diff options
437 files changed, 6941 insertions, 3936 deletions
@@ -48,6 +48,9 @@ Felix Kuhling <fxkuehl@gmx.de> Felix Moeller <felix@derklecks.de> Filipe Lautert <filipe@icewall.org> Franck Bui-Huu <vagabon.xyz@gmail.com> +Frank Rowand <frowand.list@gmail.com> <frowand@mvista.com> +Frank Rowand <frowand.list@gmail.com> <frank.rowand@am.sony.com> +Frank Rowand <frowand.list@gmail.com> <frank.rowand@sonymobile.com> Frank Zago <fzago@systemfabricworks.com> Greg Kroah-Hartman <greg@echidna.(none)> Greg Kroah-Hartman <gregkh@suse.de> @@ -66,6 +69,7 @@ Jean Tourrilhes <jt@hpl.hp.com> Jeff Garzik <jgarzik@pretzel.yyz.us> Jens Axboe <axboe@suse.de> Jens Osterkamp <Jens.Osterkamp@de.ibm.com> +John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de> John Stultz <johnstul@us.ibm.com> <josh@joshtriplett.org> <josh@freedesktop.org> <josh@joshtriplett.org> <josh@kernel.org> @@ -79,6 +83,7 @@ Kay Sievers <kay.sievers@vrfy.org> Kenneth W Chen <kenneth.w.chen@intel.com> Konstantin Khlebnikov <koct9i@gmail.com> <k.khlebnikov@samsung.com> Koushik <raghavendra.koushik@neterion.com> +Krzysztof Kozlowski <krzk@kernel.org> <k.kozlowski.k@gmail.com> Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Leonid I Ananiev <leonid.i.ananiev@intel.com> Linas Vepstas <linas@austin.ibm.com> diff --git a/Documentation/devicetree/bindings/arc/archs-pct.txt b/Documentation/devicetree/bindings/arc/archs-pct.txt index 1ae98b87c640..e4b9dcee6d41 100644 --- a/Documentation/devicetree/bindings/arc/archs-pct.txt +++ b/Documentation/devicetree/bindings/arc/archs-pct.txt @@ -2,7 +2,7 @@ The ARC HS can be configured with a pipeline performance monitor for counting CPU and cache events like cache misses and hits. Like conventional PCT there -are 100+ hardware conditions dynamically mapped to upto 32 counters. +are 100+ hardware conditions dynamically mapped to up to 32 counters. It also supports overflow interrupts. Required properties: diff --git a/Documentation/devicetree/bindings/arc/pct.txt b/Documentation/devicetree/bindings/arc/pct.txt index 7b9588444f20..4e874d9a38a6 100644 --- a/Documentation/devicetree/bindings/arc/pct.txt +++ b/Documentation/devicetree/bindings/arc/pct.txt @@ -2,7 +2,7 @@ The ARC700 can be configured with a pipeline performance monitor for counting CPU and cache events like cache misses and hits. Like conventional PCT there -are 100+ hardware conditions dynamically mapped to upto 32 counters +are 100+ hardware conditions dynamically mapped to up to 32 counters Note that: * The ARC 700 PCT does not support interrupts; although HW events may be diff --git a/Documentation/devicetree/bindings/arm/cpus.txt b/Documentation/devicetree/bindings/arm/cpus.txt index ccc62f145306..3f0cbbb8395f 100644 --- a/Documentation/devicetree/bindings/arm/cpus.txt +++ b/Documentation/devicetree/bindings/arm/cpus.txt @@ -192,7 +192,6 @@ nodes to be present and contain the properties described below. can be one of: "allwinner,sun6i-a31" "allwinner,sun8i-a23" - "arm,psci" "arm,realview-smp" "brcm,bcm-nsp-smp" "brcm,brahma-b15" diff --git a/Documentation/devicetree/bindings/ata/ahci-platform.txt b/Documentation/devicetree/bindings/ata/ahci-platform.txt index 30df832a6f2f..87adfb227ca9 100644 --- a/Documentation/devicetree/bindings/ata/ahci-platform.txt +++ b/Documentation/devicetree/bindings/ata/ahci-platform.txt @@ -32,6 +32,10 @@ Optional properties: - target-supply : regulator for SATA target power - phys : reference to the SATA PHY node - phy-names : must be "sata-phy" +- ports-implemented : Mask that indicates which ports that the HBA supports + are available for software to use. Useful if PORTS_IMPL + is not programmed by the BIOS, which is true with + some embedded SOC's. Required properties when using sub-nodes: - #address-cells : number of cells to encode an address diff --git a/Documentation/devicetree/bindings/i2c/i2c-rk3x.txt b/Documentation/devicetree/bindings/i2c/i2c-rk3x.txt index f0d71bc52e64..0b4a85fe2d86 100644 --- a/Documentation/devicetree/bindings/i2c/i2c-rk3x.txt +++ b/Documentation/devicetree/bindings/i2c/i2c-rk3x.txt @@ -6,8 +6,8 @@ RK3xxx SoCs. Required properties : - reg : Offset and length of the register set for the device - - compatible : should be "rockchip,rk3066-i2c", "rockchip,rk3188-i2c" or - "rockchip,rk3288-i2c". + - compatible : should be "rockchip,rk3066-i2c", "rockchip,rk3188-i2c", + "rockchip,rk3228-i2c" or "rockchip,rk3288-i2c". - interrupts : interrupt number - clocks : parent clock diff --git a/Documentation/devicetree/bindings/net/cpsw.txt b/Documentation/devicetree/bindings/net/cpsw.txt index 28a4781ab6d7..0ae06491b430 100644 --- a/Documentation/devicetree/bindings/net/cpsw.txt +++ b/Documentation/devicetree/bindings/net/cpsw.txt @@ -45,13 +45,13 @@ Required properties: Optional properties: - dual_emac_res_vlan : Specifies VID to be used to segregate the ports - mac-address : See ethernet.txt file in the same directory -- phy_id : Specifies slave phy id +- phy_id : Specifies slave phy id (deprecated, use phy-handle) - phy-handle : See ethernet.txt file in the same directory Slave sub-nodes: - fixed-link : See fixed-link.txt file in the same directory - Either the property phy_id, or the sub-node - fixed-link can be specified + +Note: Exactly one of phy_id, phy-handle, or fixed-link must be specified. Note: "ti,hwmods" field is used to fetch the base address and irq resources from TI, omap hwmod data base during device registration. diff --git a/Documentation/networking/altera_tse.txt b/Documentation/networking/altera_tse.txt index 3f24df8c6e65..50b8589d12fd 100644 --- a/Documentation/networking/altera_tse.txt +++ b/Documentation/networking/altera_tse.txt @@ -6,7 +6,7 @@ This is the driver for the Altera Triple-Speed Ethernet (TSE) controllers using the SGDMA and MSGDMA soft DMA IP components. The driver uses the platform bus to obtain component resources. The designs used to test this driver were built for a Cyclone(R) V SOC FPGA board, a Cyclone(R) V FPGA board, -and tested with ARM and NIOS processor hosts seperately. The anticipated use +and tested with ARM and NIOS processor hosts separately. The anticipated use cases are simple communications between an embedded system and an external peer for status and simple configuration of the embedded system. @@ -65,14 +65,14 @@ Driver parameters can be also passed in command line by using: 4.1) Transmit process When the driver's transmit routine is called by the kernel, it sets up a transmit descriptor by calling the underlying DMA transmit routine (SGDMA or -MSGDMA), and initites a transmit operation. Once the transmit is complete, an +MSGDMA), and initiates a transmit operation. Once the transmit is complete, an interrupt is driven by the transmit DMA logic. The driver handles the transmit completion in the context of the interrupt handling chain by recycling resource required to send and track the requested transmit operation. 4.2) Receive process The driver will post receive buffers to the receive DMA logic during driver -intialization. Receive buffers may or may not be queued depending upon the +initialization. Receive buffers may or may not be queued depending upon the underlying DMA logic (MSGDMA is able queue receive buffers, SGDMA is not able to queue receive buffers to the SGDMA receive logic). When a packet is received, the DMA logic generates an interrupt. The driver handles a receive diff --git a/Documentation/networking/ipvlan.txt b/Documentation/networking/ipvlan.txt index cf996394e466..14422f8fcdc4 100644 --- a/Documentation/networking/ipvlan.txt +++ b/Documentation/networking/ipvlan.txt @@ -8,7 +8,7 @@ Initial Release: This is conceptually very similar to the macvlan driver with one major exception of using L3 for mux-ing /demux-ing among slaves. This property makes the master device share the L2 with it's slave devices. I have developed this -driver in conjuntion with network namespaces and not sure if there is use case +driver in conjunction with network namespaces and not sure if there is use case outside of it. @@ -42,7 +42,7 @@ out. In this mode the slaves will RX/TX multicast and broadcast (if applicable) as well. 4.2 L3 mode: - In this mode TX processing upto L3 happens on the stack instance attached + In this mode TX processing up to L3 happens on the stack instance attached to the slave device and packets are switched to the stack instance of the master device for the L2 processing and routing from that instance will be used before packets are queued on the outbound device. In this mode the slaves @@ -56,7 +56,7 @@ situations defines your use case then you can choose to use ipvlan - (a) The Linux host that is connected to the external switch / router has policy configured that allows only one mac per port. (b) No of virtual devices created on a master exceed the mac capacity and -puts the NIC in promiscous mode and degraded performance is a concern. +puts the NIC in promiscuous mode and degraded performance is a concern. (c) If the slave device is to be put into the hostile / untrusted network namespace where L2 on the slave could be changed / misused. diff --git a/Documentation/networking/pktgen.txt b/Documentation/networking/pktgen.txt index f4be85e96005..2c4e3354e128 100644 --- a/Documentation/networking/pktgen.txt +++ b/Documentation/networking/pktgen.txt @@ -67,12 +67,12 @@ The two basic thread commands are: * add_device DEVICE@NAME -- adds a single device * rem_device_all -- remove all associated devices -When adding a device to a thread, a corrosponding procfile is created +When adding a device to a thread, a corresponding procfile is created which is used for configuring this device. Thus, device names need to be unique. To support adding the same device to multiple threads, which is useful -with multi queue NICs, a the device naming scheme is extended with "@": +with multi queue NICs, the device naming scheme is extended with "@": device@something The part after "@" can be anything, but it is custom to use the thread @@ -221,7 +221,7 @@ Sample scripts A collection of tutorial scripts and helpers for pktgen is in the samples/pktgen directory. The helper parameters.sh file support easy -and consistant parameter parsing across the sample scripts. +and consistent parameter parsing across the sample scripts. Usage example and help: ./pktgen_sample01_simple.sh -i eth4 -m 00:1B:21:3C:9D:F8 -d 192.168.8.2 diff --git a/Documentation/networking/vrf.txt b/Documentation/networking/vrf.txt index d52aa10cfe91..5da679c573d2 100644 --- a/Documentation/networking/vrf.txt +++ b/Documentation/networking/vrf.txt @@ -41,7 +41,7 @@ using an rx_handler which gives the impression that packets flow through the VRF device. Similarly on egress routing rules are used to send packets to the VRF device driver before getting sent out the actual interface. This allows tcpdump on a VRF device to capture all packets into and out of the -VRF as a whole.[1] Similiarly, netfilter [2] and tc rules can be applied +VRF as a whole.[1] Similarly, netfilter [2] and tc rules can be applied using the VRF device to specify rules that apply to the VRF domain as a whole. [1] Packets in the forwarded state do not flow through the device, so those diff --git a/Documentation/networking/xfrm_sync.txt b/Documentation/networking/xfrm_sync.txt index d7aac9dedeb4..8d88e0f2ec49 100644 --- a/Documentation/networking/xfrm_sync.txt +++ b/Documentation/networking/xfrm_sync.txt @@ -4,7 +4,7 @@ Krisztian <hidden@balabit.hu> and others and additional patches from Jamal <hadi@cyberus.ca>. The end goal for syncing is to be able to insert attributes + generate -events so that the an SA can be safely moved from one machine to another +events so that the SA can be safely moved from one machine to another for HA purposes. The idea is to synchronize the SA so that the takeover machine can do the processing of the SA as accurate as possible if it has access to it. @@ -13,7 +13,7 @@ We already have the ability to generate SA add/del/upd events. These patches add ability to sync and have accurate lifetime byte (to ensure proper decay of SAs) and replay counters to avoid replay attacks with as minimal loss at failover time. -This way a backup stays as closely uptodate as an active member. +This way a backup stays as closely up-to-date as an active member. Because the above items change for every packet the SA receives, it is possible for a lot of the events to be generated. @@ -163,7 +163,7 @@ If you have an SA that is getting hit by traffic in bursts such that there is a period where the timer threshold expires with no packets seen, then an odd behavior is seen as follows: The first packet arrival after a timer expiry will trigger a timeout -aevent; i.e we dont wait for a timeout period or a packet threshold +event; i.e we don't wait for a timeout period or a packet threshold to be reached. This is done for simplicity and efficiency reasons. -JHS diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt index cb0368459da3..34a5fece3121 100644 --- a/Documentation/sysctl/vm.txt +++ b/Documentation/sysctl/vm.txt @@ -581,15 +581,16 @@ Specify "[Nn]ode" for node order "Zone Order" orders the zonelists by zone type, then by node within each zone. Specify "[Zz]one" for zone order. -Specify "[Dd]efault" to request automatic configuration. Autoconfiguration -will select "node" order in following case. -(1) if the DMA zone does not exist or -(2) if the DMA zone comprises greater than 50% of the available memory or -(3) if any node's DMA zone comprises greater than 70% of its local memory and - the amount of local memory is big enough. - -Otherwise, "zone" order will be selected. Default order is recommended unless -this is causing problems for your system/application. +Specify "[Dd]efault" to request automatic configuration. + +On 32-bit, the Normal zone needs to be preserved for allocations accessible +by the kernel, so "zone" order will be selected. + +On 64-bit, devices that require DMA32/DMA are relatively rare, so "node" +order will be selected. + +Default order is recommended unless this is causing problems for your +system/application. ============================================================== diff --git a/MAINTAINERS b/MAINTAINERS index 1d5b4becab6f..a727d9959ecd 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -872,9 +872,9 @@ F: drivers/perf/arm_pmu.c F: include/linux/perf/arm_pmu.h ARM PORT -M: Russell King <linux@arm.linux.org.uk> +M: Russell King <linux@armlinux.org.uk> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) -W: http://www.arm.linux.org.uk/ +W: http://www.armlinux.org.uk/ S: Maintained F: arch/arm/ @@ -886,35 +886,35 @@ F: arch/arm/plat-*/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/arm/arm-soc.git ARM PRIMECELL AACI PL041 DRIVER -M: Russell King <linux@arm.linux.org.uk> +M: Russell King <linux@armlinux.org.uk> S: Maintained F: sound/arm/aaci.* ARM PRIMECELL CLCD PL110 DRIVER -M: Russell King <linux@arm.linux.org.uk> +M: Russell King <linux@armlinux.org.uk> S: Maintained F: drivers/video/fbdev/amba-clcd.* ARM PRIMECELL KMI PL050 DRIVER -M: Russell King <linux@arm.linux.org.uk> +M: Russell King <linux@armlinux.org.uk> S: Maintained F: drivers/input/serio/ambakmi.* F: include/linux/amba/kmi.h ARM PRIMECELL MMCI PL180/1 DRIVER -M: Russell King <linux@arm.linux.org.uk> +M: Russell King <linux@armlinux.org.uk> S: Maintained F: drivers/mmc/host/mmci.* F: include/linux/amba/mmci.h ARM PRIMECELL UART PL010 AND PL011 DRIVERS -M: Russell King <linux@arm.linux.org.uk> +M: Russell King <linux@armlinux.org.uk> S: Maintained F: drivers/tty/serial/amba-pl01*.c F: include/linux/amba/serial.h ARM PRIMECELL BUS SUPPORT -M: Russell King <linux@arm.linux.org.uk> +M: Russell King <linux@armlinux.org.uk> S: Maintained F: drivers/amba/ F: include/linux/amba/bus.h @@ -1036,7 +1036,7 @@ L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained ARM/CLKDEV SUPPORT -M: Russell King <linux@arm.linux.org.uk> +M: Russell King <linux@armlinux.org.uk> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained F: arch/arm/include/asm/clkdev.h @@ -1093,9 +1093,9 @@ F: arch/arm/boot/dts/cx92755* N: digicolor ARM/EBSA110 MACHINE SUPPORT -M: Russell King <linux@arm.linux.org.uk> +M: Russell King <linux@armlinux.org.uk> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) -W: http://www.arm.linux.org.uk/ +W: http://www.armlinux.org.uk/ S: Maintained F: arch/arm/mach-ebsa110/ F: drivers/net/ethernet/amd/am79c961a.* @@ -1124,9 +1124,9 @@ T: git git://git.berlios.de/gemini-board F: arch/arm/mm/*-fa* ARM/FOOTBRIDGE ARCHITECTURE -M: Russell King <linux@arm.linux.org.uk> +M: Russell King <linux@armlinux.org.uk> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) -W: http://www.arm.linux.org.uk/ +W: http://www.armlinux.org.uk/ S: Maintained F: arch/arm/include/asm/hardware/dec21285.h F: arch/arm/mach-footbridge/ @@ -1457,7 +1457,7 @@ S: Maintained ARM/PT DIGITAL BOARD PORT M: Stefan Eletzhofer <stefan.eletzhofer@eletztrick.de> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) -W: http://www.arm.linux.org.uk/ +W: http://www.armlinux.org.uk/ S: Maintained ARM/QUALCOMM SUPPORT @@ -1493,9 +1493,9 @@ S: Supported F: arch/arm64/boot/dts/renesas/ ARM/RISCPC ARCHITECTURE -M: Russell King <linux@arm.linux.org.uk> +M: Russell King <linux@armlinux.org.uk> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) -W: http://www.arm.linux.org.uk/ +W: http://www.armlinux.org.uk/ S: Maintained F: arch/arm/include/asm/hardware/entry-macro-iomd.S F: arch/arm/include/asm/hardware/ioc.h @@ -1773,9 +1773,9 @@ F: drivers/clk/versatile/clk-vexpress-osc.c F: drivers/clocksource/versatile.c ARM/VFP SUPPORT -M: Russell King <linux@arm.linux.org.uk> +M: Russell King <linux@armlinux.org.uk> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) -W: http://www.arm.linux.org.uk/ +W: http://www.armlinux.org.uk/ S: Maintained F: arch/arm/vfp/ @@ -2921,7 +2921,7 @@ F: mm/cleancache.c F: include/linux/cleancache.h CLK API -M: Russell King <linux@arm.linux.org.uk> +M: Russell King <linux@armlinux.org.uk> L: linux-clk@vger.kernel.org S: Maintained F: include/linux/clk.h @@ -3354,9 +3354,9 @@ S: Supported F: drivers/net/ethernet/stmicro/stmmac/ CYBERPRO FB DRIVER -M: Russell King <linux@arm.linux.org.uk> +M: Russell King <linux@armlinux.org.uk> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) -W: http://www.arm.linux.org.uk/ +W: http://www.armlinux.org.uk/ S: Maintained F: drivers/video/fbdev/cyber2000fb.* @@ -3881,7 +3881,7 @@ F: Documentation/devicetree/bindings/display/st,stih4xx.txt DRM DRIVERS FOR VIVANTE GPU IP M: Lucas Stach <l.stach@pengutronix.de> -R: Russell King <linux+etnaviv@arm.linux.org.uk> +R: Russell King <linux+etnaviv@armlinux.org.uk> R: Christian Gmeiner <christian.gmeiner@gmail.com> L: dri-devel@lists.freedesktop.org S: Maintained @@ -4223,8 +4223,8 @@ F: Documentation/efi-stub.txt F: arch/ia64/kernel/efi.c F: arch/x86/boot/compressed/eboot.[ch] F: arch/x86/include/asm/efi.h -F: arch/x86/platform/efi/* -F: drivers/firmware/efi/* +F: arch/x86/platform/efi/ +F: drivers/firmware/efi/ F: include/linux/efi*.h EFI VARIABLE FILESYSTEM @@ -4744,7 +4744,7 @@ F: drivers/platform/x86/fujitsu-tablet.c FUSE: FILESYSTEM IN USERSPACE M: Miklos Szeredi <miklos@szeredi.hu> -L: fuse-devel@lists.sourceforge.net +L: linux-fsdevel@vger.kernel.org W: http://fuse.sourceforge.net/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/fuse.git S: Maintained @@ -4903,7 +4903,7 @@ F: net/ipv4/gre_offload.c F: include/net/gre.h GRETH 10/100/1G Ethernet MAC device driver -M: Kristoffer Glembo <kristoffer@gaisler.com> +M: Andreas Larsson <andreas@gaisler.com> L: netdev@vger.kernel.org S: Maintained F: drivers/net/ethernet/aeroflex/ @@ -6027,7 +6027,7 @@ F: include/scsi/*iscsi* ISCSI EXTENSIONS FOR RDMA (ISER) INITIATOR M: Or Gerlitz <ogerlitz@mellanox.com> -M: Sagi Grimberg <sagig@mellanox.com> +M: Sagi Grimberg <sagi@grimberg.me> M: Roi Dayan <roid@mellanox.com> L: linux-rdma@vger.kernel.org S: Supported @@ -6037,7 +6037,7 @@ Q: http://patchwork.kernel.org/project/linux-rdma/list/ F: drivers/infiniband/ulp/iser/ ISCSI EXTENSIONS FOR RDMA (ISER) TARGET -M: Sagi Grimberg <sagig@mellanox.com> +M: Sagi Grimberg <sagi@grimberg.me> T: git git://git.kernel.org/pub/scm/linux/kernel/git/nab/target-pending.git master L: linux-rdma@vger.kernel.org L: target-devel@vger.kernel.org @@ -6400,7 +6400,7 @@ F: mm/kmemleak.c F: mm/kmemleak-test.c KPROBES -M: Ananth N Mavinakayanahalli <ananth@in.ibm.com> +M: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com> M: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com> M: "David S. Miller" <davem@davemloft.net> M: Masami Hiramatsu <mhiramat@kernel.org> @@ -6905,7 +6905,7 @@ L: linux-man@vger.kernel.org S: Maintained MARVELL ARMADA DRM SUPPORT -M: Russell King <rmk+kernel@arm.linux.org.uk> +M: Russell King <rmk+kernel@armlinux.org.uk> S: Maintained F: drivers/gpu/drm/armada/ @@ -7905,7 +7905,7 @@ S: Supported F: drivers/nfc/nxp-nci NXP TDA998X DRM DRIVER -M: Russell King <rmk+kernel@arm.linux.org.uk> +M: Russell King <rmk+kernel@armlinux.org.uk> S: Supported F: drivers/gpu/drm/i2c/tda998x_drv.c F: include/drm/i2c/tda998x.h @@ -7978,7 +7978,7 @@ F: arch/arm/*omap*/*pm* F: drivers/cpufreq/omap-cpufreq.c OMAP POWERDOMAIN SOC ADAPTATION LAYER SUPPORT -M: Rajendra Nayak <rnayak@ti.com> +M: Rajendra Nayak <rnayak@codeaurora.org> M: Paul Walmsley <paul@pwsan.com> L: linux-omap@vger.kernel.org S: Maintained @@ -10014,7 +10014,8 @@ F: drivers/infiniband/hw/ocrdma/ SFC NETWORK DRIVER M: Solarflare linux maintainers <linux-net-drivers@solarflare.com> -M: Shradha Shah <sshah@solarflare.com> +M: Edward Cree <ecree@solarflare.com> +M: Bert Kenward <bkenward@solarflare.com> L: netdev@vger.kernel.org S: Supported F: drivers/net/ethernet/sfc/ @@ -11071,6 +11072,15 @@ S: Maintained F: drivers/clk/ti/ F: include/linux/clk/ti.h +TI ETHERNET SWITCH DRIVER (CPSW) +M: Mugunthan V N <mugunthanvnm@ti.com> +R: Grygorii Strashko <grygorii.strashko@ti.com> +L: linux-omap@vger.kernel.org +L: netdev@vger.kernel.org +S: Maintained +F: drivers/net/ethernet/ti/cpsw* +F: drivers/net/ethernet/ti/davinci* + TI FLASH MEDIA INTERFACE DRIVER M: Alex Dubov <oakad@yahoo.com> S: Maintained @@ -1,8 +1,8 @@ VERSION = 4 PATCHLEVEL = 6 SUBLEVEL = 0 -EXTRAVERSION = -rc5 -NAME = Blurry Fish Butt +EXTRAVERSION = -rc7 +NAME = Charred Weasel # *DOCUMENTATION* # To see a list of typical targets execute "make help" diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index 12d0284a46e5..a8767430df7d 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -35,8 +35,10 @@ config ARC select NO_BOOTMEM select OF select OF_EARLY_FLATTREE + select OF_RESERVED_MEM select PERF_USE_VMALLOC select HAVE_DEBUG_STACKOVERFLOW + select HAVE_GENERIC_DMA_COHERENT config MIGHT_HAVE_PCI bool @@ -56,6 +58,9 @@ config GENERIC_CSUM config RWSEM_GENERIC_SPINLOCK def_bool y +config ARCH_DISCONTIGMEM_ENABLE + def_bool y + config ARCH_FLATMEM_ENABLE def_bool y @@ -345,6 +350,15 @@ config ARC_HUGEPAGE_16M endchoice +config NODES_SHIFT + int "Maximum NUMA Nodes (as a power of 2)" + default "1" if !DISCONTIGMEM + default "2" if DISCONTIGMEM + depends on NEED_MULTIPLE_NODES + ---help--- + Accessing memory beyond 1GB (with or w/o PAE) requires 2 memory + zones. + if ISA_ARCOMPACT config ARC_COMPACT_IRQ_LEVELS @@ -453,6 +467,7 @@ config LINUX_LINK_BASE config HIGHMEM bool "High Memory Support" + select DISCONTIGMEM help With ARC 2G:2G address split, only upper 2G is directly addressable by kernel. Enable this to potentially allow access to rest of 2G and PAE diff --git a/arch/arc/include/asm/io.h b/arch/arc/include/asm/io.h index 17f85c9c73cf..c22b181e8206 100644 --- a/arch/arc/include/asm/io.h +++ b/arch/arc/include/asm/io.h @@ -13,6 +13,15 @@ #include <asm/byteorder.h> #include <asm/page.h> +#ifdef CONFIG_ISA_ARCV2 +#include <asm/barrier.h> +#define __iormb() rmb() +#define __iowmb() wmb() +#else +#define __iormb() do { } while (0) +#define __iowmb() do { } while (0) +#endif + extern void __iomem *ioremap(phys_addr_t paddr, unsigned long size); extern void __iomem *ioremap_prot(phys_addr_t paddr, unsigned long size, unsigned long flags); @@ -31,6 +40,15 @@ extern void iounmap(const void __iomem *addr); #define ioremap_wc(phy, sz) ioremap(phy, sz) #define ioremap_wt(phy, sz) ioremap(phy, sz) +/* + * io{read,write}{16,32}be() macros + */ +#define ioread16be(p) ({ u16 __v = be16_to_cpu((__force __be16)__raw_readw(p)); __iormb(); __v; }) +#define ioread32be(p) ({ u32 __v = be32_to_cpu((__force __be32)__raw_readl(p)); __iormb(); __v; }) + +#define iowrite16be(v,p) ({ __iowmb(); __raw_writew((__force u16)cpu_to_be16(v), p); }) +#define iowrite32be(v,p) ({ __iowmb(); __raw_writel((__force u32)cpu_to_be32(v), p); }) + /* Change struct page to physical address */ #define page_to_phys(page) (page_to_pfn(page) << PAGE_SHIFT) @@ -108,15 +126,6 @@ static inline void __raw_writel(u32 w, volatile void __iomem *addr) } -#ifdef CONFIG_ISA_ARCV2 -#include <asm/barrier.h> -#define __iormb() rmb() -#define __iowmb() wmb() -#else -#define __iormb() do { } while (0) -#define __iowmb() do { } while (0) -#endif - /* * MMIO can also get buffered/optimized in micro-arch, so barriers needed * Based on ARM model for the typical use case diff --git a/arch/arc/include/asm/irqflags-arcv2.h b/arch/arc/include/asm/irqflags-arcv2.h index 37c2f751eebf..d1ec7f6b31e0 100644 --- a/arch/arc/include/asm/irqflags-arcv2.h +++ b/arch/arc/include/asm/irqflags-arcv2.h @@ -18,6 +18,12 @@ #define STATUS_AD_MASK (1<<STATUS_AD_BIT) #define STATUS_IE_MASK (1<<STATUS_IE_BIT) +/* status32 Bits as encoded/expected by CLRI/SETI */ +#define CLRI_STATUS_IE_BIT 4 + +#define CLRI_STATUS_E_MASK 0xF +#define CLRI_STATUS_IE_MASK (1 << CLRI_STATUS_IE_BIT) + #define AUX_USER_SP 0x00D #define AUX_IRQ_CTRL 0x00E #define AUX_IRQ_ACT 0x043 /* Active Intr across all levels */ @@ -100,6 +106,13 @@ static inline long arch_local_save_flags(void) : : "memory"); + /* To be compatible with irq_save()/irq_restore() + * encode the irq bits as expected by CLRI/SETI + * (this was needed to make CONFIG_TRACE_IRQFLAGS work) + */ + temp = (1 << 5) | + ((!!(temp & STATUS_IE_MASK)) << CLRI_STATUS_IE_BIT) | + (temp & CLRI_STATUS_E_MASK); return temp; } @@ -108,7 +121,7 @@ static inline long arch_local_save_flags(void) */ static inline int arch_irqs_disabled_flags(unsigned long flags) { - return !(flags & (STATUS_IE_MASK)); + return !(flags & CLRI_STATUS_IE_MASK); } static inline int arch_irqs_disabled(void) @@ -128,11 +141,32 @@ static inline void arc_softirq_clear(int irq) #else +#ifdef CONFIG_TRACE_IRQFLAGS + +.macro TRACE_ASM_IRQ_DISABLE + bl trace_hardirqs_off +.endm + +.macro TRACE_ASM_IRQ_ENABLE + bl trace_hardirqs_on +.endm + +#else + +.macro TRACE_ASM_IRQ_DISABLE +.endm + +.macro TRACE_ASM_IRQ_ENABLE +.endm + +#endif .macro IRQ_DISABLE scratch clri + TRACE_ASM_IRQ_DISABLE .endm .macro IRQ_ENABLE scratch + TRACE_ASM_IRQ_ENABLE seti .endm diff --git a/arch/arc/include/asm/mmzone.h b/arch/arc/include/asm/mmzone.h new file mode 100644 index 000000000000..8e97136413d9 --- /dev/null +++ b/arch/arc/include/asm/mmzone.h @@ -0,0 +1,43 @@ +/* + * Copyright (C) 2016 Synopsys, Inc. (www.synopsys.com) + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef _ASM_ARC_MMZONE_H +#define _ASM_ARC_MMZONE_H + +#ifdef CONFIG_DISCONTIGMEM + +extern struct pglist_data node_data[]; +#define NODE_DATA(nid) (&node_data[nid]) + +static inline int pfn_to_nid(unsigned long pfn) +{ + int is_end_low = 1; + + if (IS_ENABLED(CONFIG_ARC_HAS_PAE40)) + is_end_low = pfn <= virt_to_pfn(0xFFFFFFFFUL); + + /* + * node 0: lowmem: 0x8000_0000 to 0xFFFF_FFFF + * node 1: HIGHMEM w/o PAE40: 0x0 to 0x7FFF_FFFF + * HIGHMEM with PAE40: 0x1_0000_0000 to ... + */ + if (pfn >= ARCH_PFN_OFFSET && is_end_low) + return 0; + + return 1; +} + +static inline int pfn_valid(unsigned long pfn) +{ + int nid = pfn_to_nid(pfn); + + return (pfn <= node_end_pfn(nid)); +} +#endif /* CONFIG_DISCONTIGMEM */ + +#endif diff --git a/arch/arc/include/asm/page.h b/arch/arc/include/asm/page.h index 36da89e2c853..0d53854884d0 100644 --- a/arch/arc/include/asm/page.h +++ b/arch/arc/include/asm/page.h @@ -72,11 +72,20 @@ typedef unsigned long pgprot_t; typedef pte_t * pgtable_t; +/* + * Use virt_to_pfn with caution: + * If used in pte or paddr related macros, it could cause truncation + * in PAE40 builds + * As a rule of thumb, only use it in helpers starting with virt_ + * You have been warned ! + */ #define virt_to_pfn(kaddr) (__pa(kaddr) >> PAGE_SHIFT) #define ARCH_PFN_OFFSET virt_to_pfn(CONFIG_LINUX_LINK_BASE) +#ifdef CONFIG_FLATMEM #define pfn_valid(pfn) (((pfn) - ARCH_PFN_OFFSET) < max_mapnr) +#endif /* * __pa, __va, virt_to_page (ALERT: deprecated, don't use them) @@ -85,12 +94,10 @@ typedef pte_t * pgtable_t; * virt here means link-address/program-address as embedded in object code. * And for ARC, link-addr = physical address */ -#define __pa(vaddr) ((unsigned long)vaddr) +#define __pa(vaddr) ((unsigned long)(vaddr)) #define __va(paddr) ((void *)((unsigned long)(paddr))) -#define virt_to_page(kaddr) \ - (mem_map + virt_to_pfn((kaddr) - CONFIG_LINUX_LINK_BASE)) - +#define virt_to_page(kaddr) pfn_to_page(virt_to_pfn(kaddr)) #define virt_addr_valid(kaddr) pfn_valid(virt_to_pfn(kaddr)) /* Default Permissions for stack/heaps pages (Non Executable) */ diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h index 7d6c93e63adf..10d4b8b8e545 100644 --- a/arch/arc/include/asm/pgtable.h +++ b/arch/arc/include/asm/pgtable.h @@ -278,14 +278,13 @@ static inline void pmd_set(pmd_t *pmdp, pte_t *ptep) #define pmd_present(x) (pmd_val(x)) #define pmd_clear(xp) do { pmd_val(*(xp)) = 0; } while (0) -#define pte_page(pte) \ - (mem_map + virt_to_pfn(pte_val(pte) - CONFIG_LINUX_LINK_BASE)) - +#define pte_page(pte) pfn_to_page(pte_pfn(pte)) #define mk_pte(page, prot) pfn_pte(page_to_pfn(page), prot) -#define pte_pfn(pte) virt_to_pfn(pte_val(pte)) -#define pfn_pte(pfn, prot) (__pte(((pte_t)(pfn) << PAGE_SHIFT) | \ - pgprot_val(prot))) -#define __pte_index(addr) (virt_to_pfn(addr) & (PTRS_PER_PTE - 1)) +#define pfn_pte(pfn, prot) (__pte(((pte_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot))) + +/* Don't use virt_to_pfn for macros below: could cause truncations for PAE40*/ +#define pte_pfn(pte) (pte_val(pte) >> PAGE_SHIFT) +#define __pte_index(addr) (((addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)) /* * pte_offset gets a @ptr to PMD entry (PGD in our 2-tier paging system) diff --git a/arch/arc/kernel/entry-arcv2.S b/arch/arc/kernel/entry-arcv2.S index c1264607bbff..7a1c124ff021 100644 --- a/arch/arc/kernel/entry-arcv2.S +++ b/arch/arc/kernel/entry-arcv2.S @@ -69,8 +69,11 @@ ENTRY(handle_interrupt) clri ; To make status32.IE agree with CPU internal state - lr r0, [ICAUSE] +#ifdef CONFIG_TRACE_IRQFLAGS + TRACE_ASM_IRQ_DISABLE +#endif + lr r0, [ICAUSE] mov blink, ret_from_exception b.d arch_do_IRQ @@ -169,6 +172,11 @@ END(EV_TLBProtV) .Lrestore_regs: + # Interrpts are actually disabled from this point on, but will get + # reenabled after we return from interrupt/exception. + # But irq tracer needs to be told now... + TRACE_ASM_IRQ_ENABLE + ld r0, [sp, PT_status32] ; U/K mode at time of entry lr r10, [AUX_IRQ_ACT] diff --git a/arch/arc/kernel/entry-compact.S b/arch/arc/kernel/entry-compact.S index 431433929189..0cb0abaa0479 100644 --- a/arch/arc/kernel/entry-compact.S +++ b/arch/arc/kernel/entry-compact.S @@ -341,6 +341,9 @@ END(call_do_page_fault) .Lrestore_regs: + # Interrpts are actually disabled from this point on, but will get + # reenabled after we return from interrupt/exception. + # But irq tracer needs to be told now... TRACE_ASM_IRQ_ENABLE lr r10, [status32] diff --git a/arch/arc/mm/init.c b/arch/arc/mm/init.c index 7d2c4fbf4f22..8be930394750 100644 --- a/arch/arc/mm/init.c +++ b/arch/arc/mm/init.c @@ -13,6 +13,7 @@ #ifdef CONFIG_BLK_DEV_INITRD #include <linux/initrd.h> #endif +#include <linux/of_fdt.h> #include <linux/swap.h> #include <linux/module.h> #include <linux/highmem.h> @@ -29,11 +30,16 @@ static const unsigned long low_mem_start = CONFIG_LINUX_LINK_BASE; static unsigned long low_mem_sz; #ifdef CONFIG_HIGHMEM -static unsigned long min_high_pfn; +static unsigned long min_high_pfn, max_high_pfn; static u64 high_mem_start; static u64 high_mem_sz; #endif +#ifdef CONFIG_DISCONTIGMEM +struct pglist_data node_data[MAX_NUMNODES] __read_mostly; +EXPORT_SYMBOL(node_data); +#endif + /* User can over-ride above with "mem=nnn[KkMm]" in cmdline */ static int __init setup_mem_sz(char *str) { @@ -108,13 +114,11 @@ void __init setup_arch_memory(void) /* Last usable page of low mem */ max_low_pfn = max_pfn = PFN_DOWN(low_mem_start + low_mem_sz); -#ifdef CONFIG_HIGHMEM - min_high_pfn = PFN_DOWN(high_mem_start); - max_pfn = PFN_DOWN(high_mem_start + high_mem_sz); +#ifdef CONFIG_FLATMEM + /* pfn_valid() uses this */ + max_mapnr = max_low_pfn - min_low_pfn; #endif - max_mapnr = max_pfn - min_low_pfn; - /*------------- bootmem allocator setup -----------------------*/ /* @@ -128,7 +132,7 @@ void __init setup_arch_memory(void) * the crash */ - memblock_add(low_mem_start, low_mem_sz); + memblock_add_node(low_mem_start, low_mem_sz, 0); memblock_reserve(low_mem_start, __pa(_end) - low_mem_start); #ifdef CONFIG_BLK_DEV_INITRD @@ -136,6 +140,9 @@ void __init setup_arch_memory(void) memblock_reserve(__pa(initrd_start), initrd_end - initrd_start); #endif + early_init_fdt_reserve_self(); + early_init_fdt_scan_reserved_mem(); + memblock_dump_all(); /*----------------- node/zones setup --------------------------*/ @@ -145,13 +152,6 @@ void __init setup_arch_memory(void) zones_size[ZONE_NORMAL] = max_low_pfn - min_low_pfn; zones_holes[ZONE_NORMAL] = 0; -#ifdef CONFIG_HIGHMEM - zones_size[ZONE_HIGHMEM] = max_pfn - max_low_pfn; - - /* This handles the peripheral address space hole */ - zones_holes[ZONE_HIGHMEM] = min_high_pfn - max_low_pfn; -#endif - /* * We can't use the helper free_area_init(zones[]) because it uses * PAGE_OFFSET to compute the @min_low_pfn which would be wrong @@ -164,6 +164,34 @@ void __init setup_arch_memory(void) zones_holes); /* holes */ #ifdef CONFIG_HIGHMEM + /* + * Populate a new node with highmem + * + * On ARC (w/o PAE) HIGHMEM addresses are actually smaller (0 based) + * than addresses in normal ala low memory (0x8000_0000 based). + * Even with PAE, the huge peripheral space hole would waste a lot of + * mem with single mem_map[]. This warrants a mem_map per region design. + * Thus HIGHMEM on ARC is imlemented with DISCONTIGMEM. + * + * DISCONTIGMEM in turns requires multiple nodes. node 0 above is + * populated with normal memory zone while node 1 only has highmem + */ + node_set_online(1); + + min_high_pfn = PFN_DOWN(high_mem_start); + max_high_pfn = PFN_DOWN(high_mem_start + high_mem_sz); + + zones_size[ZONE_NORMAL] = 0; + zones_holes[ZONE_NORMAL] = 0; + + zones_size[ZONE_HIGHMEM] = max_high_pfn - min_high_pfn; + zones_holes[ZONE_HIGHMEM] = 0; + + free_area_init_node(1, /* node-id */ + zones_size, /* num pages per zone */ + min_high_pfn, /* first pfn of node */ + zones_holes); /* holes */ + high_memory = (void *)(min_high_pfn << PAGE_SHIFT); kmap_init(); #endif @@ -181,7 +209,7 @@ void __init mem_init(void) unsigned long tmp; reset_all_zones_managed_pages(); - for (tmp = min_high_pfn; tmp < max_pfn; tmp++) + for (tmp = min_high_pfn; tmp < max_high_pfn; tmp++) free_highmem_page(pfn_to_page(tmp)); #endif diff --git a/arch/arm/boot/dts/am33xx.dtsi b/arch/arm/boot/dts/am33xx.dtsi index 55ca9c7dcf6a..0467846b4cc3 100644 --- a/arch/arm/boot/dts/am33xx.dtsi +++ b/arch/arm/boot/dts/am33xx.dtsi @@ -860,7 +860,7 @@ ti,no-idle-on-init; reg = <0x50000000 0x2000>; interrupts = <100>; - dmas = <&edma 52>; + dmas = <&edma 52 0>; dma-names = "rxtx"; gpmc,num-cs = <7>; gpmc,num-waitpins = <2>; diff --git a/arch/arm/boot/dts/am4372.dtsi b/arch/arm/boot/dts/am4372.dtsi index 344b861a55a5..ba580a9da390 100644 --- a/arch/arm/boot/dts/am4372.dtsi +++ b/arch/arm/boot/dts/am4372.dtsi @@ -884,7 +884,7 @@ gpmc: gpmc@50000000 { compatible = "ti,am3352-gpmc"; ti,hwmods = "gpmc"; - dmas = <&edma 52>; + dmas = <&edma 52 0>; dma-names = "rxtx"; clocks = <&l3s_gclk>; clock-names = "fck"; diff --git a/arch/arm/boot/dts/am57xx-beagle-x15.dts b/arch/arm/boot/dts/am57xx-beagle-x15.dts index 0a5fc5d02ce2..4168eb9dd369 100644 --- a/arch/arm/boot/dts/am57xx-beagle-x15.dts +++ b/arch/arm/boot/dts/am57xx-beagle-x15.dts @@ -99,13 +99,6 @@ #cooling-cells = <2>; }; - extcon_usb1: extcon_usb1 { - compatible = "linux,extcon-usb-gpio"; - id-gpio = <&gpio7 25 GPIO_ACTIVE_HIGH>; - pinctrl-names = "default"; - pinctrl-0 = <&extcon_usb1_pins>; - }; - hdmi0: connector { compatible = "hdmi-connector"; label = "hdmi"; @@ -349,12 +342,6 @@ >; }; - extcon_usb1_pins: extcon_usb1_pins { - pinctrl-single,pins = < - DRA7XX_CORE_IOPAD(0x37ec, PIN_INPUT_PULLUP | MUX_MODE14) /* uart1_rtsn.gpio7_25 */ - >; - }; - tpd12s015_pins: pinmux_tpd12s015_pins { pinctrl-single,pins = < DRA7XX_CORE_IOPAD(0x37b0, PIN_OUTPUT | MUX_MODE14) /* gpio7_10 CT_CP_HPD */ @@ -706,10 +693,6 @@ pinctrl-0 = <&usb1_pins>; }; -&omap_dwc3_1 { - extcon = <&extcon_usb1>; -}; - &omap_dwc3_2 { extcon = <&extcon_usb2>; }; diff --git a/arch/arm/boot/dts/dm814x-clocks.dtsi b/arch/arm/boot/dts/dm814x-clocks.dtsi index e0ea6a93a22e..792a64ee0df7 100644 --- a/arch/arm/boot/dts/dm814x-clocks.dtsi +++ b/arch/arm/boot/dts/dm814x-clocks.dtsi @@ -4,6 +4,157 @@ * published by the Free Software Foundation. */ +&pllss { + /* + * See TRM "2.6.10 Connected outputso DPLLS" and + * "2.6.11 Connected Outputs of DPLLJ". Only clkout is + * connected except for hdmi and usb. + */ + adpll_mpu_ck: adpll@40 { + #clock-cells = <1>; + compatible = "ti,dm814-adpll-s-clock"; + reg = <0x40 0x40>; + clocks = <&devosc_ck &devosc_ck &devosc_ck>; + clock-names = "clkinp", "clkinpulow", "clkinphif"; + clock-output-names = "481c5040.adpll.dcoclkldo", + "481c5040.adpll.clkout", + "481c5040.adpll.clkoutx2", + "481c5040.adpll.clkouthif"; + }; + + adpll_dsp_ck: adpll@80 { + #clock-cells = <1>; + compatible = "ti,dm814-adpll-lj-clock"; + reg = <0x80 0x30>; + clocks = <&devosc_ck &devosc_ck>; + clock-names = "clkinp", "clkinpulow"; + clock-output-names = "481c5080.adpll.dcoclkldo", + "481c5080.adpll.clkout", + "481c5080.adpll.clkoutldo"; + }; + + adpll_sgx_ck: adpll@b0 { + #clock-cells = <1>; + compatible = "ti,dm814-adpll-lj-clock"; + reg = <0xb0 0x30>; + clocks = <&devosc_ck &devosc_ck>; + clock-names = "clkinp", "clkinpulow"; + clock-output-names = "481c50b0.adpll.dcoclkldo", + "481c50b0.adpll.clkout", + "481c50b0.adpll.clkoutldo"; + }; + + adpll_hdvic_ck: adpll@e0 { + #clock-cells = <1>; + compatible = "ti,dm814-adpll-lj-clock"; + reg = <0xe0 0x30>; + clocks = <&devosc_ck &devosc_ck>; + clock-names = "clkinp", "clkinpulow"; + clock-output-names = "481c50e0.adpll.dcoclkldo", + "481c50e0.adpll.clkout", + "481c50e0.adpll.clkoutldo"; + }; + + adpll_l3_ck: adpll@110 { + #clock-cells = <1>; + compatible = "ti,dm814-adpll-lj-clock"; + reg = <0x110 0x30>; + clocks = <&devosc_ck &devosc_ck>; + clock-names = "clkinp", "clkinpulow"; + clock-output-names = "481c5110.adpll.dcoclkldo", + "481c5110.adpll.clkout", + "481c5110.adpll.clkoutldo"; + }; + + adpll_isp_ck: adpll@140 { + #clock-cells = <1>; + compatible = "ti,dm814-adpll-lj-clock"; + reg = <0x140 0x30>; + clocks = <&devosc_ck &devosc_ck>; + clock-names = "clkinp", "clkinpulow"; + clock-output-names = "481c5140.adpll.dcoclkldo", + "481c5140.adpll.clkout", + "481c5140.adpll.clkoutldo"; + }; + + adpll_dss_ck: adpll@170 { + #clock-cells = <1>; + compatible = "ti,dm814-adpll-lj-clock"; + reg = <0x170 0x30>; + clocks = <&devosc_ck &devosc_ck>; + clock-names = "clkinp", "clkinpulow"; + clock-output-names = "481c5170.adpll.dcoclkldo", + "481c5170.adpll.clkout", + "481c5170.adpll.clkoutldo"; + }; + + adpll_video0_ck: adpll@1a0 { + #clock-cells = <1>; + compatible = "ti,dm814-adpll-lj-clock"; + reg = <0x1a0 0x30>; + clocks = <&devosc_ck &devosc_ck>; + clock-names = "clkinp", "clkinpulow"; + clock-output-names = "481c51a0.adpll.dcoclkldo", + "481c51a0.adpll.clkout", + "481c51a0.adpll.clkoutldo"; + }; + + adpll_video1_ck: adpll@1d0 { + #clock-cells = <1>; + compatible = "ti,dm814-adpll-lj-clock"; + reg = <0x1d0 0x30>; + clocks = <&devosc_ck &devosc_ck>; + clock-names = "clkinp", "clkinpulow"; + clock-output-names = "481c51d0.adpll.dcoclkldo", + "481c51d0.adpll.clkout", + "481c51d0.adpll.clkoutldo"; + }; + + adpll_hdmi_ck: adpll@200 { + #clock-cells = <1>; + compatible = "ti,dm814-adpll-lj-clock"; + reg = <0x200 0x30>; + clocks = <&devosc_ck &devosc_ck>; + clock-names = "clkinp", "clkinpulow"; + clock-output-names = "481c5200.adpll.dcoclkldo", + "481c5200.adpll.clkout", + "481c5200.adpll.clkoutldo"; + }; + + adpll_audio_ck: adpll@230 { + #clock-cells = <1>; + compatible = "ti,dm814-adpll-lj-clock"; + reg = <0x230 0x30>; + clocks = <&devosc_ck &devosc_ck>; + clock-names = "clkinp", "clkinpulow"; + clock-output-names = "481c5230.adpll.dcoclkldo", + "481c5230.adpll.clkout", + "481c5230.adpll.clkoutldo"; + }; + + adpll_usb_ck: adpll@260 { + #clock-cells = <1>; + compatible = "ti,dm814-adpll-lj-clock"; + reg = <0x260 0x30>; + clocks = <&devosc_ck &devosc_ck>; + clock-names = "clkinp", "clkinpulow"; + clock-output-names = "481c5260.adpll.dcoclkldo", + "481c5260.adpll.clkout", + "481c5260.adpll.clkoutldo"; + }; + + adpll_ddr_ck: adpll@290 { + #clock-cells = <1>; + compatible = "ti,dm814-adpll-lj-clock"; + reg = <0x290 0x30>; + clocks = <&devosc_ck &devosc_ck>; + clock-names = "clkinp", "clkinpulow"; + clock-output-names = "481c5290.adpll.dcoclkldo", + "481c5290.adpll.clkout", + "481c5290.adpll.clkoutldo"; + }; +}; + &pllss_clocks { timer1_fck: timer1_fck { #clock-cells = <0>; @@ -23,6 +174,24 @@ reg = <0x2e0>; }; + /* CPTS_RFT_CLK in RMII_REFCLK_SRC, usually sourced from auiod */ + cpsw_cpts_rft_clk: cpsw_cpts_rft_clk { + #clock-cells = <0>; + compatible = "ti,mux-clock"; + clocks = <&adpll_video0_ck 1 + &adpll_video1_ck 1 + &adpll_audio_ck 1>; + ti,bit-shift = <1>; + reg = <0x2e8>; + }; + + /* REVISIT: Set up with a proper mux using RMII_REFCLK_SRC */ + cpsw_125mhz_gclk: cpsw_125mhz_gclk { + #clock-cells = <0>; + compatible = "fixed-clock"; + clock-frequency = <125000000>; + }; + sysclk18_ck: sysclk18_ck { #clock-cells = <0>; compatible = "ti,mux-clock"; @@ -79,37 +248,6 @@ compatible = "fixed-clock"; clock-frequency = <1000000000>; }; - - sysclk4_ck: sysclk4_ck { - #clock-cells = <0>; - compatible = "fixed-clock"; - clock-frequency = <222000000>; - }; - - sysclk6_ck: sysclk6_ck { - #clock-cells = <0>; - compatible = "fixed-clock"; - clock-frequency = <100000000>; - }; - - sysclk10_ck: sysclk10_ck { - #clock-cells = <0>; - compatible = "fixed-clock"; - clock-frequency = <48000000>; - }; - - cpsw_125mhz_gclk: cpsw_125mhz_gclk { - #clock-cells = <0>; - compatible = "fixed-clock"; - clock-frequency = <125000000>; - }; - - cpsw_cpts_rft_clk: cpsw_cpts_rft_clk { - #clock-cells = <0>; - compatible = "fixed-clock"; - clock-frequency = <250000000>; - }; - }; &prcm_clocks { @@ -138,6 +276,49 @@ clock-div = <78125>; }; + /* L4_HS 220 MHz*/ + sysclk4_ck: sysclk4_ck { + #clock-cells = <0>; + compatible = "ti,fixed-factor-clock"; + clocks = <&adpll_l3_ck 1>; + ti,clock-mult = <1>; + ti,clock-div = <1>; + }; + + /* L4_FWCFG */ + sysclk5_ck: sysclk5_ck { + #clock-cells = <0>; + compatible = "ti,fixed-factor-clock"; + clocks = <&adpll_l3_ck 1>; + ti,clock-mult = <1>; + ti,clock-div = <2>; + }; + + /* L4_LS 110 MHz */ + sysclk6_ck: sysclk6_ck { + #clock-cells = <0>; + compatible = "ti,fixed-factor-clock"; + clocks = <&adpll_l3_ck 1>; + ti,clock-mult = <1>; + ti,clock-div = <2>; + }; + + sysclk8_ck: sysclk8_ck { + #clock-cells = <0>; + compatible = "ti,fixed-factor-clock"; + clocks = <&adpll_usb_ck 1>; + ti,clock-mult = <1>; + ti,clock-div = <1>; + }; + + sysclk10_ck: sysclk10_ck { + compatible = "ti,divider-clock"; + reg = <0x324>; + ti,max-div = <7>; + #clock-cells = <0>; + clocks = <&adpll_usb_ck 1>; + }; + aud_clkin0_ck: aud_clkin0_ck { #clock-cells = <0>; compatible = "fixed-clock"; diff --git a/arch/arm/boot/dts/dra62x-clocks.dtsi b/arch/arm/boot/dts/dra62x-clocks.dtsi index 6f98dc8df9dd..0e49741747ef 100644 --- a/arch/arm/boot/dts/dra62x-clocks.dtsi +++ b/arch/arm/boot/dts/dra62x-clocks.dtsi @@ -6,6 +6,32 @@ #include "dm814x-clocks.dtsi" +/* Compared to dm814x, dra62x does not have hdic, l3 or dss PLLs */ +&adpll_hdvic_ck { + status = "disabled"; +}; + +&adpll_l3_ck { + status = "disabled"; +}; + +&adpll_dss_ck { + status = "disabled"; +}; + +/* Compared to dm814x, dra62x has interconnect clocks on isp PLL */ +&sysclk4_ck { + clocks = <&adpll_isp_ck 1>; +}; + +&sysclk5_ck { + clocks = <&adpll_isp_ck 1>; +}; + +&sysclk6_ck { + clocks = <&adpll_isp_ck 1>; +}; + /* * Compared to dm814x, dra62x has different shifts and more mux options. * Please add the extra options for ysclk_14 and 16 if really needed. diff --git a/arch/arm/boot/dts/dra7xx-clocks.dtsi b/arch/arm/boot/dts/dra7xx-clocks.dtsi index d0bae06b7eb7..ef2164a99d0f 100644 --- a/arch/arm/boot/dts/dra7xx-clocks.dtsi +++ b/arch/arm/boot/dts/dra7xx-clocks.dtsi @@ -98,12 +98,20 @@ clock-frequency = <32768>; }; - sys_32k_ck: sys_32k_ck { + sys_clk32_crystal_ck: sys_clk32_crystal_ck { #clock-cells = <0>; compatible = "fixed-clock"; clock-frequency = <32768>; }; + sys_clk32_pseudo_ck: sys_clk32_pseudo_ck { + #clock-cells = <0>; + compatible = "fixed-factor-clock"; + clocks = <&sys_clkin1>; + clock-mult = <1>; + clock-div = <610>; + }; + virt_12000000_ck: virt_12000000_ck { #clock-cells = <0>; compatible = "fixed-clock"; @@ -2170,4 +2178,12 @@ ti,bit-shift = <22>; reg = <0x0558>; }; + + sys_32k_ck: sys_32k_ck { + #clock-cells = <0>; + compatible = "ti,mux-clock"; + clocks = <&sys_clk32_crystal_ck>, <&sys_clk32_pseudo_ck>, <&sys_clk32_pseudo_ck>, <&sys_clk32_pseudo_ck>; + ti,bit-shift = <8>; + reg = <0x6c4>; + }; }; diff --git a/arch/arm/boot/dts/omap3-n900.dts b/arch/arm/boot/dts/omap3-n900.dts index b3c26a96a726..d9e2d9c6e999 100644 --- a/arch/arm/boot/dts/omap3-n900.dts +++ b/arch/arm/boot/dts/omap3-n900.dts @@ -329,6 +329,7 @@ regulator-name = "V28"; regulator-min-microvolt = <2800000>; regulator-max-microvolt = <2800000>; + regulator-initial-mode = <0x0e>; /* RES_STATE_ACTIVE */ regulator-always-on; /* due to battery cover sensor */ }; @@ -336,30 +337,35 @@ regulator-name = "VCSI"; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; + regulator-initial-mode = <0x0e>; /* RES_STATE_ACTIVE */ }; &vaux3 { regulator-name = "VMMC2_30"; regulator-min-microvolt = <2800000>; regulator-max-microvolt = <3000000>; + regulator-initial-mode = <0x0e>; /* RES_STATE_ACTIVE */ }; &vaux4 { regulator-name = "VCAM_ANA_28"; regulator-min-microvolt = <2800000>; regulator-max-microvolt = <2800000>; + regulator-initial-mode = <0x0e>; /* RES_STATE_ACTIVE */ }; &vmmc1 { regulator-name = "VMMC1"; regulator-min-microvolt = <1850000>; regulator-max-microvolt = <3150000>; + regulator-initial-mode = <0x0e>; /* RES_STATE_ACTIVE */ }; &vmmc2 { regulator-name = "V28_A"; regulator-min-microvolt = <2800000>; regulator-max-microvolt = <3000000>; + regulator-initial-mode = <0x0e>; /* RES_STATE_ACTIVE */ regulator-always-on; /* due VIO leak to AIC34 VDDs */ }; @@ -367,6 +373,7 @@ regulator-name = "VPLL"; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; + regulator-initial-mode = <0x0e>; /* RES_STATE_ACTIVE */ regulator-always-on; }; @@ -374,6 +381,7 @@ regulator-name = "VSDI_CSI"; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; + regulator-initial-mode = <0x0e>; /* RES_STATE_ACTIVE */ regulator-always-on; }; @@ -381,6 +389,7 @@ regulator-name = "VMMC2_IO_18"; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; + regulator-initial-mode = <0x0e>; /* RES_STATE_ACTIVE */ }; &vio { diff --git a/arch/arm/boot/dts/omap34xx.dtsi b/arch/arm/boot/dts/omap34xx.dtsi index 387dc31822fe..96f8ce7bd2af 100644 --- a/arch/arm/boot/dts/omap34xx.dtsi +++ b/arch/arm/boot/dts/omap34xx.dtsi @@ -46,7 +46,7 @@ 0x480bd800 0x017c>; interrupts = <24>; iommus = <&mmu_isp>; - syscon = <&scm_conf 0xdc>; + syscon = <&scm_conf 0x6c>; ti,phy-type = <OMAP3ISP_PHY_TYPE_COMPLEX_IO>; #clock-cells = <1>; ports { diff --git a/arch/arm/boot/dts/omap5-board-common.dtsi b/arch/arm/boot/dts/omap5-board-common.dtsi index 902657d6713b..914bf4c47404 100644 --- a/arch/arm/boot/dts/omap5-board-common.dtsi +++ b/arch/arm/boot/dts/omap5-board-common.dtsi @@ -472,7 +472,7 @@ ldo1_reg: ldo1 { /* VDDAPHY_CAM: vdda_csiport */ regulator-name = "ldo1"; - regulator-min-microvolt = <1500000>; + regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; }; @@ -498,7 +498,7 @@ ldo4_reg: ldo4 { /* VDDAPHY_DISP: vdda_dsiport/hdmi */ regulator-name = "ldo4"; - regulator-min-microvolt = <1500000>; + regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; }; diff --git a/arch/arm/boot/dts/omap5-cm-t54.dts b/arch/arm/boot/dts/omap5-cm-t54.dts index ecc591dc0778..4d87d9c6c86d 100644 --- a/arch/arm/boot/dts/omap5-cm-t54.dts +++ b/arch/arm/boot/dts/omap5-cm-t54.dts @@ -513,7 +513,7 @@ ldo1_reg: ldo1 { /* VDDAPHY_CAM: vdda_csiport */ regulator-name = "ldo1"; - regulator-min-microvolt = <1500000>; + regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; }; @@ -537,7 +537,7 @@ ldo4_reg: ldo4 { /* VDDAPHY_DISP: vdda_dsiport/hdmi */ regulator-name = "ldo4"; - regulator-min-microvolt = <1500000>; + regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; }; diff --git a/arch/arm/boot/dts/omap5.dtsi b/arch/arm/boot/dts/omap5.dtsi index 38805ebbe2ba..120b6b80cd39 100644 --- a/arch/arm/boot/dts/omap5.dtsi +++ b/arch/arm/boot/dts/omap5.dtsi @@ -269,7 +269,7 @@ omap5_pmx_wkup: pinmux@c840 { compatible = "ti,omap5-padconf", "pinctrl-single"; - reg = <0xc840 0x0038>; + reg = <0xc840 0x003c>; #address-cells = <1>; #size-cells = <0>; #interrupt-cells = <1>; diff --git a/arch/arm/boot/dts/qcom-apq8064.dtsi b/arch/arm/boot/dts/qcom-apq8064.dtsi index 65d0e8d98259..04f541bffbdd 100644 --- a/arch/arm/boot/dts/qcom-apq8064.dtsi +++ b/arch/arm/boot/dts/qcom-apq8064.dtsi @@ -666,7 +666,7 @@ }; sata0: sata@29000000 { - compatible = "generic-ahci"; + compatible = "qcom,apq8064-ahci", "generic-ahci"; status = "disabled"; reg = <0x29000000 0x180>; interrupts = <GIC_SPI 209 IRQ_TYPE_NONE>; @@ -688,6 +688,7 @@ phys = <&sata_phy0>; phy-names = "sata-phy"; + ports-implemented = <0x1>; }; /* Temporary fixed regulator */ diff --git a/arch/arm/boot/dts/qcom-msm8974.dtsi b/arch/arm/boot/dts/qcom-msm8974.dtsi index ef5330578431..8193139d0d87 100644 --- a/arch/arm/boot/dts/qcom-msm8974.dtsi +++ b/arch/arm/boot/dts/qcom-msm8974.dtsi @@ -1,6 +1,6 @@ /dts-v1/; -#include <dt-bindings/interrupt-controller/arm-gic.h> +#include <dt-bindings/interrupt-controller/irq.h> #include <dt-bindings/clock/qcom,gcc-msm8974.h> #include "skeleton.dtsi" @@ -460,8 +460,6 @@ clock-names = "core", "iface"; #address-cells = <1>; #size-cells = <0>; - dmas = <&blsp2_dma 20>, <&blsp2_dma 21>; - dma-names = "tx", "rx"; }; spmi_bus: spmi@fc4cf000 { @@ -479,16 +477,6 @@ interrupt-controller; #interrupt-cells = <4>; }; - - blsp2_dma: dma-controller@f9944000 { - compatible = "qcom,bam-v1.4.0"; - reg = <0xf9944000 0x19000>; - interrupts = <GIC_SPI 239 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&gcc GCC_BLSP2_AHB_CLK>; - clock-names = "bam_clk"; - #dma-cells = <1>; - qcom,ee = <0>; - }; }; smd { diff --git a/arch/arm/boot/dts/r8a7791-koelsch.dts b/arch/arm/boot/dts/r8a7791-koelsch.dts index 0ad71b81d3a2..cc6e28f81fe4 100644 --- a/arch/arm/boot/dts/r8a7791-koelsch.dts +++ b/arch/arm/boot/dts/r8a7791-koelsch.dts @@ -661,6 +661,7 @@ }; &pcie_bus_clk { + clock-frequency = <100000000>; status = "okay"; }; diff --git a/arch/arm/boot/dts/r8a7791-porter.dts b/arch/arm/boot/dts/r8a7791-porter.dts index 6c08314427d6..a9285d9a57cd 100644 --- a/arch/arm/boot/dts/r8a7791-porter.dts +++ b/arch/arm/boot/dts/r8a7791-porter.dts @@ -143,19 +143,11 @@ }; &pfc { - pinctrl-0 = <&scif_clk_pins>; - pinctrl-names = "default"; - scif0_pins: serial0 { renesas,groups = "scif0_data_d"; renesas,function = "scif0"; }; - scif_clk_pins: scif_clk { - renesas,groups = "scif_clk"; - renesas,function = "scif_clk"; - }; - ether_pins: ether { renesas,groups = "eth_link", "eth_mdio", "eth_rmii"; renesas,function = "eth"; @@ -229,11 +221,6 @@ status = "okay"; }; -&scif_clk { - clock-frequency = <14745600>; - status = "okay"; -}; - ðer { pinctrl-0 = <ðer_pins &phy1_pins>; pinctrl-names = "default"; @@ -414,6 +401,7 @@ }; &pcie_bus_clk { + clock-frequency = <100000000>; status = "okay"; }; diff --git a/arch/arm/boot/dts/r8a7791.dtsi b/arch/arm/boot/dts/r8a7791.dtsi index 6439f0569fe2..1cd1b6a3a72a 100644 --- a/arch/arm/boot/dts/r8a7791.dtsi +++ b/arch/arm/boot/dts/r8a7791.dtsi @@ -1083,9 +1083,8 @@ pcie_bus_clk: pcie_bus_clk { compatible = "fixed-clock"; #clock-cells = <0>; - clock-frequency = <100000000>; + clock-frequency = <0>; clock-output-names = "pcie_bus"; - status = "disabled"; }; /* External SCIF clock */ @@ -1094,7 +1093,6 @@ #clock-cells = <0>; /* This value must be overridden by the board. */ clock-frequency = <0>; - status = "disabled"; }; /* External USB clock - can be overridden by the board */ @@ -1112,7 +1110,6 @@ /* This value must be overridden by the board. */ clock-frequency = <0>; clock-output-names = "can_clk"; - status = "disabled"; }; /* Special CPG clocks */ diff --git a/arch/arm/boot/dts/sun8i-q8-common.dtsi b/arch/arm/boot/dts/sun8i-q8-common.dtsi index 9d2b7e2f5975..346a49d805a7 100644 --- a/arch/arm/boot/dts/sun8i-q8-common.dtsi +++ b/arch/arm/boot/dts/sun8i-q8-common.dtsi @@ -125,8 +125,6 @@ }; ®_dc1sw { - regulator-min-microvolt = <3000000>; - regulator-max-microvolt = <3000000>; regulator-name = "vcc-lcd"; }; diff --git a/arch/arm/include/asm/domain.h b/arch/arm/include/asm/domain.h index fc8ba1663601..99d9f630d6b6 100644 --- a/arch/arm/include/asm/domain.h +++ b/arch/arm/include/asm/domain.h @@ -84,6 +84,7 @@ #ifndef __ASSEMBLY__ +#ifdef CONFIG_CPU_CP15_MMU static inline unsigned int get_domain(void) { unsigned int domain; @@ -103,6 +104,16 @@ static inline void set_domain(unsigned val) : : "r" (val) : "memory"); isb(); } +#else +static inline unsigned int get_domain(void) +{ + return 0; +} + +static inline void set_domain(unsigned val) +{ +} +#endif #ifdef CONFIG_CPU_USE_DOMAINS #define modify_domain(dom,type) \ diff --git a/arch/arm/kernel/head-nommu.S b/arch/arm/kernel/head-nommu.S index 9b8c5a113434..fb1a69eb49c1 100644 --- a/arch/arm/kernel/head-nommu.S +++ b/arch/arm/kernel/head-nommu.S @@ -236,7 +236,7 @@ ENTRY(__setup_mpu) mov r0, #CONFIG_VECTORS_BASE @ Cover from VECTORS_BASE ldr r5,=(MPU_AP_PL1RW_PL0NA | MPU_RGN_NORMAL) /* Writing N to bits 5:1 (RSR_SZ) --> region size 2^N+1 */ - mov r6, #(((PAGE_SHIFT - 1) << MPU_RSR_SZ) | 1 << MPU_RSR_EN) + mov r6, #(((2 * PAGE_SHIFT - 1) << MPU_RSR_SZ) | 1 << MPU_RSR_EN) setup_region r0, r5, r6, MPU_DATA_SIDE @ VECTORS_BASE, PL0 NA, enabled beq 3f @ Memory-map not unified diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index 58dbd5c439df..d6d4191e68f2 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -1004,7 +1004,7 @@ static bool transparent_hugepage_adjust(kvm_pfn_t *pfnp, phys_addr_t *ipap) kvm_pfn_t pfn = *pfnp; gfn_t gfn = *ipap >> PAGE_SHIFT; - if (PageTransCompound(pfn_to_page(pfn))) { + if (PageTransCompoundMap(pfn_to_page(pfn))) { unsigned long mask; /* * The address we faulted on is backed by a transparent huge diff --git a/arch/arm/mach-davinci/board-mityomapl138.c b/arch/arm/mach-davinci/board-mityomapl138.c index d97c588550ad..bc4e63fa9808 100644 --- a/arch/arm/mach-davinci/board-mityomapl138.c +++ b/arch/arm/mach-davinci/board-mityomapl138.c @@ -121,6 +121,11 @@ static void read_factory_config(struct nvmem_device *nvmem, void *context) const char *partnum = NULL; struct davinci_soc_info *soc_info = &davinci_soc_info; + if (!IS_BUILTIN(CONFIG_NVMEM)) { + pr_warn("Factory Config not available without CONFIG_NVMEM\n"); + goto bad_config; + } + ret = nvmem_device_read(nvmem, 0, sizeof(factory_config), &factory_config); if (ret != sizeof(struct factory_config)) { diff --git a/arch/arm/mach-davinci/common.c b/arch/arm/mach-davinci/common.c index f55ef2ef2f92..742133b7266a 100644 --- a/arch/arm/mach-davinci/common.c +++ b/arch/arm/mach-davinci/common.c @@ -33,6 +33,11 @@ void davinci_get_mac_addr(struct nvmem_device *nvmem, void *context) char *mac_addr = davinci_soc_info.emac_pdata->mac_addr; off_t offset = (off_t)context; + if (!IS_BUILTIN(CONFIG_NVMEM)) { + pr_warn("Cannot read MAC addr from EEPROM without CONFIG_NVMEM\n"); + return; + } + /* Read MAC addr from EEPROM */ if (nvmem_device_read(nvmem, offset, ETH_ALEN, mac_addr) == ETH_ALEN) pr_info("Read MAC addr from EEPROM: %pM\n", mac_addr); diff --git a/arch/arm/mach-exynos/pm_domains.c b/arch/arm/mach-exynos/pm_domains.c index 7c21760f590f..875a2bab64f6 100644 --- a/arch/arm/mach-exynos/pm_domains.c +++ b/arch/arm/mach-exynos/pm_domains.c @@ -92,7 +92,7 @@ static int exynos_pd_power(struct generic_pm_domain *domain, bool power_on) if (IS_ERR(pd->clk[i])) break; - if (IS_ERR(pd->clk[i])) + if (IS_ERR(pd->pclk[i])) continue; /* Skip on first power up */ if (clk_set_parent(pd->clk[i], pd->pclk[i])) pr_err("%s: error setting parent to clock%d\n", diff --git a/arch/arm/mach-imx/devices/platform-sdhci-esdhc-imx.c b/arch/arm/mach-imx/devices/platform-sdhci-esdhc-imx.c index a5edd7d60266..3d039ef021e0 100644 --- a/arch/arm/mach-imx/devices/platform-sdhci-esdhc-imx.c +++ b/arch/arm/mach-imx/devices/platform-sdhci-esdhc-imx.c @@ -71,6 +71,7 @@ struct platform_device *__init imx_add_sdhci_esdhc_imx( if (!pdata) pdata = &default_esdhc_pdata; - return imx_add_platform_device(data->devid, data->id, res, - ARRAY_SIZE(res), pdata, sizeof(*pdata)); + return imx_add_platform_device_dmamask(data->devid, data->id, res, + ARRAY_SIZE(res), pdata, sizeof(*pdata), + DMA_BIT_MASK(32)); } diff --git a/arch/arm/mach-omap2/clockdomains7xx_data.c b/arch/arm/mach-omap2/clockdomains7xx_data.c index 7581e036bda6..ef9ed36e8a61 100644 --- a/arch/arm/mach-omap2/clockdomains7xx_data.c +++ b/arch/arm/mach-omap2/clockdomains7xx_data.c @@ -461,7 +461,7 @@ static struct clockdomain ipu_7xx_clkdm = { .cm_inst = DRA7XX_CM_CORE_AON_IPU_INST, .clkdm_offs = DRA7XX_CM_CORE_AON_IPU_IPU_CDOFFS, .dep_bit = DRA7XX_IPU_STATDEP_SHIFT, - .flags = CLKDM_CAN_HWSUP_SWSUP, + .flags = CLKDM_CAN_SWSUP, }; static struct clockdomain mpu1_7xx_clkdm = { diff --git a/arch/arm/mach-omap2/io.c b/arch/arm/mach-omap2/io.c index 9821be6dfd5e..49de4dd227be 100644 --- a/arch/arm/mach-omap2/io.c +++ b/arch/arm/mach-omap2/io.c @@ -737,7 +737,8 @@ void __init omap5_init_late(void) #ifdef CONFIG_SOC_DRA7XX void __init dra7xx_init_early(void) { - omap2_set_globals_tap(-1, OMAP2_L4_IO_ADDRESS(DRA7XX_TAP_BASE)); + omap2_set_globals_tap(DRA7XX_CLASS, + OMAP2_L4_IO_ADDRESS(DRA7XX_TAP_BASE)); omap2_set_globals_prcm_mpu(OMAP2_L4_IO_ADDRESS(OMAP54XX_PRCM_MPU_BASE)); omap2_control_base_init(); omap4_pm_init_early(); diff --git a/arch/arm/mach-omap2/omap-wakeupgen.c b/arch/arm/mach-omap2/omap-wakeupgen.c index f397bd6bd6e3..2c04f2741476 100644 --- a/arch/arm/mach-omap2/omap-wakeupgen.c +++ b/arch/arm/mach-omap2/omap-wakeupgen.c @@ -274,6 +274,10 @@ static inline void omap5_irq_save_context(void) */ static void irq_save_context(void) { + /* DRA7 has no SAR to save */ + if (soc_is_dra7xx()) + return; + if (!sar_base) sar_base = omap4_get_sar_ram_base(); @@ -290,6 +294,9 @@ static void irq_sar_clear(void) { u32 val; u32 offset = SAR_BACKUP_STATUS_OFFSET; + /* DRA7 has no SAR to save */ + if (soc_is_dra7xx()) + return; if (soc_is_omap54xx()) offset = OMAP5_SAR_BACKUP_STATUS_OFFSET; diff --git a/arch/arm/mach-omap2/pm34xx.c b/arch/arm/mach-omap2/pm34xx.c index 2dbd3785ee6f..d44e0e2f1106 100644 --- a/arch/arm/mach-omap2/pm34xx.c +++ b/arch/arm/mach-omap2/pm34xx.c @@ -198,7 +198,6 @@ void omap_sram_idle(void) int per_next_state = PWRDM_POWER_ON; int core_next_state = PWRDM_POWER_ON; int per_going_off; - int core_prev_state; u32 sdrc_pwr = 0; mpu_next_state = pwrdm_read_next_pwrst(mpu_pwrdm); @@ -278,16 +277,20 @@ void omap_sram_idle(void) sdrc_write_reg(sdrc_pwr, SDRC_POWER); /* CORE */ - if (core_next_state < PWRDM_POWER_ON) { - core_prev_state = pwrdm_read_prev_pwrst(core_pwrdm); - if (core_prev_state == PWRDM_POWER_OFF) { - omap3_core_restore_context(); - omap3_cm_restore_context(); - omap3_sram_restore_context(); - omap2_sms_restore_context(); - } + if (core_next_state < PWRDM_POWER_ON && + pwrdm_read_prev_pwrst(core_pwrdm) == PWRDM_POWER_OFF) { + omap3_core_restore_context(); + omap3_cm_restore_context(); + omap3_sram_restore_context(); + omap2_sms_restore_context(); + } else { + /* + * In off-mode resume path above, omap3_core_restore_context + * also handles the INTC autoidle restore done here so limit + * this to non-off mode resume paths so we don't do it twice. + */ + omap3_intc_resume_idle(); } - omap3_intc_resume_idle(); pwrdm_post_transition(NULL); diff --git a/arch/arm/mach-shmobile/timer.c b/arch/arm/mach-shmobile/timer.c index ad008e4b0c49..67d79f9c6bad 100644 --- a/arch/arm/mach-shmobile/timer.c +++ b/arch/arm/mach-shmobile/timer.c @@ -40,8 +40,7 @@ static void __init shmobile_setup_delay_hz(unsigned int max_cpu_core_hz, void __init shmobile_init_delay(void) { struct device_node *np, *cpus; - bool is_a7_a8_a9 = false; - bool is_a15 = false; + unsigned int div = 0; bool has_arch_timer = false; u32 max_freq = 0; @@ -55,27 +54,22 @@ void __init shmobile_init_delay(void) if (!of_property_read_u32(np, "clock-frequency", &freq)) max_freq = max(max_freq, freq); - if (of_device_is_compatible(np, "arm,cortex-a8") || - of_device_is_compatible(np, "arm,cortex-a9")) { - is_a7_a8_a9 = true; - } else if (of_device_is_compatible(np, "arm,cortex-a7")) { - is_a7_a8_a9 = true; - has_arch_timer = true; - } else if (of_device_is_compatible(np, "arm,cortex-a15")) { - is_a15 = true; + if (of_device_is_compatible(np, "arm,cortex-a8")) { + div = 2; + } else if (of_device_is_compatible(np, "arm,cortex-a9")) { + div = 1; + } else if (of_device_is_compatible(np, "arm,cortex-a7") || + of_device_is_compatible(np, "arm,cortex-a15")) { + div = 1; has_arch_timer = true; } } of_node_put(cpus); - if (!max_freq) + if (!max_freq || !div) return; - if (!has_arch_timer || !IS_ENABLED(CONFIG_ARM_ARCH_TIMER)) { - if (is_a7_a8_a9) - shmobile_setup_delay_hz(max_freq, 1, 3); - else if (is_a15) - shmobile_setup_delay_hz(max_freq, 2, 4); - } + if (!has_arch_timer || !IS_ENABLED(CONFIG_ARM_ARCH_TIMER)) + shmobile_setup_delay_hz(max_freq, 1, div); } diff --git a/arch/arm/mach-socfpga/headsmp.S b/arch/arm/mach-socfpga/headsmp.S index 5d94b7a2fb10..c160fa3007e9 100644 --- a/arch/arm/mach-socfpga/headsmp.S +++ b/arch/arm/mach-socfpga/headsmp.S @@ -13,6 +13,7 @@ #include <asm/assembler.h> .arch armv7-a + .arm ENTRY(secondary_trampoline) /* CPU1 will always fetch from 0x0 when it is brought out of reset. diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c index 1dd10936d68d..d5805e4bf2fc 100644 --- a/arch/arm/mm/nommu.c +++ b/arch/arm/mm/nommu.c @@ -87,7 +87,6 @@ static unsigned long irbar_read(void) /* MPU initialisation functions */ void __init sanity_check_meminfo_mpu(void) { - int i; phys_addr_t phys_offset = PHYS_OFFSET; phys_addr_t aligned_region_size, specified_mem_size, rounded_mem_size; struct memblock_region *reg; @@ -110,11 +109,13 @@ void __init sanity_check_meminfo_mpu(void) } else { /* * memblock auto merges contiguous blocks, remove - * all blocks afterwards + * all blocks afterwards in one go (we can't remove + * blocks separately while iterating) */ pr_notice("Ignoring RAM after %pa, memory at %pa ignored\n", - &mem_start, ®->base); - memblock_remove(reg->base, reg->size); + &mem_end, ®->base); + memblock_remove(reg->base, 0 - reg->base); + break; } } @@ -144,7 +145,7 @@ void __init sanity_check_meminfo_mpu(void) pr_warn("Truncating memory from %pa to %pa (MPU region constraints)", &specified_mem_size, &aligned_region_size); memblock_remove(mem_start + aligned_region_size, - specified_mem_size - aligned_round_size); + specified_mem_size - aligned_region_size); mem_end = mem_start + aligned_region_size; } @@ -261,7 +262,7 @@ void __init mpu_setup(void) return; region_err = mpu_setup_region(MPU_RAM_REGION, PHYS_OFFSET, - ilog2(meminfo.bank[0].size), + ilog2(memblock.memory.regions[0].size), MPU_AP_PL1RW_PL0RW | MPU_RGN_NORMAL); if (region_err) { panic("MPU region initialization failure! %d", region_err); @@ -285,7 +286,7 @@ void __init arm_mm_memblock_reserve(void) * some architectures which the DRAM is the exception vector to trap, * alloc_page breaks with error, although it is not NULL, but "0." */ - memblock_reserve(CONFIG_VECTORS_BASE, PAGE_SIZE); + memblock_reserve(CONFIG_VECTORS_BASE, 2 * PAGE_SIZE); #else /* ifndef CONFIG_CPU_V7M */ /* * There is no dedicated vector page on V7-M. So nothing needs to be diff --git a/arch/arm64/boot/dts/renesas/r8a7795.dtsi b/arch/arm64/boot/dts/renesas/r8a7795.dtsi index a7315ebe3883..706d2426024f 100644 --- a/arch/arm64/boot/dts/renesas/r8a7795.dtsi +++ b/arch/arm64/boot/dts/renesas/r8a7795.dtsi @@ -120,7 +120,6 @@ compatible = "fixed-clock"; #clock-cells = <0>; clock-frequency = <0>; - status = "disabled"; }; soc { diff --git a/arch/arm64/boot/dts/socionext/uniphier-ph1-ld20-ref.dts b/arch/arm64/boot/dts/socionext/uniphier-ph1-ld20-ref.dts index 727ae5f8c4e7..b0ed44313a5b 100644 --- a/arch/arm64/boot/dts/socionext/uniphier-ph1-ld20-ref.dts +++ b/arch/arm64/boot/dts/socionext/uniphier-ph1-ld20-ref.dts @@ -70,7 +70,6 @@ i2c3 = &i2c3; i2c4 = &i2c4; i2c5 = &i2c5; - i2c6 = &i2c6; }; }; diff --git a/arch/arm64/boot/dts/socionext/uniphier-ph1-ld20.dtsi b/arch/arm64/boot/dts/socionext/uniphier-ph1-ld20.dtsi index e682a3f52791..651c9d9d2d54 100644 --- a/arch/arm64/boot/dts/socionext/uniphier-ph1-ld20.dtsi +++ b/arch/arm64/boot/dts/socionext/uniphier-ph1-ld20.dtsi @@ -201,15 +201,12 @@ i2c2: i2c@58782000 { compatible = "socionext,uniphier-fi2c"; - status = "disabled"; reg = <0x58782000 0x80>; #address-cells = <1>; #size-cells = <0>; interrupts = <0 43 4>; - pinctrl-names = "default"; - pinctrl-0 = <&pinctrl_i2c2>; clocks = <&i2c_clk>; - clock-frequency = <100000>; + clock-frequency = <400000>; }; i2c3: i2c@58783000 { @@ -227,12 +224,15 @@ i2c4: i2c@58784000 { compatible = "socionext,uniphier-fi2c"; + status = "disabled"; reg = <0x58784000 0x80>; #address-cells = <1>; #size-cells = <0>; interrupts = <0 45 4>; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_i2c4>; clocks = <&i2c_clk>; - clock-frequency = <400000>; + clock-frequency = <100000>; }; i2c5: i2c@58785000 { @@ -245,16 +245,6 @@ clock-frequency = <400000>; }; - i2c6: i2c@58786000 { - compatible = "socionext,uniphier-fi2c"; - reg = <0x58786000 0x80>; - #address-cells = <1>; - #size-cells = <0>; - interrupts = <0 26 4>; - clocks = <&i2c_clk>; - clock-frequency = <400000>; - }; - system_bus: system-bus@58c00000 { compatible = "socionext,uniphier-system-bus"; status = "disabled"; diff --git a/arch/nios2/lib/memset.c b/arch/nios2/lib/memset.c index c2cfcb121e34..2fcefe720283 100644 --- a/arch/nios2/lib/memset.c +++ b/arch/nios2/lib/memset.c @@ -68,7 +68,7 @@ void *memset(void *s, int c, size_t count) "=r" (charcnt), /* %1 Output */ "=r" (dwordcnt), /* %2 Output */ "=r" (fill8reg), /* %3 Output */ - "=r" (wrkrega) /* %4 Output */ + "=&r" (wrkrega) /* %4 Output only */ : "r" (c), /* %5 Input */ "0" (s), /* %0 Input/Output */ "1" (count) /* %1 Input/Output */ diff --git a/arch/parisc/kernel/syscall.S b/arch/parisc/kernel/syscall.S index c976ebfe2269..57b4836b7ecd 100644 --- a/arch/parisc/kernel/syscall.S +++ b/arch/parisc/kernel/syscall.S @@ -344,7 +344,7 @@ tracesys_next: #endif cmpib,COND(=),n -1,%r20,tracesys_exit /* seccomp may have returned -1 */ - comiclr,>>= __NR_Linux_syscalls, %r20, %r0 + comiclr,>> __NR_Linux_syscalls, %r20, %r0 b,n .Ltracesys_nosys LDREGX %r20(%r19), %r19 diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h index 3fa9df70aa20..2fc5d4db503c 100644 --- a/arch/powerpc/include/asm/systbl.h +++ b/arch/powerpc/include/asm/systbl.h @@ -384,3 +384,5 @@ SYSCALL(ni_syscall) SYSCALL(ni_syscall) SYSCALL(mlock2) SYSCALL(copy_file_range) +COMPAT_SYS_SPU(preadv2) +COMPAT_SYS_SPU(pwritev2) diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h index 1f2594d45605..cf12c580f6b2 100644 --- a/arch/powerpc/include/asm/unistd.h +++ b/arch/powerpc/include/asm/unistd.h @@ -12,7 +12,7 @@ #include <uapi/asm/unistd.h> -#define NR_syscalls 380 +#define NR_syscalls 382 #define __NR__exit __NR_exit diff --git a/arch/powerpc/include/asm/word-at-a-time.h b/arch/powerpc/include/asm/word-at-a-time.h index e4396a7d0f7c..4afe66aa1400 100644 --- a/arch/powerpc/include/asm/word-at-a-time.h +++ b/arch/powerpc/include/asm/word-at-a-time.h @@ -82,7 +82,7 @@ static inline unsigned long create_zero_mask(unsigned long bits) "andc %1,%1,%2\n\t" "popcntd %0,%1" : "=r" (leading_zero_bits), "=&r" (trailing_zero_bit_mask) - : "r" (bits)); + : "b" (bits)); return leading_zero_bits; } diff --git a/arch/powerpc/include/uapi/asm/unistd.h b/arch/powerpc/include/uapi/asm/unistd.h index 940290d45b08..e9f5f41aa55a 100644 --- a/arch/powerpc/include/uapi/asm/unistd.h +++ b/arch/powerpc/include/uapi/asm/unistd.h @@ -390,5 +390,7 @@ #define __NR_membarrier 365 #define __NR_mlock2 378 #define __NR_copy_file_range 379 +#define __NR_preadv2 380 +#define __NR_pwritev2 381 #endif /* _UAPI_ASM_POWERPC_UNISTD_H_ */ diff --git a/arch/s390/include/asm/mmu.h b/arch/s390/include/asm/mmu.h index d29ad9545b41..081b2ad99d73 100644 --- a/arch/s390/include/asm/mmu.h +++ b/arch/s390/include/asm/mmu.h @@ -11,7 +11,7 @@ typedef struct { spinlock_t list_lock; struct list_head pgtable_list; struct list_head gmap_list; - unsigned long asce_bits; + unsigned long asce; unsigned long asce_limit; unsigned long vdso_base; /* The mmu context allocates 4K page tables. */ diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h index d321469eeda7..c837b79b455d 100644 --- a/arch/s390/include/asm/mmu_context.h +++ b/arch/s390/include/asm/mmu_context.h @@ -26,12 +26,28 @@ static inline int init_new_context(struct task_struct *tsk, mm->context.has_pgste = 0; mm->context.use_skey = 0; #endif - if (mm->context.asce_limit == 0) { + switch (mm->context.asce_limit) { + case 1UL << 42: + /* + * forked 3-level task, fall through to set new asce with new + * mm->pgd + */ + case 0: /* context created by exec, set asce limit to 4TB */ - mm->context.asce_bits = _ASCE_TABLE_LENGTH | - _ASCE_USER_BITS | _ASCE_TYPE_REGION3; mm->context.asce_limit = STACK_TOP_MAX; - } else if (mm->context.asce_limit == (1UL << 31)) { + mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH | + _ASCE_USER_BITS | _ASCE_TYPE_REGION3; + break; + case 1UL << 53: + /* forked 4-level task, set new asce with new mm->pgd */ + mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH | + _ASCE_USER_BITS | _ASCE_TYPE_REGION2; + break; + case 1UL << 31: + /* forked 2-level compat task, set new asce with new mm->pgd */ + mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH | + _ASCE_USER_BITS | _ASCE_TYPE_SEGMENT; + /* pgd_alloc() did not increase mm->nr_pmds */ mm_inc_nr_pmds(mm); } crst_table_init((unsigned long *) mm->pgd, pgd_entry_type(mm)); @@ -42,7 +58,7 @@ static inline int init_new_context(struct task_struct *tsk, static inline void set_user_asce(struct mm_struct *mm) { - S390_lowcore.user_asce = mm->context.asce_bits | __pa(mm->pgd); + S390_lowcore.user_asce = mm->context.asce; if (current->thread.mm_segment.ar4) __ctl_load(S390_lowcore.user_asce, 7, 7); set_cpu_flag(CIF_ASCE); @@ -71,7 +87,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, { int cpu = smp_processor_id(); - S390_lowcore.user_asce = next->context.asce_bits | __pa(next->pgd); + S390_lowcore.user_asce = next->context.asce; if (prev == next) return; if (MACHINE_HAS_TLB_LC) diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h index 9b3d9b6099f2..da34cb6b1f3b 100644 --- a/arch/s390/include/asm/pgalloc.h +++ b/arch/s390/include/asm/pgalloc.h @@ -52,8 +52,8 @@ static inline unsigned long pgd_entry_type(struct mm_struct *mm) return _REGION2_ENTRY_EMPTY; } -int crst_table_upgrade(struct mm_struct *, unsigned long limit); -void crst_table_downgrade(struct mm_struct *, unsigned long limit); +int crst_table_upgrade(struct mm_struct *); +void crst_table_downgrade(struct mm_struct *); static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address) { diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index d6fd22ea270d..18cdede1aeda 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -175,7 +175,7 @@ extern __vector128 init_task_fpu_regs[__NUM_VXRS]; regs->psw.mask = PSW_USER_BITS | PSW_MASK_BA; \ regs->psw.addr = new_psw; \ regs->gprs[15] = new_stackp; \ - crst_table_downgrade(current->mm, 1UL << 31); \ + crst_table_downgrade(current->mm); \ execve_tail(); \ } while (0) diff --git a/arch/s390/include/asm/tlbflush.h b/arch/s390/include/asm/tlbflush.h index ca148f7c3eaa..a2e6ef32e054 100644 --- a/arch/s390/include/asm/tlbflush.h +++ b/arch/s390/include/asm/tlbflush.h @@ -110,8 +110,7 @@ static inline void __tlb_flush_asce(struct mm_struct *mm, unsigned long asce) static inline void __tlb_flush_kernel(void) { if (MACHINE_HAS_IDTE) - __tlb_flush_idte((unsigned long) init_mm.pgd | - init_mm.context.asce_bits); + __tlb_flush_idte(init_mm.context.asce); else __tlb_flush_global(); } @@ -133,8 +132,7 @@ static inline void __tlb_flush_asce(struct mm_struct *mm, unsigned long asce) static inline void __tlb_flush_kernel(void) { if (MACHINE_HAS_TLB_LC) - __tlb_flush_idte_local((unsigned long) init_mm.pgd | - init_mm.context.asce_bits); + __tlb_flush_idte_local(init_mm.context.asce); else __tlb_flush_local(); } @@ -148,8 +146,7 @@ static inline void __tlb_flush_mm(struct mm_struct * mm) * only ran on the local cpu. */ if (MACHINE_HAS_IDTE && list_empty(&mm->context.gmap_list)) - __tlb_flush_asce(mm, (unsigned long) mm->pgd | - mm->context.asce_bits); + __tlb_flush_asce(mm, mm->context.asce); else __tlb_flush_full(mm); } diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index c7b0451397d6..2489b2e917c8 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -89,7 +89,8 @@ void __init paging_init(void) asce_bits = _ASCE_TYPE_REGION3 | _ASCE_TABLE_LENGTH; pgd_type = _REGION3_ENTRY_EMPTY; } - S390_lowcore.kernel_asce = (__pa(init_mm.pgd) & PAGE_MASK) | asce_bits; + init_mm.context.asce = (__pa(init_mm.pgd) & PAGE_MASK) | asce_bits; + S390_lowcore.kernel_asce = init_mm.context.asce; clear_table((unsigned long *) init_mm.pgd, pgd_type, sizeof(unsigned long)*2048); vmem_map_init(); diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c index 45c4daa49930..89cf09e5f168 100644 --- a/arch/s390/mm/mmap.c +++ b/arch/s390/mm/mmap.c @@ -174,7 +174,7 @@ int s390_mmap_check(unsigned long addr, unsigned long len, unsigned long flags) if (!