_DECL(sta32x_preset_eq_enum, + STA32X_AUTO3, STA32X_AUTO3_PEQ_SHIFT, + sta32x_preset_eq_mode); +static SOC_ENUM_SINGLE_DECL(sta32x_limiter_ch1_enum, + STA32X_C1CFG, STA32X_CxCFG_LS_SHIFT, + sta32x_limiter_select); +static SOC_ENUM_SINGLE_DECL(sta32x_limiter_ch2_enum, + STA32X_C2CFG, STA32X_CxCFG_LS_SHIFT, + sta32x_limiter_select); +static SOC_ENUM_SINGLE_DECL(sta32x_limiter_ch3_enum, + STA32X_C3CFG, STA32X_CxCFG_LS_SHIFT, + sta32x_limiter_select); +static SOC_ENUM_SINGLE_DECL(sta32x_limiter1_attack_rate_enum, + STA32X_L1AR, STA32X_LxA_SHIFT, + sta32x_limiter_attack_rate); +static SOC_ENUM_SINGLE_DECL(sta32x_limiter2_attack_rate_enum, + STA32X_L2AR, STA32X_LxA_SHIFT, + sta32x_limiter_attack_rate); +static SOC_ENUM_SINGLE_DECL(sta32x_limiter1_release_rate_enum, + STA32X_L1AR, STA32X_LxR_SHIFT, + sta32x_limiter_release_rate); +static SOC_ENUM_SINGLE_DECL(sta32x_limiter2_release_rate_enum, + STA32X_L2AR, STA32X_LxR_SHIFT, + sta32x_limiter_release_rate); /* byte array controls for setting biquad, mixer, scaling coefficients; * for biquads all five coefficients need to be set in one go, @@ -331,7 +331,7 @@ static int sta32x_sync_coef_shadow(struct snd_soc_codec *codec) static int sta32x_cache_sync(struct snd_soc_codec *codec) { - struct sta32x_priv *sta32x = codec->control_data; + struct sta32x_priv *sta32x = snd_soc_codec_get_drvdata(codec); unsigned int mute; int rc; @@ -434,7 +434,7 @@ SOC_SINGLE_TLV("Treble Tone Control", STA32X_TONE, STA32X_TONE_TTC_SHIFT, 15, 0, SOC_ENUM("Limiter1 Attack Rate (dB/ms)", sta32x_limiter1_attack_rate_enum), SOC_ENUM("Limiter2 Attack Rate (dB/ms)", sta32x_limiter2_attack_rate_enum), SOC_ENUM("Limiter1 Release Rate (dB/ms)", sta32x_limiter1_release_rate_enum), -SOC_ENUM("Limiter2 Release Rate (dB/ms)", sta32x_limiter1_release_rate_enum), +SOC_ENUM("Limiter2 Release Rate (dB/ms)", sta32x_limiter2_release_rate_enum), /* depending on mode, the attack/release thresholds have * two different enum definitions; provide both diff --git a/sound/soc/codecs/wm8400.c b/sound/soc/codecs/wm8400.c index 48dc7d2fee36..6d684d934f4d 100644 --- a/sound/soc/codecs/wm8400.c +++ b/sound/soc/codecs/wm8400.c @@ -117,19 +117,23 @@ static int wm8400_outpga_put_volsw_vu(struct snd_kcontrol *kcontrol, static const char *wm8400_digital_sidetone[] = {"None", "Left ADC", "Right ADC", "Reserved"}; -static const struct soc_enum wm8400_left_digital_sidetone_enum = -SOC_ENUM_SINGLE(WM8400_DIGITAL_SIDE_TONE, - WM8400_ADC_TO_DACL_SHIFT, 2, wm8400_digital_sidetone); +static SOC_ENUM_SINGLE_DECL(wm8400_left_digital_sidetone_enum, + WM8400_DIGITAL_SIDE_TONE, + WM8400_ADC_TO_DACL_SHIFT, + wm8400_digital_sidetone); -static const struct soc_enum wm8400_right_digital_sidetone_enum = -SOC_ENUM_SINGLE(WM8400_DIGITAL_SIDE_TONE, - WM8400_ADC_TO_DACR_SHIFT, 2, wm8400_digital_sidetone); +static SOC_ENUM_SINGLE_DECL(wm8400_right_digital_sidetone_enum, + WM8400_DIGITAL_SIDE_TONE, + WM8400_ADC_TO_DACR_SHIFT, + wm8400_digital_sidetone); static const char *wm8400_adcmode[] = {"Hi-fi mode", "Voice mode 1", "Voice mode 2", "Voice mode 3"}; -static const struct soc_enum wm8400_right_adcmode_enum = -SOC_ENUM_SINGLE(WM8400_ADC_CTRL, WM8400_ADC_HPF_CUT_SHIFT, 3, wm8400_adcmode); +static SOC_ENUM_SINGLE_DECL(wm8400_right_adcmode_enum, + WM8400_ADC_CTRL, + WM8400_ADC_HPF_CUT_SHIFT, + wm8400_adcmode); static const struct snd_kcontrol_new wm8400_snd_controls[] = { /* INMIXL */ @@ -422,9 +426,10 @@ SOC_DAPM_SINGLE("RINPGA34 Switch", WM8400_INPUT_MIXER3, WM8400_L34MNB_SHIFT, static const char *wm8400_ainlmux[] = {"INMIXL Mix", "RXVOICE Mix", "DIFFINL Mix"}; -static const struct soc_enum wm8400_ainlmux_enum = -SOC_ENUM_SINGLE( WM8400_INPUT_MIXER1, WM8400_AINLMODE_SHIFT, - ARRAY_SIZE(wm8400_ainlmux), wm8400_ainlmux); +static SOC_ENUM_SINGLE_DECL(wm8400_ainlmux_enum, + WM8400_INPUT_MIXER1, + WM8400_AINLMODE_SHIFT, + wm8400_ainlmux); static const struct snd_kcontrol_new wm8400_dapm_ainlmux_controls = SOC_DAPM_ENUM("Route", wm8400_ainlmux_enum); @@ -435,9 +440,10 @@ SOC_DAPM_ENUM("Route", wm8400_ainlmux_enum); static const char *wm8400_ainrmux[] = {"INMIXR Mix", "RXVOICE Mix", "DIFFINR Mix"}; -static const struct soc_enum wm8400_ainrmux_enum = -SOC_ENUM_SINGLE( WM8400_INPUT_MIXER1, WM8400_AINRMODE_SHIFT, - ARRAY_SIZE(wm8400_ainrmux), wm8400_ainrmux); +static SOC_ENUM_SINGLE_DECL(wm8400_ainrmux_enum, + WM8400_INPUT_MIXER1, + WM8400_AINRMODE_SHIFT, + wm8400_ainrmux); static const struct snd_kcontrol_new wm8400_dapm_ainrmux_controls = SOC_DAPM_ENUM("Route", wm8400_ainrmux_enum); diff --git a/sound/soc/codecs/wm8770.c b/sound/soc/codecs/wm8770.c index 89a18d82f303..5bce21013485 100644 --- a/sound/soc/codecs/wm8770.c +++ b/sound/soc/codecs/wm8770.c @@ -196,8 +196,8 @@ static const char *ain_text[] = { "AIN5", "AIN6", "AIN7", "AIN8" }; -static const struct soc_enum ain_enum = - SOC_ENUM_DOUBLE(WM8770_ADCMUX, 0, 4, 8, ain_text); +static SOC_ENUM_DOUBLE_DECL(ain_enum, + WM8770_ADCMUX, 0, 4, ain_text); static const struct snd_kcontrol_new ain_mux = SOC_DAPM_ENUM("Capture Mux", ain_enum); diff --git a/sound/soc/codecs/wm8900.c b/sound/soc/codecs/wm8900.c index e98bc7038a08..43c2201cb901 100644 --- a/sound/soc/codecs/wm8900.c +++ b/sound/soc/codecs/wm8900.c @@ -304,53 +304,53 @@ static const DECLARE_TLV_DB_SCALE(adc_tlv, -7200, 75, 1); static const char *mic_bias_level_txt[] = { "0.9*AVDD", "0.65*AVDD" }; -static const struct soc_enum mic_bias_level = -SOC_ENUM_SINGLE(WM8900_REG_INCTL, 8, 2, mic_bias_level_txt); +static SOC_ENUM_SINGLE_DECL(mic_bias_level, + WM8900_REG_INCTL, 8, mic_bias_level_txt); static const char *dac_mute_rate_txt[] = { "Fast", "Slow" }; -static const struct soc_enum dac_mute_rate = -SOC_ENUM_SINGLE(WM8900_REG_DACCTRL, 7, 2, dac_mute_rate_txt); +static SOC_ENUM_SINGLE_DECL(dac_mute_rate, + WM8900_REG_DACCTRL, 7, dac_mute_rate_txt); static const char *dac_deemphasis_txt[] = { "Disabled", "32kHz", "44.1kHz", "48kHz" }; -static const struct soc_enum dac_deemphasis = -SOC_ENUM_SINGLE(WM8900_REG_DACCTRL, 4, 4, dac_deemphasis_txt); +static SOC_ENUM_SINGLE_DECL(dac_deemphasis, + WM8900_REG_DACCTRL, 4, dac_deemphasis_txt); static const char *adc_hpf_cut_txt[] = { "Hi-fi mode", "Voice mode 1", "Voice mode 2", "Voice mode 3" }; -static const struct soc_enum adc_hpf_cut = -SOC_ENUM_SINGLE(WM8900_REG_ADCCTRL, 5, 4, adc_hpf_cut_txt); +static SOC_ENUM_SINGLE_DECL(adc_hpf_cut, + WM8900_REG_ADCCTRL, 5, adc_hpf_cut_txt); static const char *lr_txt[] = { "Left", "Right" }; -static const struct soc_enum aifl_src = -SOC_ENUM_SINGLE(WM8900_REG_AUDIO1, 15, 2, lr_txt); +static SOC_ENUM_SINGLE_DECL(aifl_src, + WM8900_REG_AUDIO1, 15, lr_txt); -static const struct soc_enum aifr_src = -SOC_ENUM_SINGLE(WM8900_REG_AUDIO1, 14, 2, lr_txt); +static SOC_ENUM_SINGLE_DECL(aifr_src, + WM8900_REG_AUDIO1, 14, lr_txt); -static const struct soc_enum dacl_src = -SOC_ENUM_SINGLE(WM8900_REG_AUDIO2, 15, 2, lr_txt); +static SOC_ENUM_SINGLE_DECL(dacl_src, + WM8900_REG_AUDIO2, 15, lr_txt); -static const struct soc_enum dacr_src = -SOC_ENUM_SINGLE(WM8900_REG_AUDIO2, 14, 2, lr_txt); +static SOC_ENUM_SINGLE_DECL(dacr_src, + WM8900_REG_AUDIO2, 14, lr_txt); static const char *sidetone_txt[] = { "Disabled", "Left ADC", "Right ADC" }; -static const struct soc_enum dacl_sidetone = -SOC_ENUM_SINGLE(WM8900_REG_SIDETONE, 2, 3, sidetone_txt); +static SOC_ENUM_SINGLE_DECL(dacl_sidetone, + WM8900_REG_SIDETONE, 2, sidetone_txt); -static const struct soc_enum dacr_sidetone = -SOC_ENUM_SINGLE(WM8900_REG_SIDETONE, 0, 3, sidetone_txt); +static SOC_ENUM_SINGLE_DECL(dacr_sidetone, + WM8900_REG_SIDETONE, 0, sidetone_txt); static const struct snd_kcontrol_new wm8900_snd_controls[] = { SOC_ENUM("Mic Bias Level", mic_bias_level), @@ -496,8 +496,8 @@ SOC_DAPM_SINGLE("RINPUT3 Switch", WM8900_REG_INCTL, 0, 1, 0), static const char *wm8900_lp_mux[] = { "Disabled", "Enabled" }; -static const struct soc_enum wm8900_lineout2_lp_mux = -SOC_ENUM_SINGLE(WM8900_REG_LOUTMIXCTL1, 1, 2, wm8900_lp_mux); +static SOC_ENUM_SINGLE_DECL(wm8900_lineout2_lp_mux, + WM8900_REG_LOUTMIXCTL1, 1, wm8900_lp_mux); static const struct snd_kcontrol_new wm8900_lineout2_lp = SOC_DAPM_ENUM("Route", wm8900_lineout2_lp_mux); diff --git a/sound/soc/codecs/wm8958-dsp2.c b/sound/soc/codecs/wm8958-dsp2.c index b7488f190d2b..d4248e00160e 100644 --- a/sound/soc/codecs/wm8958-dsp2.c +++ b/sound/soc/codecs/wm8958-dsp2.c @@ -153,7 +153,7 @@ static int wm8958_dsp2_fw(struct snd_soc_codec *codec, const char *name, data32 &= 0xffffff; - wm8994_bulk_write(codec->control_data, + wm8994_bulk_write(wm8994->wm8994, data32 & 0xffffff, block_len / 2, (void *)(data + 8)); diff --git a/sound/soc/codecs/wm8993.c b/sound/soc/codecs/wm8993.c index 433d59a0f3ef..2ee23a39622c 100644 --- a/sound/soc/codecs/wm8993.c +++ b/sound/soc/codecs/wm8993.c @@ -1562,7 +1562,6 @@ static int wm8993_remove(struct snd_soc_codec *codec) struct wm8993_priv *wm8993 = snd_soc_codec_get_drvdata(codec); wm8993_set_bias_level(codec, SND_SOC_BIAS_OFF); - regulator_bulk_free(ARRAY_SIZE(wm8993->supplies), wm8993->supplies); return 0; } diff --git a/sound/soc/codecs/wm8994.c b/sound/soc/codecs/wm8994.c index b9be9cbc4603..adb72063d44e 100644 --- a/sound/soc/codecs/wm8994.c +++ b/sound/soc/codecs/wm8994.c @@ -265,21 +265,21 @@ static const char *sidetone_hpf_text[] = { "2.7kHz", "1.35kHz", "675Hz", "370Hz", "180Hz", "90Hz", "45Hz" }; -static const struct soc_enum sidetone_hpf = - SOC_ENUM_SINGLE(WM8994_SIDETONE, 7, 7, sidetone_hpf_text); +static SOC_ENUM_SINGLE_DECL(sidetone_hpf, + WM8994_SIDETONE, 7, sidetone_hpf_text); static const char *adc_hpf_text[] = { "HiFi", "Voice 1", "Voice 2", "Voice 3" }; -static const struct soc_enum aif1adc1_hpf = - SOC_ENUM_SINGLE(WM8994_AIF1_ADC1_FILTERS, 13, 4, adc_hpf_text); +static SOC_ENUM_SINGLE_DECL(aif1adc1_hpf, + WM8994_AIF1_ADC1_FILTERS, 13, adc_hpf_text); -static const struct soc_enum aif1adc2_hpf = - SOC_ENUM_SINGLE(WM8994_AIF1_ADC2_FILTERS, 13, 4, adc_hpf_text); +static SOC_ENUM_SINGLE_DECL(aif1adc2_hpf, + WM8994_AIF1_ADC2_FILTERS, 13, adc_hpf_text); -static const struct soc_enum aif2adc_hpf = - SOC_ENUM_SINGLE(WM8994_AIF2_ADC_FILTERS, 13, 4, adc_hpf_text); +static SOC_ENUM_SINGLE_DECL(aif2adc_hpf, + WM8994_AIF2_ADC_FILTERS, 13, adc_hpf_text); static const DECLARE_TLV_DB_SCALE(aif_tlv, 0, 600, 0); static const DECLARE_TLV_DB_SCALE(digital_tlv, -7200, 75, 1); @@ -501,39 +501,39 @@ static const char *aif_chan_src_text[] = { "Left", "Right" }; -static const struct soc_enum aif1adcl_src = - SOC_ENUM_SINGLE(WM8994_AIF1_CONTROL_1, 15, 2, aif_chan_src_text); +static SOC_ENUM_SINGLE_DECL(aif1adcl_src, + WM8994_AIF1_CONTROL_1, 15, aif_chan_src_text); -static const struct soc_enum aif1adcr_src = - SOC_ENUM_SINGLE(WM8994_AIF1_CONTROL_1, 14, 2, aif_chan_src_text); +static SOC_ENUM_SINGLE_DECL(aif1adcr_src, + WM8994_AIF1_CONTROL_1, 14, aif_chan_src_text); -static const struct soc_enum aif2adcl_src = - SOC_ENUM_SINGLE(WM8994_AIF2_CONTROL_1, 15, 2, aif_chan_src_text); +static SOC_ENUM_SINGLE_DECL(aif2adcl_src, + WM8994_AIF2_CONTROL_1, 15, aif_chan_src_text); -static const struct soc_enum aif2adcr_src = - SOC_ENUM_SINGLE(WM8994_AIF2_CONTROL_1, 14, 2, aif_chan_src_text); +static SOC_ENUM_SINGLE_DECL(aif2adcr_src, + WM8994_AIF2_CONTROL_1, 14, aif_chan_src_text); -static const struct soc_enum aif1dacl_src = - SOC_ENUM_SINGLE(WM8994_AIF1_CONTROL_2, 15, 2, aif_chan_src_text); +static SOC_ENUM_SINGLE_DECL(aif1dacl_src, + WM8994_AIF1_CONTROL_2, 15, aif_chan_src_text); -static const struct soc_enum aif1dacr_src = - SOC_ENUM_SINGLE(WM8994_AIF1_CONTROL_2, 14, 2, aif_chan_src_text); +static SOC_ENUM_SINGLE_DECL(aif1dacr_src, + WM8994_AIF1_CONTROL_2, 14, aif_chan_src_text); -static const struct soc_enum aif2dacl_src = - SOC_ENUM_SINGLE(WM8994_AIF2_CONTROL_2, 15, 2, aif_chan_src_text); +static SOC_ENUM_SINGLE_DECL(aif2dacl_src, + WM8994_AIF2_CONTROL_2, 15, aif_chan_src_text); -static const struct soc_enum aif2dacr_src = - SOC_ENUM_SINGLE(WM8994_AIF2_CONTROL_2, 14, 2, aif_chan_src_text); +static SOC_ENUM_SINGLE_DECL(aif2dacr_src, + WM8994_AIF2_CONTROL_2, 14, aif_chan_src_text); static const char *osr_text[] = { "Low Power", "High Performance", }; -static const struct soc_enum dac_osr = - SOC_ENUM_SINGLE(WM8994_OVERSAMPLING, 0, 2, osr_text); +static SOC_ENUM_SINGLE_DECL(dac_osr, + WM8994_OVERSAMPLING, 0, osr_text); -static const struct soc_enum adc_osr = - SOC_ENUM_SINGLE(WM8994_OVERSAMPLING, 1, 2, osr_text); +static SOC_ENUM_SINGLE_DECL(adc_osr, + WM8994_OVERSAMPLING, 1, osr_text); static const struct snd_kcontrol_new wm8994_snd_controls[] = { SOC_DOUBLE_R_TLV("AIF1ADC1 Volume", WM8994_AIF1_ADC1_LEFT_VOLUME, @@ -690,17 +690,20 @@ static const char *wm8958_ng_text[] = { "30ms", "125ms", "250ms", "500ms", }; -static const struct soc_enum wm8958_aif1dac1_ng_hold = - SOC_ENUM_SINGLE(WM8958_AIF1_DAC1_NOISE_GATE, - WM8958_AIF1DAC1_NG_THR_SHIFT, 4, wm8958_ng_text); +static SOC_ENUM_SINGLE_DECL(wm8958_aif1dac1_ng_hold, + WM8958_AIF1_DAC1_NOISE_GATE, + WM8958_AIF1DAC1_NG_THR_SHIFT, + wm8958_ng_text); -static const struct soc_enum wm8958_aif1dac2_ng_hold = - SOC_ENUM_SINGLE(WM8958_AIF1_DAC2_NOISE_GATE, - WM8958_AIF1DAC2_NG_THR_SHIFT, 4, wm8958_ng_text); +static SOC_ENUM_SINGLE_DECL(wm8958_aif1dac2_ng_hold, + WM8958_AIF1_DAC2_NOISE_GATE, + WM8958_AIF1DAC2_NG_THR_SHIFT, + wm8958_ng_text); -static const struct soc_enum wm8958_aif2dac_ng_hold = - SOC_ENUM_SINGLE(WM8958_AIF2_DAC_NOISE_GATE, - WM8958_AIF2DAC_NG_THR_SHIFT, 4, wm8958_ng_text); +static SOC_ENUM_SINGLE_DECL(wm8958_aif2dac_ng_hold, + WM8958_AIF2_DAC_NOISE_GATE, + WM8958_AIF2DAC_NG_THR_SHIFT, + wm8958_ng_text); static const struct snd_kcontrol_new wm8958_snd_controls[] = { SOC_SINGLE_TLV("AIF3 Boost Volume", WM8958_AIF3_CONTROL_2, 10, 3, 0, aif_tlv), @@ -1341,8 +1344,8 @@ static const char *adc_mux_text[] = { "DMIC", }; -static const struct soc_enum adc_enum = - SOC_ENUM_SINGLE(0, 0, 2, adc_mux_text); +static SOC_ENUM_SINGLE_DECL(adc_enum, + 0, 0, adc_mux_text); static const struct snd_kcontrol_new adcl_mux = SOC_DAPM_ENUM_VIRT("ADCL Mux", adc_enum); @@ -1478,14 +1481,14 @@ static const char *sidetone_text[] = { "ADC/DMIC1", "DMIC2", }; -static const struct soc_enum sidetone1_enum = - SOC_ENUM_SINGLE(WM8994_SIDETONE, 0, 2, sidetone_text); +static SOC_ENUM_SINGLE_DECL(sidetone1_enum, + WM8994_SIDETONE, 0, sidetone_text); static const struct snd_kcontrol_new sidetone1_mux = SOC_DAPM_ENUM("Left Sidetone Mux", sidetone1_enum); -static const struct soc_enum sidetone2_enum = - SOC_ENUM_SINGLE(WM8994_SIDETONE, 1, 2, sidetone_text); +static SOC_ENUM_SINGLE_DECL(sidetone2_enum, + WM8994_SIDETONE, 1, sidetone_text); static const struct snd_kcontrol_new sidetone2_mux = SOC_DAPM_ENUM("Right Sidetone Mux", sidetone2_enum); @@ -1498,22 +1501,24 @@ static const char *loopback_text[] = { "None", "ADCDAT", }; -static const struct soc_enum aif1_loopback_enum = - SOC_ENUM_SINGLE(WM8994_AIF1_CONTROL_2, WM8994_AIF1_LOOPBACK_SHIFT, 2, - loopback_text); +static SOC_ENUM_SINGLE_DECL(aif1_loopback_enum, + WM8994_AIF1_CONTROL_2, + WM8994_AIF1_LOOPBACK_SHIFT, + loopback_text); static const struct snd_kcontrol_new aif1_loopback = SOC_DAPM_ENUM("AIF1 Loopback", aif1_loopback_enum); -static const struct soc_enum aif2_loopback_enum = - SOC_ENUM_SINGLE(WM8994_AIF2_CONTROL_2, WM8994_AIF2_LOOPBACK_SHIFT, 2, - loopback_text); +static SOC_ENUM_SINGLE_DECL(aif2_loopback_enum, + WM8994_AIF2_CONTROL_2, + WM8994_AIF2_LOOPBACK_SHIFT, + loopback_text); static const struct snd_kcontrol_new aif2_loopback = SOC_DAPM_ENUM("AIF2 Loopback", aif2_loopback_enum); -static const struct soc_enum aif1dac_enum = - SOC_ENUM_SINGLE(WM8994_POWER_MANAGEMENT_6, 0, 2, aif1dac_text); +static SOC_ENUM_SINGLE_DECL(aif1dac_enum, + WM8994_POWER_MANAGEMENT_6, 0, aif1dac_text); static const struct snd_kcontrol_new aif1dac_mux = SOC_DAPM_ENUM("AIF1DAC Mux", aif1dac_enum); @@ -1522,8 +1527,8 @@ static const char *aif2dac_text[] = { "AIF2DACDAT", "AIF3DACDAT", }; -static const struct soc_enum aif2dac_enum = - SOC_ENUM_SINGLE(WM8994_POWER_MANAGEMENT_6, 1, 2, aif2dac_text); +static SOC_ENUM_SINGLE_DECL(aif2dac_enum, + WM8994_POWER_MANAGEMENT_6, 1, aif2dac_text); static const struct snd_kcontrol_new aif2dac_mux = SOC_DAPM_ENUM("AIF2DAC Mux", aif2dac_enum); @@ -1532,8 +1537,8 @@ static const char *aif2adc_text[] = { "AIF2ADCDAT", "AIF3DACDAT", }; -static const struct soc_enum aif2adc_enum = - SOC_ENUM_SINGLE(WM8994_POWER_MANAGEMENT_6, 2, 2, aif2adc_text); +static SOC_ENUM_SINGLE_DECL(aif2adc_enum, + WM8994_POWER_MANAGEMENT_6, 2, aif2adc_text); static const struct snd_kcontrol_new aif2adc_mux = SOC_DAPM_ENUM("AIF2ADC Mux", aif2adc_enum); @@ -1542,14 +1547,14 @@ static const char *aif3adc_text[] = { "AIF1ADCDAT", "AIF2ADCDAT", "AIF2DACDAT", "Mono PCM", }; -static const struct soc_enum wm8994_aif3adc_enum = - SOC_ENUM_SINGLE(WM8994_POWER_MANAGEMENT_6, 3, 3, aif3adc_text); +static SOC_ENUM_SINGLE_DECL(wm8994_aif3adc_enum, + WM8994_POWER_MANAGEMENT_6, 3, aif3adc_text); static const struct snd_kcontrol_new wm8994_aif3adc_mux = SOC_DAPM_ENUM("AIF3ADC Mux", wm8994_aif3adc_enum); -static const struct soc_enum wm8958_aif3adc_enum = - SOC_ENUM_SINGLE(WM8994_POWER_MANAGEMENT_6, 3, 4, aif3adc_text); +static SOC_ENUM_SINGLE_DECL(wm8958_aif3adc_enum, + WM8994_POWER_MANAGEMENT_6, 3, aif3adc_text); static const struct snd_kcontrol_new wm8958_aif3adc_mux = SOC_DAPM_ENUM("AIF3ADC Mux", wm8958_aif3adc_enum); @@ -1558,8 +1563,8 @@ static const char *mono_pcm_out_text[] = { "None", "AIF2ADCL", "AIF2ADCR", }; -static const struct soc_enum mono_pcm_out_enum = - SOC_ENUM_SINGLE(WM8994_POWER_MANAGEMENT_6, 9, 3, mono_pcm_out_text); +static SOC_ENUM_SINGLE_DECL(mono_pcm_out_enum, + WM8994_POWER_MANAGEMENT_6, 9, mono_pcm_out_text); static const struct snd_kcontrol_new mono_pcm_out_mux = SOC_DAPM_ENUM("Mono PCM Out Mux", mono_pcm_out_enum); @@ -1569,14 +1574,14 @@ static const char *aif2dac_src_text[] = { }; /* Note that these two control shouldn't be simultaneously switched to AIF3 */ -static const struct soc_enum aif2dacl_src_enum = - SOC_ENUM_SINGLE(WM8994_POWER_MANAGEMENT_6, 7, 2, aif2dac_src_text); +static SOC_ENUM_SINGLE_DECL(aif2dacl_src_enum, + WM8994_POWER_MANAGEMENT_6, 7, aif2dac_src_text); static const struct snd_kcontrol_new aif2dacl_src_mux = SOC_DAPM_ENUM("AIF2DACL Mux", aif2dacl_src_enum); -static const struct soc_enum aif2dacr_src_enum = - SOC_ENUM_SINGLE(WM8994_POWER_MANAGEMENT_6, 8, 2, aif2dac_src_text); +static SOC_ENUM_SINGLE_DECL(aif2dacr_src_enum, + WM8994_POWER_MANAGEMENT_6, 8, aif2dac_src_text); static const struct snd_kcontrol_new aif2dacr_src_mux = SOC_DAPM_ENUM("AIF2DACR Mux", aif2dacr_src_enum); diff --git a/sound/soc/davinci/davinci-evm.c b/sound/soc/davinci/davinci-evm.c index 70ff3772079f..5e3bc3c6801a 100644 --- a/sound/soc/davinci/davinci-evm.c +++ b/sound/soc/davinci/davinci-evm.c @@ -399,6 +399,7 @@ static struct platform_driver davinci_evm_driver = { .driver = { .name = "davinci_evm", .owner = THIS_MODULE, + .pm = &snd_soc_pm_ops, .of_match_table = of_match_ptr(davinci_evm_dt_ids), }, }; diff --git a/sound/soc/davinci/davinci-mcasp.c b/sound/soc/davinci/davinci-mcasp.c index b7858bfa0295..670afa29e30d 100644 --- a/sound/soc/davinci/davinci-mcasp.c +++ b/sound/soc/davinci/davinci-mcasp.c @@ -263,7 +263,9 @@ static int davinci_mcasp_set_dai_fmt(struct snd_soc_dai *cpu_dai, unsigned int fmt) { struct davinci_mcasp *mcasp = snd_soc_dai_get_drvdata(cpu_dai); + int ret = 0; + pm_runtime_get_sync(mcasp->dev); switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) { case SND_SOC_DAIFMT_DSP_B: case SND_SOC_DAIFMT_AC97: @@ -317,7 +319,8 @@ static int davinci_mcasp_set_dai_fmt(struct snd_soc_dai *cpu_dai, break; default: - return -EINVAL; + ret = -EINVAL; + goto out; } switch (fmt & SND_SOC_DAIFMT_INV_MASK) { @@ -354,10 +357,12 @@ static int davinci_mcasp_set_dai_fmt(struct snd_soc_dai *cpu_dai, break; default: - return -EINVAL; + ret = -EINVAL; + break; } - - return 0; +out: + pm_runtime_put_sync(mcasp->dev); + return ret; } static int davinci_mcasp_set_clkdiv(struct snd_soc_dai *dai, int div_id, int div) @@ -448,7 +453,7 @@ static int davinci_config_channel_size(struct davinci_mcasp *mcasp, return 0; } -static int davinci_hw_common_param(struct davinci_mcasp *mcasp, int stream, +static int mcasp_common_hw_param(struct davinci_mcasp *mcasp, int stream, int channels) { int i; @@ -524,12 +529,18 @@ static int davinci_hw_common_param(struct davinci_mcasp *mcasp, int stream, return 0; } -static void davinci_hw_param(struct davinci_mcasp *mcasp, int stream) +static int mcasp_i2s_hw_param(struct davinci_mcasp *mcasp, int stream) { int i, active_slots; u32 mask = 0; u32 busel = 0; + if ((mcasp->tdm_slots < 2) || (mcasp->tdm_slots > 32)) { + dev_err(mcasp->dev, "tdm slot %d not supported\n", + mcasp->tdm_slots); + return -EINVAL; + } + active_slots = (mcasp->tdm_slots > 31) ? 