(flags & MAP_FIXED)) addr = 0; if ((addr + len) >= TASK_SIZE) - return crst_table_upgrade(current->mm, TASK_MAX_SIZE); + return crst_table_upgrade(current->mm); return 0; } @@ -191,7 +191,7 @@ s390_get_unmapped_area(struct file *filp, unsigned long addr, return area; if (area == -ENOMEM && !is_compat_task() && TASK_SIZE < TASK_MAX_SIZE) { /* Upgrade the page table to 4 levels and retry. */ - rc = crst_table_upgrade(mm, TASK_MAX_SIZE); + rc = crst_table_upgrade(mm); if (rc) return (unsigned long) rc; area = arch_get_unmapped_area(filp, addr, len, pgoff, flags); @@ -213,7 +213,7 @@ s390_get_unmapped_area_topdown(struct file *filp, const unsigned long addr, return area; if (area == -ENOMEM && !is_compat_task() && TASK_SIZE < TASK_MAX_SIZE) { /* Upgrade the page table to 4 levels and retry. */ - rc = crst_table_upgrade(mm, TASK_MAX_SIZE); + rc = crst_table_upgrade(mm); if (rc) return (unsigned long) rc; area = arch_get_unmapped_area_topdown(filp, addr, len, diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c index f6c3de26cda8..e8b5962ac12a 100644 --- a/arch/s390/mm/pgalloc.c +++ b/arch/s390/mm/pgalloc.c @@ -76,81 +76,52 @@ static void __crst_table_upgrade(void *arg) __tlb_flush_local(); } -int crst_table_upgrade(struct mm_struct *mm, unsigned long limit) +int crst_table_upgrade(struct mm_struct *mm) { unsigned long *table, *pgd; - unsigned long entry; - int flush; - BUG_ON(limit > TASK_MAX_SIZE); - flush = 0; -repeat: + /* upgrade should only happen from 3 to 4 levels */ + BUG_ON(mm->context.asce_limit != (1UL << 42)); + table = crst_table_alloc(mm); if (!table) return -ENOMEM; + spin_lock_bh(&mm->page_table_lock); - if (mm->context.asce_limit < limit) { - pgd = (unsigned long *) mm->pgd; - if (mm->context.asce_limit <= (1UL << 31)) { - entry = _REGION3_ENTRY_EMPTY; - mm->context.asce_limit = 1UL << 42; - mm->context.asce_bits = _ASCE_TABLE_LENGTH | - _ASCE_USER_BITS | - _ASCE_TYPE_REGION3; - } else { - entry = _REGION2_ENTRY_EMPTY; - mm->context.asce_limit = 1UL << 53; - mm->context.asce_bits = _ASCE_TABLE_LENGTH | - _ASCE_USER_BITS | - _ASCE_TYPE_REGION2; - } - crst_table_init(table, entry); - pgd_populate(mm, (pgd_t *) table, (pud_t *) pgd); - mm->pgd = (pgd_t *) table; - mm->task_size = mm->context.asce_limit; - table = NULL; - flush = 1; - } + pgd = (unsigned long *) mm->pgd; + crst_table_init(table, _REGION2_ENTRY_EMPTY); + pgd_populate(mm, (pgd_t *) table, (pud_t *) pgd); + mm->pgd = (pgd_t *) table; + mm->context.asce_limit = 1UL << 53; + mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH | + _ASCE_USER_BITS | _ASCE_TYPE_REGION2; + mm->task_size = mm->context.asce_limit; spin_unlock_bh(&mm->page_table_lock); - if (table) - crst_table_free(mm, table); - if (mm->context.asce_limit < limit) - goto repeat; - if (flush) - on_each_cpu(__crst_table_upgrade, mm, 0); + + on_each_cpu(__crst_table_upgrade, mm, 0); return 0; } -void crst_table_downgrade(struct mm_struct *mm, unsigned long limit) +void crst_table_downgrade(struct mm_struct *mm) { pgd_t *pgd; + /* downgrade should only happen from 3 to 2 levels (compat only) */ + BUG_ON(mm->context.asce_limit != (1UL << 42)); + if (current->active_mm == mm) { clear_user_asce(); __tlb_flush_mm(mm); } - while (mm->context.asce_limit > limit) { - pgd = mm->pgd; - switch (pgd_val(*pgd) & _REGION_ENTRY_TYPE_MASK) { - case _REGION_ENTRY_TYPE_R2: - mm->context.asce_limit = 1UL << 42; - mm->context.asce_bits = _ASCE_TABLE_LENGTH | - _ASCE_USER_BITS | - _ASCE_TYPE_REGION3; - break; - case _REGION_ENTRY_TYPE_R3: - mm->context.asce_limit = 1UL << 31; - mm->context.asce_bits = _ASCE_TABLE_LENGTH | - _ASCE_USER_BITS | - _ASCE_TYPE_SEGMENT; - break; - default: - BUG(); - } - mm->pgd = (pgd_t *) (pgd_val(*pgd) & _REGION_ENTRY_ORIGIN); - mm->task_size = mm->context.asce_limit; - crst_table_free(mm, (unsigned long *) pgd); - } + + pgd = mm->pgd; + mm->pgd = (pgd_t *) (pgd_val(*pgd) & _REGION_ENTRY_ORIGIN); + mm->context.asce_limit = 1UL << 31; + mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH | + _ASCE_USER_BITS | _ASCE_TYPE_SEGMENT; + mm->task_size = mm->context.asce_limit; + crst_table_free(mm, (unsigned long *) pgd); + if (current->active_mm == mm) set_user_asce(mm); } diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c index e595e89eac65..1ea8c07eab84 100644 --- a/arch/s390/pci/pci_dma.c +++ b/arch/s390/pci/pci_dma.c @@ -457,7 +457,7 @@ int zpci_dma_init_device(struct zpci_dev *zdev) zdev->dma_table = dma_alloc_cpu_table(); if (!zdev->dma_table) { rc = -ENOMEM; - goto out_clean; + goto out; } /* @@ -477,18 +477,22 @@ int zpci_dma_init_device(struct zpci_dev *zdev) zdev->iommu_bitmap = vzalloc(zdev->iommu_pages / 8); if (!zdev->iommu_bitmap) { rc = -ENOMEM; - goto out_reg; + goto free_dma_table; } rc = zpci_register_ioat(zdev, 0, zdev->start_dma, zdev->end_dma, (u64) zdev->dma_table); if (rc) - goto out_reg; - return 0; + goto free_bitmap; -out_reg: + return 0; +free_bitmap: + vfree(zdev->iommu_bitmap); + zdev->iommu_bitmap = NULL; +free_dma_table: dma_free_cpu_table(zdev->dma_table); -out_clean: + zdev->dma_table = NULL; +out: return rc; } diff --git a/arch/sparc/configs/sparc32_defconfig b/arch/sparc/configs/sparc32_defconfig index fb23fd6b186a..c74d3701ad68 100644 --- a/arch/sparc/configs/sparc32_defconfig +++ b/arch/sparc/configs/sparc32_defconfig @@ -24,7 +24,6 @@ CONFIG_INET_AH=y CONFIG_INET_ESP=y CONFIG_INET_IPCOMP=y # CONFIG_INET_LRO is not set -CONFIG_IPV6_PRIVACY=y CONFIG_INET6_AH=m CONFIG_INET6_ESP=m CONFIG_INET6_IPCOMP=m diff --git a/arch/sparc/configs/sparc64_defconfig b/arch/sparc/configs/sparc64_defconfig index 04920ab8e292..3583d676a916 100644 --- a/arch/sparc/configs/sparc64_defconfig +++ b/arch/sparc/configs/sparc64_defconfig @@ -48,7 +48,6 @@ CONFIG_SYN_COOKIES=y CONFIG_INET_AH=y CONFIG_INET_ESP=y CONFIG_INET_IPCOMP=y -CONFIG_IPV6_PRIVACY=y CONFIG_IPV6_ROUTER_PREF=y CONFIG_IPV6_ROUTE_INFO=y CONFIG_IPV6_OPTIMISTIC_DAD=y diff --git a/arch/sparc/include/asm/spitfire.h b/arch/sparc/include/asm/spitfire.h index 56f933816144..1d8321c827a8 100644 --- a/arch/sparc/include/asm/spitfire.h +++ b/arch/sparc/include/asm/spitfire.h @@ -48,6 +48,7 @@ #define SUN4V_CHIP_SPARC_M6 0x06 #define SUN4V_CHIP_SPARC_M7 0x07 #define SUN4V_CHIP_SPARC64X 0x8a +#define SUN4V_CHIP_SPARC_SN 0x8b #define SUN4V_CHIP_UNKNOWN 0xff #ifndef __ASSEMBLY__ diff --git a/arch/sparc/include/uapi/asm/unistd.h b/arch/sparc/include/uapi/asm/unistd.h index b6de8b10a55b..36eee8132c22 100644 --- a/arch/sparc/include/uapi/asm/unistd.h +++ b/arch/sparc/include/uapi/asm/unistd.h @@ -423,8 +423,10 @@ #define __NR_setsockopt 355 #define __NR_mlock2 356 #define __NR_copy_file_range 357 +#define __NR_preadv2 358 +#define __NR_pwritev2 359 -#define NR_syscalls 358 +#define NR_syscalls 360 /* Bitmask values returned from kern_features system call. */ #define KERN_FEATURE_MIXED_MODE_STACK 0x00000001 diff --git a/arch/sparc/kernel/cherrs.S b/arch/sparc/kernel/cherrs.S index 4ee1ad420862..655628def68e 100644 --- a/arch/sparc/kernel/cherrs.S +++ b/arch/sparc/kernel/cherrs.S @@ -214,8 +214,7 @@ do_dcpe_tl1_nonfatal: /* Ok we may use interrupt globals safely. */ subcc %g1, %g2, %g1 ! Next cacheline bge,pt %icc, 1b nop - ba,pt %xcc, dcpe_icpe_tl1_common - nop + ba,a,pt %xcc, dcpe_icpe_tl1_common do_dcpe_tl1_fatal: sethi %hi(1f), %g7 @@ -224,8 +223,7 @@ do_dcpe_tl1_fatal: mov 0x2, %o0 call cheetah_plus_parity_error add %sp, PTREGS_OFF, %o1 - ba,pt %xcc, rtrap - nop + ba,a,pt %xcc, rtrap .size do_dcpe_tl1,.-do_dcpe_tl1 .globl do_icpe_tl1 @@ -259,8 +257,7 @@ do_icpe_tl1_nonfatal: /* Ok we may use interrupt globals safely. */ subcc %g1, %g2, %g1 bge,pt %icc, 1b nop - ba,pt %xcc, dcpe_icpe_tl1_common - nop + ba,a,pt %xcc, dcpe_icpe_tl1_common do_icpe_tl1_fatal: sethi %hi(1f), %g7 @@ -269,8 +266,7 @@ do_icpe_tl1_fatal: mov 0x3, %o0 call cheetah_plus_parity_error add %sp, PTREGS_OFF, %o1 - ba,pt %xcc, rtrap - nop + ba,a,pt %xcc, rtrap .size do_icpe_tl1,.-do_icpe_tl1 .type dcpe_icpe_tl1_common,#function @@ -456,7 +452,7 @@ __cheetah_log_error: cmp %g2, 0x63 be c_cee nop - ba,pt %xcc, c_deferred + ba,a,pt %xcc, c_deferred .size __cheetah_log_error,.-__cheetah_log_error /* Cheetah FECC trap handling, we get here from tl{0,1}_fecc diff --git a/arch/sparc/kernel/cpu.c b/arch/sparc/kernel/cpu.c index dfad8b1aea9f..493e023a468a 100644 --- a/arch/sparc/kernel/cpu.c +++ b/arch/sparc/kernel/cpu.c @@ -506,6 +506,12 @@ static void __init sun4v_cpu_probe(void) sparc_pmu_type = "sparc-m7"; break; + case SUN4V_CHIP_SPARC_SN: + sparc_cpu_type = "SPARC-SN"; + sparc_fpu_type = "SPARC-SN integrated FPU"; + sparc_pmu_type = "sparc-sn"; + break; + case SUN4V_CHIP_SPARC64X: sparc_cpu_type = "SPARC64-X"; sparc_fpu_type = "SPARC64-X integrated FPU"; diff --git a/arch/sparc/kernel/cpumap.c b/arch/sparc/kernel/cpumap.c index e69ec0e3f155..45c820e1cba5 100644 --- a/arch/sparc/kernel/cpumap.c +++ b/arch/sparc/kernel/cpumap.c @@ -328,6 +328,7 @@ static int iterate_cpu(struct cpuinfo_tree *t, unsigned int root_index) case SUN4V_CHIP_NIAGARA5: case SUN4V_CHIP_SPARC_M6: case SUN4V_CHIP_SPARC_M7: + case SUN4V_CHIP_SPARC_SN: case SUN4V_CHIP_SPARC64X: rover_inc_table = niagara_iterate_method; break; diff --git a/arch/sparc/kernel/fpu_traps.S b/arch/sparc/kernel/fpu_traps.S index a6864826a4bd..336d2750fe78 100644 --- a/arch/sparc/kernel/fpu_traps.S +++ b/arch/sparc/kernel/fpu_traps.S @@ -100,8 +100,8 @@ do_fpdis: fmuld %f0, %f2, %f26 faddd %f0, %f2, %f28 fmuld %f0, %f2, %f30 - b,pt %xcc, fpdis_exit - nop + ba,a,pt %xcc, fpdis_exit + 2: andcc %g5, FPRS_DU, %g0 bne,pt %icc, 3f fzero %f32 @@ -144,8 +144,8 @@ do_fpdis: fmuld %f32, %f34, %f58 faddd %f32, %f34, %f60 fmuld %f32, %f34, %f62 - ba,pt %xcc, fpdis_exit - nop + ba,a,pt %xcc, fpdis_exit + 3: mov SECONDARY_CONTEXT, %g3 add %g6, TI_FPREGS, %g1 @@ -197,8 +197,7 @@ fpdis_exit2: fp_other_bounce: call do_fpother add %sp, PTREGS_OFF, %o0 - ba,pt %xcc, rtrap - nop + ba,a,pt %xcc, rtrap .size fp_other_bounce,.-fp_other_bounce .align 32 diff --git a/arch/sparc/kernel/head_64.S b/arch/sparc/kernel/head_64.S index cd1f592cd347..a076b4249e62 100644 --- a/arch/sparc/kernel/head_64.S +++ b/arch/sparc/kernel/head_64.S @@ -414,6 +414,8 @@ sun4v_chip_type: cmp %g2, 'T' be,pt %xcc, 70f cmp %g2, 'M' + be,pt %xcc, 70f + cmp %g2, 'S' bne,pn %xcc, 49f nop @@ -433,6 +435,9 @@ sun4v_chip_type: cmp %g2, '7' be,pt %xcc, 5f mov SUN4V_CHIP_SPARC_M7, %g4 + cmp %g2, 'N' + be,pt %xcc, 5f + mov SUN4V_CHIP_SPARC_SN, %g4 ba,pt %xcc, 49f nop @@ -461,9 +466,8 @@ sun4v_chip_type: subcc %g3, 1, %g3 bne,pt %xcc, 41b add %g1, 1, %g1 - mov SUN4V_CHIP_SPARC64X, %g4 ba,pt %xcc, 5f - nop + mov SUN4V_CHIP_SPARC64X, %g4 49: mov SUN4V_CHIP_UNKNOWN, %g4 @@ -548,8 +552,7 @@ sun4u_init: stxa %g0, [%g7] ASI_DMMU membar #Sync - ba,pt %xcc, sun4u_continue - nop + ba,a,pt %xcc, sun4u_continue sun4v_init: /* Set ctx 0 */ @@ -560,14 +563,12 @@ sun4v_init: mov SECONDARY_CONTEXT, %g7 stxa %g0, [%g7] ASI_MMU membar #Sync - ba,pt %xcc, niagara_tlb_fixup - nop + ba,a,pt %xcc, niagara_tlb_fixup sun4u_continue: BRANCH_IF_ANY_CHEETAH(g1, g7, cheetah_tlb_fixup) - ba,pt %xcc, spitfire_tlb_fixup - nop + ba,a,pt %xcc, spitfire_tlb_fixup niagara_tlb_fixup: mov 3, %g2 /* Set TLB type to hypervisor. */ @@ -597,6 +598,9 @@ niagara_tlb_fixup: cmp %g1, SUN4V_CHIP_SPARC_M7 be,pt %xcc, niagara4_patch nop + cmp %g1, SUN4V_CHIP_SPARC_SN + be,pt %xcc, niagara4_patch + nop call generic_patch_copyops nop @@ -639,8 +643,7 @@ niagara_patch: call hypervisor_patch_cachetlbops nop - ba,pt %xcc, tlb_fixup_done - nop + ba,a,pt %xcc, tlb_fixup_done cheetah_tlb_fixup: mov 2, %g2 /* Set TLB type to cheetah+. */ @@ -659,8 +662,7 @@ cheetah_tlb_fixup: call cheetah_patch_cachetlbops nop - ba,pt %xcc, tlb_fixup_done - nop + ba,a,pt %xcc, tlb_fixup_done spitfire_tlb_fixup: /* Set TLB type to spitfire. */ @@ -774,8 +776,7 @@ setup_trap_table: call %o1 add %sp, (2047 + 128), %o0 - ba,pt %xcc, 2f - nop + ba,a,pt %xcc, 2f 1: sethi %hi(sparc64_ttable_tl0), %o0 set prom_set_trap_table_name, %g2 @@ -814,8 +815,7 @@ setup_trap_table: BRANCH_IF_ANY_CHEETAH(o2, o3, 1f) - ba,pt %xcc, 2f - nop + ba,a,pt %xcc, 2f /* Disable STICK_INT interrupts. */ 1: diff --git a/arch/sparc/kernel/misctrap.S b/arch/sparc/kernel/misctrap.S index 753b4f031bfb..34b4933900bf 100644 --- a/arch/sparc/kernel/misctrap.S +++ b/arch/sparc/kernel/misctrap.S @@ -18,8 +18,7 @@ __do_privact: 109: or %g7, %lo(109b), %g7 call do_privact add %sp, PTREGS_OFF, %o0 - ba,pt %xcc, rtrap - nop + ba,a,pt %xcc, rtrap .size __do_privact,.-__do_privact .type do_mna,#function @@ -46,8 +45,7 @@ do_mna: mov %l5, %o2 call mem_address_unaligned add %sp, PTREGS_OFF, %o0 - ba,pt %xcc, rtrap - nop + ba,a,pt %xcc, rtrap .size do_mna,.-do_mna .type do_lddfmna,#function @@ -65,8 +63,7 @@ do_lddfmna: mov %l5, %o2 call handle_lddfmna add %sp, PTREGS_OFF, %o0 - ba,pt %xcc, rtrap - nop + ba,a,pt %xcc, rtrap .size do_lddfmna,.-do_lddfmna .type do_stdfmna,#function @@ -84,8 +81,7 @@ do_stdfmna: mov %l5, %o2 call handle_stdfmna add %sp, PTREGS_OFF, %o0 - ba,pt %xcc, rtrap - nop + ba,a,pt %xcc, rtrap .size do_stdfmna,.-do_stdfmna .type breakpoint_trap,#function diff --git a/arch/sparc/kernel/pci.c b/arch/sparc/kernel/pci.c index badf0951d73c..c2b202d763a1 100644 --- a/arch/sparc/kernel/pci.c +++ b/arch/sparc/kernel/pci.c @@ -245,6 +245,18 @@ static void pci_parse_of_addrs(struct platform_device *op, } } +static void pci_init_dev_archdata(struct dev_archdata *sd, void *iommu, + void *stc, void *host_controller, + struct platform_device *op, + int numa_node) +{ + sd->iommu = iommu; + sd->stc = stc; + sd->host_controller = host_controller; + sd->op = op; + sd->numa_node = numa_node; +} + static struct pci_dev *of_create_pci_dev(struct pci_pbm_info *pbm, struct device_node *node, struct pci_bus *bus, int devfn) @@ -259,13 +271,10 @@ static struct pci_dev *of_create_pci_dev(struct pci_pbm_info *pbm, if (!dev) return NULL; + op = of_find_device_by_node(node); sd = &dev->dev.archdata; - sd->iommu = pbm->iommu; - sd->stc = &pbm->stc; - sd->host_controller = pbm; - sd->op = op = of_find_device_by_node(node); - sd->numa_node = pbm->numa_node; - + pci_init_dev_archdata(sd, pbm->iommu, &pbm->stc, pbm, op, + pbm->numa_node); sd = &op->dev.archdata; sd->iommu = pbm->iommu; sd->stc = &pbm->stc; @@ -994,6 +1003,27 @@ void pcibios_set_master(struct pci_dev *dev) /* No special bus mastering setup handling */ } +#ifdef CONFIG_PCI_IOV +int pcibios_add_device(struct pci_dev *dev) +{ + struct pci_dev *pdev; + + /* Add sriov arch specific initialization here. + * Copy dev_archdata from PF to VF + */ + if (dev->is_virtfn) { + struct dev_archdata *psd; + + pdev = dev->physfn; + psd = &pdev->dev.archdata; + pci_init_dev_archdata(&dev->dev.archdata, psd->iommu, + psd->stc, psd->host_controller, NULL, + psd->numa_node); + } + return 0; +} +#endif /* CONFIG_PCI_IOV */ + static int __init pcibios_init(void) { pci_dfl_cache_line_size = 64 >> 2; diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c index 26db95b54ee9..599f1207eed2 100644 --- a/arch/sparc/kernel/setup_64.c +++ b/arch/sparc/kernel/setup_64.c @@ -285,7 +285,8 @@ static void __init sun4v_patch(void) sun4v_patch_2insn_range(&__sun4v_2insn_patch, &__sun4v_2insn_patch_end); - if (sun4v_chip_type == SUN4V_CHIP_SPARC_M7) + if (sun4v_chip_type == SUN4V_CHIP_SPARC_M7 || + sun4v_chip_type == SUN4V_CHIP_SPARC_SN) sun_m7_patch_2insn_range(&__sun_m7_2insn_patch, &__sun_m7_2insn_patch_end); @@ -524,6 +525,7 @@ static void __init init_sparc64_elf_hwcap(void) sun4v_chip_type == SUN4V_CHIP_NIAGARA5 || sun4v_chip_type == SUN4V_CHIP_SPARC_M6 || sun4v_chip_type == SUN4V_CHIP_SPARC_M7 || + sun4v_chip_type == SUN4V_CHIP_SPARC_SN || sun4v_chip_type == SUN4V_CHIP_SPARC64X) cap |= HWCAP_SPARC_BLKINIT; if (sun4v_chip_type == SUN4V_CHIP_NIAGARA2 || @@ -532,6 +534,7 @@ static void __init init_sparc64_elf_hwcap(void) sun4v_chip_type == SUN4V_CHIP_NIAGARA5 || sun4v_chip_type == SUN4V_CHIP_SPARC_M6 || sun4v_chip_type == SUN4V_CHIP_SPARC_M7 || + sun4v_chip_type == SUN4V_CHIP_SPARC_SN || sun4v_chip_type == SUN4V_CHIP_SPARC64X) cap |= HWCAP_SPARC_N2; } @@ -561,6 +564,7 @@ static void __init init_sparc64_elf_hwcap(void) sun4v_chip_type == SUN4V_CHIP_NIAGARA5 || sun4v_chip_type == SUN4V_CHIP_SPARC_M6 || sun4v_chip_type == SUN4V_CHIP_SPARC_M7 || + sun4v_chip_type == SUN4V_CHIP_SPARC_SN || sun4v_chip_type == SUN4V_CHIP_SPARC64X) cap |= (AV_SPARC_VIS | AV_SPARC_VIS2 | AV_SPARC_ASI_BLK_INIT | @@ -570,6 +574,7 @@ static void __init init_sparc64_elf_hwcap(void) sun4v_chip_type == SUN4V_CHIP_NIAGARA5 || sun4v_chip_type == SUN4V_CHIP_SPARC_M6 || sun4v_chip_type == SUN4V_CHIP_SPARC_M7 || + sun4v_chip_type == SUN4V_CHIP_SPARC_SN || sun4v_chip_type == SUN4V_CHIP_SPARC64X) cap |= (AV_SPARC_VIS3 | AV_SPARC_HPC | AV_SPARC_FMAF); diff --git a/arch/sparc/kernel/spiterrs.S b/arch/sparc/kernel/spiterrs.S index c357e40ffd01..4a73009f66a5 100644 --- a/arch/sparc/kernel/spiterrs.S +++ b/arch/sparc/kernel/spiterrs.S @@ -85,8 +85,7 @@ __spitfire_cee_trap_continue: ba,pt %xcc, etraptl1 rd %pc, %g7 - ba,pt %xcc, 2f - nop + ba,a,pt %xcc, 2f 1: ba,pt %xcc, etrap_irq rd %pc, %g7 @@ -100,8 +99,7 @@ __spitfire_cee_trap_continue: mov %l5, %o2 call spitfire_access_error add %sp, PTREGS_OFF, %o0 - ba,pt %xcc, rtrap - nop + ba,a,pt %xcc, rtrap .size __spitfire_access_error,.-__spitfire_access_error /* This is the trap handler entry point for ECC correctable @@ -179,8 +177,7 @@ __spitfire_data_access_exception_tl1: mov %l5, %o2 call spitfire_data_access_exception_tl1 add %sp, PTREGS_OFF, %o0 - ba,pt %xcc, rtrap - nop + ba,a,pt %xcc, rtrap .size __spitfire_data_access_exception_tl1,.-__spitfire_data_access_exception_tl1 .type __spitfire_data_access_exception,#function @@ -200,8 +197,7 @@ __spitfire_data_access_exception: mov %l5, %o2 call spitfire_data_access_exception add %sp, PTREGS_OFF, %o0 - ba,pt %xcc, rtrap - nop + ba,a,pt %xcc, rtrap .size __spitfire_data_access_exception,.-__spitfire_data_access_exception .type __spitfire_insn_access_exception_tl1,#function @@ -220,8 +216,7 @@ __spitfire_insn_access_exception_tl1: mov %l5, %o2 call spitfire_insn_access_exception_tl1 add %sp, PTREGS_OFF, %o0 - ba,pt %xcc, rtrap - nop + ba,a,pt %xcc, rtrap .size __spitfire_insn_access_exception_tl1,.-__spitfire_insn_access_exception_tl1 .type __spitfire_insn_access_exception,#function @@ -240,6 +235,5 @@ __spitfire_insn_access_exception: mov %l5, %o2 call spitfire_insn_access_exception add %sp, PTREGS_OFF, %o0 - ba,pt %xcc, rtrap - nop + ba,a,pt %xcc, rtrap .size __spitfire_insn_access_exception,.-__spitfire_insn_access_exception diff --git a/arch/sparc/kernel/systbls_32.S b/arch/sparc/kernel/systbls_32.S index 6c3dd6c52f8b..eac7f0db5c8c 100644 --- a/arch/sparc/kernel/systbls_32.S +++ b/arch/sparc/kernel/systbls_32.S @@ -88,4 +88,4 @@ sys_call_table: /*340*/ .long sys_ni_syscall, sys_kcmp, sys_finit_module, sys_sched_setattr, sys_sched_getattr /*345*/ .long sys_renameat2, sys_seccomp, sys_getrandom, sys_memfd_create, sys_bpf /*350*/ .long sys_execveat, sys_membarrier, sys_userfaultfd, sys_bind, sys_listen -/*355*/ .long sys_setsockopt, sys_mlock2, sys_copy_file_range +/*355*/ .long sys_setsockopt, sys_mlock2, sys_copy_file_range, sys_preadv2, sys_pwritev2 diff --git a/arch/sparc/kernel/systbls_64.S b/arch/sparc/kernel/systbls_64.S index 12b524cfcfa0..b0f17ff2ddba 100644 --- a/arch/sparc/kernel/systbls_64.S +++ b/arch/sparc/kernel/systbls_64.S @@ -89,7 +89,7 @@ sys_call_table32: /*340*/ .word sys_kern_features, sys_kcmp, sys_finit_module, sys_sched_setattr, sys_sched_getattr .word sys32_renameat2, sys_seccomp, sys_getrandom, sys_memfd_create, sys_bpf /*350*/ .word sys32_execveat, sys_membarrier, sys_userfaultfd, sys_bind, sys_listen - .word compat_sys_setsockopt, sys_mlock2, sys_copy_file_range + .word compat_sys_setsockopt, sys_mlock2, sys_copy_file_range, compat_sys_preadv2, compat_sys_pwritev2 #endif /* CONFIG_COMPAT */ @@ -170,4 +170,4 @@ sys_call_table: /*340*/ .word sys_kern_features, sys_kcmp, sys_finit_module, sys_sched_setattr, sys_sched_getattr .word sys_renameat2, sys_seccomp, sys_getrandom, sys_memfd_create, sys_bpf /*350*/ .word sys64_execveat, sys_membarrier, sys_userfaultfd, sys_bind, sys_listen - .word sys_setsockopt, sys_mlock2, sys_copy_file_range + .word sys_setsockopt, sys_mlock2, sys_copy_file_range, sys_preadv2, sys_pwritev2 diff --git a/arch/sparc/kernel/utrap.S b/arch/sparc/kernel/utrap.S index b7f0f3f3a909..c731e8023d3e 100644 --- a/arch/sparc/kernel/utrap.S +++ b/arch/sparc/kernel/utrap.S @@ -11,8 +11,7 @@ utrap_trap: /* %g3=handler,%g4=level */ mov %l4, %o1 call bad_trap add %sp, PTREGS_OFF, %o0 - ba,pt %xcc, rtrap - nop + ba,a,pt %xcc, rtrap invoke_utrap: sllx %g3, 3, %g3 diff --git a/arch/sparc/kernel/vio.c b/arch/sparc/kernel/vio.c index cb5789c9f961..f6bb857254fc 100644 --- a/arch/sparc/kernel/vio.c +++ b/arch/sparc/kernel/vio.c @@ -45,6 +45,14 @@ static const struct vio_device_id *vio_match_device( return NULL; } +static int vio_hotplug(struct device *dev, struct kobj_uevent_env *env) +{ + const struct vio_dev *vio_dev = to_vio_dev(dev); + + add_uevent_var(env, "MODALIAS=vio:T%sS%s", vio_dev->type, vio_dev->compat); + return 0; +} + static int vio_bus_match(struct device *dev, struct device_driver *drv) { struct vio_dev *vio_dev = to_vio_dev(dev); @@ -105,15 +113,25 @@ static ssize_t type_show(struct device *dev, return sprintf(buf, "%s\n", vdev->type); } +static ssize_t modalias_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + const struct vio_dev *vdev = to_vio_dev(dev); + + return sprintf(buf, "vio:T%sS%s\n", vdev->type, vdev->compat); +} + static struct device_attribute vio_dev_attrs[] = { __ATTR_RO(devspec), __ATTR_RO(type), + __ATTR_RO(modalias), __ATTR_NULL }; static struct bus_type vio_bus_type = { .name = "vio", .dev_attrs = vio_dev_attrs, + .uevent = vio_hotplug, .match = vio_bus_match, .probe = vio_device_probe, .remove = vio_device_remove, diff --git a/arch/sparc/kernel/vmlinux.lds.S b/arch/sparc/kernel/vmlinux.lds.S index aadd321aa05d..7d02b1fef025 100644 --- a/arch/sparc/kernel/vmlinux.lds.S +++ b/arch/sparc/kernel/vmlinux.lds.S @@ -33,6 +33,10 @@ ENTRY(_start) jiffies = jiffies_64; #endif +#ifdef CONFIG_SPARC64 +ASSERT((swapper_tsb == 0x0000000000408000), "Error: sparc64 early assembler too large") +#endif + SECTIONS { #ifdef CONFIG_SPARC64 diff --git a/arch/sparc/kernel/winfixup.S b/arch/sparc/kernel/winfixup.S index 1e67ce958369..855019a8590e 100644 --- a/arch/sparc/kernel/winfixup.S +++ b/arch/sparc/kernel/winfixup.S @@ -32,8 +32,7 @@ fill_fixup: rd %pc, %g7 call do_sparc64_fault add %sp, PTREGS_OFF, %o0 - ba,pt %xcc, rtrap - nop + ba,a,pt %xcc, rtrap /* Be very careful about usage of the trap globals here. * You cannot touch %g5 as that has the fault information. diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index 1cfe6aab7a11..09e838801e39 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -1769,6 +1769,7 @@ static void __init setup_page_offset(void) max_phys_bits = 47; break; case SUN4V_CHIP_SPARC_M7: + case SUN4V_CHIP_SPARC_SN: default: /* M7 and later support 52-bit virtual addresses. */ sparc64_va_hole_top = 0xfff8000000000000UL; @@ -1986,6 +1987,7 @@ static void __init sun4v_linear_pte_xor_finalize(void) */ switch (sun4v_chip_type) { case SUN4V_CHIP_SPARC_M7: + case SUN4V_CHIP_SPARC_SN: pagecv_flag = 0x00; break; default: @@ -2138,6 +2140,7 @@ void __init paging_init(void) */ switch (sun4v_chip_type) { case SUN4V_CHIP_SPARC_M7: + case SUN4V_CHIP_SPARC_SN: page_cache4v_flag = _PAGE_CP_4V; break; default: diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c index 86a9bec18dab..bd3e8421b57c 100644 --- a/arch/x86/events/amd/core.c +++ b/arch/x86/events/amd/core.c @@ -115,7 +115,7 @@ static __initconst const u64 amd_hw_cache_event_ids /* * AMD Performance Monitor K7 and later. */ -static const u64 amd_perfmon_event_map[] = +static const u64 amd_perfmon_event_map[PERF_COUNT_HW_MAX] = { [PERF_COUNT_HW_CPU_CYCLES] = 0x0076, [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0, diff --git a/arch/x86/events/amd/iommu.c b/arch/x86/events/amd/iommu.c index 40625ca7a190..6011a573dd64 100644 --- a/arch/x86/events/amd/iommu.c +++ b/arch/x86/events/amd/iommu.c @@ -474,6 +474,7 @@ static __init int _init_perf_amd_iommu( static struct perf_amd_iommu __perf_iommu = { .pmu = { + .task_ctx_nr = perf_invalid_context, .event_init = perf_iommu_event_init, .add = perf_iommu_add, .del = perf_iommu_del, diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 68fa55b4d42e..a6fd4dbcf820 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -3637,8 +3637,11 @@ __init int intel_pmu_init(void) pr_cont("Knights Landing events, "); break; + case 142: /* 14nm Kabylake Mobile */ + case 158: /* 14nm Kabylake Desktop */ case 78: /* 14nm Skylake Mobile */ case 94: /* 14nm Skylake Desktop */ + case 85: /* 14nm Skylake Server */ x86_pmu.late_ack = true; memcpy(hw_cache_event_ids, skl_hw_cache_event_ids, sizeof(hw_cache_event_ids)); memcpy(hw_cache_extra_regs, skl_hw_cache_extra_regs, sizeof(hw_cache_extra_regs)); diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index 6c3b7c1780c9..1ca5d1e7d4f2 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -63,7 +63,7 @@ static enum { #define LBR_PLM (LBR_KERNEL | LBR_USER) -#define LBR_SEL_MASK 0x1ff /* valid bits in LBR_SELECT */ +#define LBR_SEL_MASK 0x3ff /* valid bits in LBR_SELECT */ #define LBR_NOT_SUPP -1 /* LBR filter not supported */ #define LBR_IGN 0 /* ignored */ @@ -610,8 +610,10 @@ static int intel_pmu_setup_hw_lbr_filter(struct perf_event *event) * The first 9 bits (LBR_SEL_MASK) in LBR_SELECT operate * in suppress mode. So LBR_SELECT should be set to * (~mask & LBR_SEL_MASK) | (mask & ~LBR_SEL_MASK) + * But the 10th bit LBR_CALL_STACK does not operate + * in suppress mode. */ - reg->config = mask ^ x86_pmu.lbr_sel_mask; + reg->config = mask ^ (x86_pmu.lbr_sel_mask & ~LBR_CALL_STACK); if ((br_type & PERF_SAMPLE_BRANCH_NO_CYCLES) && (br_type & PERF_SAMPLE_BRANCH_NO_FLAGS) && diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c index 6af7cf71d6b2..09a77dbc73c9 100644 --- a/arch/x86/events/intel/pt.c +++ b/arch/x86/events/intel/pt.c @@ -136,9 +136,21 @@ static int __init pt_pmu_hw_init(void) struct dev_ext_attribute *de_attrs; struct attribute **attrs; size_t size; + u64 reg; int ret; long i; + if (boot_cpu_has(X86_FEATURE_VMX)) { + /* + * Intel SDM, 36.5 "Tracing post-VMXON" says that + * "IA32_VMX_MISC[bit 14]" being 1 means PT can trace + * post-VMXON. + */ + rdmsrl(MSR_IA32_VMX_MISC, reg); + if (reg & BIT(14)) + pt_pmu.vmx = true; + } + attrs = NULL; for (i = 0; i < PT_CPUID_LEAVES; i++) { @@ -269,20 +281,23 @@ static void pt_config(struct perf_event *event) reg |= (event->attr.config & PT_CONFIG_MASK); + event->hw.config = reg; wrmsrl(MSR_IA32_RTIT_CTL, reg); } -static void pt_config_start(bool start) +static void pt_config_stop(struct perf_event *event) { - u64 ctl; + u64 ctl = READ_ONCE(event->hw.config); + + /* may be already stopped by a PMI */ + if (!(ctl & RTIT_CTL_TRACEEN)) + return; - rdmsrl(MSR_IA32_RTIT_CTL, ctl); - if (start) - ctl |= RTIT_CTL_TRACEEN; - else - ctl &= ~RTIT_CTL_TRACEEN; + ctl &= ~RTIT_CTL_TRACEEN; wrmsrl(MSR_IA32_RTIT_CTL, ctl); + WRITE_ONCE(event->hw.config, ctl); + /* * A wrmsr that disables trace generation serializes other PT * registers and causes all data packets to be written to memory, @@ -291,8 +306,7 @@ static void pt_config_start(bool start) * The below WMB, separating data store and aux_head store matches * the consumer's RMB that separates aux_head load and data load. */ - if (!start) - wmb(); + wmb(); } static void pt_config_buffer(void *buf, unsigned int topa_idx, @@ -942,11 +956,17 @@ void intel_pt_interrupt(void) if (!ACCESS_ONCE(pt->handle_nmi)) return; - pt_config_start(false); + /* + * If VMX is on and PT does not support it, don't touch anything. + */ + if (READ_ONCE(pt->vmx_on)) + return; if (!event) return; + pt_config_stop(event); + buf = perf_get_aux(&pt->handle); if (!buf) return; @@ -983,6 +1003,35 @@ void intel_pt_interrupt(void) } } +void intel_pt_handle_vmx(int on) +{ + struct pt *pt = this_cpu_ptr(&pt_ctx); + struct perf_event *event; + unsigned long flags; + + /* PT plays nice with VMX, do nothing */ + if (pt_pmu.vmx) + return; + + /* + * VMXON will clear RTIT_CTL.TraceEn; we need to make + * sure to not try to set it while VMX is on. Disable + * interrupts to avoid racing with pmu callbacks; + * concurrent PMI should be handled fine. + */ + local_irq_save(flags); + WRITE_ONCE(pt->vmx_on, on); + + if (on) { + /* prevent pt_config_stop() from writing RTIT_CTL */ + event = pt->handle.event; + if (event) + event->hw.config = 0; + } + local_irq_restore(flags); +} +EXPORT_SYMBOL_GPL(intel_pt_handle_vmx); + /* * PMU callbacks */ @@ -992,6 +1041,9 @@ static void pt_event_start(struct perf_event *event, int mode) struct pt *pt = this_cpu_ptr(&pt_ctx); struct pt_buffer *buf = perf_get_aux(&pt->handle); + if (READ_ONCE(pt->vmx_on)) + return; + if (!buf || pt_buffer_is_full(buf, pt)) { event->hw.state = PERF_HES_STOPPED; return; @@ -1014,7 +1066,8 @@ static void pt_event_stop(struct perf_event *event, int mode) * see comment in intel_pt_interrupt(). */ ACCESS_ONCE(pt->handle_nmi) = 0; - pt_config_start(false); + + pt_config_stop(event); if (event->hw.state == PERF_HES_STOPPED) return; diff --git a/arch/x86/events/intel/pt.h b/arch/x86/events/intel/pt.h index 336878a5d205..3abb5f5cccc8 100644 --- a/arch/x86/events/intel/pt.h +++ b/arch/x86/events/intel/pt.h @@ -65,6 +65,7 @@ enum pt_capabilities { struct pt_pmu { struct pmu pmu; u32 caps[PT_CPUID_REGS_NUM * PT_CPUID_LEAVES]; + bool vmx; }; /** @@ -107,10 +108,12 @@ struct pt_buffer { * struct pt - per-cpu pt context * @handle: perf output handle * @handle_nmi: do handle PT PMI on this cpu, there's an active event + * @vmx_on: 1 if VMX is ON on this cpu */ struct pt { struct perf_output_handle handle; int handle_nmi; + int vmx_on; }; #endif /* __INTEL_PT_H__ */ diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c index 70c93f9b03ac..1705c9d75e44 100644 --- a/arch/x86/events/intel/rapl.c +++ b/arch/x86/events/intel/rapl.c @@ -718,6 +718,7 @@ static int __init rapl_pmu_init(void) break; case 60: /* Haswell */ case 69: /* Haswell-Celeron */ + case 70: /* Haswell GT3e */ case 61: /* Broadwell */ case 71: /* Broadwell-H */ rapl_cntr_mask = RAPL_IDX_HSW; diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 5a2ed3ed2f26..f353061bba1d 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -285,6 +285,10 @@ static inline void perf_events_lapic_init(void) { } static inline void perf_check_microcode(void) { } #endif +#ifdef CONFIG_CPU_SUP_INTEL + extern void intel_pt_handle_vmx(int on); +#endif + #if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_AMD) extern void amd_pmu_enable_virt(void); extern void amd_pmu_disable_virt(void); diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index ad59d70bcb1a..ef495511f019 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -256,7 +256,8 @@ static void clear_irq_vector(int irq, struct apic_chip_data *data) struct irq_desc *desc; int cpu, vector; - BUG_ON(!data->cfg.vector); + if (!data->cfg.vector) + return; vector = data->cfg.vector; for_each_cpu_and(cpu, data->domain, cpu_online_mask) diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 8f4942e2bcbb..d7ce96a7daca 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -891,9 +891,7 @@ void __init uv_system_init(void) } pr_info("UV: Found %s hub\n", hub); - /* We now only need to map the MMRs on UV1 */ - if (is_uv1_hub()) - map_low_mmrs(); + map_low_mmrs(); m_n_config.v = uv_read_local_mmr(UVH_RH_GAM_CONFIG_MMR ); m_val = m_n_config.s.m_skt; diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 54cdbd2003fe..af1112980dd4 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -389,12 +389,6 @@ default_entry: /* Make changes effective */ wrmsr - /* - * And make sure that all the mappings we set up have NX set from - * the beginning. - */ - orl $(1 << (_PAGE_BIT_NX - 32)), pa(__supported_pte_mask + 4) - enable_paging: /* diff --git a/arch/x86/kernel/sysfb_efi.c b/arch/x86/kernel/sysfb_efi.c index b285d4e8c68e..5da924bbf0a0 100644 --- a/arch/x86/kernel/sysfb_efi.c +++ b/arch/x86/kernel/sysfb_efi.c @@ -106,14 +106,24 @@ static int __init efifb_set_system(const struct dmi_system_id *id) continue; for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) { resource_size_t start, end; + unsigned long flags; + + flags = pci_resource_flags(dev, i); + if (!(flags & IORESOURCE_MEM)) + continue; + + if (flags & IORESOURCE_UNSET) + continue; + + if (pci_resource_len(dev, i) == 0) + continue; start = pci_resource_start(dev, i); - if (start == 0) - break; end = pci_resource_end(dev, i); if (screen_info.lfb_base >= start && screen_info.lfb_base < end) { found_bar = 1; + break; } } } diff --git a/arch/x86/kernel/tsc_msr.c b/arch/x86/kernel/tsc_msr.c index 92ae6acac8a7..6aa0f4d9eea6 100644 --- a/arch/x86/kernel/tsc_msr.c +++ b/arch/x86/kernel/tsc_msr.c @@ -92,7 +92,7 @@ unsigned long try_msr_calibrate_tsc(void) if (freq_desc_tables[cpu_index].msr_plat) { rdmsr(MSR_PLATFORM_INFO, lo, hi); - ratio = (lo >> 8) & 0x1f; + ratio = (lo >> 8) & 0xff; } else { rdmsr(MSR_IA32_PERF_STATUS, lo, hi); ratio = (hi >> 8) & 0x1f; diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 1ff4dbb73fb7..b6f50e8b0a39 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -2823,7 +2823,7 @@ static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu, */ if (!is_error_noslot_pfn(pfn) && !kvm_is_reserved_pfn(pfn) && level == PT_PAGE_TABLE_LEVEL && - PageTransCompound(pfn_to_page(pfn)) && + PageTransCompoundMap(pfn_to_page(pfn)) && !mmu_gfn_lpage_is_disallowed(vcpu, gfn, PT_DIRECTORY_LEVEL)) { unsigned long mask; /* @@ -4785,7 +4785,7 @@ restart: */ if (sp->role.direct && !kvm_is_reserved_pfn(pfn) && - PageTransCompound(pfn_to_page(pfn))) { + PageTransCompoundMap(pfn_to_page(pfn))) { drop_spte(kvm, sptep); need_tlb_flush = 1; goto restart; diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index ee1c8a93871c..133679d520af 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -3103,6 +3103,8 @@ static __init int vmx_disabled_by_bios(void) static void kvm_cpu_vmxon(u64 addr) { + intel_pt_handle_vmx(1); + asm volatile (ASM_VMX_VMXON_RAX : : "a"(&addr), "m"(addr) : "memory", "cc"); @@ -3172,6 +3174,8 @@ static void vmclear_local_loaded_vmcss(void) static void kvm_cpu_vmxoff(void) { asm volatile (__ex(ASM_VMX_VMXOFF) : : : "cc"); + + intel_pt_handle_vmx(0); } static void hardware_disable(void) diff --git a/arch/x86/mm/setup_nx.c b/arch/x86/mm/setup_nx.c index 8bea84724a7d..f65a33f505b6 100644 --- a/arch/x86/mm/setup_nx.c +++ b/arch/x86/mm/setup_nx.c @@ -32,8 +32,9 @@ early_param("noexec", noexec_setup); void x86_configure_nx(void) { - /* If disable_nx is set, clear NX on all new mappings going forward. */ - if (disable_nx) + if (boot_cpu_has(X86_FEATURE_NX) && !disable_nx) + __supported_pte_mask |= _PAGE_NX; + else __supported_pte_mask &= ~_PAGE_NX; } diff --git a/arch/x86/platform/efi/efi-bgrt.c b/arch/x86/platform/efi/efi-bgrt.c index a2433817c987..6a2f5691b1ab 100644 --- a/arch/x86/platform/efi/efi-bgrt.c +++ b/arch/x86/platform/efi/efi-bgrt.c @@ -43,40 +43,40 @@ void __init efi_bgrt_init(void) return; if (bgrt_tab->header.length < sizeof(*bgrt_tab)) { - pr_err("Ignoring BGRT: invalid length %u (expected %zu)\n", + pr_notice("Ignoring BGRT: invalid length %u (expected %zu)\n", bgrt_tab->header.length, sizeof(*bgrt_tab)); return; } if (bgrt_tab->version != 1) { - pr_err("Ignoring BGRT: invalid version %u (expected 1)\n", + pr_notice("Ignoring BGRT: invalid version %u (expected 1)\n", bgrt_tab->version); return; } if (bgrt_tab->status & 0xfe) { - pr_err("Ignoring BGRT: reserved status bits are non-zero %u\n", + pr_notice("Ignoring BGRT: reserved status bits are non-zero %u\n", bgrt_tab->status); return; } if (bgrt_tab->image_type != 0) { - pr_err("Ignoring BGRT: invalid image type %u (expected 0)\n", + pr_notice("Ignoring BGRT: invalid image type %u (expected 0)\n", bgrt_tab->image_type); return; } if (!bgrt_tab->image_address) { - pr_err("Ignoring BGRT: null image address\n"); + pr_notice("Ignoring BGRT: null image address\n"); return; } image = memremap(bgrt_tab->image_address, sizeof(bmp_header), MEMREMAP_WB); if (!image) { - pr_err("Ignoring BGRT: failed to map image header memory\n"); + pr_notice("Ignoring BGRT: failed to map image header memory\n"); return; } memcpy(&bmp_header, image, sizeof(bmp_header)); memunmap(image); if (bmp_header.id != 0x4d42) { - pr_err("Ignoring BGRT: Incorrect BMP magic number 0x%x (expected 0x4d42)\n", + pr_notice("Ignoring BGRT: Incorrect BMP magic number 0x%x (expected 0x4d42)\n", bmp_header.id); return; } @@ -84,14 +84,14 @@ void __init efi_bgrt_init(void) bgrt_image = kmalloc(bgrt_image_size, GFP_KERNEL | __GFP_NOWARN); if (!bgrt_image) { - pr_err("Ignoring BGRT: failed to allocate memory for image (wanted %zu bytes)\n", + pr_notice("Ignoring BGRT: failed to allocate memory for image (wanted %zu bytes)\n", bgrt_image_size); return; } image = memremap(bgrt_tab->image_address, bmp_header.size, MEMREMAP_WB); if (!image) { - pr_err("Ignoring BGRT: failed to map image memory\n"); + pr_notice("Ignoring BGRT: failed to map image memory\n"); kfree(bgrt_image); bgrt_image = NULL; return; diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c index 9e2ba5c6e1dd..f42e78de1e10 100644 --- a/arch/x86/xen/spinlock.c +++ b/arch/x86/xen/spinlock.c @@ -27,6 +27,12 @@ static bool xen_pvspin = true; static void xen_qlock_kick(int cpu) { + int irq = per_cpu(lock_kicker_irq, cpu); + + /* Don't kick if the target's kicker interrupt is not initialized. */ + if (irq == -1) + return; + xen_send_IPI_one(cpu, XEN_SPIN_UNLOCK_VECTOR); } diff --git a/drivers/acpi/acpica/dsmethod.c b/drivers/acpi/acpica/dsmethod.c index 1982310e6d83..da198b864107 100644 --- a/drivers/acpi/acpica/dsmethod.c +++ b/drivers/acpi/acpica/dsmethod.c @@ -428,6 +428,9 @@ acpi_ds_begin_method_execution(struct acpi_namespace_node *method_node, obj_desc->method.mutex->mutex. original_sync_level = obj_desc->method.mutex->mutex.sync_level; + + obj_desc->method.mutex->mutex.thread_id = + acpi_os_get_thread_id(); } } diff --git a/drivers/acpi/nfit.c b/drivers/acpi/nfit.c index d0f35e63640b..63cc9dbe4f3b 100644 --- a/drivers/acpi/nfit.c +++ b/drivers/acpi/nfit.c @@ -287,8 +287,11 @@ static int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, offset); rc = -ENXIO; } - } else + } else { rc = 0; + if (cmd_rc) + *cmd_rc = xlat_status(buf, cmd); + } out: ACPI_FREE(out_obj); diff --git a/drivers/ata/Kconfig b/drivers/ata/Kconfig index 5083f85efea7..cfa936a32513 100644 --- a/drivers/ata/Kconfig +++ b/drivers/ata/Kconfig @@ -202,6 +202,14 @@ config SATA_FSL If unsure, say N. +config SATA_AHCI_SEATTLE + tristate "AMD Seattle 6.0Gbps AHCI SATA host controller support" + depends on ARCH_SEATTLE + help + This option enables support for AMD Seattle SATA host controller. + + If unsure, say N + config SATA_INIC162X tristate "Initio 162x SATA support (Very Experimental)" depends on PCI diff --git a/drivers/ata/Makefile b/drivers/ata/Makefile index 18579521464e..0b2afb7e5f35 100644 --- a/drivers/ata/Makefile +++ b/drivers/ata/Makefile @@ -4,6 +4,7 @@ obj-$(CONFIG_ATA) += libata.o # non-SFF interface obj-$(CONFIG_SATA_AHCI) += ahci.o libahci.o obj-$(CONFIG_SATA_ACARD_AHCI) += acard-ahci.o libahci.o +obj-$(CONFIG_SATA_AHCI_SEATTLE) += ahci_seattle.o libahci.o libahci_platform.o obj-$(CONFIG_SATA_AHCI_PLATFORM) += ahci_platform.o libahci.o libahci_platform.o obj-$(CONFIG_SATA_FSL) += sata_fsl.o obj-$(CONFIG_SATA_INIC162X) += sata_inic162x.o diff --git a/drivers/ata/ahci_platform.c b/drivers/ata/ahci_platform.c index 40442332bfa7..62a04c8fb5c9 100644 --- a/drivers/ata/ahci_platform.c +++ b/drivers/ata/ahci_platform.c @@ -51,6 +51,9 @@ static int ahci_probe(struct platform_device *pdev) if (rc) return rc; + of_property_read_u32(dev->of_node, + "ports-implemented", &hpriv->force_port_map); + if (of_device_is_compatible(dev->of_node, "hisilicon,hisi-ahci")) hpriv->flags |= AHCI_HFLAG_NO_FBS | AHCI_HFLAG_NO_NCQ; diff --git a/drivers/ata/ahci_seattle.c b/drivers/ata/ahci_seattle.c new file mode 100644 index 000000000000..6e702ab57220 --- /dev/null +++ b/drivers/ata/ahci_seattle.c @@ -0,0 +1,210 @@ +/* + * AMD Seattle AHCI SATA driver + * + * Copyright (c) 2015, Advanced Micro Devices + * Author: Brijesh Singh <brijesh.singh@amd.com> + * + * based on the AHCI SATA platform driver by Jeff Garzik and Anton Vorontsov + * + * 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. + * + * 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. + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/pm.h> +#include <linux/device.h> +#include <linux/of_device.h> +#include <linux/platform_device.h> +#include <linux/libata.h> +#include <linux/ahci_platform.h> +#include <linux/acpi.h> +#include <linux/pci_ids.h> +#include "ahci.h" + +/* SGPIO Control Register definition + * + * Bit Type Description + * 31 RW OD7.2 (activity) + * 30 RW OD7.1 (locate) + * 29 RW OD7.0 (fault) + * 28...8 RW OD6.2...OD0.0 (3bits per port, 1 bit per LED) + * 7 RO SGPIO feature flag + * 6:4 RO Reserved + * 3:0 RO Number of ports (0 means no port supported) + */ +#define ACTIVITY_BIT_POS(x) (8 + (3 * x)) +#define LOCATE_BIT_POS(x) (ACTIVITY_BIT_POS(x) + 1) +#define FAULT_BIT_POS(x) (LOCATE_BIT_POS(x) + 1) + +#define ACTIVITY_MASK 0x00010000 +#define LOCATE_MASK 0x00080000 +#define FAULT_MASK 0x00400000 + +#define DRV_NAME "ahci-seattle" + +static ssize_t seattle_transmit_led_message(struct ata_port *ap, u32 state, + ssize_t size); + +struct seattle_plat_data { + void __iomem *sgpio_ctrl; +}; + +static struct ata_port_operations ahci_port_ops = { + .inherits = &ahci_ops, +}; + +static const struct ata_port_info ahci_port_info = { + .flags = AHCI_FLAG_COMMON, + .pio_mask = ATA_PIO4, + .udma_mask = ATA_UDMA6, + .port_ops = &ahci_port_ops, +}; + +static struct ata_port_operations ahci_seattle_ops = { + .inherits = &ahci_ops, + .transmit_led_message = seattle_transmit_led_message, +}; + +static const struct ata_port_info ahci_port_seattle_info = { + .flags = AHCI_FLAG_COMMON | ATA_FLAG_EM | ATA_FLAG_SW_ACTIVITY, + .link_flags = ATA_LFLAG_SW_ACTIVITY, + .pio_mask = ATA_PIO4, + .udma_mask = ATA_UDMA6, + .port_ops = &ahci_seattle_ops, +}; + +static struct scsi_host_template ahci_platform_sht = { + AHCI_SHT(DRV_NAME), +}; + +static ssize_t seattle_transmit_led_message(struct ata_port *ap, u32 state, + ssize_t size) +{ + struct ahci_host_priv *hpriv = ap->host->private_data; + struct ahci_port_priv *pp = ap->private_data; + struct seattle_plat_data *plat_data = hpriv->plat_data; + unsigned long flags; + int pmp; + struct ahci_em_priv *emp; + u32 val; + + /* get the slot number from the message */ + pmp = (state & EM_MSG_LED_PMP_SLOT) >> 8; + if (pmp >= EM_MAX_SLOTS) + return -EINVAL; + emp = &pp->em_priv[pmp]; + + val = ioread32(plat_data->sgpio_ctrl); + if (state & ACTIVITY_MASK) + val |= 1 << ACTIVITY_BIT_POS((ap->port_no)); + else + val &= ~(1 << ACTIVITY_BIT_POS((ap->port_no))); + + if (state & LOCATE_MASK) + val |= 1 << LOCATE_BIT_POS((ap->port_no)); + else + val &= ~(1 << LOCATE_BIT_POS((ap->port_no))); + + if (state & FAULT_MASK) + val |= 1 << FAULT_BIT_POS((ap->port_no)); + else + val &= ~(1 << FAULT_BIT_POS((ap->port_no))); + + iowrite32(val, plat_data->sgpio_ctrl); + + spin_lock_irqsave(ap->lock, flags); + + /* save off new led state for port/slot */ + emp->led_state = state; + + spin_unlock_irqrestore(ap->lock, flags); + + return size; +} + +static const struct ata_port_info *ahci_seattle_get_port_info( + struct platform_device *pdev, struct ahci_host_priv *hpriv) +{ + struct device *dev = &pdev->dev; + struct seattle_plat_data *plat_data; + u32 val; + + plat_data = devm_kzalloc(dev, sizeof(*plat_data), GFP_KERNEL); + if (IS_ERR(plat_data)) + return &ahci_port_info; + + plat_data->sgpio_ctrl = devm_ioremap_resource(dev, + platform_get_resource(pdev, IORESOURCE_MEM, 1)); + if (IS_ERR(plat_data->sgpio_ctrl)) + return &ahci_port_info; + + val = ioread32(plat_data->sgpio_ctrl); + + if (!(val & 0xf)) + return &ahci_port_info; + + hpriv->em_loc = 0; + hpriv->em_buf_sz = 4; + hpriv->em_msg_type = EM_MSG_TYPE_LED; + hpriv->plat_data = plat_data; + + dev_info(dev, "SGPIO LED control is enabled.\n"); + return &ahci_port_seattle_info; +} + +static int ahci_seattle_probe(struct platform_device *pdev) +{ + int rc; + struct ahci_host_priv *hpriv; + + hpriv = ahci_platform_get_resources(pdev); + if (IS_ERR(hpriv)) + return PTR_ERR(hpriv); + + rc = ahci_platform_enable_resources(hpriv); + if (rc) + return rc; + + rc = ahci_platform_init_host(pdev, hpriv, + ahci_seattle_get_port_info(pdev, hpriv), + &ahci_platform_sht); + if (rc) + goto disable_resources; + + return 0; +disable_resources: + ahci_platform_disable_resources(hpriv); + return rc; +} + +static SIMPLE_DEV_PM_OPS(ahci_pm_ops, ahci_platform_suspend, + ahci_platform_resume); + +static const struct acpi_device_id ahci_acpi_match[] = { + { "AMDI0600", 0 }, + {} +}; +MODULE_DEVICE_TABLE(acpi, ahci_acpi_match); + +static struct platform_driver ahci_seattle_driver = { + .probe = ahci_seattle_probe, + .remove = ata_platform_remove_one, + .driver = { + .name = DRV_NAME, + .acpi_match_table = ahci_acpi_match, + .pm = &ahci_pm_ops, + }, +}; +module_platform_driver(ahci_seattle_driver); + +MODULE_DESCRIPTION("Seattle AHCI SATA platform driver"); +MODULE_AUTHOR("Brijesh Singh <brijesh.singh@amd.com>"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("platform:" DRV_NAME); diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c index 3982054060b8..a5d7c1c2a05e 100644 --- a/drivers/ata/libahci.c +++ b/drivers/ata/libahci.c @@ -507,6 +507,7 @@ void ahci_save_initial_config(struct device *dev, struct ahci_host_priv *hpriv) dev_info(dev, "forcing port_map 0x%x -> 0x%x\n", port_map, hpriv->force_port_map); port_map = hpriv->force_port_map; + hpriv->saved_port_map = port_map; } if (hpriv->mask_port_map) { diff --git a/drivers/base/power/opp/core.c b/drivers/base/power/opp/core.c index 433b60092972..d8f4cc22856c 100644 --- a/drivers/base/power/opp/core.c +++ b/drivers/base/power/opp/core.c @@ -259,9 +259,6 @@ unsigned long dev_pm_opp_get_max_volt_latency(struct device *dev) reg = opp_table->regulator; if (IS_ERR(reg)) { /* Regulator may not be required for device */ - if (reg) - dev_err(dev, "%s: Invalid regulator (%ld)\n", __func__, - PTR_ERR(reg)); rcu_read_unlock(); return 0; } diff --git a/drivers/base/property.c b/drivers/base/property.c index 9b1a65debd49..7f692accdc90 100644 --- a/drivers/base/property.c +++ b/drivers/base/property.c @@ -21,7 +21,7 @@ static inline bool is_pset_node(struct fwnode_handle *fwnode) { - return fwnode && fwnode->type == FWNODE_PDATA; + return !IS_ERR_OR_NULL(fwnode) && fwnode->type == FWNODE_PDATA; } static inline struct property_set *to_pset_node(struct fwnode_handle *fwnode) diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 94a1843b0426..0ede6d7e2568 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -538,7 +538,6 @@ static int _rbd_dev_v2_snap_size(struct rbd_device *rbd_dev, u64 snap_id, u8 *order, u64 *snap_size); static int _rbd_dev_v2_snap_features(struct rbd_device *rbd_dev, u64 snap_id, u64 *snap_features); -static u64 rbd_snap_id_by_name(struct rbd_device *rbd_dev, const char *name); static int rbd_open(struct block_device *bdev, fmode_t mode) { @@ -3127,9 +3126,6 @@ static void rbd_watch_cb(u64 ver, u64 notify_id, u8 opcode, void *data) struct rbd_device *rbd_dev = (struct rbd_device *)data; int ret; - if (!rbd_dev) - return; - dout("%s: \"%s\" notify_id %llu opcode %u\n", __func__, rbd_dev->header_name, (unsigned long long)notify_id, (unsigned int)opcode); @@ -3263,6 +3259,9 @@ static void rbd_dev_header_unwatch_sync(struct rbd_device *rbd_dev) ceph_osdc_cancel_event(rbd_dev->watch_event); rbd_dev->watch_event = NULL; + + dout("%s flushing notifies\n", __func__); + ceph_osdc_flush_notifies(&rbd_dev->rbd_client->client->osdc); } /* @@ -3642,21 +3641,14 @@ static void rbd_exists_validate(struct rbd_device *rbd_dev) static void rbd_dev_update_size(struct rbd_device *rbd_dev) { sector_t size; - bool removing; /* - * Don't hold the lock while doing disk operations, - * or lock ordering will conflict with the bdev mutex via: - * rbd_add() -> blkdev_get() -> rbd_open() + * If EXISTS is not set, rbd_dev->disk may be NULL, so don't + * try to update its size. If REMOVING is set, updating size + * is just useless work since the device can't be opened. */ - spin_lock_irq(&rbd_dev->lock); - removing = test_bit(RBD_DEV_FLAG_REMOVING, &rbd_dev->flags); - spin_unlock_irq(&rbd_dev->lock); - /* - * If the device is being removed, rbd_dev->disk has - * been destroyed, so don't try to update its size - */ - if (!removing) { + if (test_bit(RBD_DEV_FLAG_EXISTS, &rbd_dev->flags) && + !test_bit(RBD_DEV_FLAG_REMOVING, &rbd_dev->flags)) { size = (sector_t)rbd_dev->mapping.size / SECTOR_SIZE; dout("setting size to %llu sectors", (unsigned long long)size); set_capacity(rbd_dev->disk, size); @@ -4191,7 +4183,7 @@ static int _rbd_dev_v2_snap_features(struct rbd_device *rbd_dev, u64 snap_id, __le64 features; __le64 incompat; } __attribute__ ((packed)) features_buf = { 0 }; - u64 incompat; + u64 unsup; int ret; ret = rbd_obj_method_sync(rbd_dev, rbd_dev->header_name, @@ -4204,9 +4196,12 @@ static int _rbd_dev_v2_snap_features(struct rbd_device *rbd_dev, u64 snap_id, if (ret < sizeof (features_buf)) return -ERANGE; - incompat = le64_to_cpu(features_buf.incompat); - if (incompat & ~RBD_FEATURES_SUPPORTED) + unsup = le64_to_cpu(features_buf.incompat) & ~RBD_FEATURES_SUPPORTED; + if (unsup) { + rbd_warn(rbd_dev, "image uses unsupported features: 0x%llx", + unsup); return -ENXIO; + } *snap_features = le64_to_cpu(features_buf.features); @@ -5187,6 +5182,10 @@ out_err: return ret; } +/* + * rbd_dev->header_rwsem must be locked for write and will be unlocked + * upon return. + */ static int rbd_dev_device_setup(struct rbd_device *rbd_dev) { int ret; @@ -5195,7 +5194,7 @@ static int rbd_dev_device_setup(struct rbd_device *rbd_dev) ret = rbd_dev_id_get(rbd_dev); if (ret) - return ret; + goto err_out_unlock; BUILD_BUG_ON(DEV_NAME_LEN < sizeof (RBD_DRV_NAME) + MAX_INT_FORMAT_WIDTH); @@ -5236,8 +5235,9 @@ static int rbd_dev_device_setup(struct rbd_device *rbd_dev) /* Everything's ready. Announce the disk to the world. */ set_bit(RBD_DEV_FLAG_EXISTS, &rbd_dev->flags); - add_disk(rbd_dev->disk); + up_write(&rbd_dev->header_rwsem); + add_disk(rbd_dev->disk); pr_info("%s: added with size 0x%llx\n", rbd_dev->disk->disk_name, (unsigned long long) rbd_dev->mapping.size); @@ -5252,6 +5252,8 @@ err_out_blkdev: unregister_blkdev(rbd_dev->major, rbd_dev->name); err_out_id: rbd_dev_id_put(rbd_dev); +err_out_unlock: + up_write(&rbd_dev->header_rwsem); return ret; } @@ -5442,6 +5444,7 @@ static ssize_t do_rbd_add(struct bus_type *bus, spec = NULL; /* rbd_dev now owns this */ rbd_opts = NULL; /* rbd_dev now owns this */ + down_write(&rbd_dev->header_rwsem); rc = rbd_dev_image_probe(rbd_dev, 0); if (rc < 0) goto err_out_rbd_dev; @@ -5471,6 +5474,7 @@ out: return rc; err_out_rbd_dev: + up_write(&rbd_dev->header_rwsem); rbd_dev_destroy(rbd_dev); err_out_client: rbd_put_client(rbdc); @@ -5577,12 +5581,6 @@ static ssize_t do_rbd_remove(struct bus_type *bus, return ret; rbd_dev_header_unwatch_sync(rbd_dev); - /* - * flush remaining watch callbacks - these must be complete - * before the osd_client is shutdown - */ - dout("%s: flushing notifies", __func__); - ceph_osdc_flush_notifies(&rbd_dev->rbd_client->client->osdc); /* * Don't free anything from rbd_dev->disk until after all diff --git a/drivers/clk/imx/clk-imx6q.c b/drivers/clk/imx/clk-imx6q.c index 02e18182fcb5..2beb396fe652 100644 --- a/drivers/clk/imx/clk-imx6q.c +++ b/drivers/clk/imx/clk-imx6q.c @@ -394,7 +394,7 @@ static void __init imx6q_clocks_init(struct device_node *ccm_node) clk[IMX6QDL_CLK_LDB_DI1_DIV_3_5] = imx_clk_fixed_factor("ldb_di1_div_3_5", "ldb_di1", 2, 7); } else { clk[IMX6QDL_CLK_ECSPI_ROOT] = imx_clk_divider("ecspi_root", "pll3_60m", base + 0x38, 19, 6); - clk[IMX6QDL_CLK_CAN_ROOT] = imx_clk_divider("can_root", "pll3_60", base + 0x20, 2, 6); + clk[IMX6QDL_CLK_CAN_ROOT] = imx_clk_divider("can_root", "pll3_60m", base + 0x20, 2, 6); clk[IMX6QDL_CLK_IPG_PER] = imx_clk_fixup_divider("ipg_per", "ipg", base + 0x1c, 0, 6, imx_cscmr1_fixup); clk[IMX6QDL_CLK_UART_SERIAL_PODF] = imx_clk_divider("uart_serial_podf", "pll3_80m", base + 0x24, 0, 6); clk[IMX6QDL_CLK_LDB_DI0_DIV_3_5] = imx_clk_fixed_factor("ldb_di0_div_3_5", "ldb_di0_sel", 2, 7); diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index e93405f0eac4..c4acfc5273b3 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -1557,21 +1557,25 @@ void cpufreq_suspend(void) if (!cpufreq_driver) return; - if (!has_target()) + if (!has_target() && !cpufreq_driver->suspend) goto suspend; pr_debug("%s: Suspending Governors\n", __func__); for_each_active_policy(policy) { - down_write(&policy->rwsem); - ret = cpufreq_governor(policy, CPUFREQ_GOV_STOP); - up_write(&policy->rwsem); + if (has_target()) { + down_write(&policy->rwsem); + ret = cpufreq_governor(policy, CPUFREQ_GOV_STOP); + up_write(&policy->rwsem); - if (ret) - pr_err("%s: Failed to stop governor for policy: %p\n", - __func__, policy); - else if (cpufreq_driver->suspend - && cpufreq_driver->suspend(policy)) + if (ret) { + pr_err("%s: Failed to stop governor for policy: %p\n", + __func__, policy); + continue; + } + } + + if (cpufreq_driver->suspend && cpufreq_driver->suspend(policy)) pr_err("%s: Failed to suspend driver: %p\n", __func__, policy); } @@ -1596,7 +1600,7 @@ void cpufreq_resume(void) cpufreq_suspended = false; - if (!has_target()) + if (!has_target() && !cpufreq_driver->resume) return; pr_debug("%s: Resuming Governors\n", __func__); @@ -1605,7 +1609,7 @@ void cpufreq_resume(void) if (cpufreq_driver->resume && cpufreq_driver->resume(policy)) { pr_err("%s: Failed to resume driver: %p\n", __func__, policy); - } else { + } else if (has_target()) { down_write(&policy->rwsem); ret = cpufreq_start_governor(policy); up_write(&policy->rwsem); diff --git a/drivers/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c index 10a5cfeae8c5..5f1147fa9239 100644 --- a/drivers/cpufreq/cpufreq_governor.c +++ b/drivers/cpufreq/cpufreq_governor.c @@ -193,12 +193,8 @@ unsigned int dbs_update(struct cpufreq_policy *policy) wall_time = cur_wall_time - j_cdbs->prev_cpu_wall; j_cdbs->prev_cpu_wall = cur_wall_time; - if (cur_idle_time <= j_cdbs->prev_cpu_idle) { - idle_time = 0; - } else { - idle_time = cur_idle_time - j_cdbs->prev_cpu_idle; - j_cdbs->prev_cpu_idle = cur_idle_time; - } + idle_time = cur_idle_time - j_cdbs->prev_cpu_idle; + j_cdbs->prev_cpu_idle = cur_idle_time; if (ignore_nice) { u64 cur_nice = kcpustat_cpu(j).cpustat[CPUTIME_NICE]; diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 30fe323c4551..b230ebaae66c 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -453,6 +453,14 @@ static void intel_pstate_hwp_set(const struct cpumask *cpumask) } } +static int intel_pstate_hwp_set_policy(struct cpufreq_policy *policy) +{ + if (hwp_active) + intel_pstate_hwp_set(policy->cpus); + + return 0; +} + static void intel_pstate_hwp_set_online_cpus(void) { get_online_cpus(); @@ -813,6 +821,11 @@ static int core_get_max_pstate(void) if (err) goto skip_tar; + /* For level 1 and 2, bits[23:16] contain the ratio */ + if (tdp_ctrl) + tdp_ratio >>= 16; + + tdp_ratio &= 0xff; /* ratios are only 8 bits long */ if (tdp_ratio - 1 == tar) { max_pstate = tar; pr_debug("max_pstate=TAC %x\n", max_pstate); @@ -1057,8 +1070,9 @@ static inline bool intel_pstate_sample(struct cpudata *cpu, u64 time) static inline int32_t get_avg_frequency(struct cpudata *cpu) { - return div64_u64(cpu->pstate.max_pstate_physical * cpu->sample.aperf * - cpu->pstate.scaling, cpu->sample.mperf); + return fp_toint(mul_fp(cpu->sample.core_pct_busy, + int_tofp(cpu->pstate.max_pstate_physical * + cpu->pstate.scaling / 100))); } static inline int32_t get_target_pstate_use_cpu_load(struct cpudata *cpu) @@ -1101,8 +1115,6 @@ static inline int32_t get_target_pstate_use_performance(struct cpudata *cpu) int32_t core_busy, max_pstate, current_pstate, sample_ratio; u64 duration_ns; - intel_pstate_calc_busy(cpu); - /* * core_busy is the ratio of actual performance to max * max_pstate is the max non turbo pstate available @@ -1186,8 +1198,11 @@ static void intel_pstate_update_util(struct update_util_data *data, u64 time, if ((s64)delta_ns >= pid_params.sample_rate_ns) { bool sample_taken = intel_pstate_sample(cpu, time); - if (sample_taken && !hwp_active) - intel_pstate_adjust_busy_pstate(cpu); + if (sample_taken) { + intel_pstate_calc_busy(cpu); + if (!hwp_active) + intel_pstate_adjust_busy_pstate(cpu); + } } } @@ -1341,8 +1356,7 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy) out: intel_pstate_set_update_util_hook(policy->cpu); - if (hwp_active) - intel_pstate_hwp_set(policy->cpus); + intel_pstate_hwp_set_policy(policy); return 0; } @@ -1406,6 +1420,7 @@ static struct cpufreq_driver intel_pstate_driver = { .flags = CPUFREQ_CONST_LOOPS, .verify = intel_pstate_verify_policy, .setpolicy = intel_pstate_set_policy, + .resume = intel_pstate_hwp_set_policy, .get = intel_pstate_get, .init = intel_pstate_cpu_init, .stop_cpu = intel_pstate_stop_cpu, diff --git a/drivers/cpufreq/sti-cpufreq.c b/drivers/cpufreq/sti-cpufreq.c index a9c659f58974..04042038ec4b 100644 --- a/drivers/cpufreq/sti-cpufreq.c +++ b/drivers/cpufreq/sti-cpufreq.c @@ -259,6 +259,10 @@ static int sti_cpufreq_init(void) { int ret; + if ((!of_machine_is_compatible("st,stih407")) && + (!of_machine_is_compatible("st,stih410"))) + return -ENODEV; + ddata.cpu = get_cpu_device(0); if (!ddata.cpu) { dev_err(ddata.cpu, "Failed to get device for CPU0\n"); diff --git a/drivers/cpuidle/cpuidle-arm.c b/drivers/cpuidle/cpuidle-arm.c index 545069d5fdfb..e342565e8715 100644 --- a/drivers/cpuidle/cpuidle-arm.c +++ b/drivers/cpuidle/cpuidle-arm.c @@ -50,7 +50,7 @@ static int arm_enter_idle_state(struct cpuidle_device *dev, * call the CPU ops suspend protocol with idle index as a * parameter. */ - arm_cpuidle_suspend(idx); + ret = arm_cpuidle_suspend(idx); cpu_pm_exit(); } diff --git a/drivers/crypto/talitos.c b/drivers/crypto/talitos.c index a0d4a08313ae..aae05547b924 100644 --- a/drivers/crypto/talitos.c +++ b/drivers/crypto/talitos.c @@ -63,6 +63,14 @@ static void to_talitos_ptr(struct talitos_ptr *ptr, dma_addr_t dma_addr, ptr->eptr = upper_32_bits(dma_addr); } +static void copy_talitos_ptr(struct talitos_ptr *dst_ptr, + struct talitos_ptr *src_ptr, bool is_sec1) +{ + dst_ptr->ptr = src_ptr->ptr; + if (!is_sec1) + dst_ptr->eptr = src_ptr->eptr; +} + static void to_talitos_ptr_len(struct talitos_ptr *ptr, unsigned int len, bool is_sec1) { @@ -1083,21 +1091,20 @@ static int ipsec_esp(struct talitos_edesc *edesc, struct aead_request *areq, sg_count = dma_map_sg(dev, areq->src, edesc->src_nents ?: 1, (areq->src == areq->dst) ? DMA_BIDIRECTIONAL : DMA_TO_DEVICE); - /* hmac data */ desc->ptr[1].len = cpu_to_be16(areq->assoclen); if (sg_count > 1 && (ret = sg_to_link_tbl_offset(areq->src, sg_count, 0, areq->assoclen, &edesc->link_tbl[tbl_off])) > 1) { - tbl_off += ret; - to_talitos_ptr(&desc->ptr[1], edesc->dma_link_tbl + tbl_off * sizeof(struct talitos_ptr), 0); desc->ptr[1].j_extent = DESC_PTR_LNKTBL_JUMP; dma_sync_single_for_device(dev, edesc->dma_link_tbl, edesc->dma_len, DMA_BIDIRECTIONAL); + + tbl_off += ret; } else { to_talitos_ptr(&desc->ptr[1], sg_dma_address(areq->src), 0); desc->ptr[1].j_extent = 0; @@ -1126,11 +1133,13 @@ static int ipsec_esp(struct talitos_edesc *edesc, struct aead_request *areq, if (edesc->desc.hdr & DESC_HDR_MODE1_MDEU_CICV) sg_link_tbl_len += authsize; - if (sg_count > 1 && - (ret = sg_to_link_tbl_offset(areq->src, sg_count, areq->assoclen, - sg_link_tbl_len, - &edesc->link_tbl[tbl_off])) > 1) { - tbl_off += ret; + if (sg_count == 1) { + to_talitos_ptr(&desc->ptr[4], sg_dma_address(areq->src) + + areq->assoclen, 0); + } else if ((ret = sg_to_link_tbl_offset(areq->src, sg_count, + areq->assoclen, sg_link_tbl_len, + &edesc->link_tbl[tbl_off])) > + 1) { desc->ptr[4].j_extent |= DESC_PTR_LNKTBL_JUMP; to_talitos_ptr(&desc->ptr[4], edesc->dma_link_tbl + tbl_off * @@ -1138,8 +1147,10 @@ static int ipsec_esp(struct talitos_edesc *edesc, struct aead_request *areq, dma_sync_single_for_device(dev, edesc->dma_link_tbl, edesc->dma_len, DMA_BIDIRECTIONAL); - } else - to_talitos_ptr(&desc->ptr[4], sg_dma_address(areq->src), 0); + tbl_off += ret; + } else { + copy_talitos_ptr(&desc->ptr[4], &edesc->link_tbl[tbl_off], 0); + } /* cipher out */ desc->ptr[5].len = cpu_to_be16(cryptlen); @@ -1151,11 +1162,13 @@ static int ipsec_esp(struct talitos_edesc *edesc, struct aead_request *areq, edesc->icv_ool = false; - if (sg_count > 1 && - (sg_count = sg_to_link_tbl_offset(areq->dst, sg_count, + if (sg_count == 1) { + to_talitos_ptr(&desc->ptr[5], sg_dma_address(areq->dst) + + areq->assoclen, 0); + } else if ((sg_count = + sg_to_link_tbl_offset(areq->dst, sg_count, areq->assoclen, cryptlen, - &edesc->link_tbl[tbl_off])) > - 1) { + &edesc->link_tbl[tbl_off])) > 1) { struct talitos_ptr *tbl_ptr = &edesc->link_tbl[tbl_off]; to_talitos_ptr(&desc->ptr[5], edesc->dma_link_tbl + @@ -1178,8 +1191,9 @@ static int ipsec_esp(struct talitos_edesc *edesc, struct aead_request *areq, edesc->dma_len, DMA_BIDIRECTIONAL); edesc->icv_ool = true; - } else - to_talitos_ptr(&desc->ptr[5], sg_dma_address(areq->dst), 0); + } else { + copy_talitos_ptr(&desc->ptr[5], &edesc->link_tbl[tbl_off], 0); + } /* iv out */ map_single_talitos_ptr(dev, &desc->ptr[6], ivsize, ctx->iv, @@ -2629,21 +2643,11 @@ struct talitos_crypto_alg { struct talitos_alg_template algt; }; -static int talitos_cra_init(struct crypto_tfm *tfm) +static int talitos_init_common(struct talitos_ctx *ctx, + struct talitos_crypto_alg *talitos_alg) { - struct crypto_alg *alg = tfm->__crt_alg; - struct talitos_crypto_alg *talitos_alg; - struct talitos_ctx *ctx = crypto_tfm_ctx(tfm); struct talitos_private *priv; - if ((alg->cra_flags & CRYPTO_ALG_TYPE_MASK) == CRYPTO_ALG_TYPE_AHASH) - talitos_alg = container_of(__crypto_ahash_alg(alg), - struct talitos_crypto_alg, - algt.alg.hash); - else - talitos_alg = container_of(alg, struct talitos_crypto_alg, - algt.alg.crypto); - /* update context with ptr to dev */ ctx->dev = talitos_alg->dev; @@ -2661,10 +2665,33 @@ static int talitos_cra_init(struct crypto_tfm *tfm) return 0; } +static int talitos_cra_init(struct crypto_tfm *tfm) +{ + struct crypto_alg *alg = tfm->__crt_alg; + struct talitos_crypto_alg *talitos_alg; + struct talitos_ctx *ctx = crypto_tfm_ctx(tfm); + + if ((alg->cra_flags & CRYPTO_ALG_TYPE_MASK) == CRYPTO_ALG_TYPE_AHASH) + talitos_alg = container_of(__crypto_ahash_alg(alg), + struct talitos_crypto_alg, + algt.alg.hash); + else + talitos_alg = container_of(alg, struct talitos_crypto_alg, + algt.alg.crypto); + + return talitos_init_common(ctx, talitos_alg); +} + static int talitos_cra_init_aead(struct crypto_aead *tfm) { - talitos_cra_init(crypto_aead_tfm(tfm)); - return 0; + struct aead_alg *alg = crypto_aead_alg(tfm); + struct talitos_crypto_alg *talitos_alg; + struct talitos_ctx *ctx = crypto_aead_ctx(tfm); + + talitos_alg = container_of(alg, struct talitos_crypto_alg, + algt.alg.aead); + + return talitos_init_common(ctx, talitos_alg); } static int talitos_cra_init_ahash(struct crypto_tfm *tfm) diff --git a/drivers/edac/i7core_edac.c b/drivers/edac/i7core_edac.c index 01087a38da22..792bdae2b91d 100644 --- a/drivers/edac/i7core_edac.c +++ b/drivers/edac/i7core_edac.c @@ -1866,7 +1866,7 @@ static int i7core_mce_check_error(struct notifier_block *nb, unsigned long val, i7_dev = get_i7core_dev(mce->socketid); if (!i7_dev) - return NOTIFY_BAD; + return NOTIFY_DONE; mci = i7_dev->mci; pvt = mci->pvt_info; diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c index 468447aff8eb..8bf745d2da7e 100644 --- a/drivers/edac/sb_edac.c +++ b/drivers/edac/sb_edac.c @@ -3168,7 +3168,7 @@ static int sbridge_mce_check_error(struct notifier_block *nb, unsigned long val, mci = get_mci_for_node_id(mce->socketid); if (!mci) - return NOTIFY_BAD; + return NOTIFY_DONE; pvt = mci->pvt_info; /* diff --git a/drivers/firmware/efi/vars.c b/drivers/firmware/efi/vars.c index 0ac594c0a234..34b741940494 100644 --- a/drivers/firmware/efi/vars.c +++ b/drivers/firmware/efi/vars.c @@ -202,29 +202,44 @@ static const struct variable_validate variable_validate[] = { { NULL_GUID, "", NULL }, }; +/* + * Check if @var_name matches the pattern given in @match_name. + * + * @var_name: an array of @len non-NUL characters. + * @match_name: a NUL-terminated pattern string, optionally ending in "*". A + * final "*" character matches any trailing characters @var_name, + * including the case when there are none left in @var_name. + * @match: on output, the number of non-wildcard characters in @match_name + * that @var_name matches, regardless of the return value. + * @return: whether @var_name fully matches @match_name. + */ static bool variable_matches(const char *var_name, size_t len, const char *match_name, int *match) { for (*match = 0; ; (*match)++) { char c = match_name[*match]; - char u = var_name[*match]; - /* Wildcard in the matching name means we've matched */ - if (c == '*') + switch (c) { + case '*': + /* Wildcard in @match_name means we've matched. */ return true; - /* Case sensitive match */ - if (!c && *match == len) - return true; + case '\0': + /* @match_name has ended. Has @var_name too? */ + return (*match == len); - if (c != u) + default: + /* + * We've reached a non-wildcard char in @match_name. + * Continue only if there's an identical character in + * @var_name. + */ + if (*match < len && c == var_name[*match]) + continue; return false; - - if (!c) - return true; + } } - return true; } bool diff --git a/drivers/firmware/psci.c b/drivers/firmware/psci.c index 11bfee8b79a9..b5d05807e6ec 100644 --- a/drivers/firmware/psci.c +++ b/drivers/firmware/psci.c @@ -360,7 +360,7 @@ static struct cpuidle_ops psci_cpuidle_ops __initdata = { .init = psci_dt_cpu_init_idle, }; -CPUIDLE_METHOD_OF_DECLARE(psci, "arm,psci", &psci_cpuidle_ops); +CPUIDLE_METHOD_OF_DECLARE(psci, "psci", &psci_cpuidle_ops); #endif #endif diff --git a/drivers/firmware/qemu_fw_cfg.c b/drivers/firmware/qemu_fw_cfg.c index 815c4a5cae54..1b95475b6aef 100644 --- a/drivers/firmware/qemu_fw_cfg.c +++ b/drivers/firmware/qemu_fw_cfg.c @@ -77,7 +77,7 @@ static inline u16 fw_cfg_sel_endianness(u16 key) static inline void fw_cfg_read_blob(u16 key, void *buf, loff_t pos, size_t count) { - u32 glk; + u32 glk = -1U; acpi_status status; /* If we have ACPI, ensure mutual exclusion against any potential diff --git a/drivers/gpio/gpio-rcar.c b/drivers/gpio/gpio-rcar.c index d9ab0cd1d205..4d9a315cfd43 100644 --- a/drivers/gpio/gpio-rcar.c +++ b/drivers/gpio/gpio-rcar.c @@ -196,44 +196,6 @@ static int gpio_rcar_irq_set_wake(struct irq_data *d, unsigned int on) return 0; } -static void gpio_rcar_irq_bus_lock(struct irq_data *d) -{ - struct gpio_chip *gc = irq_data_get_irq_chip_data(d); - struct gpio_rcar_priv *p = gpiochip_get_data(gc); - - pm_runtime_get_sync(&p->pdev->dev); -} - -static void gpio_rcar_irq_bus_sync_unlock(struct irq_data *d) -{ - struct gpio_chip *gc = irq_data_get_irq_chip_data(d); - struct gpio_rcar_priv *p = gpiochip_get_data(gc); - - pm_runtime_put(&p->pdev->dev); -} - - -static int gpio_rcar_irq_request_resources(struct irq_data *d) -{ - struct gpio_chip *gc = irq_data_get_irq_chip_data(d); - struct gpio_rcar_priv *p = gpiochip_get_data(gc); - int error; - - error = pm_runtime_get_sync(&p->pdev->dev); - if (error < 0) - return error; - - return 0; -} - -static void gpio_rcar_irq_release_resources(struct irq_data *d) -{ - struct gpio_chip *gc = irq_data_get_irq_chip_data(d); - struct gpio_rcar_priv *p = gpiochip_get_data(gc); - - pm_runtime_put(&p->pdev->dev); -} - static irqreturn_t gpio_rcar_irq_handler(int irq, void *dev_id) { struct gpio_rcar_priv *p = dev_id; @@ -280,32 +242,18 @@ static void gpio_rcar_config_general_input_output_mode(struct gpio_chip *chip, static int gpio_rcar_request(struct gpio_chip *chip, unsigned offset) { - struct gpio_rcar_priv *p = gpiochip_get_data(chip); - int error; - - error = pm_runtime_get_sync(&p->pdev->dev); - if (error < 0) - return error; - - error = pinctrl_request_gpio(chip->base + offset); - if (error) - pm_runtime_put(&p->pdev->dev); - - return error; + return pinctrl_request_gpio(chip->base + offset); } static void gpio_rcar_free(struct gpio_chip *chip, unsigned offset) { - struct gpio_rcar_priv *p = gpiochip_get_data(chip); - pinctrl_free_gpio(chip->base + offset); - /* Set the GPIO as an input to ensure that the next GPIO request won't + /* + * Set the GPIO as an input to ensure that the next GPIO request won't * drive the GPIO pin as an output. */ gpio_rcar_config_general_input_output_mode(chip, offset, false); - - pm_runtime_put(&p->pdev->dev); } static int gpio_rcar_direction_input(struct gpio_chip *chip, unsigned offset) @@ -452,6 +400,7 @@ static int gpio_rcar_probe(struct platform_device *pdev) } pm_runtime_enable(dev); + pm_runtime_get_sync(dev); io = platform_get_resource(pdev, IORESOURCE_MEM, 0); irq = platform_get_resource(pdev, IORESOURCE_IRQ, 0); @@ -488,10 +437,6 @@ static int gpio_rcar_probe(struct platform_device *pdev) irq_chip->irq_unmask = gpio_rcar_irq_enable; irq_chip->irq_set_type = gpio_rcar_irq_set_type; irq_chip->irq_set_wake = gpio_rcar_irq_set_wake; - irq_chip->irq_bus_lock = gpio_rcar_irq_bus_lock; - irq_chip->irq_bus_sync_unlock = gpio_rcar_irq_bus_sync_unlock; - irq_chip->irq_request_resources = gpio_rcar_irq_request_resources; - irq_chip->irq_release_resources = gpio_rcar_irq_release_resources; irq_chip->flags = IRQCHIP_SET_TYPE_MASKED | IRQCHIP_MASK_ON_SUSPEND; ret = gpiochip_add_data(gpio_chip, p); @@ -522,6 +467,7 @@ static int gpio_rcar_probe(struct platform_device *pdev) err1: gpiochip_remove(gpio_chip); err0: + pm_runtime_put(dev); pm_runtime_disable(dev); return ret; } @@ -532,6 +478,7 @@ static int gpio_rcar_remove(struct platform_device *pdev) gpiochip_remove(&p->gpio_chip); + pm_runtime_put(&pdev->dev); pm_runtime_disable(&pdev->dev); return 0; } diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c index 682070d20f00..2dc52585e3f2 100644 --- a/drivers/gpio/gpiolib-acpi.c +++ b/drivers/gpio/gpiolib-acpi.c @@ -977,7 +977,7 @@ bool acpi_can_fallback_to_crs(struct acpi_device *adev, const char *con_id) lookup = kmalloc(sizeof(*lookup), GFP_KERNEL); if (lookup) { lookup->adev = adev; - lookup->con_id = con_id; + lookup->con_id = kstrdup(con_id, GFP_KERNEL); list_add_tail(&lookup->node, &acpi_crs_lookup_list); } } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c index 0020a0ea43ff..35a1248aaa77 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c @@ -63,10 +63,6 @@ bool amdgpu_has_atpx(void) { return amdgpu_atpx_priv.atpx_detected; } -bool amdgpu_has_atpx_dgpu_power_cntl(void) { - return amdgpu_atpx_priv.atpx.functions.power_cntl; -} - /** * amdgpu_atpx_call - call an ATPX method * @@ -146,6 +142,13 @@ static void amdgpu_atpx_parse_functions(struct amdgpu_atpx_functions *f, u32 mas */ static int amdgpu_atpx_validate(struct amdgpu_atpx *atpx) { + /* make sure required functions are enabled */ + /* dGPU power control is required */ + if (atpx->functions.power_cntl == false) { + printk("ATPX dGPU power cntl not present, forcing\n"); + atpx->functions.power_cntl = true; + } + if (atpx->functions.px_params) { union acpi_object *info; struct atpx_px_params output; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 612117478b57..2139da773da6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -62,12 +62,6 @@ static const char *amdgpu_asic_name[] = { "LAST", }; -#if defined(CONFIG_VGA_SWITCHEROO) -bool amdgpu_has_atpx_dgpu_power_cntl(void); -#else -static inline bool amdgpu_has_atpx_dgpu_power_cntl(void) { return false; } -#endif - bool amdgpu_device_is_px(struct drm_device *dev) { struct amdgpu_device *adev = dev->dev_private; @@ -1485,7 +1479,7 @@ int amdgpu_device_init(struct amdgpu_device *adev, if (amdgpu_runtime_pm == 1) runtime = true; - if (amdgpu_device_is_px(ddev) && amdgpu_has_atpx_dgpu_power_cntl()) + if (amdgpu_device_is_px(ddev)) runtime = true; vga_switcheroo_register_client(adev->pdev, &amdgpu_switcheroo_ops, runtime); if (runtime) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index e557fc1f17c8..7ecea83ce453 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -541,6 +541,7 @@ int amdgpu_bo_set_metadata (struct amdgpu_bo *bo, void *metadata, if (!metadata_size) { if (bo->metadata_size) { kfree(bo->metadata); + bo->metadata = NULL; bo->metadata_size = 0; } return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c b/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c index 1e0bba29e167..1cd6de575305 100644 --- a/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c +++ b/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c @@ -298,6 +298,10 @@ bool amdgpu_atombios_encoder_mode_fixup(struct drm_encoder *encoder, && (mode->crtc_vsync_start < (mode->crtc_vdisplay + 2))) adjusted_mode->crtc_vsync_start = adjusted_mode->crtc_vdisplay + 2; + /* vertical FP must be at least 1 */ + if (mode->crtc_vsync_start == mode->crtc_vdisplay) + adjusted_mode->crtc_vsync_start++; + /* get the native mode for scaling */ if (amdgpu_encoder->active_device & (ATOM_DEVICE_LCD_SUPPORT)) amdgpu_panel_mode_fixup(encoder, adjusted_mode); diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c index 05b0353d3880..a4a2e6cc61bb 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c @@ -910,7 +910,10 @@ static int gmc_v7_0_late_init(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; - return amdgpu_irq_get(adev, &adev->mc.vm_fault, 0); + if (amdgpu_vm_fault_stop != AMDGPU_VM_FAULT_STOP_ALWAYS) + return amdgpu_irq_get(adev, &adev->mc.vm_fault, 0); + else + return 0; } static int gmc_v7_0_sw_init(void *handle) diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c index 02deb3229405..7a9db2c72c89 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c @@ -870,7 +870,10 @@ static int gmc_v8_0_late_init(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; - return amdgpu_irq_get(adev, &adev->mc.vm_fault, 0); + if (amdgpu_vm_fault_stop != AMDGPU_VM_FAULT_STOP_ALWAYS) + return amdgpu_irq_get(adev, &adev->mc.vm_fault, 0); + else + return 0; } #define mmMC_SEQ_MISC0_FIJI 0xA71 diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c index e17fbdaf874b..71ea0521ea96 100644 --- a/drivers/gpu/drm/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/drm_dp_mst_topology.c @@ -1796,6 +1796,11 @@ int drm_dp_update_payload_part1(struct drm_dp_mst_topology_mgr *mgr) req_payload.start_slot = cur_slots; if (mgr->proposed_vcpis[i]) { port = container_of(mgr->proposed_vcpis[i], struct drm_dp_mst_port, vcpi); + port = drm_dp_get_validated_port_ref(mgr, port); + if (!port) { + mutex_unlock(&mgr->payload_lock); + return -EINVAL; + } req_payload.num_slots = mgr->proposed_vcpis[i]->num_slots; req_payload.vcpi = mgr->proposed_vcpis[i]->vcpi; } else { @@ -1823,6 +1828,9 @@ int drm_dp_update_payload_part1(struct drm_dp_mst_topology_mgr *mgr) mgr->payloads[i].payload_state = req_payload.payload_state; } cur_slots += req_payload.num_slots; + + if (port) + drm_dp_put_port(port); } for (i = 0; i < mgr->max_payloads; i++) { @@ -2128,6 +2136,8 @@ int drm_dp_mst_topology_mgr_resume(struct drm_dp_mst_topology_mgr *mgr) if (mgr->mst_primary) { int sret; + u8 guid[16]; + sret = drm_dp_dpcd_read(mgr->aux, DP_DPCD_REV, mgr->dpcd, DP_RECEIVER_CAP_SIZE); if (sret != DP_RECEIVER_CAP_SIZE) { DRM_DEBUG_KMS("dpcd read failed - undocked during suspend?