32 : mcasp->tdm_slots; for (i = 0; i < active_slots; i++) mask |= (1 << i); @@ -539,35 +550,21 @@ static void davinci_hw_param(struct davinci_mcasp *mcasp, int stream) if (!mcasp->dat_port) busel = TXSEL; - if (stream == SNDRV_PCM_STREAM_PLAYBACK) { - /* bit stream is MSB first with no delay */ - /* DSP_B mode */ - mcasp_set_reg(mcasp, DAVINCI_MCASP_TXTDM_REG, mask); - mcasp_set_bits(mcasp, DAVINCI_MCASP_TXFMT_REG, busel | TXORD); - - if ((mcasp->tdm_slots >= 2) && (mcasp->tdm_slots <= 32)) - mcasp_mod_bits(mcasp, DAVINCI_MCASP_TXFMCTL_REG, - FSXMOD(mcasp->tdm_slots), FSXMOD(0x1FF)); - else - printk(KERN_ERR "playback tdm slot %d not supported\n", - mcasp->tdm_slots); - } else { - /* bit stream is MSB first with no delay */ - /* DSP_B mode */ - mcasp_set_bits(mcasp, DAVINCI_MCASP_RXFMT_REG, busel | RXORD); - mcasp_set_reg(mcasp, DAVINCI_MCASP_RXTDM_REG, mask); - - if ((mcasp->tdm_slots >= 2) && (mcasp->tdm_slots <= 32)) - mcasp_mod_bits(mcasp, DAVINCI_MCASP_RXFMCTL_REG, - FSRMOD(mcasp->tdm_slots), FSRMOD(0x1FF)); - else - printk(KERN_ERR "capture tdm slot %d not supported\n", - mcasp->tdm_slots); - } + mcasp_set_reg(mcasp, DAVINCI_MCASP_TXTDM_REG, mask); + mcasp_set_bits(mcasp, DAVINCI_MCASP_TXFMT_REG, busel | TXORD); + mcasp_mod_bits(mcasp, DAVINCI_MCASP_TXFMCTL_REG, + FSXMOD(mcasp->tdm_slots), FSXMOD(0x1FF)); + + mcasp_set_reg(mcasp, DAVINCI_MCASP_RXTDM_REG, mask); + mcasp_set_bits(mcasp, DAVINCI_MCASP_RXFMT_REG, busel | RXORD); + mcasp_mod_bits(mcasp, DAVINCI_MCASP_RXFMCTL_REG, + FSRMOD(mcasp->tdm_slots), FSRMOD(0x1FF)); + + return 0; } /* S/PDIF */ -static void davinci_hw_dit_param(struct davinci_mcasp *mcasp) +static int mcasp_dit_hw_param(struct davinci_mcasp *mcasp) { /* Set the TX format : 24 bit right rotation, 32 bit slot, Pad 0 and LSB first */ @@ -589,6 +586,8 @@ static void davinci_hw_dit_param(struct davinci_mcasp *mcasp) /* Enable the DIT */ mcasp_set_bits(mcasp, DAVINCI_MCASP_TXDITCTL_REG, DITEN); + + return 0; } static int davinci_mcasp_hw_params(struct snd_pcm_substream *substream, @@ -605,13 +604,14 @@ static int davinci_mcasp_hw_params(struct snd_pcm_substream *substream, u8 slots = mcasp->tdm_slots; u8 active_serializers; int channels; + int ret; struct snd_interval *pcm_channels = hw_param_interval(params, SNDRV_PCM_HW_PARAM_CHANNELS); channels = pcm_channels->min; active_serializers = (channels + slots - 1) / slots; - if (davinci_hw_common_param(mcasp, substream->stream, channels) == -EINVAL) + if (mcasp_common_hw_param(mcasp, substream->stream, channels) == -EINVAL) return -EINVAL; if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) fifo_level = mcasp->txnumevt * active_serializers; @@ -619,9 +619,12 @@ static int davinci_mcasp_hw_params(struct snd_pcm_substream *substream, fifo_level = mcasp->rxnumevt * active_serializers; if (mcasp->op_mode == DAVINCI_MCASP_DIT_MODE) - davinci_hw_dit_param(mcasp); + ret = mcasp_dit_hw_param(mcasp); else - davinci_hw_param(mcasp, substream->stream); + ret = mcasp_i2s_hw_param(mcasp, substream->stream); + + if (ret) + return ret; switch (params_format(params)) { case SNDRV_PCM_FORMAT_U8: @@ -678,19 +681,9 @@ static int davinci_mcasp_trigger(struct snd_pcm_substream *substream, case SNDRV_PCM_TRIGGER_RESUME: case SNDRV_PCM_TRIGGER_START: case SNDRV_PCM_TRIGGER_PAUSE_RELEASE: - ret = pm_runtime_get_sync(mcasp->dev); - if (IS_ERR_VALUE(ret)) - dev_err(mcasp->dev, "pm_runtime_get_sync() failed\n"); davinci_mcasp_start(mcasp, substream->stream); break; - case SNDRV_PCM_TRIGGER_SUSPEND: - davinci_mcasp_stop(mcasp, substream->stream); - ret = pm_runtime_put_sync(mcasp->dev); - if (IS_ERR_VALUE(ret)) - dev_err(mcasp->dev, "pm_runtime_put_sync() failed\n"); - break; - case SNDRV_PCM_TRIGGER_STOP: case SNDRV_PCM_TRIGGER_PAUSE_PUSH: davinci_mcasp_stop(mcasp, substream->stream); diff --git a/sound/soc/fsl/fsl_esai.c b/sound/soc/fsl/fsl_esai.c index d0c72ed261e7..c84026c99134 100644 --- a/sound/soc/fsl/fsl_esai.c +++ b/sound/soc/fsl/fsl_esai.c @@ -326,7 +326,7 @@ static int fsl_esai_set_dai_tdm_slot(struct snd_soc_dai *dai, u32 tx_mask, regmap_update_bits(esai_priv->regmap, REG_ESAI_TSMA, ESAI_xSMA_xS_MASK, ESAI_xSMA_xS(tx_mask)); regmap_update_bits(esai_priv->regmap, REG_ESAI_TSMB, - ESAI_xSMA_xS_MASK, ESAI_xSMB_xS(tx_mask)); + ESAI_xSMB_xS_MASK, ESAI_xSMB_xS(tx_mask)); regmap_update_bits(esai_priv->regmap, REG_ESAI_RCCR, ESAI_xCCR_xDC_MASK, ESAI_xCCR_xDC(slots)); @@ -334,7 +334,7 @@ static int fsl_esai_set_dai_tdm_slot(struct snd_soc_dai *dai, u32 tx_mask, regmap_update_bits(esai_priv->regmap, REG_ESAI_RSMA, ESAI_xSMA_xS_MASK, ESAI_xSMA_xS(rx_mask)); regmap_update_bits(esai_priv->regmap, REG_ESAI_RSMB, - ESAI_xSMA_xS_MASK, ESAI_xSMB_xS(rx_mask)); + ESAI_xSMB_xS_MASK, ESAI_xSMB_xS(rx_mask)); esai_priv->slot_width = slot_width; diff --git a/sound/soc/fsl/fsl_esai.h b/sound/soc/fsl/fsl_esai.h index 9c9f957fcae1..75e14033e8d8 100644 --- a/sound/soc/fsl/fsl_esai.h +++ b/sound/soc/fsl/fsl_esai.h @@ -322,7 +322,7 @@ #define ESAI_xSMB_xS_SHIFT 0 #define ESAI_xSMB_xS_WIDTH 16 #define ESAI_xSMB_xS_MASK (((1 << ESAI_xSMB_xS_WIDTH) - 1) << ESAI_xSMB_xS_SHIFT) -#define ESAI_xSMB_xS(v) (((v) >> ESAI_xSMA_xS_WIDTH) & ESAI_xSMA_xS_MASK) +#define ESAI_xSMB_xS(v) (((v) >> ESAI_xSMA_xS_WIDTH) & ESAI_xSMB_xS_MASK) /* Port C Direction Register -- REG_ESAI_PRRC 0xF8 */ #define ESAI_PRRC_PDC_SHIFT 0 diff --git a/sound/soc/fsl/imx-mc13783.c b/sound/soc/fsl/imx-mc13783.c index 79cee782dbbf..a2fd7321b5a9 100644 --- a/sound/soc/fsl/imx-mc13783.c +++ b/sound/soc/fsl/imx-mc13783.c @@ -160,7 +160,6 @@ static struct platform_driver imx_mc13783_audio_driver = { .driver = { .name = "imx_mc13783", .owner = THIS_MODULE, - .pm = &snd_soc_pm_ops, }, .probe = imx_mc13783_probe, .remove = imx_mc13783_remove diff --git a/sound/soc/fsl/imx-sgtl5000.c b/sound/soc/fsl/imx-sgtl5000.c index f2beae78969f..1cb22dd034eb 100644 --- a/sound/soc/fsl/imx-sgtl5000.c +++ b/sound/soc/fsl/imx-sgtl5000.c @@ -33,8 +33,7 @@ struct imx_sgtl5000_data { static int imx_sgtl5000_dai_init(struct snd_soc_pcm_runtime *rtd) { - struct imx_sgtl5000_data *data = container_of(rtd->card, - struct imx_sgtl5000_data, card); + struct imx_sgtl5000_data *data = snd_soc_card_get_drvdata(rtd->card); struct device *dev = rtd->card->dev; int ret; @@ -159,13 +158,15 @@ static int imx_sgtl5000_probe(struct platform_device *pdev) data->card.dapm_widgets = imx_sgtl5000_dapm_widgets; data->card.num_dapm_widgets = ARRAY_SIZE(imx_sgtl5000_dapm_widgets); + platform_set_drvdata(pdev, &data->card); + snd_soc_card_set_drvdata(&data->card, data); + ret = devm_snd_soc_register_card(&pdev->dev, &data->card); if (ret) { dev_err(&pdev->dev, "snd_soc_register_card failed (%d)\n", ret); goto fail; } - platform_set_drvdata(pdev, data); of_node_put(ssi_np); of_node_put(codec_np); @@ -184,7 +185,8 @@ fail: static int imx_sgtl5000_remove(struct platform_device *pdev) { - struct imx_sgtl5000_data *data = platform_get_drvdata(pdev); + struct snd_soc_card *card = platform_get_drvdata(pdev); + struct imx_sgtl5000_data *data = snd_soc_card_get_drvdata(card); clk_put(data->codec_clk); diff --git a/sound/soc/fsl/imx-wm8962.c b/sound/soc/fsl/imx-wm8962.c index 3fd76bc391de..3a3d17ce6ba4 100644 --- a/sound/soc/fsl/imx-wm8962.c +++ b/sound/soc/fsl/imx-wm8962.c @@ -71,7 +71,7 @@ static int imx_wm8962_set_bias_level(struct snd_soc_card *card, { struct snd_soc_dai *codec_dai = card->rtd[0].codec_dai; struct imx_priv *priv = &card_priv; - struct imx_wm8962_data *data = platform_get_drvdata(priv->pdev); + struct imx_wm8962_data *data = snd_soc_card_get_drvdata(card); struct device *dev = &priv->pdev->dev; unsigned int pll_out; int ret; @@ -137,7 +137,7 @@ static int imx_wm8962_late_probe(struct snd_soc_card *card) { struct snd_soc_dai *codec_dai = card->rtd[0].codec_dai; struct imx_priv *priv = &card_priv; - struct imx_wm8962_data *data = platform_get_drvdata(priv->pdev); + struct imx_wm8962_data *data = snd_soc_card_get_drvdata(card); struct device *dev = &priv->pdev->dev; int ret; @@ -264,13 +264,15 @@ static int imx_wm8962_probe(struct platform_device *pdev) data->card.late_probe = imx_wm8962_late_probe; data->card.set_bias_level = imx_wm8962_set_bias_level; + platform_set_drvdata(pdev, &data->card); + snd_soc_card_set_drvdata(&data->card, data); + ret = devm_snd_soc_register_card(&pdev->dev, &data->card); if (ret) { dev_err(&pdev->dev, "snd_soc_register_card failed (%d)\n", ret); goto clk_fail; } - platform_set_drvdata(pdev, data); of_node_put(ssi_np); of_node_put(codec_np); @@ -289,7 +291,8 @@ fail: static int imx_wm8962_remove(struct platform_device *pdev) { - struct imx_wm8962_data *data = platform_get_drvdata(pdev); + struct snd_soc_card *card = platform_get_drvdata(pdev); + struct imx_wm8962_data *data = snd_soc_card_get_drvdata(card); if (!IS_ERR(data->codec_clk)) clk_disable_unprepare(data->codec_clk); diff --git a/sound/soc/samsung/Kconfig b/sound/soc/samsung/Kconfig index 454f41cfc828..350757400391 100644 --- a/sound/soc/samsung/Kconfig +++ b/sound/soc/samsung/Kconfig @@ -59,7 +59,7 @@ config SND_SOC_SAMSUNG_JIVE_WM8750 select SND_SOC_WM8750 select SND_S3C2412_SOC_I2S help - Sat Y if you want to add support for SoC audio on the Jive. + Say Y if you want to add support for SoC audio on the Jive. config SND_SOC_SAMSUNG_SMDK_WM8580 tristate "SoC I2S Audio support for WM8580 on SMDK" @@ -145,11 +145,11 @@ config SND_SOC_SAMSUNG_RX1950_UDA1380 config SND_SOC_SAMSUNG_SMDK_WM9713 tristate "SoC AC97 Audio support for SMDK with WM9713" - depends on SND_SOC_SAMSUNG && (MACH_SMDK6410 || MACH_SMDKC100 || MACH_SMDKV210 || MACH_SMDKC110 || MACH_SMDKV310 || MACH_SMDKC210) + depends on SND_SOC_SAMSUNG && (MACH_SMDK6410 || MACH_SMDKC100 || MACH_SMDKV210 || MACH_SMDKC110) select SND_SOC_WM9713 select SND_SAMSUNG_AC97 help - Sat Y if you want to add support for SoC audio on the SMDK. + Say Y if you want to add support for SoC audio on the SMDK. config SND_SOC_SMARTQ tristate "SoC I2S Audio support for SmartQ board" diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c index dc8ff13187f7..b9dc6acbba8c 100644 --- a/sound/soc/soc-dapm.c +++ b/sound/soc/soc-dapm.c @@ -1218,7 +1218,7 @@ int dapm_regulator_event(struct snd_soc_dapm_widget *w, ret = regulator_allow_bypass(w->regulator, false); if (ret != 0) dev_warn(w->dapm->dev, - "ASoC: Failed to bypass %s: %d\n", + "ASoC: Failed to unbypass %s: %d\n", w->name, ret); } @@ -1228,7 +1228,7 @@ int dapm_regulator_event(struct snd_soc_dapm_widget *w, ret = regulator_allow_bypass(w->regulator, true); if (ret != 0) dev_warn(w->dapm->dev, - "ASoC: Failed to unbypass %s: %d\n", + "ASoC: Failed to bypass %s: %d\n", w->name, ret); } @@ -3210,15 +3210,11 @@ int snd_soc_dapm_put_pin_switch(struct snd_kcontrol *kcontrol, struct snd_soc_card *card = snd_kcontrol_chip(kcontrol); const char *pin = (const char *)kcontrol->private_value; - mutex_lock_nested(&card->dapm_mutex, SND_SOC_DAPM_CLASS_RUNTIME); - if (ucontrol->value.integer.value[0]) snd_soc_dapm_enable_pin(&card->dapm, pin); else snd_soc_dapm_disable_pin(&card->dapm, pin); - mutex_unlock(&card->dapm_mutex); - snd_soc_dapm_sync(&card->dapm); return 0; } @@ -3248,7 +3244,7 @@ snd_soc_dapm_new_control(struct snd_soc_dapm_context *dapm, ret = regulator_allow_bypass(w->regulator, true); if (ret != 0) dev_warn(w->dapm->dev, - "ASoC: Failed to unbypass %s: %d\n", + "ASoC: Failed to bypass %s: %d\n", w->name, ret); } break; @@ -3767,23 +3763,52 @@ void snd_soc_dapm_stream_event(struct snd_soc_pcm_runtime *rtd, int stream, } /** + * snd_soc_dapm_enable_pin_unlocked - enable pin. + * @dapm: DAPM context + * @pin: pin name + * + * Enables input/output pin and its parents or children widgets iff there is + * a valid audio route and active audio stream. + * + * Requires external locking. + * + * NOTE: snd_soc_dapm_sync() needs to be called after this for DAPM to + * do any widget power switching. + */ +int snd_soc_dapm_enable_pin_unlocked(struct snd_soc_dapm_context *dapm, + const char *pin) +{ + return snd_soc_dapm_set_pin(dapm, pin, 1); +} +EXPORT_SYMBOL_GPL(snd_soc_dapm_enable_pin_unlocked); + +/** * snd_soc_dapm_enable_pin - enable pin. * @dapm: DAPM context * @pin: pin name * * Enables input/output pin and its parents or children widgets iff there is * a valid audio route and active audio stream. + * * NOTE: snd_soc_dapm_sync() needs to be called after this for DAPM to * do any widget power switching. */ int snd_soc_dapm_enable_pin(struct snd_soc_dapm_context *dapm, const char *pin) { - return snd_soc_dapm_set_pin(dapm, pin, 1); + int ret; + + mutex_lock_nested(&dapm->card->dapm_mutex, SND_SOC_DAPM_CLASS_RUNTIME); + + ret = snd_soc_dapm_set_pin(dapm, pin, 1); + + mutex_unlock(&dapm->card->dapm_mutex); + + return ret; } EXPORT_SYMBOL_GPL(snd_soc_dapm_enable_pin); /** - * snd_soc_dapm_force_enable_pin - force a pin to be enabled + * snd_soc_dapm_force_enable_pin_unlocked - force a pin to be enabled * @dapm: DAPM context * @pin: pin name * @@ -3791,11 +3816,13 @@ EXPORT_SYMBOL_GPL(snd_soc_dapm_enable_pin); * intended for use with microphone bias supplies used in microphone * jack detection. * + * Requires external locking. + * * NOTE: snd_soc_dapm_sync() needs to be called after this for DAPM to * do any widget power switching. */ -int snd_soc_dapm_force_enable_pin(struct snd_soc_dapm_context *dapm, - const char *pin) +int snd_soc_dapm_force_enable_pin_unlocked(struct snd_soc_dapm_context *dapm, + const char *pin) { struct snd_soc_dapm_widget *w = dapm_find_widget(dapm, pin, true); @@ -3811,25 +3838,103 @@ int snd_soc_dapm_force_enable_pin(struct snd_soc_dapm_context *dapm, return 0; } +EXPORT_SYMBOL_GPL(snd_soc_dapm_force_enable_pin_unlocked); + +/** + * snd_soc_dapm_force_enable_pin - force a pin to be enabled + * @dapm: DAPM context + * @pin: pin name + * + * Enables input/output pin regardless of any other state. This is + * intended for use with microphone bias supplies used in microphone + * jack detection. + * + * NOTE: snd_soc_dapm_sync() needs to be called after this for DAPM to + * do any widget power switching. + */ +int snd_soc_dapm_force_enable_pin(struct snd_soc_dapm_context *dapm, + const char *pin) +{ + int ret; + + mutex_lock_nested(&dapm->card->dapm_mutex, SND_SOC_DAPM_CLASS_RUNTIME); + + ret = snd_soc_dapm_force_enable_pin_unlocked(dapm, pin); + + mutex_unlock(&dapm->card->dapm_mutex); + + return ret; +} EXPORT_SYMBOL_GPL(snd_soc_dapm_force_enable_pin); /** + * snd_soc_dapm_disable_pin_unlocked - disable pin. + * @dapm: DAPM context + * @pin: pin name + * + * Disables input/output pin and its parents or children widgets. + * + * Requires external locking. + * + * NOTE: snd_soc_dapm_sync() needs to be called after this for DAPM to + * do any widget power switching. + */ +int snd_soc_dapm_disable_pin_unlocked(struct snd_soc_dapm_context *dapm, + const char *pin) +{ + return snd_soc_dapm_set_pin(dapm, pin, 0); +} +EXPORT_SYMBOL_GPL(snd_soc_dapm_disable_pin_unlocked); + +/** * snd_soc_dapm_disable_pin - disable pin. * @dapm: DAPM context * @pin: pin name * * Disables input/output pin and its parents or children widgets. + * * NOTE: snd_soc_dapm_sync() needs to be called after this for DAPM to * do any widget power switching. */ int snd_soc_dapm_disable_pin(struct snd_soc_dapm_context *dapm, const char *pin) { - return snd_soc_dapm_set_pin(dapm, pin, 0); + int ret; + + mutex_lock_nested(&dapm->card->dapm_mutex, SND_SOC_DAPM_CLASS_RUNTIME); + + ret = snd_soc_dapm_set_pin(dapm, pin, 