\n"); @@ -2142,6 +2152,16 @@ int drm_dp_mst_topology_mgr_resume(struct drm_dp_mst_topology_mgr *mgr) ret = -1; goto out_unlock; } + + /* Some hubs forget their guids after they resume */ + sret = drm_dp_dpcd_read(mgr->aux, DP_GUID, guid, 16); + if (sret != 16) { + DRM_DEBUG_KMS("dpcd read failed - undocked during suspend?\n"); + ret = -1; + goto out_unlock; + } + drm_dp_check_mstb_guid(mgr->mst_primary, guid); + ret = 0; } else ret = -1; diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c index 09198d0b5814..306dde18a94a 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c @@ -572,6 +572,24 @@ int etnaviv_gpu_init(struct etnaviv_gpu *gpu) goto fail; } + /* + * Set the GPU linear window to be at the end of the DMA window, where + * the CMA area is likely to reside. This ensures that we are able to + * map the command buffers while having the linear window overlap as + * much RAM as possible, so we can optimize mappings for other buffers. + * + * For 3D cores only do this if MC2.0 is present, as with MC1.0 it leads + * to different views of the memory on the individual engines. + */ + if (!(gpu->identity.features & chipFeatures_PIPE_3D) || + (gpu->identity.minor_features0 & chipMinorFeatures0_MC20)) { + u32 dma_mask = (u32)dma_get_required_mask(gpu->dev); + if (dma_mask < PHYS_OFFSET + SZ_2G) + gpu->memory_base = PHYS_OFFSET; + else + gpu->memory_base = dma_mask - SZ_2G + 1; + } + ret = etnaviv_hw_reset(gpu); if (ret) goto fail; @@ -1566,7 +1584,6 @@ static int etnaviv_gpu_platform_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct etnaviv_gpu *gpu; - u32 dma_mask; int err = 0; gpu = devm_kzalloc(dev, sizeof(*gpu), GFP_KERNEL); @@ -1576,18 +1593,6 @@ static int etnaviv_gpu_platform_probe(struct platform_device *pdev) gpu->dev = &pdev->dev; mutex_init(&gpu->lock); - /* - * Set the GPU linear window to be at the end of the DMA window, where - * the CMA area is likely to reside. This ensures that we are able to - * map the command buffers while having the linear window overlap as - * much RAM as possible, so we can optimize mappings for other buffers. - */ - dma_mask = (u32)dma_get_required_mask(dev); - if (dma_mask < PHYS_OFFSET + SZ_2G) - gpu->memory_base = PHYS_OFFSET; - else - gpu->memory_base = dma_mask - SZ_2G + 1; - /* Map registers: */ gpu->mmio = etnaviv_ioremap(pdev, NULL, dev_name(gpu->dev)); if (IS_ERR(gpu->mmio)) diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index 30798cbc6fc0..6d2fb3f4ac62 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -792,7 +792,7 @@ static int i915_drm_resume(struct drm_device *dev) static int i915_drm_resume_early(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; - int ret = 0; + int ret; /* * We have a resume ordering issue with the snd-hda driver also @@ -803,6 +803,36 @@ static int i915_drm_resume_early(struct drm_device *dev) * FIXME: This should be solved with a special hdmi sink device or * similar so that power domains can be employed. */ + + /* + * Note that we need to set the power state explicitly, since we + * powered off the device during freeze and the PCI core won't power + * it back up for us during thaw. Powering off the device during + * freeze is not a hard requirement though, and during the + * suspend/resume phases the PCI core makes sure we get here with the + * device powered on. So in case we change our freeze logic and keep + * the device powered we can also remove the following set power state + * call. + */ + ret = pci_set_power_state(dev->pdev, PCI_D0); + if (ret) { + DRM_ERROR("failed to set PCI D0 power state (%d)\n", ret); + goto out; + } + + /* + * Note that pci_enable_device() first enables any parent bridge + * device and only then sets the power state for this device. The + * bridge enabling is a nop though, since bridge devices are resumed + * first. The order of enabling power and enabling the device is + * imposed by the PCI core as described above, so here we preserve the + * same order for the freeze/thaw phases. + * + * TODO: eventually we should remove pci_disable_device() / + * pci_enable_enable_device() from suspend/resume. Due to how they + * depend on the device enable refcount we can't anyway depend on them + * disabling/enabling the device. + */ if (pci_enable_device(dev->pdev)) { ret = -EIO; goto out; diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index f76cbf3e5d1e..fffdac801d3b 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -2907,7 +2907,14 @@ enum skl_disp_power_wells { #define GEN6_RP_STATE_CAP _MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5998) #define BXT_RP_STATE_CAP _MMIO(0x138170) -#define INTERVAL_1_28_US(us) (((us) * 100) >> 7) +/* + * Make these a multiple of magic 25 to avoid SNB (eg. Dell XPS + * 8300) freezing up around GPU hangs. Looks as if even + * scheduling/timer interrupts start misbehaving if the RPS + * EI/thresholds are "bad", leading to a very sluggish or even + * frozen machine. + */ +#define INTERVAL_1_28_US(us) roundup(((us) * 100) >> 7, 25) #define INTERVAL_1_33_US(us) (((us) * 3) >> 2) #define INTERVAL_0_833_US(us) (((us) * 6) / 5) #define GT_INTERVAL_FROM_US(dev_priv, us) (IS_GEN9(dev_priv) ? \ diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c index 62de9f4bce09..3b57bf06abe8 100644 --- a/drivers/gpu/drm/i915/intel_ddi.c +++ b/drivers/gpu/drm/i915/intel_ddi.c @@ -443,9 +443,17 @@ void intel_prepare_ddi_buffer(struct intel_encoder *encoder) } else if (IS_BROADWELL(dev_priv)) { ddi_translations_fdi = bdw_ddi_translations_fdi; ddi_translations_dp = bdw_ddi_translations_dp; - ddi_translations_edp = bdw_ddi_translations_edp; + + if (dev_priv->edp_low_vswing) { + ddi_translations_edp = bdw_ddi_translations_edp; + n_edp_entries = ARRAY_SIZE(bdw_ddi_translations_edp); + } else { + ddi_translations_edp = bdw_ddi_translations_dp; + n_edp_entries = ARRAY_SIZE(bdw_ddi_translations_dp); + } + ddi_translations_hdmi = bdw_ddi_translations_hdmi; - n_edp_entries = ARRAY_SIZE(bdw_ddi_translations_edp); + n_dp_entries = ARRAY_SIZE(bdw_ddi_translations_dp); n_hdmi_entries = ARRAY_SIZE(bdw_ddi_translations_hdmi); hdmi_default_entry = 7; @@ -3201,12 +3209,6 @@ void intel_ddi_get_config(struct intel_encoder *encoder, intel_ddi_clock_get(encoder, pipe_config); } -static void intel_ddi_destroy(struct drm_encoder *encoder) -{ - /* HDMI has nothing special to destroy, so we can go with this. */ - intel_dp_encoder_destroy(encoder); -} - static bool intel_ddi_compute_config(struct intel_encoder *encoder, struct intel_crtc_state *pipe_config) { @@ -3225,7 +3227,8 @@ static bool intel_ddi_compute_config(struct intel_encoder *encoder, } static const struct drm_encoder_funcs intel_ddi_funcs = { - .destroy = intel_ddi_destroy, + .reset = intel_dp_encoder_reset, + .destroy = intel_dp_encoder_destroy, }; static struct intel_connector * @@ -3324,6 +3327,7 @@ void intel_ddi_init(struct drm_device *dev, enum port port) intel_encoder->post_disable = intel_ddi_post_disable; intel_encoder->get_hw_state = intel_ddi_get_hw_state; intel_encoder->get_config = intel_ddi_get_config; + intel_encoder->suspend = intel_dp_encoder_suspend; intel_dig_port->port = port; intel_dig_port->saved_port_bits = I915_READ(DDI_BUF_CTL(port)) & diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 6e0d8283daa6..182f84937345 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -13351,6 +13351,9 @@ static int intel_atomic_prepare_commit(struct drm_device *dev, } for_each_crtc_in_state(state, crtc, crtc_state, i) { + if (state->legacy_cursor_update) + continue; + ret = intel_crtc_wait_for_pending_flips(crtc); if (ret) return ret; diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index f069a82deb57..412a34c39522 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -4898,7 +4898,7 @@ void intel_dp_encoder_destroy(struct drm_encoder *encoder) kfree(intel_dig_port); } -static void intel_dp_encoder_suspend(struct intel_encoder *intel_encoder) +void intel_dp_encoder_suspend(struct intel_encoder *intel_encoder) { struct intel_dp *intel_dp = enc_to_intel_dp(&intel_encoder->base); @@ -4940,7 +4940,7 @@ static void intel_edp_panel_vdd_sanitize(struct intel_dp *intel_dp) edp_panel_vdd_schedule_off(intel_dp); } -static void intel_dp_encoder_reset(struct drm_encoder *encoder) +void intel_dp_encoder_reset(struct drm_encoder *encoder) { struct intel_dp *intel_dp; diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h index 4c027d69fac9..7d3af3a72abe 100644 --- a/drivers/gpu/drm/i915/intel_drv.h +++ b/drivers/gpu/drm/i915/intel_drv.h @@ -1238,6 +1238,8 @@ void intel_dp_set_link_params(struct intel_dp *intel_dp, void intel_dp_start_link_train(struct intel_dp *intel_dp); void intel_dp_stop_link_train(struct intel_dp *intel_dp); void intel_dp_sink_dpms(struct intel_dp *intel_dp, int mode); +void intel_dp_encoder_reset(struct drm_encoder *encoder); +void intel_dp_encoder_suspend(struct intel_encoder *intel_encoder); void intel_dp_encoder_destroy(struct drm_encoder *encoder); int intel_dp_sink_crc(struct intel_dp *intel_dp, u8 *crc); bool intel_dp_compute_config(struct intel_encoder *encoder, diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c index a0d8daed2470..1ab6f687f640 100644 --- a/drivers/gpu/drm/i915/intel_hdmi.c +++ b/drivers/gpu/drm/i915/intel_hdmi.c @@ -1415,8 +1415,16 @@ intel_hdmi_detect(struct drm_connector *connector, bool force) hdmi_to_dig_port(intel_hdmi)); } - if (!live_status) - DRM_DEBUG_KMS("Live status not up!"); + if (!live_status) { + DRM_DEBUG_KMS("HDMI live status down\n"); + /* + * Live status register is not reliable on all intel platforms. + * So consider live_status only for certain platforms, for + * others, read EDID to determine presence of sink. + */ + if (INTEL_INFO(dev_priv)->gen < 7 || IS_IVYBRIDGE(dev_priv)) + live_status = true; + } intel_hdmi_unset_edid(connector); diff --git a/drivers/gpu/drm/radeon/atombios_encoders.c b/drivers/gpu/drm/radeon/atombios_encoders.c index edd05cdb0cd8..587cae4e73c9 100644 --- a/drivers/gpu/drm/radeon/atombios_encoders.c +++ b/drivers/gpu/drm/radeon/atombios_encoders.c @@ -310,6 +310,10 @@ static bool radeon_atom_mode_fixup(struct drm_encoder *encoder, && (mode->crtc_vsync_start < (mode->crtc_vdisplay + 2))) adjusted_mode->crtc_vsync_start = adjusted_mode->crtc_vdisplay + 2; + /* vertical FP must be at least 1 */ + if (mode->crtc_vsync_start == mode->crtc_vdisplay) + adjusted_mode->crtc_vsync_start++; + /* get the native mode for scaling */ if (radeon_encoder->active_device & (ATOM_DEVICE_LCD_SUPPORT)) { radeon_panel_mode_fixup(encoder, adjusted_mode); diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c index 76c4bdf21b20..34f7a29d9366 100644 --- a/drivers/gpu/drm/radeon/evergreen.c +++ b/drivers/gpu/drm/radeon/evergreen.c @@ -2608,10 +2608,152 @@ static void evergreen_agp_enable(struct radeon_device *rdev) WREG32(VM_CONTEXT1_CNTL, 0); } +static const unsigned ni_dig_offsets[] = +{ + NI_DIG0_REGISTER_OFFSET, + NI_DIG1_REGISTER_OFFSET, + NI_DIG2_REGISTER_OFFSET, + NI_DIG3_REGISTER_OFFSET, + NI_DIG4_REGISTER_OFFSET, + NI_DIG5_REGISTER_OFFSET +}; + +static const unsigned ni_tx_offsets[] = +{ + NI_DCIO_UNIPHY0_UNIPHY_TX_CONTROL1, + NI_DCIO_UNIPHY1_UNIPHY_TX_CONTROL1, + NI_DCIO_UNIPHY2_UNIPHY_TX_CONTROL1, + NI_DCIO_UNIPHY3_UNIPHY_TX_CONTROL1, + NI_DCIO_UNIPHY4_UNIPHY_TX_CONTROL1, + NI_DCIO_UNIPHY5_UNIPHY_TX_CONTROL1 +}; + +static const unsigned evergreen_dp_offsets[] = +{ + EVERGREEN_DP0_REGISTER_OFFSET, + EVERGREEN_DP1_REGISTER_OFFSET, + EVERGREEN_DP2_REGISTER_OFFSET, + EVERGREEN_DP3_REGISTER_OFFSET, + EVERGREEN_DP4_REGISTER_OFFSET, + EVERGREEN_DP5_REGISTER_OFFSET +}; + + +/* + * Assumption is that EVERGREEN_CRTC_MASTER_EN enable for requested crtc + * We go from crtc to connector and it is not relible since it + * should be an opposite direction .If crtc is enable then + * find the dig_fe which selects this crtc and insure that it enable. + * if such dig_fe is found then find dig_be which selects found dig_be and + * insure that it enable and in DP_SST mode. + * if UNIPHY_PLL_CONTROL1.enable then we should disconnect timing + * from dp symbols clocks . + */ +static bool evergreen_is_dp_sst_stream_enabled(struct radeon_device *rdev, + unsigned crtc_id, unsigned *ret_dig_fe) +{ + unsigned i; + unsigned dig_fe; + unsigned dig_be; + unsigned dig_en_be; + unsigned uniphy_pll; + unsigned digs_fe_selected; + unsigned dig_be_mode; + unsigned dig_fe_mask; + bool is_enabled = false; + bool found_crtc = false; + + /* loop through all running dig_fe to find selected crtc */ + for (i = 0; i < ARRAY_SIZE(ni_dig_offsets); i++) { + dig_fe = RREG32(NI_DIG_FE_CNTL + ni_dig_offsets[i]); + if (dig_fe & NI_DIG_FE_CNTL_SYMCLK_FE_ON && + crtc_id == NI_DIG_FE_CNTL_SOURCE_SELECT(dig_fe)) { + /* found running pipe */ + found_crtc = true; + dig_fe_mask = 1 << i; + dig_fe = i; + break; + } + } + + if (found_crtc) { + /* loop through all running dig_be to find selected dig_fe */ + for (i = 0; i < ARRAY_SIZE(ni_dig_offsets); i++) { + dig_be = RREG32(NI_DIG_BE_CNTL + ni_dig_offsets[i]); + /* if dig_fe_selected by dig_be? */ + digs_fe_selected = NI_DIG_BE_CNTL_FE_SOURCE_SELECT(dig_be); + dig_be_mode = NI_DIG_FE_CNTL_MODE(dig_be); + if (dig_fe_mask & digs_fe_selected && + /* if dig_be in sst mode? */ + dig_be_mode == NI_DIG_BE_DPSST) { + dig_en_be = RREG32(NI_DIG_BE_EN_CNTL + + ni_dig_offsets[i]); + uniphy_pll = RREG32(NI_DCIO_UNIPHY0_PLL_CONTROL1 + + ni_tx_offsets[i]); + /* dig_be enable and tx is running */ + if (dig_en_be & NI_DIG_BE_EN_CNTL_ENABLE && + dig_en_be & NI_DIG_BE_EN_CNTL_SYMBCLK_ON && + uniphy_pll & NI_DCIO_UNIPHY0_PLL_CONTROL1_ENABLE) { + is_enabled = true; + *ret_dig_fe = dig_fe; + break; + } + } + } + } + + return is_enabled; +} + +/* + * Blank dig when in dp sst mode + * Dig ignores crtc timing + */ +static void evergreen_blank_dp_output(struct radeon_device *rdev, + unsigned dig_fe) +{ + unsigned stream_ctrl; + unsigned fifo_ctrl; + unsigned counter = 0; + + if (dig_fe >= ARRAY_SIZE(evergreen_dp_offsets)) { + DRM_ERROR("invalid dig_fe %d\n", dig_fe); + return; + } + + stream_ctrl = RREG32(EVERGREEN_DP_VID_STREAM_CNTL + + evergreen_dp_offsets[dig_fe]); + if (!(stream_ctrl & EVERGREEN_DP_VID_STREAM_CNTL_ENABLE)) { + DRM_ERROR("dig %d , should be enable\n", dig_fe); + return; + } + + stream_ctrl &=~EVERGREEN_DP_VID_STREAM_CNTL_ENABLE; + WREG32(EVERGREEN_DP_VID_STREAM_CNTL + + evergreen_dp_offsets[dig_fe], stream_ctrl); + + stream_ctrl = RREG32(EVERGREEN_DP_VID_STREAM_CNTL + + evergreen_dp_offsets[dig_fe]); + while (counter < 32 && stream_ctrl & EVERGREEN_DP_VID_STREAM_STATUS) { + msleep(1); + counter++; + stream_ctrl = RREG32(EVERGREEN_DP_VID_STREAM_CNTL + + evergreen_dp_offsets[dig_fe]); + } + if (counter >= 32 ) + DRM_ERROR("counter exceeds %d\n", counter); + + fifo_ctrl = RREG32(EVERGREEN_DP_STEER_FIFO + evergreen_dp_offsets[dig_fe]); + fifo_ctrl |= EVERGREEN_DP_STEER_FIFO_RESET; + WREG32(EVERGREEN_DP_STEER_FIFO + evergreen_dp_offsets[dig_fe], fifo_ctrl); + +} + void evergreen_mc_stop(struct radeon_device *rdev, struct evergreen_mc_save *save) { u32 crtc_enabled, tmp, frame_count, blackout; int i, j; + unsigned dig_fe; if (!ASIC_IS_NODCE(rdev)) { save->vga_render_control = RREG32(VGA_RENDER_CONTROL); @@ -2651,7 +2793,17 @@ void evergreen_mc_stop(struct radeon_device *rdev, struct evergreen_mc_save *sav break; udelay(1); } - + /*we should disable dig if it drives dp sst*/ + /*but we are in radeon_device_init and the topology is unknown*/ + /*and it is available after radeon_modeset_init*/ + /*the following method radeon_atom_encoder_dpms_dig*/ + /*does the job if we initialize it properly*/ + /*for now we do it this manually*/ + /**/ + if (ASIC_IS_DCE5(rdev) && + evergreen_is_dp_sst_stream_enabled(rdev, i ,&dig_fe)) + evergreen_blank_dp_output(rdev, dig_fe); + /*we could remove 6 lines below*/ /* XXX this is a hack to avoid strange behavior with EFI on certain systems */ WREG32(EVERGREEN_CRTC_UPDATE_LOCK + crtc_offsets[i], 1); tmp = RREG32(EVERGREEN_CRTC_CONTROL + crtc_offsets[i]); diff --git a/drivers/gpu/drm/radeon/evergreen_reg.h b/drivers/gpu/drm/radeon/evergreen_reg.h index aa939dfed3a3..b436badf9efa 100644 --- a/drivers/gpu/drm/radeon/evergreen_reg.h +++ b/drivers/gpu/drm/radeon/evergreen_reg.h @@ -250,8 +250,43 @@ /* HDMI blocks at 0x7030, 0x7c30, 0x10830, 0x11430, 0x12030, 0x12c30 */ #define EVERGREEN_HDMI_BASE 0x7030 +/*DIG block*/ +#define NI_DIG0_REGISTER_OFFSET (0x7000 - 0x7000) +#define NI_DIG1_REGISTER_OFFSET (0x7C00 - 0x7000) +#define NI_DIG2_REGISTER_OFFSET (0x10800 - 0x7000) +#define NI_DIG3_REGISTER_OFFSET (0x11400 - 0x7000) +#define NI_DIG4_REGISTER_OFFSET (0x12000 - 0x7000) +#define NI_DIG5_REGISTER_OFFSET (0x12C00 - 0x7000) + + +#define NI_DIG_FE_CNTL 0x7000 +# define NI_DIG_FE_CNTL_SOURCE_SELECT(x) ((x) & 0x3) +# define NI_DIG_FE_CNTL_SYMCLK_FE_ON (1<<24) + + +#define NI_DIG_BE_CNTL 0x7140 +# define NI_DIG_BE_CNTL_FE_SOURCE_SELECT(x) (((x) >> 8 ) & 0x3F) +# define NI_DIG_FE_CNTL_MODE(x) (((x) >> 16) & 0x7 ) + +#define NI_DIG_BE_EN_CNTL 0x7144 +# define NI_DIG_BE_EN_CNTL_ENABLE (1 << 0) +# define NI_DIG_BE_EN_CNTL_SYMBCLK_ON (1 << 8) +# define NI_DIG_BE_DPSST 0 /* Display Port block */ +#define EVERGREEN_DP0_REGISTER_OFFSET (0x730C - 0x730C) +#define EVERGREEN_DP1_REGISTER_OFFSET (0x7F0C - 0x730C) +#define EVERGREEN_DP2_REGISTER_OFFSET (0x10B0C - 0x730C) +#define EVERGREEN_DP3_REGISTER_OFFSET (0x1170C - 0x730C) +#define EVERGREEN_DP4_REGISTER_OFFSET (0x1230C - 0x730C) +#define EVERGREEN_DP5_REGISTER_OFFSET (0x12F0C - 0x730C) + + +#define EVERGREEN_DP_VID_STREAM_CNTL 0x730C +# define EVERGREEN_DP_VID_STREAM_CNTL_ENABLE (1 << 0) +# define EVERGREEN_DP_VID_STREAM_STATUS (1 <<16) +#define EVERGREEN_DP_STEER_FIFO 0x7310 +# define EVERGREEN_DP_STEER_FIFO_RESET (1 << 0) #define EVERGREEN_DP_SEC_CNTL 0x7280 # define EVERGREEN_DP_SEC_STREAM_ENABLE (1 << 0) # define EVERGREEN_DP_SEC_ASP_ENABLE (1 << 4) @@ -266,4 +301,15 @@ # define EVERGREEN_DP_SEC_N_BASE_MULTIPLE(x) (((x) & 0xf) << 24) # define EVERGREEN_DP_SEC_SS_EN (1 << 28) +/*DCIO_UNIPHY block*/ +#define NI_DCIO_UNIPHY0_UNIPHY_TX_CONTROL1 (0x6600 -0x6600) +#define NI_DCIO_UNIPHY1_UNIPHY_TX_CONTROL1 (0x6640 -0x6600) +#define NI_DCIO_UNIPHY2_UNIPHY_TX_CONTROL1 (0x6680 - 0x6600) +#define NI_DCIO_UNIPHY3_UNIPHY_TX_CONTROL1 (0x66C0 - 0x6600) +#define NI_DCIO_UNIPHY4_UNIPHY_TX_CONTROL1 (0x6700 - 0x6600) +#define NI_DCIO_UNIPHY5_UNIPHY_TX_CONTROL1 (0x6740 - 0x6600) + +#define NI_DCIO_UNIPHY0_PLL_CONTROL1 0x6618 +# define NI_DCIO_UNIPHY0_PLL_CONTROL1_ENABLE (1 << 0) + #endif diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index 4cbf26555093..e3daafa1be13 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -230,22 +230,13 @@ EXPORT_SYMBOL(ttm_bo_del_sub_from_lru); void ttm_bo_move_to_lru_tail(struct ttm_buffer_object *bo) { - struct ttm_bo_device *bdev = bo->bdev; - struct ttm_mem_type_manager *man; + int put_count = 0; lockdep_assert_held(&bo->resv->lock.base); - if (bo->mem.placement & TTM_PL_FLAG_NO_EVICT) { - list_del_init(&bo->swap); - list_del_init(&bo->lru); - - } else { - if (bo->ttm && !(bo->ttm->page_flags & TTM_PAGE_FLAG_SG)) - list_move_tail(&bo->swap, &bo->glob->swap_lru); - - man = &bdev->man[bo->mem.mem_type]; - list_move_tail(&bo->lru, &man->lru); - } + put_count = ttm_bo_del_from_lru(bo); + ttm_bo_list_ref_sub(bo, put_count, true); + ttm_bo_add_to_lru(bo); } EXPORT_SYMBOL(ttm_bo_move_to_lru_tail); diff --git a/drivers/gpu/drm/virtio/virtgpu_display.c b/drivers/gpu/drm/virtio/virtgpu_display.c index 4854dac87e24..5fd1fd06effc 100644 --- a/drivers/gpu/drm/virtio/virtgpu_display.c +++ b/drivers/gpu/drm/virtio/virtgpu_display.c @@ -267,11 +267,23 @@ static int virtio_gpu_crtc_atomic_check(struct drm_crtc *crtc, return 0; } +static void virtio_gpu_crtc_atomic_flush(struct drm_crtc *crtc, + struct drm_crtc_state *old_state) +{ + unsigned long flags; + + spin_lock_irqsave(&crtc->dev->event_lock, flags); + if (crtc->state->event) + drm_crtc_send_vblank_event(crtc, crtc->state->event); + spin_unlock_irqrestore(&crtc->dev->event_lock, flags); +} + static const struct drm_crtc_helper_funcs virtio_gpu_crtc_helper_funcs = { .enable = virtio_gpu_crtc_enable, .disable = virtio_gpu_crtc_disable, .mode_set_nofb = virtio_gpu_crtc_mode_set_nofb, .atomic_check = virtio_gpu_crtc_atomic_check, + .atomic_flush = virtio_gpu_crtc_atomic_flush, }; static void virtio_gpu_enc_mode_set(struct drm_encoder *encoder, diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c index 723ba16c6084..1a1a87cbf109 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c @@ -3293,19 +3293,19 @@ static const struct vmw_cmd_entry vmw_cmd_entries[SVGA_3D_CMD_MAX] = { &vmw_cmd_dx_cid_check, true, false, true), VMW_CMD_DEF(SVGA_3D_CMD_DX_DEFINE_QUERY, &vmw_cmd_dx_define_query, true, false, true), - VMW_CMD_DEF(SVGA_3D_CMD_DX_DESTROY_QUERY, &vmw_cmd_ok, + VMW_CMD_DEF(SVGA_3D_CMD_DX_DESTROY_QUERY, &vmw_cmd_dx_cid_check, true, false, true), VMW_CMD_DEF(SVGA_3D_CMD_DX_BIND_QUERY, &vmw_cmd_dx_bind_query, true, false, true), VMW_CMD_DEF(SVGA_3D_CMD_DX_SET_QUERY_OFFSET, - &vmw_cmd_ok, true, false, true), - VMW_CMD_DEF(SVGA_3D_CMD_DX_BEGIN_QUERY, &vmw_cmd_ok, + &vmw_cmd_dx_cid_check, true, false, true), + VMW_CMD_DEF(SVGA_3D_CMD_DX_BEGIN_QUERY, &vmw_cmd_dx_cid_check, true, false, true), - VMW_CMD_DEF(SVGA_3D_CMD_DX_END_QUERY, &vmw_cmd_ok, + VMW_CMD_DEF(SVGA_3D_CMD_DX_END_QUERY, &vmw_cmd_dx_cid_check, true, false, true), VMW_CMD_DEF(SVGA_3D_CMD_DX_READBACK_QUERY, &vmw_cmd_invalid, true, false, true), - VMW_CMD_DEF(SVGA_3D_CMD_DX_SET_PREDICATION, &vmw_cmd_invalid, + VMW_CMD_DEF(SVGA_3D_CMD_DX_SET_PREDICATION, &vmw_cmd_dx_cid_check, true, false, true), VMW_CMD_DEF(SVGA_3D_CMD_DX_SET_VIEWPORTS, &vmw_cmd_dx_cid_check, true, false, true), diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c index 3b1faf7862a5..679a4cb98ee3 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c @@ -573,9 +573,9 @@ static int vmw_fb_set_par(struct fb_info *info) mode = old_mode; old_mode = NULL; } else if (!vmw_kms_validate_mode_vram(vmw_priv, - mode->hdisplay * - (var->bits_per_pixel + 7) / 8, - mode->vdisplay)) { + mode->hdisplay * + DIV_ROUND_UP(var->bits_per_pixel, 8), + mode->vdisplay)) { drm_mode_destroy(vmw_priv->dev, mode); return -EINVAL; } diff --git a/drivers/gpu/ipu-v3/ipu-common.c b/drivers/gpu/ipu-v3/ipu-common.c index e00db3f510dd..abb98c77bad2 100644 --- a/drivers/gpu/ipu-v3/ipu-common.c +++ b/drivers/gpu/ipu-v3/ipu-common.c @@ -1068,7 +1068,6 @@ static int ipu_add_client_devices(struct ipu_soc *ipu, unsigned long ipu_base) goto err_register; } - pdev->dev.of_node = of_node; pdev->dev.parent = dev; ret = platform_device_add_data(pdev, ®->pdata, @@ -1079,6 +1078,12 @@ static int ipu_add_client_devices(struct ipu_soc *ipu, unsigned long ipu_base) platform_device_put(pdev); goto err_register; } + + /* + * Set of_node only after calling platform_device_add. Otherwise + * the platform:imx-ipuv3-crtc modalias won't be used. + */ + pdev->dev.of_node = of_node; } return 0; diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index c6eaff5f8845..0238f0169e48 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -259,6 +259,7 @@ #define USB_DEVICE_ID_CORSAIR_K90 0x1b02 #define USB_VENDOR_ID_CREATIVELABS 0x041e +#define USB_DEVICE_ID_CREATIVE_SB_OMNI_SURROUND_51 0x322c #define USB_DEVICE_ID_PRODIKEYS_PCMIDI 0x2801 #define USB_VENDOR_ID_CVTOUCH 0x1ff7 diff --git a/drivers/hid/usbhid/hid-quirks.c b/drivers/hid/usbhid/hid-quirks.c index ed2f68edc8f1..53fc856d6867 100644 --- a/drivers/hid/usbhid/hid-quirks.c +++ b/drivers/hid/usbhid/hid-quirks.c @@ -71,6 +71,7 @@ static const struct hid_blacklist { { USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_3AXIS_5BUTTON_STICK, HID_QUIRK_NOGET }, { USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_AXIS_295, HID_QUIRK_NOGET }, { USB_VENDOR_ID_CHICONY, USB_DEVICE_ID_CHICONY_PIXART_USB_OPTICAL_MOUSE, HID_QUIRK_ALWAYS_POLL }, + { USB_VENDOR_ID_CREATIVELABS, USB_DEVICE_ID_CREATIVE_SB_OMNI_SURROUND_51, HID_QUIRK_NOGET }, { USB_VENDOR_ID_DMI, USB_DEVICE_ID_DMI_ENC, HID_QUIRK_NOGET }, { USB_VENDOR_ID_DRAGONRISE, USB_DEVICE_ID_DRAGONRISE_WIIU, HID_QUIRK_MULTI_INPUT }, { USB_VENDOR_ID_ELAN, HID_ANY_ID, HID_QUIRK_ALWAYS_POLL }, diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index 02c4efea241c..cf2ba43453fd 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -684,6 +684,7 @@ static int wacom_intuos_inout(struct wacom_wac *wacom) wacom->tool[idx] = wacom_intuos_get_tool_type(wacom->id[idx]); + wacom->shared->stylus_in_proximity = true; return 1; } @@ -3395,6 +3396,10 @@ static const struct wacom_features wacom_features_0x33E = { "Wacom Intuos PT M 2", 21600, 13500, 2047, 63, INTUOSHT2, WACOM_INTUOS_RES, WACOM_INTUOS_RES, .touch_max = 16, .check_for_hid_type = true, .hid_type = HID_TYPE_USBNONE }; +static const struct wacom_features wacom_features_0x343 = + { "Wacom DTK1651", 34616, 19559, 1023, 0, + DTUS, WACOM_INTUOS_RES, WACOM_INTUOS_RES, 4, + WACOM_DTU_OFFSET, WACOM_DTU_OFFSET }; static const struct wacom_features wacom_features_HID_ANY_ID = { "Wacom HID", .type = HID_GENERIC }; @@ -3560,6 +3565,7 @@ const struct hid_device_id wacom_ids[] = { { USB_DEVICE_WACOM(0x33C) }, { USB_DEVICE_WACOM(0x33D) }, { USB_DEVICE_WACOM(0x33E) }, + { USB_DEVICE_WACOM(0x343) }, { USB_DEVICE_WACOM(0x4001) }, { USB_DEVICE_WACOM(0x4004) }, { USB_DEVICE_WACOM(0x5000) }, diff --git a/drivers/hv/ring_buffer.c b/drivers/hv/ring_buffer.c index 5613e2b5cff7..a40a73a7b71d 100644 --- a/drivers/hv/ring_buffer.c +++ b/drivers/hv/ring_buffer.c @@ -103,15 +103,29 @@ static bool hv_need_to_signal(u32 old_write, struct hv_ring_buffer_info *rbi) * there is room for the producer to send the pending packet. */ -static bool hv_need_to_signal_on_read(u32 prev_write_sz, - struct hv_ring_buffer_info *rbi) +static bool hv_need_to_signal_on_read(struct hv_ring_buffer_info *rbi) { u32 cur_write_sz; u32 r_size; - u32 write_loc = rbi->ring_buffer->write_index; + u32 write_loc; u32 read_loc = rbi->ring_buffer->read_index; - u32 pending_sz = rbi->ring_buffer->pending_send_sz; + u32 pending_sz; + /* + * Issue a full memory barrier before making the signaling decision. + * Here is the reason for having this barrier: + * If the reading of the pend_sz (in this function) + * were to be reordered and read before we commit the new read + * index (in the calling function) we could + * have a problem. If the host were to set the pending_sz after we + * have sampled pending_sz and go to sleep before we commit the + * read index, we could miss sending the interrupt. Issue a full + * memory barrier to address this. + */ + mb(); + + pending_sz = rbi->ring_buffer->pending_send_sz; + write_loc = rbi->ring_buffer->write_index; /* If the other end is not blocked on write don't bother. */ if (pending_sz == 0) return false; @@ -120,7 +134,7 @@ static bool hv_need_to_signal_on_read(u32 prev_write_sz, cur_write_sz = write_loc >= read_loc ? r_size - (write_loc - read_loc) : read_loc - write_loc; - if ((prev_write_sz < pending_sz) && (cur_write_sz >= pending_sz)) + if (cur_write_sz >= pending_sz) return true; return false; @@ -455,7 +469,7 @@ int hv_ringbuffer_read(struct hv_ring_buffer_info *inring_info, /* Update the read index */ hv_set_next_read_location(inring_info, next_read_location); - *signal = hv_need_to_signal_on_read(bytes_avail_towrite, inring_info); + *signal = hv_need_to_signal_on_read(inring_info); return ret; } diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig index faa8e6821fea..0967e1a5b3a2 100644 --- a/drivers/i2c/busses/Kconfig +++ b/drivers/i2c/busses/Kconfig @@ -975,10 +975,10 @@ config I2C_XLR config I2C_XLP9XX tristate "XLP9XX I2C support" - depends on CPU_XLP || COMPILE_TEST + depends on CPU_XLP || ARCH_VULCAN || COMPILE_TEST help This driver enables support for the on-chip I2C interface of - the Broadcom XLP9xx/XLP5xx MIPS processors. + the Broadcom XLP9xx/XLP5xx MIPS and Vulcan ARM64 processors. This driver can also be built as a module. If so, the module will be called i2c-xlp9xx. diff --git a/drivers/i2c/busses/i2c-cpm.c b/drivers/i2c/busses/i2c-cpm.c index 714bdc837769..b167ab25310a 100644 --- a/drivers/i2c/busses/i2c-cpm.c +++ b/drivers/i2c/busses/i2c-cpm.c @@ -116,8 +116,8 @@ struct cpm_i2c { cbd_t __iomem *rbase; u_char *txbuf[CPM_MAXBD]; u_char *rxbuf[CPM_MAXBD]; - u32 txdma[CPM_MAXBD]; - u32 rxdma[CPM_MAXBD]; + dma_addr_t txdma[CPM_MAXBD]; + dma_addr_t rxdma[CPM_MAXBD]; }; static irqreturn_t cpm_i2c_interrupt(int irq, void *dev_id) diff --git a/drivers/i2c/busses/i2c-exynos5.c b/drivers/i2c/busses/i2c-exynos5.c index b29c7500461a..f54ece8fce78 100644 --- a/drivers/i2c/busses/i2c-exynos5.c +++ b/drivers/i2c/busses/i2c-exynos5.c @@ -671,7 +671,9 @@ static int exynos5_i2c_xfer(struct i2c_adapter *adap, return -EIO; } - clk_prepare_enable(i2c->clk); + ret = clk_enable(i2c->clk); + if (ret) + return ret; for (i = 0; i < num; i++, msgs++) { stop = (i == num - 1); @@ -695,7 +697,7 @@ static int exynos5_i2c_xfer(struct i2c_adapter *adap, } out: - clk_disable_unprepare(i2c->clk); + clk_disable(i2c->clk); return ret; } @@ -747,7 +749,9 @@ static int exynos5_i2c_probe(struct platform_device *pdev) return -ENOENT; } - clk_prepare_enable(i2c->clk); + ret = clk_prepare_enable(i2c->clk); + if (ret) + return ret; mem = platform_get_resource(pdev, IORESOURCE_MEM, 0); i2c->regs = devm_ioremap_resource(&pdev->dev, mem); @@ -799,6 +803,10 @@ static int exynos5_i2c_probe(struct platform_device *pdev) platform_set_drvdata(pdev, i2c); + clk_disable(i2c->clk); + + return 0; + err_clk: clk_disable_unprepare(i2c->clk); return ret; @@ -810,6 +818,8 @@ static int exynos5_i2c_remove(struct platform_device *pdev) i2c_del_adapter(&i2c->adap); + clk_unprepare(i2c->clk); + return 0; } @@ -821,6 +831,8 @@ static int exynos5_i2c_suspend_noirq(struct device *dev) i2c->suspended = 1; + clk_unprepare(i2c->clk); + return 0; } @@ -830,7 +842,9 @@ static int exynos5_i2c_resume_noirq(struct device *dev) struct exynos5_i2c *i2c = platform_get_drvdata(pdev); int ret = 0; - clk_prepare_enable(i2c->clk); + ret = clk_prepare_enable(i2c->clk); + if (ret) + return ret; ret = exynos5_hsi2c_clock_setup(i2c); if (ret) { @@ -839,7 +853,7 @@ static int exynos5_i2c_resume_noirq(struct device *dev) } exynos5_i2c_init(i2c); - clk_disable_unprepare(i2c->clk); + clk_disable(i2c->clk); i2c->suspended = 0; return 0; diff --git a/drivers/i2c/busses/i2c-ismt.c b/drivers/i2c/busses/i2c-ismt.c index 7ba795b24e75..1c8707710098 100644 --- a/drivers/i2c/busses/i2c-ismt.c +++ b/drivers/i2c/busses/i2c-ismt.c @@ -75,6 +75,7 @@ /* PCI DIDs for the Intel SMBus Message Transport (SMT) Devices */ #define PCI_DEVICE_ID_INTEL_S1200_SMT0 0x0c59 #define PCI_DEVICE_ID_INTEL_S1200_SMT1 0x0c5a +#define PCI_DEVICE_ID_INTEL_DNV_SMT 0x19ac #define PCI_DEVICE_ID_INTEL_AVOTON_SMT 0x1f15 #define ISMT_DESC_ENTRIES 2 /* number of descriptor entries */ @@ -180,6 +181,7 @@ struct ismt_priv { static const struct pci_device_id ismt_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_S1200_SMT0) }, { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_S1200_SMT1) }, + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_DNV_SMT) }, { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_AVOTON_SMT) }, { 0, } }; diff --git a/drivers/i2c/busses/i2c-rk3x.c b/drivers/i2c/busses/i2c-rk3x.c index 9096d17beb5b..3dcc5f3f26cb 100644 --- a/drivers/i2c/busses/i2c-rk3x.c +++ b/drivers/i2c/busses/i2c-rk3x.c @@ -855,6 +855,7 @@ static struct rk3x_i2c_soc_data soc_data[3] = { static const struct of_device_id rk3x_i2c_match[] = { { .compatible = "rockchip,rk3066-i2c", .data = (void *)&soc_data[0] }, { .compatible = "rockchip,rk3188-i2c", .data = (void *)&soc_data[1] }, + { .compatible = "rockchip,rk3228-i2c", .data = (void *)&soc_data[2] }, { .compatible = "rockchip,rk3288-i2c", .data = (void *)&soc_data[2] }, {}, }; diff --git a/drivers/iio/adc/at91-sama5d2_adc.c b/drivers/iio/adc/at91-sama5d2_adc.c index dbee13ad33a3..2e154cb51685 100644 --- a/drivers/iio/adc/at91-sama5d2_adc.c +++ b/drivers/iio/adc/at91-sama5d2_adc.c @@ -451,6 +451,8 @@ static int at91_adc_probe(struct platform_device *pdev) if (ret) goto vref_disable; + platform_set_drvdata(pdev, indio_dev); + ret = iio_device_register(indio_dev); if (ret < 0) goto per_clk_disable_unprepare; diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_i2c.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_i2c.c index f581256d9d4c..5ee4e0dc093e 100644 --- a/drivers/iio/imu/inv_mpu6050/inv_mpu_i2c.c +++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_i2c.c @@ -104,6 +104,19 @@ static int inv_mpu6050_deselect_bypass(struct i2c_adapter *adap, return 0; } +static const char *inv_mpu_match_acpi_device(struct device *dev, int *chip_id) +{ + const struct acpi_device_id *id; + + id = acpi_match_device(dev->driver->acpi_match_table, dev); + if (!id) + return NULL; + + *chip_id = (int)id->driver_data; + + return dev_name(dev); +} + /** * inv_mpu_probe() - probe function. * @client: i2c client. @@ -115,14 +128,25 @@ static int inv_mpu_probe(struct i2c_client *client, const struct i2c_device_id *id) { struct inv_mpu6050_state *st; - int result; - const char *name = id ? id->name : NULL; + int result, chip_type; struct regmap *regmap; + const char *name; if (!i2c_check_functionality(client->adapter, I2C_FUNC_SMBUS_I2C_BLOCK)) return -EOPNOTSUPP; + if (id) { + chip_type = (int)id->driver_data; + name = id->name; + } else if (ACPI_HANDLE(&client->dev)) { + name = inv_mpu_match_acpi_device(&client->dev, &chip_type); + if (!name) + return -ENODEV; + } else { + return -ENOSYS; + } + regmap = devm_regmap_init_i2c(client, &inv_mpu_regmap_config); if (IS_ERR(regmap)) { dev_err(&client->dev, "Failed to register i2c regmap %d\n", @@ -131,7 +155,7 @@ static int inv_mpu_probe(struct i2c_client *client, } result = inv_mpu_core_probe(regmap, client->irq, name, - NULL, id->driver_data); + NULL, chip_type); if (result < 0) return result; diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_spi.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_spi.c index dea6c4361de0..7bcb8d839f05 100644 --- a/drivers/iio/imu/inv_mpu6050/inv_mpu_spi.c +++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_spi.c @@ -46,6 +46,7 @@ static int inv_mpu_probe(struct spi_device *spi) struct regmap *regmap; const struct spi_device_id *id = spi_get_device_id(spi); const char *name = id ? id->name : NULL; + const int chip_type = id ? id->driver_data : 0; regmap = devm_regmap_init_spi(spi, &inv_mpu_regmap_config); if (IS_ERR(regmap)) { @@ -55,7 +56,7 @@ static int inv_mpu_probe(struct spi_device *spi) } return inv_mpu_core_probe(regmap, spi->irq, name, - inv_mpu_i2c_disable, id->driver_data); + inv_mpu_i2c_disable, chip_type); } static int inv_mpu_remove(struct spi_device *spi) diff --git a/drivers/iio/magnetometer/ak8975.c b/drivers/iio/magnetometer/ak8975.c index 9c5c9ef3f1da..0e931a9a1669 100644 --- a/drivers/iio/magnetometer/ak8975.c +++ b/drivers/iio/magnetometer/ak8975.c @@ -462,6 +462,8 @@ static int ak8975_setup_irq(struct ak8975_data *data) int rc; int irq; + init_waitqueue_head(&data->data_ready_queue); + clear_bit(0, &data->flags); if (client->irq) irq = client->irq; else @@ -477,8 +479,6 @@ static int ak8975_setup_irq(struct ak8975_data *data) return rc; } - init_waitqueue_head(&data->data_ready_queue); - clear_bit(0, &data->flags); data->eoc_irq = irq; return rc; @@ -732,7 +732,7 @@ static int ak8975_probe(struct i2c_client *client, int eoc_gpio; int err; const char *name = NULL; - enum asahi_compass_chipset chipset; + enum asahi_compass_chipset chipset = AK_MAX_TYPE; /* Grab and set up the supplied GPIO. */ if (client->dev.platform_data) diff --git a/drivers/infiniband/core/cache.c b/drivers/infiniband/core/cache.c index cb00d59da456..c2e257d97eff 100644 --- a/drivers/infiniband/core/cache.c +++ b/drivers/infiniband/core/cache.c @@ -691,7 +691,8 @@ void ib_cache_gid_set_default_gid(struct ib_device *ib_dev, u8 port, NULL); /* Coudn't find default GID location */ - WARN_ON(ix < 0); + if (WARN_ON(ix < 0)) + goto release; zattr_type.gid_type = gid_type; diff --git a/drivers/infiniband/core/ucm.c b/drivers/infiniband/core/ucm.c index 4a9aa0433b07..7713ef089c3c 100644 --- a/drivers/infiniband/core/ucm.c +++ b/drivers/infiniband/core/ucm.c @@ -48,6 +48,7 @@ #include <asm/uaccess.h> +#include <rdma/ib.h> #include <rdma/ib_cm.h> #include <rdma/ib_user_cm.h> #include <rdma/ib_marshall.h> @@ -1103,6 +1104,9 @@ static ssize_t ib_ucm_write(struct file *filp, const char __user *buf, struct ib_ucm_cmd_hdr hdr; ssize_t result; + if (WARN_ON_ONCE(!ib_safe_file_access(filp))) + return -EACCES; + if (len < sizeof(hdr)) return -EINVAL; diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c index dd3bcceadfde..c0f3826abb30 100644 --- a/drivers/infiniband/core/ucma.c +++ b/drivers/infiniband/core/ucma.c @@ -1574,6 +1574,9 @@ static ssize_t ucma_write(struct file *filp, const char __user *buf, struct rdma_ucm_cmd_hdr hdr; ssize_t ret; + if (WARN_ON_ONCE(!ib_safe_file_access(filp))) + return -EACCES; + if (len < sizeof(hdr)) return -EINVAL; diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c index 28ba2cc81535..31f422a70623 100644 --- a/drivers/infiniband/core/uverbs_main.c +++ b/drivers/infiniband/core/uverbs_main.c @@ -48,6 +48,8 @@ #include <asm/uaccess.h> +#include <rdma/ib.h> + #include "uverbs.h" MODULE_AUTHOR("Roland Dreier"); @@ -709,6 +711,9 @@ static ssize_t ib_uverbs_write(struct file *filp, const char __user *buf, int srcu_key; ssize_t ret; + if (WARN_ON_ONCE(!ib_safe_file_access(filp))) + return -EACCES; + if (count < sizeof hdr) return -EINVAL; diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c index 15b8adbf39c0..b65b3541e732 100644 --- a/drivers/infiniband/core/verbs.c +++ b/drivers/infiniband/core/verbs.c @@ -1860,6 +1860,7 @@ EXPORT_SYMBOL(ib_drain_rq); void ib_drain_qp(struct ib_qp *qp) { ib_drain_sq(qp); - ib_drain_rq(qp); + if (!qp->srq) + ib_drain_rq(qp); } EXPORT_SYMBOL(ib_drain_qp); diff --git a/drivers/infiniband/hw/cxgb3/iwch_provider.c b/drivers/infiniband/hw/cxgb3/iwch_provider.c index 42a7b8952d13..3234a8be16f6 100644 --- a/drivers/infiniband/hw/cxgb3/iwch_provider.c +++ b/drivers/infiniband/hw/cxgb3/iwch_provider.c @@ -1390,6 +1390,8 @@ int iwch_register_device(struct iwch_dev *dev) dev->ibdev.iwcm->add_ref = iwch_qp_add_ref; dev->ibdev.iwcm->rem_ref = iwch_qp_rem_ref; dev->ibdev.iwcm->get_qp = iwch_get_qp; + memcpy(dev->ibdev.iwcm->ifname, dev->rdev.t3cdev_p->lldev->name, + sizeof(dev->ibdev.iwcm->ifname)); ret = ib_register_device(&dev->ibdev, NULL); if (ret) diff --git a/drivers/infiniband/hw/cxgb4/cq.c b/drivers/infiniband/hw/cxgb4/cq.c index b4eeb783573c..b0b955724458 100644 --- a/drivers/infiniband/hw/cxgb4/cq.c +++ b/drivers/infiniband/hw/cxgb4/cq.c @@ -162,7 +162,7 @@ static int create_cq(struct c4iw_rdev *rdev, struct t4_cq *cq, cq->bar2_va = c4iw_bar2_addrs(rdev, cq->cqid, T4_BAR2_QTYPE_INGRESS, &cq->bar2_qid, user ? &cq->bar2_pa : NULL); - if (user && !cq->bar2_va) { + if (user && !cq->bar2_pa) { pr_warn(MOD "%s: cqid %u not in BAR2 range.\n", pci_name(rdev->lldi.pdev), cq->cqid); ret = -EINVAL; diff --git a/drivers/infiniband/hw/cxgb4/provider.c b/drivers/infiniband/hw/cxgb4/provider.c index 124682dc5709..7574f394fdac 100644 --- a/drivers/infiniband/hw/cxgb4/provider.c +++ b/drivers/infiniband/hw/cxgb4/provider.c @@ -580,6 +580,8 @@ int c4iw_register_device(struct c4iw_dev *dev) dev->ibdev.iwcm->add_ref = c4iw_qp_add_ref; dev->ibdev.iwcm->rem_ref = c4iw_qp_rem_ref; dev->ibdev.iwcm->get_qp = c4iw_get_qp; + memcpy(dev->ibdev.iwcm->ifname, dev->rdev.lldi.ports[0]->name, + sizeof(dev->ibdev.iwcm->ifname)); ret = ib_register_device(&dev->ibdev, NULL); if (ret) diff --git a/drivers/infiniband/hw/cxgb4/qp.c b/drivers/infiniband/hw/cxgb4/qp.c index e17fb5d5e033..e8993e49b8b3 100644 --- a/drivers/infiniband/hw/cxgb4/qp.c +++ b/drivers/infiniband/hw/cxgb4/qp.c @@ -185,6 +185,10 @@ void __iomem *c4iw_bar2_addrs(struct c4iw_rdev *rdev, unsigned int qid, if (pbar2_pa) *pbar2_pa = (rdev->bar2_pa + bar2_qoffset) & PAGE_MASK; + + if (is_t4(rdev->lldi.adapter_type)) + return NULL; + return rdev->bar2_kva + bar2_qoffset; } @@ -270,7 +274,7 @@ static int create_qp(struct c4iw_rdev *rdev, struct t4_wq *wq, /* * User mode must have bar2 access. */ - if (user && (!wq->sq.bar2_va || !wq->rq.bar2_va)) { + if (user && (!wq->sq.bar2_pa || !wq->rq.bar2_pa)) { pr_warn(MOD "%s: sqid %u or rqid %u not in BAR2 range.\n", pci_name(rdev->lldi.pdev), wq->sq.qid, wq->rq.qid); goto free_dma; @@ -1895,13 +1899,27 @@ int c4iw_ib_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, void c4iw_drain_sq(struct ib_qp *ibqp) { struct c4iw_qp *qp = to_c4iw_qp(ibqp); + unsigned long flag; + bool need_to_wait; - wait_for_completion(&qp->sq_drained); + spin_lock_irqsave(&qp->lock, flag); + need_to_wait = !t4_sq_empty(&qp->wq); + spin_unlock_irqrestore(&qp->lock, flag); + + if (need_to_wait) + wait_for_completion(&qp->sq_drained); } void c4iw_drain_rq(struct ib_qp *ibqp) { struct c4iw_qp *qp = to_c4iw_qp(ibqp); + unsigned long flag; + bool need_to_wait; + + spin_lock_irqsave(&qp->lock, flag); + need_to_wait = !t4_rq_empty(&qp->wq); + spin_unlock_irqrestore(&qp->lock, flag); - wait_for_completion(&qp->rq_drained); + if (need_to_wait) + wait_for_completion(&qp->rq_drained); } diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 5acf346e048e..6ad0489cb3c5 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -530,7 +530,7 @@ static int mlx5_ib_query_device(struct ib_device *ibdev, sizeof(struct mlx5_wqe_ctrl_seg)) / sizeof(struct mlx5_wqe_data_seg); props->max_sge = min(max_rq_sg, max_sq_sg); - props->max_sge_rd = props->max_sge; + props->max_sge_rd = MLX5_MAX_SGE_RD; props->max_cq = 1 << MLX5_CAP_GEN(mdev, log_max_cq); props->max_cqe = (1 << MLX5_CAP_GEN(mdev, log_max_cq_sz)) - 1; props->max_mr = 1 << MLX5_CAP_GEN(mdev, log_max_mkey); @@ -671,8 +671,8 @@ static int mlx5_query_hca_port(struct ib_device *ibdev, u8 port, struct mlx5_ib_dev *dev = to_mdev(ibdev); struct mlx5_core_dev *mdev = dev->mdev; struct mlx5_hca_vport_context *rep; - int max_mtu; - int oper_mtu; + u16 max_mtu; + u16 oper_mtu; int err; u8 ib_link_width_oper; u8 vl_hw_cap; diff --git a/drivers/infiniband/hw/nes/nes_nic.c b/drivers/infiniband/hw/nes/nes_nic.c index 3ea9e055fdd3..92914539edc7 100644 --- a/drivers/infiniband/hw/nes/nes_nic.c +++ b/drivers/infiniband/hw/nes/nes_nic.c @@ -500,9 +500,6 @@ static int nes_netdev_start_xmit(struct sk_buff *skb, struct net_device *netdev) * skb_shinfo(skb)->nr_frags, skb_is_gso(skb)); */ - if (!netif_carrier_ok(netdev)) - return NETDEV_TX_OK; - if (netif_queue_stopped(netdev)) return NETDEV_TX_BUSY; diff --git a/drivers/infiniband/hw/qib/qib_file_ops.c b/drivers/infiniband/hw/qib/qib_file_ops.c index e449e394963f..24f4a782e0f4 100644 --- a/drivers/infiniband/hw/qib/qib_file_ops.c +++ b/drivers/infiniband/hw/qib/qib_file_ops.c @@ -45,6 +45,8 @@ #include <linux/export.h> #include <linux/uio.h> +#include <rdma/ib.h> + #include "qib.h" #include "qib_common.h" #include "qib_user_sdma.h" @@ -2067,6 +2069,9 @@ static ssize_t qib_write(struct file *fp, const char __user *data, ssize_t ret = 0; void *dest; + if (WARN_ON_ONCE(!ib_safe_file_access(fp))) + return -EACCES; + if (count < sizeof(cmd.type)) { ret = -EINVAL; goto bail; diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c index bd82a6948dc8..a9e3bcc522c4 100644 --- a/drivers/infiniband/sw/rdmavt/qp.c +++ b/drivers/infiniband/sw/rdmavt/qp.c @@ -1637,9 +1637,9 @@ bail: spin_unlock_irqrestore(&qp->s_hlock, flags); if (nreq) { if (call_send) - rdi->driver_f.schedule_send_no_lock(qp); - else rdi->driver_f.do_send(qp); + else + rdi->driver_f.schedule_send_no_lock(qp); } return err; } diff --git a/drivers/infiniband/ulp/iser/iscsi_iser.c b/drivers/infiniband/ulp/iser/iscsi_iser.c index 80b6bedc172f..64b3d11dcf1e 100644 --- a/drivers/infiniband/ulp/iser/iscsi_iser.c +++ b/drivers/infiniband/ulp/iser/iscsi_iser.c @@ -612,6 +612,7 @@ iscsi_iser_session_create(struct iscsi_endpoint *ep, struct Scsi_Host *shost; struct iser_conn *iser_conn = NULL; struct ib_conn *ib_conn; + u32 max_fr_sectors; u16 max_cmds; shost = iscsi_host_alloc(&iscsi_iser_sht, 0, 0); @@ -632,7 +633,6 @@ iscsi_iser_session_create(struct iscsi_endpoint *ep, iser_conn = ep->dd_data; max_cmds = iser_conn->max_cmds; shost->sg_tablesize = iser_conn->scsi_sg_tablesize; - shost->max_sectors = iser_conn->scsi_max_sectors; mutex_lock(&iser_conn->state_mutex); if (iser_conn->state != ISER_CONN_UP) { @@ -657,8 +657,6 @@ iscsi_iser_session_create(struct iscsi_endpoint *ep, */ shost->sg_tablesize = min_t(unsigned short, shost->sg_tablesize, ib_conn->device->ib_device->attrs.max_fast_reg_page_list_len); - shost->max_sectors = min_t(unsigned int, - 1024, (shost->sg_tablesize * PAGE_SIZE) >> 9); if (iscsi_host_add(shost, ib_conn->device->ib_device->dma_device)) { @@ -672,6 +670,15 @@ iscsi_iser_session_create(struct iscsi_endpoint *ep, goto free_host; } + /* + * FRs or FMRs can only map up to a (device) page per entry, but if the + * first entry is misaligned we'll end up using using two entries + * (head and tail) for a single page worth data, so we have to drop + * one segment from the calculation. + */ + max_fr_sectors = ((shost->sg_tablesize - 1) * PAGE_SIZE) >> 9; + shost->max_sectors = min(iser_max_sectors, max_fr_sectors); + if (cmds_max > max_cmds) { iser_info("cmds_max changed from %u to %u\n", cmds_max, max_cmds); @@ -989,7 +996,6 @@ static struct scsi_host_template iscsi_iser_sht = { .queuecommand = iscsi_queuecommand, .change_queue_depth = scsi_change_queue_depth, .sg_tablesize = ISCSI_ISER_DEF_SG_TABLESIZE, - .max_sectors = ISER_DEF_MAX_SECTORS, .cmd_per_lun = ISER_DEF_CMD_PER_LUN, .eh_abort_handler = iscsi_eh_abort, .eh_device_reset_handler= iscsi_eh_device_reset, diff --git a/drivers/input/misc/twl6040-vibra.c b/drivers/input/misc/twl6040-vibra.c index 53e33fab3f7a..df3581f60628 100644 --- a/drivers/input/misc/twl6040-vibra.c +++ b/drivers/input/misc/twl6040-vibra.c @@ -181,6 +181,14 @@ static void vibra_play_work(struct work_struct *work) { struct vibra_info *info = container_of(work, struct vibra_info, play_work); + int ret; + + /* Do not allow effect, while the routing is set to use audio */ + ret = twl6040_get_vibralr_status(info->twl6040); + if (ret & TWL6040_VIBSEL) { + dev_info(info->dev, "Vibra is configured for audio\n"); + return; + } mutex_lock(&info->mutex); @@ -199,14 +207,6 @@ static int vibra_play(struct input_dev *input, void *data, struct ff_effect *effect) { struct vibra_info *info = input_get_drvdata(input); - int ret; - - /* Do not allow effect, while the routing is set to use audio */ - ret = twl6040_get_vibralr_status(info->twl6040); - if (ret & TWL6040_VIBSEL) { - dev_info(&input->dev, "Vibra is configured for audio\n"); - return -EBUSY; - } info->weak_speed = effect->u.rumble.weak_magnitude; info->strong_speed = effect->u.rumble.strong_magnitude; diff --git a/drivers/input/touchscreen/atmel_mxt_ts.c b/drivers/input/touchscreen/atmel_mxt_ts.c index 2160512e861a..5af7907d0af4 100644 --- a/drivers/input/touchscreen/atmel_mxt_ts.c +++ b/drivers/input/touchscreen/atmel_mxt_ts.c @@ -1093,6 +1093,19 @@ static int mxt_t6_command(struct mxt_data *data, u16 cmd_offset, return 0; } +static int mxt_acquire_irq(struct mxt_data *data) +{ + int error; + + enable_irq(data->irq); + + error = mxt_process_messages_until_invalid(data); + if (error) + return error; + + return 0; +} + static int mxt_soft_reset(struct mxt_data *data) { struct device *dev = &data->client->dev; @@ -1111,7 +1124,7 @@ static int mxt_soft_reset(struct mxt_data *data) /* Ignore CHG line for 100ms after reset */ msleep(100); - enable_irq(data->irq); + mxt_acquire_irq(data); ret = mxt_wait_for_completion(data, &data->reset_completion, MXT_RESET_TIMEOUT); @@ -1466,19 +1479,6 @@ release_mem: return ret; } -static int mxt_acquire_irq(struct mxt_data *data) -{ - int error; - - enable_irq(data->irq); - - error = mxt_process_messages_until_invalid(data); - if (error) - return error; - - return 0; -} - static int mxt_get_info(struct mxt_data *data) { struct i2c_client *client = data->client; diff --git a/drivers/input/touchscreen/zforce_ts.c b/drivers/input/touchscreen/zforce_ts.c index 9bbadaaf6bc3..7b3845aa5983 100644 --- a/drivers/input/touchscreen/zforce_ts.c +++ b/drivers/input/touchscreen/zforce_ts.c @@ -370,8 +370,8 @@ static int zforce_touch_event(struct zforce_ts *ts, u8 *payload) point.coord_x = point.coord_y = 0; } - point.state = payload[9 * i + 5] & 0x03; - point.id = (payload[9 * i + 5] & 0xfc) >> 2; + point.state = payload[9 * i + 5] & 0x0f; + point.id = (payload[9 * i + 5] & 0xf0) >> 4; /* determine touch major, minor and orientation */ point.area_major = max(payload[9 * i + 6], diff --git a/drivers/md/md.c b/drivers/md/md.c index 194580fba7fd..14d3b37944df 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -284,6 +284,8 @@ static blk_qc_t md_make_request(struct request_queue *q, struct bio *bio) * go away inside make_request */ sectors = bio_sectors(bio); + /* bio could be mergeable after passing to underlayer */ + bio->bi_rw &= ~REQ_NOMERGE; mddev->pers->make_request(mddev, bio); cpu = part_stat_lock(); diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index 2ea12c6bf659..34783a3c8b3c 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -70,7 +70,6 @@ static void dump_zones(struct mddev *mddev) (unsigned long long)zone_size>>1); zone_start = conf->strip_zone[j].zone_end; } - printk(KERN_INFO "\n"); } static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf) @@ -85,6 +84,7 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf) struct r0conf *conf = kzalloc(sizeof(*conf), GFP_KERNEL); unsigned short blksize = 512; + *private_conf = ERR_PTR(-ENOMEM); if (!conf) return -ENOMEM; rdev_for_each(rdev1, mddev) { diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 8ab8b65e1741..e48c262ce032 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -3502,8 +3502,6 @@ returnbi: dev = &sh->dev[i]; } else if (test_bit(R5_Discard, &dev->flags)) discard_pending = 1; - WARN_ON(test_bit(R5_SkipCopy, &dev->flags)); - WARN_ON(dev->page != dev->orig_page); } r5l_stripe_write_finished(sh); diff --git a/drivers/media/media-device.c b/drivers/media/media-device.c index 6e43c95629ea..3cfd7af8c5ca 100644 --- a/drivers/media/media-device.c +++ b/drivers/media/media-device.c @@ -846,11 +846,11 @@ struct media_device *media_device_find_devres(struct device *dev) } EXPORT_SYMBOL_GPL(media_device_find_devres); +#if IS_ENABLED(CONFIG_PCI) void media_device_pci_init(struct media_device *mdev, struct pci_dev *pci_dev, const char *name) { -#ifdef CONFIG_PCI mdev->dev = &pci_dev->dev; if (name) @@ -866,16 +866,16 @@ void media_device_pci_init(struct media_device *mdev, mdev->driver_version = LINUX_VERSION_CODE; media_device_init(mdev); -#endif } EXPORT_SYMBOL_GPL(media_device_pci_init); +#endif +#if IS_ENABLED(CONFIG_USB) void __media_device_usb_init(struct media_device *mdev, struct usb_device *udev, const char *board_name, const char *driver_name) { -#ifdef CONFIG_USB mdev->dev = &udev->dev; if (driver_name) @@ -895,9 +895,9 @@ void __media_device_usb_init(struct media_device *mdev, mdev->driver_version = LINUX_VERSION_CODE; media_device_init(mdev); -#endif } EXPORT_SYMBOL_GPL(__media_device_usb_init); +#endif #endif /* CONFIG_MEDIA_CONTROLLER */ diff --git a/drivers/media/platform/exynos4-is/media-dev.c b/drivers/media/platform/exynos4-is/media-dev.c index feb521f28e14..4f494acd8150 100644 --- a/drivers/media/platform/exynos4-is/media-dev.c +++ b/drivers/media/platform/exynos4-is/media-dev.c @@ -1446,22 +1446,13 @@ static int fimc_md_probe(struct platform_device *pdev) platform_set_drvdata(pdev, fmd); - /* Protect the media graph while we're registering entities */ - mutex_lock(&fmd->media_dev.graph_mutex); - ret = fimc_md_register_platform_entities(fmd, dev->of_node); - if (ret) { - mutex_unlock(&fmd->media_dev.graph_mutex); + if (ret) goto err_clk; - } ret = fimc_md_register_sensor_entities(fmd); - if (ret) { - mutex_unlock(&fmd->media_dev.graph_mutex); + if (ret) goto err_m_ent; - } - - mutex_unlock(&fmd->media_dev.graph_mutex); ret = device_create_file(&pdev->dev, &dev_attr_subdev_conf_mode); if (ret) diff --git a/drivers/media/platform/s3c-camif/camif-core.c b/drivers/media/platform/s3c-camif/camif-core.c index 0b44b9accf50..af237af204e2 100644 --- a/drivers/media/platform/s3c-camif/camif-core.c +++ b/drivers/media/platform/s3c-camif/camif-core.c @@ -493,21 +493,17 @@ static int s3c_camif_probe(struct platform_device *pdev) if (ret < 0) goto err_sens; - mutex_lock(&camif->media_dev.graph_mutex); - ret = v4l2_device_register_subdev_nodes(&camif->v4l2_dev); if (ret < 0) - goto err_unlock; + goto err_sens; ret = camif_register_video_nodes(camif); if (ret < 0) - goto err_unlock; + goto err_sens; ret = camif_create_media_links(camif); if (ret < 0) - goto err_unlock; - - mutex_unlock(&camif->media_dev.graph_mutex); + goto err_sens; ret = media_device_register(&camif->media_dev); if (ret < 0) @@ -516,8 +512,6 @@ static int s3c_camif_probe(struct platform_device *pdev) pm_runtime_put(dev); return 0; -err_unlock: - mutex_unlock(&camif->media_dev.graph_mutex); err_sens: v4l2_device_unregister(&camif->v4l2_dev); media_device_unregister(&camif->media_dev); diff --git a/drivers/media/usb/usbvision/usbvision-video.c b/drivers/media/usb/usbvision/usbvision-video.c index 12f5ebbd0436..ad2f3d27b266 100644 --- a/drivers/media/usb/usbvision/usbvision-video.c +++ b/drivers/media/usb/usbvision/usbvision-video.c @@ -1452,13 +1452,6 @@ static int usbvision_probe(struct usb_interface *intf, printk(KERN_INFO "%s: %s found\n", __func__, usbvision_device_data[model].model_string); - /* - * this is a security check. - * an exploit using an incorrect bInterfaceNumber is known - */ - if (ifnum >= USB_MAXINTERFACES || !dev->actconfig->interface[ifnum]) - return -ENODEV; - if (usbvision_device_data[model].interface >= 0) interface = &dev->actconfig->interface[usbvision_device_data[model].interface]->altsetting[0]; else if (ifnum < dev->actconfig->desc.bNumInterfaces) diff --git a/drivers/media/v4l2-core/videobuf2-core.c b/drivers/media/v4l2-core/videobuf2-core.c index 5d016f496e0e..9fbcb67a9ee6 100644 --- a/drivers/media/v4l2-core/videobuf2-core.c +++ b/drivers/media/v4l2-core/videobuf2-core.c @@ -1645,7 +1645,7 @@ static int __vb2_wait_for_done_vb(struct vb2_queue *q, int nonblocking) * Will sleep if required for nonblocking == false. */ static int __vb2_get_done_vb(struct vb2_queue *q, struct vb2_buffer **vb, - int nonblocking) + void *pb, int nonblocking) { unsigned long flags; int ret; @@ -1666,10 +1666,10 @@ static int __vb2_get_done_vb(struct vb2_queue *q, struct vb2_buffer **vb, /* * Only remove the buffer from done_list if v4l2_buffer can handle all * the planes. - * Verifying planes is NOT necessary since it already has been checked - * before the buffer is queued/prepared. So it can never fail. */ - list_del(&(*vb)->done_entry); + ret = call_bufop(q, verify_planes_array, *vb, pb); + if (!ret) + list_del(&(*vb)->done_entry); spin_unlock_irqrestore(&q->done_lock, flags); return ret; @@ -1748,7 +1748,7 @@ int vb2_core_dqbuf(struct vb2_queue *q, unsigned int *pindex, void *pb, struct vb2_buffer *vb = NULL; int ret; - ret = __vb2_get_done_vb(q, &vb, nonblocking); + ret = __vb2_get_done_vb(q, &vb, pb, nonblocking); if (ret < 0) return ret; @@ -2298,6 +2298,16 @@ unsigned int vb2_core_poll(struct vb2_queue *q, struct file *file, return POLLERR; /* + * If this quirk is set and QBUF hasn't been called yet then + * return POLLERR as well. This only affects capture queues, output + * queues will always initialize waiting_for_buffers to false. + * This quirk is set by V4L2 for backwards compatibility reasons. + */ + if (q->quirk_poll_must_check_waiting_for_buffers && + q->waiting_for_buffers && (req_events & (POLLIN | POLLRDNORM))) + return POLLERR; + + /* * For output streams you can call write() as long as there are fewer * buffers queued than there are buffers available. */ diff --git a/drivers/media/v4l2-core/videobuf2-memops.c b/drivers/media/v4l2-core/videobuf2-memops.c index dbec5923fcf0..3c3b517f1d1c 100644 --- a/drivers/media/v4l2-core/videobuf2-memops.c +++ b/drivers/media/v4l2-core/videobuf2-memops.c @@ -49,7 +49,7 @@ struct frame_vector *vb2_create_framevec(unsigned long start, vec = frame_vector_create(nr); if (!vec) return ERR_PTR(-ENOMEM); - ret = get_vaddr_frames(start, nr, write, 1, vec); + ret = get_vaddr_frames(start & PAGE_MASK, nr, write, true, vec); if (ret < 0) goto out_destroy; /* We accept only complete set of PFNs */ diff --git a/drivers/media/v4l2-core/videobuf2-v4l2.c b/drivers/media/v4l2-core/videobuf2-v4l2.c index 91f552124050..7f366f1b0377 100644 --- a/drivers/media/v4l2-core/videobuf2-v4l2.c +++ b/drivers/media/v4l2-core/videobuf2-v4l2.c @@ -74,6 +74,11 @@ static int __verify_planes_array(struct vb2_buffer *vb, const struct v4l2_buffer return 0; } +static int __verify_planes_array_core(struct vb2_buffer *vb, const void *pb) +{ + return __verify_planes_array(vb, pb); +} + /** * __verify_length() - Verify that the bytesused value for each plane fits in * the plane length and that the data offset doesn't exceed the bytesused value. @@ -437,6 +442,7 @@ static int __fill_vb2_buffer(struct vb2_buffer *vb, } static const struct vb2_buf_ops v4l2_buf_ops = { + .verify_planes_array = __verify_planes_array_core, .fill_user_buffer = __fill_v4l2_buffer, .fill_vb2_buffer = __fill_vb2_buffer, .copy_timestamp = __copy_timestamp, @@ -765,6 +771,12 @@ int vb2_queue_init(struct vb2_queue *q) q->is_output = V4L2_TYPE_IS_OUTPUT(q->type); q->copy_timestamp = (q->timestamp_flags & V4L2_BUF_FLAG_TIMESTAMP_MASK) == V4L2_BUF_FLAG_TIMESTAMP_COPY; + /* + * For compatibility with vb1: if QBUF hasn't been called yet, then + * return POLLERR as well. This only affects capture queues, output + * queues will always initialize waiting_for_buffers to false. + */ + q->quirk_poll_must_check_waiting_for_buffers = true; return vb2_core_queue_init(q); } @@ -818,14 +830,6 @@ unsigned int vb2_poll(struct vb2_queue *q, struct file *file, poll_table *wait) poll_wait(file, &fh->wait, wait); } - /* - * For compatibility with vb1: if QBUF hasn't been called yet, then - * return POLLERR as well. This only affects capture queues, output - * queues will always initialize waiting_for_buffers to false. - */ - if (q->waiting_for_buffers && (req_events & (POLLIN | POLLRDNORM))) - return POLLERR; - return res | vb2_core_poll(q, file, wait); } EXPORT_SYMBOL_GPL(vb2_poll); diff --git a/drivers/misc/cxl/context.c b/drivers/misc/cxl/context.c index 10370f280500..7edea9c19199 100644 --- a/drivers/misc/cxl/context.c +++ b/drivers/misc/cxl/context.c @@ -223,6 +223,13 @@ int __detach_context(struct cxl_context *ctx) cxl_ops->link_ok(ctx->afu->adapter, ctx->afu)); flush_work(&ctx->fault_work); /* Only needed for dedicated process */ + /* + * Wait until no further interrupts are presented by the PSL + * for this context. + */ + if (cxl_ops->irq_wait) + cxl_ops->irq_wait(ctx); + /* release the reference to the group leader and mm handling pid */ put_pid(ctx->pid); put_pid(ctx->glpid); diff --git a/drivers/misc/cxl/cxl.h b/drivers/misc/cxl/cxl.h index 38e21cf7806e..73dc2a33da74 100644 --- a/drivers/misc/cxl/cxl.h +++ b/drivers/misc/cxl/cxl.h @@ -274,6 +274,7 @@ static const cxl_p2n_reg_t CXL_PSL_WED_An = {0x0A0}; #define CXL_PSL_DSISR_An_PE (1ull << (63-4)) /* PSL Error (implementation specific) */ #define CXL_PSL_DSISR_An_AE (1ull << (63-5)) /* AFU Error */ #define CXL_PSL_DSISR_An_OC (1ull << (63-6)) /* OS Context Warning */ +#define CXL_PSL_DSISR_PENDING (CXL_PSL_DSISR_TRANS | CXL_PSL_DSISR_An_PE | CXL_PSL_DSISR_An_AE | CXL_PSL_DSISR_An_OC) /* NOTE: Bits 32:63 are undefined if DSISR[DS] = 1 */ #define CXL_PSL_DSISR_An_M DSISR_NOHPTE /* PTE not found */ #define CXL_PSL_DSISR_An_P DSISR_PROTFAULT /* Storage protection violation */ @@ -855,6 +856,7 @@ struct cxl_backend_ops { u64 dsisr, u64 errstat); irqreturn_t (*psl_interrupt)(int irq, void *data); int (*ack_irq)(struct cxl_context *ctx, u64 tfc, u64 psl_reset_mask); + void (*irq_wait)(struct cxl_context *ctx); int (*attach_process)(struct cxl_context *ctx, bool kernel, u64 wed, u64 amr); int (*detach_process)(struct cxl_context *ctx); diff --git a/drivers/misc/cxl/irq.c b/drivers/misc/cxl/irq.c index be646dc41a2c..8def4553acba 100644 --- a/drivers/misc/cxl/irq.c +++ b/drivers/misc/cxl/irq.c @@ -203,7 +203,6 @@ unsigned int cxl_map_irq(struct cxl *adapter, irq_hw_number_t hwirq, void cxl_unmap_irq(unsigned int virq, void *cookie) { free_irq(virq, cookie); - irq_dispose_mapping(virq); } int cxl_register_one_irq(struct cxl *adapter, diff --git a/drivers/misc/cxl/native.c b/drivers/misc/cxl/native.c index 387fcbdf9793..ecf7557cd657 100644 --- a/drivers/misc/cxl/native.c +++ b/drivers/misc/cxl/native.c @@ -14,6 +14,7 @@ #include <linux/mutex.h> #include <linux/mm.h> #include <linux/uaccess.h> +#include <linux/delay.h> #include <asm/synch.h> #include <misc/cxl-base.h> @@ -797,6 +798,35 @@ static irqreturn_t native_irq_multiplexed(int irq, void *data) return fail_psl_irq(afu, &irq_info); } +void native_irq_wait(struct cxl_context *ctx) +{ + u64 dsisr; + int timeout = 1000; + int ph; + + /* + * Wait until no further interrupts are presented by the PSL + * for this context. + */ + while (timeout--) { + ph = cxl_p2n_read(ctx->afu, CXL_PSL_PEHandle_An) & 0xffff; + if (ph != ctx->pe) + return; + dsisr = cxl_p2n_read(ctx->afu, CXL_PSL_DSISR_An); + if ((dsisr & CXL_PSL_DSISR_PENDING) == 0) + return; + /* + * We are waiting for the workqueue to process our + * irq, so need to let that run here. + */ + msleep(1); + } + + dev_warn(&ctx->afu->dev, "WARNING: waiting on DSI for PE %i" + " DSISR %016llx!\n", ph, dsisr); + return; +} + static irqreturn_t native_slice_irq_err(int irq, void *data) { struct cxl_afu *afu = data; @@ -1076,6 +1106,7 @@ const struct cxl_backend_ops cxl_native_ops = { .handle_psl_slice_error = native_handle_psl_slice_error, .psl_interrupt = NULL, .ack_irq = native_ack_irq, + .irq_wait = native_irq_wait, .attach_process = native_attach_process, .detach_process = native_detach_process, .support_attributes = native_support_attributes, diff --git a/drivers/misc/mic/vop/vop_vringh.c b/drivers/misc/mic/vop/vop_vringh.c index e94c7fb6712a..88e45234d527 100644 --- a/drivers/misc/mic/vop/vop_vringh.c +++ b/drivers/misc/mic/vop/vop_vringh.c @@ -945,6 +945,11 @@ static long vop_ioctl(struct file *f, unsigned int cmd, unsigned long arg) ret = -EFAULT; goto free_ret; } + /* Ensure desc has not changed between the two reads */ + if (memcmp(&dd, dd_config, sizeof(dd))) { + ret = -EINVAL; + goto free_ret; + } mutex_lock(&vdev->vdev_mutex); mutex_lock(&vi->vop_mutex); ret = vop_virtio_add_device(vdev, dd_config); diff --git a/drivers/mmc/host/Kconfig b/drivers/mmc/host/Kconfig index 04feea8354cb..e657af0e95fa 100644 --- a/drivers/mmc/host/Kconfig +++ b/drivers/mmc/host/Kconfig @@ -97,6 +97,7 @@ config MMC_RICOH_MMC config MMC_SDHCI_ACPI tristate "SDHCI support for ACPI enumerated SDHCI controllers" depends on MMC_SDHCI && ACPI + select IOSF_MBI if X86 help This selects support for ACPI enumerated SDHCI controllers, identified by ACPI Compatibility ID PNP0D40 or specific diff --git a/drivers/mmc/host/sdhci-acpi.c b/drivers/mmc/host/sdhci-acpi.c index 6839e41c6d58..bed6a494f52c 100644 --- a/drivers/mmc/host/sdhci-acpi.c +++ b/drivers/mmc/host/sdhci-acpi.c @@ -41,6 +41,11 @@ #include <linux/mmc/pm.h> #include <linux/mmc/slot-gpio.h> +#ifdef CONFIG_X86 +#include <asm/cpu_device_id.h> +#include <asm/iosf_mbi.h> +#endif + #include "sdhci.h" enum { @@ -116,6 +121,75 @@ static const struct sdhci_acpi_chip sdhci_acpi_chip_int = { .ops = &sdhci_acpi_ops_int, }; +#ifdef CONFIG_X86 + +static bool sdhci_acpi_byt(void) +{ + static const struct x86_cpu_id byt[] = { + { X86_VENDOR_INTEL, 6, 0x37 }, + {} + }; + + return x86_match_cpu(byt); +} + +#define BYT_IOSF_SCCEP 0x63 +#define BYT_IOSF_OCP_NETCTRL0 0x1078 +#define BYT_IOSF_OCP_TIMEOUT_BASE GENMASK(10, 8) + +static void sdhci_acpi_byt_setting(struct device *dev) +{ + u32 val = 0; + + if (!sdhci_acpi_byt()) + return; + + if (iosf_mbi_read(BYT_IOSF_SCCEP, MBI_CR_READ, BYT_IOSF_OCP_NETCTRL0, + &val)) { + dev_err(dev, "%s read error\n", __func__); + return; + } + + if (!(val & BYT_IOSF_OCP_TIMEOUT_BASE)) + return; + + val &= ~BYT_IOSF_OCP_TIMEOUT_BASE; + + if (iosf_mbi_write(BYT_IOSF_SCCEP, MBI_CR_WRITE, BYT_IOSF_OCP_NETCTRL0, + val)) { + dev_err(dev, "%s write error\n", __func__); + return; + } + + dev_dbg(dev, "%s completed\n", __func__); +} + +static bool sdhci_acpi_byt_defer(struct device *dev) +{ + if (!sdhci_acpi_byt()) + return false; + + if (!iosf_mbi_available()) + return true; + + sdhci_acpi_byt_setting(dev); + + return false; +} + +#else + +static inline void sdhci_acpi_byt_setting(struct device *dev) +{ +} + +static inline bool sdhci_acpi_byt_defer(struct device *dev) +{ + return false; +} + +#endif + static int bxt_get_cd(struct mmc_host *mmc) { int gpio_cd = mmc_gpio_get_cd(mmc); @@ -322,6 +396,9 @@ static int sdhci_acpi_probe(struct platform_device *pdev) if (acpi_bus_get_status(device) || !device->status.present) return -ENODEV; + if (sdhci_acpi_byt_defer(dev)) + return -EPROBE_DEFER; + hid = acpi_device_hid(device); uid = device->pnp.unique_id; @@ -447,6 +524,8 @@ static int sdhci_acpi_resume(struct device *dev) { struct sdhci_acpi_host *c = dev_get_drvdata(dev); + sdhci_acpi_byt_setting(&c->pdev->dev); + return sdhci_resume_host(c->host); } @@ -470,6 +549,8 @@ static int sdhci_acpi_runtime_resume(struct device *dev) { struct sdhci_acpi_host *c = dev_get_drvdata(dev); + sdhci_acpi_byt_setting(&c->pdev->dev); + return sdhci_runtime_resume_host(c->host); } diff --git a/drivers/mmc/host/sunxi-mmc.c b/drivers/mmc/host/sunxi-mmc.c index 8372a413848c..7fc8b7aa83f0 100644 --- a/drivers/mmc/host/sunxi-mmc.c +++ b/drivers/mmc/host/sunxi-mmc.c @@ -1129,6 +1129,11 @@ static int sunxi_mmc_probe(struct platform_device *pdev) MMC_CAP_1_8V_DDR | MMC_CAP_ERASE | MMC_CAP_SDIO_IRQ; + /* TODO MMC DDR is not working on A80 */ + if (of_device_is_compatible(pdev->dev.of_node, + "allwinner,sun9i-a80-mmc")) + mmc->caps &= ~MMC_CAP_1_8V_DDR; + ret = mmc_of_parse(mmc); if (ret) goto error_free_dma; diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index a24c18eee598..befd67df08e1 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -62,9 +62,8 @@ config DUMMY this device is consigned into oblivion) with a configurable IP address. It is most commonly used in order to make your currently inactive SLIP address seem like a real address for local programs. - If you use SLIP or PPP, you might want to say Y here. Since this - thing often comes in handy, the default is Y. It won't enlarge your - kernel either. What a deal. Read about it in the Network + If you use SLIP or PPP, you might want to say Y here. It won't + enlarge your kernel. What a deal. Read about it in the Network Administrator's Guide, available from <http://www.tldp.org/docs.html#guide>. diff --git a/drivers/net/dsa/mv88e6xxx.c b/drivers/net/dsa/mv88e6xxx.c index a2904029cccc..5e572b3510b9 100644 --- a/drivers/net/dsa/mv88e6xxx.c +++ b/drivers/net/dsa/mv88e6xxx.c @@ -2181,7 +2181,7 @@ int mv88e6xxx_port_bridge_join(struct dsa_switch *ds, int port, struct net_device *bridge) { struct mv88e6xxx_priv_state *ps = ds_to_priv(ds); - int i, err; + int i, err = 0; mutex_lock(&ps->smi_mutex); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 12a009d720cd..72eb29ed0359 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -581,12 +581,30 @@ static inline int bnxt_alloc_rx_page(struct bnxt *bp, struct page *page; dma_addr_t mapping; u16 sw_prod = rxr->rx_sw_agg_prod; + unsigned int offset = 0; - page = alloc_page(gfp); - if (!page) - return -ENOMEM; + if (PAGE_SIZE > BNXT_RX_PAGE_SIZE) { + page = rxr->rx_page; + if (!page) { + page = alloc_page(gfp); + if (!page) + return -ENOMEM; + rxr->rx_page = page; + rxr->rx_page_offset = 0; + } + offset = rxr->rx_page_offset; + rxr->rx_page_offset += BNXT_RX_PAGE_SIZE; + if (rxr->rx_page_offset == PAGE_SIZE) + rxr->rx_page = NULL; + else + get_page(page); + } else { + page = alloc_page(gfp); + if (!page) + return -ENOMEM; + } - mapping = dma_map_page(&pdev->dev, page, 0, PAGE_SIZE, + mapping = dma_map_page(&pdev->dev, page, offset, BNXT_RX_PAGE_SIZE, PCI_DMA_FROMDEVICE); if (dma_mapping_error(&pdev->dev, mapping)) { __free_page(page); @@ -601,6 +619,7 @@ static inline int bnxt_alloc_rx_page(struct bnxt *bp, rxr->rx_sw_agg_prod = NEXT_RX_AGG(sw_prod); rx_agg_buf->page = page; + rx_agg_buf->offset = offset; rx_agg_buf->mapping = mapping; rxbd->rx_bd_haddr = cpu_to_le64(mapping); rxbd->rx_bd_opaque = sw_prod; @@ -642,6 +661,7 @@ static void bnxt_reuse_rx_agg_bufs(struct bnxt_napi *bnapi, u16 cp_cons, page = cons_rx_buf->page; cons_rx_buf->page = NULL; prod_rx_buf->page = page; + prod_rx_buf->offset = cons_rx_buf->offset; prod_rx_buf->mapping = cons_rx_buf->mapping; @@ -709,7 +729,8 @@ static struct sk_buff *bnxt_rx_pages(struct bnxt *bp, struct bnxt_napi *bnapi, RX_AGG_CMP_LEN) >> RX_AGG_CMP_LEN_SHIFT; cons_rx_buf = &rxr->rx_agg_ring[cons]; - skb_fill_page_desc(skb, i, cons_rx_buf->page, 0, frag_len); + skb_fill_page_desc(skb, i, cons_rx_buf->page, + cons_rx_buf->offset, frag_len); __clear_bit(cons, rxr->rx_agg_bmap); /* It is possible for bnxt_alloc_rx_page() to allocate @@ -740,7 +761,7 @@ static struct sk_buff *bnxt_rx_pages(struct bnxt *bp, struct bnxt_napi *bnapi, return NULL; } - dma_unmap_page(&pdev->dev, mapping, PAGE_SIZE, + dma_unmap_page(&pdev->dev, mapping, BNXT_RX_PAGE_SIZE, PCI_DMA_FROMDEVICE); skb->data_len += frag_len; @@ -1584,13 +1605,17 @@ static void bnxt_free_rx_skbs(struct bnxt *bp) dma_unmap_page(&pdev->dev, dma_unmap_addr(rx_agg_buf, mapping), - PAGE_SIZE, PCI_DMA_FROMDEVICE); + BNXT_RX_PAGE_SIZE, PCI_DMA_FROMDEVICE); rx_agg_buf->page = NULL; __clear_bit(j, rxr->rx_agg_bmap); __free_page(page); } + if (rxr->rx_page) { + __free_page(rxr->rx_page); + rxr->rx_page = NULL; + } } } @@ -1973,7 +1998,7 @@ static int bnxt_init_one_rx_ring(struct bnxt *bp, int ring_nr) if (!(bp->flags & BNXT_FLAG_AGG_RINGS)) return 0; - type = ((u32)PAGE_SIZE << RX_BD_LEN_SHIFT) | + type = ((u32)BNXT_RX_PAGE_SIZE << RX_BD_LEN_SHIFT) | RX_BD_TYPE_RX_AGG_BD | RX_BD_FLAGS_SOP; bnxt_init_rxbd_pages(ring, type); @@ -2164,7 +2189,7 @@ void bnxt_set_ring_params(struct bnxt *bp) bp->rx_agg_nr_pages = 0; if (bp->flags & BNXT_FLAG_TPA) - agg_factor = 4; + agg_factor = min_t(u32, 4, 65536 / BNXT_RX_PAGE_SIZE); bp->flags &= ~BNXT_FLAG_JUMBO; if (rx_space > PAGE_SIZE) { @@ -3020,12 +3045,12 @@ static int bnxt_hwrm_vnic_set_tpa(struct bnxt *bp, u16 vnic_id, u32 tpa_flags) /* Number of segs are log2 units, and first packet is not * included as part of this units. */ - if (mss <= PAGE_SIZE) { - n = PAGE_SIZE / mss; + if (mss <= BNXT_RX_PAGE_SIZE) { + n = BNXT_RX_PAGE_SIZE / mss; nsegs = (MAX_SKB_FRAGS - 1) * n; } else { - n = mss / PAGE_SIZE; - if (mss & (PAGE_SIZE - 1)) + n = mss / BNXT_RX_PAGE_SIZE; + if (mss & (BNXT_RX_PAGE_SIZE - 1)) n++; nsegs = (MAX_SKB_FRAGS - n) / n; } @@ -4309,7 +4334,7 @@ static int bnxt_setup_int_mode(struct bnxt *bp) if (bp->flags & BNXT_FLAG_MSIX_CAP) rc = bnxt_setup_msix(bp); - if (!(bp->flags & BNXT_FLAG_USING_MSIX)) { + if (!(bp->flags & BNXT_FLAG_USING_MSIX) && BNXT_PF(bp)) { /* fallback to INTA */ rc = bnxt_setup_inta(bp); } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 709b95b8fcba..8b823ff558ff 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -407,6 +407,15 @@ struct rx_tpa_end_cmp_ext { #define BNXT_PAGE_SIZE (1 << BNXT_PAGE_SHIFT) +/* The RXBD length is 16-bit so we can only support page sizes < 64K */ +#if (PAGE_SHIFT > 15) +#define BNXT_RX_PAGE_SHIFT 15 +#else +#define BNXT_RX_PAGE_SHIFT PAGE_SHIFT +#endif + +#define BNXT_RX_PAGE_SIZE (1 << BNXT_RX_PAGE_SHIFT) + #define BNXT_MIN_PKT_SIZE 45 #define BNXT_NUM_TESTS(bp) 0 @@ -506,6 +515,7 @@ struct bnxt_sw_rx_bd { struct bnxt_sw_rx_agg_bd { struct page *page; + unsigned int offset; dma_addr_t mapping; }; @@ -586,6 +596,9 @@ struct bnxt_rx_ring_info { unsigned long *rx_agg_bmap; u16 rx_agg_bmap_size; + struct page *rx_page; + unsigned int rx_page_offset; + dma_addr_t rx_desc_mapping[MAX_RX_PAGES]; dma_addr_t rx_agg_desc_mapping[MAX_RX_AGG_PAGES]; diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c index 48a7d7dee846..a63551d0a18a 100644 --- a/drivers/net/ethernet/cadence/macb.c +++ b/drivers/net/ethernet/cadence/macb.c @@ -441,7 +441,7 @@ static int macb_mii_init(struct macb *bp) snprintf(bp->mii_bus->id, MII_BUS_ID_SIZE, "%s-%x", bp->pdev->name, bp->pdev->id); bp->mii_bus->priv = bp; - bp->mii_bus->parent = &bp->dev->dev; + bp->mii_bus->parent = &bp->pdev->dev; pdata = dev_get_platdata(&bp->pdev->dev); dev_set_drvdata(&bp->dev->dev, bp->mii_bus); @@ -458,7 +458,8 @@ static int macb_mii_init(struct macb *bp) struct phy_device *phydev; phydev = mdiobus_scan(bp->mii_bus, i); - if (IS_ERR(phydev)) { + if (IS_ERR(phydev) && + PTR_ERR(phydev) != -ENODEV) { err = PTR_ERR(phydev); break; } @@ -3019,29 +3020,36 @@ static int macb_probe(struct platform_device *pdev) if (err) goto err_out_free_netdev; + err = macb_mii_init(bp); + if (err) + goto err_out_free_netdev; + + phydev = bp->phy_dev; + + netif_carrier_off(dev); + err = register_netdev(dev); if (err) { dev_err(&pdev->dev, "Cannot register net device, aborting.\n"); - goto err_out_unregister_netdev; + goto err_out_unregister_mdio; } - err = macb_mii_init(bp); - if (err) - goto err_out_unregister_netdev; - - netif_carrier_off(dev); + phy_attached_info(phydev); netdev_info(dev, "Cadence %s rev 0x%08x at 0x%08lx irq %d (%pM)\n", macb_is_gem(bp) ? "GEM" : "MACB", macb_readl(bp, MID), dev->base_addr, dev->irq, dev->dev_addr); - phydev = bp->phy_dev; - phy_attached_info(phydev); - return 0; -err_out_unregister_netdev: - unregister_netdev(dev); +err_out_unregister_mdio: + phy_disconnect(bp->phy_dev); + mdiobus_unregister(bp->mii_bus); + mdiobus_free(bp->mii_bus); + + /* Shutdown the PHY if there is a GPIO reset */ + if (bp->reset_gpio) + gpiod_set_value(bp->reset_gpio, 0); err_out_free_netdev: free_netdev(dev); diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c index 60908eab3b3a..43da891fab97 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c +++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c @@ -576,7 +576,7 @@ static void setup_rss(struct adapter *adap) unsigned int nq0 = adap2pinfo(adap, 0)->nqsets; unsigned int nq1 = adap->port[1] ? adap2pinfo(adap, 1)->nqsets : 1; u8 cpus[SGE_QSETS + 1]; - u16 rspq_map[RSS_TABLE_SIZE]; + u16 rspq_map[RSS_TABLE_SIZE + 1]; for (i = 0; i < SGE_QSETS; ++i) cpus[i] = i; @@ -586,6 +586,7 @@ static void setup_rss(struct adapter *adap) rspq_map[i] = i % nq0; rspq_map[i + RSS_TABLE_SIZE / 2] = (i % nq1) + nq0; } + rspq_map[RSS_TABLE_SIZE] = 0xffff; /* terminator */ t3_config_rss(adap, F_RQFEEDBACKENABLE | F_TNLLKPEN | F_TNLMAPEN | F_TNLPRTEN | F_TNL2TUPEN | F_TNL4TUPEN | diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 7fc490225da5..a6d26d351dfc 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -3354,8 +3354,7 @@ static int mvneta_percpu_notifier(struct notifier_block *nfb, /* Enable per-CPU interrupts on the CPU that is * brought up. */ - smp_call_function_single(cpu, mvneta_percpu_enable, - pp, true); + mvneta_percpu_enable(pp); /* Enable per-CPU interrupt on the one CPU we care * about. @@ -3387,8 +3386,7 @@ static int mvneta_percpu_notifier(struct notifier_block *nfb, /* Disable per-CPU interrupts on the CPU that is * brought down. */ - smp_call_function_single(cpu, mvneta_percpu_disable, - pp, true); + mvneta_percpu_disable(pp); break; case CPU_DEAD: diff --git a/drivers/net/ethernet/marvell/pxa168_eth.c b/drivers/net/ethernet/marvell/pxa168_eth.c index 7ace07dad6a3..c442f6ad15ff 100644 --- a/drivers/net/ethernet/marvell/pxa168_eth.c +++ b/drivers/net/ethernet/marvell/pxa168_eth.c @@ -979,6 +979,8 @@ static int pxa168_init_phy(struct net_device *dev) return 0; pep->phy = mdiobus_scan(pep->smi_bus, pep->phy_addr); + if (IS_ERR(pep->phy)) + return PTR_ERR(pep->phy); if (!pep->phy) return -ENODEV; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index c0d7b7296236..a386f047c1af 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -405,7 +405,6 @@ static bool mlx4_en_process_tx_cq(struct net_device *dev, u32 packets = 0; u32 bytes = 0; int factor = priv->cqe_factor; - u64 timestamp = 0; int done = 0; int budget = priv->tx_work_limit; u32 last_nr_txbb; @@ -445,9 +444,12 @@ static bool mlx4_en_process_tx_cq(struct net_device *dev, new_index = be16_to_cpu(cqe->wqe_index) & size_mask; do { + u64 timestamp = 0; + txbbs_skipped += last_nr_txbb; ring_index = (ring_index + last_nr_txbb) & size_mask; - if (ring->tx_info[ring_index].ts_requested) + + if (unlikely(ring->tx_info[ring_index].ts_requested)) timestamp = mlx4_en_get_cqe_ts(cqe); /* free next descriptor */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig index 1cf722eba607..559d11a443bc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig +++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig @@ -14,6 +14,7 @@ config MLX5_CORE_EN bool "Mellanox Technologies ConnectX-4 Ethernet support" depends on NETDEVICES && ETHERNET && PCI && MLX5_CORE select PTP_1588_CLOCK + select VXLAN if MLX5_CORE=y default n ---help--- Ethernet support in Mellanox Technologies ConnectX-4 NIC. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 879e6276c473..3881dce0cc30 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -567,6 +567,7 @@ struct mlx5e_priv { struct mlx5e_vxlan_db vxlan; struct mlx5e_params params; + struct workqueue_struct *wq; struct work_struct update_carrier_work; struct work_struct set_rx_mode_work; struct delayed_work update_stats_work; @@ -609,7 +610,7 @@ enum mlx5e_link_mode { MLX5E_100GBASE_KR4 = 22, MLX5E_100GBASE_LR4 = 23, MLX5E_100BASE_TX = 24, - MLX5E_100BASE_T = 25, + MLX5E_1000BASE_T = 25, MLX5E_10GBASE_T = 26, MLX5E_25GBASE_CR = 27, MLX5E_25GBASE_KR = 28, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 68834b715f6c..3476ab844634 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -138,10 +138,10 @@ static const struct { [MLX5E_100BASE_TX] = { .speed = 100, }, - [MLX5E_100BASE_T] = { - .supported = SUPPORTED_100baseT_Full, - .advertised = ADVERTISED_100baseT_Full, - .speed = 100, + [MLX5E_1000BASE_T] = { + .supported = SUPPORTED_1000baseT_Full, + .advertised = ADVERTISED_1000baseT_Full, + .speed = 1000, }, [MLX5E_10GBASE_T] = { .supported = SUPPORTED_10000baseT_Full, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index e0adb604f461..d4dfc5ce516a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -262,9 +262,8 @@ static void mlx5e_update_stats_work(struct work_struct *work) mutex_lock(&priv->state_lock); if (test_bit(MLX5E_STATE_OPENED, &priv->state)) { mlx5e_update_stats(priv); - schedule_delayed_work(dwork, - msecs_to_jiffies( - MLX5E_UPDATE_STATS_INTERVAL)); + queue_delayed_work(priv->wq, dwork, + msecs_to_jiffies(MLX5E_UPDATE_STATS_INTERVAL)); } mutex_unlock(&priv->state_lock); } @@ -280,7 +279,7 @@ static void mlx5e_async_event(struct mlx5_core_dev *mdev, void *vpriv, switch (event) { case MLX5_DEV_EVENT_PORT_UP: case MLX5_DEV_EVENT_PORT_DOWN: - schedule_work(&priv->update_carrier_work); + queue_work(priv->wq, &priv->update_carrier_work); break; default: @@ -1404,24 +1403,50 @@ static int mlx5e_refresh_tirs_self_loopback_enable(struct mlx5e_priv *priv) return 0; } -static int mlx5e_set_dev_port_mtu(struct net_device *netdev) +static int mlx5e_set_mtu(struct mlx5e_priv *priv, u16 mtu) { - struct mlx5e_priv *priv = netdev_priv(netdev); struct mlx5_core_dev *mdev = priv->mdev; - int hw_mtu; + u16 hw_mtu = MLX5E_SW2HW_MTU(mtu); int err; - err = mlx5_set_port_mtu(mdev, MLX5E_SW2HW_MTU(netdev->mtu), 1); + err = mlx5_set_port_mtu(mdev, hw_mtu, 1); if (err) return err; - mlx5_query_port_oper_mtu(mdev, &hw_mtu, 1); + /* Update vport context MTU */ + mlx5_modify_nic_vport_mtu(mdev, hw_mtu); + return 0; +} + +static void mlx5e_query_mtu(struct mlx5e_priv *priv, u16 *mtu) +{ + struct mlx5_core_dev *mdev = priv->mdev; + u16 hw_mtu = 0; + int err; - if (MLX5E_HW2SW_MTU(hw_mtu) != netdev->mtu) - netdev_warn(netdev, "%s: Port MTU %d is different than netdev mtu %d\n", - __func__, MLX5E_HW2SW_MTU(hw_mtu), netdev->mtu); + err = mlx5_query_nic_vport_mtu(mdev, &hw_mtu); + if (err || !hw_mtu) /* fallback to port oper mtu */ + mlx5_query_port_oper_mtu(mdev, &hw_mtu, 1); + + *mtu = MLX5E_HW2SW_MTU(hw_mtu); +} + +static int mlx5e_set_dev_port_mtu(struct net_device *netdev) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + u16 mtu; + int err; - netdev->mtu = MLX5E_HW2SW_MTU(hw_mtu); + err = mlx5e_set_mtu(priv, netdev->mtu); + if (err) + return err; + + mlx5e_query_mtu(priv, &mtu); + if (mtu != netdev->mtu) + netdev_warn(netdev, "%s: VPort MTU %d is different than netdev mtu %d\n", + __func__, mtu, netdev->mtu); + + netdev->mtu = mtu; return 0; } @@ -1479,7 +1504,7 @@ int mlx5e_open_locked(struct net_device *netdev) mlx5e_update_carrier(priv); mlx5e_timestamp_init(priv); - schedule_delayed_work(&priv->update_stats_work, 0); + queue_delayed_work(priv->wq, &priv->update_stats_work, 0); return 0; @@ -1935,7 +1960,7 @@ static void mlx5e_set_rx_mode(struct net_device *dev) { struct mlx5e_priv *priv = netdev_priv(dev); - schedule_work(&priv->set_rx_mode_work); + queue_work(priv->wq, &priv->set_rx_mode_work); } static int mlx5e_set_mac(struct net_device *netdev, void *addr) @@ -1950,7 +1975,7 @@ static int mlx5e_set_mac(struct net_device *netdev, void *addr) ether_addr_copy(netdev->dev_addr, saddr->sa_data); netif_addr_unlock_bh(netdev); - schedule_work(&priv->set_rx_mode_work); + queue_work(priv->wq, &priv->set_rx_mode_work); return 0; } @@ -1999,22 +2024,27 @@ static int mlx5e_set_features(struct net_device *netdev, return err; } +#define MXL5_HW_MIN_MTU 64 +#define MXL5E_MIN_MTU (MXL5_HW_MIN_MTU + ETH_FCS_LEN) + static int mlx5e_change_mtu(struct net_device *netdev, int new_mtu) { struct mlx5e_priv *priv = netdev_priv(netdev); struct mlx5_core_dev *mdev = priv->mdev; bool was_opened; - int max_mtu; + u16 max_mtu; + u16 min_mtu; int err = 0; mlx5_query_port_max_mtu(mdev, &max_mtu, 1); max_mtu = MLX5E_HW2SW_MTU(max_mtu); + min_mtu = MLX5E_HW2SW_MTU(MXL5E_MIN_MTU); - if (new_mtu > max_mtu) { + if (new_mtu > max_mtu || new_mtu < min_mtu) { netdev_err(netdev, - "%s: Bad MTU (%d) > (%d) Max\n", - __func__, new_mtu, max_mtu); + "%s: Bad MTU (%d), valid range is: [%d..%d]\n", + __func__, new_mtu, min_mtu, max_mtu); return -EINVAL; } @@ -2127,7 +2157,7 @@ static void mlx5e_add_vxlan_port(struct net_device *netdev, if (!mlx5e_vxlan_allowed(priv->mdev)) return; - mlx5e_vxlan_add_port(priv, be16_to_cpu(port)); + mlx5e_vxlan_queue_work(priv, sa_family, be16_to_cpu(port), 1); } static void mlx5e_del_vxlan_port(struct net_device *netdev, @@ -2138,7 +2168,7 @@ static void mlx5e_del_vxlan_port(struct net_device *netdev, if (!mlx5e_vxlan_allowed(priv->mdev)) return; - mlx5e_vxlan_del_port(priv, be16_to_cpu(port)); + mlx5e_vxlan_queue_work(priv, sa_family, be16_to_cpu(port), 0); } static netdev_features_t mlx5e_vxlan_features_check(struct mlx5e_priv *priv, @@ -2467,10 +2497,14 @@ static void *mlx5e_create_netdev(struct mlx5_core_dev *mdev) priv = netdev_priv(netdev); + priv->wq = create_singlethread_workqueue("mlx5e"); + if (!priv->wq) + goto err_free_netdev; + err = mlx5_alloc_map_uar(mdev, &priv->cq_uar, false); if (err) { mlx5_core_err(mdev, "alloc_map uar failed, %d\n", err); - goto err_free_netdev; + goto err_destroy_wq; } err = mlx5_core_alloc_pd(mdev, &priv->pdn); @@ -2549,7 +2583,7 @@ static void *mlx5e_create_netdev(struct mlx5_core_dev *mdev) vxlan_get_rx_port(netdev); mlx5e_enable_async_events(priv); - schedule_work(&priv->set_rx_mode_work); + queue_work(priv->wq, &priv->set_rx_mode_work); return priv; @@ -2586,6 +2620,9 @@ err_dealloc_pd: err_unmap_free_uar: mlx5_unmap_free_uar(mdev, &priv->cq_uar); +err_destroy_wq: + destroy_workqueue(priv->wq); + err_free_netdev: free_netdev(netdev); @@ -2599,10 +2636,19 @@ static void mlx5e_destroy_netdev(struct mlx5_core_dev *mdev, void *vpriv) set_bit(MLX5E_STATE_DESTROYING, &priv->state); - schedule_work(&priv->set_rx_mode_work); + queue_work(priv->wq, &priv->set_rx_mode_work); mlx5e_disable_async_events(priv); - flush_scheduled_work(); - unregister_netdev(netdev); + flush_workqueue(priv->wq); + if (test_bit(MLX5_INTERFACE_STATE_SHUTDOWN, &mdev->intf_state)) { + netif_device_detach(netdev); + mutex_lock(&priv->state_lock); + if (test_bit(MLX5E_STATE_OPENED, &priv->state)) + mlx5e_close_locked(netdev); + mutex_unlock(&priv->state_lock); + } else { + unregister_netdev(netdev); + } + mlx5e_tc_cleanup(priv); mlx5e_vxlan_cleanup(priv); mlx5e_destroy_flow_tables(priv); @@ -2615,7 +2661,11 @@ static void mlx5e_destroy_netdev(struct mlx5_core_dev *mdev, void *vpriv) mlx5_core_dealloc_transport_domain(priv->mdev, priv->tdn); mlx5_core_dealloc_pd(priv->mdev, priv->pdn); mlx5_unmap_free_uar(priv->mdev, &priv->cq_uar); - free_netdev(netdev); + cancel_delayed_work_sync(&priv->update_stats_work); + destroy_workqueue(priv->wq); + + if (!test_bit(MLX5_INTERFACE_STATE_SHUTDOWN, &mdev->intf_state)) + free_netdev(netdev); } static void *mlx5e_get_netdev(void *vpriv) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 5121be4675d1..89cce97d46c6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -1065,33 +1065,6 @@ unlock_fg: return rule; } -static struct mlx5_flow_rule *add_rule_to_auto_fg(struct mlx5_flow_table *ft, - u8 match_criteria_enable, - u32 *match_criteria, - u32 *match_value, - u8 action, - u32 flow_tag, - struct mlx5_flow_destination *dest) -{ - struct mlx5_flow_rule *rule; - struct mlx5_flow_group *g; - - g = create_autogroup(ft, match_criteria_enable, match_criteria); - if (IS_ERR(g)) - return (void *)g; - - rule = add_rule_fg(g, match_value, - action, flow_tag, dest); - if (IS_ERR(rule)) { - /* Remove assumes refcount > 0 and autogroup creates a group - * with a refcount = 0. - */ - tree_get_node(&g->node); - tree_remove_node(&g->node); - } - return rule; -} - static struct mlx5_flow_rule * _mlx5_add_flow_rule(struct mlx5_flow_table *ft, u8 match_criteria_enable, @@ -1119,8 +1092,23 @@ _mlx5_add_flow_rule(struct mlx5_flow_table *ft, goto unlock; } - rule = add_rule_to_auto_fg(ft, match_criteria_enable, match_criteria, - match_value, action, flow_tag, dest); + g = create_autogroup(ft, match_criteria_enable, match_criteria); + if (IS_ERR(g)) { + rule = (void *)g; + goto unlock; + } + + rule = add_rule_fg(g, match_value, + action, flow_tag, dest); + if (IS_ERR(rule)) { + /* Remove assumes refcount > 0 and autogroup creates a group + * with a refcount = 0. + */ + unlock_ref_node(&ft->node); + tree_get_node(&g->node); + tree_remove_node(&g->node); + return rule; + } unlock: unlock_ref_node(&ft->node); return rule; @@ -1288,7 +1276,7 @@ struct mlx5_flow_namespace *mlx5_get_flow_namespace(struct mlx5_core_dev *dev, { struct mlx5_flow_root_namespace *root_ns = dev->priv.root_ns; int prio; - static struct fs_prio *fs_prio; + struct fs_prio *fs_prio; struct mlx5_flow_namespace *ns; if (!root_ns) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 3f3b2fae4991..6892746fd10d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -966,7 +966,7 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv) int err; mutex_lock(&dev->intf_state_mutex); - if (dev->interface_state == MLX5_INTERFACE_STATE_UP) { + if (test_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state)) { dev_warn(&dev->pdev->dev, "%s: interface is up, NOP\n", __func__); goto out; @@ -1133,7 +1133,8 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv) if (err) pr_info("failed request module on %s\n", MLX5_IB_MOD); - dev->interface_state = MLX5_INTERFACE_STATE_UP; + clear_bit(MLX5_INTERFACE_STATE_DOWN, &dev->intf_state); + set_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state); out: mutex_unlock(&dev->intf_state_mutex); @@ -1207,7 +1208,7 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv) } mutex_lock(&dev->intf_state_mutex); - if (dev->interface_state == MLX5_INTERFACE_STATE_DOWN) { + if (test_bit(MLX5_INTERFACE_STATE_DOWN, &dev->intf_state)) { dev_warn(&dev->pdev->dev, "%s: interface is down, NOP\n", __func__); goto out; @@ -1241,7 +1242,8 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv) mlx5_cmd_cleanup(dev); out: - dev->interface_state = MLX5_INTERFACE_STATE_DOWN; + clear_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state); + set_bit(MLX5_INTERFACE_STATE_DOWN, &dev->intf_state); mutex_unlock(&dev->intf_state_mutex); return err; } @@ -1452,6 +1454,18 @@ static const struct pci_error_handlers mlx5_err_handler = { .resume = mlx5_pci_resume }; +static void shutdown(struct pci_dev *pdev) +{ + struct mlx5_core_dev *dev = pci_get_drvdata(pdev); + struct mlx5_priv *priv = &dev->priv; + + dev_info(&pdev->dev, "Shutdown was called\n"); + /* Notify mlx5 clients that the kernel is being shut down */ + set_bit(MLX5_INTERFACE_STATE_SHUTDOWN, &dev->intf_state); + mlx5_unload_one(dev, priv); + mlx5_pci_disable_device(dev); +} + static const struct pci_device_id mlx5_core_pci_table[] = { { PCI_VDEVICE(MELLANOX, 0x1011) }, /* Connect-IB */ { PCI_VDEVICE(MELLANOX, 0x1012), MLX5_PCI_DEV_IS_VF}, /* Connect-IB VF */ @@ -1459,6 +1473,8 @@ static const struct pci_device_id mlx5_core_pci_table[] = { { PCI_VDEVICE(MELLANOX, 0x1014), MLX5_PCI_DEV_IS_VF}, /* ConnectX-4 VF */ { PCI_VDEVICE(MELLANOX, 0x1015) }, /* ConnectX-4LX */ { PCI_VDEVICE(MELLANOX, 0x1016), MLX5_PCI_DEV_IS_VF}, /* ConnectX-4LX VF */ + { PCI_VDEVICE(MELLANOX, 0x1017) }, /* ConnectX-5 */ + { PCI_VDEVICE(MELLANOX, 0x1018), MLX5_PCI_DEV_IS_VF}, /* ConnectX-5 VF */ { 0, } }; @@ -1469,6 +1485,7 @@ static struct pci_driver mlx5_core_driver = { .id_table = mlx5_core_pci_table, .probe = init_one, .remove = remove_one, + .shutdown = shutdown, .err_handler = &mlx5_err_handler, .sriov_configure = mlx5_core_sriov_configure, }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c index ae378c575deb..53cc1e2c693b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c @@ -247,8 +247,8 @@ int mlx5_query_port_admin_status(struct mlx5_core_dev *dev, } EXPORT_SYMBOL_GPL(mlx5_query_port_admin_status); -static void mlx5_query_port_mtu(struct mlx5_core_dev *dev, int *admin_mtu, - int *max_mtu, int *oper_mtu, u8 port) +static void mlx5_query_port_mtu(struct mlx5_core_dev *dev, u16 *admin_mtu, + u16 *max_mtu, u16 *oper_mtu, u8 port) { u32 in[MLX5_ST_SZ_DW(pmtu_reg)]; u32 out[MLX5_ST_SZ_DW(pmtu_reg)]; @@ -268,7 +268,7 @@ static void mlx5_query_port_mtu(struct mlx5_core_dev *dev, int *admin_mtu, *admin_mtu = MLX5_GET(pmtu_reg, out, admin_mtu); } -int mlx5_set_port_mtu(struct mlx5_core_dev *dev, int mtu, u8 port) +int mlx5_set_port_mtu(struct mlx5_core_dev *dev, u16 mtu, u8 port) { u32 in[MLX5_ST_SZ_DW(pmtu_reg)]; u32 out[MLX5_ST_SZ_DW(pmtu_reg)]; @@ -283,14 +283,14 @@ int mlx5_set_port_mtu(struct mlx5_core_dev *dev, int mtu, u8 port) } EXPORT_SYMBOL_GPL(mlx5_set_port_mtu); -void mlx5_query_port_max_mtu(struct mlx5_core_dev *dev, int *max_mtu, +void mlx5_query_port_max_mtu(struct mlx5_core_dev *dev, u16 *max_mtu, u8 port) { mlx5_query_port_mtu(dev, NULL, max_mtu, NULL, port); } EXPORT_SYMBOL_GPL(mlx5_query_port_max_mtu); -void mlx5_query_port_oper_mtu(struct mlx5_core_dev *dev, int *oper_mtu, +void mlx5_query_port_oper_mtu(struct mlx5_core_dev *dev, u16 *oper_mtu, u8 port) { mlx5_query_port_mtu(dev, NULL, NULL, oper_mtu, port); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/uar.c b/drivers/net/ethernet/mellanox/mlx5/core/uar.c index 8ba080e441a1..5ff8af472bf5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/uar.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/uar.c @@ -269,8 +269,10 @@ EXPORT_SYMBOL(mlx5_alloc_map_uar); void mlx5_unmap_free_uar(struct mlx5_core_dev *mdev, struct mlx5_uar *uar) { - iounmap(uar->map); - iounmap(uar->bf_map); + if (uar->map) + iounmap(uar->map); + else + iounmap(uar->bf_map); mlx5_cmd_free_uar(mdev, uar->index); } EXPORT_SYMBOL(mlx5_unmap_free_uar); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c index bd518405859e..b69dadcfb897 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c @@ -196,6 +196,46 @@ int mlx5_modify_nic_vport_mac_address(struct mlx5_core_dev *mdev, } EXPORT_SYMBOL_GPL(mlx5_modify_nic_vport_mac_address); +int mlx5_query_nic_vport_mtu(struct mlx5_core_dev *mdev, u16 *mtu) +{ + int outlen = MLX5_ST_SZ_BYTES(query_nic_vport_context_out); + u32 *out; + int err; + + out = mlx5_vzalloc(outlen); + if (!out) + return -ENOMEM; + + err = mlx5_query_nic_vport_context(mdev, 0, out, outlen); + if (!err) + *mtu = MLX5_GET(query_nic_vport_context_out, out, + nic_vport_context.mtu); + + kvfree(out); + return err; +} +EXPORT_SYMBOL_GPL(mlx5_query_nic_vport_mtu); + +int mlx5_modify_nic_vport_mtu(struct mlx5_core_dev *mdev, u16 mtu) +{ + int inlen = MLX5_ST_SZ_BYTES(modify_nic_vport_context_in); + void *in; + int err; + + in = mlx5_vzalloc(inlen); + if (!in) + return -ENOMEM; + + MLX5_SET(modify_nic_vport_context_in, in, field_select.mtu, 1); + MLX5_SET(modify_nic_vport_context_in, in, nic_vport_context.mtu, mtu); + + err = mlx5_modify_nic_vport_context(mdev, in, inlen); + + kvfree(in); + return err; +} +EXPORT_SYMBOL_GPL(mlx5_modify_nic_vport_mtu); + int mlx5_query_nic_vport_mac_list(struct mlx5_core_dev *dev, u32 vport, enum mlx5_list_type list_type, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c index 9f10df25f3cd..f2fd1ef16da7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c @@ -95,21 +95,22 @@ struct mlx5e_vxlan *mlx5e_vxlan_lookup_port(struct mlx5e_priv *priv, u16 port) return vxlan; } -int mlx5e_vxlan_add_port(struct mlx5e_priv *priv, u16 port) +static void mlx5e_vxlan_add_port(struct work_struct *work) { + struct mlx5e_vxlan_work *vxlan_work = + container_of(work, struct mlx5e_vxlan_work, work); + struct mlx5e_priv *priv = vxlan_work->priv; struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan; + u16 port = vxlan_work->port; struct mlx5e_vxlan *vxlan; int err; - err = mlx5e_vxlan_core_add_port_cmd(priv->mdev, port); - if (err) - return err; + if (mlx5e_vxlan_core_add_port_cmd(priv->mdev, port)) + goto free_work; vxlan = kzalloc(sizeof(*vxlan), GFP_KERNEL); - if (!vxlan) { - err = -ENOMEM; + if (!vxlan) goto err_delete_port; - } vxlan->udp_port = port; @@ -119,13 +120,14 @@ int mlx5e_vxlan_add_port(struct mlx5e_priv *priv, u16 port) if (err) goto err_free; - return 0; + goto free_work; err_free: kfree(vxlan); err_delete_port: mlx5e_vxlan_core_del_port_cmd(priv->mdev, port); - return err; +free_work: + kfree(vxlan_work); } static void __mlx5e_vxlan_core_del_port(struct mlx5e_priv *priv, u16 port) @@ -145,12 +147,36 @@ static void __mlx5e_vxlan_core_del_port(struct mlx5e_priv *priv, u16 port) kfree(vxlan); } -void mlx5e_vxlan_del_port(struct mlx5e_priv *priv, u16 port) +static void mlx5e_vxlan_del_port(struct work_struct *work) { - if (!mlx5e_vxlan_lookup_port(priv, port)) - return; + struct mlx5e_vxlan_work *vxlan_work = + container_of(work, struct mlx5e_vxlan_work, work); + struct mlx5e_priv *priv = vxlan_work->priv; + u16 port = vxlan_work->port; __mlx5e_vxlan_core_del_port(priv, port); + + kfree(vxlan_work); +} + +void mlx5e_vxlan_queue_work(struct mlx5e_priv *priv, sa_family_t sa_family, + u16 port, int add) +{ + struct mlx5e_vxlan_work *vxlan_work; + + vxlan_work = kmalloc(sizeof(*vxlan_work), GFP_ATOMIC); + if (!vxlan_work) + return; + + if (add) + INIT_WORK(&vxlan_work->work, mlx5e_vxlan_add_port); + else + INIT_WORK(&vxlan_work->work, mlx5e_vxlan_del_port); + + vxlan_work->priv = priv; + vxlan_work->port = port; + vxlan_work->sa_family = sa_family; + queue_work(priv->wq, &vxlan_work->work); } void mlx5e_vxlan_cleanup(struct mlx5e_priv *priv) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h index a01685056ab1..129f3527aa14 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h @@ -39,6 +39,13 @@ struct mlx5e_vxlan { u16 udp_port; }; +struct mlx5e_vxlan_work { + struct work_struct work; + struct mlx5e_priv *priv; + sa_family_t sa_family; + u16 port; +}; + static inline bool mlx5e_vxlan_allowed(struct mlx5_core_dev *mdev) { return (MLX5_CAP_ETH(mdev, tunnel_stateless_vxlan) && @@ -46,8 +53,8 @@ static inline bool mlx5e_vxlan_allowed(struct mlx5_core_dev *mdev) } void mlx5e_vxlan_init(struct mlx5e_priv *priv); -int mlx5e_vxlan_add_port(struct mlx5e_priv *priv, u16 port); -void mlx5e_vxlan_del_port(struct mlx5e_priv *priv, u16 port); +void mlx5e_vxlan_queue_work(struct mlx5e_priv *priv, sa_family_t sa_family, + u16 port, int add); struct mlx5e_vxlan *mlx5e_vxlan_lookup_port(struct mlx5e_priv *priv, u16 port); void mlx5e_vxlan_cleanup(struct mlx5e_priv *priv); diff --git a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c index 270c9eeb7ab6..6d1a956e3f77 100644 --- a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c +++ b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c @@ -2668,9 +2668,9 @@ static int myri10ge_close(struct net_device *dev) del_timer_sync(&mgp->watchdog_timer); mgp->running = MYRI10GE_ETH_STOPPING; - local_bh_disable(); /* myri10ge_ss_lock_napi needs bh disabled */ for (i = 0; i < mgp->num_slices; i++) { napi_disable(&mgp->ss[i].napi); + local_bh_disable(); /* myri10ge_ss_lock_napi needs this */ /* Lock the slice to prevent the busy_poll handler from * accessing it. Later when we bring the NIC up, myri10ge_open * resets the slice including this lock. @@ -2679,8 +2679,8 @@ static int myri10ge_close(struct net_device *dev) pr_info("Slice %d locked\n", i); mdelay(1); } + local_bh_enable(); } - local_bh_enable(); netif_carrier_off(dev); netif_tx_stop_all_queues(dev); diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h index 55007f1e6bbc..caf6ddb7ea76 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h @@ -37,8 +37,8 @@ #define _QLCNIC_LINUX_MAJOR 5 #define _QLCNIC_LINUX_MINOR 3 -#define _QLCNIC_LINUX_SUBVERSION 63 -#define QLCNIC_LINUX_VERSIONID "5.3.63" +#define _QLCNIC_LINUX_SUBVERSION 64 +#define QLCNIC_LINUX_VERSIONID "5.3.64" #define QLCNIC_DRV_IDC_VER 0x01 #define QLCNIC_DRIVER_VERSION ((_QLCNIC_LINUX_MAJOR << 16) |\ (_QLCNIC_LINUX_MINOR << 8) | (_QLCNIC_LINUX_SUBVERSION)) diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c index 98d33d462c6c..1681084cc96f 100644 --- a/drivers/net/ethernet/sfc/ef10.c +++ b/drivers/net/ethernet/sfc/ef10.c @@ -1920,6 +1920,10 @@ static int efx_ef10_alloc_rss_context(struct efx_nic *efx, u32 *context, return 0; } + if (nic_data->datapath_caps & + 1 << MC_CMD_GET_CAPABILITIES_OUT_RX_RSS_LIMITED_LBN) + return -EOPNOTSUPP; + MCDI_SET_DWORD(inbuf, RSS_CONTEXT_ALLOC_IN_UPSTREAM_PORT_ID, nic_data->vport_id); MCDI_SET_DWORD(inbuf, RSS_CONTEXT_ALLOC_IN_TYPE, alloc_type); @@ -2923,9 +2927,16 @@ static void efx_ef10_filter_push_prep(struct efx_nic *efx, bool replacing) { struct efx_ef10_nic_data *nic_data = efx->nic_data; + u32 flags = spec->flags; memset(inbuf, 0, MC_CMD_FILTER_OP_IN_LEN); + /* Remove RSS flag if we don't have an RSS context. */ + if (flags & EFX_FILTER_FLAG_RX_RSS && + spec->rss_context == EFX_FILTER_RSS_CONTEXT_DEFAULT && + nic_data->rx_rss_context == EFX_EF10_RSS_CONTEXT_INVALID) + flags &= ~EFX_FILTER_FLAG_RX_RSS; + if (replacing) { MCDI_SET_DWORD(inbuf, FILTER_OP_IN_OP, MC_CMD_FILTER_OP_IN_OP_REPLACE); @@ -2985,10 +2996,10 @@ static void efx_ef10_filter_push_prep(struct efx_nic *efx, spec->dmaq_id == EFX_FILTER_RX_DMAQ_ID_DROP ? 0 : spec->dmaq_id); MCDI_SET_DWORD(inbuf, FILTER_OP_IN_RX_MODE, - (spec->flags & EFX_FILTER_FLAG_RX_RSS) ? + (flags & EFX_FILTER_FLAG_RX_RSS) ? MC_CMD_FILTER_OP_IN_RX_MODE_RSS : MC_CMD_FILTER_OP_IN_RX_MODE_SIMPLE); - if (spec->flags & EFX_FILTER_FLAG_RX_RSS) + if (flags & EFX_FILTER_FLAG_RX_RSS) MCDI_SET_DWORD(inbuf, FILTER_OP_IN_RX_CONTEXT, spec->rss_context != EFX_FILTER_RSS_CONTEXT_DEFAULT ? diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c index 44022b1845ce..afb90d129cb6 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c @@ -49,7 +49,6 @@ struct socfpga_dwmac { u32 reg_shift; struct device *dev; struct regmap *sys_mgr_base_addr; - struct reset_control *stmmac_rst; void __iomem *splitter_base; bool f2h_ptp_ref_clk; }; @@ -92,15 +91,6 @@ static int socfpga_dwmac_parse_data(struct socfpga_dwmac *dwmac, struct device * struct device_node *np_splitter; struct resource res_splitter; - dwmac->stmmac_rst = devm_reset_control_get(dev, - STMMAC_RESOURCE_NAME); - if (IS_ERR(dwmac->stmmac_rst)) { - dev_info(dev, "Could not get reset control!\n"); - if (PTR_ERR(dwmac->stmmac_rst) == -EPROBE_DEFER) - return -EPROBE_DEFER; - dwmac->stmmac_rst = NULL; - } - dwmac->interface = of_get_phy_mode(np); sys_mgr_base_addr = syscon_regmap_lookup_by_phandle(np, "altr,sysmgr-syscon"); @@ -194,30 +184,23 @@ static int socfpga_dwmac_setup(struct socfpga_dwmac *dwmac) return 0; } -static void socfpga_dwmac_exit(struct platform_device *pdev, void *priv) -{ - struct socfpga_dwmac *dwmac = priv; - - /* On socfpga platform exit, assert and hold reset to the - * enet controller - the default state after a hard reset. - */ - if (dwmac->stmmac_rst) - reset_control_assert(dwmac->stmmac_rst); -} - static int socfpga_dwmac_init(struct platform_device *pdev, void *priv) { - struct socfpga_dwmac *dwmac = priv; + struct socfpga_dwmac *dwmac = priv; struct net_device *ndev = platform_get_drvdata(pdev); struct stmmac_priv *stpriv = NULL; int ret = 0; - if (ndev) - stpriv = netdev_priv(ndev); + if (!ndev) + return -EINVAL; + + stpriv = netdev_priv(ndev); + if (!stpriv) + return -EINVAL; /* Assert reset to the enet controller before changing the phy mode */ - if (dwmac->stmmac_rst) - reset_control_assert(dwmac->stmmac_rst); + if (stpriv->stmmac_rst) + reset_control_assert(stpriv->stmmac_rst); /* Setup the phy mode in the system manager registers according to * devicetree configuration @@ -227,8 +210,8 @@ static int socfpga_dwmac_init(struct platform_device *pdev, void *priv) /* Deassert reset for the phy configuration to be sampled by * the enet controller, and operation to start in requested mode */ - if (dwmac->stmmac_rst) - reset_control_deassert(dwmac->stmmac_rst); + if (stpriv->stmmac_rst) + reset_control_deassert(stpriv->stmmac_rst); /* Before the enet controller is suspended, the phy is suspended. * This causes the phy clock to be gated. The enet controller is @@ -245,7 +228,7 @@ static int socfpga_dwmac_init(struct platform_device *pdev, void *priv) * control register 0, and can be modified by the phy driver * framework. */ - if (stpriv && stpriv->phydev) + if (stpriv->phydev) phy_resume(stpriv->phydev); return ret; @@ -285,14 +268,13 @@ static int socfpga_dwmac_probe(struct platform_device *pdev) plat_dat->bsp_priv = dwmac; plat_dat->init = socfpga_dwmac_init; - plat_dat->exit = socfpga_dwmac_exit; plat_dat->fix_mac_speed = socfpga_dwmac_fix_mac_speed; - ret = socfpga_dwmac_init(pdev, plat_dat->bsp_priv); - if (ret) - return ret; + ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); + if (!ret) + ret = socfpga_dwmac_init(pdev, dwmac); - return stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); + return ret; } static const struct of_device_id socfpga_dwmac_match[] = { diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index bbb77cd8ad67..e2fcdf1eec44 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -367,7 +367,6 @@ struct cpsw_priv { spinlock_t lock; struct platform_device *pdev; struct net_device *ndev; - struct device_node *phy_node; struct napi_struct napi_rx; struct napi_struct napi_tx; struct device *dev; @@ -1148,25 +1147,34 @@ static void cpsw_slave_open(struct cpsw_slave *slave, struct cpsw_priv *priv) cpsw_ale_add_mcast(priv->ale, priv->ndev->broadcast, 1 << slave_port, 0, 0, ALE_MCAST_FWD_2); - if (priv->phy_node) - slave->phy = of_phy_connect(priv->ndev, priv->phy_node, + if (slave->data->phy_node) { + slave->phy = of_phy_connect(priv->ndev, slave->data->phy_node, &cpsw_adjust_link, 0, slave->data->phy_if); - else + if (!slave->phy) { + dev_err(priv->dev, "phy \"%s\" not found on slave %d\n", + slave->data->phy_node->full_name, + slave->slave_num); + return; + } + } else { slave->phy = phy_connect(priv->ndev, slave->data->phy_id, &cpsw_adjust_link, slave->data->phy_if); - if (IS_ERR(slave->phy)) { - dev_err(priv->dev, "phy %s not found on slave %d\n", - slave->data->phy_id, slave->slave_num); - slave->phy = NULL; - } else { - phy_attached_info(slave->phy); + if (IS_ERR(slave->phy)) { + dev_err(priv->dev, + "phy \"%s\" not found on slave %d, err %ld\n", + slave->data->phy_id, slave->slave_num, + PTR_ERR(slave->phy)); + slave->phy = NULL; + return; + } + } - phy_start(slave->phy); + phy_attached_info(slave->phy); - /* Configure GMII_SEL register */ - cpsw_phy_sel(&priv->pdev->dev, slave->phy->interface, - slave->slave_num); - } + phy_start(slave->phy); + + /* Configure GMII_SEL register */ + cpsw_phy_sel(&priv->pdev->dev, slave->phy->interface, slave->slave_num); } static inline void cpsw_add_default_vlan(struct cpsw_priv *priv) @@ -1940,12 +1948,11 @@ static void cpsw_slave_init(struct cpsw_slave *slave, struct cpsw_priv *priv, slave->port_vlan = data->dual_emac_res_vlan; } -static int cpsw_probe_dt(struct cpsw_priv *priv, +static int cpsw_probe_dt(struct cpsw_platform_data *data, struct platform_device *pdev) { struct device_node *node = pdev->dev.of_node; struct device_node *slave_node; - struct cpsw_platform_data *data = &priv->data; int i = 0, ret; u32 prop; @@ -2033,25 +2040,21 @@ static int cpsw_probe_dt(struct cpsw_priv *priv, if (strcmp(slave_node->name, "slave")) continue; - priv->phy_node = of_parse_phandle(slave_node, "phy-handle", 0); + slave_data->phy_node = of_parse_phandle(slave_node, + "phy-handle", 0); parp = of_get_property(slave_node, "phy_id", &lenp); - if (of_phy_is_fixed_link(slave_node)) { - struct device_node *phy_node; - struct phy_device *phy_dev; - + if (slave_data->phy_node) { + dev_dbg(&pdev->dev, + "slave[%d] using phy-handle=\"%s\"\n", + i, slave_data->phy_node->full_name); + } else if (of_phy_is_fixed_link(slave_node)) { /* In the case of a fixed PHY, the DT node associated * to the PHY is the Ethernet MAC DT node. */ ret = of_phy_register_fixed_link(slave_node); if (ret) return ret; - phy_node = of_node_get(slave_node); - phy_dev = of_phy_find_device(phy_node); - if (!phy_dev) - return -ENODEV; - snprintf(slave_data->phy_id, sizeof(slave_data->phy_id), - PHY_ID_FMT, phy_dev->mdio.bus->id, - phy_dev->mdio.addr); + slave_data->phy_node = of_node_get(slave_node); } else if (parp) { u32 phyid; struct device_node *mdio_node; @@ -2072,7 +2075,9 @@ static int cpsw_probe_dt(struct cpsw_priv *priv, snprintf(slave_data->phy_id, sizeof(slave_data->phy_id), PHY_ID_FMT, mdio->name, phyid); } else { - dev_err(&pdev->dev, "No slave[%d] phy_id or fixed-link property\n", i); + dev_err(&pdev->dev, + "No slave[%d] phy_id, phy-handle, or fixed-link property\n", + i); goto no_phy_slave; } slave_data->phy_if = of_get_phy_mode(slave_node); @@ -2275,7 +2280,7 @@ static int cpsw_probe(struct platform_device *pdev) /* Select default pin state */ pinctrl_pm_select_default_state(&pdev->dev); - if (cpsw_probe_dt(priv, pdev)) { + if (cpsw_probe_dt(&priv->data, pdev)) { dev_err(&pdev->dev, "cpsw: platform data missing\n"); ret = -ENODEV; goto clean_runtime_disable_ret; diff --git a/drivers/net/ethernet/ti/cpsw.h b/drivers/net/ethernet/ti/cpsw.h index 442a7038e660..e50afd1b2eda 100644 --- a/drivers/net/ethernet/ti/cpsw.h +++ b/drivers/net/ethernet/ti/cpsw.h @@ -18,6 +18,7 @@ #include <linux/phy.h> struct cpsw_slave_data { + struct device_node *phy_node; char phy_id[MII_BUS_ID_SIZE]; int phy_if; u8 mac_addr[ETH_ALEN]; diff --git a/drivers/net/ethernet/ti/davinci_emac.c b/drivers/net/ethernet/ti/davinci_emac.c index 58d58f002559..f56d66e6ec15 100644 --- a/drivers/net/ethernet/ti/davinci_emac.c +++ b/drivers/net/ethernet/ti/davinci_emac.c @@ -1512,7 +1512,10 @@ static int emac_devioctl(struct net_device *ndev, struct ifreq *ifrq, int cmd) /* TODO: Add phy read and write and private statistics get feature */ - return phy_mii_ioctl(priv->phydev, ifrq, cmd); + if (priv->phydev) + return phy_mii_ioctl(priv->phydev, ifrq, cmd); + else + return -EOPNOTSUPP; } static int match_first_device(struct device *dev, void *data) diff --git a/drivers/net/ethernet/toshiba/ps3_gelic_wireless.c b/drivers/net/ethernet/toshiba/ps3_gelic_wireless.c index 13214a6492ac..743b18266a7c 100644 --- a/drivers/net/ethernet/toshiba/ps3_gelic_wireless.c +++ b/drivers/net/ethernet/toshiba/ps3_gelic_wireless.c @@ -1622,7 +1622,7 @@ static void gelic_wl_scan_complete_event(struct gelic_wl_info *wl) continue; /* copy hw scan info */ - memcpy(target->hwinfo, scan_info, scan_info->size); + memcpy(target->hwinfo, scan_info, be16_to_cpu(scan_info->size)); target->essid_len = strnlen(scan_info->essid, sizeof(scan_info->essid)); target->rate_len = 0; diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 84d3e5ca8817..c6385617bfb2 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -880,12 +880,12 @@ static struct sk_buff *macsec_decrypt(struct sk_buff *skb, macsec_skb_cb(skb)->valid = false; skb = skb_share_check(skb, GFP_ATOMIC); if (!skb) - return NULL; + return ERR_PTR(-ENOMEM); req = aead_request_alloc(rx_sa->key.tfm, GFP_ATOMIC); if (!req) { kfree_skb(skb); - return NULL; + return ERR_PTR(-ENOMEM); } hdr = (struct macsec_eth_header *)skb->data; @@ -905,7 +905,7 @@ static struct sk_buff *macsec_decrypt(struct sk_buff *skb, skb = skb_unshare(skb, GFP_ATOMIC); if (!skb) { aead_request_free(req); - return NULL; + return ERR_PTR(-ENOMEM); } } else { /* integrity only: all headers + data authenticated */ @@ -921,14 +921,14 @@ static struct sk_buff *macsec_decrypt(struct sk_buff *skb, dev_hold(dev); ret = crypto_aead_decrypt(req); if (ret == -EINPROGRESS) { - return NULL; + return ERR_PTR(ret); } else if (ret != 0) { /* decryption/authentication failed * 10.6 if validateFrames is disabled, deliver anyway */ if (ret != -EBADMSG) { kfree_skb(skb); - skb = NULL; + skb = ERR_PTR(ret); } } else { macsec_skb_cb(skb)->valid = true; @@ -1146,8 +1146,10 @@ static rx_handler_result_t macsec_handle_frame(struct sk_buff **pskb) secy->validate_frames != MACSEC_VALIDATE_DISABLED) skb = macsec_decrypt(skb, dev, rx_sa, sci, secy); - if (!skb) { - macsec_rxsa_put(rx_sa); + if (IS_ERR(skb)) { + /* the decrypt callback needs the reference */ + if (PTR_ERR(skb) != -EINPROGRESS) + macsec_rxsa_put(rx_sa); rcu_read_unlock(); *pskb = NULL; return RX_HANDLER_CONSUMED; @@ -1161,7 +1163,8 @@ deliver: macsec_extra_len(macsec_skb_cb(skb)->has_sci)); macsec_reset_skb(skb, secy->netdev); - macsec_rxsa_put(rx_sa); + if (rx_sa) + macsec_rxsa_put(rx_sa); count_rx(dev, skb->len); rcu_read_unlock(); @@ -1622,8 +1625,9 @@ static int macsec_add_rxsa(struct sk_buff *skb, struct genl_info *info) } rx_sa = kmalloc(sizeof(*rx_sa), GFP_KERNEL); - if (init_rx_sa(rx_sa, nla_data(tb_sa[MACSEC_SA_ATTR_KEY]), secy->key_len, - secy->icv_len)) { + if (!rx_sa || init_rx_sa(rx_sa, nla_data(tb_sa[MACSEC_SA_ATTR_KEY]), + secy->key_len, secy->icv_len)) { + kfree(rx_sa); rtnl_unlock(); return -ENOMEM; } @@ -1768,6 +1772,7 @@ static int macsec_add_txsa(struct sk_buff *skb, struct genl_info *info) tx_sa = kmalloc(sizeof(*tx_sa), GFP_KERNEL); if (!tx_sa || init_tx_sa(tx_sa, nla_data(tb_sa[MACSEC_SA_ATTR_KEY]), secy->key_len, secy->icv_len)) { + kfree(tx_sa); rtnl_unlock(); return -ENOMEM; } @@ -2227,7 +2232,8 @@ static int nla_put_secy(struct macsec_secy *secy, struct sk_buff *skb) return 1; if (nla_put_sci(skb, MACSEC_SECY_ATTR_SCI, secy->sci) || - nla_put_u64(skb, MACSEC_SECY_ATTR_CIPHER_SUITE, DEFAULT_CIPHER_ID) || + nla_put_u64(skb, MACSEC_SECY_ATTR_CIPHER_SUITE, + MACSEC_DEFAULT_CIPHER_ID) || nla_put_u8(skb, MACSEC_SECY_ATTR_ICV_LEN, secy->icv_len) || nla_put_u8(skb, MACSEC_SECY_ATTR_OPER, secy->operational) || nla_put_u8(skb, MACSEC_SECY_ATTR_PROTECT, secy->protect_frames) || @@ -2268,7 +2274,7 @@ static int dump_secy(struct macsec_secy *secy, struct net_device *dev, if (!hdr) return -EMSGSIZE; - rtnl_lock(); + genl_dump_check_consistent(cb, hdr, &macsec_fam); if (nla_put_u32(skb, MACSEC_ATTR_IFINDEX, dev->ifindex)) goto nla_put_failure; @@ -2429,18 +2435,17 @@ static int dump_secy(struct macsec_secy *secy, struct net_device *dev, nla_nest_end(skb, rxsc_list); - rtnl_unlock(); - genlmsg_end(skb, hdr); return 0; nla_put_failure: - rtnl_unlock(); genlmsg_cancel(skb, hdr); return -EMSGSIZE; } +static int macsec_generation = 1; /* protected by RTNL */ + static int macsec_dump_txsc(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); @@ -2450,6 +2455,10 @@ static int macsec_dump_txsc(struct sk_buff *skb, struct netlink_callback *cb) dev_idx = cb->args[0]; d = 0; + rtnl_lock(); + + cb->seq = macsec_generation; + for_each_netdev(net, dev) { struct macsec_secy *secy; @@ -2467,6 +2476,7 @@ next: } done: + rtnl_unlock(); cb->args[0] = d; return skb->len; } @@ -2920,10 +2930,14 @@ static void macsec_dellink(struct net_device *dev, struct list_head *head) struct net_device *real_dev = macsec->real_dev; struct macsec_rxh_data *rxd = macsec_data_rtnl(real_dev); + macsec_generation++; + unregister_netdevice_queue(dev, head); list_del_rcu(&macsec->secys); - if (list_empty(&rxd->secys)) + if (list_empty(&rxd->secys)) { netdev_rx_handler_unregister(real_dev); + kfree(rxd); + } macsec_del_dev(macsec); } @@ -2945,8 +2959,10 @@ static int register_macsec_dev(struct net_device *real_dev, err = netdev_rx_handler_register(real_dev, macsec_handle_frame, rxd); - if (err < 0) + if (err < 0) { + kfree(rxd); return err; + } } list_add_tail_rcu(&macsec->secys, &rxd->secys); @@ -3066,6 +3082,8 @@ static int macsec_newlink(struct net *net, struct net_device *dev, if (err < 0) goto del_dev; + macsec_generation++; + dev_hold(real_dev); return 0; @@ -3079,7 +3097,7 @@ unregister: static int macsec_validate_attr(struct nlattr *tb[], struct nlattr *data[]) { - u64 csid = DEFAULT_CIPHER_ID; + u64 csid = MACSEC_DEFAULT_CIPHER_ID; u8 icv_len = DEFAULT_ICV_LEN; int flag; bool es, scb, sci; @@ -3094,8 +3112,8 @@ static int macsec_validate_attr(struct nlattr *tb[], struct nlattr *data[]) icv_len = nla_get_u8(data[IFLA_MACSEC_ICV_LEN]); switch (csid) { - case DEFAULT_CIPHER_ID: - case DEFAULT_CIPHER_ALT: + case MACSEC_DEFAULT_CIPHER_ID: + case MACSEC_DEFAULT_CIPHER_ALT: if (icv_len < MACSEC_MIN_ICV_LEN || icv_len > MACSEC_MAX_ICV_LEN) return -EINVAL; @@ -3129,8 +3147,8 @@ static int macsec_validate_attr(struct nlattr *tb[], struct nlattr *data[]) nla_get_u8(data[IFLA_MACSEC_VALIDATION]) > MACSEC_VALIDATE_MAX) return -EINVAL; - if ((data[IFLA_MACSEC_PROTECT] && - nla_get_u8(data[IFLA_MACSEC_PROTECT])) && + if ((data[IFLA_MACSEC_REPLAY_PROTECT] && + nla_get_u8(data[IFLA_MACSEC_REPLAY_PROTECT])) && !data[IFLA_MACSEC_WINDOW]) return -EINVAL; @@ -3168,7 +3186,8 @@ static int macsec_fill_info(struct sk_buff *skb, if (nla_put_sci(skb, IFLA_MACSEC_SCI, secy->sci) || nla_put_u8(skb, IFLA_MACSEC_ICV_LEN, secy->icv_len) || - nla_put_u64(skb, IFLA_MACSEC_CIPHER_SUITE, DEFAULT_CIPHER_ID) || + nla_put_u64(skb, IFLA_MACSEC_CIPHER_SUITE, + MACSEC_DEFAULT_CIPHER_ID) || nla_put_u8(skb, IFLA_MACSEC_ENCODING_SA, tx_sc->encoding_sa) || nla_put_u8(skb, IFLA_MACSEC_ENCRYPT, tx_sc->encrypt) || nla_put_u8(skb, IFLA_MACSEC_PROTECT, secy->protect_frames) || diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c index b3ffaee30858..f279a897a5c7 100644 --- a/drivers/net/phy/at803x.c +++ b/drivers/net/phy/at803x.c @@ -359,27 +359,25 @@ static void at803x_link_change_notify(struct phy_device *phydev) * in the FIFO. In such cases, the FIFO enters an error mode it * cannot recover from by software. */ - if (phydev->drv->phy_id == ATH8030_PHY_ID) { - if (phydev->state == PHY_NOLINK) { - if (priv->gpiod_reset && !priv->phy_reset) { - struct at803x_context context; - - at803x_context_save(phydev, &context); - - gpiod_set_value(priv->gpiod_reset, 1); - msleep(1); - gpiod_set_value(priv->gpiod_reset, 0); - msleep(1); - - at803x_context_restore(phydev, &context); - - phydev_dbg(phydev, "%s(): phy was reset\n", - __func__); - priv->phy_reset = true; - } - } else { - priv->phy_reset = false; + if (phydev->state == PHY_NOLINK) { + if (priv->gpiod_reset && !priv->phy_reset) { + struct at803x_context context; + + at803x_context_save(phydev, &context); + + gpiod_set_value(priv->gpiod_reset, 1); + msleep(1); + gpiod_set_value(priv->gpiod_reset, 0); + msleep(1); + + at803x_context_restore(phydev, &context); + + phydev_dbg(phydev, "%s(): phy was reset\n", + __func__); + priv->phy_reset = true; } + } else { + priv->phy_reset = false; } } @@ -391,7 +389,6 @@ static struct phy_driver at803x_driver[] = { .phy_id_mask = 0xffffffef, .probe = at803x_probe, .config_init = at803x_config_init, - .link_change_notify = at803x_link_change_notify, .set_wol = at803x_set_wol, .get_wol = at803x_get_wol, .suspend = at803x_suspend, @@ -427,7 +424,6 @@ static struct phy_driver at803x_driver[] = { .phy_id_mask = 0xffffffef, .probe = at803x_probe, .config_init = at803x_config_init, - .link_change_notify = at803x_link_change_notify, .set_wol = at803x_set_wol, .get_wol = at803x_get_wol, .suspend = at803x_suspend, diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index f20890ee03f3..f64778ad9753 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -269,6 +269,7 @@ struct skb_data { /* skb->cb is one of these */ struct lan78xx_net *dev; enum skb_state state; size_t length; + int num_of_packet; }; struct usb_context { @@ -1803,7 +1804,34 @@ static void lan78xx_remove_mdio(struct lan78xx_net *dev) static void lan78xx_link_status_change(struct net_device *net) { - /* nothing to do */ + struct phy_device *phydev = net->phydev; + int ret, temp; + + /* At forced 100 F/H mode, chip may fail to set mode correctly + * when cable is switched between long(~50+m) and short one. + * As workaround, set to 10 before setting to 100 + * at forced 100 F/H mode. + */ + if (!phydev->autoneg && (phydev->speed == 100)) { + /* disable phy interrupt */ + temp = phy_read(phydev, LAN88XX_INT_MASK); + temp &= ~LAN88XX_INT_MASK_MDINTPIN_EN_; + ret = phy_write(phydev, LAN88XX_INT_MASK, temp); + + temp = phy_read(phydev, MII_BMCR); + temp &= ~(BMCR_SPEED100 | BMCR_SPEED1000); + phy_write(phydev, MII_BMCR, temp); /* set to 10 first */ + temp |= BMCR_SPEED100; + phy_write(phydev, MII_BMCR, temp); /* set to 100 later */ + + /* clear pending interrupt generated while workaround */ + temp = phy_read(phydev, LAN88XX_INT_STS); + + /* enable phy interrupt back */ + temp = phy_read(phydev, LAN88XX_INT_MASK); + temp |= LAN88XX_INT_MASK_MDINTPIN_EN_; + ret = phy_write(phydev, LAN88XX_INT_MASK, temp); + } } static int lan78xx_phy_init(struct lan78xx_net *dev) @@ -2464,7 +2492,7 @@ static void tx_complete(struct urb *urb) struct lan78xx_net *dev = entry->dev; if (urb->status == 0) { - dev->net->stats.tx_packets++; + dev->net->stats.tx_packets += entry->num_of_packet; dev->net->stats.tx_bytes += entry->length; } else { dev->net->stats.tx_errors++; @@ -2681,10 +2709,11 @@ void lan78xx_skb_return(struct lan78xx_net *dev, struct sk_buff *skb) return; } - skb->protocol = eth_type_trans(skb, dev->net); dev->net->stats.rx_packets++; dev->net->stats.rx_bytes += skb->len; + skb->protocol = eth_type_trans(skb, dev->net); + netif_dbg(dev, rx_status, dev->net, "< rx, len %zu, type 0x%x\n", skb->len + sizeof(struct ethhdr), skb->protocol); memset(skb->cb, 0, sizeof(struct skb_data)); @@ -2934,13 +2963,16 @@ static void lan78xx_tx_bh(struct lan78xx_net *dev) skb_totallen = 0; pkt_cnt = 0; + count = 0; + length = 0; for (skb = tqp->next; pkt_cnt < tqp->qlen; skb = skb->next) { if (skb_is_gso(skb)) { if (pkt_cnt) { /* handle previous packets first */ break; } - length = skb->len; + count = 1; + length = skb->len - TX_OVERHEAD; skb2 = skb_dequeue(tqp); goto gso_skb; } @@ -2961,14 +2993,13 @@ static void lan78xx_tx_bh(struct lan78xx_net *dev) for (count = pos = 0; count < pkt_cnt; count++) { skb2 = skb_dequeue(tqp); if (skb2) { + length += (skb2->len - TX_OVERHEAD); memcpy(skb->data + pos, skb2->data, skb2->len); pos += roundup(skb2->len, sizeof(u32)); dev_kfree_skb(skb2); } } - length = skb_totallen; - gso_skb: urb = usb_alloc_urb(0, GFP_ATOMIC); if (!urb) { @@ -2980,6 +3011,7 @@ gso_skb: entry->urb = urb; entry->dev = dev; entry->length = length; + entry->num_of_packet = count; spin_lock_irqsave(&dev->txq.lock, flags); ret = usb_autopm_get_interface_async(dev->intf); diff --git a/drivers/net/usb/pegasus.c b/drivers/net/usb/pegasus.c index f84080215915..82129eef7774 100644 --- a/drivers/net/usb/pegasus.c +++ b/drivers/net/usb/pegasus.c @@ -411,7 +411,7 @@ static int enable_net_traffic(struct net_device *dev, struct usb_device *usb) int ret; read_mii_word(pegasus, pegasus->phy, MII_LPA, &linkpart); - data[0] = 0xc9; + data[0] = 0xc8; /* TX & RX enable, append status, no CRC */ data[1] = 0; if (linkpart & (ADVERTISE_100FULL | ADVERTISE_10FULL)) data[1] |= 0x20; /* set full duplex */ @@ -497,7 +497,7 @@ static void read_bulk_callback(struct urb *urb) pkt_len = buf[count - 3] << 8; pkt_len += buf[count - 4]; pkt_len &= 0xfff; - pkt_len -= 8; + pkt_len -= 4; } /* @@ -528,7 +528,7 @@ static void read_bulk_callback(struct urb *urb) goon: usb_fill_bulk_urb(pegasus->rx_urb, pegasus->usb, usb_rcvbulkpipe(pegasus->usb, 1), - pegasus->rx_skb->data, PEGASUS_MTU + 8, + pegasus->rx_skb->data, PEGASUS_MTU, read_bulk_callback, pegasus); rx_status = usb_submit_urb(pegasus->rx_urb, GFP_ATOMIC); if (rx_status == -ENODEV) @@ -569,7 +569,7 @@ static void rx_fixup(unsigned long data) } usb_fill_bulk_urb(pegasus->rx_urb, pegasus->usb, usb_rcvbulkpipe(pegasus->usb, 1), - pegasus->rx_skb->data, PEGASUS_MTU + 8, + pegasus->rx_skb->data, PEGASUS_MTU, read_bulk_callback, pegasus); try_again: status = usb_submit_urb(pegasus->rx_urb, GFP_ATOMIC); @@ -823,7 +823,7 @@ static int pegasus_open(struct net_device *net) usb_fill_bulk_urb(pegasus->rx_urb, pegasus->usb, usb_rcvbulkpipe(pegasus->usb, 1), - pegasus->rx_skb->data, PEGASUS_MTU + 8, + pegasus->rx_skb->data, PEGASUS_MTU, read_bulk_callback, pegasus); if ((res = usb_submit_urb(pegasus->rx_urb, GFP_KERNEL))) { if (res == -ENODEV) diff --git a/drivers/net/usb/smsc75xx.c b/drivers/net/usb/smsc75xx.c index 30033dbe6662..c369db99c005 100644 --- a/drivers/net/usb/smsc75xx.c +++ b/drivers/net/usb/smsc75xx.c @@ -29,6 +29,7 @@ #include <linux/crc32.h> #include <linux/usb/usbnet.h> #include <linux/slab.h> +#include <linux/of_net.h> #include "smsc75xx.h" #define SMSC_CHIPNAME "smsc75xx" @@ -761,6 +762,15 @@ static int smsc75xx_ioctl(struct net_device *netdev, struct ifreq *rq, int cmd) static void smsc75xx_init_mac_address(struct usbnet *dev) { + const u8 *mac_addr; + + /* maybe the boot loader passed the MAC address in devicetree */ + mac_addr = of_get_mac_address(dev->udev->dev.of_node); + if (mac_addr) { + memcpy(dev->net->dev_addr, mac_addr, ETH_ALEN); + return; + } + /* try reading mac address from EEPROM */ if (smsc75xx_read_eeprom(dev, EEPROM_MAC_OFFSET, ETH_ALEN, dev->net->dev_addr) == 0) { @@ -772,7 +782,7 @@ static void smsc75xx_init_mac_address(struct usbnet *dev) } } - /* no eeprom, or eeprom values are invalid. generate random MAC */ + /* no useful static MAC address found. generate a random one */ eth_hw_addr_random(dev->net); netif_dbg(dev, ifup, dev->net, "MAC address set to eth_random_addr\n"); } diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c index 66b3ab9f614e..2edc2bc6d1b9 100644 --- a/drivers/net/usb/smsc95xx.c +++ b/drivers/net/usb/smsc95xx.c @@ -29,6 +29,7 @@ #include <linux/crc32.h> #include <linux/usb/usbnet.h> #include <linux/slab.h> +#include <linux/of_net.h> #include "smsc95xx.h" #define SMSC_CHIPNAME "smsc95xx" @@ -765,6 +766,15 @@ static int smsc95xx_ioctl(struct net_device *netdev, struct ifreq *rq, int cmd) static void smsc95xx_init_mac_address(struct usbnet *dev) { + const u8 *mac_addr; + + /* maybe the boot loader passed the MAC address in devicetree */ + mac_addr = of_get_mac_address(dev->udev->dev.of_node); + if (mac_addr) { + memcpy(dev->net->dev_addr, mac_addr, ETH_ALEN); + return; + } + /* try reading mac address from EEPROM */ if (smsc95xx_read_eeprom(dev, EEPROM_MAC_OFFSET, ETH_ALEN, dev->net->dev_addr) == 0) { @@ -775,7 +785,7 @@ static void smsc95xx_init_mac_address(struct usbnet *dev) } } - /* no eeprom, or eeprom values are invalid. generate random MAC */ + /* no useful static MAC address found. generate a random one */ eth_hw_addr_random(dev->net); netif_dbg(dev, ifup, dev->net, "MAC address set to eth_random_addr\n"); } diff --git a/drivers/net/wireless/ath/ath9k/ar5008_phy.c b/drivers/net/wireless/ath/ath9k/ar5008_phy.c index 8f8793004b9f..1b271b99c49e 100644 --- a/drivers/net/wireless/ath/ath9k/ar5008_phy.c +++ b/drivers/net/wireless/ath/ath9k/ar5008_phy.c @@ -274,6 +274,9 @@ void ar5008_hw_cmn_spur_mitigate(struct ath_hw *ah, }; static const int inc[4] = { 0, 100, 0, 0 }; + memset(&mask_m, 0, sizeof(int8_t) * 123); + memset(&mask_p, 0, sizeof(int8_t) * 123); + cur_bin = -6000; upper = bin + 100; lower = bin - 100; @@ -424,14 +427,9 @@ static void ar5008_hw_spur_mitigate(struct ath_hw *ah, int tmp, new; int i; - int8_t mask_m[123]; - int8_t mask_p[123]; int cur_bb_spur; bool is2GHz = IS_CHAN_2GHZ(chan); - memset(&mask_m, 0, sizeof(int8_t) * 123); - memset(&mask_p, 0, sizeof(int8_t) * 123); - for (i = 0; i < AR_EEPROM_MODAL_SPURS; i++) { cur_bb_spur = ah->eep_ops->get_spur_channel(ah, i, is2GHz); if (AR_NO_SPUR == cur_bb_spur) diff --git a/drivers/net/wireless/ath/ath9k/ar9002_phy.c b/drivers/net/wireless/ath/ath9k/ar9002_phy.c index db6624527d99..53d7445a5d12 100644 --- a/drivers/net/wireless/ath/ath9k/ar9002_phy.c +++ b/drivers/net/wireless/ath/ath9k/ar9002_phy.c @@ -178,14 +178,9 @@ static void ar9002_hw_spur_mitigate(struct ath_hw *ah, int i; struct chan_centers centers; - int8_t mask_m[123]; - int8_t mask_p[123]; int cur_bb_spur; bool is2GHz = IS_CHAN_2GHZ(chan); - memset(&mask_m, 0, sizeof(int8_t) * 123); - memset(&mask_p, 0, sizeof(int8_t) * 123); - ath9k_hw_get_channel_centers(ah, chan, ¢ers); freq = centers.synth_center; diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-8000.c b/drivers/net/wireless/intel/iwlwifi/iwl-8000.c index 97be104d1203..b5c57eebf995 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-8000.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-8000.c @@ -93,7 +93,7 @@ #define IWL8260_SMEM_OFFSET 0x400000 #define IWL8260_SMEM_LEN 0x68000 -#define IWL8000_FW_PRE "iwlwifi-8000" +#define IWL8000_FW_PRE "iwlwifi-8000C-" #define IWL8000_MODULE_FIRMWARE(api) \ IWL8000_FW_PRE "-" __stringify(api) ".ucode" diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c index f899666acb41..9e45bf9c6071 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c @@ -238,19 +238,6 @@ static int iwl_request_firmware(struct iwl_drv *drv, bool first) snprintf(drv->firmware_name, sizeof(drv->firmware_name), "%s%s.ucode", name_pre, tag); - /* - * Starting 8000B - FW name format has changed. This overwrites the - * previous name and uses the new format. - */ - if (drv->trans->cfg->device_family == IWL_DEVICE_FAMILY_8000) { - char rev_step = 'A' + CSR_HW_REV_STEP(drv->trans->hw_rev); - - if (rev_step != 'A') - snprintf(drv->firmware_name, - sizeof(drv->firmware_name), "%s%c-%s.ucode", - name_pre, rev_step, tag); - } - IWL_DEBUG_INFO(drv, "attempting to load firmware %s'%s'\n", (drv->fw_index == UCODE_EXPERIMENTAL_INDEX) ? "EXPERIMENTAL " : "", @@ -1060,11 +1047,18 @@ static int iwl_parse_tlv_firmware(struct iwl_drv *drv, return -EINVAL; } - if (WARN(fw_has_capa(capa, IWL_UCODE_TLV_CAPA_GSCAN_SUPPORT) && - !gscan_capa, - "GSCAN is supported but capabilities TLV is unavailable\n")) + /* + * If ucode advertises that it supports GSCAN but GSCAN + * capabilities TLV is not present, or if it has an old format, + * warn and continue without GSCAN. + */ + if (fw_has_capa(capa, IWL_UCODE_TLV_CAPA_GSCAN_SUPPORT) && + !gscan_capa) { + IWL_DEBUG_INFO(drv, + "GSCAN is supported but capabilities TLV is unavailable\n"); __clear_bit((__force long)IWL_UCODE_TLV_CAPA_GSCAN_SUPPORT, capa->_capa); + } return 0; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw-dbg.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw-dbg.c index 4856eac120f6..6938cd37be57 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/fw-dbg.