0); + + mutex_unlock(&dapm->card->dapm_mutex); + + return ret; } EXPORT_SYMBOL_GPL(snd_soc_dapm_disable_pin); /** + * snd_soc_dapm_nc_pin_unlocked - permanently disable pin. + * @dapm: DAPM context + * @pin: pin name + * + * Marks the specified pin as being not connected, disabling it along + * any parent or child widgets. At present this is identical to + * snd_soc_dapm_disable_pin() but in future it will be extended to do + * additional things such as disabling controls which only affect + * paths through the pin. + * + * Requires external locking. + * + * NOTE: snd_soc_dapm_sync() needs to be called after this for DAPM to + * do any widget power switching. + */ +int snd_soc_dapm_nc_pin_unlocked(struct snd_soc_dapm_context *dapm, + const char *pin) +{ + return snd_soc_dapm_set_pin(dapm, pin, 0); +} +EXPORT_SYMBOL_GPL(snd_soc_dapm_nc_pin_unlocked); + +/** * snd_soc_dapm_nc_pin - permanently disable pin. * @dapm: DAPM context * @pin: pin name @@ -3845,7 +3950,15 @@ EXPORT_SYMBOL_GPL(snd_soc_dapm_disable_pin); */ int snd_soc_dapm_nc_pin(struct snd_soc_dapm_context *dapm, const char *pin) { - return snd_soc_dapm_set_pin(dapm, pin, 0); + int ret; + + mutex_lock_nested(&dapm->card->dapm_mutex, SND_SOC_DAPM_CLASS_RUNTIME); + + ret = snd_soc_dapm_set_pin(dapm, pin, 0); + + mutex_unlock(&dapm->card->dapm_mutex); + + return ret; } EXPORT_SYMBOL_GPL(snd_soc_dapm_nc_pin); diff --git a/sound/soc/txx9/txx9aclc-ac97.c b/sound/soc/txx9/txx9aclc-ac97.c index e0305a148568..9edd68db9f48 100644 --- a/sound/soc/txx9/txx9aclc-ac97.c +++ b/sound/soc/txx9/txx9aclc-ac97.c @@ -183,14 +183,16 @@ static int txx9aclc_ac97_dev_probe(struct platform_device *pdev) irq = platform_get_irq(pdev, 0); if (irq < 0) return irq; + + drvdata = devm_kzalloc(&pdev->dev, sizeof(*drvdata), GFP_KERNEL); + if (!drvdata) + return -ENOMEM; + r = platform_get_resource(pdev, IORESOURCE_MEM, 0); drvdata->base = devm_ioremap_resource(&pdev->dev, r); if (IS_ERR(drvdata->base)) return PTR_ERR(drvdata->base); - drvdata = devm_kzalloc(&pdev->dev, sizeof(*drvdata), GFP_KERNEL); - if (!drvdata) - return -ENOMEM; platform_set_drvdata(pdev, drvdata); drvdata->physbase = r->start; if (sizeof(drvdata->physbase) > sizeof(r->start) && diff --git a/sound/usb/mixer_maps.c b/sound/usb/mixer_maps.c index 32af6b741ef5..d1d72ff50347 100644 --- a/sound/usb/mixer_maps.c +++ b/sound/usb/mixer_maps.c @@ -328,6 +328,11 @@ static struct usbmix_name_map gamecom780_map[] = { {} }; +static const struct usbmix_name_map kef_x300a_map[] = { + { 10, NULL }, /* firmware locks up (?) when we try to access this FU */ + { 0 } +}; + /* * Control map entries */ @@ -419,6 +424,10 @@ static struct usbmix_ctl_map usbmix_ctl_maps[] = { .id = USB_ID(0x200c, 0x1018), .map = ebox44_map, }, + { + .id = USB_ID(0x27ac, 0x1000), + .map = kef_x300a_map, + }, { 0 } /* terminator */ }; diff --git a/tools/lib/lockdep/Makefile b/tools/lib/lockdep/Makefile index da8b7aa3d351..07b0b7542511 100644 --- a/tools/lib/lockdep/Makefile +++ b/tools/lib/lockdep/Makefile @@ -87,8 +87,8 @@ endif # BUILD_SRC # We process the rest of the Makefile if this is the final invocation of make ifeq ($(skip-makefile),) -srctree := $(if $(BUILD_SRC),$(BUILD_SRC),$(CURDIR)) -objtree := $(CURDIR) +srctree := $(realpath $(if $(BUILD_SRC),$(BUILD_SRC),$(CURDIR))) +objtree := $(realpath $(CURDIR)) src := $(srctree) obj := $(objtree) @@ -112,7 +112,7 @@ export Q VERBOSE LIBLOCKDEP_VERSION = $(LL_VERSION).$(LL_PATCHLEVEL).$(LL_EXTRAVERSION) -INCLUDES = -I. -I/usr/local/include -I./uinclude $(CONFIG_INCLUDES) +INCLUDES = -I. -I/usr/local/include -I./uinclude -I./include $(CONFIG_INCLUDES) # Set compile option CFLAGS if not set elsewhere CFLAGS ?= -g -DCONFIG_LOCKDEP -DCONFIG_STACKTRACE -DCONFIG_PROVE_LOCKING -DBITS_PER_LONG=__WORDSIZE -DLIBLOCKDEP_VERSION='"$(LIBLOCKDEP_VERSION)"' -rdynamic -O0 -g diff --git a/tools/lib/lockdep/preload.c b/tools/lib/lockdep/preload.c index f8465a811aa5..23bd69cb5ade 100644 --- a/tools/lib/lockdep/preload.c +++ b/tools/lib/lockdep/preload.c @@ -418,7 +418,7 @@ int pthread_rwlock_unlock(pthread_rwlock_t *rwlock) __attribute__((constructor)) static void init_preload(void) { - if (__init_state != done) + if (__init_state == done) return; #ifndef __GLIBC__ diff --git a/tools/lib/lockdep/run_tests.sh b/tools/lib/lockdep/run_tests.sh index 5334ad9d39b7..5334ad9d39b7 100644..100755 --- a/tools/lib/lockdep/run_tests.sh +++ b/tools/lib/lockdep/run_tests.sh diff --git a/tools/lib/lockdep/uinclude/asm/hash.h b/tools/lib/lockdep/uinclude/asm/hash.h new file mode 100644 index 000000000000..d82b170bb216 --- /dev/null +++ b/tools/lib/lockdep/uinclude/asm/hash.h @@ -0,0 +1,6 @@ +#ifndef __ASM_GENERIC_HASH_H +#define __ASM_GENERIC_HASH_H + +/* Stub */ + +#endif /* __ASM_GENERIC_HASH_H */ diff --git a/tools/lib/lockdep/uinclude/linux/rcu.h b/tools/lib/lockdep/uinclude/linux/rcu.h index 4c99fcb5da27..042ee8e463c9 100644 --- a/tools/lib/lockdep/uinclude/linux/rcu.h +++ b/tools/lib/lockdep/uinclude/linux/rcu.h @@ -13,4 +13,9 @@ static inline int rcu_is_cpu_idle(void) return 1; } +static inline bool rcu_is_watching(void) +{ + return false; +} + #endif diff --git a/tools/net/bpf_dbg.c b/tools/net/bpf_dbg.c index 65dc757f7f7b..bb31813e43dd 100644 --- a/tools/net/bpf_dbg.c +++ b/tools/net/bpf_dbg.c @@ -87,9 +87,6 @@ __attribute__ ((format (printf, (pos_fmtstr), (pos_fmtargs)))) #endif -#define CMD(_name, _func) { .name = _name, .func = _func, } -#define OP(_op, _name) [_op] = _name - enum { CMD_OK, CMD_ERR, @@ -145,32 +142,32 @@ static size_t pcap_map_size = 0; static char *pcap_ptr_va_start, *pcap_ptr_va_curr; static const char * const op_table[] = { - OP(BPF_ST, "st"), - OP(BPF_STX, "stx"), - OP(BPF_LD_B, "ldb"), - OP(BPF_LD_H, "ldh"), - OP(BPF_LD_W, "ld"), - OP(BPF_LDX, "ldx"), - OP(BPF_LDX_B, "ldxb"), - OP(BPF_JMP_JA, "ja"), - OP(BPF_JMP_JEQ, "jeq"), - OP(BPF_JMP_JGT, "jgt"), - OP(BPF_JMP_JGE, "jge"), - OP(BPF_JMP_JSET, "jset"), - OP(BPF_ALU_ADD, "add"), - OP(BPF_ALU_SUB, "sub"), - OP(BPF_ALU_MUL, "mul"), - OP(BPF_ALU_DIV, "div"), - OP(BPF_ALU_MOD, "mod"), - OP(BPF_ALU_NEG, "neg"), - OP(BPF_ALU_AND, "and"), - OP(BPF_ALU_OR, "or"), - OP(BPF_ALU_XOR, "xor"), - OP(BPF_ALU_LSH, "lsh"), - OP(BPF_ALU_RSH, "rsh"), - OP(BPF_MISC_TAX, "tax"), - OP(BPF_MISC_TXA, "txa"), - OP(BPF_RET, "ret"), + [BPF_ST] = "st", + [BPF_STX] = "stx", + [BPF_LD_B] = "ldb", + [BPF_LD_H] = "ldh", + [BPF_LD_W] = "ld", + [BPF_LDX] = "ldx", + [BPF_LDX_B] = "ldxb", + [BPF_JMP_JA] = "ja", + [BPF_JMP_JEQ] = "jeq", + [BPF_JMP_JGT] = "jgt", + [BPF_JMP_JGE] = "jge", + [BPF_JMP_JSET] = "jset", + [BPF_ALU_ADD] = "add", + [BPF_ALU_SUB] = "sub", + [BPF_ALU_MUL] = "mul", + [BPF_ALU_DIV] = "div", + [BPF_ALU_MOD] = "mod", + [BPF_ALU_NEG] = "neg", + [BPF_ALU_AND] = "and", + [BPF_ALU_OR] = "or", + [BPF_ALU_XOR] = "xor", + [BPF_ALU_LSH] = "lsh", + [BPF_ALU_RSH] = "rsh", + [BPF_MISC_TAX] = "tax", + [BPF_MISC_TXA] = "txa", + [BPF_RET] = "ret", }; static __check_format_printf(1, 2) int rl_printf(const char *fmt, ...) @@ -1127,7 +1124,6 @@ static int cmd_step(char *num) static int cmd_select(char *num) { unsigned int which, i; - struct pcap_pkthdr *hdr; bool have_next = true; if (!pcap_loaded() || strlen(num) == 0) @@ -1144,7 +1140,7 @@ static int cmd_select(char *num) for (i = 0; i < which && (have_next = pcap_next_pkt()); i++) /* noop */; - if (!have_next || (hdr = pcap_curr_pkt()) == NULL) { + if (!have_next || pcap_curr_pkt() == NULL) { rl_printf("no packet #%u available!