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw-dbg.c @@ -526,7 +526,8 @@ void iwl_mvm_fw_error_dump(struct iwl_mvm *mvm) file_len += sizeof(*dump_data) + sizeof(*dump_mem) + sram2_len; /* Make room for fw's virtual image pages, if it exists */ - if (mvm->fw->img[mvm->cur_ucode].paging_mem_size) + if (mvm->fw->img[mvm->cur_ucode].paging_mem_size && + mvm->fw_paging_db[0].fw_paging_block) file_len += mvm->num_of_paging_blk * (sizeof(*dump_data) + sizeof(struct iwl_fw_error_dump_paging) + @@ -643,7 +644,8 @@ void iwl_mvm_fw_error_dump(struct iwl_mvm *mvm) } /* Dump fw's virtual image */ - if (mvm->fw->img[mvm->cur_ucode].paging_mem_size) { + if (mvm->fw->img[mvm->cur_ucode].paging_mem_size && + mvm->fw_paging_db[0].fw_paging_block) { for (i = 1; i < mvm->num_of_paging_blk + 1; i++) { struct iwl_fw_error_dump_paging *paging; struct page *pages = diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c index 594cd0dc7df9..09d895fafaf2 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c @@ -144,9 +144,11 @@ void iwl_free_fw_paging(struct iwl_mvm *mvm) __free_pages(mvm->fw_paging_db[i].fw_paging_block, get_order(mvm->fw_paging_db[i].fw_paging_size)); + mvm->fw_paging_db[i].fw_paging_block = NULL; } kfree(mvm->trans->paging_download_buf); mvm->trans->paging_download_buf = NULL; + mvm->trans->paging_db = NULL; memset(mvm->fw_paging_db, 0, sizeof(mvm->fw_paging_db)); } diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c index 05b968506836..79d7cd7d461e 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c @@ -479,8 +479,18 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x24F3, 0x0930, iwl8260_2ac_cfg)}, {IWL_PCI_DEVICE(0x24F3, 0x0000, iwl8265_2ac_cfg)}, {IWL_PCI_DEVICE(0x24FD, 0x0010, iwl8265_2ac_cfg)}, + {IWL_PCI_DEVICE(0x24FD, 0x0110, iwl8265_2ac_cfg)}, + {IWL_PCI_DEVICE(0x24FD, 0x1110, iwl8265_2ac_cfg)}, + {IWL_PCI_DEVICE(0x24FD, 0x1010, iwl8265_2ac_cfg)}, + {IWL_PCI_DEVICE(0x24FD, 0x0050, iwl8265_2ac_cfg)}, + {IWL_PCI_DEVICE(0x24FD, 0x0150, iwl8265_2ac_cfg)}, + {IWL_PCI_DEVICE(0x24FD, 0x9010, iwl8265_2ac_cfg)}, + {IWL_PCI_DEVICE(0x24FD, 0x8110, iwl8265_2ac_cfg)}, + {IWL_PCI_DEVICE(0x24FD, 0x8050, iwl8265_2ac_cfg)}, {IWL_PCI_DEVICE(0x24FD, 0x8010, iwl8265_2ac_cfg)}, {IWL_PCI_DEVICE(0x24FD, 0x0810, iwl8265_2ac_cfg)}, + {IWL_PCI_DEVICE(0x24FD, 0x9110, iwl8265_2ac_cfg)}, + {IWL_PCI_DEVICE(0x24FD, 0x8130, iwl8265_2ac_cfg)}, /* 9000 Series */ {IWL_PCI_DEVICE(0x9DF0, 0x2A10, iwl5165_2ac_cfg)}, diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index f798899338ed..5101f3ab4f29 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -397,10 +397,17 @@ static int nd_pfn_init(struct nd_pfn *nd_pfn) */ start += start_pad; npfns = (pmem->size - start_pad - end_trunc - SZ_8K) / SZ_4K; - if (nd_pfn->mode == PFN_MODE_PMEM) - offset = ALIGN(start + SZ_8K + 64 * npfns, nd_pfn->align) + if (nd_pfn->mode == PFN_MODE_PMEM) { + unsigned long memmap_size; + + /* + * vmemmap_populate_hugepages() allocates the memmap array in + * HPAGE_SIZE chunks. + */ + memmap_size = ALIGN(64 * npfns, HPAGE_SIZE); + offset = ALIGN(start + SZ_8K + memmap_size, nd_pfn->align) - start; - else if (nd_pfn->mode == PFN_MODE_RAM) + } else if (nd_pfn->mode == PFN_MODE_RAM) offset = ALIGN(start + SZ_8K, nd_pfn->align) - start; else goto err; diff --git a/drivers/nvmem/mxs-ocotp.c b/drivers/nvmem/mxs-ocotp.c index 8ba19bba3156..2bb3c5799ac4 100644 --- a/drivers/nvmem/mxs-ocotp.c +++ b/drivers/nvmem/mxs-ocotp.c @@ -94,7 +94,7 @@ static int mxs_ocotp_read(void *context, const void *reg, size_t reg_size, if (ret) goto close_banks; - while (val_size) { + while (val_size >= reg_size) { if ((offset < OCOTP_DATA_OFFSET) || (offset % 16)) { /* fill up non-data register */ *buf = 0; @@ -103,7 +103,7 @@ static int mxs_ocotp_read(void *context, const void *reg, size_t reg_size, } buf++; - val_size--; + val_size -= reg_size; offset += reg_size; } diff --git a/drivers/platform/x86/toshiba_acpi.c b/drivers/platform/x86/toshiba_acpi.c index df1f1a76a862..01e12d221a8b 100644 --- a/drivers/platform/x86/toshiba_acpi.c +++ b/drivers/platform/x86/toshiba_acpi.c @@ -135,7 +135,7 @@ MODULE_LICENSE("GPL"); /* Field definitions */ #define HCI_ACCEL_MASK 0x7fff #define HCI_HOTKEY_DISABLE 0x0b -#define HCI_HOTKEY_ENABLE 0x01 +#define HCI_HOTKEY_ENABLE 0x09 #define HCI_HOTKEY_SPECIAL_FUNCTIONS 0x10 #define HCI_LCD_BRIGHTNESS_BITS 3 #define HCI_LCD_BRIGHTNESS_SHIFT (16-HCI_LCD_BRIGHTNESS_BITS) diff --git a/drivers/rapidio/devices/rio_mport_cdev.c b/drivers/rapidio/devices/rio_mport_cdev.c index 5d4d91846357..e165b7ce29d7 100644 --- a/drivers/rapidio/devices/rio_mport_cdev.c +++ b/drivers/rapidio/devices/rio_mport_cdev.c @@ -126,7 +126,7 @@ struct rio_mport_mapping { struct list_head node; struct mport_dev *md; enum rio_mport_map_dir dir; - u32 rioid; + u16 rioid; u64 rio_addr; dma_addr_t phys_addr; /* for mmap */ void *virt_addr; /* kernel address, for dma_free_coherent */ @@ -137,7 +137,7 @@ struct rio_mport_mapping { struct rio_mport_dma_map { int valid; - uint64_t length; + u64 length; void *vaddr; dma_addr_t paddr; }; @@ -208,7 +208,7 @@ struct mport_cdev_priv { struct kfifo event_fifo; wait_queue_head_t event_rx_wait; spinlock_t fifo_lock; - unsigned int event_mask; /* RIO_DOORBELL, RIO_PORTWRITE */ + u32 event_mask; /* RIO_DOORBELL, RIO_PORTWRITE */ #ifdef CONFIG_RAPIDIO_DMA_ENGINE struct dma_chan *dmach; struct list_head async_list; @@ -276,7 +276,8 @@ static int rio_mport_maint_rd(struct mport_cdev_priv *priv, void __user *arg, return -EFAULT; if ((maint_io.offset % 4) || - (maint_io.length == 0) || (maint_io.length % 4)) + (maint_io.length == 0) || (maint_io.length % 4) || + (maint_io.length + maint_io.offset) > RIO_MAINT_SPACE_SZ) return -EINVAL; buffer = vmalloc(maint_io.length); @@ -298,7 +299,8 @@ static int rio_mport_maint_rd(struct mport_cdev_priv *priv, void __user *arg, offset += 4; } - if (unlikely(copy_to_user(maint_io.buffer, buffer, maint_io.length))) + if (unlikely(copy_to_user((void __user *)(uintptr_t)maint_io.buffer, + buffer, maint_io.length))) ret = -EFAULT; out: vfree(buffer); @@ -319,7 +321,8 @@ static int rio_mport_maint_wr(struct mport_cdev_priv *priv, void __user *arg, return -EFAULT; if ((maint_io.offset % 4) || - (maint_io.length == 0) || (maint_io.length % 4)) + (maint_io.length == 0) || (maint_io.length % 4) || + (maint_io.length + maint_io.offset) > RIO_MAINT_SPACE_SZ) return -EINVAL; buffer = vmalloc(maint_io.length); @@ -327,7 +330,8 @@ static int rio_mport_maint_wr(struct mport_cdev_priv *priv, void __user *arg, return -ENOMEM; length = maint_io.length; - if (unlikely(copy_from_user(buffer, maint_io.buffer, length))) { + if (unlikely(copy_from_user(buffer, + (void __user *)(uintptr_t)maint_io.buffer, length))) { ret = -EFAULT; goto out; } @@ -360,7 +364,7 @@ out: */ static int rio_mport_create_outbound_mapping(struct mport_dev *md, struct file *filp, - u32 rioid, u64 raddr, u32 size, + u16 rioid, u64 raddr, u32 size, dma_addr_t *paddr) { struct rio_mport *mport = md->mport; @@ -369,7 +373,7 @@ rio_mport_create_outbound_mapping(struct mport_dev *md, struct file *filp, rmcd_debug(OBW, "did=%d ra=0x%llx sz=0x%x", rioid, raddr, size); - map = kzalloc(sizeof(struct rio_mport_mapping), GFP_KERNEL); + map = kzalloc(sizeof(*map), GFP_KERNEL); if (map == NULL) return -ENOMEM; @@ -394,7 +398,7 @@ err_map_outb: static int rio_mport_get_outbound_mapping(struct mport_dev *md, struct file *filp, - u32 rioid, u64 raddr, u32 size, + u16 rioid, u64 raddr, u32 size, dma_addr_t *paddr) { struct rio_mport_mapping *map; @@ -433,7 +437,7 @@ static int rio_mport_obw_map(struct file *filp, void __user *arg) dma_addr_t paddr; int ret; - if (unlikely(copy_from_user(&map, arg, sizeof(struct rio_mmap)))) + if (unlikely(copy_from_user(&map, arg, sizeof(map)))) return -EFAULT; rmcd_debug(OBW, "did=%d ra=0x%llx sz=0x%llx", @@ -448,7 +452,7 @@ static int rio_mport_obw_map(struct file *filp, void __user *arg) map.handle = paddr; - if (unlikely(copy_to_user(arg, &map, sizeof(struct rio_mmap)))) + if (unlikely(copy_to_user(arg, &map, sizeof(map)))) return -EFAULT; return 0; } @@ -469,7 +473,7 @@ static int rio_mport_obw_free(struct file *filp, void __user *arg) if (!md->mport->ops->unmap_outb) return -EPROTONOSUPPORT; - if (copy_from_user(&handle, arg, sizeof(u64))) + if (copy_from_user(&handle, arg, sizeof(handle))) return -EFAULT; rmcd_debug(OBW, "h=0x%llx", handle); @@ -498,9 +502,9 @@ static int rio_mport_obw_free(struct file *filp, void __user *arg) static int maint_hdid_set(struct mport_cdev_priv *priv, void __user *arg) { struct mport_dev *md = priv->md; - uint16_t hdid; + u16 hdid; - if (copy_from_user(&hdid, arg, sizeof(uint16_t))) + if (copy_from_user(&hdid, arg, sizeof(hdid))) return -EFAULT; md->mport->host_deviceid = hdid; @@ -520,9 +524,9 @@ static int maint_hdid_set(struct mport_cdev_priv *priv, void __user *arg) static int maint_comptag_set(struct mport_cdev_priv *priv, void __user *arg) { struct mport_dev *md = priv->md; - uint32_t comptag; + u32 comptag; - if (copy_from_user(&comptag, arg, sizeof(uint32_t))) + if (copy_from_user(&comptag, arg, sizeof(comptag))) return -EFAULT; rio_local_write_config_32(md->mport, RIO_COMPONENT_TAG_CSR, comptag); @@ -837,7 +841,7 @@ err_out: * @xfer: data transfer descriptor structure */ static int -rio_dma_transfer(struct file *filp, uint32_t transfer_mode, +rio_dma_transfer(struct file *filp, u32 transfer_mode, enum rio_transfer_sync sync, enum dma_data_direction dir, struct rio_transfer_io *xfer) { @@ -875,7 +879,7 @@ rio_dma_transfer(struct file *filp, uint32_t transfer_mode, unsigned long offset; long pinned; - offset = (unsigned long)xfer->loc_addr & ~PAGE_MASK; + offset = (unsigned long)(uintptr_t)xfer->loc_addr & ~PAGE_MASK; nr_pages = PAGE_ALIGN(xfer->length + offset) >> PAGE_SHIFT; page_list = kmalloc_array(nr_pages, @@ -1015,19 +1019,20 @@ static int rio_mport_transfer_ioctl(struct file *filp, void __user *arg) if (unlikely(copy_from_user(&transaction, arg, sizeof(transaction)))) return -EFAULT; - if (transaction.count != 1) + if (transaction.count != 1) /* only single transfer for now */ return -EINVAL; if ((transaction.transfer_mode & priv->md->properties.transfer_mode) == 0) return -ENODEV; - transfer = vmalloc(transaction.count * sizeof(struct rio_transfer_io)); + transfer = vmalloc(transaction.count * sizeof(*transfer)); if (!transfer) return -ENOMEM; - if (unlikely(copy_from_user(transfer, transaction.block, - transaction.count * sizeof(struct rio_transfer_io)))) { + if (unlikely(copy_from_user(transfer, + (void __user *)(uintptr_t)transaction.block, + transaction.count * sizeof(*transfer)))) { ret = -EFAULT; goto out_free; } @@ -1038,8 +1043,9 @@ static int rio_mport_transfer_ioctl(struct file *filp, void __user *arg) ret = rio_dma_transfer(filp, transaction.transfer_mode, transaction.sync, dir, &transfer[i]); - if (unlikely(copy_to_user(transaction.block, transfer, - transaction.count * sizeof(struct rio_transfer_io)))) + if (unlikely(copy_to_user((void __user *)(uintptr_t)transaction.block, + transfer, + transaction.count * sizeof(*transfer)))) ret = -EFAULT; out_free: @@ -1129,11 +1135,11 @@ err_tmo: } static int rio_mport_create_dma_mapping(struct mport_dev *md, struct file *filp, - uint64_t size, struct rio_mport_mapping **mapping) + u64 size, struct rio_mport_mapping **mapping) { struct rio_mport_mapping *map; - map = kzalloc(sizeof(struct rio_mport_mapping), GFP_KERNEL); + map = kzalloc(sizeof(*map), GFP_KERNEL); if (map == NULL) return -ENOMEM; @@ -1165,7 +1171,7 @@ static int rio_mport_alloc_dma(struct file *filp, void __user *arg) struct rio_mport_mapping *mapping = NULL; int ret; - if (unlikely(copy_from_user(&map, arg, sizeof(struct rio_dma_mem)))) + if (unlikely(copy_from_user(&map, arg, sizeof(map)))) return -EFAULT; ret = rio_mport_create_dma_mapping(md, filp, map.length, &mapping); @@ -1174,7 +1180,7 @@ static int rio_mport_alloc_dma(struct file *filp, void __user *arg) map.dma_handle = mapping->phys_addr; - if (unlikely(copy_to_user(arg, &map, sizeof(struct rio_dma_mem)))) { + if (unlikely(copy_to_user(arg, &map, sizeof(map)))) { mutex_lock(&md->buf_mutex); kref_put(&mapping->ref, mport_release_mapping); mutex_unlock(&md->buf_mutex); @@ -1192,7 +1198,7 @@ static int rio_mport_free_dma(struct file *filp, void __user *arg) int ret = -EFAULT; struct rio_mport_mapping *map, *_map; - if (copy_from_user(&handle, arg, sizeof(u64))) + if (copy_from_user(&handle, arg, sizeof(handle))) return -EFAULT; rmcd_debug(EXIT, "filp=%p", filp); @@ -1242,14 +1248,18 @@ static int rio_mport_free_dma(struct file *filp, void __user *arg) static int rio_mport_create_inbound_mapping(struct mport_dev *md, struct file *filp, - u64 raddr, u32 size, + u64 raddr, u64 size, struct rio_mport_mapping **mapping) { struct rio_mport *mport = md->mport; struct rio_mport_mapping *map; int ret; - map = kzalloc(sizeof(struct rio_mport_mapping), GFP_KERNEL); + /* rio_map_inb_region() accepts u32 size */ + if (size > 0xffffffff) + return -EINVAL; + + map = kzalloc(sizeof(*map), GFP_KERNEL); if (map == NULL) return -ENOMEM; @@ -1262,7 +1272,7 @@ rio_mport_create_inbound_mapping(struct mport_dev *md, struct file *filp, if (raddr == RIO_MAP_ANY_ADDR) raddr = map->phys_addr; - ret = rio_map_inb_region(mport, map->phys_addr, raddr, size, 0); + ret = rio_map_inb_region(mport, map->phys_addr, raddr, (u32)size, 0); if (ret < 0) goto err_map_inb; @@ -1288,7 +1298,7 @@ err_dma_alloc: static int rio_mport_get_inbound_mapping(struct mport_dev *md, struct file *filp, - u64 raddr, u32 size, + u64 raddr, u64 size, struct rio_mport_mapping **mapping) { struct rio_mport_mapping *map; @@ -1331,7 +1341,7 @@ static int rio_mport_map_inbound(struct file *filp, void __user *arg) if (!md->mport->ops->map_inb) return -EPROTONOSUPPORT; - if (unlikely(copy_from_user(&map, arg, sizeof(struct rio_mmap)))) + if (unlikely(copy_from_user(&map, arg, sizeof(map)))) return -EFAULT; rmcd_debug(IBW, "%s filp=%p", dev_name(&priv->md->dev), filp); @@ -1344,7 +1354,7 @@ static int rio_mport_map_inbound(struct file *filp, void __user *arg) map.handle = mapping->phys_addr; map.rio_addr = mapping->rio_addr; - if (unlikely(copy_to_user(arg, &map, sizeof(struct rio_mmap)))) { + if (unlikely(copy_to_user(arg, &map, sizeof(map)))) { /* Delete mapping if it was created by this request */ if (ret == 0 && mapping->filp == filp) { mutex_lock(&md->buf_mutex); @@ -1375,7 +1385,7 @@ static int rio_mport_inbound_free(struct file *filp, void __user *arg) if (!md->mport->ops->unmap_inb) return -EPROTONOSUPPORT; - if (copy_from_user(&handle, arg, sizeof(u64))) + if (copy_from_user(&handle, arg, sizeof(handle))) return -EFAULT; mutex_lock(&md->buf_mutex); @@ -1401,7 +1411,7 @@ static int rio_mport_inbound_free(struct file *filp, void __user *arg) static int maint_port_idx_get(struct mport_cdev_priv *priv, void __user *arg) { struct mport_dev *md = priv->md; - uint32_t port_idx = md->mport->index; + u32 port_idx = md->mport->index; rmcd_debug(MPORT, "port_index=%d", port_idx); @@ -1451,7 +1461,7 @@ static void rio_mport_doorbell_handler(struct rio_mport *mport, void *dev_id, handled = 0; spin_lock(&data->db_lock); list_for_each_entry(db_filter, &data->doorbells, data_node) { - if (((db_filter->filter.rioid == 0xffffffff || + if (((db_filter->filter.rioid == RIO_INVALID_DESTID || db_filter->filter.rioid == src)) && info >= db_filter->filter.low && info <= db_filter->filter.high) { @@ -1525,6 +1535,9 @@ static int rio_mport_remove_db_filter(struct mport_cdev_priv *priv, if (copy_from_user(&filter, arg, sizeof(filter))) return -EFAULT; + if (filter.low > filter.high) + return -EINVAL; + spin_lock_irqsave(&priv->md->db_lock, flags); list_for_each_entry(db_filter, &priv->db_filters, priv_node) { if (db_filter->filter.rioid == filter.rioid && @@ -1737,10 +1750,10 @@ static int rio_mport_add_riodev(struct mport_cdev_priv *priv, return -EEXIST; } - size = sizeof(struct rio_dev); + size = sizeof(*rdev); mport = md->mport; - destid = (u16)dev_info.destid; - hopcount = (u8)dev_info.hopcount; + destid = dev_info.destid; + hopcount = dev_info.hopcount; if (rio_mport_read_config_32(mport, destid, hopcount, RIO_PEF_CAR, &rval)) @@ -1872,8 +1885,8 @@ static int rio_mport_del_riodev(struct mport_cdev_priv *priv, void __user *arg) do { rdev = rio_get_comptag(dev_info.comptag, rdev); if (rdev && rdev->dev.parent == &mport->net->dev && - rdev->destid == (u16)dev_info.destid && - rdev->hopcount == (u8)dev_info.hopcount) + rdev->destid == dev_info.destid && + rdev->hopcount == dev_info.hopcount) break; } while (rdev); } @@ -2146,8 +2159,8 @@ static long mport_cdev_ioctl(struct file *filp, return maint_port_idx_get(data, (void __user *)arg); case RIO_MPORT_GET_PROPERTIES: md->properties.hdid = md->mport->host_deviceid; - if (copy_to_user((void __user *)arg, &(data->md->properties), - sizeof(data->md->properties))) + if (copy_to_user((void __user *)arg, &(md->properties), + sizeof(md->properties))) return -EFAULT; return 0; case RIO_ENABLE_DOORBELL_RANGE: @@ -2159,11 +2172,11 @@ static long mport_cdev_ioctl(struct file *filp, case RIO_DISABLE_PORTWRITE_RANGE: return rio_mport_remove_pw_filter(data, (void __user *)arg); case RIO_SET_EVENT_MASK: - data->event_mask = arg; + data->event_mask = (u32)arg; return 0; case RIO_GET_EVENT_MASK: if (copy_to_user((void __user *)arg, &data->event_mask, - sizeof(data->event_mask))) + sizeof(u32))) return -EFAULT; return 0; case RIO_MAP_OUTBOUND: @@ -2374,7 +2387,7 @@ static ssize_t mport_write(struct file *filp, const char __user *buf, return -EINVAL; ret = rio_mport_send_doorbell(mport, - (u16)event.u.doorbell.rioid, + event.u.doorbell.rioid, event.u.doorbell.payload); if (ret < 0) return ret; @@ -2421,7 +2434,7 @@ static struct mport_dev *mport_cdev_add(struct rio_mport *mport) struct mport_dev *md; struct rio_mport_attr attr; - md = kzalloc(sizeof(struct mport_dev), GFP_KERNEL); + md = kzalloc(sizeof(*md), GFP_KERNEL); if (!md) { rmcd_error("Unable allocate a device object"); return NULL; @@ -2470,7 +2483,7 @@ static struct mport_dev *mport_cdev_add(struct rio_mport *mport) /* The transfer_mode property will be returned through mport query * interface */ -#ifdef CONFIG_PPC /* for now: only on Freescale's SoCs */ +#ifdef CONFIG_FSL_RIO /* for now: only on Freescale's SoCs */ md->properties.transfer_mode |= RIO_TRANSFER_MODE_MAPPED; #else md->properties.transfer_mode |= RIO_TRANSFER_MODE_TRANSFER; @@ -2669,9 +2682,9 @@ static int __init mport_init(void) /* Create device class needed by udev */ dev_class = class_create(THIS_MODULE, DRV_NAME); - if (!dev_class) { + if (IS_ERR(dev_class)) { rmcd_error("Unable to create " DRV_NAME " class"); - return -EINVAL; + return PTR_ERR(dev_class); } ret = alloc_chrdev_region(&dev_number, 0, RIO_MAX_MPORTS, DRV_NAME); diff --git a/drivers/s390/char/sclp_ctl.c b/drivers/s390/char/sclp_ctl.c index 648cb86afd42..ea607a4a1bdd 100644 --- a/drivers/s390/char/sclp_ctl.c +++ b/drivers/s390/char/sclp_ctl.c @@ -56,6 +56,7 @@ static int sclp_ctl_ioctl_sccb(void __user *user_area) { struct sclp_ctl_sccb ctl_sccb; struct sccb_header *sccb; + unsigned long copied; int rc; if (copy_from_user(&ctl_sccb, user_area, sizeof(ctl_sccb))) @@ -65,14 +66,15 @@ static int sclp_ctl_ioctl_sccb(void __user *user_area) sccb = (void *) get_zeroed_page(GFP_KERNEL | GFP_DMA); if (!sccb) return -ENOMEM; - if (copy_from_user(sccb, u64_to_uptr(ctl_sccb.sccb), sizeof(*sccb))) { + copied = PAGE_SIZE - + copy_from_user(sccb, u64_to_uptr(ctl_sccb.sccb), PAGE_SIZE); + if (offsetof(struct sccb_header, length) + + sizeof(sccb->length) > copied || sccb->length > copied) { rc = -EFAULT; goto out_free; } - if (sccb->length > PAGE_SIZE || sccb->length < 8) - return -EINVAL; - if (copy_from_user(sccb, u64_to_uptr(ctl_sccb.sccb), sccb->length)) { - rc = -EFAULT; + if (sccb->length < 8) { + rc = -EINVAL; goto out_free; } rc = sclp_sync_request(ctl_sccb.cmdw, sccb); diff --git a/drivers/scsi/cxgbi/libcxgbi.c b/drivers/scsi/cxgbi/libcxgbi.c index f3bb7af4e984..ead83a24bcd1 100644 --- a/drivers/scsi/cxgbi/libcxgbi.c +++ b/drivers/scsi/cxgbi/libcxgbi.c @@ -688,6 +688,7 @@ static struct rt6_info *find_route_ipv6(const struct in6_addr *saddr, { struct flowi6 fl; + memset(&fl, 0, sizeof(fl)); if (saddr) memcpy(&fl.saddr, saddr, sizeof(struct in6_addr)); if (daddr) diff --git a/drivers/soc/mediatek/mtk-scpsys.c b/drivers/soc/mediatek/mtk-scpsys.c index 57e781c71e67..837effe19907 100644 --- a/drivers/soc/mediatek/mtk-scpsys.c +++ b/drivers/soc/mediatek/mtk-scpsys.c @@ -491,13 +491,14 @@ static int scpsys_probe(struct platform_device *pdev) genpd->dev_ops.active_wakeup = scpsys_active_wakeup; /* - * With CONFIG_PM disabled turn on all domains to make the - * hardware usable. + * Initially turn on all domains to make the domains usable + * with !CONFIG_PM and to get the hardware in sync with the + * software. The unused domains will be switched off during + * late_init time. */ - if (!IS_ENABLED(CONFIG_PM)) - genpd->power_on(genpd); + genpd->power_on(genpd); - pm_genpd_init(genpd, NULL, true); + pm_genpd_init(genpd, NULL, false); } /* diff --git a/drivers/staging/media/davinci_vpfe/vpfe_video.c b/drivers/staging/media/davinci_vpfe/vpfe_video.c index b793c04028a3..be72a8e5f221 100644 --- a/drivers/staging/media/davinci_vpfe/vpfe_video.c +++ b/drivers/staging/media/davinci_vpfe/vpfe_video.c @@ -172,9 +172,11 @@ static int vpfe_prepare_pipeline(struct vpfe_video_device *video) static int vpfe_update_pipe_state(struct vpfe_video_device *video) { struct vpfe_pipeline *pipe = &video->pipe; + int ret; - if (vpfe_prepare_pipeline(video)) - return vpfe_prepare_pipeline(video); + ret = vpfe_prepare_pipeline(video); + if (ret) + return ret; /* * Find out if there is any input video @@ -182,9 +184,10 @@ static int vpfe_update_pipe_state(struct vpfe_video_device *video) */ if (pipe->input_num == 0) { pipe->state = VPFE_PIPELINE_STREAM_CONTINUOUS; - if (vpfe_update_current_ext_subdev(video)) { + ret = vpfe_update_current_ext_subdev(video); + if (ret) { pr_err("Invalid external subdev\n"); - return vpfe_update_current_ext_subdev(video); + return ret; } } else { pipe->state = VPFE_PIPELINE_STREAM_SINGLESHOT; @@ -667,6 +670,7 @@ static int vpfe_enum_fmt(struct file *file, void *priv, struct v4l2_subdev *subdev; struct v4l2_format format; struct media_pad *remote; + int ret; v4l2_dbg(1, debug, &vpfe_dev->v4l2_dev, "vpfe_enum_fmt\n"); @@ -695,10 +699,11 @@ static int vpfe_enum_fmt(struct file *file, void *priv, sd_fmt.pad = remote->index; sd_fmt.which = V4L2_SUBDEV_FORMAT_ACTIVE; /* get output format of remote subdev */ - if (v4l2_subdev_call(subdev, pad, get_fmt, NULL, &sd_fmt)) { + ret = v4l2_subdev_call(subdev, pad, get_fmt, NULL, &sd_fmt); + if (ret) { v4l2_err(&vpfe_dev->v4l2_dev, "invalid remote subdev for video node\n"); - return v4l2_subdev_call(subdev, pad, get_fmt, NULL, &sd_fmt); + return ret; } /* convert to pix format */ mbus.code = sd_fmt.format.code; @@ -725,6 +730,7 @@ static int vpfe_s_fmt(struct file *file, void *priv, struct vpfe_video_device *video = video_drvdata(file); struct vpfe_device *vpfe_dev = video->vpfe_dev; struct v4l2_format format; + int ret; v4l2_dbg(1, debug, &vpfe_dev->v4l2_dev, "vpfe_s_fmt\n"); /* If streaming is started, return error */ @@ -733,8 +739,9 @@ static int vpfe_s_fmt(struct file *file, void *priv, return -EBUSY; } /* get adjacent subdev's output pad format */ - if (__vpfe_video_get_format(video, &format)) - return __vpfe_video_get_format(video, &format); + ret = __vpfe_video_get_format(video, &format); + if (ret) + return ret; *fmt = format; video->fmt = *fmt; return 0; @@ -757,11 +764,13 @@ static int vpfe_try_fmt(struct file *file, void *priv, struct vpfe_video_device *video = video_drvdata(file); struct vpfe_device *vpfe_dev = video->vpfe_dev; struct v4l2_format format; + int ret; v4l2_dbg(1, debug, &vpfe_dev->v4l2_dev, "vpfe_try_fmt\n"); /* get adjacent subdev's output pad format */ - if (__vpfe_video_get_format(video, &format)) - return __vpfe_video_get_format(video, &format); + ret = __vpfe_video_get_format(video, &format); + if (ret) + return ret; *fmt = format; return 0; @@ -838,8 +847,9 @@ static int vpfe_s_input(struct file *file, void *priv, unsigned int index) v4l2_dbg(1, debug, &vpfe_dev->v4l2_dev, "vpfe_s_input\n"); - if (mutex_lock_interruptible(&video->lock)) - return mutex_lock_interruptible(&video->lock); + ret = mutex_lock_interruptible(&video->lock); + if (ret) + return ret; /* * If streaming is started return device busy * error @@ -940,8 +950,9 @@ static int vpfe_s_std(struct file *file, void *priv, v4l2_std_id std_id) v4l2_dbg(1, debug, &vpfe_dev->v4l2_dev, "vpfe_s_std\n"); /* Call decoder driver function to set the standard */ - if (mutex_lock_interruptible(&video->lock)) - return mutex_lock_interruptible(&video->lock); + ret = mutex_lock_interruptible(&video->lock); + if (ret) + return ret; sdinfo = video->current_ext_subdev; /* If streaming is started, return device busy error */ if (video->started) { @@ -1327,8 +1338,9 @@ static int vpfe_reqbufs(struct file *file, void *priv, return -EINVAL; } - if (mutex_lock_interruptible(&video->lock)) - return mutex_lock_interruptible(&video->lock); + ret = mutex_lock_interruptible(&video->lock); + if (ret) + return ret; if (video->io_usrs != 0) { v4l2_err(&vpfe_dev->v4l2_dev, "Only one IO user allowed\n"); @@ -1354,10 +1366,11 @@ static int vpfe_reqbufs(struct file *file, void *priv, q->buf_struct_size = sizeof(struct vpfe_cap_buffer); q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC; - if (vb2_queue_init(q)) { + ret = vb2_queue_init(q); + if (ret) { v4l2_err(&vpfe_dev->v4l2_dev, "vb2_queue_init() failed\n"); vb2_dma_contig_cleanup_ctx(vpfe_dev->pdev); - return vb2_queue_init(q); + return ret; } fh->io_allowed = 1; @@ -1533,8 +1546,9 @@ static int vpfe_streamoff(struct file *file, void *priv, return -EINVAL; } - if (mutex_lock_interruptible(&video->lock)) - return mutex_lock_interruptible(&video->lock); + ret = mutex_lock_interruptible(&video->lock); + if (ret) + return ret; vpfe_stop_capture(video); ret = vb2_streamoff(&video->buffer_queue, buf_type); diff --git a/drivers/staging/rdma/hfi1/TODO b/drivers/staging/rdma/hfi1/TODO index 05de0dad8762..4c6f1d7d2eaf 100644 --- a/drivers/staging/rdma/hfi1/TODO +++ b/drivers/staging/rdma/hfi1/TODO @@ -3,4 +3,4 @@ July, 2015 - Remove unneeded file entries in sysfs - Remove software processing of IB protocol and place in library for use by qib, ipath (if still present), hfi1, and eventually soft-roce - +- Replace incorrect uAPI diff --git a/drivers/staging/rdma/hfi1/file_ops.c b/drivers/staging/rdma/hfi1/file_ops.c index 8396dc5fb6c1..c1c5bf82addb 100644 --- a/drivers/staging/rdma/hfi1/file_ops.c +++ b/drivers/staging/rdma/hfi1/file_ops.c @@ -49,6 +49,8 @@ #include <linux/vmalloc.h> #include <linux/io.h> +#include <rdma/ib.h> + #include "hfi.h" #include "pio.h" #include "device.h" @@ -190,6 +192,10 @@ static ssize_t hfi1_file_write(struct file *fp, const char __user *data, int uctxt_required = 1; int must_be_root = 0; + /* FIXME: This interface cannot continue out of staging */ + if (WARN_ON_ONCE(!ib_safe_file_access(fp))) + return -EACCES; + if (count < sizeof(cmd)) { ret = -EINVAL; goto bail; @@ -791,15 +797,16 @@ static int hfi1_file_close(struct inode *inode, struct file *fp) spin_unlock_irqrestore(&dd->uctxt_lock, flags); dd->rcd[uctxt->ctxt] = NULL; + + hfi1_user_exp_rcv_free(fdata); + hfi1_clear_ctxt_pkey(dd, uctxt->ctxt); + uctxt->rcvwait_to = 0; uctxt->piowait_to = 0; uctxt->rcvnowait = 0; uctxt->pionowait = 0; uctxt->event_flags = 0; - hfi1_user_exp_rcv_free(fdata); - hfi1_clear_ctxt_pkey(dd, uctxt->ctxt); - hfi1_stats.sps_ctxts--; if (++dd->freectxts == dd->num_user_contexts) aspm_enable_all(dd); @@ -1127,27 +1134,13 @@ bail: static int user_init(struct file *fp) { - int ret; unsigned int rcvctrl_ops = 0; struct hfi1_filedata *fd = fp->private_data; struct hfi1_ctxtdata *uctxt = fd->uctxt; /* make sure that the context has already been setup */ - if (!test_bit(HFI1_CTXT_SETUP_DONE, &uctxt->event_flags)) { - ret = -EFAULT; - goto done; - } - - /* - * Subctxts don't need to initialize anything since master - * has done it. - */ - if (fd->subctxt) { - ret = wait_event_interruptible(uctxt->wait, !test_bit( - HFI1_CTXT_MASTER_UNINIT, - &uctxt->event_flags)); - goto expected; - } + if (!test_bit(HFI1_CTXT_SETUP_DONE, &uctxt->event_flags)) + return -EFAULT; /* initialize poll variables... */ uctxt->urgent = 0; @@ -1202,19 +1195,7 @@ static int user_init(struct file *fp) wake_up(&uctxt->wait); } -expected: - /* - * Expected receive has to be setup for all processes (including - * shared contexts). However, it has to be done after the master - * context has been fully configured as it depends on the - * eager/expected split of the RcvArray entries. - * Setting it up here ensures that the subcontexts will be waiting - * (due to the above wait_event_interruptible() until the master - * is setup. - */ - ret = hfi1_user_exp_rcv_init(fp); -done: - return ret; + return 0; } static int get_ctxt_info(struct file *fp, void __user *ubase, __u32 len) @@ -1261,7 +1242,7 @@ static int setup_ctxt(struct file *fp) int ret = 0; /* - * Context should be set up only once (including allocation and + * Context should be set up only once, including allocation and * programming of eager buffers. This is done if context sharing * is not requested or by the master process. */ @@ -1282,10 +1263,29 @@ static int setup_ctxt(struct file *fp) if (ret) goto done; } + } else { + ret = wait_event_interruptible(uctxt->wait, !test_bit( + HFI1_CTXT_MASTER_UNINIT, + &uctxt->event_flags)); + if (ret) + goto done; } + ret = hfi1_user_sdma_alloc_queues(uctxt, fp); if (ret) goto done; + /* + * Expected receive has to be setup for all processes (including + * shared contexts). However, it has to be done after the master + * context has been fully configured as it depends on the + * eager/expected split of the RcvArray entries. + * Setting it up here ensures that the subcontexts will be waiting + * (due to the above wait_event_interruptible() until the master + * is setup. + */ + ret = hfi1_user_exp_rcv_init(fp); + if (ret) + goto done; set_bit(HFI1_CTXT_SETUP_DONE, &uctxt->event_flags); done: @@ -1565,29 +1565,8 @@ static loff_t ui_lseek(struct file *filp, loff_t offset, int whence) { struct hfi1_devdata *dd = filp->private_data; - switch (whence) { - case SEEK_SET: - break; - case SEEK_CUR: - offset += filp->f_pos; - break; - case SEEK_END: - offset = ((dd->kregend - dd->kregbase) + DC8051_DATA_MEM_SIZE) - - offset; - break; - default: - return -EINVAL; - } - - if (offset < 0) - return -EINVAL; - - if (offset >= (dd->kregend - dd->kregbase) + DC8051_DATA_MEM_SIZE) - return -EINVAL; - - filp->f_pos = offset; - - return filp->f_pos; + return fixed_size_llseek(filp, offset, whence, + (dd->kregend - dd->kregbase) + DC8051_DATA_MEM_SIZE); } /* NOTE: assumes unsigned long is 8 bytes */ diff --git a/drivers/staging/rdma/hfi1/mmu_rb.c b/drivers/staging/rdma/hfi1/mmu_rb.c index c7ad0164ea9a..b3f0682a36c9 100644 --- a/drivers/staging/rdma/hfi1/mmu_rb.c +++ b/drivers/staging/rdma/hfi1/mmu_rb.c @@ -71,6 +71,7 @@ static inline void mmu_notifier_range_start(struct mmu_notifier *, struct mm_struct *, unsigned long, unsigned long); static void mmu_notifier_mem_invalidate(struct mmu_notifier *, + struct mm_struct *, unsigned long, unsigned long); static struct mmu_rb_node *__mmu_rb_search(struct mmu_rb_handler *, unsigned long, unsigned long); @@ -137,7 +138,7 @@ void hfi1_mmu_rb_unregister(struct rb_root *root) rbnode = rb_entry(node, struct mmu_rb_node, node); rb_erase(node, root); if (handler->ops->remove) - handler->ops->remove(root, rbnode, false); + handler->ops->remove(root, rbnode, NULL); } } @@ -176,7 +177,7 @@ unlock: return ret; } -/* Caller must host handler lock */ +/* Caller must hold handler lock */ static struct mmu_rb_node *__mmu_rb_search(struct mmu_rb_handler *handler, unsigned long addr, unsigned long len) @@ -200,15 +201,21 @@ static struct mmu_rb_node *__mmu_rb_search(struct mmu_rb_handler *handler, return node; } +/* Caller must *not* hold handler lock. */ static void __mmu_rb_remove(struct mmu_rb_handler *handler, - struct mmu_rb_node *node, bool arg) + struct mmu_rb_node *node, struct mm_struct *mm) { + unsigned long flags; + /* Validity of handler and node pointers has been checked by caller. */ hfi1_cdbg(MMU, "Removing node addr 0x%llx, len %u", node->addr, node->len); + spin_lock_irqsave(&handler->lock, flags); __mmu_int_rb_remove(node, handler->root); + spin_unlock_irqrestore(&handler->lock, flags); + if (handler->ops->remove) - handler->ops->remove(handler->root, node, arg); + handler->ops->remove(handler->root, node, mm); } struct mmu_rb_node *hfi1_mmu_rb_search(struct rb_root *root, unsigned long addr, @@ -231,14 +238,11 @@ struct mmu_rb_node *hfi1_mmu_rb_search(struct rb_root *root, unsigned long addr, void hfi1_mmu_rb_remove(struct rb_root *root, struct mmu_rb_node *node) { struct mmu_rb_handler *handler = find_mmu_handler(root); - unsigned long flags; if (!handler || !node) return; - spin_lock_irqsave(&handler->lock, flags); - __mmu_rb_remove(handler, node, false); - spin_unlock_irqrestore(&handler->lock, flags); + __mmu_rb_remove(handler, node, NULL); } static struct mmu_rb_handler *find_mmu_handler(struct rb_root *root) @@ -260,7 +264,7 @@ unlock: static inline void mmu_notifier_page(struct mmu_notifier *mn, struct mm_struct *mm, unsigned long addr) { - mmu_notifier_mem_invalidate(mn, addr, addr + PAGE_SIZE); + mmu_notifier_mem_invalidate(mn, mm, addr, addr + PAGE_SIZE); } static inline void mmu_notifier_range_start(struct mmu_notifier *mn, @@ -268,25 +272,31 @@ static inline void mmu_notifier_range_start(struct mmu_notifier *mn, unsigned long start, unsigned long end) { - mmu_notifier_mem_invalidate(mn, start, end); + mmu_notifier_mem_invalidate(mn, mm, start, end); } static void mmu_notifier_mem_invalidate(struct mmu_notifier *mn, + struct mm_struct *mm, unsigned long start, unsigned long end) { struct mmu_rb_handler *handler = container_of(mn, struct mmu_rb_handler, mn); struct rb_root *root = handler->root; - struct mmu_rb_node *node; + struct mmu_rb_node *node, *ptr = NULL; unsigned long flags; spin_lock_irqsave(&handler->lock, flags); - for (node = __mmu_int_rb_iter_first(root, start, end - 1); node; - node = __mmu_int_rb_iter_next(node, start, end - 1)) { + for (node = __mmu_int_rb_iter_first(root, start, end - 1); + node; node = ptr) { + /* Guard against node removal. */ + ptr = __mmu_int_rb_iter_next(node, start, end - 1); hfi1_cdbg(MMU, "Invalidating node addr 0x%llx, len %u", node->addr, node->len); - if (handler->ops->invalidate(root, node)) - __mmu_rb_remove(handler, node, true); + if (handler->ops->invalidate(root, node)) { + spin_unlock_irqrestore(&handler->lock, flags); + __mmu_rb_remove(handler, node, mm); + spin_lock_irqsave(&handler->lock, flags); + } } spin_unlock_irqrestore(&handler->lock, flags); } diff --git a/drivers/staging/rdma/hfi1/mmu_rb.h b/drivers/staging/rdma/hfi1/mmu_rb.h index f8523fdb8a18..19a306e83c7d 100644 --- a/drivers/staging/rdma/hfi1/mmu_rb.h +++ b/drivers/staging/rdma/hfi1/mmu_rb.h @@ -59,7 +59,8 @@ struct mmu_rb_node { struct mmu_rb_ops { bool (*filter)(struct mmu_rb_node *, unsigned long, unsigned long); int (*insert)(struct rb_root *, struct mmu_rb_node *); - void (*remove)(struct rb_root *, struct mmu_rb_node *, bool); + void (*remove)(struct rb_root *, struct mmu_rb_node *, + struct mm_struct *); int (*invalidate)(struct rb_root *, struct mmu_rb_node *); }; diff --git a/drivers/staging/rdma/hfi1/qp.c b/drivers/staging/rdma/hfi1/qp.c index 29a5ad28019b..dc9119e1b458 100644 --- a/drivers/staging/rdma/hfi1/qp.c +++ b/drivers/staging/rdma/hfi1/qp.c @@ -519,10 +519,12 @@ static void iowait_sdma_drained(struct iowait *wait) * do the flush work until that QP's * sdma work has finished. */ + spin_lock(&qp->s_lock); if (qp->s_flags & RVT_S_WAIT_DMA) { qp->s_flags &= ~RVT_S_WAIT_DMA; hfi1_schedule_send(qp); } + spin_unlock(&qp->s_lock); } /** diff --git a/drivers/staging/rdma/hfi1/user_exp_rcv.c b/drivers/staging/rdma/hfi1/user_exp_rcv.c index 0861e095df8d..8bd56d5c783d 100644 --- a/drivers/staging/rdma/hfi1/user_exp_rcv.c +++ b/drivers/staging/rdma/hfi1/user_exp_rcv.c @@ -87,7 +87,8 @@ static u32 find_phys_blocks(struct page **, unsigned, struct tid_pageset *); static int set_rcvarray_entry(struct file *, unsigned long, u32, struct tid_group *, struct page **, unsigned); static int mmu_rb_insert(struct rb_root *, struct mmu_rb_node *); -static void mmu_rb_remove(struct rb_root *, struct mmu_rb_node *, bool); +static void mmu_rb_remove(struct rb_root *, struct mmu_rb_node *, + struct mm_struct *); static int mmu_rb_invalidate(struct rb_root *, struct mmu_rb_node *); static int program_rcvarray(struct file *, unsigned long, struct tid_group *, struct tid_pageset *, unsigned, u16, struct page **, @@ -254,6 +255,8 @@ int hfi1_user_exp_rcv_free(struct hfi1_filedata *fd) struct hfi1_ctxtdata *uctxt = fd->uctxt; struct tid_group *grp, *gptr; + if (!test_bit(HFI1_CTXT_SETUP_DONE, &uctxt->event_flags)) + return 0; /* * The notifier would have been removed when the process'es mm * was freed. @@ -899,7 +902,7 @@ static int unprogram_rcvarray(struct file *fp, u32 tidinfo, if (!node || node->rcventry != (uctxt->expected_base + rcventry)) return -EBADF; if (HFI1_CAP_IS_USET(TID_UNMAP)) - mmu_rb_remove(&fd->tid_rb_root, &node->mmu, false); + mmu_rb_remove(&fd->tid_rb_root, &node->mmu, NULL); else hfi1_mmu_rb_remove(&fd->tid_rb_root, &node->mmu); @@ -965,7 +968,7 @@ static void unlock_exp_tids(struct hfi1_ctxtdata *uctxt, continue; if (HFI1_CAP_IS_USET(TID_UNMAP)) mmu_rb_remove(&fd->tid_rb_root, - &node->mmu, false); + &node->mmu, NULL); else hfi1_mmu_rb_remove(&fd->tid_rb_root, &node->mmu); @@ -1032,7 +1035,7 @@ static int mmu_rb_insert(struct rb_root *root, struct mmu_rb_node *node) } static void mmu_rb_remove(struct rb_root *root, struct mmu_rb_node *node, - bool notifier) + struct mm_struct *mm) { struct hfi1_filedata *fdata = container_of(root, struct hfi1_filedata, tid_rb_root); diff --git a/drivers/staging/rdma/hfi1/user_sdma.c b/drivers/staging/rdma/hfi1/user_sdma.c index ab6b6a42000f..d53a659548e0 100644 --- a/drivers/staging/rdma/hfi1/user_sdma.c +++ b/drivers/staging/rdma/hfi1/user_sdma.c @@ -278,7 +278,8 @@ static inline void pq_update(struct hfi1_user_sdma_pkt_q *); static void user_sdma_free_request(struct user_sdma_request *, bool); static int pin_vector_pages(struct user_sdma_request *, struct user_sdma_iovec *); -static void unpin_vector_pages(struct mm_struct *, struct page **, unsigned); +static void unpin_vector_pages(struct mm_struct *, struct page **, unsigned, + unsigned); static int check_header_template(struct user_sdma_request *, struct hfi1_pkt_header *, u32, u32); static int set_txreq_header(struct user_sdma_request *, @@ -299,7 +300,8 @@ static int defer_packet_queue( static void activate_packet_queue(struct iowait *, int); static bool sdma_rb_filter(struct mmu_rb_node *, unsigned long, unsigned long); static int sdma_rb_insert(struct rb_root *, struct mmu_rb_node *); -static void sdma_rb_remove(struct rb_root *, struct mmu_rb_node *, bool); +static void sdma_rb_remove(struct rb_root *, struct mmu_rb_node *, + struct mm_struct *); static int sdma_rb_invalidate(struct rb_root *, struct mmu_rb_node *); static struct mmu_rb_ops sdma_rb_ops = { @@ -1063,8 +1065,10 @@ static int pin_vector_pages(struct user_sdma_request *req, rb_node = hfi1_mmu_rb_search(&pq->sdma_rb_root, (unsigned long)iovec->iov.iov_base, iovec->iov.iov_len); - if (rb_node) + if (rb_node && !IS_ERR(rb_node)) node = container_of(rb_node, struct sdma_mmu_node, rb); + else + rb_node = NULL; if (!node) { node = kzalloc(sizeof(*node), GFP_KERNEL); @@ -1107,7 +1111,8 @@ retry: goto bail; } if (pinned != npages) { - unpin_vector_pages(current->mm, pages, pinned); + unpin_vector_pages(current->mm, pages, node->npages, + pinned); ret = -EFAULT; goto bail; } @@ -1147,9 +1152,9 @@ bail: } static void unpin_vector_pages(struct mm_struct *mm, struct page **pages, - unsigned npages) + unsigned start, unsigned npages) { - hfi1_release_user_pages(mm, pages, npages, 0); + hfi1_release_user_pages(mm, pages + start, npages, 0); kfree(pages); } @@ -1502,7 +1507,7 @@ static void user_sdma_free_request(struct user_sdma_request *req, bool unpin) &req->pq->sdma_rb_root, (unsigned long)req->iovs[i].iov.iov_base, req->iovs[i].iov.iov_len); - if (!mnode) + if (!mnode || IS_ERR(mnode)) continue; node = container_of(mnode, struct sdma_mmu_node, rb); @@ -1547,7 +1552,7 @@ static int sdma_rb_insert(struct rb_root *root, struct mmu_rb_node *mnode) } static void sdma_rb_remove(struct rb_root *root, struct mmu_rb_node *mnode, - bool notifier) + struct mm_struct *mm) { struct sdma_mmu_node *node = container_of(mnode, struct sdma_mmu_node, rb); @@ -1557,14 +1562,20 @@ static void sdma_rb_remove(struct rb_root *root, struct mmu_rb_node *mnode, node->pq->n_locked -= node->npages; spin_unlock(&node->pq->evict_lock); - unpin_vector_pages(notifier ? NULL : current->mm, node->pages, + /* + * If mm is set, we are being called by the MMU notifier and we + * should not pass a mm_struct to unpin_vector_page(). This is to + * prevent a deadlock when hfi1_release_user_pages() attempts to + * take the mmap_sem, which the MMU notifier has already taken. + */ + unpin_vector_pages(mm ? NULL : current->mm, node->pages, 0, node->npages); /* * If called by the MMU notifier, we have to adjust the pinned * page count ourselves. */ - if (notifier) - current->mm->pinned_vm -= node->npages; + if (mm) + mm->pinned_vm -= node->npages; kfree(node); } diff --git a/drivers/thermal/hisi_thermal.c b/drivers/thermal/hisi_thermal.c index 36d07295f8e3..5e820b541506 100644 --- a/drivers/thermal/hisi_thermal.c +++ b/drivers/thermal/hisi_thermal.c @@ -68,12 +68,12 @@ static inline int _step_to_temp(int step) * Every step equals (1 * 200) / 255 celsius, and finally * need convert to millicelsius. */ - return (HISI_TEMP_BASE + (step * 200 / 255)) * 1000; + return (HISI_TEMP_BASE * 1000 + (step * 200000 / 255)); } static inline long _temp_to_step(long temp) { - return ((temp / 1000 - HISI_TEMP_BASE) * 255 / 200); + return ((temp - HISI_TEMP_BASE * 1000) * 255) / 200000; } static long hisi_thermal_get_sensor_temp(struct hisi_thermal_data *data, diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c index f1db49625555..5133cd1e10b7 100644 --- a/drivers/thermal/thermal_core.c +++ b/drivers/thermal/thermal_core.c @@ -959,7 +959,7 @@ static DEVICE_ATTR(sustainable_power, S_IWUSR | S_IRUGO, sustainable_power_show, struct thermal_zone_device *tz = to_thermal_zone(dev); \ \ if (tz->tzp) \ - return sprintf(buf, "%u\n", tz->tzp->name); \ + return sprintf(buf, "%d\n", tz->tzp->name); \ else \ return -EIO; \ } \ diff --git a/drivers/tty/pty.c b/drivers/tty/pty.c index 0058d9fbf931..cf0dc51a2690 100644 --- a/drivers/tty/pty.c +++ b/drivers/tty/pty.c @@ -626,7 +626,7 @@ static int pty_unix98_ioctl(struct tty_struct *tty, */ static struct tty_struct *ptm_unix98_lookup(struct tty_driver *driver, - struct inode *ptm_inode, int idx) + struct file *file, int idx) { /* Master must be open via /dev/ptmx */ return ERR_PTR(-EIO); @@ -642,12 +642,12 @@ static struct tty_struct *ptm_unix98_lookup(struct tty_driver *driver, */ static struct tty_struct *pts_unix98_lookup(struct tty_driver *driver, - struct inode *pts_inode, int idx) + struct file *file, int idx) { struct tty_struct *tty; mutex_lock(&devpts_mutex); - tty = devpts_get_priv(pts_inode); + tty = devpts_get_priv(file->f_path.dentry); mutex_unlock(&devpts_mutex); /* Master must be open before slave */ if (!tty) @@ -722,7 +722,7 @@ static int ptmx_open(struct inode *inode, struct file *filp) { struct pts_fs_info *fsi; struct tty_struct *tty; - struct inode *slave_inode; + struct dentry *dentry; int retval; int index; @@ -769,14 +769,12 @@ static int ptmx_open(struct inode *inode, struct file *filp) tty_add_file(tty, filp); - slave_inode = devpts_pty_new(fsi, - MKDEV(UNIX98_PTY_SLAVE_MAJOR, index), index, - tty->link); - if (IS_ERR(slave_inode)) { - retval = PTR_ERR(slave_inode); + dentry = devpts_pty_new(fsi, index, tty->link); + if (IS_ERR(dentry)) { + retval = PTR_ERR(dentry); goto err_release; } - tty->link->driver_data = slave_inode; + tty->link->driver_data = dentry; retval = ptm_driver->ops->open(tty, filp); if (retval) diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index 9b04d72e752e..24d5491ef0da 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -1367,12 +1367,12 @@ static ssize_t tty_line_name(struct tty_driver *driver, int index, char *p) * Locking: tty_mutex must be held. If the tty is found, bump the tty kref. */ static struct tty_struct *tty_driver_lookup_tty(struct tty_driver *driver, - struct inode *inode, int idx) + struct file *file, int idx) { struct tty_struct *tty; if (driver->ops->lookup) - tty = driver->ops->lookup(driver, inode, idx); + tty = driver->ops->lookup(driver, file, idx); else tty = driver->ttys[idx]; @@ -2040,7 +2040,7 @@ static struct tty_struct *tty_open_by_driver(dev_t device, struct inode *inode, } /* check whether we're reopening an existing tty */ - tty = tty_driver_lookup_tty(driver, inode, index); + tty = tty_driver_lookup_tty(driver, filp, index); if (IS_ERR(tty)) { mutex_unlock(&tty_mutex); goto out; diff --git a/drivers/usb/core/port.c b/drivers/usb/core/port.c index 14718a9ffcfb..460c855be0d0 100644 --- a/drivers/usb/core/port.c +++ b/drivers/usb/core/port.c @@ -249,18 +249,12 @@ static int usb_port_runtime_suspend(struct device *dev) return retval; } - -static int usb_port_prepare(struct device *dev) -{ - return 1; -} #endif static const struct dev_pm_ops usb_port_pm_ops = { #ifdef CONFIG_PM .runtime_suspend = usb_port_runtime_suspend, .runtime_resume = usb_port_runtime_resume, - .prepare = usb_port_prepare, #endif }; diff --git a/drivers/usb/core/usb.c b/drivers/usb/core/usb.c index dcb85e3cd5a7..479187c32571 100644 --- a/drivers/usb/core/usb.c +++ b/drivers/usb/core/usb.c @@ -312,13 +312,7 @@ static int usb_dev_uevent(struct device *dev, struct kobj_uevent_env *env) static int usb_dev_prepare(struct device *dev) { - struct usb_device *udev = to_usb_device(dev); - - /* Return 0 if the current wakeup setting is wrong, otherwise 1 */ - if (udev->do_remote_wakeup != device_may_wakeup(dev)) - return 0; - - return 1; + return 0; /* Implement eventually? */ } static void usb_dev_complete(struct device *dev) diff --git a/drivers/usb/musb/jz4740.c b/drivers/usb/musb/jz4740.c index 5e5a8fa005f8..bc8889956d17 100644 --- a/drivers/usb/musb/jz4740.c +++ b/drivers/usb/musb/jz4740.c @@ -83,9 +83,9 @@ static int jz4740_musb_init(struct musb *musb) { usb_phy_generic_register(); musb->xceiv = usb_get_phy(USB_PHY_TYPE_USB2); - if (!musb->xceiv) { + if (IS_ERR(musb->xceiv)) { pr_err("HS UDC: no transceiver configured\n"); - return -ENODEV; + return PTR_ERR(musb->xceiv); } /* Silicon does not implement ConfigData register. diff --git a/drivers/usb/musb/musb_gadget.c b/drivers/usb/musb/musb_gadget.c index 87bd578799a8..152865b36522 100644 --- a/drivers/usb/musb/musb_gadget.c +++ b/drivers/usb/musb/musb_gadget.c @@ -1164,12 +1164,12 @@ static int musb_gadget_disable(struct usb_ep *ep) musb_writew(epio, MUSB_RXMAXP, 0); } - musb_ep->desc = NULL; - musb_ep->end_point.desc = NULL; - /* abort all pending DMA and requests */ nuke(musb_ep, -ESHUTDOWN); + musb_ep->desc = NULL; + musb_ep->end_point.desc = NULL; + schedule_work(&musb->irq_work); spin_unlock_irqrestore(&(musb->lock), flags); diff --git a/drivers/usb/musb/musb_host.c b/drivers/usb/musb/musb_host.c index 58487a473521..2f8ad7f1f482 100644 --- a/drivers/usb/musb/musb_host.c +++ b/drivers/usb/musb/musb_host.c @@ -2735,7 +2735,7 @@ static const struct hc_driver musb_hc_driver = { .description = "musb-hcd", .product_desc = "MUSB HDRC host driver", .hcd_priv_size = sizeof(struct musb *), - .flags = HCD_USB2 | HCD_MEMORY | HCD_BH, + .flags = HCD_USB2 | HCD_MEMORY, /* not using irq handler or reset hooks from usbcore, since * those must be shared with peripheral code for OTG configs diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c index dd47823bb014..7c9f25e9c422 100644 --- a/drivers/usb/serial/cp210x.c +++ b/drivers/usb/serial/cp210x.c @@ -109,6 +109,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x10C4, 0x826B) }, /* Cygnal Integrated Products, Inc., Fasttrax GPS demonstration module */ { USB_DEVICE(0x10C4, 0x8281) }, /* Nanotec Plug & Drive */ { USB_DEVICE(0x10C4, 0x8293) }, /* Telegesis ETRX2USB */ + { USB_DEVICE(0x10C4, 0x82F4) }, /* Starizona MicroTouch */ { USB_DEVICE(0x10C4, 0x82F9) }, /* Procyon AVS */ { USB_DEVICE(0x10C4, 0x8341) }, /* Siemens MC35PU GPRS Modem */ { USB_DEVICE(0x10C4, 0x8382) }, /* Cygnal Integrated Products, Inc. */ @@ -118,6 +119,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x10C4, 0x8418) }, /* IRZ Automation Teleport SG-10 GSM/GPRS Modem */ { USB_DEVICE(0x10C4, 0x846E) }, /* BEI USB Sensor Interface (VCP) */ { USB_DEVICE(0x10C4, 0x8477) }, /* Balluff RFID */ + { USB_DEVICE(0x10C4, 0x84B6) }, /* Starizona Hyperion */ { USB_DEVICE(0x10C4, 0x85EA) }, /* AC-Services IBUS-IF */ { USB_DEVICE(0x10C4, 0x85EB) }, /* AC-Services CIS-IBUS */ { USB_DEVICE(0x10C4, 0x85F8) }, /* Virtenio Preon32 */ @@ -141,6 +143,8 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x10C4, 0xF004) }, /* Elan Digital Systems USBcount50 */ { USB_DEVICE(0x10C5, 0xEA61) }, /* Silicon Labs MobiData GPRS USB Modem */ { USB_DEVICE(0x10CE, 0xEA6A) }, /* Silicon Labs MobiData GPRS USB Modem 100EU */ + { USB_DEVICE(0x12B8, 0xEC60) }, /* Link G4 ECU */ + { USB_DEVICE(0x12B8, 0xEC62) }, /* Link G4+ ECU */ { USB_DEVICE(0x13AD, 0x9999) }, /* Baltech card reader */ { USB_DEVICE(0x1555, 0x0004) }, /* Owen AC4 USB-RS485 Converter */ { USB_DEVICE(0x166A, 0x0201) }, /* Clipsal 5500PACA C-Bus Pascal Automation Controller */ diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index 5c802d47892c..ca6bfddaacad 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -1006,7 +1006,7 @@ struct virtqueue *vring_create_virtqueue( const char *name) { struct virtqueue *vq; - void *queue; + void *queue = NULL; dma_addr_t dma_addr; size_t queue_size_in_bytes; struct vring vring; diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c index 9781e0dd59d6..d46839f51e73 100644 --- a/drivers/xen/balloon.c +++ b/drivers/xen/balloon.c @@ -151,6 +151,8 @@ static DECLARE_WAIT_QUEUE_HEAD(balloon_wq); static void balloon_process(struct work_struct *work); static DECLARE_DELAYED_WORK(balloon_worker, balloon_process); +static void release_memory_resource(struct resource *resource); + /* When ballooning out (allocating memory to return to Xen) we don't really want the kernel to try too hard since that can trigger the oom killer. */ #define GFP_BALLOON \ @@ -267,6 +269,20 @@ static struct resource *additional_memory_resource(phys_addr_t size) return NULL; } +#ifdef CONFIG_SPARSEMEM + { + unsigned long limit = 1UL << (MAX_PHYSMEM_BITS - PAGE_SHIFT); + unsigned long pfn = res->start >> PAGE_SHIFT; + + if (pfn > limit) { + pr_err("New System RAM resource outside addressable RAM (%lu > %lu)\n", + pfn, limit); + release_memory_resource(res); + return NULL; + } + } +#endif + return res; } diff --git a/drivers/xen/evtchn.c b/drivers/xen/evtchn.c index 38272ad24551..f4edd6df3df2 100644 --- a/drivers/xen/evtchn.c +++ b/drivers/xen/evtchn.c @@ -316,7 +316,6 @@ static int evtchn_resize_ring(struct per_user_data *u) { unsigned int new_size; evtchn_port_t *new_ring, *old_ring; - unsigned int p, c; /* * Ensure the ring is large enough to capture all possible @@ -346,20 +345,17 @@ static int evtchn_resize_ring(struct per_user_data *u) /* * Copy the old ring contents to the new ring. * - * If the ring contents crosses the end of the current ring, - * it needs to be copied in two chunks. + * To take care of wrapping, a full ring, and the new index + * pointing into the second half, simply copy the old contents + * twice. * * +---------+ +------------------+ - * |34567 12| -> | 1234567 | - * +-----p-c-+ +------------------+ + * |34567 12| -> |34567 1234567 12| + * +-----p-c-+ +-------c------p---+ */ - p = evtchn_ring_offset(u, u->ring_prod); - c = evtchn_ring_offset(u, u->ring_cons); - if (p < c) { - memcpy(new_ring + c, u->ring + c, (u->ring_size - c) * sizeof(*u->ring)); - memcpy(new_ring + u->ring_size, u->ring, p * sizeof(*u->ring)); - } else - memcpy(new_ring + c, u->ring + c, (p - c) * sizeof(*u->ring)); + memcpy(new_ring, old_ring, u->ring_size * sizeof(*u->ring)); + memcpy(new_ring + u->ring_size, old_ring, + u->ring_size * sizeof(*u->ring)); u->ring = new_ring; u->ring_size = new_size; diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index b8b598740bbd..8bb3509099e8 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -1991,7 +1991,7 @@ struct inode_fs_paths *init_ipath(s32 total_bytes, struct btrfs_root *fs_root, ifp = kmalloc(sizeof(*ifp), GFP_NOFS); if (!ifp) { - kfree(fspath); + vfree(fspath); return ERR_PTR(-ENOMEM); } diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h index c0a2018761f9..4919aedb5fc1 100644 --- a/fs/btrfs/btrfs_inode.h +++ b/fs/btrfs/btrfs_inode.h @@ -196,6 +196,16 @@ struct btrfs_inode { struct list_head delayed_iput; long delayed_iput_count; + /* + * To avoid races between lockless (i_mutex not held) direct IO writes + * and concurrent fsync requests. Direct IO writes must acquire read + * access on this semaphore for creating an extent map and its + * corresponding ordered extent. The fast fsync path must acquire write + * access on this semaphore before it collects ordered extents and + * extent maps. + */ + struct rw_semaphore dio_sem; + struct inode vfs_inode; }; diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index ff61a41ac90b..658c39b70fba 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -743,8 +743,11 @@ out: static struct { struct list_head idle_ws; spinlock_t ws_lock; - int num_ws; - atomic_t alloc_ws; + /* Number of free workspaces */ + int free_ws; + /* Total number of allocated workspaces */ + atomic_t total_ws; + /* Waiters for a free workspace */ wait_queue_head_t ws_wait; } btrfs_comp_ws[BTRFS_COMPRESS_TYPES]; @@ -758,16 +761,34 @@ void __init btrfs_init_compress(void) int i; for (i = 0; i < BTRFS_COMPRESS_TYPES; i++) { + struct list_head *workspace; + INIT_LIST_HEAD(&btrfs_comp_ws[i].idle_ws); spin_lock_init(&btrfs_comp_ws[i].ws_lock); - atomic_set(&btrfs_comp_ws[i].alloc_ws, 0); + atomic_set(&btrfs_comp_ws[i].total_ws, 0); init_waitqueue_head(&btrfs_comp_ws[i].ws_wait); + + /* + * Preallocate one workspace for each compression type so + * we can guarantee forward progress in the worst case + */ + workspace = btrfs_compress_op[i]->alloc_workspace(); + if (IS_ERR(workspace)) { + printk(KERN_WARNING + "BTRFS: cannot preallocate compression workspace, will try later"); + } else { + atomic_set(&btrfs_comp_ws[i].total_ws, 1); + btrfs_comp_ws[i].free_ws = 1; + list_add(workspace, &btrfs_comp_ws[i].idle_ws); + } } } /* - * this finds an available workspace or allocates a new one - * ERR_PTR is returned if things go bad. + * This finds an available workspace or allocates a new one. + * If it's not possible to allocate a new one, waits until there's one. + * Preallocation makes a forward progress guarantees and we do not return + * errors. */ static struct list_head *find_workspace(int type) { @@ -777,36 +798,58 @@ static struct list_head *find_workspace(int type) struct list_head *idle_ws = &btrfs_comp_ws[idx].idle_ws; spinlock_t *ws_lock = &btrfs_comp_ws[idx].ws_lock; - atomic_t *alloc_ws = &btrfs_comp_ws[idx].alloc_ws; + atomic_t *total_ws = &btrfs_comp_ws[idx].total_ws; wait_queue_head_t *ws_wait = &btrfs_comp_ws[idx].ws_wait; - int *num_ws = &btrfs_comp_ws[idx].num_ws; + int *free_ws = &btrfs_comp_ws[idx].free_ws; again: spin_lock(ws_lock); if (!list_empty(idle_ws)) { workspace = idle_ws->next; list_del(workspace); - (*num_ws)--; + (*free_ws)--; spin_unlock(ws_lock); return workspace; } - if (atomic_read(alloc_ws) > cpus) { + if (atomic_read(total_ws) > cpus) { DEFINE_WAIT(wait); spin_unlock(ws_lock); prepare_to_wait(ws_wait, &wait, TASK_UNINTERRUPTIBLE); - if (atomic_read(alloc_ws) > cpus && !*num_ws) + if (atomic_read(total_ws) > cpus && !*free_ws) schedule(); finish_wait(ws_wait, &wait); goto again; } - atomic_inc(alloc_ws); + atomic_inc(total_ws); spin_unlock(ws_lock); workspace = btrfs_compress_op[idx]->alloc_workspace(); if (IS_ERR(workspace)) { - atomic_dec(alloc_ws); + atomic_dec(total_ws); wake_up(ws_wait); + + /* + * Do not return the error but go back to waiting. There's a + * workspace preallocated for each type and the compression + * time is bounded so we get to a workspace eventually. This + * makes our caller's life easier. + * + * To prevent silent and low-probability deadlocks (when the + * initial preallocation fails), check if there are any + * workspaces at all. + */ + if (atomic_read(total_ws) == 0) { + static DEFINE_RATELIMIT_STATE(_rs, + /* once per minute */ 60 * HZ, + /* no burst */ 1); + + if (__ratelimit(&_rs)) { + printk(KERN_WARNING + "no compression workspaces, low memory, retrying"); + } + } + goto again; } return workspace; } @@ -820,21 +863,21 @@ static void free_workspace(int type, struct list_head *workspace) int idx = type - 1; struct list_head *idle_ws = &btrfs_comp_ws[idx].idle_ws; spinlock_t *ws_lock = &btrfs_comp_ws[idx].ws_lock; - atomic_t *alloc_ws = &btrfs_comp_ws[idx].alloc_ws; + atomic_t *total_ws = &btrfs_comp_ws[idx].total_ws; wait_queue_head_t *ws_wait = &btrfs_comp_ws[idx].ws_wait; - int *num_ws = &btrfs_comp_ws[idx].num_ws; + int *free_ws = &btrfs_comp_ws[idx].free_ws; spin_lock(ws_lock); - if (*num_ws < num_online_cpus()) { + if (*free_ws < num_online_cpus()) { list_add(workspace, idle_ws); - (*num_ws)++; + (*free_ws)++; spin_unlock(ws_lock); goto wake; } spin_unlock(ws_lock); btrfs_compress_op[idx]->free_workspace(workspace); - atomic_dec(alloc_ws); + atomic_dec(total_ws); wake: /* * Make sure counter is updated before we wake up waiters. @@ -857,7 +900,7 @@ static void free_workspaces(void) workspace = btrfs_comp_ws[i].idle_ws.next; list_del(workspace); btrfs_compress_op[i]->free_workspace(workspace); - atomic_dec(&btrfs_comp_ws[i].alloc_ws); + atomic_dec(&btrfs_comp_ws[i].total_ws); } } } @@ -894,8 +937,6 @@ int btrfs_compress_pages(int type, struct address_space *mapping, int ret; workspace = find_workspace(type); - if (IS_ERR(workspace)) - return PTR_ERR(workspace); ret = btrfs_compress_op[type-1]->compress_pages(workspace, mapping, start, len, pages, @@ -930,8 +971,6 @@ static int btrfs_decompress_biovec(int type, struct page **pages_in, int ret; workspace = find_workspace(type); - if (IS_ERR(workspace)) - return PTR_ERR(workspace); ret = btrfs_compress_op[type-1]->decompress_biovec(workspace, pages_in, disk_start, @@ -952,8 +991,6 @@ int btrfs_decompress(int type, unsigned char *data_in, struct page *dest_page, int ret; workspace = find_workspace(type); - if (IS_ERR(workspace)) - return PTR_ERR(workspace); ret = btrfs_compress_op[type-1]->decompress(workspace, data_in, dest_page, start_byte, diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 4997f175b446..427c36b430a6 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -1011,7 +1011,7 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans, return ret; if (refs == 0) { ret = -EROFS; - btrfs_std_error(root->fs_info, ret, NULL); + btrfs_handle_fs_error(root->fs_info, ret, NULL); return ret; } } else { @@ -1928,7 +1928,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, child = read_node_slot(root, mid, 0); if (!child) { ret = -EROFS; - btrfs_std_error(root->fs_info, ret, NULL); + btrfs_handle_fs_error(root->fs_info, ret, NULL); goto enospc; } @@ -2031,7 +2031,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, */ if (!left) { ret = -EROFS; - btrfs_std_error(root->fs_info, ret, NULL); + btrfs_handle_fs_error(root->fs_info, ret, NULL); goto enospc; } wret = balance_node_right(trans, root, mid, left); diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 65e7a9fa881f..101c3cfd3f7c 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -33,6 +33,7 @@ #include <asm/kmap_types.h> #include <linux/pagemap.h> #include <linux/btrfs.h> +#include <linux/btrfs_tree.h> #include <linux/workqueue.h> #include <linux/security.h> #include <linux/sizes.h> @@ -64,98 +65,6 @@ struct btrfs_ordered_sum; #define BTRFS_COMPAT_EXTENT_TREE_V0 -/* holds pointers to all of the tree roots */ -#define BTRFS_ROOT_TREE_OBJECTID 1ULL - -/* stores information about which extents are in use, and reference counts */ -#define BTRFS_EXTENT_TREE_OBJECTID 2ULL - -/* - * chunk tree stores translations from logical -> physical block numbering - * the super block points to the chunk tree - */ -#define BTRFS_CHUNK_TREE_OBJECTID 3ULL - -/* - * stores information about which areas of a given device are in use. - * one per device. The tree of tree roots points to the device tree - */ -#define BTRFS_DEV_TREE_OBJECTID 4ULL - -/* one per subvolume, storing files and directories */ -#define BTRFS_FS_TREE_OBJECTID 5ULL - -/* directory objectid inside the root tree */ -#define BTRFS_ROOT_TREE_DIR_OBJECTID 6ULL - -/* holds checksums of all the data extents */ -#define BTRFS_CSUM_TREE_OBJECTID 7ULL - -/* holds quota configuration and tracking */ -#define BTRFS_QUOTA_TREE_OBJECTID 8ULL - -/* for storing items that use the BTRFS_UUID_KEY* types */ -#define BTRFS_UUID_TREE_OBJECTID 9ULL - -/* tracks free space in block groups. */ -#define BTRFS_FREE_SPACE_TREE_OBJECTID 10ULL - -/* device stats in the device tree */ -#define BTRFS_DEV_STATS_OBJECTID 0ULL - -/* for storing balance parameters in the root tree */ -#define BTRFS_BALANCE_OBJECTID -4ULL - -/* orhpan objectid for tracking unlinked/truncated files */ -#define BTRFS_ORPHAN_OBJECTID -5ULL - -/* does write ahead logging to speed up fsyncs */ -#define BTRFS_TREE_LOG_OBJECTID -6ULL -#define BTRFS_TREE_LOG_FIXUP_OBJECTID -7ULL - -/* for space balancing */ -#define BTRFS_TREE_RELOC_OBJECTID -8ULL -#define BTRFS_DATA_RELOC_TREE_OBJECTID -9ULL - -/* - * extent checksums all have this objectid - * this allows them to share the logging tree - * for fsyncs - */ -#define BTRFS_EXTENT_CSUM_OBJECTID -10ULL - -/* For storing free space cache */ -#define BTRFS_FREE_SPACE_OBJECTID -11ULL - -/* - * The inode number assigned to the special inode for storing - * free ino cache - */ -#define BTRFS_FREE_INO_OBJECTID -12ULL - -/* dummy objectid represents multiple objectids */ -#define BTRFS_MULTIPLE_OBJECTIDS -255ULL - -/* - * All files have objectids in this range. - */ -#define BTRFS_FIRST_FREE_OBJECTID 256ULL -#define BTRFS_LAST_FREE_OBJECTID -256ULL -#define BTRFS_FIRST_CHUNK_TREE_OBJECTID 256ULL - - -/* - * the device items go into the chunk tree. The key is in the form - * [ 1 BTRFS_DEV_ITEM_KEY device_id ] - */ -#define BTRFS_DEV_ITEMS_OBJECTID 1ULL - -#define BTRFS_BTREE_INODE_OBJECTID 1 - -#define BTRFS_EMPTY_SUBVOL_DIR_OBJECTID 2 - -#define BTRFS_DEV_REPLACE_DEVID 0ULL - /* * the max metadata block size. This limit is somewhat artificial, * but the memmove costs go through the roof for larger blocks. @@ -175,12 +84,6 @@ struct btrfs_ordered_sum; */ #define BTRFS_LINK_MAX 65535U -/* 32 bytes in various csum fields */ -#define BTRFS_CSUM_SIZE 32 - -/* csum types */ -#define BTRFS_CSUM_TYPE_CRC32 0 - static const int btrfs_csum_sizes[] = { 4 }; /* four bytes for CRC32 */ @@ -189,17 +92,6 @@ static const int btrfs_csum_sizes[] = { 4 }; /* specific to btrfs_map_block(), therefore not in include/linux/blk_types.h */ #define REQ_GET_READ_MIRRORS (1 << 30) -#define BTRFS_FT_UNKNOWN 0 -#define BTRFS_FT_REG_FILE 1 -#define BTRFS_FT_DIR 2 -#define BTRFS_FT_CHRDEV 3 -#define BTRFS_FT_BLKDEV 4 -#define BTRFS_FT_FIFO 5 -#define BTRFS_FT_SOCK 6 -#define BTRFS_FT_SYMLINK 7 -#define BTRFS_FT_XATTR 8 -#define BTRFS_FT_MAX 9 - /* ioprio of readahead is set to idle */ #define BTRFS_IOPRIO_READA (IOPRIO_PRIO_VALUE(IOPRIO_CLASS_IDLE, 0)) @@ -207,138 +99,10 @@ static const int btrfs_csum_sizes[] = { 4 }; #define BTRFS_MAX_EXTENT_SIZE SZ_128M -/* - * The key defines the order in the tree, and so it also defines (optimal) - * block layout. - * - * objectid corresponds to the inode number. - * - * type tells us things about the object, and is a kind of stream selector. - * so for a given inode, keys with type of 1 might refer to the inode data, - * type of 2 may point to file data in the btree and type == 3 may point to - * extents. - * - * offset is the starting byte offset for this key in the stream. - * - * btrfs_disk_key is in disk byte order. struct btrfs_key is always - * in cpu native order. Otherwise they are identical and their sizes - * should be the same (ie both packed) - */ -struct btrfs_disk_key { - __le64 objectid; - u8 type; - __le64 offset; -} __attribute__ ((__packed__)); - -struct btrfs_key { - u64 objectid; - u8 type; - u64 offset; -} __attribute__ ((__packed__)); - struct btrfs_mapping_tree { struct extent_map_tree map_tree; }; -struct btrfs_dev_item { - /* the internal btrfs device id */ - __le64 devid; - - /* size of the device */ - __le64 total_bytes; - - /* bytes used */ - __le64 bytes_used; - - /* optimal io alignment for this device */ - __le32 io_align; - - /* optimal io width for this device */ - __le32 io_width; - - /* minimal io size for this device */ - __le32 sector_size; - - /* type and info about this device */ - __le64 type; - - /* expected generation for this device */ - __le64 generation; - - /* - * starting byte of this partition on the device, - * to allow for stripe alignment in the future - */ - __le64 start_offset; - - /* grouping information for allocation decisions */ - __le32 dev_group; - - /* seek speed 0-100 where 100 is fastest */ - u8 seek_speed; - - /* bandwidth 0-100 where 100 is fastest */ - u8 bandwidth; - - /* btrfs generated uuid for this device */ - u8 uuid[BTRFS_UUID_SIZE]; - - /* uuid of FS who owns this device */ - u8 fsid[BTRFS_UUID_SIZE]; -} __attribute__ ((__packed__)); - -struct btrfs_stripe { - __le64 devid; - __le64 offset; - u8 dev_uuid[BTRFS_UUID_SIZE]; -} __attribute__ ((__packed__)); - -struct btrfs_chunk { - /* size of this chunk in bytes */ - __le64 length; - - /* objectid of the root referencing this chunk */ - __le64 owner; - - __le64 stripe_len; - __le64 type; - - /* optimal io alignment for this chunk */ - __le32 io_align; - - /* optimal io width for this chunk */ - __le32 io_width; - - /* minimal io size for this chunk */ - __le32 sector_size; - - /* 2^16 stripes is quite a lot, a second limit is the size of a single - * item in the btree - */ - __le16 num_stripes; - - /* sub stripes only matter for raid10 */ - __le16 sub_stripes; - struct btrfs_stripe stripe; - /* additional stripes go here */ -} __attribute__ ((__packed__)); - -#define BTRFS_FREE_SPACE_EXTENT 1 -#define BTRFS_FREE_SPACE_BITMAP 2 - -struct btrfs_free_space_entry { - __le64 offset; - __le64 bytes; - u8 type; -} __attribute__ ((__packed__)); - -struct btrfs_free_space_header { - struct btrfs_disk_key location; - __le64 generation; - __le64 num_entries; - __le64 num_bitmaps; -} __attribute__ ((__packed__)); - static inline unsigned long btrfs_chunk_item_size(int num_stripes) { BUG_ON(num_stripes == 0); @@ -346,9 +110,6 @@ static inline unsigned long btrfs_chunk_item_size(int num_stripes) sizeof(struct btrfs_stripe) * (num_stripes - 1); } -#define BTRFS_HEADER_FLAG_WRITTEN (1ULL << 0) -#define BTRFS_HEADER_FLAG_RELOC (1ULL << 1) - /* * File system states */ @@ -357,13 +118,6 @@ static inline unsigned long btrfs_chunk_item_size(int num_stripes) #define BTRFS_FS_STATE_TRANS_ABORTED 2 #define BTRFS_FS_STATE_DEV_REPLACING 3 -/* Super block flags */ -/* Errors detected */ -#define BTRFS_SUPER_FLAG_ERROR (1ULL << 2) - -#define BTRFS_SUPER_FLAG_SEEDING (1ULL << 32) -#define BTRFS_SUPER_FLAG_METADUMP (1ULL << 33) - #define BTRFS_BACKREF_REV_MAX 256 #define BTRFS_BACKREF_REV_SHIFT 56 #define BTRFS_BACKREF_REV_MASK (((u64)BTRFS_BACKREF_REV_MAX - 1) << \ @@ -410,7 +164,6 @@ struct btrfs_header { * room to translate 14 chunks with 3 stripes each. */ #define BTRFS_SYSTEM_CHUNK_ARRAY_SIZE 2048 -#define BTRFS_LABEL_SIZE 256 /* * just in case we somehow lose the roots and are not able to mount, @@ -507,31 +260,6 @@ struct btrfs_super_block { * Compat flags that we support. If any incompat flags are set other than the * ones specified below then we will fail to mount */ -#define BTRFS_FEATURE_COMPAT_RO_FREE_SPACE_TREE (1ULL << 0) - -#define BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF (1ULL << 0) -#define BTRFS_FEATURE_INCOMPAT_DEFAULT_SUBVOL (1ULL << 1) -#define BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS (1ULL << 2) -#define BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO (1ULL << 3) -/* - * some patches floated around with a second compression method - * lets save that incompat here for when they do get in - * Note we don't actually support it, we're just reserving the - * number - */ -#define BTRFS_FEATURE_INCOMPAT_COMPRESS_LZOv2 (1ULL << 4) - -/* - * older kernels tried to do bigger metadata blocks, but the - * code was pretty buggy. Lets not let them try anymore. - */ -#define BTRFS_FEATURE_INCOMPAT_BIG_METADATA (1ULL << 5) - -#define BTRFS_FEATURE_INCOMPAT_EXTENDED_IREF (1ULL << 6) -#define BTRFS_FEATURE_INCOMPAT_RAID56 (1ULL << 7) -#define BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA (1ULL << 8) -#define BTRFS_FEATURE_INCOMPAT_NO_HOLES (1ULL << 9) - #define BTRFS_FEATURE_COMPAT_SUPP 0ULL #define BTRFS_FEATURE_COMPAT_SAFE_SET 0ULL #define BTRFS_FEATURE_COMPAT_SAFE_CLEAR 0ULL @@ -624,357 +352,8 @@ struct btrfs_path { unsigned int need_commit_sem:1; unsigned int skip_release_on_error:1; }; - -/* - * items in the extent btree are used to record the objectid of the - * owner of the block and the number of references - */ - -struct btrfs_extent_item { - __le64 refs; - __le64 generation; - __le64 flags; -} __attribute__ ((__packed__)); - -struct btrfs_extent_item_v0 { - __le32 refs; -} __attribute__ ((__packed__)); - #define BTRFS_MAX_EXTENT_ITEM_SIZE(r) ((BTRFS_LEAF_DATA_SIZE(r) >> 4) - \ sizeof(struct btrfs_item)) - -#define BTRFS_EXTENT_FLAG_DATA (1ULL << 0) -#define BTRFS_EXTENT_FLAG_TREE_BLOCK (1ULL << 1) - -/* following flags only apply to tree blocks */ - -/* use full backrefs for extent pointers in the block */ -#define BTRFS_BLOCK_FLAG_FULL_BACKREF (1ULL << 8) - -/* - * this flag is only used internally by scrub and may be changed at any time - * it is only declared here to avoid collisions - */ -#define BTRFS_EXTENT_FLAG_SUPER (1ULL << 48) - -struct btrfs_tree_block_info { - struct btrfs_disk_key key; - u8 level; -} __attribute__ ((__packed__)); - -struct btrfs_extent_data_ref { - __le64 root; - __le64 objectid; - __le64 offset; - __le32 count; -} __attribute__ ((__packed__)); - -struct btrfs_shared_data_ref { - __le32 count; -} __attribute__ ((__packed__)); - -struct btrfs_extent_inline_ref { - u8 type; - __le64 offset; -} __attribute__ ((__packed__)); - -/* old style backrefs item */ -struct btrfs_extent_ref_v0 { - __le64 root; - __le64 generation; - __le64 objectid; - __le32 count; -} __attribute__ ((__packed__)); - - -/* dev extents record free space on individual devices. The owner - * field points back to the chunk allocation mapping tree that allocated - * the extent. The chunk tree uuid field is a way to double check the owner - */ -struct btrfs_dev_extent { - __le64 chunk_tree; - __le64 chunk_objectid; - __le64 chunk_offset; - __le64 length; - u8 chunk_tree_uuid[BTRFS_UUID_SIZE]; -} __attribute__ ((__packed__)); - -struct btrfs_inode_ref { - __le64 index; - __le16 name_len; - /* name goes here */ -} __attribute__ ((__packed__)); - -struct btrfs_inode_extref { - __le64 parent_objectid; - __le64 index; - __le16 name_len; - __u8 name[0]; - /* name goes here */ -} __attribute__ ((__packed__)); - -struct btrfs_timespec { - __le64 sec; - __le32 nsec; -} __attribute__ ((__packed__)); - -struct btrfs_inode_item { - /* nfs style generation number */ - __le64 generation; - /* transid that last touched this inode */ - __le64 transid; - __le64 size; - __le64 nbytes; - __le64 block_group; - __le32 nlink; - __le32 uid; - __le32 gid; - __le32 mode; - __le64 rdev; - __le64 flags; - - /* modification sequence number for NFS */ - __le64 sequence; - - /* - * a little future expansion, for more than this we can - * just grow the inode item and version it - */ - __le64 reserved[4]; - struct btrfs_timespec atime; - struct btrfs_timespec ctime; - struct btrfs_timespec mtime; - struct btrfs_timespec otime; -} __attribute__ ((__packed__)); - -struct btrfs_dir_log_item { - __le64 end; -} __attribute__ ((__packed__)); - -struct btrfs_dir_item { - struct btrfs_disk_key location; - __le64 transid; - __le16 data_len; - __le16 name_len; - u8 type; -} __attribute__ ((__packed__)); - -#define BTRFS_ROOT_SUBVOL_RDONLY (1ULL << 0) - -/* - * Internal in-memory flag that a subvolume has been marked for deletion but - * still visible as a directory - */ -#define BTRFS_ROOT_SUBVOL_DEAD (1ULL << 48) - -struct btrfs_root_item { - struct btrfs_inode_item inode; - __le64 generation; - __le64 root_dirid; - __le64 bytenr; - __le64 byte_limit; - __le64 bytes_used; - __le64 last_snapshot; - __le64 flags; - __le32 refs; - struct btrfs_disk_key drop_progress; - u8 drop_level; - u8 level; - - /* - * The following fields appear after subvol_uuids+subvol_times - * were introduced. - */ - - /* - * This generation number is used to test if the new fields are valid - * and up to date while reading the root item. Every time the root item - * is written out, the "generation" field is copied into this field. If - * anyone ever mounted the fs with an older kernel, we will have - * mismatching generation values here and thus must invalidate the - * new fields. See btrfs_update_root and btrfs_find_last_root for - * details. - * the offset of generation_v2 is also used as the start for the memset - * when invalidating the fields. - */ - __le64 generation_v2; - u8 uuid[BTRFS_UUID_SIZE]; - u8 parent_uuid[BTRFS_UUID_SIZE]; - u8 received_uuid[BTRFS_UUID_SIZE]; - __le64 ctransid; /* updated when an inode changes */ - __le64 otransid; /* trans when created */ - __le64 stransid; /* trans when sent. non-zero for received subvol */ - __le64 rtransid; /* trans when received. non-zero for received subvol */ - struct btrfs_timespec ctime; - struct btrfs_timespec otime; - struct btrfs_timespec stime; - struct btrfs_timespec rtime; - __le64 reserved[8]; /* for future */ -} __attribute__ ((__packed__)); - -/* - * this is used for both forward and backward root refs - */ -struct btrfs_root_ref { - __le64 dirid; - __le64 sequence; - __le16 name_len; -} __attribute__ ((__packed__)); - -struct btrfs_disk_balance_args { - /* - * profiles to operate on, single is denoted by - * BTRFS_AVAIL_ALLOC_BIT_SINGLE - */ - __le64 profiles; - - /* - * usage filter - * BTRFS_BALANCE_ARGS_USAGE with a single value means '0..N' - * BTRFS_BALANCE_ARGS_USAGE_RANGE - range syntax, min..max - */ - union { - __le64 usage; - struct { - __le32 usage_min; - __le32 usage_max; - }; - }; - - /* devid filter */ - __le64 devid; - - /* devid subset filter [pstart..pend) */ - __le64 pstart; - __le64 pend; - - /* btrfs virtual address space subset filter [vstart..vend) */ - __le64 vstart; - __le64 vend; - - /* - * profile to convert to, single is denoted by - * BTRFS_AVAIL_ALLOC_BIT_SINGLE - */ - __le64 target; - - /* BTRFS_BALANCE_ARGS_* */ - __le64 flags; - - /* - * BTRFS_BALANCE_ARGS_LIMIT with value 'limit' - * BTRFS_BALANCE_ARGS_LIMIT_RANGE - the extend version can use minimum - * and maximum - */ - union { - __le64 limit; - struct { - __le32 limit_min; - __le32 limit_max; - }; - }; - - /* - * Process chunks that cross stripes_min..stripes_max devices, - * BTRFS_BALANCE_ARGS_STRIPES_RANGE - */ - __le32 stripes_min; - __le32 stripes_max; - - __le64 unused[6]; -} __attribute__ ((__packed__)); - -/* - * store balance parameters to disk so that balance can be properly - * resumed after crash or unmount - */ -struct btrfs_balance_item { - /* BTRFS_BALANCE_* */ - __le64 flags; - - struct btrfs_disk_balance_args data; - struct btrfs_disk_balance_args meta; - struct btrfs_disk_balance_args sys; - - __le64 unused[4]; -} __attribute__ ((__packed__)); - -#define BTRFS_FILE_EXTENT_INLINE 0 -#define BTRFS_FILE_EXTENT_REG 1 -#define BTRFS_FILE_EXTENT_PREALLOC 2 - -struct btrfs_file_extent_item { - /* - * transaction id that created this extent - */ - __le64 generation; - /* - * max number of bytes to hold this extent in ram - * when we split a compressed extent we can't know how big - * each of the resulting pieces will be. So, this is - * an upper limit on the size of the extent in ram instead of - * an exact limit. - */ - __le64 ram_bytes; - - /* - * 32 bits for the various ways we might encode the data, - * including compression and encryption. If any of these - * are set to something a given disk format doesn't understand - * it is treated like an incompat flag for reading and writing, - * but not for stat. - */ - u8 compression; - u8 encryption; - __le16 other_encoding; /* spare for later use */ - - /* are we inline data or a real extent? */ - u8 type; - - /* - * disk space consumed by the extent, checksum blocks are included - * in these numbers - * - * At this offset in the structure, the inline extent data start. - */ - __le64 disk_bytenr; - __le64 disk_num_bytes; - /* - * the logical offset in file blocks (no csums) - * this extent record is for. This allows a file extent to point - * into the middle of an existing extent on disk, sharing it - * between two snapshots (useful if some bytes in the middle of the - * extent have changed - */ - __le64 offset; - /* - * the logical number of file blocks (no csums included). This - * always reflects the size uncompressed and without encoding. - */ - __le64 num_bytes; - -} __attribute__ ((__packed__)); - -struct btrfs_csum_item { - u8 csum; -} __attribute__ ((__packed__)); - -struct btrfs_dev_stats_item { - /* - * grow this item struct at the end for future enhancements and keep - * the existing values unchanged - */ - __le64 values[BTRFS_DEV_STAT_VALUES_MAX]; -} __attribute__ ((__packed__)); - -#define BTRFS_DEV_REPLACE_ITEM_CONT_READING_FROM_SRCDEV_MODE_ALWAYS 0 -#define BTRFS_DEV_REPLACE_ITEM_CONT_READING_FROM_SRCDEV_MODE_AVOID 1 -#define BTRFS_DEV_REPLACE_ITEM_STATE_NEVER_STARTED 0 -#define BTRFS_DEV_REPLACE_ITEM_STATE_STARTED 1 -#define BTRFS_DEV_REPLACE_ITEM_STATE_SUSPENDED 2 -#define BTRFS_DEV_REPLACE_ITEM_STATE_FINISHED 3 -#define BTRFS_DEV_REPLACE_ITEM_STATE_CANCELED 4 - struct btrfs_dev_replace { u64 replace_state; /* see #define above */ u64 time_started; /* seconds since 1-Jan-1970 */ @@ -1005,175 +384,6 @@ struct btrfs_dev_replace { struct btrfs_scrub_progress scrub_progress; }; -struct btrfs_dev_replace_item { - /* - * grow this item struct at the end for future enhancements and keep - * the existing values unchanged - */ - __le64 src_devid; - __le64 cursor_left; - __le64 cursor_right; - __le64 cont_reading_from_srcdev_mode; - - __le64 replace_state; - __le64 time_started; - __le64 time_stopped; - __le64 num_write_errors; - __le64 num_uncorrectable_read_errors; -} __attribute__ ((__packed__)); - -/* different types of block groups (and chunks) */ -#define BTRFS_BLOCK_GROUP_DATA (1ULL << 0) -#define BTRFS_BLOCK_GROUP_SYSTEM (1ULL << 1) -#define BTRFS_BLOCK_GROUP_METADATA (1ULL << 2) -#define BTRFS_BLOCK_GROUP_RAID0 (1ULL << 3) -#define BTRFS_BLOCK_GROUP_RAID1 (1ULL << 4) -#define BTRFS_BLOCK_GROUP_DUP (1ULL << 5) -#define BTRFS_BLOCK_GROUP_RAID10 (1ULL << 6) -#define BTRFS_BLOCK_GROUP_RAID5 (1ULL << 7) -#define BTRFS_BLOCK_GROUP_RAID6 (1ULL << 8) -#define BTRFS_BLOCK_GROUP_RESERVED (BTRFS_AVAIL_ALLOC_BIT_SINGLE | \ - BTRFS_SPACE_INFO_GLOBAL_RSV) - -enum btrfs_raid_types { - BTRFS_RAID_RAID10, - BTRFS_RAID_RAID1, - BTRFS_RAID_DUP, - BTRFS_RAID_RAID0, - BTRFS_RAID_SINGLE, - BTRFS_RAID_RAID5, - BTRFS_RAID_RAID6, - BTRFS_NR_RAID_TYPES -}; - -#define BTRFS_BLOCK_GROUP_TYPE_MASK (BTRFS_BLOCK_GROUP_DATA | \ - BTRFS_BLOCK_GROUP_SYSTEM | \ - BTRFS_BLOCK_GROUP_METADATA) - -#define BTRFS_BLOCK_GROUP_PROFILE_MASK (BTRFS_BLOCK_GROUP_RAID0 | \ - BTRFS_BLOCK_GROUP_RAID1 | \ - BTRFS_BLOCK_GROUP_RAID5 | \ - BTRFS_BLOCK_GROUP_RAID6 | \ - BTRFS_BLOCK_GROUP_DUP | \ - BTRFS_BLOCK_GROUP_RAID10) -#define BTRFS_BLOCK_GROUP_RAID56_MASK (BTRFS_BLOCK_GROUP_RAID5 | \ - BTRFS_BLOCK_GROUP_RAID6) - -/* - * We need a bit for restriper to be able to tell when chunks of type - * SINGLE are available. This "extended" profile format is used in - * fs_info->avail_*_alloc_bits (in-memory) and balance item fields - * (on-disk). The corresponding on-disk bit in chunk.type is reserved - * to avoid remappings between two formats in future. - */ -#define BTRFS_AVAIL_ALLOC_BIT_SINGLE (1ULL << 48) - -/* - * A fake block group type that is used to communicate global block reserve - * size to userspace via the SPACE_INFO ioctl. - */ -#define BTRFS_SPACE_INFO_GLOBAL_RSV (1ULL << 49) - -#define BTRFS_EXTENDED_PROFILE_MASK (BTRFS_BLOCK_GROUP_PROFILE_MASK | \ - BTRFS_AVAIL_ALLOC_BIT_SINGLE) - -static inline u64 chunk_to_extended(u64 flags) -{ - if ((flags & BTRFS_BLOCK_GROUP_PROFILE_MASK) == 0) - flags |= BTRFS_AVAIL_ALLOC_BIT_SINGLE; - - return flags; -} -static inline u64 extended_to_chunk(u64 flags) -{ - return flags & ~BTRFS_AVAIL_ALLOC_BIT_SINGLE; -} - -struct btrfs_block_group_item { - __le64 used; - __le64 chunk_objectid; - __le64 flags; -} __attribute__ ((__packed__)); - -struct btrfs_free_space_info { - __le32 extent_count; - __le32 flags; -} __attribute__ ((__packed__)); - -#define BTRFS_FREE_SPACE_USING_BITMAPS (1ULL << 0) - -#define BTRFS_QGROUP_LEVEL_SHIFT 48 -static inline u64 btrfs_qgroup_level(u64 qgroupid) -{ - return qgroupid >> BTRFS_QGROUP_LEVEL_SHIFT; -} - -/* - * is subvolume quota turned on? - */ -#define BTRFS_QGROUP_STATUS_FLAG_ON (1ULL << 0) -/* - * RESCAN is set during the initialization phase - */ -#define BTRFS_QGROUP_STATUS_FLAG_RESCAN (1ULL << 1) -/* - * Some qgroup entries are known to be out of date, - * either because the configuration has changed in a way that - * makes a rescan necessary, or because the fs has been mounted - * with a non-qgroup-aware version. - * Turning qouta off and on again makes it inconsistent, too. - */ -#define BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT (1ULL << 2) - -#define BTRFS_QGROUP_STATUS_VERSION 1 - -struct btrfs_qgroup_status_item { - __le64 version; - /* - * the generation is updated during every commit. As older - * versions of btrfs are not aware of qgroups, it will be - * possible to detect inconsistencies by checking the - * generation on mount time - */ - __le64 generation; - - /* flag definitions see above */ - __le64 flags; - - /* - * only used during scanning to record the progress - * of the scan. It contains a logical address - */ - __le64 rescan; -} __attribute__ ((__packed__)); - -struct btrfs_qgroup_info_item { - __le64 generation; - __le64 rfer; - __le64 rfer_cmpr; - __le64 excl; - __le64 excl_cmpr; -} __attribute__ ((__packed__)); - -/* flags definition for qgroup limits */ -#define BTRFS_QGROUP_LIMIT_MAX_RFER (1ULL << 0) -#define BTRFS_QGROUP_LIMIT_MAX_EXCL (1ULL << 1) -#define BTRFS_QGROUP_LIMIT_RSV_RFER (1ULL << 2) -#define BTRFS_QGROUP_LIMIT_RSV_EXCL (1ULL << 3) -#define BTRFS_QGROUP_LIMIT_RFER_CMPR (1ULL << 4) -#define BTRFS_QGROUP_LIMIT_EXCL_CMPR (1ULL << 5) - -struct btrfs_qgroup_limit_item { - /* - * only updated when any of the other values change - */ - __le64 flags; - __le64 max_rfer; - __le64 max_excl; - __le64 rsv_rfer; - __le64 rsv_excl; -} __attribute__ ((__packed__)); - /* For raid type sysfs entries */ struct raid_kobject { int raid_type; @@ -1408,6 +618,27 @@ struct btrfs_block_group_cache { struct btrfs_io_ctl io_ctl; + /* + * Incremented when doing extent allocations and holding a read lock + * on the space_info's groups_sem semaphore. + * Decremented when an ordered extent that represents an IO against this + * block group's range is created (after it's added to its inode's + * root's list of ordered extents) or immediately after the allocation + * if it's a metadata extent or fallocate extent (for these cases we + * don't create ordered extents). + */ + atomic_t reservations; + + /* + * Incremented while holding the spinlock *lock* by a task checking if + * it can perform a nocow write (incremented if the value for the *ro* + * field is 0). Decremented by such tasks once they create an ordered + * extent or before that if some error happens before reaching that step. + * This is to prevent races between block group relocation and nocow + * writes through direct IO. + */ + atomic_t nocow_writers; + /* Lock for free space tree operations. */ struct mutex free_space_lock; @@ -2026,228 +1257,6 @@ struct btrfs_root { atomic_t qgroup_meta_rsv; }; -struct btrfs_ioctl_defrag_range_args { - /* start of the defrag operation */ - __u64 start; - - /* number of bytes to defrag, use (u64)-1 to say all */ - __u64 len; - - /* - * flags for the operation, which can include turning - * on compression for this one defrag - */ - __u64 flags; - - /* - * any extent bigger than this will be considered - * already defragged. Use 0 to take the kernel default - * Use 1 to say every single extent must be rewritten - */ - __u32 extent_thresh; - - /* - * which compression method to use if turning on compression - * for this defrag operation. If unspecified, zlib will - * be used - */ - __u32 compress_type; - - /* spare for later */ - __u32 unused[4]; -}; - - -/* - * inode items have the data typically returned from stat and store other - * info about object characteristics. There is one for every file and dir in - * the FS - */ -#define BTRFS_INODE_ITEM_KEY 1 -#define BTRFS_INODE_REF_KEY 12 -#define BTRFS_INODE_EXTREF_KEY 13 -#define BTRFS_XATTR_ITEM_KEY 24 -#define BTRFS_ORPHAN_ITEM_KEY 48 -/* reserve 2-15 close to the inode for later flexibility */ - -/* - * dir items are the name -> inode pointers in a directory. There is one - * for every name in a directory. - */ -#define BTRFS_DIR_LOG_ITEM_KEY 60 -#define BTRFS_DIR_LOG_INDEX_KEY 72 -#define BTRFS_DIR_ITEM_KEY 84 -#define BTRFS_DIR_INDEX_KEY 96 -/* - * extent data is for file data - */ -#define BTRFS_EXTENT_DATA_KEY 108 - -/* - * extent csums are stored in a separate tree and hold csums for - * an entire extent on disk. - */ -#define BTRFS_EXTENT_CSUM_KEY 128 - -/* - * root items point to tree roots. They are typically in the root - * tree used by the super block to find all the other trees - */ -#define BTRFS_ROOT_ITEM_KEY 132 - -/* - * root backrefs tie subvols and snapshots to the directory entries that - * reference them - */ -#define BTRFS_ROOT_BACKREF_KEY 144 - -/* - * root refs make a fast index for listing all of the snapshots and - * subvolumes referenced by a given root. They point directly to the - * directory item in the root that references the subvol - */ -#define BTRFS_ROOT_REF_KEY 156 - -/* - * extent items are in the extent map tree. These record which blocks - * are used, and how many references there are to each block - */ -#define BTRFS_EXTENT_ITEM_KEY 168 - -/* - * The same as the BTRFS_EXTENT_ITEM_KEY, except it's metadata we already know - * the length, so we save the level in key->offset instead of the length. - */ -#define BTRFS_METADATA_ITEM_KEY 169 - -#define BTRFS_TREE_BLOCK_REF_KEY 176 - -#define BTRFS_EXTENT_DATA_REF_KEY 178 - -#define BTRFS_EXTENT_REF_V0_KEY 180 - -#define BTRFS_SHARED_BLOCK_REF_KEY 182 - -#define BTRFS_SHARED_DATA_REF_KEY 184 - -/* - * block groups give us hints into the extent allocation trees. Which - * blocks are free etc etc - */ -#define BTRFS_BLOCK_GROUP_ITEM_KEY 192 - -/* - * Every block group is represented in the free space tree by a free space info - * item, which stores some accounting information. It is keyed on - * (block_group_start, FREE_SPACE_INFO, block_group_length). - */ -#define BTRFS_FREE_SPACE_INFO_KEY 198 - -/* - * A free space extent tracks an extent of space that is free in a block group. - * It is keyed on (start, FREE_SPACE_EXTENT, length). - */ -#define BTRFS_FREE_SPACE_EXTENT_KEY 199 - -/* - * When a block group becomes very fragmented, we convert it to use bitmaps - * instead of extents. A free space bitmap is keyed on - * (start, FREE_SPACE_BITMAP, length); the corresponding item is a bitmap with - * (length / sectorsize) bits. - */ -#define BTRFS_FREE_SPACE_BITMAP_KEY 200 - -#define BTRFS_DEV_EXTENT_KEY 204 -#define BTRFS_DEV_ITEM_KEY 216 -#define BTRFS_CHUNK_ITEM_KEY 228 - -/* - * Records the overall state of the qgroups. - * There's only one instance of this key present, - * (0, BTRFS_QGROUP_STATUS_KEY, 0) - */ -#define BTRFS_QGROUP_STATUS_KEY 240 -/* - * Records the currently used space of the qgroup. - * One key per qgroup, (0, BTRFS_QGROUP_INFO_KEY, qgroupid). - */ -#define BTRFS_QGROUP_INFO_KEY 242 -/* - * Contains the user configured limits for the qgroup. - * One key per qgroup, (0, BTRFS_QGROUP_LIMIT_KEY, qgroupid). - */ -#define BTRFS_QGROUP_LIMIT_KEY 244 -/* - * Records the child-parent relationship of qgroups. For - * each relation, 2 keys are present: - * (childid, BTRFS_QGROUP_RELATION_KEY, parentid) - * (parentid, BTRFS_QGROUP_RELATION_KEY, childid) - */ -#define BTRFS_QGROUP_RELATION_KEY 246 - -/* - * Obsolete name, see BTRFS_TEMPORARY_ITEM_KEY. - */ -#define BTRFS_BALANCE_ITEM_KEY 248 - -/* - * The key type for tree items that are stored persistently, but do not need to - * exist for extended period of time. The items can exist in any tree. - * - * [subtype, BTRFS_TEMPORARY_ITEM_KEY, data] - * - * Existing items: - * - * - balance status item - * (BTRFS_BALANCE_OBJECTID, BTRFS_TEMPORARY_ITEM_KEY, 0) - */ -#define BTRFS_TEMPORARY_ITEM_KEY 248 - -/* - * Obsolete name, see BTRFS_PERSISTENT_ITEM_KEY - */ -#define BTRFS_DEV_STATS_KEY 249 - -/* - * The key type for tree items that are stored persistently and usually exist - * for a long period, eg. filesystem lifetime. The item kinds can be status - * information, stats or preference values. The item can exist in any tree. - * - * [subtype, BTRFS_PERSISTENT_ITEM_KEY, data] - * - * Existing items: - * - * - device statistics, store IO stats in the device tree, one key for all - * stats - * (BTRFS_DEV_STATS_OBJECTID, BTRFS_DEV_STATS_KEY, 0) - */ -#define BTRFS_PERSISTENT_ITEM_KEY 249 - -/* - * Persistantly stores the device replace state in the device tree. - * The key is built like this: (0, BTRFS_DEV_REPLACE_KEY, 0). - */ -#define BTRFS_DEV_REPLACE_KEY 250 - -/* - * Stores items that allow to quickly map UUIDs to something else. - * These items are part of the filesystem UUID tree. - * The key is built like this: - * (UUID_upper_64_bits, BTRFS_UUID_KEY*, UUID_lower_64_bits). - */ -#if BTRFS_UUID_SIZE != 16 -#error "UUID items require BTRFS_UUID_SIZE == 16!" -#endif -#define BTRFS_UUID_KEY_SUBVOL 251 /* for UUIDs assigned to subvols */ -#define BTRFS_UUID_KEY_RECEIVED_SUBVOL 252 /* for UUIDs assigned to - * received subvols */ - -/* - * string items are for debugging. They just store a short string of - * data in the FS - */ -#define BTRFS_STRING_ITEM_KEY 253 - /* * Flags for mount options. * @@ -3499,6 +2508,12 @@ int btrfs_should_throttle_delayed_refs(struct btrfs_trans_handle *trans, struct btrfs_root *root); int btrfs_check_space_for_delayed_refs(struct btrfs_trans_handle *trans, struct btrfs_root *root); +void btrfs_dec_block_group_reservations(struct btrfs_fs_info *fs_info, + const u64 start); +void btrfs_wait_block_group_reservations(struct btrfs_block_group_cache *bg); +bool btrfs_inc_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr); +void btrfs_dec_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr); +void btrfs_wait_nocow_writers(struct btrfs_block_group_cache *bg); void btrfs_put_block_group(struct btrfs_block_group_cache *cache); int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans, struct btrfs_root *root, unsigned long count); @@ -4122,6 +3137,7 @@ void btrfs_test_inode_set_ops(struct inode *inode); /* ioctl.c */ long btrfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg); +long btrfs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg); int btrfs_ioctl_get_supported_features(void __user *arg); void btrfs_update_iflags(struct inode *inode); void btrfs_inherit_iflags(struct inode *inode, struct inode *dir); @@ -4326,10 +3342,9 @@ static inline void assfail(char *expr, char *file, int line) #define ASSERT(expr) ((void)0) #endif -#define btrfs_assert() __printf(5, 6) __cold -void __btrfs_std_error(struct btrfs_fs_info *fs_info, const char *function, +void __btrfs_handle_fs_error(struct btrfs_fs_info *fs_info, const char *function, unsigned int line, int errno, const char *fmt, ...); const char *btrfs_decode_error(int errno); @@ -4339,6 +3354,46 @@ void __btrfs_abort_transaction(struct btrfs_trans_handle *trans, struct btrfs_root *root, const char *function, unsigned int line, int errno); +/* + * Call btrfs_abort_transaction as early as possible when an error condition is + * detected, that way the exact line number is reported. + */ +#define btrfs_abort_transaction(trans, root, errno) \ +do { \ + /* Report first abort since mount */ \ + if (!test_and_set_bit(BTRFS_FS_STATE_TRANS_ABORTED, \ + &((root)->fs_info->fs_state))) { \ + WARN(1, KERN_DEBUG \ + "BTRFS: Transaction aborted (error %d)\n", \ + (errno)); \ + } \ + __btrfs_abort_transaction((trans), (root), __func__, \ + __LINE__, (errno)); \ +} while (0) + +#define btrfs_handle_fs_error(fs_info, errno, fmt, args...) \ +do { \ + __btrfs_handle_fs_error((fs_info), __func__, __LINE__, \ + (errno), fmt, ##args); \ +} while (0) + +__printf(5, 6) +__cold +void __btrfs_panic(struct btrfs_fs_info *fs_info, const char *function, + unsigned int line, int errno, const char *fmt, ...); +/* + * If BTRFS_MOUNT_PANIC_ON_FATAL_ERROR is in mount_opt, __btrfs_panic + * will panic(). Otherwise we BUG() here. + */ +#define btrfs_panic(fs_info, errno, fmt, args...) \ +do { \ + __btrfs_panic(fs_info, __func__, __LINE__, errno, fmt, ##args); \ + BUG(); \ +} while (0) + + +/* compatibility and incompatibility defines */ + #define btrfs_set_fs_incompat(__fs_info, opt) \ __btrfs_set_fs_incompat((__fs_info), BTRFS_FEATURE_INCOMPAT_##opt) @@ -4455,44 +3510,6 @@ static inline int __btrfs_fs_compat_ro(struct btrfs_fs_info *fs_info, u64 flag) return !!(btrfs_super_compat_ro_flags(disk_super) & flag); } -/* - * Call btrfs_abort_transaction as early as possible when an error condition is - * detected, that way the exact line number is reported. - */ -#define btrfs_abort_transaction(trans, root, errno) \ -do { \ - /* Report first abort since mount */ \ - if (!test_and_set_bit(BTRFS_FS_STATE_TRANS_ABORTED, \ - &((root)->fs_info->fs_state))) { \ - WARN(1, KERN_DEBUG \ - "BTRFS: Transaction aborted (error %d)\n", \ - (errno)); \ - } \ - __btrfs_abort_transaction((trans), (root), __func__, \ - __LINE__, (errno)); \ -} while (0) - -#define btrfs_std_error(fs_info, errno, fmt, args...) \ -do { \ - __btrfs_std_error((fs_info), __func__, __LINE__, \ - (errno), fmt, ##args); \ -} while (0) - -__printf(5, 6) -__cold -void __btrfs_panic(struct btrfs_fs_info *fs_info, const char *function, - unsigned int line, int errno, const char *fmt, ...); - -/* - * If BTRFS_MOUNT_PANIC_ON_FATAL_ERROR is in mount_opt, __btrfs_panic - * will panic(). Otherwise we BUG() here. - */ -#define btrfs_panic(fs_info, errno, fmt, args...) \ -do { \ - __btrfs_panic(fs_info, __func__, __LINE__, errno, fmt, ##args); \ - BUG(); \ -} while (0) - /* acl.c */ #ifdef CONFIG_BTRFS_FS_POSIX_ACL struct posix_acl *btrfs_get_acl(struct inode *inode, int type); diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index 6cef0062f929..61561c2a3f96 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -134,7 +134,7 @@ again: /* cached in the btrfs inode and can be accessed */ atomic_add(2, &node->refs); - ret = radix_tree_preload(GFP_NOFS & ~__GFP_HIGHMEM); + ret = radix_tree_preload(GFP_NOFS); if (ret) { kmem_cache_free(delayed_node_cache, node); return ERR_PTR(ret); diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index 0584b6c2df57..63ef9cdf0144 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -44,9 +44,6 @@ static void btrfs_dev_replace_update_device_in_mapping_tree( struct btrfs_fs_info *fs_info, struct btrfs_device *srcdev, struct btrfs_device *tgtdev); -static int btrfs_dev_replace_find_srcdev(struct btrfs_root *root, u64 srcdevid, - char *srcdev_name, - struct btrfs_device **device); static u64 __btrfs_dev_replace_cancel(struct btrfs_fs_info *fs_info); static int btrfs_dev_replace_kthread(void *data); static int btrfs_dev_replace_continue_on_mount(struct btrfs_fs_info *fs_info); @@ -305,8 +302,8 @@ void btrfs_after_dev_replace_commit(struct btrfs_fs_info *fs_info) dev_replace->cursor_left_last_write_of_item; } -int btrfs_dev_replace_start(struct btrfs_root *root, - struct btrfs_ioctl_dev_replace_args *args) +int btrfs_dev_replace_start(struct btrfs_root *root, char *tgtdev_name, + u64 srcdevid, char *srcdev_name, int read_src) { struct btrfs_trans_handle *trans; struct btrfs_fs_info *fs_info = root->fs_info; @@ -315,29 +312,16 @@ int btrfs_dev_replace_start(struct btrfs_root *root, struct btrfs_device *tgt_device = NULL; struct btrfs_device *src_device = NULL; - switch (args->start.cont_reading_from_srcdev_mode) { - case BTRFS_IOCTL_DEV_REPLACE_CONT_READING_FROM_SRCDEV_MODE_ALWAYS: - case BTRFS_IOCTL_DEV_REPLACE_CONT_READING_FROM_SRCDEV_MODE_AVOID: - break; - default: - return -EINVAL; - } - - if ((args->start.srcdevid == 0 && args->start.srcdev_name[0] == '\0') || - args->start.tgtdev_name[0] == '\0') - return -EINVAL; - /* the disk copy procedure reuses the scrub code */ mutex_lock(&fs_info->volume_mutex); - ret = btrfs_dev_replace_find_srcdev(root, args->start.srcdevid, - args->start.srcdev_name, - &src_device); + ret = btrfs_find_device_by_devspec(root, srcdevid, + srcdev_name, &src_device); if (ret) { mutex_unlock(&fs_info->volume_mutex); return ret; } - ret = btrfs_init_dev_replace_tgtdev(root, args->start.tgtdev_name, + ret = btrfs_init_dev_replace_tgtdev(root, tgtdev_name, src_device, &tgt_device); mutex_unlock(&fs_info->volume_mutex); if (ret) @@ -364,18 +348,17 @@ int btrfs_dev_replace_start(struct btrfs_root *root, break; case BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED: case BTRFS_IOCTL_DEV_REPLACE_STATE_SUSPENDED: - args->result = BTRFS_IOCTL_DEV_REPLACE_RESULT_ALREADY_STARTED; + ret = BTRFS_IOCTL_DEV_REPLACE_RESULT_ALREADY_STARTED; goto leave; } - dev_replace->cont_reading_from_srcdev_mode = - args->start.cont_reading_from_srcdev_mode; + dev_replace->cont_reading_from_srcdev_mode = read_src; WARN_ON(!src_device); dev_replace->srcdev = src_device; WARN_ON(!tgt_device); dev_replace->tgtdev = tgt_device; - btrfs_info_in_rcu(root->fs_info, + btrfs_info_in_rcu(fs_info, "dev_replace from %s (devid %llu) to %s started", src_device->missing ? "<missing disk>" : rcu_str_deref(src_device->name), @@ -396,14 +379,13 @@ int btrfs_dev_replace_start(struct btrfs_root *root, dev_replace->item_needs_writeback = 1; atomic64_set(&dev_replace->num_write_errors, 0); atomic64_set(&dev_replace->num_uncorrectable_read_errors, 0); - args->result = BTRFS_IOCTL_DEV_REPLACE_RESULT_NO_ERROR; btrfs_dev_replace_unlock(dev_replace, 1); ret = btrfs_sysfs_add_device_link(tgt_device->fs_devices, tgt_device); if (ret) - btrfs_err(root->fs_info, "kobj add dev failed %d\n", ret); + btrfs_err(fs_info, "kobj add dev failed %d\n", ret); - btrfs_wait_ordered_roots(root->fs_info, -1); + btrfs_wait_ordered_roots(root->fs_info, -1, 0, (u64)-1); /* force writing the updated state information to disk */ trans = btrfs_start_transaction(root, 0); @@ -421,11 +403,9 @@ int btrfs_dev_replace_start(struct btrfs_root *root, btrfs_device_get_total_bytes(src_device), &dev_replace->scrub_progress, 0, 1); - ret = btrfs_dev_replace_finishing(root->fs_info, ret); - /* don't warn if EINPROGRESS, someone else might be running scrub */ + ret = btrfs_dev_replace_finishing(fs_info, ret); if (ret == -EINPROGRESS) { - args->result = BTRFS_IOCTL_DEV_REPLACE_RESULT_SCRUB_INPROGRESS; - ret = 0; + ret = BTRFS_IOCTL_DEV_REPLACE_RESULT_SCRUB_INPROGRESS; } else { WARN_ON(ret); } @@ -440,6 +420,35 @@ leave: return ret; } +int btrfs_dev_replace_by_ioctl(struct btrfs_root *root, + struct btrfs_ioctl_dev_replace_args *args) +{ + int ret; + + switch (args->start.cont_reading_from_srcdev_mode) { + case BTRFS_IOCTL_DEV_REPLACE_CONT_READING_FROM_SRCDEV_MODE_ALWAYS: + case BTRFS_IOCTL_DEV_REPLACE_CONT_READING_FROM_SRCDEV_MODE_AVOID: + break; + default: + return -EINVAL; + } + + if ((args->start.srcdevid == 0 && args->start.srcdev_name[0] == '\0') || + args->start.tgtdev_name[0] == '\0') + return -EINVAL; + + ret = btrfs_dev_replace_start(root, args->start.tgtdev_name, + args->start.srcdevid, + args->start.srcdev_name, + args->start.cont_reading_from_srcdev_mode); + args->result = ret; + /* don't warn if EINPROGRESS, someone else might be running scrub */ + if (ret == BTRFS_IOCTL_DEV_REPLACE_RESULT_SCRUB_INPROGRESS) + ret = 0; + + return ret; +} + /* * blocked until all in-flight bios operations are finished. */ @@ -495,7 +504,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info, mutex_unlock(&dev_replace->lock_finishing_cancel_unmount); return ret; } - btrfs_wait_ordered_roots(root->fs_info, -1); + btrfs_wait_ordered_roots(root->fs_info, -1, 0, (u64)-1); trans = btrfs_start_transaction(root, 0); if (IS_ERR(trans)) { @@ -560,10 +569,9 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info, ASSERT(list_empty(&src_device->resized_list)); tgt_device->commit_total_bytes = src_device->commit_total_bytes; tgt_device->commit_bytes_used = src_device->bytes_used; - if (fs_info->sb->s_bdev == src_device->bdev) - fs_info->sb->s_bdev = tgt_device->bdev; - if (fs_info->fs_devices->latest_bdev == src_device->bdev) - fs_info->fs_devices->latest_bdev = tgt_device->bdev; + + btrfs_assign_next_active_device(fs_info, src_device, tgt_device); + list_add(&tgt_device->dev_alloc_list, &fs_info->fs_devices->alloc_list); fs_info->fs_devices->rw_devices++; @@ -626,25 +634,6 @@ static void btrfs_dev_replace_update_device_in_mapping_tree( write_unlock(&em_tree->lock); } -static int btrfs_dev_replace_find_srcdev(struct btrfs_root *root, u64 srcdevid, - char *srcdev_name, - struct btrfs_device **device) -{ - int ret; - - if (srcdevid) { - ret = 0; - *device = btrfs_find_device(root->fs_info, srcdevid, NULL, - NULL); - if (!*device) - ret = -ENOENT; - } else { - ret = btrfs_find_device_missing_or_by_path(root, srcdev_name, - device); - } - return ret; -} - void btrfs_dev_replace_status(struct btrfs_fs_info *fs_info, struct btrfs_ioctl_dev_replace_args *args) { diff --git a/fs/btrfs/dev-replace.h b/fs/btrfs/dev-replace.h index 29e3ef5f96bd..e922b42d91df 100644 --- a/fs/btrfs/dev-replace.h +++ b/fs/btrfs/dev-replace.h @@ -25,8 +25,10 @@ int btrfs_init_dev_replace(struct btrfs_fs_info *fs_info); int btrfs_run_dev_replace(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info); void btrfs_after_dev_replace_commit(struct btrfs_fs_info *fs_info); -int btrfs_dev_replace_start(struct btrfs_root *root, +int btrfs_dev_replace_by_ioctl(struct btrfs_root *root, struct btrfs_ioctl_dev_replace_args *args); +int btrfs_dev_replace_start(struct btrfs_root *root, char *tgtdev_name, + u64 srcdevid, char *srcdev_name, int read_src); void btrfs_dev_replace_status(struct btrfs_fs_info *fs_info, struct btrfs_ioctl_dev_replace_args *args); int btrfs_dev_replace_cancel(struct btrfs_fs_info *fs_info, diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index aacc707ef952..6628fca9f4ed 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1640,7 +1640,7 @@ int btrfs_insert_fs_root(struct btrfs_fs_info *fs_info, { int ret; - ret = radix_tree_preload(GFP_NOFS & ~__GFP_HIGHMEM); + ret = radix_tree_preload(GFP_NOFS); if (ret) return ret; @@ -2417,7 +2417,7 @@ static int btrfs_replay_log(struct btrfs_fs_info *fs_info, /* returns with log_tree_root freed on success */ ret = btrfs_recover_log_trees(log_tree_root); if (ret) { - btrfs_std_error(tree_root->fs_info, ret, + btrfs_handle_fs_error(tree_root->fs_info, ret, "Failed to recover log tree"); free_extent_buffer(log_tree_root->node); kfree(log_tree_root); @@ -2517,6 +2517,7 @@ int open_ctree(struct super_block *sb, int num_backups_tried = 0; int backup_index = 0; int max_active; + bool cleaner_mutex_locked = false; tree_root = fs_info->tree_root = btrfs_alloc_root(fs_info, GFP_KERNEL); chunk_root = fs_info->chunk_root = btrfs_alloc_root(fs_info, GFP_KERNEL); @@ -2713,7 +2714,7 @@ int open_ctree(struct super_block *sb, * Pass the whole disk block of size BTRFS_SUPER_INFO_SIZE (4k). */ if (btrfs_check_super_csum(bh->b_data)) { - printk(KERN_ERR "BTRFS: superblock checksum mismatch\n"); + btrfs_err(fs_info, "superblock checksum mismatch"); err = -EINVAL; brelse(bh); goto fail_alloc; @@ -2733,7 +2734,7 @@ int open_ctree(struct super_block *sb, ret = btrfs_check_super_valid(fs_info, sb->s_flags & MS_RDONLY); if (ret) { - printk(KERN_ERR "BTRFS: superblock contains fatal errors\n"); + btrfs_err(fs_info, "superblock contains fatal errors"); err = -EINVAL; goto fail_alloc; } @@ -2768,9 +2769,9 @@ int open_ctree(struct super_block *sb, features = btrfs_super_incompat_flags(disk_super) & ~BTRFS_FEATURE_INCOMPAT_SUPP; if (features) { - printk(KERN_ERR "BTRFS: couldn't mount because of " - "unsupported optional features (%Lx).\n", - features); + btrfs_err(fs_info, + "cannot mount because of unsupported optional features (%llx)", + features); err = -EINVAL; goto fail_alloc; } @@ -2781,7 +2782,7 @@ int open_ctree(struct super_block *sb, features |= BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO; if (features & BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA) - printk(KERN_INFO "BTRFS: has skinny extents\n"); + btrfs_info(fs_info, "has skinny extents"); /* * flag our filesystem as having big metadata blocks if @@ -2789,7 +2790,8 @@ int open_ctree(struct super_block *sb, */ if (btrfs_super_nodesize(disk_super) > PAGE_SIZE) { if (!(features & BTRFS_FEATURE_INCOMPAT_BIG_METADATA)) - printk(KERN_INFO "BTRFS: flagging fs with big metadata feature\n"); + btrfs_info(fs_info, + "flagging fs with big metadata feature"); features |= BTRFS_FEATURE_INCOMPAT_BIG_METADATA; } @@ -2805,9 +2807,9 @@ int open_ctree(struct super_block *sb, */ if ((features & BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS) && (sectorsize != nodesize)) { - printk(KERN_ERR "BTRFS: unequal leaf/node/sector sizes " - "are not allowed for mixed block groups on %s\n", - sb->s_id); + btrfs_err(fs_info, +"unequal nodesize/sectorsize (%u != %u) are not allowed for mixed block groups", + nodesize, sectorsize); goto fail_alloc; } @@ -2820,8 +2822,8 @@ int open_ctree(struct super_block *sb, features = btrfs_super_compat_ro_flags(disk_super) & ~BTRFS_FEATURE_COMPAT_RO_SUPP; if (!(sb->s_flags & MS_RDONLY) && features) { - printk(KERN_ERR "BTRFS: couldn't mount RDWR because of " - "unsupported option features (%Lx).\n", + btrfs_err(fs_info, + "cannot mount read-write because of unsupported optional features (%llx)", features); err = -EINVAL; goto fail_alloc; @@ -2850,8 +2852,7 @@ int open_ctree(struct super_block *sb, ret = btrfs_read_sys_array(tree_root); mutex_unlock(&fs_info->chunk_mutex); if (ret) { - printk(KERN_ERR "BTRFS: failed to read the system " - "array on %s\n", sb->s_id); + btrfs_err(fs_info, "failed to read the system array: %d", ret); goto fail_sb_buffer; } @@ -2865,8 +2866,7 @@ int open_ctree(struct super_block *sb, generation); if (IS_ERR(chunk_root->node) || !extent_buffer_uptodate(chunk_root->node)) { - printk(KERN_ERR "BTRFS: failed to read chunk root on %s\n", - sb->s_id); + btrfs_err(fs_info, "failed to read chunk root"); if (!IS_ERR(chunk_root->node)) free_extent_buffer(chunk_root->node); chunk_root->node = NULL; @@ -2880,8 +2880,7 @@ int open_ctree(struct super_block *sb, ret = btrfs_read_chunk_tree(chunk_root); if (ret) { - printk(KERN_ERR "BTRFS: failed to read chunk tree on %s\n", - sb->s_id); + btrfs_err(fs_info, "failed to read chunk tree: %d", ret); goto fail_tree_roots; } @@ -2892,8 +2891,7 @@ int open_ctree(struct super_block *sb, btrfs_close_extra_devices(fs_devices, 0); if (!fs_devices->latest_bdev) { - printk(KERN_ERR "BTRFS: failed to read devices on %s\n", - sb->s_id); + btrfs_err(fs_info, "failed to read devices"); goto fail_tree_roots; } @@ -2905,8 +2903,7 @@ retry_root_backup: generation); if (IS_ERR(tree_root->node) || !extent_buffer_uptodate(tree_root->node)) { - printk(KERN_WARNING "BTRFS: failed to read tree root on %s\n", - sb->s_id); + btrfs_warn(fs_info, "failed to read tree root"); if (!IS_ERR(tree_root->node)) free_extent_buffer(tree_root->node); tree_root->node = NULL; @@ -2938,20 +2935,19 @@ retry_root_backup: ret = btrfs_recover_balance(fs_info); if (ret) { - printk(KERN_ERR "BTRFS: failed to recover balance\n"); + btrfs_err(fs_info, "failed to recover balance: %d", ret); goto fail_block_groups; } ret = btrfs_init_dev_stats(fs_info); if (ret) { - printk(KERN_ERR "BTRFS: failed to init dev_stats: %d\n", - ret); + btrfs_err(fs_info, "failed to init dev_stats: %d", ret); goto fail_block_groups; } ret = btrfs_init_dev_replace(fs_info); if (ret) { - pr_err("BTRFS: failed to init dev_replace: %d\n", ret); + btrfs_err(fs_info, "failed to init dev_replace: %d", ret); goto fail_block_groups; } @@ -2959,31 +2955,33 @@ retry_root_backup: ret = btrfs_sysfs_add_fsid(fs_devices, NULL); if (ret) { - pr_err("BTRFS: failed to init sysfs fsid interface: %d\n", ret); + btrfs_err(fs_info, "failed to init sysfs fsid interface: %d", + ret); goto fail_block_groups; } ret = btrfs_sysfs_add_device(fs_devices); if (ret) { - pr_err("BTRFS: failed to init sysfs device interface: %d\n", ret); + btrfs_err(fs_info, "failed to init sysfs device interface: %d", + ret); goto fail_fsdev_sysfs; } ret = btrfs_sysfs_add_mounted(fs_info); if (ret) { - pr_err("BTRFS: failed to init sysfs interface: %d\n", ret); + btrfs_err(fs_info, "failed to init sysfs interface: %d", ret); goto fail_fsdev_sysfs; } ret = btrfs_init_space_info(fs_info); if (ret) { - printk(KERN_ERR "BTRFS: Failed to initial space info: %d\n", ret); + btrfs_err(fs_info, "failed to initialize space info: %d", ret); goto fail_sysfs; } ret = btrfs_read_block_groups(fs_info->extent_root); if (ret) { - printk(KERN_ERR "BTRFS: Failed to read block groups: %d\n", ret); + btrfs_err(fs_info, "failed to read block groups: %d", ret); goto fail_sysfs; } fs_info->num_tolerated_disk_barrier_failures = @@ -2991,12 +2989,20 @@ retry_root_backup: if (fs_info->fs_devices->missing_devices > fs_info->num_tolerated_disk_barrier_failures && !(sb->s_flags & MS_RDONLY)) { - pr_warn("BTRFS: missing devices(%llu) exceeds the limit(%d), writeable mount is not allowed\n", + btrfs_warn(fs_info, +"missing devices (%llu) exceeds the limit (%d), writeable mount is not allowed", fs_info->fs_devices->missing_devices, fs_info->num_tolerated_disk_barrier_failures); goto fail_sysfs; } + /* + * Hold the cleaner_mutex thread here so that we don't block + * for a long time on btrfs_recover_relocation. cleaner_kthread + * will wait for us to finish mounting the filesystem. + */ + mutex_lock(&fs_info->cleaner_mutex); + cleaner_mutex_locked = true; fs_info->cleaner_kthread = kthread_run(cleaner_kthread, tree_root, "btrfs-cleaner"); if (IS_ERR(fs_info->cleaner_kthread)) @@ -3011,8 +3017,7 @@ retry_root_backup: if (!btrfs_test_opt(tree_root, SSD) && !btrfs_test_opt(tree_root, NOSSD) && !fs_info->fs_devices->rotating) { - printk(KERN_INFO "BTRFS: detected SSD devices, enabling SSD " - "mode\n"); + btrfs_info(fs_info, "detected SSD devices, enabling SSD mode"); btrfs_set_opt(fs_info->mount_opt, SSD); } @@ -3030,8 +3035,9 @@ retry_root_backup: 1 : 0, fs_info->check_integrity_print_mask); if (ret) - printk(KERN_WARNING "BTRFS: failed to initialize" - " integrity check module %s\n", sb->s_id); + btrfs_warn(fs_info, + "failed to initialize integrity check module: %d", + ret); } #endif ret = btrfs_read_qgroup_config(fs_info); @@ -3056,17 +3062,17 @@ retry_root_backup: ret = btrfs_cleanup_fs_roots(fs_info); if (ret) goto fail_qgroup; - - mutex_lock(&fs_info->cleaner_mutex); + /* We locked cleaner_mutex before creating cleaner_kthread. */ ret = btrfs_recover_relocation(tree_root); - mutex_unlock(&fs_info->cleaner_mutex); if (ret < 0) { - printk(KERN_WARNING - "BTRFS: failed to recover relocation\n"); + btrfs_warn(fs_info, "failed to recover relocation: %d", + ret); err = -EINVAL; goto fail_qgroup; } } + mutex_unlock(&fs_info->cleaner_mutex); + cleaner_mutex_locked = false; location.objectid = BTRFS_FS_TREE_OBJECTID; location.type = BTRFS_ROOT_ITEM_KEY; @@ -3083,11 +3089,11 @@ retry_root_backup: if (btrfs_test_opt(tree_root, FREE_SPACE_TREE) && !btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE)) { - pr_info("BTRFS: creating free space tree\n"); + btrfs_info(fs_info, "creating free space tree"); ret = btrfs_create_free_space_tree(fs_info); if (ret) { - pr_warn("BTRFS: failed to create free space tree %d\n", - ret); + btrfs_warn(fs_info, + "failed to create free space tree: %d", ret); close_ctree(tree_root); return ret; } @@ -3104,14 +3110,14 @@ retry_root_backup: ret = btrfs_resume_balance_async(fs_info); if (ret) { - printk(KERN_WARNING "BTRFS: failed to resume balance\n"); + btrfs_warn(fs_info, "failed to resume balance: %d", ret); close_ctree(tree_root); return ret; } ret = btrfs_resume_dev_replace_async(fs_info); if (ret) { - pr_warn("BTRFS: failed to resume dev_replace\n"); + btrfs_warn(fs_info, "failed to resume device replace: %d", ret); close_ctree(tree_root); return ret; } @@ -3120,33 +3126,33 @@ retry_root_backup: if (btrfs_test_opt(tree_root, CLEAR_CACHE) && btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE)) { - pr_info("BTRFS: clearing free space tree\n"); + btrfs_info(fs_info, "clearing free space tree"); ret = btrfs_clear_free_space_tree(fs_info); if (ret) { - pr_warn("BTRFS: failed to clear free space tree %d\n", - ret); + btrfs_warn(fs_info, + "failed to clear free space tree: %d", ret); close_ctree(tree_root); return ret; } } if (!fs_info->uuid_root) { - pr_info("BTRFS: creating UUID tree\n"); + btrfs_info(fs_info, "creating UUID tree"); ret = btrfs_create_uuid_tree(fs_info); if (ret) { - pr_warn("BTRFS: failed to create the UUID tree %d\n", - ret); + btrfs_warn(fs_info, + "failed to create the UUID tree: %d", ret); close_ctree(tree_root); return ret; } } else if (btrfs_test_opt(tree_root, RESCAN_UUID_TREE) || fs_info->generation != btrfs_super_uuid_tree_generation(disk_super)) { - pr_info("BTRFS: checking UUID tree\n"); + btrfs_info(fs_info, "checking UUID tree"); ret = btrfs_check_uuid_tree(fs_info); if (ret) { - pr_warn("BTRFS: failed to check the UUID tree %d\n", - ret); + btrfs_warn(fs_info, + "failed to check the UUID tree: %d", ret); close_ctree(tree_root); return ret; } @@ -3180,6 +3186,10 @@ fail_cleaner: filemap_write_and_wait(fs_info->btree_inode->i_mapping); fail_sysfs: + if (cleaner_mutex_locked) { + mutex_unlock(&fs_info->cleaner_mutex); + cleaner_mutex_locked = false; + } btrfs_sysfs_remove_mounted(fs_info); fail_fsdev_sysfs: @@ -3646,7 +3656,7 @@ static int write_all_supers(struct btrfs_root *root, int max_mirrors) if (ret) { mutex_unlock( &root->fs_info->fs_devices->device_list_mutex); - btrfs_std_error(root->fs_info, ret, + btrfs_handle_fs_error(root->fs_info, ret, "errors while submitting device barriers."); return ret; } @@ -3686,7 +3696,7 @@ static int write_all_supers(struct btrfs_root *root, int max_mirrors) mutex_unlock(&root->fs_info->fs_devices->device_list_mutex); /* FUA is masked off if unsupported and can't be the reason */ - btrfs_std_error(root->fs_info, -EIO, + btrfs_handle_fs_error(root->fs_info, -EIO, "%d errors while writing supers", total_errors); return -EIO; } @@ -3704,7 +3714,7 @@ static int write_all_supers(struct btrfs_root *root, int max_mirrors) } mutex_unlock(&root->fs_info->fs_devices->device_list_mutex); if (total_errors > max_errors) { - btrfs_std_error(root->fs_info, -EIO, + btrfs_handle_fs_error(root->fs_info, -EIO, "%d errors while writing supers", total_errors); return -EIO; } diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 939a043eabfa..a400951e8678 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -3824,6 +3824,59 @@ int btrfs_extent_readonly(struct btrfs_root *root, u64 bytenr) return readonly; } +bool btrfs_inc_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr) +{ + struct btrfs_block_group_cache *bg; + bool ret = true; + + bg = btrfs_lookup_block_group(fs_info, bytenr); + if (!bg) + return false; + + spin_lock(&bg->lock); + if (bg->ro) + ret = false; + else + atomic_inc(&bg->nocow_writers); + spin_unlock(&bg->lock); + + /* no put on block group, done by btrfs_dec_nocow_writers */ + if (!ret) + btrfs_put_block_group(bg); + + return ret; + +} + +void btrfs_dec_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr) +{ + struct btrfs_block_group_cache *bg; + + bg = btrfs_lookup_block_group(fs_info, bytenr); + ASSERT(bg); + if (atomic_dec_and_test(&bg->nocow_writers)) + wake_up_atomic_t(&bg->nocow_writers); + /* + * Once for our lookup and once for the lookup done by a previous call + * to btrfs_inc_nocow_writers() + */ + btrfs_put_block_group(bg); + btrfs_put_block_group(bg); +} + +static int btrfs_wait_nocow_writers_atomic_t(atomic_t *a) +{ + schedule(); + return 0; +} + +void btrfs_wait_nocow_writers(struct btrfs_block_group_cache *bg) +{ + wait_on_atomic_t(&bg->nocow_writers, + btrfs_wait_nocow_writers_atomic_t, + TASK_UNINTERRUPTIBLE); +} + static const char *alloc_name(u64 flags) { switch (flags) { @@ -4141,7 +4194,7 @@ commit_trans: if (need_commit > 0) { btrfs_start_delalloc_roots(fs_info, 0, -1); - btrfs_wait_ordered_roots(fs_info, -1); + btrfs_wait_ordered_roots(fs_info, -1, 0, (u64)-1); } trans = btrfs_join_transaction(root); @@ -4583,7 +4636,8 @@ static void btrfs_writeback_inodes_sb_nr(struct btrfs_root *root, */ btrfs_start_delalloc_roots(root->fs_info, 0, nr_items); if (!current->journal_info) - btrfs_wait_ordered_roots(root->fs_info, nr_items); + btrfs_wait_ordered_roots(root->fs_info, nr_items, + 0, (u64)-1); } } @@ -4620,7 +4674,7 @@ static void shrink_delalloc(struct btrfs_root *root, u64 to_reclaim, u64 orig, /* Calc the number of the pages we need flush for space reservation */ items = calc_reclaim_items_nr(root, to_reclaim); - to_reclaim = items * EXTENT_SIZE_PER_ITEM; + to_reclaim = (u64)items * EXTENT_SIZE_PER_ITEM; trans = (struct btrfs_trans_handle *)current->journal_info; block_rsv = &root->fs_info->delalloc_block_rsv; @@ -4632,7 +4686,8 @@ static void shrink_delalloc(struct btrfs_root *root, u64 to_reclaim, u64 orig, if (trans) return; if (wait_ordered) - btrfs_wait_ordered_roots(root->fs_info, items); + btrfs_wait_ordered_roots(root->fs_info, items, + 0, (u64)-1); return; } @@ -4671,7 +4726,8 @@ skip_async: loops++; if (wait_ordered && !trans) { - btrfs_wait_ordered_roots(root->fs_info, items); + btrfs_wait_ordered_roots(root->fs_info, items, + 0, (u64)-1); } else { time_left = schedule_timeout_killable(1); if (time_left) @@ -6172,6 +6228,57 @@ int btrfs_exclude_logged_extents(struct btrfs_root *log, return 0; } +static void +btrfs_inc_block_group_reservations(struct btrfs_block_group_cache *bg) +{ + atomic_inc(&bg->reservations); +} + +void btrfs_dec_block_group_reservations(struct btrfs_fs_info *fs_info, + const u64 start) +{ + struct btrfs_block_group_cache *bg; + + bg = btrfs_lookup_block_group(fs_info, start); + ASSERT(bg); + if (atomic_dec_and_test(&bg->reservations)) + wake_up_atomic_t(&bg->reservations); + btrfs_put_block_group(bg); +} + +static int btrfs_wait_bg_reservations_atomic_t(atomic_t *a) +{ + schedule(); + return 0; +} + +void btrfs_wait_block_group_reservations(struct btrfs_block_group_cache *bg) +{ + struct btrfs_space_info *space_info = bg->space_info; + + ASSERT(bg->ro); + + if (!(bg->flags & BTRFS_BLOCK_GROUP_DATA)) + return; + + /* + * Our block group is read only but before we set it to read only, + * some task might have had allocated an extent from it already, but it + * has not yet created a respective ordered extent (and added it to a + * root's list of ordered extents). + * Therefore wait for any task currently allocating extents, since the + * block group's reservations counter is incremented while a read lock + * on the groups' semaphore is held and decremented after releasing + * the read access on that semaphore and creating the ordered extent. + */ + down_write(&space_info->groups_sem); + up_write(&space_info->groups_sem); + + wait_on_atomic_t(&bg->reservations, + btrfs_wait_bg_reservations_atomic_t, + TASK_UNINTERRUPTIBLE); +} + /** * btrfs_update_reserved_bytes - update the block_group and space info counters * @cache: The cache we are manipulating @@ -7025,36 +7132,35 @@ btrfs_lock_cluster(struct btrfs_block_group_cache *block_group, int delalloc) { struct btrfs_block_group_cache *used_bg = NULL; - bool locked = false; -again: + spin_lock(&cluster->refill_lock); - if (locked) { - if (used_bg == cluster->block_group) + while (1) { + used_bg = cluster->block_group; + if (!used_bg) + return NULL; + + if (used_bg == block_group) return used_bg; - up_read(&used_bg->data_rwsem); - btrfs_put_block_group(used_bg); - } + btrfs_get_block_group(used_bg); - used_bg = cluster->block_group; - if (!used_bg) - return NULL; + if (!delalloc) + return used_bg; - if (used_bg == block_group) - return used_bg; + if (down_read_trylock(&used_bg->data_rwsem)) + return used_bg; - btrfs_get_block_group(used_bg); + spin_unlock(&cluster->refill_lock); - if (!delalloc) - return used_bg; + down_read(&used_bg->data_rwsem); - if (down_read_trylock(&used_bg->data_rwsem)) - return used_bg; + spin_lock(&cluster->refill_lock); + if (used_bg == cluster->block_group) + return used_bg; - spin_unlock(&cluster->refill_lock); - down_read(&used_bg->data_rwsem); - locked = true; - goto again; + up_read(&used_bg->data_rwsem); + btrfs_put_block_group(used_bg); + } } static inline void @@ -7431,6 +7537,7 @@ checks: btrfs_add_free_space(block_group, offset, num_bytes); goto loop; } + btrfs_inc_block_group_reservations(block_group); /* we are all good, lets return */ ins->objectid = search_start; @@ -7612,8 +7719,10 @@ again: WARN_ON(num_bytes < root->sectorsize); ret = find_free_extent(root, num_bytes, empty_size, hint_byte, ins, flags, delalloc); - - if (ret == -ENOSPC) { + if (!ret && !is_data) { + btrfs_dec_block_group_reservations(root->fs_info, + ins->objectid); + } else if (ret == -ENOSPC) { if (!final_tried && ins->offset) { num_bytes = min(num_bytes >> 1, ins->offset); num_bytes = round_down(num_bytes, root->sectorsize); @@ -9058,7 +9167,7 @@ out: if (!for_reloc && root_dropped == false) btrfs_add_dead_root(root); if (err && err != -EAGAIN) - btrfs_std_error(root->fs_info, err, NULL); + btrfs_handle_fs_error(root->fs_info, err, NULL); return err; } diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 5fdf1fcb03c9..3cd57825c75f 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -3200,14 +3200,10 @@ int extent_read_full_page(struct extent_io_tree *tree, struct page *page, return ret; } -static noinline void update_nr_written(struct page *page, - struct writeback_control *wbc, - unsigned long nr_written) +static void update_nr_written(struct page *page, struct writeback_control *wbc, + unsigned long nr_written) { wbc->nr_to_write -= nr_written; - if (wbc->range_cyclic || (wbc->nr_to_write > 0 && - wbc->range_start == 0 && wbc->range_end == LLONG_MAX)) - page->mapping->writeback_index = page->index + nr_written; } /* @@ -3368,6 +3364,8 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode, while (cur <= end) { u64 em_end; + unsigned long max_nr; + if (cur >= i_size) { if (tree->ops && tree->ops->writepage_end_io_hook) tree->ops->writepage_end_io_hook(page, cur, @@ -3423,32 +3421,23 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode, continue; } - if (tree->ops && tree->ops->writepage_io_hook) { - ret = tree->ops->writepage_io_hook(page, cur, - cur + iosize - 1); - } else { - ret = 0; + max_nr = (i_size >> PAGE_SHIFT) + 1; + + set_range_writeback(tree, cur, cur + iosize - 1); + if (!PageWriteback(page)) { + btrfs_err(BTRFS_I(inode)->root->fs_info, + "page %lu not writeback, cur %llu end %llu", + page->index, cur, end); } - if (ret) { - SetPageError(page); - } else { - unsigned long max_nr = (i_size >> PAGE_SHIFT) + 1; - set_range_writeback(tree, cur, cur + iosize - 1); - if (!PageWriteback(page)) { - btrfs_err(BTRFS_I(inode)->root->fs_info, - "page %lu not writeback, cur %llu end %llu", - page->index, cur, end); - } + ret = submit_extent_page(write_flags, tree, wbc, page, + sector, iosize, pg_offset, + bdev, &epd->bio, max_nr, + end_bio_extent_writepage, + 0, 0, 0, false); + if (ret) + SetPageError(page); - ret = submit_extent_page(write_flags, tree, wbc, page, - sector, iosize, pg_offset, - bdev, &epd->bio, max_nr, - end_bio_extent_writepage, - 0, 0, 0, false); - if (ret) - SetPageError(page); - } cur = cur + iosize; pg_offset += iosize; nr++; @@ -3920,12 +3909,13 @@ static int extent_write_cache_pages(struct extent_io_tree *tree, struct inode *inode = mapping->host; int ret = 0; int done = 0; - int err = 0; int nr_to_write_done = 0; struct pagevec pvec; int nr_pages; pgoff_t index; pgoff_t end; /* Inclusive */ + pgoff_t done_index; + int range_whole = 0; int scanned = 0; int tag; @@ -3948,6 +3938,8 @@ static int extent_write_cache_pages(struct extent_io_tree *tree, } else { index = wbc->range_start >> PAGE_SHIFT; end = wbc->range_end >> PAGE_SHIFT; + if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) + range_whole = 1; scanned = 1; } if (wbc->sync_mode == WB_SYNC_ALL) @@ -3957,6 +3949,7 @@ static int extent_write_cache_pages(struct extent_io_tree *tree, retry: if (wbc->sync_mode == WB_SYNC_ALL) tag_pages_for_writeback(mapping, index, end); + done_index = index; while (!done && !nr_to_write_done && (index <= end) && (nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, tag, min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1))) { @@ -3966,6 +3959,7 @@ retry: for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; + done_index = page->index; /* * At this point we hold neither mapping->tree_lock nor * lock on the page itself: the page may be truncated or @@ -4007,8 +4001,20 @@ retry: unlock_page(page); ret = 0; } - if (!err && ret < 0) - err = ret; + if (ret < 0) { + /* + * done_index is set past this page, + * so media errors will not choke + * background writeout for the entire + * file. This has consequences for + * range_cyclic semantics (ie. it may + * not be suitable for data integrity + * writeout). + */ + done_index = page->index + 1; + done = 1; + break; + } /* * the filesystem may choose to bump up nr_to_write. @@ -4020,7 +4026,7 @@ retry: pagevec_release(&pvec); cond_resched(); } - if (!scanned && !done && !err) { + if (!scanned && !done) { /* * We hit the last page and there is more work to be done: wrap * back to the start of the file @@ -4029,8 +4035,12 @@ retry: index = 0; goto retry; } + + if (wbc->range_cyclic || (wbc->nr_to_write > 0 && range_whole)) + mapping->writeback_index = done_index; + btrfs_add_delayed_iput(inode); - return err; + return ret; } static void flush_epd_write_bio(struct extent_page_data *epd) @@ -4379,8 +4389,12 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, if (ret < 0) { btrfs_free_path(path); return ret; + } else { + WARN_ON(!ret); + if (ret == 1) + ret = 0; } - WARN_ON(!ret); + path->slots[0]--; btrfs_item_key_to_cpu(path->nodes[0], &found_key, path->slots[0]); found_type = found_key.type; @@ -4822,7 +4836,7 @@ struct extent_buffer *alloc_test_extent_buffer(struct btrfs_fs_info *fs_info, return NULL; eb->fs_info = fs_info; again: - ret = radix_tree_preload(GFP_NOFS & ~__GFP_HIGHMEM); + ret = radix_tree_preload(GFP_NOFS); if (ret) goto free_eb; spin_lock(&fs_info->buffer_lock); @@ -4923,7 +4937,7 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, if (uptodate) set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags); again: - ret = radix_tree_preload(GFP_NOFS & ~__GFP_HIGHMEM); + ret = radix_tree_preload(GFP_NOFS); if (ret) goto free_eb; diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index 9c1f160c5984..1baf19c9b79d 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -71,7 +71,6 @@ struct extent_io_ops { u64 start, u64 end, int *page_started, unsigned long *nr_written); int (*writepage_start_hook)(struct page *page, u64 start, u64 end); - int (*writepage_io_hook)(struct page *page, u64 start, u64 end); extent_submit_bio_hook_t *submit_bio_hook; int (*merge_bio_hook)(int rw, struct page *page, unsigned long offset, size_t size, struct bio *bio, diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 50dac40d9561..1933e8b07ed7 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1696,7 +1696,9 @@ again: btrfs_end_write_no_snapshoting(root); btrfs_delalloc_release_metadata(inode, release_bytes); } else { - btrfs_delalloc_release_space(inode, pos, release_bytes); + btrfs_delalloc_release_space(inode, + round_down(pos, root->sectorsize), + release_bytes); } } @@ -2956,7 +2958,7 @@ const struct file_operations btrfs_file_operations = { .fallocate = btrfs_fallocate, .unlocked_ioctl = btrfs_ioctl, #ifdef CONFIG_COMPAT - .compat_ioctl = btrfs_ioctl, + .compat_ioctl = btrfs_compat_ioctl, #endif .copy_file_range = btrfs_copy_file_range, .clone_file_range = btrfs_clone_file_range, diff --git a/fs/btrfs/inode-item.c b/fs/btrfs/inode-item.c index be4d22a5022f..b8acc07ac6c2 100644 --- a/fs/btrfs/inode-item.c +++ b/fs/btrfs/inode-item.c @@ -157,7 +157,7 @@ static int btrfs_del_inode_extref(struct btrfs_trans_handle *trans, */ if (!btrfs_find_name_in_ext_backref(path, ref_objectid, name, name_len, &extref)) { - btrfs_std_error(root->fs_info, -ENOENT, NULL); + btrfs_handle_fs_error(root->fs_info, -ENOENT, NULL); ret = -EROFS; goto out; } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 2027bbd4b05e..2debd42c4660 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -824,6 +824,7 @@ retry: async_extent->ram_size - 1, 0); goto out_free_reserve; } + btrfs_dec_block_group_reservations(root->fs_info, ins.objectid); /* * clear dirty, set writeback and unlock the pages. @@ -861,6 +862,7 @@ retry: } return; out_free_reserve: + btrfs_dec_block_group_reservations(root->fs_info, ins.objectid); btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1); out_free: extent_clear_unlock_delalloc(inode, async_extent->start, @@ -1038,6 +1040,8 @@ static noinline int cow_file_range(struct inode *inode, goto out_drop_extent_cache; } + btrfs_dec_block_group_reservations(root->fs_info, ins.objectid); + if (disk_num_bytes < cur_alloc_size) break; @@ -1066,6 +1070,7 @@ out: out_drop_extent_cache: btrfs_drop_extent_cache(inode, start, start + ram_size - 1, 0); out_reserve: + btrfs_dec_block_group_reservations(root->fs_info, ins.objectid); btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1); out_unlock: extent_clear_unlock_delalloc(inode, start, end, locked_page, @@ -1377,6 +1382,9 @@ next_slot: */ if (csum_exist_in_range(root, disk_bytenr, num_bytes)) goto out_check; + if (!btrfs_inc_nocow_writers(root->fs_info, + disk_bytenr)) + goto out_check; nocow = 1; } else if (extent_type == BTRFS_FILE_EXTENT_INLINE) { extent_end = found_key.offset + @@ -1391,6 +1399,9 @@ out_check: path->slots[0]++; if (!nolock && nocow) btrfs_end_write_no_snapshoting(root); + if (nocow) + btrfs_dec_nocow_writers(root->fs_info, + disk_bytenr); goto next_slot; } if (!nocow) { @@ -1411,6 +1422,9 @@ out_check: if (ret) { if (!nolock && nocow) btrfs_end_write_no_snapshoting(root); + if (nocow) + btrfs_dec_nocow_writers(root->fs_info, + disk_bytenr); goto error; } cow_start = (u64)-1; @@ -1453,6 +1467,8 @@ out_check: ret = btrfs_add_ordered_extent(inode, cur_offset, disk_bytenr, num_bytes, num_bytes, type); + if (nocow) + btrfs_dec_nocow_writers(root->fs_info, disk_bytenr); BUG_ON(ret); /* -ENOMEM */ if (root->root_key.objectid == @@ -7128,6 +7144,43 @@ out: return em; } +static struct extent_map *btrfs_create_dio_extent(struct inode *inode, + const u64 start, + const u64 len, + const u64 orig_start, + const u64 block_start, + const u64 block_len, + const u64 orig_block_len, + const u64 ram_bytes, + const int type) +{ + struct extent_map *em = NULL; + int ret; + + down_read(&BTRFS_I(inode)->dio_sem); + if (type != BTRFS_ORDERED_NOCOW) { + em = create_pinned_em(inode, start, len, orig_start, + block_start, block_len, orig_block_len, + ram_bytes, type); + if (IS_ERR(em)) + goto out; + } + ret = btrfs_add_ordered_extent_dio(inode, start, block_start, + len, block_len, type); + if (ret) { + if (em) { + free_extent_map(em); + btrfs_drop_extent_cache(inode, start, + start + len - 1, 0); + } + em = ERR_PTR(ret); + } + out: + up_read(&BTRFS_I(inode)->dio_sem); + + return em; +} + static struct extent_map *btrfs_new_extent_direct(struct inode *inode, u64 start, u64 len) { @@ -7143,41 +7196,13 @@ static struct extent_map *btrfs_new_extent_direct(struct inode *inode, if (ret) return ERR_PTR(ret); - /* - * Create the ordered extent before the extent map. This is to avoid - * races with the fast fsync path that would lead to it logging file - * extent items that point to disk extents that were not yet written to. - * The fast fsync path collects ordered extents into a local list and - * then collects all the new extent maps, so we must create the ordered - * extent first and make sure the fast fsync path collects any new - * ordered extents after collecting new extent maps as well. - * The fsync path simply can not rely on inode_dio_wait() because it - * causes deadlock with AIO. - */ - ret = btrfs_add_ordered_extent_dio(inode, start, ins.objectid, - ins.offset, ins.offset, 0); - if (ret) { + em = btrfs_create_dio_extent(inode, start, ins.offset, start, + ins.objectid, ins.offset, ins.offset, + ins.offset, 0); + btrfs_dec_block_group_reservations(root->fs_info, ins.objectid); + if (IS_ERR(em)) btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1); - return ERR_PTR(ret); - } - - em = create_pinned_em(inode, start, ins.offset, start, ins.objectid, - ins.offset, ins.offset, ins.offset, 0); - if (IS_ERR(em)) { - struct btrfs_ordered_extent *oe; - btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1); - oe = btrfs_lookup_ordered_extent(inode, start); - ASSERT(oe); - if (WARN_ON(!oe)) - return em; - set_bit(BTRFS_ORDERED_IOERR, &oe->flags); - set_bit(BTRFS_ORDERED_IO_DONE, &oe->flags); - btrfs_remove_ordered_extent(inode, oe); - /* Once for our lookup and once for the ordered extents tree. */ - btrfs_put_ordered_extent(oe); - btrfs_put_ordered_extent(oe); - } return em; } @@ -7649,24 +7674,21 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock, block_start = em->block_start + (start - em->start); if (can_nocow_extent(inode, start, &len, &orig_start, - &orig_block_len, &ram_bytes) == 1) { + &orig_block_len, &ram_bytes) == 1 && + btrfs_inc_nocow_writers(root->fs_info, block_start)) { + struct extent_map *em2; + + em2 = btrfs_create_dio_extent(inode, start, len, + orig_start, block_start, + len, orig_block_len, + ram_bytes, type); + btrfs_dec_nocow_writers(root->fs_info, block_start); if (type == BTRFS_ORDERED_PREALLOC) { free_extent_map(em); - em = create_pinned_em(inode, start, len, - orig_start, - block_start, len, - orig_block_len, - ram_bytes, type); - if (IS_ERR(em)) { - ret = PTR_ERR(em); - goto unlock_err; - } + em = em2; } - - ret = btrfs_add_ordered_extent_dio(inode, start, - block_start, len, len, type); - if (ret) { - free_extent_map(em); + if (em2 && IS_ERR(em2)) { + ret = PTR_ERR(em2); goto unlock_err; } goto unlock; @@ -9229,6 +9251,7 @@ struct inode *btrfs_alloc_inode(struct super_block *sb) INIT_LIST_HEAD(&ei->delalloc_inodes); INIT_LIST_HEAD(&ei->delayed_iput); RB_CLEAR_NODE(&ei->rb_node); + init_rwsem(&ei->dio_sem); return inode; } @@ -9386,10 +9409,281 @@ static int btrfs_getattr(struct vfsmount *mnt, return 0; } +static int btrfs_rename_exchange(struct inode *old_dir, + struct dentry *old_dentry, + struct inode *new_dir, + struct dentry *new_dentry) +{ + struct btrfs_trans_handle *trans; + struct btrfs_root *root = BTRFS_I(old_dir)->root; + struct btrfs_root *dest = BTRFS_I(new_dir)->root; + struct inode *new_inode = new_dentry->d_inode; + struct inode *old_inode = old_dentry->d_inode; + struct timespec ctime = CURRENT_TIME; + struct dentry *parent; + u64 old_ino = btrfs_ino(old_inode); + u64 new_ino = btrfs_ino(new_inode); + u64 old_idx = 0; + u64 new_idx = 0; + u64 root_objectid; + int ret; + bool root_log_pinned = false; + bool dest_log_pinned = false; + + /* we only allow rename subvolume link between subvolumes */ + if (old_ino != BTRFS_FIRST_FREE_OBJECTID && root != dest) + return -EXDEV; + + /* close the race window with snapshot create/destroy ioctl */ + if (old_ino == BTRFS_FIRST_FREE_OBJECTID) + down_read(&root->fs_info->subvol_sem); + if (new_ino == BTRFS_FIRST_FREE_OBJECTID) + down_read(&dest->fs_info->subvol_sem); + + /* + * We want to reserve the absolute worst case amount of items. So if + * both inodes are subvols and we need to unlink them then that would + * require 4 item modifications, but if they are both normal inodes it + * would require 5 item modifications, so we'll assume their normal + * inodes. So 5 * 2 is 10, plus 2 for the new links, so 12 total items + * should cover the worst case number of items we'll modify. + */ + trans = btrfs_start_transaction(root, 12); + if (IS_ERR(trans)) { + ret = PTR_ERR(trans); + goto out_notrans; + } + + /* + * We need to find a free sequence number both in the source and + * in the destination directory for the exchange. + */ + ret = btrfs_set_inode_index(new_dir, &old_idx); + if (ret) + goto out_fail; + ret = btrfs_set_inode_index(old_dir, &new_idx); + if (ret) + goto out_fail; + + BTRFS_I(old_inode)->dir_index = 0ULL; + BTRFS_I(new_inode)->dir_index = 0ULL; + + /* Reference for the source. */ + if (old_ino == BTRFS_FIRST_FREE_OBJECTID) { + /* force full log commit if subvolume involved. */ + btrfs_set_log_full_commit(root->fs_info, trans); + } else { + btrfs_pin_log_trans(root); + root_log_pinned = true; + ret = btrfs_insert_inode_ref(trans, dest, + new_dentry->d_name.name, + new_dentry->d_name.len, + old_ino, + btrfs_ino(new_dir), old_idx); + if (ret) + goto out_fail; + } + + /* And now for the dest. */ + if (new_ino == BTRFS_FIRST_FREE_OBJECTID) { + /* force full log commit if subvolume involved. */ + btrfs_set_log_full_commit(dest->fs_info, trans); + } else { + btrfs_pin_log_trans(dest); + dest_log_pinned = true; + ret = btrfs_insert_inode_ref(trans, root, + old_dentry->d_name.name, + old_dentry->d_name.len, + new_ino, + btrfs_ino(old_dir), new_idx); + if (ret) + goto out_fail; + } + + /* Update inode version and ctime/mtime. */ + inode_inc_iversion(old_dir); + inode_inc_iversion(new_dir); + inode_inc_iversion(old_inode); + inode_inc_iversion(new_inode); + old_dir->i_ctime = old_dir->i_mtime = ctime; + new_dir->i_ctime = new_dir->i_mtime = ctime; + old_inode->i_ctime = ctime; + new_inode->i_ctime = ctime; + + if (old_dentry->d_parent != new_dentry->d_parent) { + btrfs_record_unlink_dir(trans, old_dir, old_inode, 1); + btrfs_record_unlink_dir(trans, new_dir, new_inode, 1); + } + + /* src is a subvolume */ + if (old_ino == BTRFS_FIRST_FREE_OBJECTID) { + root_objectid = BTRFS_I(old_inode)->root->root_key.objectid; + ret = btrfs_unlink_subvol(trans, root, old_dir, + root_objectid, + old_dentry->d_name.name, + old_dentry->d_name.len); + } else { /* src is an inode */ + ret = __btrfs_unlink_inode(trans, root, old_dir, + old_dentry->d_inode, + old_dentry->d_name.name, + old_dentry->d_name.len); + if (!ret) + ret = btrfs_update_inode(trans, root, old_inode); + } + if (ret) { + btrfs_abort_transaction(trans, root, ret); + goto out_fail; + } + + /* dest is a subvolume */ + if (new_ino == BTRFS_FIRST_FREE_OBJECTID) { + root_objectid = BTRFS_I(new_inode)->root->root_key.objectid; + ret = btrfs_unlink_subvol(trans, dest, new_dir, + root_objectid, + new_dentry->d_name.name, + new_dentry->d_name.len); + } else { /* dest is an inode */ + ret = __btrfs_unlink_inode(trans, dest, new_dir, + new_dentry->d_inode, + new_dentry->d_name.name, + new_dentry->d_name.len); + if (!ret) + ret = btrfs_update_inode(trans, dest, new_inode); + } + if (ret) { + btrfs_abort_transaction(trans, root, ret); + goto out_fail; + } + + ret = btrfs_add_link(trans, new_dir, old_inode, + new_dentry->d_name.name, + new_dentry->d_name.len, 0, old_idx); + if (ret) { + btrfs_abort_transaction(trans, root, ret); + goto out_fail; + } + + ret = btrfs_add_link(trans, old_dir, new_inode, + old_dentry->d_name.name, + old_dentry->d_name.len, 0, new_idx); + if (ret) { + btrfs_abort_transaction(trans, root, ret); + goto out_fail; + } + + if (old_inode->i_nlink == 1) + BTRFS_I(old_inode)->dir_index = old_idx; + if (new_inode->i_nlink == 1) + BTRFS_I(new_inode)->dir_index = new_idx; + + if (root_log_pinned) { + parent = new_dentry->d_parent; + btrfs_log_new_name(trans, old_inode, old_dir, parent); + btrfs_end_log_trans(root); + root_log_pinned = false; + } + if (dest_log_pinned) { + parent = old_dentry->d_parent; + btrfs_log_new_name(trans, new_inode, new_dir, parent); + btrfs_end_log_trans(dest); + dest_log_pinned = false; + } +out_fail: + /* + * If we have pinned a log and an error happened, we unpin tasks + * trying to sync the log and force them to fallback to a transaction + * commit if the log currently contains any of the inodes involved in + * this rename operation (to ensure we do not persist a log with an + * inconsistent state for any of these inodes or leading to any + * inconsistencies when replayed). If the transaction was aborted, the + * abortion reason is propagated to userspace when attempting to commit + * the transaction. If the log does not contain any of these inodes, we + * allow the tasks to sync it. + */ + if (ret && (root_log_pinned || dest_log_pinned)) { + if (btrfs_inode_in_log(old_dir, root->fs_info->generation) || + btrfs_inode_in_log(new_dir, root->fs_info->generation) || + btrfs_inode_in_log(old_inode, root->fs_info->generation) || + (new_inode && + btrfs_inode_in_log(new_inode, root->fs_info->generation))) + btrfs_set_log_full_commit(root->fs_info, trans); + + if (root_log_pinned) { + btrfs_end_log_trans(root); + root_log_pinned = false; + } + if (dest_log_pinned) { + btrfs_end_log_trans(dest); + dest_log_pinned = false; + } + } + ret = btrfs_end_transaction(trans, root); +out_notrans: + if (new_ino == BTRFS_FIRST_FREE_OBJECTID) + up_read(&dest->fs_info->subvol_sem); + if (old_ino == BTRFS_FIRST_FREE_OBJECTID) + up_read(&root->fs_info->subvol_sem); + + return ret; +} + +static int btrfs_whiteout_for_rename(struct btrfs_trans_handle *trans, + struct btrfs_root *root, + struct inode *dir, + struct dentry *dentry) +{ + int ret; + struct inode *inode; + u64 objectid; + u64 index; + + ret = btrfs_find_free_ino(root, &objectid); + if (ret) + return ret; + + inode = btrfs_new_inode(trans, root, dir, + dentry->d_name.name, + dentry->d_name.len, + btrfs_ino(dir), + objectid, + S_IFCHR | WHITEOUT_MODE, + &index); + + if (IS_ERR(inode)) { + ret = PTR_ERR(inode); + return ret; + } + + inode->i_op = &btrfs_special_inode_operations; + init_special_inode(inode, inode->i_mode, + WHITEOUT_DEV); + + ret = btrfs_init_inode_security(trans, inode, dir, + &dentry->d_name); + if (ret) + goto out; + + ret = btrfs_add_nondir(trans, dir, dentry, + inode, 0, index); + if (ret) + goto out; + + ret = btrfs_update_inode(trans, root, inode); +out: + unlock_new_inode(inode); + if (ret) + inode_dec_link_count(inode); + iput(inode); + + return ret; +} + static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry, - struct inode *new_dir, struct dentry *new_dentry) + struct inode *new_dir, struct dentry *new_dentry, + unsigned int flags) { struct btrfs_trans_handle *trans; + unsigned int trans_num_items; struct btrfs_root *root = BTRFS_I(old_dir)->root; struct btrfs_root *dest = BTRFS_I(new_dir)->root; struct inode *new_inode = d_inode(new_dentry); @@ -9398,6 +9692,7 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry, u64 root_objectid; int ret; u64 old_ino = btrfs_ino(old_inode); + bool log_pinned = false; if (btrfs_ino(new_dir) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID) return -EPERM; @@ -9448,15 +9743,21 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry, * We want to reserve the absolute worst case amount of items. So if * both inodes are subvols and we need to unlink them then that would * require 4 item modifications, but if they are both normal inodes it - * would require 5 item modifications, so we'll assume their normal + * would require 5 item modifications, so we'll assume they are normal * inodes. So 5 * 2 is 10, plus 1 for the new link, so 11 total items * should cover the worst case number of items we'll modify. + * If our rename has the whiteout flag, we need more 5 units for the + * new inode (1 inode item, 1 inode ref, 2 dir items and 1 xattr item + * when selinux is enabled). */ - trans = btrfs_start_transaction(root, 11); + trans_num_items = 11; + if (flags & RENAME_WHITEOUT) + trans_num_items += 5; + trans = btrfs_start_transaction(root, trans_num_items); if (IS_ERR(trans)) { - ret = PTR_ERR(trans); - goto out_notrans; - } + ret = PTR_ERR(trans); + goto out_notrans; + } if (dest != root) btrfs_record_root_in_trans(trans, dest); @@ -9470,6 +9771,8 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry, /* force full log commit if subvolume involved. */ btrfs_set_log_full_commit(root->fs_info, trans); } else { + btrfs_pin_log_trans(root); + log_pinned = true; ret = btrfs_insert_inode_ref(trans, dest, new_dentry->d_name.name, new_dentry->d_name.len, @@ -9477,14 +9780,6 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry, btrfs_ino(new_dir), index); if (ret) goto out_fail; - /* - * this is an ugly little race, but the rename is required - * to make sure that if we crash, the inode is either at the - * old name or the new one. pinning the log transaction lets - * us make sure we don't allow a log commit to come in after - * we unlink the name but before we add the new name back in. - */ - btrfs_pin_log_trans(root); } inode_inc_iversion(old_dir); @@ -9551,12 +9846,46 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry, if (old_inode->i_nlink == 1) BTRFS_I(old_inode)->dir_index = index; - if (old_ino != BTRFS_FIRST_FREE_OBJECTID) { + if (log_pinned) { struct dentry *parent = new_dentry->d_parent; + btrfs_log_new_name(trans, old_inode, old_dir, parent); btrfs_end_log_trans(root); + log_pinned = false; + } + + if (flags & RENAME_WHITEOUT) { + ret = btrfs_whiteout_for_rename(trans, root, old_dir, + old_dentry); + + if (ret) { + btrfs_abort_transaction(trans, root, ret); + goto out_fail; + } } out_fail: + /* + * If we have pinned the log and an error happened, we unpin tasks + * trying to sync the log and force them to fallback to a transaction + * commit if the log currently contains any of the inodes involved in + * this rename operation (to ensure we do not persist a log with an + * inconsistent state for any of these inodes or leading to any + * inconsistencies when replayed). If the transaction was aborted, the + * abortion reason is propagated to userspace when attempting to commit + * the transaction. If the log does not contain any of these inodes, we + * allow the tasks to sync it. + */ + if (ret && log_pinned) { + if (btrfs_inode_in_log(old_dir, root->fs_info->generation) || + btrfs_inode_in_log(new_dir, root->fs_info->generation) || + btrfs_inode_in_log(old_inode, root->fs_info->generation) || + (new_inode && + btrfs_inode_in_log(new_inode, root->fs_info->generation))) + btrfs_set_log_full_commit(root->fs_info, trans); + + btrfs_end_log_trans(root); + log_pinned = false; + } btrfs_end_transaction(trans, root); out_notrans: if (old_ino == BTRFS_FIRST_FREE_OBJECTID) @@ -9569,10 +9898,14 @@ static int btrfs_rename2(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { - if (flags & ~RENAME_NOREPLACE) + if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT)) return -EINVAL; - return btrfs_rename(old_dir, old_dentry, new_dir, new_dentry); + if (flags & RENAME_EXCHANGE) + return btrfs_rename_exchange(old_dir, old_dentry, new_dir, + new_dentry); + + return btrfs_rename(old_dir, old_dentry, new_dir, new_dentry, flags); } static void btrfs_run_delalloc_work(struct btrfs_work *work) @@ -9941,6 +10274,7 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode, btrfs_end_transaction(trans, root); break; } + btrfs_dec_block_group_reservations(root->fs_info, ins.objectid); last_alloc = ins.offset; ret = insert_reserved_file_extent(trans, inode, @@ -10183,7 +10517,7 @@ static const struct file_operations btrfs_dir_file_operations = { .iterate = btrfs_real_readdir, .unlocked_ioctl = btrfs_ioctl, #ifdef CONFIG_COMPAT - .compat_ioctl = btrfs_ioctl, + .compat_ioctl = btrfs_compat_ioctl, #endif .release = btrfs_release_file, .fsync = btrfs_sync_file, diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 972cd0b00b21..e6714e209d0f 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -125,10 +125,10 @@ static unsigned int btrfs_flags_to_ioctl(unsigned int flags) if (flags & BTRFS_INODE_NODATACOW) iflags |= FS_NOCOW_FL; - if ((flags & BTRFS_INODE_COMPRESS) && !