\n", which); pcap_reset_pkt(); return CMD_ERR; @@ -1177,9 +1173,8 @@ static int cmd_breakpoint(char *subcmd) static int cmd_run(char *num) { static uint32_t pass = 0, fail = 0; - struct pcap_pkthdr *hdr; bool has_limit = true; - int ret, pkts = 0, i = 0; + int pkts = 0, i = 0; if (!bpf_prog_loaded() || !pcap_loaded()) return CMD_ERR; @@ -1189,10 +1184,10 @@ static int cmd_run(char *num) has_limit = false; do { - hdr = pcap_curr_pkt(); - ret = bpf_run_all(bpf_image, bpf_prog_len, - (uint8_t *) hdr + sizeof(*hdr), - hdr->caplen, hdr->len); + struct pcap_pkthdr *hdr = pcap_curr_pkt(); + int ret = bpf_run_all(bpf_image, bpf_prog_len, + (uint8_t *) hdr + sizeof(*hdr), + hdr->caplen, hdr->len); if (ret > 0) pass++; else if (ret == 0) @@ -1245,14 +1240,14 @@ static int cmd_quit(char *dontcare) } static const struct shell_cmd cmds[] = { - CMD("load", cmd_load), - CMD("select", cmd_select), - CMD("step", cmd_step), - CMD("run", cmd_run), - CMD("breakpoint", cmd_breakpoint), - CMD("disassemble", cmd_disassemble), - CMD("dump", cmd_dump), - CMD("quit", cmd_quit), + { .name = "load", .func = cmd_load }, + { .name = "select", .func = cmd_select }, + { .name = "step", .func = cmd_step }, + { .name = "run", .func = cmd_run }, + { .name = "breakpoint", .func = cmd_breakpoint }, + { .name = "disassemble", .func = cmd_disassemble }, + { .name = "dump", .func = cmd_dump }, + { .name = "quit", .func = cmd_quit }, }; static int execf(char *arg) @@ -1280,7 +1275,6 @@ out: static char *shell_comp_gen(const char *buf, int state) { static int list_index, len; - const char *name; if (!state) { list_index = 0; @@ -1288,9 +1282,9 @@ static char *shell_comp_gen(const char *buf, int state) } for (; list_index < array_size(cmds); ) { - name = cmds[list_index].name; - list_index++; + const char *name = cmds[list_index].name; + list_index++; if (strncmp(name, buf, len) == 0) return strdup(name); } @@ -1322,16 +1316,9 @@ static void init_shell(FILE *fin, FILE *fout) { char file[128]; - memset(file, 0, sizeof(file)); - snprintf(file, sizeof(file) - 1, - "%s/.bpf_dbg_history", getenv("HOME")); - + snprintf(file, sizeof(file), "%s/.bpf_dbg_history", getenv("HOME")); read_history(file); - memset(file, 0, sizeof(file)); - snprintf(file, sizeof(file) - 1, - "%s/.bpf_dbg_init", getenv("HOME")); - rl_instream = fin; rl_outstream = fout; @@ -1348,37 +1335,41 @@ static void init_shell(FILE *fin, FILE *fout) rl_bind_key_in_map('\t', rl_complete, emacs_meta_keymap); rl_bind_key_in_map('\033', rl_complete, emacs_meta_keymap); + snprintf(file, sizeof(file), "%s/.bpf_dbg_init", getenv("HOME")); rl_read_init_file(file); + rl_prep_terminal(0); rl_set_signals(); signal(SIGINT, intr_shell); } -static void exit_shell(void) +static void exit_shell(FILE *fin, FILE *fout) { char file[128]; - memset(file, 0, sizeof(file)); - snprintf(file, sizeof(file) - 1, - "%s/.bpf_dbg_history", getenv("HOME")); - + snprintf(file, sizeof(file), "%s/.bpf_dbg_history", getenv("HOME")); write_history(file); + clear_history(); rl_deprep_terminal(); try_close_pcap(); + + if (fin != stdin) + fclose(fin); + if (fout != stdout) + fclose(fout); } static int run_shell_loop(FILE *fin, FILE *fout) { char *buf; - int ret; init_shell(fin, fout); while ((buf = readline("> ")) != NULL) { - ret = execf(buf); + int ret = execf(buf); if (ret == CMD_EX) break; if (ret == CMD_OK && strlen(buf) > 0) @@ -1387,7 +1378,7 @@ static int run_shell_loop(FILE *fin, FILE *fout) free(buf); } - exit_shell(); + exit_shell(fin, fout); return 0; } diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 3c53ec268fbc..02f985f3a396 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -113,14 +113,16 @@ static int report__add_mem_hist_entry(struct perf_tool *tool, struct addr_locati if (!he) return -ENOMEM; - err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr); - if (err) - goto out; + if (ui__has_annotation()) { + err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr); + if (err) + goto out; - mx = he->mem_info; - err = addr_map_symbol__inc_samples(&mx->daddr, evsel->idx); - if (err) - goto out; + mx = he->mem_info; + err = addr_map_symbol__inc_samples(&mx->daddr, evsel->idx); + if (err) + goto out; + } evsel->hists.stats.total_period += cost; hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE); @@ -164,14 +166,18 @@ static int report__add_branch_hist_entry(struct perf_tool *tool, struct addr_loc he = __hists__add_entry(&evsel->hists, al, parent, &bi[i], NULL, 1, 1, 0); if (he) { - bx = he->branch_info; - err = addr_map_symbol__inc_samples(&bx->from, evsel->idx); - if (err) - goto out; - - err = addr_map_symbol__inc_samples(&bx->to, evsel->idx); - if (err) - goto out; + if (ui__has_annotation()) { + bx = he->branch_info; + err = addr_map_symbol__inc_samples(&bx->from, + evsel->idx); + if (err) + goto out; + + err = addr_map_symbol__inc_samples(&bx->to, + evsel->idx); + if (err) + goto out; + } evsel->hists.stats.total_period += 1; hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE); @@ -205,7 +211,9 @@ static int report__add_hist_entry(struct perf_tool *tool, struct perf_evsel *evs if (err) goto out; - err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr); + if (ui__has_annotation()) + err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr); + evsel->hists.stats.total_period += sample->period; hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE); out: diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 76cd510d34d0..5f989a7d8bc2 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -176,7 +176,7 @@ static void perf_top__record_precise_ip(struct perf_top *top, { struct annotation *notes; struct symbol *sym; - int err; + int err = 0; if (he == NULL || he->ms.sym == NULL || ((top->sym_filter_entry == NULL || @@ -190,7 +190,9 @@ static void perf_top__record_precise_ip(struct perf_top *top, return; ip = he->ms.map->map_ip(he->ms.map, ip); - err = hist_entry__inc_addr_samples(he, counter, ip); + + if (ui__has_annotation()) + err = hist_entry__inc_addr_samples(he, counter, ip); pthread_mutex_unlock(¬es->lock); diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 896f27047ed6..6aa6fb6f7bd9 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -37,6 +37,10 @@ # define MADV_UNMERGEABLE 13 #endif +#ifndef EFD_SEMAPHORE +# define EFD_SEMAPHORE 1 +#endif + struct tp_field { int offset; union { @@ -279,6 +283,11 @@ static size_t syscall_arg__scnprintf_strarray(char *bf, size_t size, #define SCA_STRARRAY syscall_arg__scnprintf_strarray +#if defined(__i386__) || defined(__x86_64__) +/* + * FIXME: Make this available to all arches as soon as the ioctl beautifier + * gets rewritten to support all arches. + */ static size_t syscall_arg__scnprintf_strhexarray(char *bf, size_t size, struct syscall_arg *arg) { @@ -286,6 +295,7 @@ static size_t syscall_arg__scnprintf_strhexarray(char *bf, size_t size, } #define SCA_STRHEXARRAY syscall_arg__scnprintf_strhexarray +#endif /* defined(__i386__) || defined(__x86_64__) */ static size_t syscall_arg__scnprintf_fd(char *bf, size_t size, struct syscall_arg *arg); @@ -839,6 +849,10 @@ static size_t syscall_arg__scnprintf_signum(char *bf, size_t size, struct syscal #define SCA_SIGNUM syscall_arg__scnprintf_signum +#if defined(__i386__) || defined(__x86_64__) +/* + * FIXME: Make this available to all arches. + */ #define TCGETS 0x5401 static const char *tioctls[] = { @@ -860,6 +874,7 @@ static const char *tioctls[] = { }; static DEFINE_STRARRAY_OFFSET(tioctls, 0x5401); +#endif /* defined(__i386__) || defined(__x86_64__) */ #define STRARRAY(arg, name, array) \ .arg_scnprintf = { [arg] = SCA_STRARRAY, }, \ @@ -941,9 +956,16 @@ static struct syscall_fmt { { .name = "getrlimit", .errmsg = true, STRARRAY(0, resource, rlimit_resources), }, { .name = "ioctl", .errmsg = true, .arg_scnprintf = { [0] = SCA_FD, /* fd */ +#if defined(__i386__) || defined(__x86_64__) +/* + * FIXME: Make this available to all arches. + */ [1] = SCA_STRHEXARRAY, /* cmd */ [2] = SCA_HEX, /* arg */ }, .arg_parm = { [1] = &strarray__tioctls, /* cmd */ }, }, +#else + [2] = SCA_HEX, /* arg */ }, }, +#endif { .name = "kill", .errmsg = true, .arg_scnprintf = { [1] = SCA_SIGNUM, /* sig */ }, }, { .name = "linkat", .errmsg = true, diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile index c48d44958172..0331ea2701a3 100644 --- a/tools/perf/config/Makefile +++ b/tools/perf/config/Makefile @@ -478,7 +478,7 @@ else endif ifeq ($(feature-libbfd), 1) - EXTLIBS += -lbfd + EXTLIBS += -lbfd -lz -liberty endif ifdef NO_DEMANGLE diff --git a/tools/perf/config/feature-checks/Makefile b/tools/perf/config/feature-checks/Makefile index 12e551346fa6..523b7bc10553 100644 --- a/tools/perf/config/feature-checks/Makefile +++ b/tools/perf/config/feature-checks/Makefile @@ -121,7 +121,7 @@ test-libpython-version.bin: $(BUILD) $(FLAGS_PYTHON_EMBED) test-libbfd.bin: - $(BUILD) -DPACKAGE='"perf"' -lbfd -ldl + $(BUILD) -DPACKAGE='"perf"' -lbfd -lz -liberty -ldl test-liberty.bin: $(CC) -o $(OUTPUT)$@ test-libbfd.c -DPACKAGE='"perf"' -lbfd -ldl -liberty diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 469eb679fb9d..3aa555ff9d89 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -8,6 +8,8 @@ */ #include "util.h" +#include "ui/ui.h" +#include "sort.h" #include "build-id.h" #include "color.h" #include "cache.h" @@ -489,7 +491,7 @@ static int symbol__inc_addr_samples(struct symbol *sym, struct map *map, { struct annotation *notes; - if (sym == NULL || use_browser != 1 || !sort__has_sym) + if (sym == NULL) return 0; notes = symbol__annotation(sym); @@ -1399,3 +1401,8 @@ int hist_entry__annotate(struct hist_entry *he, size_t privsize) { return symbol__annotate(he->ms.sym, he->ms.map, privsize); } + +bool ui__has_annotation(void) +{ + return use_browser == 1 && sort__has_sym; +} diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h index b2aef59d6bb2..56ad4f5287de 100644 --- a/tools/perf/util/annotate.h +++ b/tools/perf/util/annotate.h @@ -151,6 +151,8 @@ void symbol__annotate_zero_histogram(struct symbol *sym, int evidx); void symbol__annotate_decay_histogram(struct symbol *sym, int evidx); void disasm__purge(struct list_head *head); +bool ui__has_annotation(void); + int symbol__tty_annotate(struct symbol *sym, struct map *map, struct perf_evsel *evsel, bool print_lines, bool full_paths, int min_pcnt, int max_lines); diff --git a/tools/perf/util/include/linux/bitops.h b/tools/perf/util/include/linux/bitops.h index 45cf10a562bd..dadfa7e54287 100644 --- a/tools/perf/util/include/linux/bitops.h +++ b/tools/perf/util/include/linux/bitops.h @@ -87,13 +87,15 @@ static __always_inline unsigned long __ffs(unsigned long word) return num; } +typedef const unsigned long __attribute__((__may_alias__)) long_alias_t; + /* * Find the first set bit in a memory region. */ static inline unsigned long find_first_bit(const unsigned long *addr, unsigned long size) { - const unsigned long *p = addr; + long_alias_t *p = (long_alias_t *) addr; unsigned long result = 0; unsigned long tmp; diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index d248fca6d7ed..1e15df10a88c 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -1091,12 +1091,12 @@ int is_valid_tracepoint(const char *event_string) static bool is_event_supported(u8 type, unsigned config) { bool ret = true; + int open_return; struct perf_evsel *evsel; struct perf_event_attr attr = { .type = type, .config = config, .disabled = 1, - .exclude_kernel = 1, }; struct { struct thread_map map; @@ -1108,7 +1108,20 @@ static bool is_event_supported(u8 type, unsigned config) evsel = perf_evsel__new(&attr); if (evsel) { - ret = perf_evsel__open(evsel, NULL, &tmap.map) >= 0; + open_return = perf_evsel__open(evsel, NULL, &tmap.map); + ret = open_return >= 0; + + if (open_return == -EACCES) { + /* + * This happens if the paranoid value + * /proc/sys/kernel/perf_event_paranoid is set to 2 + * Re-run with exclude_kernel set; we don't do that + * by default as some ARM machines do not support it. + * + */ + evsel->attr.exclude_kernel = 1; + ret = perf_evsel__open(evsel, NULL, &tmap.map) >= 0; + } perf_evsel__delete(evsel); } diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index a8a9b6cd93a8..d8b048c20cde 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -336,8 +336,8 @@ static int add_exec_to_probe_trace_events(struct probe_trace_event *tevs, return ret; for (i = 0; i < ntevs && ret >= 0; i++) { + /* point.address is the addres of point.symbol + point.offset */ offset = tevs[i].point.address - stext; - offset += tevs[i].point.offset; tevs[i].point.offset = 0; zfree(&tevs[i].point.symbol); ret = e_snprintf(buf, 32, "0x%lx", offset); diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 0b39a48e5110..5da6ce74c676 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -1008,6 +1008,12 @@ static int perf_session__process_user_event(struct perf_session *session, union if (err == 0) perf_session__set_id_hdr_size(session); return err; + case PERF_RECORD_HEADER_EVENT_TYPE: + /* + * Depreceated, but we need to handle it for sake + * of old data files create in pipe mode. + */ + return 0; case PERF_RECORD_HEADER_TRACING_DATA: /* setup for reading amidst mmap */ lseek(fd, file_offset, SEEK_SET); diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index a9d758a3b371..e89afc097d8a 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -1336,6 +1336,8 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter) if (syms_ss && runtime_ss) break; + } else { + symsrc__destroy(ss); } } diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c index be456ce264d0..8ca405cd7c1a 100644 --- a/virt/kvm/arm/vgic.c +++ b/virt/kvm/arm/vgic.c @@ -24,6 +24,7 @@ #include <linux/of.h> #include <linux/of_address.h> #include <linux/of_irq.h> +#include <linux/uaccess.h> #include <linux/irqchip/arm-gic.h> diff --git a/virt/kvm/coalesced_mmio.c b/virt/kvm/coalesced_mmio.c index 88b2fe3ddf42..00d86427af0f 100644 --- a/virt/kvm/coalesced_mmio.c +++ b/virt/kvm/coalesced_mmio.c @@ -154,17 +154,13 @@ int kvm_vm_ioctl_register_coalesced_mmio(struct kvm *kvm, list_add_tail(&dev->list, &kvm->coalesced_zones); mutex_unlock(&kvm->slots_lock); - return ret; + return 0; out_free_dev: mutex_unlock(&kvm->slots_lock); - kfree(dev); - if (dev == NULL) - return -ENXIO; - - return 0; + return ret; } int kvm_vm_ioctl_unregister_coalesced_mmio(struct kvm *kvm, |