(flags & BTRFS_INODE_NOCOMPRESS)) - iflags |= FS_COMPR_FL; - else if (flags & BTRFS_INODE_NOCOMPRESS) + if (flags & BTRFS_INODE_NOCOMPRESS) iflags |= FS_NOCOMP_FL; + else if (flags & BTRFS_INODE_COMPRESS) + iflags |= FS_COMPR_FL; return iflags; } @@ -439,7 +439,7 @@ static noinline int create_subvol(struct inode *dir, { struct btrfs_trans_handle *trans; struct btrfs_key key; - struct btrfs_root_item root_item; + struct btrfs_root_item *root_item; struct btrfs_inode_item *inode_item; struct extent_buffer *leaf; struct btrfs_root *root = BTRFS_I(dir)->root; @@ -455,16 +455,22 @@ static noinline int create_subvol(struct inode *dir, u64 qgroup_reserved; uuid_le new_uuid; + root_item = kzalloc(sizeof(*root_item), GFP_KERNEL); + if (!root_item) + return -ENOMEM; + ret = btrfs_find_free_objectid(root->fs_info->tree_root, &objectid); if (ret) - return ret; + goto fail_free; /* * Don't create subvolume whose level is not zero. Or qgroup will be * screwed up since it assumes subvolume qgroup's level to be 0. */ - if (btrfs_qgroup_level(objectid)) - return -ENOSPC; + if (btrfs_qgroup_level(objectid)) { + ret = -ENOSPC; + goto fail_free; + } btrfs_init_block_rsv(&block_rsv, BTRFS_BLOCK_RSV_TEMP); /* @@ -474,14 +480,14 @@ static noinline int create_subvol(struct inode *dir, ret = btrfs_subvolume_reserve_metadata(root, &block_rsv, 8, &qgroup_reserved, false); if (ret) - return ret; + goto fail_free; trans = btrfs_start_transaction(root, 0); if (IS_ERR(trans)) { ret = PTR_ERR(trans); btrfs_subvolume_release_metadata(root, &block_rsv, qgroup_reserved); - return ret; + goto fail_free; } trans->block_rsv = &block_rsv; trans->bytes_reserved = block_rsv.size; @@ -509,47 +515,45 @@ static noinline int create_subvol(struct inode *dir, BTRFS_UUID_SIZE); btrfs_mark_buffer_dirty(leaf); - memset(&root_item, 0, sizeof(root_item)); - - inode_item = &root_item.inode; + inode_item = &root_item->inode; btrfs_set_stack_inode_generation(inode_item, 1); btrfs_set_stack_inode_size(inode_item, 3); btrfs_set_stack_inode_nlink(inode_item, 1); btrfs_set_stack_inode_nbytes(inode_item, root->nodesize); btrfs_set_stack_inode_mode(inode_item, S_IFDIR | 0755); - btrfs_set_root_flags(&root_item, 0); - btrfs_set_root_limit(&root_item, 0); + btrfs_set_root_flags(root_item, 0); + btrfs_set_root_limit(root_item, 0); btrfs_set_stack_inode_flags(inode_item, BTRFS_INODE_ROOT_ITEM_INIT); - btrfs_set_root_bytenr(&root_item, leaf->start); - btrfs_set_root_generation(&root_item, trans->transid); - btrfs_set_root_level(&root_item, 0); - btrfs_set_root_refs(&root_item, 1); - btrfs_set_root_used(&root_item, leaf->len); - btrfs_set_root_last_snapshot(&root_item, 0); + btrfs_set_root_bytenr(root_item, leaf->start); + btrfs_set_root_generation(root_item, trans->transid); + btrfs_set_root_level(root_item, 0); + btrfs_set_root_refs(root_item, 1); + btrfs_set_root_used(root_item, leaf->len); + btrfs_set_root_last_snapshot(root_item, 0); - btrfs_set_root_generation_v2(&root_item, - btrfs_root_generation(&root_item)); + btrfs_set_root_generation_v2(root_item, + btrfs_root_generation(root_item)); uuid_le_gen(&new_uuid); - memcpy(root_item.uuid, new_uuid.b, BTRFS_UUID_SIZE); - btrfs_set_stack_timespec_sec(&root_item.otime, cur_time.tv_sec); - btrfs_set_stack_timespec_nsec(&root_item.otime, cur_time.tv_nsec); - root_item.ctime = root_item.otime; - btrfs_set_root_ctransid(&root_item, trans->transid); - btrfs_set_root_otransid(&root_item, trans->transid); + memcpy(root_item->uuid, new_uuid.b, BTRFS_UUID_SIZE); + btrfs_set_stack_timespec_sec(&root_item->otime, cur_time.tv_sec); + btrfs_set_stack_timespec_nsec(&root_item->otime, cur_time.tv_nsec); + root_item->ctime = root_item->otime; + btrfs_set_root_ctransid(root_item, trans->transid); + btrfs_set_root_otransid(root_item, trans->transid); btrfs_tree_unlock(leaf); free_extent_buffer(leaf); leaf = NULL; - btrfs_set_root_dirid(&root_item, new_dirid); + btrfs_set_root_dirid(root_item, new_dirid); key.objectid = objectid; key.offset = 0; key.type = BTRFS_ROOT_ITEM_KEY; ret = btrfs_insert_root(trans, root->fs_info->tree_root, &key, - &root_item); + root_item); if (ret) goto fail; @@ -601,12 +605,13 @@ static noinline int create_subvol(struct inode *dir, BUG_ON(ret); ret = btrfs_uuid_tree_add(trans, root->fs_info->uuid_root, - root_item.uuid, BTRFS_UUID_KEY_SUBVOL, + root_item->uuid, BTRFS_UUID_KEY_SUBVOL, objectid); if (ret) btrfs_abort_transaction(trans, root, ret); fail: + kfree(root_item); trans->block_rsv = NULL; trans->bytes_reserved = 0; btrfs_subvolume_release_metadata(root, &block_rsv, qgroup_reserved); @@ -629,6 +634,10 @@ fail: d_instantiate(dentry, inode); } return ret; + +fail_free: + kfree(root_item); + return ret; } static void btrfs_wait_for_no_snapshoting_writes(struct btrfs_root *root) @@ -681,7 +690,7 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir, if (ret) goto dec_and_free; - btrfs_wait_ordered_extents(root, -1); + btrfs_wait_ordered_extents(root, -1, 0, (u64)-1); btrfs_init_block_rsv(&pending_snapshot->block_rsv, BTRFS_BLOCK_RSV_TEMP); @@ -2667,10 +2676,10 @@ out: return ret; } -static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg) +static long btrfs_ioctl_rm_dev_v2(struct file *file, void __user *arg) { struct btrfs_root *root = BTRFS_I(file_inode(file))->root; - struct btrfs_ioctl_vol_args *vol_args; + struct btrfs_ioctl_vol_args_v2 *vol_args; int ret; if (!capable(CAP_SYS_ADMIN)) @@ -2686,7 +2695,9 @@ static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg) goto err_drop; } - vol_args->name[BTRFS_PATH_NAME_MAX] = '\0'; + /* Check for compatibility reject unknown flags */ + if (vol_args->flags & ~BTRFS_VOL_ARG_V2_FLAGS_SUPPORTED) + return -EOPNOTSUPP; if (atomic_xchg(&root->fs_info->mutually_exclusive_operation_running, 1)) { @@ -2695,13 +2706,23 @@ static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg) } mutex_lock(&root->fs_info->volume_mutex); - ret = btrfs_rm_device(root, vol_args->name); + if (vol_args->flags & BTRFS_DEVICE_SPEC_BY_ID) { + ret = btrfs_rm_device(root, NULL, vol_args->devid); + } else { + vol_args->name[BTRFS_SUBVOL_NAME_MAX] = '\0'; + ret = btrfs_rm_device(root, vol_args->name, 0); + } mutex_unlock(&root->fs_info->volume_mutex); atomic_set(&root->fs_info->mutually_exclusive_operation_running, 0); - if (!ret) - btrfs_info(root->fs_info, "disk deleted %s",vol_args->name); - + if (!ret) { + if (vol_args->flags & BTRFS_DEVICE_SPEC_BY_ID) + btrfs_info(root->fs_info, "device deleted: id %llu", + vol_args->devid); + else + btrfs_info(root->fs_info, "device deleted: %s", + vol_args->name); + } out: kfree(vol_args); err_drop: @@ -2709,6 +2730,47 @@ err_drop: return ret; } +static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg) +{ + struct btrfs_root *root = BTRFS_I(file_inode(file))->root; + struct btrfs_ioctl_vol_args *vol_args; + int ret; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + ret = mnt_want_write_file(file); + if (ret) + return ret; + + if (atomic_xchg(&root->fs_info->mutually_exclusive_operation_running, + 1)) { + ret = BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS; + goto out_drop_write; + } + + vol_args = memdup_user(arg, sizeof(*vol_args)); + if (IS_ERR(vol_args)) { + ret = PTR_ERR(vol_args); + goto out; + } + + vol_args->name[BTRFS_PATH_NAME_MAX] = '\0'; + mutex_lock(&root->fs_info->volume_mutex); + ret = btrfs_rm_device(root, vol_args->name, 0); + mutex_unlock(&root->fs_info->volume_mutex); + + if (!ret) + btrfs_info(root->fs_info, "disk deleted %s",vol_args->name); + kfree(vol_args); +out: + atomic_set(&root->fs_info->mutually_exclusive_operation_running, 0); +out_drop_write: + mnt_drop_write_file(file); + + return ret; +} + static long btrfs_ioctl_fs_info(struct btrfs_root *root, void __user *arg) { struct btrfs_ioctl_fs_info_args *fi_args; @@ -3468,13 +3530,16 @@ static int btrfs_clone(struct inode *src, struct inode *inode, u64 last_dest_end = destoff; ret = -ENOMEM; - buf = vmalloc(root->nodesize); - if (!buf) - return ret; + buf = kmalloc(root->nodesize, GFP_KERNEL | __GFP_NOWARN); + if (!buf) { + buf = vmalloc(root->nodesize); + if (!buf) + return ret; + } path = btrfs_alloc_path(); if (!path) { - vfree(buf); + kvfree(buf); return ret; } @@ -3775,7 +3840,7 @@ process_slot: out: btrfs_free_path(path); - vfree(buf); + kvfree(buf); return ret; } @@ -4376,7 +4441,7 @@ static long btrfs_ioctl_dev_replace(struct btrfs_root *root, void __user *arg) 1)) { ret = BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS; } else { - ret = btrfs_dev_replace_start(root, p); + ret = btrfs_dev_replace_by_ioctl(root, p); atomic_set( &root->fs_info->mutually_exclusive_operation_running, 0); @@ -4847,8 +4912,8 @@ static long btrfs_ioctl_qgroup_assign(struct file *file, void __user *arg) /* update qgroup status and info */ err = btrfs_run_qgroups(trans, root->fs_info); if (err < 0) - btrfs_std_error(root->fs_info, ret, - "failed to update qgroup status and info\n"); + btrfs_handle_fs_error(root->fs_info, err, + "failed to update qgroup status and info"); err = btrfs_end_transaction(trans, root); if (err && !ret) ret = err; @@ -5394,9 +5459,15 @@ static int btrfs_ioctl_set_features(struct file *file, void __user *arg) if (ret) return ret; + ret = mnt_want_write_file(file); + if (ret) + return ret; + trans = btrfs_start_transaction(root, 0); - if (IS_ERR(trans)) - return PTR_ERR(trans); + if (IS_ERR(trans)) { + ret = PTR_ERR(trans); + goto out_drop_write; + } spin_lock(&root->fs_info->super_lock); newflags = btrfs_super_compat_flags(super_block); @@ -5415,7 +5486,11 @@ static int btrfs_ioctl_set_features(struct file *file, void __user *arg) btrfs_set_super_incompat_flags(super_block, newflags); spin_unlock(&root->fs_info->super_lock); - return btrfs_commit_transaction(trans, root); + ret = btrfs_commit_transaction(trans, root); +out_drop_write: + mnt_drop_write_file(file); + + return ret; } long btrfs_ioctl(struct file *file, unsigned int @@ -5459,6 +5534,8 @@ long btrfs_ioctl(struct file *file, unsigned int return btrfs_ioctl_add_dev(root, argp); case BTRFS_IOC_RM_DEV: return btrfs_ioctl_rm_dev(file, argp); + case BTRFS_IOC_RM_DEV_V2: + return btrfs_ioctl_rm_dev_v2(file, argp); case BTRFS_IOC_FS_INFO: return btrfs_ioctl_fs_info(root, argp); case BTRFS_IOC_DEV_INFO: @@ -5552,3 +5629,24 @@ long btrfs_ioctl(struct file *file, unsigned int return -ENOTTY; } + +#ifdef CONFIG_COMPAT +long btrfs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + switch (cmd) { + case FS_IOC32_GETFLAGS: + cmd = FS_IOC_GETFLAGS; + break; + case FS_IOC32_SETFLAGS: + cmd = FS_IOC_SETFLAGS; + break; + case FS_IOC32_GETVERSION: + cmd = FS_IOC_GETVERSION; + break; + default: + return -ENOIOCTLCMD; + } + + return btrfs_ioctl(file, cmd, (unsigned long) compat_ptr(arg)); +} +#endif diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index 0de7da5a610d..559170464d7c 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -661,14 +661,15 @@ static void btrfs_run_ordered_extent_work(struct btrfs_work *work) * wait for all the ordered extents in a root. This is done when balancing * space between drives. */ -int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr) +int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr, + const u64 range_start, const u64 range_len) { - struct list_head splice, works; + LIST_HEAD(splice); + LIST_HEAD(skipped); + LIST_HEAD(works); struct btrfs_ordered_extent *ordered, *next; int count = 0; - - INIT_LIST_HEAD(&splice); - INIT_LIST_HEAD(&works); + const u64 range_end = range_start + range_len; mutex_lock(&root->ordered_extent_mutex); spin_lock(&root->ordered_extent_lock); @@ -676,6 +677,14 @@ int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr) while (!list_empty(&splice) && nr) { ordered = list_first_entry(&splice, struct btrfs_ordered_extent, root_extent_list); + + if (range_end <= ordered->start || + ordered->start + ordered->disk_len <= range_start) { + list_move_tail(&ordered->root_extent_list, &skipped); + cond_resched_lock(&root->ordered_extent_lock); + continue; + } + list_move_tail(&ordered->root_extent_list, &root->ordered_extents); atomic_inc(&ordered->refs); @@ -694,6 +703,7 @@ int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr) nr--; count++; } + list_splice_tail(&skipped, &root->ordered_extents); list_splice_tail(&splice, &root->ordered_extents); spin_unlock(&root->ordered_extent_lock); @@ -708,7 +718,8 @@ int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr) return count; } -void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, int nr) +void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, int nr, + const u64 range_start, const u64 range_len) { struct btrfs_root *root; struct list_head splice; @@ -728,7 +739,8 @@ void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, int nr) &fs_info->ordered_roots); spin_unlock(&fs_info->ordered_root_lock); - done = btrfs_wait_ordered_extents(root, nr); + done = btrfs_wait_ordered_extents(root, nr, + range_start, range_len); btrfs_put_fs_root(root); spin_lock(&fs_info->ordered_root_lock); diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h index ae068bbddc0d..2049c9be85ee 100644 --- a/fs/btrfs/ordered-data.h +++ b/fs/btrfs/ordered-data.h @@ -197,8 +197,10 @@ int btrfs_ordered_update_i_size(struct inode *inode, u64 offset, struct btrfs_ordered_extent *ordered); int btrfs_find_ordered_sum(struct inode *inode, u64 offset, u64 disk_bytenr, u32 *sum, int len); -int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr); -void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, int nr); +int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr, + const u64 range_start, const u64 range_len); +void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, int nr, + const u64 range_start, const u64 range_len); void btrfs_get_logged_extents(struct inode *inode, struct list_head *logged_list, const loff_t start, diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 852be779a834..0477dca154ed 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -2418,7 +2418,7 @@ again: } out: if (ret) { - btrfs_std_error(root->fs_info, ret, NULL); + btrfs_handle_fs_error(root->fs_info, ret, NULL); if (!list_empty(&reloc_roots)) free_reloc_roots(&reloc_roots); @@ -4253,12 +4253,11 @@ int btrfs_relocate_block_group(struct btrfs_root *extent_root, u64 group_start) btrfs_info(extent_root->fs_info, "relocating block group %llu flags %llu", rc->block_group->key.objectid, rc->block_group->flags); - ret = btrfs_start_delalloc_roots(fs_info, 0, -1); - if (ret < 0) { - err = ret; - goto out; - } - btrfs_wait_ordered_roots(fs_info, -1); + btrfs_wait_block_group_reservations(rc->block_group); + btrfs_wait_nocow_writers(rc->block_group); + btrfs_wait_ordered_roots(fs_info, -1, + rc->block_group->key.objectid, + rc->block_group->key.offset); while (1) { mutex_lock(&fs_info->cleaner_mutex); diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c index 5ddf14e1b2d2..f1c30861d062 100644 --- a/fs/btrfs/root-tree.c +++ b/fs/btrfs/root-tree.c @@ -284,7 +284,7 @@ int btrfs_find_orphan_roots(struct btrfs_root *tree_root) trans = btrfs_join_transaction(tree_root); if (IS_ERR(trans)) { err = PTR_ERR(trans); - btrfs_std_error(tree_root->fs_info, err, + btrfs_handle_fs_error(tree_root->fs_info, err, "Failed to start trans to delete " "orphan item"); break; @@ -293,7 +293,7 @@ int btrfs_find_orphan_roots(struct btrfs_root *tree_root) root_key.objectid); btrfs_end_transaction(trans, tree_root); if (err) { - btrfs_std_error(tree_root->fs_info, err, + btrfs_handle_fs_error(tree_root->fs_info, err, "Failed to delete root orphan " "item"); break; diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 6838b2ca3cab..46d847f66e4b 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -1350,7 +1350,7 @@ static int scrub_setup_recheck_block(struct scrub_block *original_sblock, recover->bbio = bbio; recover->map_length = mapped_length; - BUG_ON(page_index >= SCRUB_PAGES_PER_RD_BIO); + BUG_ON(page_index >= SCRUB_MAX_PAGES_PER_BLOCK); nmirrors = min(scrub_nr_raid_mirrors(bbio), BTRFS_MAX_MIRRORS); @@ -2127,6 +2127,8 @@ static void scrub_missing_raid56_end_io(struct bio *bio) if (bio->bi_error) sblock->no_io_error_seen = 0; + bio_put(bio); + btrfs_queue_work(fs_info->scrub_workers, &sblock->work); } @@ -2179,7 +2181,7 @@ static void scrub_missing_raid56_pages(struct scrub_block *sblock) struct btrfs_fs_info *fs_info = sctx->dev_root->fs_info; u64 length = sblock->page_count * PAGE_SIZE; u64 logical = sblock->pagev[0]->logical; - struct btrfs_bio *bbio; + struct btrfs_bio *bbio = NULL; struct bio *bio; struct btrfs_raid_bio *rbio; int ret; @@ -2860,7 +2862,7 @@ static noinline_for_stack int scrub_raid56_parity(struct scrub_ctx *sctx, int extent_mirror_num; int stop_loop = 0; - nsectors = map->stripe_len / root->sectorsize; + nsectors = div_u64(map->stripe_len, root->sectorsize); bitmap_len = scrub_calc_parity_bitmap_len(nsectors); sparity = kzalloc(sizeof(struct scrub_parity) + 2 * bitmap_len, GFP_NOFS); @@ -2980,6 +2982,7 @@ again: extent_len); mapped_length = extent_len; + bbio = NULL; ret = btrfs_map_block(fs_info, READ, extent_logical, &mapped_length, &bbio, 0); if (!ret) { @@ -3070,7 +3073,6 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx, int slot; u64 nstripes; struct extent_buffer *l; - struct btrfs_key key; u64 physical; u64 logical; u64 logic_end; @@ -3079,7 +3081,7 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx, int mirror_num; struct reada_control *reada1; struct reada_control *reada2; - struct btrfs_key key_start; + struct btrfs_key key; struct btrfs_key key_end; u64 increment = map->stripe_len; u64 offset; @@ -3158,21 +3160,21 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx, scrub_blocked_if_needed(fs_info); /* FIXME it might be better to start readahead at commit root */ - key_start.objectid = logical; - key_start.type = BTRFS_EXTENT_ITEM_KEY; - key_start.offset = (u64)0; + key.objectid = logical; + key.type = BTRFS_EXTENT_ITEM_KEY; + key.offset = (u64)0; key_end.objectid = logic_end; key_end.type = BTRFS_METADATA_ITEM_KEY; key_end.offset = (u64)-1; - reada1 = btrfs_reada_add(root, &key_start, &key_end); + reada1 = btrfs_reada_add(root, &key, &key_end); - key_start.objectid = BTRFS_EXTENT_CSUM_OBJECTID; - key_start.type = BTRFS_EXTENT_CSUM_KEY; - key_start.offset = logical; + key.objectid = BTRFS_EXTENT_CSUM_OBJECTID; + key.type = BTRFS_EXTENT_CSUM_KEY; + key.offset = logical; key_end.objectid = BTRFS_EXTENT_CSUM_OBJECTID; key_end.type = BTRFS_EXTENT_CSUM_KEY; key_end.offset = logic_end; - reada2 = btrfs_reada_add(csum_root, &key_start, &key_end); + reada2 = btrfs_reada_add(csum_root, &key, &key_end); if (!IS_ERR(reada1)) btrfs_reada_wait(reada1); diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index e9710f461008..b71dd298385c 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -5939,6 +5939,7 @@ long btrfs_ioctl_send(struct file *mnt_file, void __user *arg_) u32 i; u64 *clone_sources_tmp = NULL; int clone_sources_to_rollback = 0; + unsigned alloc_size; int sort_clone_roots = 0; int index; @@ -5978,6 +5979,12 @@ long btrfs_ioctl_send(struct file *mnt_file, void __user *arg_) goto out; } + if (arg->clone_sources_count > + ULLONG_MAX / sizeof(*arg->clone_sources)) { + ret = -EINVAL; + goto out; + } + if (!access_ok(VERIFY_READ, arg->clone_sources, sizeof(*arg->clone_sources) * arg->clone_sources_count)) { @@ -6022,40 +6029,53 @@ long btrfs_ioctl_send(struct file *mnt_file, void __user *arg_) sctx->clone_roots_cnt = arg->clone_sources_count; sctx->send_max_size = BTRFS_SEND_BUF_SIZE; - sctx->send_buf = vmalloc(sctx->send_max_size); + sctx->send_buf = kmalloc(sctx->send_max_size, GFP_KERNEL | __GFP_NOWARN); if (!sctx->send_buf) { - ret = -ENOMEM; - goto out; + sctx->send_buf = vmalloc(sctx->send_max_size); + if (!sctx->send_buf) { + ret = -ENOMEM; + goto out; + } } - sctx->read_buf = vmalloc(BTRFS_SEND_READ_SIZE); + sctx->read_buf = kmalloc(BTRFS_SEND_READ_SIZE, GFP_KERNEL | __GFP_NOWARN); if (!sctx->read_buf) { - ret = -ENOMEM; - goto out; + sctx->read_buf = vmalloc(BTRFS_SEND_READ_SIZE); + if (!sctx->read_buf) { + ret = -ENOMEM; + goto out; + } } sctx->pending_dir_moves = RB_ROOT; sctx->waiting_dir_moves = RB_ROOT; sctx->orphan_dirs = RB_ROOT; - sctx->clone_roots = vzalloc(sizeof(struct clone_root) * - (arg->clone_sources_count + 1)); + alloc_size = sizeof(struct clone_root) * (arg->clone_sources_count + 1); + + sctx->clone_roots = kzalloc(alloc_size, GFP_KERNEL | __GFP_NOWARN); if (!sctx->clone_roots) { - ret = -ENOMEM; - goto out; + sctx->clone_roots = vzalloc(alloc_size); + if (!sctx->clone_roots) { + ret = -ENOMEM; + goto out; + } } + alloc_size = arg->clone_sources_count * sizeof(*arg->clone_sources); + if (arg->clone_sources_count) { - clone_sources_tmp = vmalloc(arg->clone_sources_count * - sizeof(*arg->clone_sources)); + clone_sources_tmp = kmalloc(alloc_size, GFP_KERNEL | __GFP_NOWARN); if (!clone_sources_tmp) { - ret = -ENOMEM; - goto out; + clone_sources_tmp = vmalloc(alloc_size); + if (!clone_sources_tmp) { + ret = -ENOMEM; + goto out; + } } ret = copy_from_user(clone_sources_tmp, arg->clone_sources, - arg->clone_sources_count * - sizeof(*arg->clone_sources)); + alloc_size); if (ret) { ret = -EFAULT; goto out; @@ -6089,7 +6109,7 @@ long btrfs_ioctl_send(struct file *mnt_file, void __user *arg_) sctx->clone_roots[i].root = clone_root; clone_sources_to_rollback = i + 1; } - vfree(clone_sources_tmp); + kvfree(clone_sources_tmp); clone_sources_tmp = NULL; } @@ -6207,15 +6227,15 @@ out: btrfs_root_dec_send_in_progress(sctx->parent_root); kfree(arg); - vfree(clone_sources_tmp); + kvfree(clone_sources_tmp); if (sctx) { if (sctx->send_filp) fput(sctx->send_filp); - vfree(sctx->clone_roots); - vfree(sctx->send_buf); - vfree(sctx->read_buf); + kvfree(sctx->clone_roots); + kvfree(sctx->send_buf); + kvfree(sctx->read_buf); name_cache_free(sctx); diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 01ef1865db63..4e59a91a11e0 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -97,15 +97,6 @@ const char *btrfs_decode_error(int errno) return errstr; } -static void save_error_info(struct btrfs_fs_info *fs_info) -{ - /* - * today we only save the error info into ram. Long term we'll - * also send it down to the disk - */ - set_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state); -} - /* btrfs handle error by forcing the filesystem readonly */ static void btrfs_handle_error(struct btrfs_fs_info *fs_info) { @@ -131,11 +122,11 @@ static void btrfs_handle_error(struct btrfs_fs_info *fs_info) } /* - * __btrfs_std_error decodes expected errors from the caller and + * __btrfs_handle_fs_error decodes expected errors from the caller and * invokes the approciate error response. */ __cold -void __btrfs_std_error(struct btrfs_fs_info *fs_info, const char *function, +void __btrfs_handle_fs_error(struct btrfs_fs_info *fs_info, const char *function, unsigned int line, int errno, const char *fmt, ...) { struct super_block *sb = fs_info->sb; @@ -170,8 +161,13 @@ void __btrfs_std_error(struct btrfs_fs_info *fs_info, const char *function, } #endif + /* + * Today we only save the error info to memory. Long term we'll + * also send it down to the disk + */ + set_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state); + /* Don't go through full error handling during mount */ - save_error_info(fs_info); if (sb->s_flags & MS_BORN) btrfs_handle_error(fs_info); } @@ -252,7 +248,7 @@ void __btrfs_abort_transaction(struct btrfs_trans_handle *trans, /* Wake up anybody who may be waiting on this transaction */ wake_up(&root->fs_info->transaction_wait); wake_up(&root->fs_info->transaction_blocked_wait); - __btrfs_std_error(root->fs_info, function, line, errno, NULL); + __btrfs_handle_fs_error(root->fs_info, function, line, errno, NULL); } /* * __btrfs_panic decodes unexpected, fatal errors from the caller, @@ -1160,7 +1156,7 @@ int btrfs_sync_fs(struct super_block *sb, int wait) return 0; } - btrfs_wait_ordered_roots(fs_info, -1); + btrfs_wait_ordered_roots(fs_info, -1, 0, (u64)-1); trans = btrfs_attach_transaction_barrier(root); if (IS_ERR(trans)) { @@ -1488,10 +1484,10 @@ static int setup_security_options(struct btrfs_fs_info *fs_info, memcpy(&fs_info->security_opts, sec_opts, sizeof(*sec_opts)); } else { /* - * Since SELinux(the only one supports security_mnt_opts) does - * NOT support changing context during remount/mount same sb, - * This must be the same or part of the same security options, - * just free it. + * Since SELinux (the only one supporting security_mnt_opts) + * does NOT support changing context during remount/mount of + * the same sb, this must be the same or part of the same + * security options, just free it. */ security_free_mnt_opts(sec_opts); } @@ -1669,8 +1665,8 @@ static inline void btrfs_remount_cleanup(struct btrfs_fs_info *fs_info, unsigned long old_opts) { /* - * We need cleanup all defragable inodes if the autodefragment is - * close or the fs is R/O. + * We need to cleanup all defragable inodes if the autodefragment is + * close or the filesystem is read only. */ if (btrfs_raw_test_opt(old_opts, AUTO_DEFRAG) && (!btrfs_raw_test_opt(fs_info->mount_opt, AUTO_DEFRAG) || @@ -2051,9 +2047,10 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf) struct btrfs_block_rsv *block_rsv = &fs_info->global_block_rsv; int ret; u64 thresh = 0; + int mixed = 0; /* - * holding chunk_muext to avoid allocating new chunks, holding + * holding chunk_mutex to avoid allocating new chunks, holding * device_list_mutex to avoid the device being removed */ rcu_read_lock(); @@ -2076,8 +2073,17 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf) } } } - if (found->flags & BTRFS_BLOCK_GROUP_METADATA) - total_free_meta += found->disk_total - found->disk_used; + + /* + * Metadata in mixed block goup profiles are accounted in data + */ + if (!mixed && found->flags & BTRFS_BLOCK_GROUP_METADATA) { + if (found->flags & BTRFS_BLOCK_GROUP_DATA) + mixed = 1; + else + total_free_meta += found->disk_total - + found->disk_used; + } total_used += found->disk_used; } @@ -2090,7 +2096,11 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf) /* Account global block reserve as used, it's in logical size already */ spin_lock(&block_rsv->lock); - buf->f_bfree -= block_rsv->size >> bits; + /* Mixed block groups accounting is not byte-accurate, avoid overflow */ + if (buf->f_bfree >= block_rsv->size >> bits) + buf->f_bfree -= block_rsv->size >> bits; + else + buf->f_bfree = 0; spin_unlock(&block_rsv->lock); buf->f_bavail = div_u64(total_free_data, factor); @@ -2115,7 +2125,7 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf) */ thresh = 4 * 1024 * 1024; - if (total_free_meta - thresh < block_rsv->size) + if (!mixed && total_free_meta - thresh < block_rsv->size) buf->f_bavail = 0; buf->f_type = BTRFS_SUPER_MAGIC; diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c index 539e7b5e3f86..4879656bda3c 100644 --- a/fs/btrfs/sysfs.c +++ b/fs/btrfs/sysfs.c @@ -120,6 +120,9 @@ static ssize_t btrfs_feature_attr_store(struct kobject *kobj, if (!fs_info) return -EPERM; + if (fs_info->sb->s_flags & MS_RDONLY) + return -EROFS; + ret = kstrtoul(skip_spaces(buf), 0, &val); if (ret) return ret; @@ -364,7 +367,13 @@ static ssize_t btrfs_label_show(struct kobject *kobj, { struct btrfs_fs_info *fs_info = to_fs_info(kobj); char *label = fs_info->super_copy->label; - return snprintf(buf, PAGE_SIZE, label[0] ? "%s\n" : "%s", label); + ssize_t ret; + + spin_lock(&fs_info->super_lock); + ret = snprintf(buf, PAGE_SIZE, label[0] ? "%s\n" : "%s", label); + spin_unlock(&fs_info->super_lock); + + return ret; } static ssize_t btrfs_label_store(struct kobject *kobj, @@ -374,6 +383,9 @@ static ssize_t btrfs_label_store(struct kobject *kobj, struct btrfs_fs_info *fs_info = to_fs_info(kobj); size_t p_len; + if (!fs_info) + return -EPERM; + if (fs_info->sb->s_flags & MS_RDONLY) return -EROFS; diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 98b93d9c6213..f6e24cb423ae 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -311,10 +311,11 @@ loop: * when the transaction commits */ static int record_root_in_trans(struct btrfs_trans_handle *trans, - struct btrfs_root *root) + struct btrfs_root *root, + int force) { - if (test_bit(BTRFS_ROOT_REF_COWS, &root->state) && - root->last_trans < trans->transid) { + if ((test_bit(BTRFS_ROOT_REF_COWS, &root->state) && + root->last_trans < trans->transid) || force) { WARN_ON(root == root->fs_info->extent_root); WARN_ON(root->commit_root != root->node); @@ -331,7 +332,7 @@ static int record_root_in_trans(struct btrfs_trans_handle *trans, smp_wmb(); spin_lock(&root->fs_info->fs_roots_radix_lock); - if (root->last_trans == trans->transid) { + if (root->last_trans == trans->transid && !force) { spin_unlock(&root->fs_info->fs_roots_radix_lock); return 0; } @@ -402,7 +403,7 @@ int btrfs_record_root_in_trans(struct btrfs_trans_handle *trans, return 0; mutex_lock(&root->fs_info->reloc_mutex); - record_root_in_trans(trans, root); + record_root_in_trans(trans, root, 0); mutex_unlock(&root->fs_info->reloc_mutex); return 0; @@ -1310,6 +1311,97 @@ int btrfs_defrag_root(struct btrfs_root *root) return ret; } +/* Bisesctability fixup, remove in 4.8 */ +#ifndef btrfs_std_error +#define btrfs_std_error btrfs_handle_fs_error +#endif + +/* + * Do all special snapshot related qgroup dirty hack. + * + * Will do all needed qgroup inherit and dirty hack like switch commit + * roots inside one transaction and write all btree into disk, to make + * qgroup works. + */ +static int qgroup_account_snapshot(struct btrfs_trans_handle *trans, + struct btrfs_root *src, + struct btrfs_root *parent, + struct btrfs_qgroup_inherit *inherit, + u64 dst_objectid) +{ + struct btrfs_fs_info *fs_info = src->fs_info; + int ret; + + /* + * Save some performance in the case that qgroups are not + * enabled. If this check races with the ioctl, rescan will + * kick in anyway. + */ + mutex_lock(&fs_info->qgroup_ioctl_lock); + if (!fs_info->quota_enabled) { + mutex_unlock(&fs_info->qgroup_ioctl_lock); + return 0; + } + mutex_unlock(&fs_info->qgroup_ioctl_lock); + + /* + * We are going to commit transaction, see btrfs_commit_transaction() + * comment for reason locking tree_log_mutex + */ + mutex_lock(&fs_info->tree_log_mutex); + + ret = commit_fs_roots(trans, src); + if (ret) + goto out; + ret = btrfs_qgroup_prepare_account_extents(trans, fs_info); + if (ret < 0) + goto out; + ret = btrfs_qgroup_account_extents(trans, fs_info); + if (ret < 0) + goto out; + + /* Now qgroup are all updated, we can inherit it to new qgroups */ + ret = btrfs_qgroup_inherit(trans, fs_info, + src->root_key.objectid, dst_objectid, + inherit); + if (ret < 0) + goto out; + + /* + * Now we do a simplified commit transaction, which will: + * 1) commit all subvolume and extent tree + * To ensure all subvolume and extent tree have a valid + * commit_root to accounting later insert_dir_item() + * 2) write all btree blocks onto disk + * This is to make sure later btree modification will be cowed + * Or commit_root can be populated and cause wrong qgroup numbers + * In this simplified commit, we don't really care about other trees + * like chunk and root tree, as they won't affect qgroup. + * And we don't write super to avoid half committed status. + */ + ret = commit_cowonly_roots(trans, src); + if (ret) + goto out; + switch_commit_roots(trans->transaction, fs_info); + ret = btrfs_write_and_wait_transaction(trans, src); + if (ret) + btrfs_std_error(fs_info, ret, + "Error while writing out transaction for qgroup"); + +out: + mutex_unlock(&fs_info->tree_log_mutex); + + /* + * Force parent root to be updated, as we recorded it before so its + * last_trans == cur_transid. + * Or it won't be committed again onto disk after later + * insert_dir_item() + */ + if (!ret) + record_root_in_trans(trans, parent, 1); + return ret; +} + /* * new snapshots need to be created at a very specific time in the * transaction commit. This does the actual creation. @@ -1383,7 +1475,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, dentry = pending->dentry; parent_inode = pending->dir; parent_root = BTRFS_I(parent_inode)->root; - record_root_in_trans(trans, parent_root); + record_root_in_trans(trans, parent_root, 0); cur_time = current_fs_time(parent_inode->i_sb); @@ -1420,7 +1512,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, goto fail; } - record_root_in_trans(trans, root); + record_root_in_trans(trans, root, 0); btrfs_set_root_last_snapshot(&root->root_item, trans->transid); memcpy(new_root_item, &root->root_item, sizeof(*new_root_item)); btrfs_check_and_init_root_item(new_root_item); @@ -1516,6 +1608,17 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, goto fail; } + /* + * Do special qgroup accounting for snapshot, as we do some qgroup + * snapshot hack to do fast snapshot. + * To co-operate with that hack, we do hack again. + * Or snapshot will be greatly slowed down by a subtree qgroup rescan + */ + ret = qgroup_account_snapshot(trans, root, parent_root, + pending->inherit, objectid); + if (ret < 0) + goto fail; + ret = btrfs_insert_dir_item(trans, parent_root, dentry->d_name.name, dentry->d_name.len, parent_inode, &key, @@ -1559,23 +1662,6 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, goto fail; } - /* - * account qgroup counters before qgroup_inherit() - */ - ret = btrfs_qgroup_prepare_account_extents(trans, fs_info); - if (ret) - goto fail; - ret = btrfs_qgroup_account_extents(trans, fs_info); - if (ret) - goto fail; - ret = btrfs_qgroup_inherit(trans, fs_info, - root->root_key.objectid, - objectid, pending->inherit); - if (ret) { - btrfs_abort_transaction(trans, root, ret); - goto fail; - } - fail: pending->error = ret; dir_item_existed: @@ -1821,7 +1907,7 @@ static inline int btrfs_start_delalloc_flush(struct btrfs_fs_info *fs_info) static inline void btrfs_wait_delalloc_flush(struct btrfs_fs_info *fs_info) { if (btrfs_test_opt(fs_info->tree_root, FLUSHONCOMMIT)) - btrfs_wait_ordered_roots(fs_info, -1); + btrfs_wait_ordered_roots(fs_info, -1, 0, (u64)-1); } static inline void @@ -2145,7 +2231,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans, ret = btrfs_write_and_wait_transaction(trans, root); if (ret) { - btrfs_std_error(root->fs_info, ret, + btrfs_handle_fs_error(root->fs_info, ret, "Error while writing out transaction"); mutex_unlock(&root->fs_info->tree_log_mutex); goto scrub_continue; diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index f3a8939d63fb..aa8fed11f749 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -4141,6 +4141,7 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans, INIT_LIST_HEAD(&extents); + down_write(&BTRFS_I(inode)->dio_sem); write_lock(&tree->lock); test_gen = root->fs_info->last_trans_committed; @@ -4169,13 +4170,20 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans, } list_sort(NULL, &extents, extent_cmp); + btrfs_get_logged_extents(inode, logged_list, start, end); /* - * Collect any new ordered extents within the range. This is to - * prevent logging file extent items without waiting for the disk - * location they point to being written. We do this only to deal - * with races against concurrent lockless direct IO writes. + * Some ordered extents started by fsync might have completed + * before we could collect them into the list logged_list, which + * means they're gone, not in our logged_list nor in the inode's + * ordered tree. We want the application/user space to know an + * error happened while attempting to persist file data so that + * it can take proper action. If such error happened, we leave + * without writing to the log tree and the fsync must report the + * file data write error and not commit the current transaction. */ - btrfs_get_logged_extents(inode, logged_list, start, end); + ret = btrfs_inode_check_errors(inode); + if (ret) + ctx->io_err = ret; process: while (!list_empty(&extents)) { em = list_entry(extents.next, struct extent_map, list); @@ -4202,6 +4210,7 @@ process: } WARN_ON(!list_empty(&extents)); write_unlock(&tree->lock); + up_write(&BTRFS_I(inode)->dio_sem); btrfs_release_path(path); return ret; @@ -4623,23 +4632,6 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans, mutex_lock(&BTRFS_I(inode)->log_mutex); /* - * Collect ordered extents only if we are logging data. This is to - * ensure a subsequent request to log this inode in LOG_INODE_ALL mode - * will process the ordered extents if they still exists at the time, - * because when we collect them we test and set for the flag - * BTRFS_ORDERED_LOGGED to prevent multiple log requests to process the - * same ordered extents. The consequence for the LOG_INODE_ALL log mode - * not processing the ordered extents is that we end up logging the - * corresponding file extent items, based on the extent maps in the - * inode's extent_map_tree's modified_list, without logging the - * respective checksums (since the may still be only attached to the - * ordered extents and have not been inserted in the csum tree by - * btrfs_finish_ordered_io() yet). - */ - if (inode_only == LOG_INODE_ALL) - btrfs_get_logged_extents(inode, &logged_list, start, end); - - /* * a brute force approach to making sure we get the most uptodate * copies of everything. */ @@ -4846,21 +4838,6 @@ log_extents: goto out_unlock; } if (fast_search) { - /* - * Some ordered extents started by fsync might have completed - * before we collected the ordered extents in logged_list, which - * means they're gone, not in our logged_list nor in the inode's - * ordered tree. We want the application/user space to know an - * error happened while attempting to persist file data so that - * it can take proper action. If such error happened, we leave - * without writing to the log tree and the fsync must report the - * file data write error and not commit the current transaction. - */ - err = btrfs_inode_check_errors(inode); - if (err) { - ctx->io_err = err; - goto out_unlock; - } ret = btrfs_log_changed_extents(trans, root, inode, dst_path, &logged_list, ctx, start, end); if (ret) { @@ -5158,7 +5135,7 @@ process_leaf: } ctx->log_new_dentries = false; - if (type == BTRFS_FT_DIR) + if (type == BTRFS_FT_DIR || type == BTRFS_FT_SYMLINK) log_mode = LOG_INODE_ALL; btrfs_release_path(path); ret = btrfs_log_inode(trans, root, di_inode, @@ -5278,11 +5255,16 @@ static int btrfs_log_all_parents(struct btrfs_trans_handle *trans, if (IS_ERR(dir_inode)) continue; + if (ctx) + ctx->log_new_dentries = false; ret = btrfs_log_inode(trans, root, dir_inode, LOG_INODE_ALL, 0, LLONG_MAX, ctx); if (!ret && btrfs_must_commit_transaction(trans, dir_inode)) ret = 1; + if (!ret && ctx && ctx->log_new_dentries) + ret = log_new_dir_dentries(trans, root, + dir_inode, ctx); iput(dir_inode); if (ret) goto out; @@ -5519,7 +5501,7 @@ int btrfs_recover_log_trees(struct btrfs_root *log_root_tree) ret = walk_log_tree(trans, log_root_tree, &wc); if (ret) { - btrfs_std_error(fs_info, ret, "Failed to pin buffers while " + btrfs_handle_fs_error(fs_info, ret, "Failed to pin buffers while " "recovering log root tree."); goto error; } @@ -5533,7 +5515,7 @@ again: ret = btrfs_search_slot(NULL, log_root_tree, &key, path, 0, 0); if (ret < 0) { - btrfs_std_error(fs_info, ret, + btrfs_handle_fs_error(fs_info, ret, "Couldn't find tree log root."); goto error; } @@ -5551,7 +5533,7 @@ again: log = btrfs_read_fs_root(log_root_tree, &found_key); if (IS_ERR(log)) { ret = PTR_ERR(log); - btrfs_std_error(fs_info, ret, + btrfs_handle_fs_error(fs_info, ret, "Couldn't read tree log root."); goto error; } @@ -5566,7 +5548,7 @@ again: free_extent_buffer(log->node); free_extent_buffer(log->commit_root); kfree(log); - btrfs_std_error(fs_info, ret, "Couldn't read target root " + btrfs_handle_fs_error(fs_info, ret, "Couldn't read target root " "for tree log recovery."); goto error; } @@ -5652,11 +5634,9 @@ void btrfs_record_unlink_dir(struct btrfs_trans_handle *trans, * into the file. When the file is logged we check it and * don't log the parents if the file is fully on disk. */ - if (S_ISREG(inode->i_mode)) { - mutex_lock(&BTRFS_I(inode)->log_mutex); - BTRFS_I(inode)->last_unlink_trans = trans->transid; - mutex_unlock(&BTRFS_I(inode)->log_mutex); - } + mutex_lock(&BTRFS_I(inode)->log_mutex); + BTRFS_I(inode)->last_unlink_trans = trans->transid; + mutex_unlock(&BTRFS_I(inode)->log_mutex); /* * if this directory was already logged any new diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 8fe7fff5ffb7..9c01824eef08 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -118,6 +118,21 @@ const u64 btrfs_raid_group[BTRFS_NR_RAID_TYPES] = { [BTRFS_RAID_RAID6] = BTRFS_BLOCK_GROUP_RAID6, }; +/* + * Table to convert BTRFS_RAID_* to the error code if minimum number of devices + * condition is not met. Zero means there's no corresponding + * BTRFS_ERROR_DEV_*_NOT_MET value. + */ +const int btrfs_raid_mindev_error[BTRFS_NR_RAID_TYPES] = { + [BTRFS_RAID_RAID10] = BTRFS_ERROR_DEV_RAID10_MIN_NOT_MET, + [BTRFS_RAID_RAID1] = BTRFS_ERROR_DEV_RAID1_MIN_NOT_MET, + [BTRFS_RAID_DUP] = 0, + [BTRFS_RAID_RAID0] = 0, + [BTRFS_RAID_SINGLE] = 0, + [BTRFS_RAID_RAID5] = BTRFS_ERROR_DEV_RAID5_MIN_NOT_MET, + [BTRFS_RAID_RAID6] = BTRFS_ERROR_DEV_RAID6_MIN_NOT_MET, +}; + static int init_first_rw_device(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_device *device); @@ -699,7 +714,8 @@ static noinline int device_list_add(const char *path, * if there is new btrfs on an already registered device, * then remove the stale device entry. */ - btrfs_free_stale_device(device); + if (ret > 0) + btrfs_free_stale_device(device); *fs_devices_ret = fs_devices; @@ -988,6 +1004,56 @@ int btrfs_open_devices(struct btrfs_fs_devices *fs_devices, return ret; } +void btrfs_release_disk_super(struct page *page) +{ + kunmap(page); + put_page(page); +} + +int btrfs_read_disk_super(struct block_device *bdev, u64 bytenr, + struct page **page, struct btrfs_super_block **disk_super) +{ + void *p; + pgoff_t index; + + /* make sure our super fits in the device */ + if (bytenr + PAGE_SIZE >= i_size_read(bdev->bd_inode)) + return 1; + + /* make sure our super fits in the page */ + if (sizeof(**disk_super) > PAGE_SIZE) + return 1; + + /* make sure our super doesn't straddle pages on disk */ + index = bytenr >> PAGE_SHIFT; + if ((bytenr + sizeof(**disk_super) - 1) >> PAGE_SHIFT != index) + return 1; + + /* pull in the page with our super */ + *page = read_cache_page_gfp(bdev->bd_inode->i_mapping, + index, GFP_KERNEL); + + if (IS_ERR_OR_NULL(*page)) + return 1; + + p = kmap(*page); + + /* align our pointer to the offset of the super block */ + *disk_super = p + (bytenr & ~PAGE_MASK); + + if (btrfs_super_bytenr(*disk_super) != bytenr || + btrfs_super_magic(*disk_super) != BTRFS_MAGIC) { + btrfs_release_disk_super(*page); + return 1; + } + + if ((*disk_super)->label[0] && + (*disk_super)->label[BTRFS_LABEL_SIZE - 1]) + (*disk_super)->label[BTRFS_LABEL_SIZE - 1] = '\0'; + + return 0; +} + /* * Look for a btrfs signature on a device. This may be called out of the mount path * and we are not allowed to call set_blocksize during the scan. The superblock @@ -999,13 +1065,11 @@ int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder, struct btrfs_super_block *disk_super; struct block_device *bdev; struct page *page; - void *p; int ret = -EINVAL; u64 devid; u64 transid; u64 total_devices; u64 bytenr; - pgoff_t index; /* * we would like to check all the supers, but that would make @@ -1018,41 +1082,14 @@ int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder, mutex_lock(&uuid_mutex); bdev = blkdev_get_by_path(path, flags, holder); - if (IS_ERR(bdev)) { ret = PTR_ERR(bdev); goto error; } - /* make sure our super fits in the device */ - if (bytenr + PAGE_SIZE >= i_size_read(bdev->bd_inode)) - goto error_bdev_put; - - /* make sure our super fits in the page */ - if (sizeof(*disk_super) > PAGE_SIZE) - goto error_bdev_put; - - /* make sure our super doesn't straddle pages on disk */ - index = bytenr >> PAGE_SHIFT; - if ((bytenr + sizeof(*disk_super) - 1) >> PAGE_SHIFT != index) - goto error_bdev_put; - - /* pull in the page with our super */ - page = read_cache_page_gfp(bdev->bd_inode->i_mapping, - index, GFP_NOFS); - - if (IS_ERR_OR_NULL(page)) + if (btrfs_read_disk_super(bdev, bytenr, &page, &disk_super)) goto error_bdev_put; - p = kmap(page); - - /* align our pointer to the offset of the super block */ - disk_super = p + (bytenr & ~PAGE_MASK); - - if (btrfs_super_bytenr(disk_super) != bytenr || - btrfs_super_magic(disk_super) != BTRFS_MAGIC) - goto error_unmap; - devid = btrfs_stack_device_id(&disk_super->dev_item); transid = btrfs_super_generation(disk_super); total_devices = btrfs_super_num_devices(disk_super); @@ -1060,8 +1097,6 @@ int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder, ret = device_list_add(path, disk_super, devid, fs_devices_ret); if (ret > 0) { if (disk_super->label[0]) { - if (disk_super->label[BTRFS_LABEL_SIZE - 1]) - disk_super->label[BTRFS_LABEL_SIZE - 1] = '\0'; printk(KERN_INFO "BTRFS: device label %s ", disk_super->label); } else { printk(KERN_INFO "BTRFS: device fsid %pU ", disk_super->fsid); @@ -1073,9 +1108,7 @@ int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder, if (!ret && fs_devices_ret) (*fs_devices_ret)->total_devices = total_devices; -error_unmap: - kunmap(page); - put_page(page); + btrfs_release_disk_super(page); error_bdev_put: blkdev_put(bdev, flags); @@ -1454,7 +1487,7 @@ again: extent = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_dev_extent); } else { - btrfs_std_error(root->fs_info, ret, "Slot search failed"); + btrfs_handle_fs_error(root->fs_info, ret, "Slot search failed"); goto out; } @@ -1462,7 +1495,7 @@ again: ret = btrfs_del_item(trans, root, path); if (ret) { - btrfs_std_error(root->fs_info, ret, + btrfs_handle_fs_error(root->fs_info, ret, "Failed to remove dev extent item"); } else { set_bit(BTRFS_TRANS_HAVE_FREE_BGS, &trans->transaction->flags); @@ -1688,32 +1721,92 @@ out: return ret; } -int btrfs_rm_device(struct btrfs_root *root, char *device_path) +/* + * Verify that @num_devices satisfies the RAID profile constraints in the whole + * filesystem. It's up to the caller to adjust that number regarding eg. device + * replace. + */ +static int btrfs_check_raid_min_devices(struct btrfs_fs_info *fs_info, + u64 num_devices) +{ + u64 all_avail; + unsigned seq; + int i; + + do { + seq = read_seqbegin(&fs_info->profiles_lock); + + all_avail = fs_info->avail_data_alloc_bits | + fs_info->avail_system_alloc_bits | + fs_info->avail_metadata_alloc_bits; + } while (read_seqretry(&fs_info->profiles_lock, seq)); + + for (i = 0; i < BTRFS_NR_RAID_TYPES; i++) { + if (!(all_avail & btrfs_raid_group[i])) + continue; + + if (num_devices < btrfs_raid_array[i].devs_min) { + int ret = btrfs_raid_mindev_error[i]; + + if (ret) + return ret; + } + } + + return 0; +} + +struct btrfs_device *btrfs_find_next_active_device(struct btrfs_fs_devices *fs_devs, + struct btrfs_device *device) { - struct btrfs_device *device; struct btrfs_device *next_device; - struct block_device *bdev; - struct buffer_head *bh = NULL; - struct btrfs_super_block *disk_super; + + list_for_each_entry(next_device, &fs_devs->devices, dev_list) { + if (next_device != device && + !next_device->missing && next_device->bdev) + return next_device; + } + + return NULL; +} + +/* + * Helper function to check if the given device is part of s_bdev / latest_bdev + * and replace it with the provided or the next active device, in the context + * where this function called, there should be always be another device (or + * this_dev) which is active. + */ +void btrfs_assign_next_active_device(struct btrfs_fs_info *fs_info, + struct btrfs_device *device, struct btrfs_device *this_dev) +{ + struct btrfs_device *next_device; + + if (this_dev) + next_device = this_dev; + else + next_device = btrfs_find_next_active_device(fs_info->fs_devices, + device); + ASSERT(next_device); + + if (fs_info->sb->s_bdev && + (fs_info->sb->s_bdev == device->bdev)) + fs_info->sb->s_bdev = next_device->bdev; + + if (fs_info->fs_devices->latest_bdev == device->bdev) + fs_info->fs_devices->latest_bdev = next_device->bdev; +} + +int btrfs_rm_device(struct btrfs_root *root, char *device_path, u64 devid) +{ + struct btrfs_device *device; struct btrfs_fs_devices *cur_devices; - u64 all_avail; - u64 devid; u64 num_devices; - u8 *dev_uuid; - unsigned seq; int ret = 0; bool clear_super = false; + char *dev_name = NULL; mutex_lock(&uuid_mutex); - do { - seq = read_seqbegin(&root->fs_info->profiles_lock); - - all_avail = root->fs_info->avail_data_alloc_bits | - root->fs_info->avail_system_alloc_bits | - root->fs_info->avail_metadata_alloc_bits; - } while (read_seqretry(&root->fs_info->profiles_lock, seq)); - num_devices = root->fs_info->fs_devices->num_devices; btrfs_dev_replace_lock(&root->fs_info->dev_replace, 0); if (btrfs_dev_replace_is_ongoing(&root->fs_info->dev_replace)) { @@ -1722,78 +1815,23 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path) } btrfs_dev_replace_unlock(&root->fs_info->dev_replace, 0); - if ((all_avail & BTRFS_BLOCK_GROUP_RAID10) && num_devices <= 4) { - ret = BTRFS_ERROR_DEV_RAID10_MIN_NOT_MET; - goto out; - } - - if ((all_avail & BTRFS_BLOCK_GROUP_RAID1) && num_devices <= 2) { - ret = BTRFS_ERROR_DEV_RAID1_MIN_NOT_MET; + ret = btrfs_check_raid_min_devices(root->fs_info, num_devices - 1); + if (ret) goto out; - } - if ((all_avail & BTRFS_BLOCK_GROUP_RAID5) && - root->fs_info->fs_devices->rw_devices <= 2) { - ret = BTRFS_ERROR_DEV_RAID5_MIN_NOT_MET; - goto out; - } - if ((all_avail & BTRFS_BLOCK_GROUP_RAID6) && - root->fs_info->fs_devices->rw_devices <= 3) { - ret = BTRFS_ERROR_DEV_RAID6_MIN_NOT_MET; + ret = btrfs_find_device_by_devspec(root, devid, device_path, + &device); + if (ret) goto out; - } - - if (strcmp(device_path, "missing") == 0) { - struct list_head *devices; - struct btrfs_device *tmp; - - device = NULL; - devices = &root->fs_info->fs_devices->devices; - /* - * It is safe to read the devices since the volume_mutex - * is held. - */ - list_for_each_entry(tmp, devices, dev_list) { - if (tmp->in_fs_metadata && - !tmp->is_tgtdev_for_dev_replace && - !tmp->bdev) { - device = tmp; - break; - } - } - bdev = NULL; - bh = NULL; - disk_super = NULL; - if (!device) { - ret = BTRFS_ERROR_DEV_MISSING_NOT_FOUND; - goto out; - } - } else { - ret = btrfs_get_bdev_and_sb(device_path, - FMODE_WRITE | FMODE_EXCL, - root->fs_info->bdev_holder, 0, - &bdev, &bh); - if (ret) - goto out; - disk_super = (struct btrfs_super_block *)bh->b_data; - devid = btrfs_stack_device_id(&disk_super->dev_item); - dev_uuid = disk_super->dev_item.uuid; - device = btrfs_find_device(root->fs_info, devid, dev_uuid, - disk_super->fsid); - if (!device) { - ret = -ENOENT; - goto error_brelse; - } - } if (device->is_tgtdev_for_dev_replace) { ret = BTRFS_ERROR_DEV_TGT_REPLACE; - goto error_brelse; + goto out; } if (device->writeable && root->fs_info->fs_devices->rw_devices == 1) { ret = BTRFS_ERROR_DEV_ONLY_WRITABLE; - goto error_brelse; + goto out; } if (device->writeable) { @@ -1801,6 +1839,11 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path) list_del_init(&device->dev_alloc_list); device->fs_devices->rw_devices--; unlock_chunks(root); + dev_name = kstrdup(device->name->str, GFP_KERNEL); + if (!dev_name) { + ret = -ENOMEM; + goto error_undo; + } clear_super = true; } @@ -1842,12 +1885,7 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path) if (device->missing) device->fs_devices->missing_devices--; - next_device = list_entry(root->fs_info->fs_devices->devices.next, - struct btrfs_device, dev_list); - if (device->bdev == root->fs_info->sb->s_bdev) - root->fs_info->sb->s_bdev = next_device->bdev; - if (device->bdev == root->fs_info->fs_devices->latest_bdev) - root->fs_info->fs_devices->latest_bdev = next_device->bdev; + btrfs_assign_next_active_device(root->fs_info, device, NULL); if (device->bdev) { device->fs_devices->open_devices--; @@ -1883,63 +1921,23 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path) * at this point, the device is zero sized. We want to * remove it from the devices list and zero out the old super */ - if (clear_super && disk_super) { - u64 bytenr; - int i; - - /* make sure this device isn't detected as part of - * the FS anymore - */ - memset(&disk_super->magic, 0, sizeof(disk_super->magic)); - set_buffer_dirty(bh); - sync_dirty_buffer(bh); - - /* clear the mirror copies of super block on the disk - * being removed, 0th copy is been taken care above and - * the below would take of the rest - */ - for (i = 1; i < BTRFS_SUPER_MIRROR_MAX; i++) { - bytenr = btrfs_sb_offset(i); - if (bytenr + BTRFS_SUPER_INFO_SIZE >= - i_size_read(bdev->bd_inode)) - break; - - brelse(bh); - bh = __bread(bdev, bytenr / 4096, - BTRFS_SUPER_INFO_SIZE); - if (!bh) - continue; - - disk_super = (struct btrfs_super_block *)bh->b_data; - - if (btrfs_super_bytenr(disk_super) != bytenr || - btrfs_super_magic(disk_super) != BTRFS_MAGIC) { - continue; - } - memset(&disk_super->magic, 0, - sizeof(disk_super->magic)); - set_buffer_dirty(bh); - sync_dirty_buffer(bh); + if (clear_super) { + struct block_device *bdev; + + bdev = blkdev_get_by_path(dev_name, FMODE_READ | FMODE_EXCL, + root->fs_info->bdev_holder); + if (!IS_ERR(bdev)) { + btrfs_scratch_superblocks(bdev, dev_name); + blkdev_put(bdev, FMODE_READ | FMODE_EXCL); } } - ret = 0; - - if (bdev) { - /* Notify udev that device has changed */ - btrfs_kobject_uevent(bdev, KOBJ_CHANGE); - - /* Update ctime/mtime for device path for libblkid */ - update_dev_time(device_path); - } - -error_brelse: - brelse(bh); - if (bdev) - blkdev_put(bdev, FMODE_READ | FMODE_EXCL); out: + kfree(dev_name); + mutex_unlock(&uuid_mutex); return ret; + error_undo: if (device->writeable) { lock_chunks(root); @@ -1948,7 +1946,7 @@ error_undo: device->fs_devices->rw_devices++; unlock_chunks(root); } - goto error_brelse; + goto out; } void btrfs_rm_dev_replace_remove_srcdev(struct btrfs_fs_info *fs_info, @@ -1972,11 +1970,8 @@ void btrfs_rm_dev_replace_remove_srcdev(struct btrfs_fs_info *fs_info, if (srcdev->missing) fs_devices->missing_devices--; - if (srcdev->writeable) { + if (srcdev->writeable) fs_devices->rw_devices--; - /* zero out the old super if it is writable */ - btrfs_scratch_superblocks(srcdev->bdev, srcdev->name->str); - } if (srcdev->bdev) fs_devices->open_devices--; @@ -1987,6 +1982,10 @@ void btrfs_rm_dev_replace_free_srcdev(struct btrfs_fs_info *fs_info, { struct btrfs_fs_devices *fs_devices = srcdev->fs_devices; + if (srcdev->writeable) { + /* zero out the old super if it is writable */ + btrfs_scratch_superblocks(srcdev->bdev, srcdev->name->str); + } call_rcu(&srcdev->rcu, free_device); /* @@ -2016,32 +2015,33 @@ void btrfs_rm_dev_replace_free_srcdev(struct btrfs_fs_info *fs_info, void btrfs_destroy_dev_replace_tgtdev(struct btrfs_fs_info *fs_info, struct btrfs_device *tgtdev) { - struct btrfs_device *next_device; - mutex_lock(&uuid_mutex); WARN_ON(!tgtdev); mutex_lock(&fs_info->fs_devices->device_list_mutex); btrfs_sysfs_rm_device_link(fs_info->fs_devices, tgtdev); - if (tgtdev->bdev) { - btrfs_scratch_superblocks(tgtdev->bdev, tgtdev->name->str); + if (tgtdev->bdev) fs_info->fs_devices->open_devices--; - } + fs_info->fs_devices->num_devices--; - next_device = list_entry(fs_info->fs_devices->devices.next, - struct btrfs_device, dev_list); - if (tgtdev->bdev == fs_info->sb->s_bdev) - fs_info->sb->s_bdev = next_device->bdev; - if (tgtdev->bdev == fs_info->fs_devices->latest_bdev) - fs_info->fs_devices->latest_bdev = next_device->bdev; - list_del_rcu(&tgtdev->dev_list); + btrfs_assign_next_active_device(fs_info, tgtdev, NULL); - call_rcu(&tgtdev->rcu, free_device); + list_del_rcu(&tgtdev->dev_list); mutex_unlock(&fs_info->fs_devices->device_list_mutex); mutex_unlock(&uuid_mutex); + + /* + * The update_dev_time() with in btrfs_scratch_superblocks() + * may lead to a call to btrfs_show_devname() which will try + * to hold device_list_mutex. And here this device + * is already out of device list, so we don't have to hold + * the device_list_mutex lock. + */ + btrfs_scratch_superblocks(tgtdev->bdev, tgtdev->name->str); + call_rcu(&tgtdev->rcu, free_device); } static int btrfs_find_device_by_path(struct btrfs_root *root, char *device_path, @@ -2102,6 +2102,31 @@ int btrfs_find_device_missing_or_by_path(struct btrfs_root *root, } /* + * Lookup a device given by device id, or the path if the id is 0. + */ +int btrfs_find_device_by_devspec(struct btrfs_root *root, u64 devid, + char *devpath, + struct btrfs_device **device) +{ + int ret; + + if (devid) { + ret = 0; + *device = btrfs_find_device(root->fs_info, devid, NULL, + NULL); + if (!*device) + ret = -ENOENT; + } else { + if (!devpath || !devpath[0]) + return -EINVAL; + + ret = btrfs_find_device_missing_or_by_path(root, devpath, + device); + } + return ret; +} + +/* * does all the dirty work required for changing file system's UUID. */ static int btrfs_prepare_sprout(struct btrfs_root *root) @@ -2418,7 +2443,7 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path) ret = btrfs_relocate_sys_chunks(root); if (ret < 0) - btrfs_std_error(root->fs_info, ret, + btrfs_handle_fs_error(root->fs_info, ret, "Failed to relocate sys chunks after " "device initialization. This can be fixed " "using the \"btrfs balance\" command."); @@ -2663,7 +2688,7 @@ static int btrfs_free_chunk(struct btrfs_trans_handle *trans, if (ret < 0) goto out; else if (ret > 0) { /* Logic error or corruption */ - btrfs_std_error(root->fs_info, -ENOENT, + btrfs_handle_fs_error(root->fs_info, -ENOENT, "Failed lookup while freeing chunk."); ret = -ENOENT; goto out; @@ -2671,7 +2696,7 @@ static int btrfs_free_chunk(struct btrfs_trans_handle *trans, ret = btrfs_del_item(trans, root, path); if (ret < 0) - btrfs_std_error(root->fs_info, ret, + btrfs_handle_fs_error(root->fs_info, ret, "Failed to delete chunk item."); out: btrfs_free_path(path); @@ -2857,7 +2882,7 @@ static int btrfs_relocate_chunk(struct btrfs_root *root, u64 chunk_offset) chunk_offset); if (IS_ERR(trans)) { ret = PTR_ERR(trans); - btrfs_std_error(root->fs_info, ret, NULL); + btrfs_handle_fs_error(root->fs_info, ret, NULL); return ret; } @@ -3402,6 +3427,7 @@ static int __btrfs_balance(struct btrfs_fs_info *fs_info) u32 count_meta = 0; u32 count_sys = 0; int chunk_reserved = 0; + u64 bytes_used = 0; /* step one make some room on all the devices */ devices = &fs_info->fs_devices->devices; @@ -3540,7 +3566,13 @@ again: goto loop; } - if ((chunk_type & BTRFS_BLOCK_GROUP_DATA) && !chunk_reserved) { + ASSERT(fs_info->data_sinfo); + spin_lock(&fs_info->data_sinfo->lock); + bytes_used = fs_info->data_sinfo->bytes_used; + spin_unlock(&fs_info->data_sinfo->lock); + + if ((chunk_type & BTRFS_BLOCK_GROUP_DATA) && + !chunk_reserved && !bytes_used) { trans = btrfs_start_transaction(chunk_root, 0); if (IS_ERR(trans)) { mutex_unlock(&fs_info->delete_unused_bgs_mutex); @@ -3632,7 +3664,7 @@ static void __cancel_balance(struct btrfs_fs_info *fs_info) unset_balance_control(fs_info); ret = del_balance_item(fs_info->tree_root); if (ret) - btrfs_std_error(fs_info, ret, NULL); + btrfs_handle_fs_error(fs_info, ret, NULL); atomic_set(&fs_info->mutually_exclusive_operation_running, 0); } @@ -3693,10 +3725,8 @@ int btrfs_balance(struct btrfs_balance_control *bctl, num_devices--; } btrfs_dev_replace_unlock(&fs_info->dev_replace, 0); - allowed = BTRFS_AVAIL_ALLOC_BIT_SINGLE; - if (num_devices == 1) - allowed |= BTRFS_BLOCK_GROUP_DUP; - else if (num_devices > 1) + allowed = BTRFS_AVAIL_ALLOC_BIT_SINGLE | BTRFS_BLOCK_GROUP_DUP; + if (num_devices > 1) allowed |= (BTRFS_BLOCK_GROUP_RAID0 | BTRFS_BLOCK_GROUP_RAID1); if (num_devices > 2) allowed |= BTRFS_BLOCK_GROUP_RAID5; @@ -5278,7 +5308,15 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw, stripe_nr = div64_u64(stripe_nr, stripe_len); stripe_offset = stripe_nr * stripe_len; - BUG_ON(offset < stripe_offset); + if (offset < stripe_offset) { + btrfs_crit(fs_info, "stripe math has gone wrong, " + "stripe_offset=%llu, offset=%llu, start=%llu, " + "logical=%llu, stripe_len=%llu", + stripe_offset, offset, em->start, logical, + stripe_len); + free_extent_map(em); + return -EINVAL; + } /* stripe_offset is the offset of this block in its stripe*/ stripe_offset = offset - stripe_offset; @@ -5519,7 +5557,13 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw, &stripe_index); mirror_num = stripe_index + 1; } - BUG_ON(stripe_index >= map->num_stripes); + if (stripe_index >= map->num_stripes) { + btrfs_crit(fs_info, "stripe index math went horribly wrong, " + "got stripe_index=%u, num_stripes=%u", + stripe_index, map->num_stripes); + ret = -EINVAL; + goto out; + } num_alloc_stripes = num_stripes; if (dev_replace_is_ongoing) { @@ -6242,7 +6286,7 @@ static int read_one_chunk(struct btrfs_root *root, struct btrfs_key *key, "invalid chunk length %llu", length); return -EIO; } - if (!is_power_of_2(stripe_len)) { + if (!is_power_of_2(stripe_len) || stripe_len != BTRFS_STRIPE_LEN) { btrfs_err(root->fs_info, "invalid chunk stripe length: %llu", stripe_len); return -EIO; @@ -6586,13 +6630,13 @@ int btrfs_read_sys_array(struct btrfs_root *root) sb_array_offset += len; cur_offset += len; } - free_extent_buffer(sb); + free_extent_buffer_stale(sb); return ret; out_short_read: printk(KERN_ERR "BTRFS: sys_array too short to read %u bytes at offset %u\n", len, cur_offset); - free_extent_buffer(sb); + free_extent_buffer_stale(sb); return -EIO; } diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index 1939ebde63df..0ac90f8d85bd 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -340,14 +340,14 @@ struct btrfs_raid_attr { }; extern const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES]; - +extern const int btrfs_raid_mindev_error[BTRFS_NR_RAID_TYPES]; extern const u64 btrfs_raid_group[BTRFS_NR_RAID_TYPES]; struct map_lookup { u64 type; int io_align; int io_width; - int stripe_len; + u64 stripe_len; int sector_size; int num_stripes; int sub_stripes; @@ -357,52 +357,6 @@ struct map_lookup { #define map_lookup_size(n) (sizeof(struct map_lookup) + \ (sizeof(struct btrfs_bio_stripe) * (n))) -/* - * Restriper's general type filter - */ -#define BTRFS_BALANCE_DATA (1ULL << 0) -#define BTRFS_BALANCE_SYSTEM (1ULL << 1) -#define BTRFS_BALANCE_METADATA (1ULL << 2) - -#define BTRFS_BALANCE_TYPE_MASK (BTRFS_BALANCE_DATA | \ - BTRFS_BALANCE_SYSTEM | \ - BTRFS_BALANCE_METADATA) - -#define BTRFS_BALANCE_FORCE (1ULL << 3) -#define BTRFS_BALANCE_RESUME (1ULL << 4) - -/* - * Balance filters - */ -#define BTRFS_BALANCE_ARGS_PROFILES (1ULL << 0) -#define BTRFS_BALANCE_ARGS_USAGE (1ULL << 1) -#define BTRFS_BALANCE_ARGS_DEVID (1ULL << 2) -#define BTRFS_BALANCE_ARGS_DRANGE (1ULL << 3) -#define BTRFS_BALANCE_ARGS_VRANGE (1ULL << 4) -#define BTRFS_BALANCE_ARGS_LIMIT (1ULL << 5) -#define BTRFS_BALANCE_ARGS_LIMIT_RANGE (1ULL << 6) -#define BTRFS_BALANCE_ARGS_STRIPES_RANGE (1ULL << 7) -#define BTRFS_BALANCE_ARGS_USAGE_RANGE (1ULL << 10) - -#define BTRFS_BALANCE_ARGS_MASK \ - (BTRFS_BALANCE_ARGS_PROFILES | \ - BTRFS_BALANCE_ARGS_USAGE | \ - BTRFS_BALANCE_ARGS_DEVID | \ - BTRFS_BALANCE_ARGS_DRANGE | \ - BTRFS_BALANCE_ARGS_VRANGE | \ - BTRFS_BALANCE_ARGS_LIMIT | \ - BTRFS_BALANCE_ARGS_LIMIT_RANGE | \ - BTRFS_BALANCE_ARGS_STRIPES_RANGE | \ - BTRFS_BALANCE_ARGS_USAGE_RANGE) - -/* - * Profile changing flags. When SOFT is set we won't relocate chunk if - * it already has the target profile (even though it may be - * half-filled). - */ -#define BTRFS_BALANCE_ARGS_CONVERT (1ULL << 8) -#define BTRFS_BALANCE_ARGS_SOFT (1ULL << 9) - struct btrfs_balance_args; struct btrfs_balance_progress; struct btrfs_balance_control { @@ -445,13 +399,18 @@ int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder, struct btrfs_fs_devices **fs_devices_ret); int btrfs_close_devices(struct btrfs_fs_devices *fs_devices); void btrfs_close_extra_devices(struct btrfs_fs_devices *fs_devices, int step); +void btrfs_assign_next_active_device(struct btrfs_fs_info *fs_info, + struct btrfs_device *device, struct btrfs_device *this_dev); int btrfs_find_device_missing_or_by_path(struct btrfs_root *root, char *device_path, struct btrfs_device **device); +int btrfs_find_device_by_devspec(struct btrfs_root *root, u64 devid, + char *devpath, + struct btrfs_device **device); struct btrfs_device *btrfs_alloc_device(struct btrfs_fs_info *fs_info, const u64 *devid, const u8 *uuid); -int btrfs_rm_device(struct btrfs_root *root, char *device_path); +int btrfs_rm_device(struct btrfs_root *root, char *device_path, u64 devid); void btrfs_cleanup_fs_uuids(void); int btrfs_num_copies(struct btrfs_fs_info *fs_info, u64 logical, u64 len); int btrfs_grow_device(struct btrfs_trans_handle *trans, diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 541ead4d8965..85b8517f17a0 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -386,9 +386,7 @@ void ceph_put_mds_session(struct ceph_mds_session *s) atomic_read(&s->s_ref), atomic_read(&s->s_ref)-1); if (atomic_dec_and_test(&s->s_ref)) { if (s->s_auth.authorizer) - ceph_auth_destroy_authorizer( - s->s_mdsc->fsc->client->monc.auth, - s->s_auth.authorizer); + ceph_auth_destroy_authorizer(s->s_auth.authorizer); kfree(s); } } @@ -3900,7 +3898,7 @@ static struct ceph_auth_handshake *get_authorizer(struct ceph_connection *con, struct ceph_auth_handshake *auth = &s->s_auth; if (force_new && auth->authorizer) { - ceph_auth_destroy_authorizer(ac, auth->authorizer); + ceph_auth_destroy_authorizer(auth->authorizer); auth->authorizer = NULL; } if (!auth->authorizer) { diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c index 0af8e7d70d27..0b2954d7172d 100644 --- a/fs/devpts/inode.c +++ b/fs/devpts/inode.c @@ -604,8 +604,7 @@ void devpts_put_ref(struct pts_fs_info *fsi) * * The created inode is returned. Remove it from /dev/pts/ by devpts_pty_kill. */ -struct inode *devpts_pty_new(struct pts_fs_info *fsi, dev_t device, int index, - void *priv) +struct dentry *devpts_pty_new(struct pts_fs_info *fsi, int index, void *priv) { struct dentry *dentry; struct super_block *sb; @@ -629,25 +628,21 @@ struct inode *devpts_pty_new(struct pts_fs_info *fsi, dev_t device, int index, inode->i_uid = opts->setuid ? opts->uid : current_fsuid(); inode->i_gid = opts->setgid ? opts->gid : current_fsgid(); inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME; - init_special_inode(inode, S_IFCHR|opts->mode, device); - inode->i_private = priv; + init_special_inode(inode, S_IFCHR|opts->mode, MKDEV(UNIX98_PTY_SLAVE_MAJOR, index)); sprintf(s, "%d", index); - inode_lock(d_inode(root)); - dentry = d_alloc_name(root, s); if (dentry) { + dentry->d_fsdata = priv; d_add(dentry, inode); fsnotify_create(d_inode(root), dentry); } else { iput(inode); - inode = ERR_PTR(-ENOMEM); + dentry = ERR_PTR(-ENOMEM); } - inode_unlock(d_inode(root)); - - return inode; + return dentry; } /** @@ -656,24 +651,10 @@ struct inode *devpts_pty_new(struct pts_fs_info *fsi, dev_t device, int index, * * Returns whatever was passed as priv in devpts_pty_new for a given inode. */ -void *devpts_get_priv(struct inode *pts_inode) +void *devpts_get_priv(struct dentry *dentry) { - struct dentry *dentry; - void *priv = NULL; - - BUG_ON(pts_inode->i_rdev == MKDEV(TTYAUX_MAJOR, PTMX_MINOR)); - - /* Ensure dentry has not been deleted by devpts_pty_kill() */ - dentry = d_find_alias(pts_inode); - if (!dentry) - return NULL; - - if (pts_inode->i_sb->s_magic == DEVPTS_SUPER_MAGIC) - priv = pts_inode->i_private; - - dput(dentry); - - return priv; + WARN_ON_ONCE(dentry->d_sb->s_magic != DEVPTS_SUPER_MAGIC); + return dentry->d_fsdata; } /** @@ -682,24 +663,14 @@ void *devpts_get_priv(struct inode *pts_inode) * * This is an inverse operation of devpts_pty_new. */ -void devpts_pty_kill(struct inode *inode) +void devpts_pty_kill(struct dentry *dentry) { - struct super_block *sb = pts_sb_from_inode(inode); - struct dentry *root = sb->s_root; - struct dentry *dentry; + WARN_ON_ONCE(dentry->d_sb->s_magic != DEVPTS_SUPER_MAGIC); - BUG_ON(inode->i_rdev == MKDEV(TTYAUX_MAJOR, PTMX_MINOR)); - - inode_lock(d_inode(root)); - - dentry = d_find_alias(inode); - - drop_nlink(inode); + dentry->d_fsdata = NULL; + drop_nlink(dentry->d_inode); d_delete(dentry); dput(dentry); /* d_alloc_name() in devpts_pty_new() */ - dput(dentry); /* d_find_alias above */ - - inode_unlock(d_inode(root)); } static int __init init_devpts_fs(void) diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 719924d6c706..dcad5e210525 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -1295,7 +1295,7 @@ static int fuse_get_user_pages(struct fuse_req *req, struct iov_iter *ii, *nbytesp = nbytes; - return ret; + return ret < 0 ? ret : 0; } static inline int fuse_iter_npages(const struct iov_iter *ii_p) diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c index 9aed6e202201..13719d3f35f8 100644 --- a/fs/ocfs2/dlm/dlmmaster.c +++ b/fs/ocfs2/dlm/dlmmaster.c @@ -2455,6 +2455,8 @@ int dlm_deref_lockres_done_handler(struct o2net_msg *msg, u32 len, void *data, spin_unlock(&dlm->spinlock); + ret = 0; + done: dlm_put(dlm); return ret; diff --git a/fs/pnode.c b/fs/pnode.c index c524fdddc7fb..99899705b105 100644 --- a/fs/pnode.c +++ b/fs/pnode.c @@ -198,7 +198,7 @@ static struct mount *next_group(struct mount *m, struct mount *origin) /* all accesses are serialized by namespace_sem */ static struct user_namespace *user_ns; -static struct mount *last_dest, *last_source, *dest_master; +static struct mount *last_dest, *first_source, *last_source, *dest_master; static struct mountpoint *mp; static struct hlist_head *list; @@ -221,20 +221,22 @@ static int propagate_one(struct mount *m) type = CL_MAKE_SHARED; } else { struct mount *n, *p; + bool done; for (n = m; ; n = p) { p = n->mnt_master; - if (p == dest_master || IS_MNT_MARKED(p)) { - while (last_dest->mnt_master != p) { - last_source = last_source->mnt_master; - last_dest = last_source->mnt_parent; - } - if (!peers(n, last_dest)) { - last_source = last_source->mnt_master; - last_dest = last_source->mnt_parent; - } + if (p == dest_master || IS_MNT_MARKED(p)) break; - } } + do { + struct mount *parent = last_source->mnt_parent; + if (last_source == first_source) + break; + done = parent->mnt_master == p; + if (done && peers(n, parent)) + break; + last_source = last_source->mnt_master; + } while (!done); + type = CL_SLAVE; /* beginning of peer group among the slaves? */ if (IS_MNT_SHARED(m)) @@ -286,6 +288,7 @@ int propagate_mnt(struct mount *dest_mnt, struct mountpoint *dest_mp, */ user_ns = current->nsproxy->mnt_ns->user_ns; last_dest = dest_mnt; + first_source = source_mnt; last_source = source_mnt; mp = dest_mp; list = tree_list; diff --git a/fs/proc/base.c b/fs/proc/base.c index b1755b23893e..92e37e224cd2 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -955,7 +955,8 @@ static ssize_t environ_read(struct file *file, char __user *buf, struct mm_struct *mm = file->private_data; unsigned long env_start, env_end; - if (!mm) + /* Ensure the process spawned far enough to have an environment. */ + if (!mm || !mm->env_end) return 0; page = (char *)__get_free_page(GFP_TEMPORARY); diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 229cb546bee0..541583510cfb 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1518,6 +1518,32 @@ static struct page *can_gather_numa_stats(pte_t pte, struct vm_area_struct *vma, return page; } +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static struct page *can_gather_numa_stats_pmd(pmd_t pmd, + struct vm_area_struct *vma, + unsigned long addr) +{ + struct page *page; + int nid; + + if (!pmd_present(pmd)) + return NULL; + + page = vm_normal_page_pmd(vma, addr, pmd); + if (!page) + return NULL; + + if (PageReserved(page)) + return NULL; + + nid = page_to_nid(page); + if (!node_isset(nid, node_states[N_MEMORY])) + return NULL; + + return page; +} +#endif + static int gather_pte_stats(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) { @@ -1527,14 +1553,14 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr, pte_t *orig_pte; pte_t *pte; +#ifdef CONFIG_TRANSPARENT_HUGEPAGE ptl = pmd_trans_huge_lock(pmd, vma); if (ptl) { - pte_t huge_pte = *(pte_t *)pmd; struct page *page; - page = can_gather_numa_stats(huge_pte, vma, addr); + page = can_gather_numa_stats_pmd(*pmd, vma, addr); if (page) - gather_stats(page, md, pte_dirty(huge_pte), + gather_stats(page, md, pmd_dirty(*pmd), HPAGE_PMD_SIZE/PAGE_SIZE); spin_unlock(ptl); return 0; @@ -1542,6 +1568,7 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr, if (pmd_trans_unstable(pmd)) return 0; +#endif orig_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl); do { struct page *page = can_gather_numa_stats(*pte, vma, addr); diff --git a/fs/udf/super.c b/fs/udf/super.c index fa92fe839fda..36661acaf33b 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -919,14 +919,14 @@ static int udf_load_pvoldesc(struct super_block *sb, sector_t block) #endif } - ret = udf_CS0toUTF8(outstr, 31, pvoldesc->volIdent, 32); + ret = udf_dstrCS0toUTF8(outstr, 31, pvoldesc->volIdent, 32); if (ret < 0) goto out_bh; strncpy(UDF_SB(sb)->s_volume_ident, outstr, ret); udf_debug("volIdent[] = '%s'\n", UDF_SB(sb)->s_volume_ident); - ret = udf_CS0toUTF8(outstr, 127, pvoldesc->volSetIdent, 128); + ret = udf_dstrCS0toUTF8(outstr, 127, pvoldesc->volSetIdent, 128); if (ret < 0) goto out_bh; diff --git a/fs/udf/udfdecl.h b/fs/udf/udfdecl.h index 972b70625614..263829ef1873 100644 --- a/fs/udf/udfdecl.h +++ b/fs/udf/udfdecl.h @@ -212,7 +212,7 @@ extern int udf_get_filename(struct super_block *, const uint8_t *, int, uint8_t *, int); extern int udf_put_filename(struct super_block *, const uint8_t *, int, uint8_t *, int); -extern int udf_CS0toUTF8(uint8_t *, int, const uint8_t *, int); +extern int udf_dstrCS0toUTF8(uint8_t *, int, const uint8_t *, int); /* ialloc.c */ extern void udf_free_inode(struct inode *); diff --git a/fs/udf/unicode.c b/fs/udf/unicode.c index 3ff42f4437f3..695389a4fc23 100644 --- a/fs/udf/unicode.c +++ b/fs/udf/unicode.c @@ -335,9 +335,21 @@ try_again: return u_len; } -int udf_CS0toUTF8(uint8_t *utf_o, int o_len, const uint8_t *ocu_i, int i_len) +int udf_dstrCS0toUTF8(uint8_t *utf_o, int o_len, + const uint8_t *ocu_i, int i_len) { - return udf_name_from_CS0(utf_o, o_len, ocu_i, i_len, + int s_len = 0; + + if (i_len > 0) { + s_len = ocu_i[i_len - 1]; + if (s_len >= i_len) { + pr_err("incorrect dstring lengths (%d/%d)\n", + s_len, i_len); + return -EINVAL; + } + } + + return udf_name_from_CS0(utf_o, o_len, ocu_i, s_len, udf_uni2char_utf8, 0); } diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index 14362a84c78e..3a932501d690 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -394,13 +394,13 @@ struct acpi_data_node { static inline bool is_acpi_node(struct fwnode_handle *fwnode) { - return fwnode && (fwnode->type == FWNODE_ACPI + return !IS_ERR_OR_NULL(fwnode) && (fwnode->type == FWNODE_ACPI || fwnode->type == FWNODE_ACPI_DATA); } static inline bool is_acpi_device_node(struct fwnode_handle *fwnode) { - return fwnode && fwnode->type == FWNODE_ACPI; + return !IS_ERR_OR_NULL(fwnode) && fwnode->type == FWNODE_ACPI; } static inline struct acpi_device *to_acpi_device_node(struct fwnode_handle *fwnode) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 21ee41b92e8a..f1d5c5acc8dd 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -171,12 +171,13 @@ void bpf_register_prog_type(struct bpf_prog_type_list *tl); void bpf_register_map_type(struct bpf_map_type_list *tl); struct bpf_prog *bpf_prog_get(u32 ufd); +struct bpf_prog *bpf_prog_inc(struct bpf_prog *prog); void bpf_prog_put(struct bpf_prog *prog); void bpf_prog_put_rcu(struct bpf_prog *prog); struct bpf_map *bpf_map_get_with_uref(u32 ufd); struct bpf_map *__bpf_map_get(struct fd f); -void bpf_map_inc(struct bpf_map *map, bool uref); +struct bpf_map *bpf_map_inc(struct bpf_map *map, bool uref); void bpf_map_put_with_uref(struct bpf_map *map); void bpf_map_put(struct bpf_map *map); int bpf_map_precharge_memlock(u32 pages); diff --git a/include/linux/ceph/auth.h b/include/linux/ceph/auth.h index 260d78b587c4..1563265d2097 100644 --- a/include/linux/ceph/auth.h +++ b/include/linux/ceph/auth.h @@ -12,9 +12,12 @@ */ struct ceph_auth_client; -struct ceph_authorizer; struct ceph_msg; +struct ceph_authorizer { + void (*destroy)(struct ceph_authorizer *); +}; + struct ceph_auth_handshake { struct ceph_authorizer *authorizer; void *authorizer_buf; @@ -62,8 +65,6 @@ struct ceph_auth_client_ops { struct ceph_auth_handshake *auth); int (*verify_authorizer_reply)(struct ceph_auth_client *ac, struct ceph_authorizer *a, size_t len); - void (*destroy_authorizer)(struct ceph_auth_client *ac, - struct ceph_authorizer *a); void (*invalidate_authorizer)(struct ceph_auth_client *ac, int peer_type); @@ -112,8 +113,7 @@ extern int ceph_auth_is_authenticated(struct ceph_auth_client *ac); extern int ceph_auth_create_authorizer(struct ceph_auth_client *ac, int peer_type, struct ceph_auth_handshake *auth); -extern void ceph_auth_destroy_authorizer(struct ceph_auth_client *ac, - struct ceph_authorizer *a); +void ceph_auth_destroy_authorizer(struct ceph_authorizer *a); extern int ceph_auth_update_authorizer(struct ceph_auth_client *ac, int peer_type, struct ceph_auth_handshake *a); diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 4343df806710..cbf460927c42 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -16,7 +16,6 @@ struct ceph_msg; struct ceph_snap_context; struct ceph_osd_request; struct ceph_osd_client; -struct ceph_authorizer; /* * completion callback for async writepages diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 3e39ae5bc799..5b17de62c962 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -444,6 +444,7 @@ struct cgroup_subsys { int (*can_attach)(struct cgroup_taskset *tset); void (*cancel_attach)(struct cgroup_taskset *tset); void (*attach)(struct cgroup_taskset *tset); + void (*post_attach)(void); int (*can_fork)(struct task_struct *task); void (*cancel_fork)(struct task_struct *task); void (*fork)(struct task_struct *task); diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index fea160ee5803..85a868ccb493 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -137,8 +137,6 @@ static inline void set_mems_allowed(nodemask_t nodemask) task_unlock(current); } -extern void cpuset_post_attach_flush(void); - #else /* !CONFIG_CPUSETS */ static inline bool cpusets_enabled(void) { return false; } @@ -245,10 +243,6 @@ static inline bool read_mems_allowed_retry(unsigned int seq) return false; } -static inline void cpuset_post_attach_flush(void) -{ -} - #endif /* !CONFIG_CPUSETS */ #endif /* _LINUX_CPUSET_H */ diff --git a/include/linux/devpts_fs.h b/include/linux/devpts_fs.h index 358a4db72a27..5871f292b596 100644 --- a/include/linux/devpts_fs.h +++ b/include/linux/devpts_fs.h @@ -27,11 +27,11 @@ int devpts_new_index(struct pts_fs_info *); void devpts_kill_index(struct pts_fs_info *, int); /* mknod in devpts */ -struct inode *devpts_pty_new(struct pts_fs_info *, dev_t, int, void *); +struct dentry *devpts_pty_new(struct pts_fs_info *, int, void *); /* get private structure */ -void *devpts_get_priv(struct inode *pts_inode); +void *devpts_get_priv(struct dentry *); /* unlink */ -void devpts_pty_kill(struct inode *inode); +void devpts_pty_kill(struct dentry *); #endif diff --git a/include/linux/hash.h b/include/linux/hash.h index 1afde47e1528..79c52fa81cac 100644 --- a/include/linux/hash.h +++ b/include/linux/hash.h @@ -32,12 +32,28 @@ #error Wordsize not 32 or 64 #endif +/* + * The above primes are actively bad for hashing, since they are + * too sparse. The 32-bit one is mostly ok, the 64-bit one causes + * real problems. Besides, the "prime" part is pointless for the + * multiplicative hash. + * + * Although a random odd number will do, it turns out that the golden + * ratio phi = (sqrt(5)-1)/2, or its negative, has particularly nice + * properties. + * + * These are the negative, (1 - phi) = (phi^2) = (3 - sqrt(5))/2. + * (See Knuth vol 3, section 6.4, exercise 9.) + */ +#define GOLDEN_RATIO_32 0x61C88647 +#define GOLDEN_RATIO_64 0x61C8864680B583EBull + static __always_inline u64 hash_64(u64 val, unsigned int bits) { u64 hash = val; -#if defined(CONFIG_ARCH_HAS_FAST_MULTIPLIER) && BITS_PER_LONG == 64 - hash = hash * GOLDEN_RATIO_PRIME_64; +#if BITS_PER_LONG == 64 + hash = hash * GOLDEN_RATIO_64; #else /* Sigh, gcc can't optimise this alone like it does for 32 bits. */ u64 n = hash; diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 7008623e24b1..d7b9e5346fba 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -152,6 +152,7 @@ static inline bool is_huge_zero_pmd(pmd_t pmd) } struct page *get_huge_zero_page(void); +void put_huge_zero_page(void); #else /* CONFIG_TRANSPARENT_HUGEPAGE */ #define HPAGE_PMD_SHIFT ({ BUILD_BUG(); 0; }) @@ -208,6 +209,10 @@ static inline bool is_huge_zero_page(struct page *page) return false; } +static inline void put_huge_zero_page(void) +{ + BUILD_BUG(); +} static inline struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, int flags) diff --git a/include/linux/if_ether.h b/include/linux/if_ether.h index d5569734f672..548fd535fd02 100644 --- a/include/linux/if_ether.h +++ b/include/linux/if_ether.h @@ -28,6 +28,11 @@ static inline struct ethhdr *eth_hdr(const struct sk_buff *skb) return (struct ethhdr *)skb_mac_header(skb); } +static inline struct ethhdr *inner_eth_hdr(const struct sk_buff *skb) +{ + return (struct ethhdr *)skb_inner_mac_header(skb); +} + int eth_header_parse(const struct sk_buff *skb, unsigned char *haddr); extern ssize_t sysfs_format_mac(char *buf, const unsigned char *addr, int len); diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index d026b190c530..d10ef06971b5 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -196,9 +196,11 @@ struct lock_list { * We record lock dependency chains, so that we can cache them: */ struct lock_chain { - u8 irq_context; - u8 depth; - u16 base; + /* see BUILD_BUG_ON()s in lookup_chain_cache() */ + unsigned int irq_context : 2, + depth : 6, + base : 24; + /* 4 byte hole */ struct hlist_node entry; u64 chain_key; }; diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 8156e3c9239c..b3575f392492 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -392,6 +392,17 @@ enum { MLX5_CAP_OFF_CMDIF_CSUM = 46, }; +enum { + /* + * Max wqe size for rdma read is 512 bytes, so this + * limits our max_sge_rd as the wqe needs to fit: + * - ctrl segment (16 bytes) + * - rdma segment (16 bytes) + * - scatter elements (16 bytes each) + */ + MLX5_MAX_SGE_RD = (512 - 16 - 16) / 16 +}; + struct mlx5_inbox_hdr { __be16 opcode; u8 rsvd[4]; diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index dcd5ac8d3b14..369c837d40f5 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -519,8 +519,9 @@ enum mlx5_device_state { }; enum mlx5_interface_state { - MLX5_INTERFACE_STATE_DOWN, - MLX5_INTERFACE_STATE_UP, + MLX5_INTERFACE_STATE_DOWN = BIT(0), + MLX5_INTERFACE_STATE_UP = BIT(1), + MLX5_INTERFACE_STATE_SHUTDOWN = BIT(2), }; enum mlx5_pci_status { @@ -544,7 +545,7 @@ struct mlx5_core_dev { enum mlx5_device_state state; /* sync interface state */ struct mutex intf_state_mutex; - enum mlx5_interface_state interface_state; + unsigned long intf_state; void (*event) (struct mlx5_core_dev *dev, enum mlx5_dev_event event, unsigned long param); diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h index a1d145abd4eb..b30250ab7604 100644 --- a/include/linux/mlx5/port.h +++ b/include/linux/mlx5/port.h @@ -54,9 +54,9 @@ int mlx5_set_port_admin_status(struct mlx5_core_dev *dev, int mlx5_query_port_admin_status(struct mlx5_core_dev *dev, enum mlx5_port_status *status); -int mlx5_set_port_mtu(struct mlx5_core_dev *dev, int mtu, u8 port); -void mlx5_query_port_max_mtu(struct mlx5_core_dev *dev, int *max_mtu, u8 port); -void mlx5_query_port_oper_mtu(struct mlx5_core_dev *dev, int *oper_mtu, +int mlx5_set_port_mtu(struct mlx5_core_dev *dev, u16 mtu, u8 port); +void mlx5_query_port_max_mtu(struct mlx5_core_dev *dev, u16 *max_mtu, u8 port); +void mlx5_query_port_oper_mtu(struct mlx5_core_dev *dev, u16 *oper_mtu, u8 port); int mlx5_query_port_vl_hw_cap(struct mlx5_core_dev *dev, diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h index bd93e6323603..301da4a5e6bf 100644 --- a/include/linux/mlx5/vport.h +++ b/include/linux/mlx5/vport.h @@ -45,6 +45,8 @@ int mlx5_query_nic_vport_mac_address(struct mlx5_core_dev *mdev, u16 vport, u8 *addr); int mlx5_modify_nic_vport_mac_address(struct mlx5_core_dev *dev, u16 vport, u8 *addr); +int mlx5_query_nic_vport_mtu(struct mlx5_core_dev *mdev, u16 *mtu); +int mlx5_modify_nic_vport_mtu(struct mlx5_core_dev *mdev, u16 mtu); int mlx5_query_nic_vport_system_image_guid(struct mlx5_core_dev *mdev, u64 *system_image_guid); int mlx5_query_nic_vport_node_guid(struct mlx5_core_dev *mdev, u64 *node_guid); diff --git a/include/linux/mm.h b/include/linux/mm.h index a55e5be0894f..864d7221de84 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1031,6 +1031,8 @@ static inline bool page_mapped(struct page *page) page = compound_head(page); if (atomic_read(compound_mapcount_ptr(page)) >= 0) return true; + if (PageHuge(page)) + return false; for (i = 0; i < hpage_nr_pages(page); i++) { if (atomic_read(&page[i]._mapcount) >= 0) return true; @@ -1138,6 +1140,8 @@ struct zap_details { struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, pte_t pte); +struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr, + pmd_t pmd); int zap_vma_ptes(struct vm_area_struct *vma, unsigned long address, unsigned long size); diff --git a/include/linux/net.h b/include/linux/net.h index 49175e4ced11..f840d77c6c31 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -246,7 +246,15 @@ do { \ net_ratelimited_function(pr_warn, fmt, ##__VA_ARGS__) #define net_info_ratelimited(fmt, ...) \ net_ratelimited_function(pr_info, fmt, ##__VA_ARGS__) -#if defined(DEBUG) +#if defined(CONFIG_DYNAMIC_DEBUG) +#define net_dbg_ratelimited(fmt, ...) \ +do { \ + DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, fmt); \ + if (unlikely(descriptor.flags & _DPRINTK_FLAGS_PRINT) && \ + net_ratelimit()) \ + __dynamic_pr_debug(&descriptor, fmt, ##__VA_ARGS__); \ +} while (0) +#elif defined(DEBUG) #define net_dbg_ratelimited(fmt, ...) \ net_ratelimited_function(pr_debug, fmt, ##__VA_ARGS__) #else diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 8395308a2445..b3c46b019ac1 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4004,7 +4004,7 @@ netdev_features_t netif_skb_features(struct sk_buff *skb); static inline bool net_gso_ok(netdev_features_t features, int gso_type) { - netdev_features_t feature = gso_type << NETIF_F_GSO_SHIFT; + netdev_features_t feature = (netdev_features_t)gso_type << NETIF_F_GSO_SHIFT; /* check flags correspondence */ BUILD_BUG_ON(SKB_GSO_TCPV4 != (NETIF_F_TSO >> NETIF_F_GSO_SHIFT)); diff --git a/include/linux/of.h b/include/linux/of.h index 7fcb681baadf..31758036787c 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -133,7 +133,7 @@ void of_core_init(void); static inline bool is_of_node(struct fwnode_handle *fwnode) { - return fwnode && fwnode->type == FWNODE_OF; + return !IS_ERR_OR_NULL(fwnode) && fwnode->type == FWNODE_OF; } static inline struct device_node *to_of_node(struct fwnode_handle *fwnode) diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index f4ed4f1b0c77..6b052aa7b5b7 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -517,6 +517,27 @@ static inline int PageTransCompound(struct page *page) } /* + * PageTransCompoundMap is the same as PageTransCompound, but it also + * guarantees the primary MMU has the entire compound page mapped + * through pmd_trans_huge, which in turn guarantees the secondary MMUs + * can also map the entire compound page. This allows the secondary + * MMUs to call get_user_pages() only once for each compound page and + * to immediately map the entire compound page with a single secondary + * MMU fault. If there will be a pmd split later, the secondary MMUs + * will get an update through the MMU notifier invalidation through + * split_huge_pmd(). + * + * Unlike PageTransCompound, this is safe to be called only while + * split_huge_pmd() cannot run from under us, like if protected by the + * MMU notifier, otherwise it may result in page->_mapcount < 0 false + * positives. + */ +static inline int PageTransCompoundMap(struct page *page) +{ + return PageTransCompound(page) && atomic_read(&page->_mapcount) < 0; +} + +/* * PageTransTail returns true for both transparent huge pages * and hugetlbfs pages, so it should only be called when it's known * that hugetlbfs pages aren't involved. @@ -559,6 +580,7 @@ static inline int TestClearPageDoubleMap(struct page *page) #else TESTPAGEFLAG_FALSE(TransHuge) TESTPAGEFLAG_FALSE(TransCompound) +TESTPAGEFLAG_FALSE(TransCompoundMap) TESTPAGEFLAG_FALSE(TransTail) TESTPAGEFLAG_FALSE(DoubleMap) TESTSETFLAG_FALSE(DoubleMap) diff --git a/include/linux/swap.h b/include/linux/swap.h index 2b83359c19ca..0a4cd4703f40 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -533,6 +533,10 @@ static inline swp_entry_t get_swap_page(void) #ifdef CONFIG_MEMCG static inline int mem_cgroup_swappiness(struct mem_cgroup *memcg) { + /* Cgroup2 doesn't have per-cgroup swappiness */ + if (cgroup_subsys_on_dfl(memory_cgrp_subsys)) + return vm_swappiness; + /* root ? */ if (mem_cgroup_disabled() || !memcg->css.parent) return vm_swappiness; diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h index 161052477f77..b742b5e47cc2 100644 --- a/include/linux/tty_driver.h +++ b/include/linux/tty_driver.h @@ -7,7 +7,7 @@ * defined; unless noted otherwise, they are optional, and can be * filled in with a null pointer. * - * struct tty_struct * (*lookup)(struct tty_driver *self, int idx) + * struct tty_struct * (*lookup)(struct tty_driver *self, struct file *, int idx) * * Return the tty device corresponding to idx, NULL if there is not * one currently in use and an ERR_PTR value on error. Called under @@ -250,7 +250,7 @@ struct serial_icounter_struct; struct tty_operations { struct tty_struct * (*lookup)(struct tty_driver *driver, - struct inode *inode, int idx); + struct file *filp, int idx); int (*install)(struct tty_driver *driver, struct tty_struct *tty); void (*remove)(struct tty_driver *driver, struct tty_struct *tty); int (*open)(struct tty_struct * tty, struct file * filp); diff --git a/include/media/videobuf2-core.h b/include/media/videobuf2-core.h index 8a0f55b6c2ba..88e3ab496e8f 100644 --- a/include/media/videobuf2-core.h +++ b/include/media/videobuf2-core.h @@ -375,6 +375,9 @@ struct vb2_ops { /** * struct vb2_ops - driver-specific callbacks * + * @verify_planes_array: Verify that a given user space structure contains + * enough planes for the buffer. This is called + * for each dequeued buffer. * @fill_user_buffer: given a vb2_buffer fill in the userspace structure. * For V4L2 this is a struct v4l2_buffer. * @fill_vb2_buffer: given a userspace structure, fill in the vb2_buffer. @@ -384,6 +387,7 @@ struct vb2_ops { * the vb2_buffer struct. */ struct vb2_buf_ops { + int (*verify_planes_array)(struct vb2_buffer *vb, const void *pb); void (*fill_user_buffer)(struct vb2_buffer *vb, void *pb); int (*fill_vb2_buffer)(struct vb2_buffer *vb, const void *pb, struct vb2_plane *planes); @@ -400,6 +404,9 @@ struct vb2_buf_ops { * @fileio_read_once: report EOF after reading the first buffer * @fileio_write_immediately: queue buffer after each write() call * @allow_zero_bytesused: allow bytesused == 0 to be passed to the driver + * @quirk_poll_must_check_waiting_for_buffers: Return POLLERR at poll when QBUF + * has not been called. This is a vb1 idiom that has been adopted + * also by vb2. * @lock: pointer to a mutex that protects the vb2_queue struct. The * driver can set this to a mutex to let the v4l2 core serialize * the queuing ioctls. If the driver wants to handle locking @@ -463,6 +470,7 @@ struct vb2_queue { unsigned fileio_read_once:1; unsigned fileio_write_immediately:1; unsigned allow_zero_bytesused:1; + unsigned quirk_poll_must_check_waiting_for_buffers:1; struct mutex *lock; void *owner; diff --git a/include/net/switchdev.h b/include/net/switchdev.h index d451122e8404..51d77b2ce2b2 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -54,6 +54,8 @@ struct switchdev_attr { struct net_device *orig_dev; enum switchdev_attr_id id; u32 flags; + void *complete_priv; + void (*complete)(struct net_device *dev, int err, void *priv); union { struct netdev_phys_item_id ppid; /* PORT_PARENT_ID */ u8 stp_state; /* PORT_STP_STATE */ @@ -75,6 +77,8 @@ struct switchdev_obj { struct net_device *orig_dev; enum switchdev_obj_id id; u32 flags; + void *complete_priv; + void (*complete)(struct net_device *dev, int err, void *priv); }; /* SWITCHDEV_OBJ_ID_PORT_VLAN */ diff --git a/include/net/vxlan.h b/include/net/vxlan.h index 73ed2e951c02..35437c779da8 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -252,7 +252,9 @@ static inline netdev_features_t vxlan_features_check(struct sk_buff *skb, (skb->inner_protocol_type != ENCAP_TYPE_ETHER || skb->inner_protocol != htons(ETH_P_TEB) || (skb_inner_mac_header(skb) - skb_transport_header(skb) != - sizeof(struct udphdr) + sizeof(struct vxlanhdr)))) + sizeof(struct udphdr) + sizeof(struct vxlanhdr)) || + (skb->ip_summed != CHECKSUM_NONE && + !can_checksum_protocol(features, inner_eth_hdr(skb)->h_proto)))) return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); return features; diff --git a/include/rdma/ib.h b/include/rdma/ib.h index cf8f9e700e48..a6b93706b0fc 100644 --- a/include/rdma/ib.h +++ b/include/rdma/ib.h @@ -34,6 +34,7 @@ #define _RDMA_IB_H #include <linux/types.h> +#include <linux/sched.h> struct ib_addr { union { @@ -86,4 +87,19 @@ struct sockaddr_ib { __u64 sib_scope_id; }; +/* + * The IB interfaces that use write() as bi-directional ioctl() are + * fundamentally unsafe, since there are lots of ways to trigger "write()" + * calls from various contexts with elevated privileges. That includes the + * traditional suid executable error message writes, but also various kernel + * interfaces that can write to file descriptors. + * + * This function provides protection for the legacy API by restricting the + * calling context. + */ +static inline bool ib_safe_file_access(struct file *filp) +{ + return filp->f_cred == current_cred() && segment_eq(get_fs(), USER_DS); +} + #endif /* _RDMA_IB_H */ diff --git a/include/sound/hda_i915.h b/include/sound/hda_i915.h index fa341fcb5829..f5842bcd9c94 100644 --- a/include/sound/hda_i915.h +++ b/include/sound/hda_i915.h @@ -9,7 +9,7 @@ #ifdef CONFIG_SND_HDA_I915 int snd_hdac_set_codec_wakeup(struct hdac_bus *bus, bool enable); int snd_hdac_display_power(struct hdac_bus *bus, bool enable); -int snd_hdac_get_display_clk(struct hdac_bus *bus); +void snd_hdac_i915_set_bclk(struct hdac_bus *bus); int snd_hdac_sync_audio_rate(struct hdac_bus *bus, hda_nid_t nid, int rate); int snd_hdac_acomp_get_eld(struct hdac_bus *bus, hda_nid_t nid, bool *audio_enabled, char *buffer, int max_bytes); @@ -25,9 +25,8 @@ static inline int snd_hdac_display_power(struct hdac_bus *bus, bool enable) { return 0; } -static inline int snd_hdac_get_display_clk(struct hdac_bus *bus) +static inline void snd_hdac_i915_set_bclk(struct hdac_bus *bus) { - return 0; } static inline int snd_hdac_sync_audio_rate(struct hdac_bus *bus, hda_nid_t nid, int rate) diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index 6e0f5f01734c..c51afb71bfab 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -718,9 +718,9 @@ __SYSCALL(__NR_mlock2, sys_mlock2) #define __NR_copy_file_range 285 __SYSCALL(__NR_copy_file_range, sys_copy_file_range) #define __NR_preadv2 286 -__SYSCALL(__NR_preadv2, sys_preadv2) +__SC_COMP(__NR_preadv2, sys_preadv2, compat_sys_preadv2) #define __NR_pwritev2 287 -__SYSCALL(__NR_pwritev2, sys_pwritev2) +__SC_COMP(__NR_pwritev2, sys_pwritev2, compat_sys_pwritev2) #undef __NR_syscalls #define __NR_syscalls 288 diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h index dea893199257..23c6960e94a4 100644 --- a/include/uapi/linux/btrfs.h +++ b/include/uapi/linux/btrfs.h @@ -23,6 +23,7 @@ #define BTRFS_IOCTL_MAGIC 0x94 #define BTRFS_VOL_NAME_MAX 255 +#define BTRFS_LABEL_SIZE 256 /* this should be 4k */ #define BTRFS_PATH_NAME_MAX 4087 @@ -33,14 +34,31 @@ struct btrfs_ioctl_vol_args { #define BTRFS_DEVICE_PATH_NAME_MAX 1024 -#define BTRFS_SUBVOL_CREATE_ASYNC (1ULL << 0) -#define BTRFS_SUBVOL_RDONLY (1ULL << 1) -#define BTRFS_SUBVOL_QGROUP_INHERIT (1ULL << 2) +#define BTRFS_DEVICE_SPEC_BY_ID (1ULL << 3) + +#define BTRFS_VOL_ARG_V2_FLAGS_SUPPORTED \ + (BTRFS_SUBVOL_CREATE_ASYNC | \ + BTRFS_SUBVOL_RDONLY | \ + BTRFS_SUBVOL_QGROUP_INHERIT | \ + BTRFS_DEVICE_SPEC_BY_ID) + #define BTRFS_FSID_SIZE 16 #define BTRFS_UUID_SIZE 16 #define BTRFS_UUID_UNPARSED_SIZE 37 -#define BTRFS_QGROUP_INHERIT_SET_LIMITS (1ULL << 0) +/* + * flags definition for qgroup limits + * + * Used by: + * struct btrfs_qgroup_limit.flags + * struct btrfs_qgroup_limit_item.flags + */ +#define BTRFS_QGROUP_LIMIT_MAX_RFER (1ULL << 0) +#define BTRFS_QGROUP_LIMIT_MAX_EXCL (1ULL << 1) +#define BTRFS_QGROUP_LIMIT_RSV_RFER (1ULL << 2) +#define BTRFS_QGROUP_LIMIT_RSV_EXCL (1ULL << 3) +#define BTRFS_QGROUP_LIMIT_RFER_CMPR (1ULL << 4) +#define BTRFS_QGROUP_LIMIT_EXCL_CMPR (1ULL << 5) struct btrfs_qgroup_limit { __u64 flags; @@ -50,6 +68,14 @@ struct btrfs_qgroup_limit { __u64 rsv_excl; }; +/* + * flags definition for qgroup inheritance + * + * Used by: + * struct btrfs_qgroup_inherit.flags + */ +#define BTRFS_QGROUP_INHERIT_SET_LIMITS (1ULL << 0) + struct btrfs_qgroup_inherit { __u64 flags; __u64 num_qgroups; @@ -64,6 +90,20 @@ struct btrfs_ioctl_qgroup_limit_args { struct btrfs_qgroup_limit lim; }; +/* + * flags for subvolumes + * + * Used by: + * struct btrfs_ioctl_vol_args_v2.flags + * + * BTRFS_SUBVOL_RDONLY is also provided/consumed by the following ioctls: + * - BTRFS_IOC_SUBVOL_GETFLAGS + * - BTRFS_IOC_SUBVOL_SETFLAGS + */ +#define BTRFS_SUBVOL_CREATE_ASYNC (1ULL << 0) +#define BTRFS_SUBVOL_RDONLY (1ULL << 1) +#define BTRFS_SUBVOL_QGROUP_INHERIT (1ULL << 2) + #define BTRFS_SUBVOL_NAME_MAX 4039 struct btrfs_ioctl_vol_args_v2 { __s64 fd; @@ -76,7 +116,10 @@ struct btrfs_ioctl_vol_args_v2 { }; __u64 unused[4]; }; - char name[BTRFS_SUBVOL_NAME_MAX + 1]; + union { + char name[BTRFS_SUBVOL_NAME_MAX + 1]; + u64 devid; + }; }; /* @@ -190,6 +233,37 @@ struct btrfs_ioctl_fs_info_args { __u64 reserved[122]; /* pad to 1k */ }; +/* + * feature flags + * + * Used by: + * struct btrfs_ioctl_feature_flags + */ +#define BTRFS_FEATURE_COMPAT_RO_FREE_SPACE_TREE (1ULL << 0) + +#define BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF (1ULL << 0) +#define BTRFS_FEATURE_INCOMPAT_DEFAULT_SUBVOL (1ULL << 1) +#define BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS (1ULL << 2) +#define BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO (1ULL << 3) +/* + * some patches floated around with a second compression method + * lets save that incompat here for when they do get in + * Note we don't actually support it, we're just reserving the + * number + */ +#define BTRFS_FEATURE_INCOMPAT_COMPRESS_LZOv2 (1ULL << 4) + +/* + * older kernels tried to do bigger metadata blocks, but the + * code was pretty buggy. Lets not let them try anymore. + */ +#define BTRFS_FEATURE_INCOMPAT_BIG_METADATA (1ULL << 5) + +#define BTRFS_FEATURE_INCOMPAT_EXTENDED_IREF (1ULL << 6) +#define BTRFS_FEATURE_INCOMPAT_RAID56 (1ULL << 7) +#define BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA (1ULL << 8) +#define BTRFS_FEATURE_INCOMPAT_NO_HOLES (1ULL << 9) + struct btrfs_ioctl_feature_flags { __u64 compat_flags; __u64 compat_ro_flags; @@ -254,6 +328,70 @@ struct btrfs_balance_progress { __u64 completed; /* # of chunks relocated so far */ }; +/* + * flags definition for balance + * + * Restriper's general type filter + * + * Used by: + * btrfs_ioctl_balance_args.flags + * btrfs_balance_control.flags (internal) + */ +#define BTRFS_BALANCE_DATA (1ULL << 0) +#define BTRFS_BALANCE_SYSTEM (1ULL << 1) +#define BTRFS_BALANCE_METADATA (1ULL << 2) + +#define BTRFS_BALANCE_TYPE_MASK (BTRFS_BALANCE_DATA | \ + BTRFS_BALANCE_SYSTEM | \ + BTRFS_BALANCE_METADATA) + +#define BTRFS_BALANCE_FORCE (1ULL << 3) +#define BTRFS_BALANCE_RESUME (1ULL << 4) + +/* + * flags definitions for per-type balance args + * + * Balance filters + * + * Used by: + * struct btrfs_balance_args + */ +#define BTRFS_BALANCE_ARGS_PROFILES (1ULL << 0) +#define BTRFS_BALANCE_ARGS_USAGE (1ULL << 1) +#define BTRFS_BALANCE_ARGS_DEVID (1ULL << 2) +#define BTRFS_BALANCE_ARGS_DRANGE (1ULL << 3) +#define BTRFS_BALANCE_ARGS_VRANGE (1ULL << 4) +#define BTRFS_BALANCE_ARGS_LIMIT (1ULL << 5) +#define BTRFS_BALANCE_ARGS_LIMIT_RANGE (1ULL << 6) +#define BTRFS_BALANCE_ARGS_STRIPES_RANGE (1ULL << 7) +#define BTRFS_BALANCE_ARGS_USAGE_RANGE (1ULL << 10) + +#define BTRFS_BALANCE_ARGS_MASK \ + (BTRFS_BALANCE_ARGS_PROFILES | \ + BTRFS_BALANCE_ARGS_USAGE | \ + BTRFS_BALANCE_ARGS_DEVID | \ + BTRFS_BALANCE_ARGS_DRANGE | \ + BTRFS_BALANCE_ARGS_VRANGE | \ + BTRFS_BALANCE_ARGS_LIMIT | \ + BTRFS_BALANCE_ARGS_LIMIT_RANGE | \ + BTRFS_BALANCE_ARGS_STRIPES_RANGE | \ + BTRFS_BALANCE_ARGS_USAGE_RANGE) + +/* + * Profile changing flags. When SOFT is set we won't relocate chunk if + * it already has the target profile (even though it may be + * half-filled). + */ +#define BTRFS_BALANCE_ARGS_CONVERT (1ULL << 8) +#define BTRFS_BALANCE_ARGS_SOFT (1ULL << 9) + + +/* + * flags definition for balance state + * + * Used by: + * struct btrfs_ioctl_balance_args.state + */ #define BTRFS_BALANCE_STATE_RUNNING (1ULL << 0) #define BTRFS_BALANCE_STATE_PAUSE_REQ (1ULL << 1) #define BTRFS_BALANCE_STATE_CANCEL_REQ (1ULL << 2) @@ -347,9 +485,45 @@ struct btrfs_ioctl_clone_range_args { __u64 dest_offset; }; -/* flags for the defrag range ioctl */ +/* + * flags definition for the defrag range ioctl + * + * Used by: + * struct btrfs_ioctl_defrag_range_args.flags + */ #define BTRFS_DEFRAG_RANGE_COMPRESS 1 #define BTRFS_DEFRAG_RANGE_START_IO 2 +struct btrfs_ioctl_defrag_range_args { + /* start of the defrag operation */ + __u64 start; + + /* number of bytes to defrag, use (u64)-1 to say all */ + __u64 len; + + /* + * flags for the operation, which can include turning + * on compression for this one defrag + */ + __u64 flags; + + /* + * any extent bigger than this will be considered + * already defragged. Use 0 to take the kernel default + * Use 1 to say every single extent must be rewritten + */ + __u32 extent_thresh; + + /* + * which compression method to use if turning on compression + * for this defrag operation. If unspecified, zlib will + * be used + */ + __u32 compress_type; + + /* spare for later */ + __u32 unused[4]; +}; + #define BTRFS_SAME_DATA_DIFFERS 1 /* For extent-same ioctl */ @@ -659,5 +833,7 @@ static inline char *btrfs_err_str(enum btrfs_err_code err_code) struct btrfs_ioctl_feature_flags[2]) #define BTRFS_IOC_GET_SUPPORTED_FEATURES _IOR(BTRFS_IOCTL_MAGIC, 57, \ struct btrfs_ioctl_feature_flags[3]) +#define BTRFS_IOC_RM_DEV_V2 _IOW(BTRFS_IOCTL_MAGIC, 58, \ + struct btrfs_ioctl_vol_args_v2) #endif /* _UAPI_LINUX_BTRFS_H */ diff --git a/include/uapi/linux/btrfs_tree.h b/include/uapi/linux/btrfs_tree.h new file mode 100644 index 000000000000..d5ad15a106a7 --- /dev/null +++ b/include/uapi/linux/btrfs_tree.h @@ -0,0 +1,966 @@ +#ifndef _BTRFS_CTREE_H_ +#define _BTRFS_CTREE_H_ + +/* + * This header contains the structure definitions and constants used + * by file system objects that can be retrieved using + * the BTRFS_IOC_SEARCH_TREE ioctl. That means basically anything that + * is needed to describe a leaf node's key or item contents. + */ + +/* holds pointers to all of the tree roots */ +#define BTRFS_ROOT_TREE_OBJECTID 1ULL + +/* stores information about which extents are in use, and reference counts */ +#define BTRFS_EXTENT_TREE_OBJECTID 2ULL + +/* + * chunk tree stores translations from logical -> physical block numbering + * the super block points to the chunk tree + */ +#define BTRFS_CHUNK_TREE_OBJECTID 3ULL + +/* + * stores information about which areas of a given device are in use. + * one per device. The tree of tree roots points to the device tree + */ +#define BTRFS_DEV_TREE_OBJECTID 4ULL + +/* one per subvolume, storing files and directories */ +#define BTRFS_FS_TREE_OBJECTID 5ULL + +/* directory objectid inside the root tree */ +#define BTRFS_ROOT_TREE_DIR_OBJECTID 6ULL + +/* holds checksums of all the data extents */ +#define BTRFS_CSUM_TREE_OBJECTID 7ULL + +/* holds quota configuration and tracking */ +#define BTRFS_QUOTA_TREE_OBJECTID 8ULL + +/* for storing items that use the BTRFS_UUID_KEY* types */ +#define BTRFS_UUID_TREE_OBJECTID 9ULL + +/* tracks free space in block groups. */ +#define BTRFS_FREE_SPACE_TREE_OBJECTID 10ULL + +/* device stats in the device tree */ +#define BTRFS_DEV_STATS_OBJECTID 0ULL + +/* for storing balance parameters in the root tree */ +#define BTRFS_BALANCE_OBJECTID -4ULL + +/* orhpan objectid for tracking unlinked/truncated files */ +#define BTRFS_ORPHAN_OBJECTID -5ULL + +/* does write ahead logging to speed up fsyncs */ +#define BTRFS_TREE_LOG_OBJECTID -6ULL +#define BTRFS_TREE_LOG_FIXUP_OBJECTID -7ULL + +/* for space balancing */ +#define BTRFS_TREE_RELOC_OBJECTID -8ULL +#define BTRFS_DATA_RELOC_TREE_OBJECTID -9ULL + +/* + * extent checksums all have this objectid + * this allows them to share the logging tree + * for fsyncs + */ +#define BTRFS_EXTENT_CSUM_OBJECTID -10ULL + +/* For storing free space cache */ +#define BTRFS_FREE_SPACE_OBJECTID -11ULL + +/* + * The inode number assigned to the special inode for storing + * free ino cache + */ +#define BTRFS_FREE_INO_OBJECTID -12ULL + +/* dummy objectid represents multiple objectids */ +#define BTRFS_MULTIPLE_OBJECTIDS -255ULL + +/* + * All files have objectids in this range. + */ +#define BTRFS_FIRST_FREE_OBJECTID 256ULL +#define BTRFS_LAST_FREE_OBJECTID -256ULL +#define BTRFS_FIRST_CHUNK_TREE_OBJECTID 256ULL + + +/* + * the device items go into the chunk tree. The key is in the form + * [ 1 BTRFS_DEV_ITEM_KEY device_id ] + */ +#define BTRFS_DEV_ITEMS_OBJECTID 1ULL + +#define BTRFS_BTREE_INODE_OBJECTID 1 + +#define BTRFS_EMPTY_SUBVOL_DIR_OBJECTID 2 + +#define BTRFS_DEV_REPLACE_DEVID 0ULL + +/* + * inode items have the data typically returned from stat and store other + * info about object characteristics. There is one for every file and dir in + * the FS + */ +#define BTRFS_INODE_ITEM_KEY 1 +#define BTRFS_INODE_REF_KEY 12 +#define BTRFS_INODE_EXTREF_KEY 13 +#define BTRFS_XATTR_ITEM_KEY 24 +#define BTRFS_ORPHAN_ITEM_KEY 48 +/* reserve 2-15 close to the inode for later flexibility */ + +/* + * dir items are the name -> inode pointers in a directory. There is one + * for every name in a directory. + */ +#define BTRFS_DIR_LOG_ITEM_KEY 60 +#define BTRFS_DIR_LOG_INDEX_KEY 72 +#define BTRFS_DIR_ITEM_KEY 84 +#define BTRFS_DIR_INDEX_KEY 96 +/* + * extent data is for file data + */ +#define BTRFS_EXTENT_DATA_KEY 108 + +/* + * extent csums are stored in a separate tree and hold csums for + * an entire extent on disk. + */ +#define BTRFS_EXTENT_CSUM_KEY 128 + +/* + * root items point to tree roots. They are typically in the root + * tree used by the super block to find all the other trees + */ +#define BTRFS_ROOT_ITEM_KEY 132 + +/* + * root backrefs tie subvols and snapshots to the directory entries that + * reference them + */ +#define BTRFS_ROOT_BACKREF_KEY 144 + +/* + * root refs make a fast index for listing all of the snapshots and + * subvolumes referenced by a given root. They point directly to the + * directory item in the root that references the subvol + */ +#define BTRFS_ROOT_REF_KEY 156 + +/* + * extent items are in the extent map tree. These record which blocks + * are used, and how many references there are to each block + */ +#define BTRFS_EXTENT_ITEM_KEY 168 + +/* + * The same as the BTRFS_EXTENT_ITEM_KEY, except it's metadata we already know + * the length, so we save the level in key->offset instead of the length. + */ +#define BTRFS_METADATA_ITEM_KEY 169 + +#define BTRFS_TREE_BLOCK_REF_KEY 176 + +#define BTRFS_EXTENT_DATA_REF_KEY 178 + +#define BTRFS_EXTENT_REF_V0_KEY 180 + +#define BTRFS_SHARED_BLOCK_REF_KEY 182 + +#define BTRFS_SHARED_DATA_REF_KEY 184 + +/* + * block groups give us hints into the extent allocation trees. Which + * blocks are free etc etc + */ +#define BTRFS_BLOCK_GROUP_ITEM_KEY 192 + +/* + * Every block group is represented in the free space tree by a free space info + * item, which stores some accounting information. It is keyed on + * (block_group_start, FREE_SPACE_INFO, block_group_length). + */ +#define BTRFS_FREE_SPACE_INFO_KEY 198 + +/* + * A free space extent tracks an extent of space that is free in a block group. + * It is keyed on (start, FREE_SPACE_EXTENT, length). + */ +#define BTRFS_FREE_SPACE_EXTENT_KEY 199 + +/* + * When a block group becomes very fragmented, we convert it to use bitmaps + * instead of extents. A free space bitmap is keyed on + * (start, FREE_SPACE_BITMAP, length); the corresponding item is a bitmap with + * (length / sectorsize) bits. + */ +#define BTRFS_FREE_SPACE_BITMAP_KEY 200 + +#define BTRFS_DEV_EXTENT_KEY 204 +#define BTRFS_DEV_ITEM_KEY 216 +#define BTRFS_CHUNK_ITEM_KEY 228 + +/* + * Records the overall state of the qgroups. + * There's only one instance of this key present, + * (0, BTRFS_QGROUP_STATUS_KEY, 0) + */ +#define BTRFS_QGROUP_STATUS_KEY 240 +/* + * Records the currently used space of the qgroup. + * One key per qgroup, (0, BTRFS_QGROUP_INFO_KEY, qgroupid). + */ +#define BTRFS_QGROUP_INFO_KEY 242 +/* + * Contains the user configured limits for the qgroup. + * One key per qgroup, (0, BTRFS_QGROUP_LIMIT_KEY, qgroupid). + */ +#define BTRFS_QGROUP_LIMIT_KEY 244 +/* + * Records the child-parent relationship of qgroups. For + * each relation, 2 keys are present: + * (childid, BTRFS_QGROUP_RELATION_KEY, parentid) + * (parentid, BTRFS_QGROUP_RELATION_KEY, childid) + */ +#define BTRFS_QGROUP_RELATION_KEY 246 + +/* + * Obsolete name, see BTRFS_TEMPORARY_ITEM_KEY. + */ +#define BTRFS_BALANCE_ITEM_KEY 248 + +/* + * The key type for tree items that are stored persistently, but do not need to + * exist for extended period of time. The items can exist in any tree. + * + * [subtype, BTRFS_TEMPORARY_ITEM_KEY, data] + * + * Existing items: + * + * - balance status item + * (BTRFS_BALANCE_OBJECTID, BTRFS_TEMPORARY_ITEM_KEY, 0) + */ +#define BTRFS_TEMPORARY_ITEM_KEY 248 + +/* + * Obsolete name, see BTRFS_PERSISTENT_ITEM_KEY + */ +#define BTRFS_DEV_STATS_KEY 249 + +/* + * The key type for tree items that are stored persistently and usually exist + * for a long period, eg. filesystem lifetime. The item kinds can be status + * information, stats or preference values. The item can exist in any tree. + * + * [subtype, BTRFS_PERSISTENT_ITEM_KEY, data] + * + * Existing items: + * + * - device statistics, store IO stats in the device tree, one key for all + * stats + * (BTRFS_DEV_STATS_OBJECTID, BTRFS_DEV_STATS_KEY, 0) + */ +#define BTRFS_PERSISTENT_ITEM_KEY 249 + +/* + * Persistantly stores the device replace state in the device tree. + * The key is built like this: (0, BTRFS_DEV_REPLACE_KEY, 0). + */ +#define BTRFS_DEV_REPLACE_KEY 250 + +/* + * Stores items that allow to quickly map UUIDs to something else. + * These items are part of the filesystem UUID tree. + * The key is built like this: + * (UUID_upper_64_bits, BTRFS_UUID_KEY*, UUID_lower_64_bits). + */ +#if BTRFS_UUID_SIZE != 16 +#error "UUID items require BTRFS_UUID_SIZE == 16!" +#endif +#define BTRFS_UUID_KEY_SUBVOL 251 /* for UUIDs assigned to subvols */ +#define BTRFS_UUID_KEY_RECEIVED_SUBVOL 252 /* for UUIDs assigned to + * received subvols */ + +/* + * string items are for debugging. They just store a short string of + * data in the FS + */ +#define BTRFS_STRING_ITEM_KEY 253 + + + +/* 32 bytes in various csum fields */ +#define BTRFS_CSUM_SIZE 32 + +/* csum types */ +#define BTRFS_CSUM_TYPE_CRC32 0 + +/* + * flags definitions for directory entry item type + * + * Used by: + * struct btrfs_dir_item.type + */ +#define BTRFS_FT_UNKNOWN 0 +#define BTRFS_FT_REG_FILE 1 +#define BTRFS_FT_DIR 2 +#define BTRFS_FT_CHRDEV 3 +#define BTRFS_FT_BLKDEV 4 +#define BTRFS_FT_FIFO 5 +#define BTRFS_FT_SOCK 6 +#define BTRFS_FT_SYMLINK 7 +#define BTRFS_FT_XATTR 8 +#define BTRFS_FT_MAX 9 + +/* + * The key defines the order in the tree, and so it also defines (optimal) + * block layout. + * + * objectid corresponds to the inode number. + * + * type tells us things about the object, and is a kind of stream selector. + * so for a given inode, keys with type of 1 might refer to the inode data, + * type of 2 may point to file data in the btree and type == 3 may point to + * extents. + * + * offset is the starting byte offset for this key in the stream. + * + * btrfs_disk_key is in disk byte order. struct btrfs_key is always + * in cpu native order. Otherwise they are identical and their sizes + * should be the same (ie both packed) + */ +struct btrfs_disk_key { + __le64 objectid; + __u8 type; + __le64 offset; +} __attribute__ ((__packed__)); + +struct btrfs_key { + __u64 objectid; + __u8 type; + __u64 offset; +} __attribute__ ((__packed__)); + +struct btrfs_dev_item { + /* the internal btrfs device id */ + __le64 devid; + + /* size of the device */ + __le64 total_bytes; + + /* bytes used */ + __le64 bytes_used; + + /* optimal io alignment for this device */ + __le32 io_align; + + /* optimal io width for this device */ + __le32 io_width; + + /* minimal io size for this device */ + __le32 sector_size; + + /* type and info about this device */ + __le64 type; + + /* expected generation for this device */ + __le64 generation; + + /* + * starting byte of this partition on the device, + * to allow for stripe alignment in the future + */ + __le64 start_offset; + + /* grouping information for allocation decisions */ + __le32 dev_group; + + /* seek speed 0-100 where 100 is fastest */ + __u8 seek_speed; + + /* bandwidth 0-100 where 100 is fastest */ + __u8 bandwidth; + + /* btrfs generated uuid for this device */ + __u8 uuid[BTRFS_UUID_SIZE]; + + /* uuid of FS who owns this device */ + __u8 fsid[BTRFS_UUID_SIZE]; +} __attribute__ ((__packed__)); + +struct btrfs_stripe { + __le64 devid; + __le64 offset; + __u8 dev_uuid[BTRFS_UUID_SIZE]; +} __attribute__ ((__packed__)); + +struct btrfs_chunk { + /* size of this chunk in bytes */ + __le64 length; + + /* objectid of the root referencing this chunk */ + __le64 owner; + + __le64 stripe_len; + __le64 type; + + /* optimal io alignment for this chunk */ + __le32 io_align; + + /* optimal io width for this chunk */ + __le32 io_width; + + /* minimal io size for this chunk */ + __le32 sector_size; + + /* 2^16 stripes is quite a lot, a second limit is the size of a single + * item in the btree + */ + __le16 num_stripes; + + /* sub stripes only matter for raid10 */ + __le16 sub_stripes; + struct btrfs_stripe stripe; + /* additional stripes go here */ +} __attribute__ ((__packed__)); + +#define BTRFS_FREE_SPACE_EXTENT 1 +#define BTRFS_FREE_SPACE_BITMAP 2 + +struct btrfs_free_space_entry { + __le64 offset; + __le64 bytes; + __u8 type; +} __attribute__ ((__packed__)); + +struct btrfs_free_space_header { + struct btrfs_disk_key location; + __le64 generation; + __le64 num_entries; + __le64 num_bitmaps; +} __attribute__ ((__packed__)); + +#define BTRFS_HEADER_FLAG_WRITTEN (1ULL << 0) +#define BTRFS_HEADER_FLAG_RELOC (1ULL << 1) + +/* Super block flags */ +/* Errors detected */ +#define BTRFS_SUPER_FLAG_ERROR (1ULL << 2) + +#define BTRFS_SUPER_FLAG_SEEDING (1ULL << 32) +#define BTRFS_SUPER_FLAG_METADUMP (1ULL << 33) + + +/* + * items in the extent btree are used to record the objectid of the + * owner of the block and the number of references + */ + +struct btrfs_extent_item { + __le64 refs; + __le64 generation; + __le64 flags; +} __attribute__ ((__packed__)); + +struct btrfs_extent_item_v0 { + __le32 refs; +} __attribute__ ((__packed__)); + + +#define BTRFS_EXTENT_FLAG_DATA (1ULL << 0) +#define BTRFS_EXTENT_FLAG_TREE_BLOCK (1ULL << 1) + +/* following flags only apply to tree blocks */ + +/* use full backrefs for extent pointers in the block */ +#define BTRFS_BLOCK_FLAG_FULL_BACKREF (1ULL << 8) + +/* + * this flag is only used internally by scrub and may be changed at any time + * it is only declared here to avoid collisions + */ +#define BTRFS_EXTENT_FLAG_SUPER (1ULL << 48) + +struct btrfs_tree_block_info { + struct btrfs_disk_key key; + __u8 level; +} __attribute__ ((__packed__)); + +struct btrfs_extent_data_ref { + __le64 root; + __le64 objectid; + __le64 offset; + __le32 count; +} __attribute__ ((__packed__)); + +struct btrfs_shared_data_ref { + __le32 count; +} __attribute__ ((__packed__)); + +struct btrfs_extent_inline_ref { + __u8 type; + __le64 offset; +} __attribute__ ((__packed__)); + +/* old style backrefs item */ +struct btrfs_extent_ref_v0 { + __le64 root; + __le64 generation; + __le64 objectid; + __le32 count; +} __attribute__ ((__packed__)); + + +/* dev extents record free space on individual devices. The owner + * field points back to the chunk allocation mapping tree that allocated + * the extent. The chunk tree uuid field is a way to double check the owner + */ +struct btrfs_dev_extent { + __le64 chunk_tree; + __le64 chunk_objectid; + __le64 chunk_offset; + __le64 length; + __u8 chunk_tree_uuid[BTRFS_UUID_SIZE]; +} __attribute__ ((__packed__)); + +struct btrfs_inode_ref { + __le64 index; + __le16 name_len; + /* name goes here */ +} __attribute__ ((__packed__)); + +struct btrfs_inode_extref { + __le64 parent_objectid; + __le64 index; + __le16 name_len; + __u8 name[0]; + /* name goes here */ +} __attribute__ ((__packed__)); + +struct btrfs_timespec { + __le64 sec; + __le32 nsec; +} __attribute__ ((__packed__)); + +struct btrfs_inode_item { + /* nfs style generation number */ + __le64 generation; + /* transid that last touched this inode */ + __le64 transid; + __le64 size; + __le64 nbytes; + __le64 block_group; + __le32 nlink; + __le32 uid; + __le32 gid; + __le32 mode; + __le64 rdev; + __le64 flags; + + /* modification sequence number for NFS */ + __le64 sequence; + + /* + * a little future expansion, for more than this we can + * just grow the inode item and version it + */ + __le64 reserved[4]; + struct btrfs_timespec atime; + struct btrfs_timespec ctime; + struct btrfs_timespec mtime; + struct btrfs_timespec otime; +} __attribute__ ((__packed__)); + +struct btrfs_dir_log_item { + __le64 end; +} __attribute__ ((__packed__)); + +struct btrfs_dir_item { + struct btrfs_disk_key location; + __le64 transid; + __le16 data_len; + __le16 name_len; + __u8 type; +} __attribute__ ((__packed__)); + +#define BTRFS_ROOT_SUBVOL_RDONLY (1ULL << 0) + +/* + * Internal in-memory flag that a subvolume has been marked for deletion but + * still visible as a directory + */ +#define BTRFS_ROOT_SUBVOL_DEAD (1ULL << 48) + +struct btrfs_root_item { + struct btrfs_inode_item inode; + __le64 generation; + __le64 root_dirid; + __le64 bytenr; + __le64 byte_limit; + __le64 bytes_used; + __le64 last_snapshot; + __le64 flags; + __le32 refs; + struct btrfs_disk_key drop_progress; + __u8 drop_level; + __u8 level; + + /* + * The following fields appear after subvol_uuids+subvol_times + * were introduced. + */ + + /* + * This generation number is used to test if the new fields are valid + * and up to date while reading the root item. Every time the root item + * is written out, the "generation" field is copied into this field. If + * anyone ever mounted the fs with an older kernel, we will have + * mismatching generation values here and thus must invalidate the + * new fields. See btrfs_update_root and btrfs_find_last_root for + * details. + * the offset of generation_v2 is also used as the start for the memset + * when invalidating the fields. + */ + __le64 generation_v2; + __u8 uuid[BTRFS_UUID_SIZE]; + __u8 parent_uuid[BTRFS_UUID_SIZE]; + __u8 received_uuid[BTRFS_UUID_SIZE]; + __le64 ctransid; /* updated when an inode changes */ + __le64 otransid; /* trans when created */ + __le64 stransid; /* trans when sent. non-zero for received subvol */ + __le64 rtransid; /* trans when received. non-zero for received subvol */ + struct btrfs_timespec ctime; + struct btrfs_timespec otime; + struct btrfs_timespec stime; + struct btrfs_timespec rtime; + __le64 reserved[8]; /* for future */ +} __attribute__ ((__packed__)); + +/* + * this is used for both forward and backward root refs + */ +struct btrfs_root_ref { + __le64 dirid; + __le64 sequence; + __le16 name_len; +} __attribute__ ((__packed__)); + +struct btrfs_disk_balance_args { + /* + * profiles to operate on, single is denoted by + * BTRFS_AVAIL_ALLOC_BIT_SINGLE + */ + __le64 profiles; + + /* + * usage filter + * BTRFS_BALANCE_ARGS_USAGE with a single value means '0..N' + * BTRFS_BALANCE_ARGS_USAGE_RANGE - range syntax, min..max + */ + union { + __le64 usage; + struct { + __le32 usage_min; + __le32 usage_max; + }; + }; + + /* devid filter */ + __le64 devid; + + /* devid subset filter [pstart..pend) */ + __le64 pstart; + __le64 pend; + + /* btrfs virtual address space subset filter [vstart..vend) */ + __le64 vstart; + __le64 vend; + + /* + * profile to convert to, single is denoted by + * BTRFS_AVAIL_ALLOC_BIT_SINGLE + */ + __le64 target; + + /* BTRFS_BALANCE_ARGS_* */ + __le64 flags; + + /* + * BTRFS_BALANCE_ARGS_LIMIT with value 'limit' + * BTRFS_BALANCE_ARGS_LIMIT_RANGE - the extend version can use minimum + * and maximum + */ + union { + __le64 limit; + struct { + __le32 limit_min; + __le32 limit_max; + }; + }; + + /* + * Process chunks that cross stripes_min..stripes_max devices, + * BTRFS_BALANCE_ARGS_STRIPES_RANGE + */ + __le32 stripes_min; + __le32 stripes_max; + + __le64 unused[6]; +} __attribute__ ((__packed__)); + +/* + * store balance parameters to disk so that balance can be properly + * resumed after crash or unmount + */ +struct btrfs_balance_item { + /* BTRFS_BALANCE_* */ + __le64 flags; + + struct btrfs_disk_balance_args data; + struct btrfs_disk_balance_args meta; + struct btrfs_disk_balance_args sys; + + __le64 unused[4]; +} __attribute__ ((__packed__)); + +#define BTRFS_FILE_EXTENT_INLINE 0 +#define BTRFS_FILE_EXTENT_REG 1 +#define BTRFS_FILE_EXTENT_PREALLOC 2 + +struct btrfs_file_extent_item { + /* + * transaction id that created this extent + */ + __le64 generation; + /* + * max number of bytes to hold this extent in ram + * when we split a compressed extent we can't know how big + * each of the resulting pieces will be. So, this is + * an upper limit on the size of the extent in ram instead of + * an exact limit. + */ + __le64 ram_bytes; + + /* + * 32 bits for the various ways we might encode the data, + * including compression and encryption. If any of these + * are set to something a given disk format doesn't understand + * it is treated like an incompat flag for reading and writing, + * but not for stat. + */ + __u8 compression; + __u8 encryption; + __le16 other_encoding; /* spare for later use */ + + /* are we inline data or a real extent? */ + __u8 type; + + /* + * disk space consumed by the extent, checksum blocks are included + * in these numbers + * + * At this offset in the structure, the inline extent data start. + */ + __le64 disk_bytenr; + __le64 disk_num_bytes; + /* + * the logical offset in file blocks (no csums) + * this extent record is for. This allows a file extent to point + * into the middle of an existing extent on disk, sharing it + * between two snapshots (useful if some bytes in the middle of the + * extent have changed + */ + __le64 offset; + /* + * the logical number of file blocks (no csums included). This + * always reflects the size uncompressed and without encoding. + */ + __le64 num_bytes; + +} __attribute__ ((__packed__)); + +struct btrfs_csum_item { + __u8 csum; +} __attribute__ ((__packed__)); + +struct btrfs_dev_stats_item { + /* + * grow this item struct at the end for future enhancements and keep + * the existing values unchanged + */ + __le64 values[BTRFS_DEV_STAT_VALUES_MAX]; +} __attribute__ ((__packed__)); + +#define BTRFS_DEV_REPLACE_ITEM_CONT_READING_FROM_SRCDEV_MODE_ALWAYS 0 +#define BTRFS_DEV_REPLACE_ITEM_CONT_READING_FROM_SRCDEV_MODE_AVOID 1 +#define BTRFS_DEV_REPLACE_ITEM_STATE_NEVER_STARTED 0 +#define BTRFS_DEV_REPLACE_ITEM_STATE_STARTED 1 +#define BTRFS_DEV_REPLACE_ITEM_STATE_SUSPENDED 2 +#define BTRFS_DEV_REPLACE_ITEM_STATE_FINISHED 3 +#define BTRFS_DEV_REPLACE_ITEM_STATE_CANCELED 4 + +struct btrfs_dev_replace_item { + /* + * grow this item struct at the end for future enhancements and keep + * the existing values unchanged + */ + __le64 src_devid; + __le64 cursor_left; + __le64 cursor_right; + __le64 cont_reading_from_srcdev_mode; + + __le64 replace_state; + __le64 time_started; + __le64 time_stopped; + __le64 num_write_errors; + __le64 num_uncorrectable_read_errors; +} __attribute__ ((__packed__)); + +/* different types of block groups (and chunks) */ +#define BTRFS_BLOCK_GROUP_DATA (1ULL << 0) +#define BTRFS_BLOCK_GROUP_SYSTEM (1ULL << 1) +#define BTRFS_BLOCK_GROUP_METADATA (1ULL << 2) +#define BTRFS_BLOCK_GROUP_RAID0 (1ULL << 3) +#define BTRFS_BLOCK_GROUP_RAID1 (1ULL << 4) +#define BTRFS_BLOCK_GROUP_DUP (1ULL << 5) +#define BTRFS_BLOCK_GROUP_RAID10 (1ULL << 6) +#define BTRFS_BLOCK_GROUP_RAID5 (1ULL << 7) +#define BTRFS_BLOCK_GROUP_RAID6 (1ULL << 8) +#define BTRFS_BLOCK_GROUP_RESERVED (BTRFS_AVAIL_ALLOC_BIT_SINGLE | \ + BTRFS_SPACE_INFO_GLOBAL_RSV) + +enum btrfs_raid_types { + BTRFS_RAID_RAID10, + BTRFS_RAID_RAID1, + BTRFS_RAID_DUP, + BTRFS_RAID_RAID0, + BTRFS_RAID_SINGLE, + BTRFS_RAID_RAID5, + BTRFS_RAID_RAID6, + BTRFS_NR_RAID_TYPES +}; + +#define BTRFS_BLOCK_GROUP_TYPE_MASK (BTRFS_BLOCK_GROUP_DATA | \ + BTRFS_BLOCK_GROUP_SYSTEM | \ + BTRFS_BLOCK_GROUP_METADATA) + +#define BTRFS_BLOCK_GROUP_PROFILE_MASK (BTRFS_BLOCK_GROUP_RAID0 | \ + BTRFS_BLOCK_GROUP_RAID1 | \ + BTRFS_BLOCK_GROUP_RAID5 | \ + BTRFS_BLOCK_GROUP_RAID6 | \ + BTRFS_BLOCK_GROUP_DUP | \ + BTRFS_BLOCK_GROUP_RAID10) +#define BTRFS_BLOCK_GROUP_RAID56_MASK (BTRFS_BLOCK_GROUP_RAID5 | \ + BTRFS_BLOCK_GROUP_RAID6) + +/* + * We need a bit for restriper to be able to tell when chunks of type + * SINGLE are available. This "extended" profile format is used in + * fs_info->avail_*_alloc_bits (in-memory) and balance item fields + * (on-disk). The corresponding on-disk bit in chunk.type is reserved + * to avoid remappings between two formats in future. + */ +#define BTRFS_AVAIL_ALLOC_BIT_SINGLE (1ULL << 48) + +/* + * A fake block group type that is used to communicate global block reserve + * size to userspace via the SPACE_INFO ioctl. + */ +#define BTRFS_SPACE_INFO_GLOBAL_RSV (1ULL << 49) + +#define BTRFS_EXTENDED_PROFILE_MASK (BTRFS_BLOCK_GROUP_PROFILE_MASK | \ + BTRFS_AVAIL_ALLOC_BIT_SINGLE) + +static inline __u64 chunk_to_extended(__u64 flags) +{ + if ((flags & BTRFS_BLOCK_GROUP_PROFILE_MASK) == 0) + flags |= BTRFS_AVAIL_ALLOC_BIT_SINGLE; + + return flags; +} +static inline __u64 extended_to_chunk(__u64 flags) +{ + return flags & ~BTRFS_AVAIL_ALLOC_BIT_SINGLE; +} + +struct btrfs_block_group_item { + __le64 used; + __le64 chunk_objectid; + __le64 flags; +} __attribute__ ((__packed__)); + +struct btrfs_free_space_info { + __le32 extent_count; + __le32 flags; +} __attribute__ ((__packed__)); + +#define BTRFS_FREE_SPACE_USING_BITMAPS (1ULL << 0) + +#define BTRFS_QGROUP_LEVEL_SHIFT 48 +static inline __u64 btrfs_qgroup_level(__u64 qgroupid) +{ + return qgroupid >> BTRFS_QGROUP_LEVEL_SHIFT; +} + +/* + * is subvolume quota turned on? + */ +#define BTRFS_QGROUP_STATUS_FLAG_ON (1ULL << 0) +/* + * RESCAN is set during the initialization phase + */ +#define BTRFS_QGROUP_STATUS_FLAG_RESCAN (1ULL << 1) +/* + * Some qgroup entries are known to be out of date, + * either because the configuration has changed in a way that + * makes a rescan necessary, or because the fs has been mounted + * with a non-qgroup-aware version. + * Turning qouta off and on again makes it inconsistent, too. + */ +#define BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT (1ULL << 2) + +#define BTRFS_QGROUP_STATUS_VERSION 1 + +struct btrfs_qgroup_status_item { + __le64 version; + /* + * the generation is updated during every commit. As older + * versions of btrfs are not aware of qgroups, it will be + * possible to detect inconsistencies by checking the + * generation on mount time + */ + __le64 generation; + + /* flag definitions see above */ + __le64 flags; + + /* + * only used during scanning to record the progress + * of the scan. It contains a logical address + */ + __le64 rescan; +} __attribute__ ((__packed__)); + +struct btrfs_qgroup_info_item { + __le64 generation; + __le64 rfer; + __le64 rfer_cmpr; + __le64 excl; + __le64 excl_cmpr; +} __attribute__ ((__packed__)); + +struct btrfs_qgroup_limit_item { + /* + * only updated when any of the other values change + */ + __le64 flags; + __le64 max_rfer; + __le64 max_excl; + __le64 rsv_rfer; + __le64 rsv_excl; +} __attribute__ ((__packed__)); + +#endif /* _BTRFS_CTREE_H_ */ diff --git a/include/uapi/linux/if_macsec.h b/include/uapi/linux/if_macsec.h index 26b0d1e3e3e7..4c58d9917aa4 100644 --- a/include/uapi/linux/if_macsec.h +++ b/include/uapi/linux/if_macsec.h @@ -19,8 +19,8 @@ #define MACSEC_MAX_KEY_LEN 128 -#define DEFAULT_CIPHER_ID 0x0080020001000001ULL -#define DEFAULT_CIPHER_ALT 0x0080C20001000001ULL +#define MACSEC_DEFAULT_CIPHER_ID 0x0080020001000001ULL +#define MACSEC_DEFAULT_CIPHER_ALT 0x0080C20001000001ULL #define MACSEC_MIN_ICV_LEN 8 #define MACSEC_MAX_ICV_LEN 32 diff --git a/include/linux/rio_mport_cdev.h b/include/uapi/linux/rio_mport_cdev.h index b65d19df76d2..5796bf1d06ad 100644 --- a/include/linux/rio_mport_cdev.h +++ b/include/uapi/linux/rio_mport_cdev.h @@ -39,16 +39,16 @@ #ifndef _RIO_MPORT_CDEV_H_ #define _RIO_MPORT_CDEV_H_ -#ifndef __user -#define __user -#endif +#include <linux/ioctl.h> +#include <linux/types.h> struct rio_mport_maint_io { - uint32_t rioid; /* destID of remote device */ - uint32_t hopcount; /* hopcount to remote device */ - uint32_t offset; /* offset in register space */ - size_t length; /* length in bytes */ - void __user *buffer; /* data buffer */ + __u16 rioid; /* destID of remote device */ + __u8 hopcount; /* hopcount to remote device */ + __u8 pad0[5]; + __u32 offset; /* offset in register space */ + __u32 length; /* length in bytes */ + __u64 buffer; /* pointer to data buffer */ }; /* @@ -66,22 +66,23 @@ struct rio_mport_maint_io { #define RIO_CAP_MAP_INB (1 << 7) struct rio_mport_properties { - uint16_t hdid; - uint8_t id; /* Physical port ID */ - uint8_t index; - uint32_t flags; - uint32_t sys_size; /* Default addressing size */ - uint8_t port_ok; - uint8_t link_speed; - uint8_t link_width; - uint32_t dma_max_sge; - uint32_t dma_max_size; - uint32_t dma_align; - uint32_t transfer_mode; /* Default transfer mode */ - uint32_t cap_sys_size; /* Capable system sizes */ - uint32_t cap_addr_size; /* Capable addressing sizes */ - uint32_t cap_transfer_mode; /* Capable transfer modes */ - uint32_t cap_mport; /* Mport capabilities */ + __u16 hdid; + __u8 id; /* Physical port ID */ + __u8 index; + __u32 flags; + __u32 sys_size; /* Default addressing size */ + __u8 port_ok; + __u8 link_speed; + __u8 link_width; + __u8 pad0; + __u32 dma_max_sge; + __u32 dma_max_size; + __u32 dma_align; + __u32 transfer_mode; /* Default transfer mode */ + __u32 cap_sys_size; /* Capable system sizes */ + __u32 cap_addr_size; /* Capable addressing sizes */ + __u32 cap_transfer_mode; /* Capable transfer modes */ + __u32 cap_mport; /* Mport capabilities */ }; /* @@ -93,54 +94,57 @@ struct rio_mport_properties { #define RIO_PORTWRITE (1 << 1) struct rio_doorbell { - uint32_t rioid; - uint16_t payload; + __u16 rioid; + __u16 payload; }; struct rio_doorbell_filter { - uint32_t rioid; /* 0xffffffff to match all ids */ - uint16_t low; - uint16_t high; + __u16 rioid; /* Use RIO_INVALID_DESTID to match all ids */ + __u16 low; + __u16 high; + __u16 pad0; }; struct rio_portwrite { - uint32_t payload[16]; + __u32 payload[16]; }; struct rio_pw_filter { - uint32_t mask; - uint32_t low; - uint32_t high; + __u32 mask; + __u32 low; + __u32 high; + __u32 pad0; }; /* RapidIO base address for inbound requests set to value defined below * indicates that no specific RIO-to-local address translation is requested * and driver should use direct (one-to-one) address mapping. */ -#define RIO_MAP_ANY_ADDR (uint64_t)(~((uint64_t) 0)) +#define RIO_MAP_ANY_ADDR (__u64)(~((__u64) 0)) struct rio_mmap { - uint32_t rioid; - uint64_t rio_addr; - uint64_t length; - uint64_t handle; - void *address; + __u16 rioid; + __u16 pad0[3]; + __u64 rio_addr; + __u64 length; + __u64 handle; + __u64 address; }; struct rio_dma_mem { - uint64_t length; /* length of DMA memory */ - uint64_t dma_handle; /* handle associated with this memory */ - void *buffer; /* pointer to this memory */ + __u64 length; /* length of DMA memory */ + __u64 dma_handle; /* handle associated with this memory */ + __u64 address; }; - struct rio_event { - unsigned int header; /* event type RIO_DOORBELL or RIO_PORTWRITE */ + __u32 header; /* event type RIO_DOORBELL or RIO_PORTWRITE */ union { struct rio_doorbell doorbell; /* header for RIO_DOORBELL */ struct rio_portwrite portwrite; /* header for RIO_PORTWRITE */ } u; + __u32 pad0; }; enum rio_transfer_sync { @@ -184,35 +188,37 @@ enum rio_exchange { }; struct rio_transfer_io { - uint32_t rioid; /* Target destID */ - uint64_t rio_addr; /* Address in target's RIO mem space */ - enum rio_exchange method; /* Data exchange method */ - void __user *loc_addr; - uint64_t handle; - uint64_t offset; /* Offset in buffer */ - uint64_t length; /* Length in bytes */ - uint32_t completion_code; /* Completion code for this transfer */ + __u64 rio_addr; /* Address in target's RIO mem space */ + __u64 loc_addr; + __u64 handle; + __u64 offset; /* Offset in buffer */ + __u64 length; /* Length in bytes */ + __u16 rioid; /* Target destID */ + __u16 method; /* Data exchange method, one of rio_exchange enum */ + __u32 completion_code; /* Completion code for this transfer */ }; struct rio_transaction { - uint32_t transfer_mode; /* Data transfer mode */ - enum rio_transfer_sync sync; /* Synchronization method */ - enum rio_transfer_dir dir; /* Transfer direction */ - size_t count; /* Number of transfers */ - struct rio_transfer_io __user *block; /* Array of <count> transfers */ + __u64 block; /* Pointer to array of <count> transfers */ + __u32 count; /* Number of transfers */ + __u32 transfer_mode; /* Data transfer mode */ + __u16 sync; /* Synch method, one of rio_transfer_sync enum */ + __u16 dir; /* Transfer direction, one of rio_transfer_dir enum */ + __u32 pad0; }; struct rio_async_tx_wait { - uint32_t token; /* DMA transaction ID token */ - uint32_t timeout; /* Wait timeout in msec, if 0 use default TO */ + __u32 token; /* DMA transaction ID token */ + __u32 timeout; /* Wait timeout in msec, if 0 use default TO */ }; #define RIO_MAX_DEVNAME_SZ 20 struct rio_rdev_info { - uint32_t destid; - uint8_t hopcount; - uint32_t comptag; + __u16 destid; + __u8 hopcount; + __u8 pad0; + __u32 comptag; char name[RIO_MAX_DEVNAME_SZ + 1]; }; @@ -220,11 +226,11 @@ struct rio_rdev_info { #define RIO_MPORT_DRV_MAGIC 'm' #define RIO_MPORT_MAINT_HDID_SET \ - _IOW(RIO_MPORT_DRV_MAGIC, 1, uint16_t) + _IOW(RIO_MPORT_DRV_MAGIC, 1, __u16) #define RIO_MPORT_MAINT_COMPTAG_SET \ - _IOW(RIO_MPORT_DRV_MAGIC, 2, uint32_t) + _IOW(RIO_MPORT_DRV_MAGIC, 2, __u32) #define RIO_MPORT_MAINT_PORT_IDX_GET \ - _IOR(RIO_MPORT_DRV_MAGIC, 3, uint32_t) + _IOR(RIO_MPORT_DRV_MAGIC, 3, __u32) #define RIO_MPORT_GET_PROPERTIES \ _IOR(RIO_MPORT_DRV_MAGIC, 4, struct rio_mport_properties) #define RIO_MPORT_MAINT_READ_LOCAL \ @@ -244,9 +250,9 @@ struct rio_rdev_info { #define RIO_DISABLE_PORTWRITE_RANGE \ _IOW(RIO_MPORT_DRV_MAGIC, 12, struct rio_pw_filter) #define RIO_SET_EVENT_MASK \ - _IOW(RIO_MPORT_DRV_MAGIC, 13, unsigned int) + _IOW(RIO_MPORT_DRV_MAGIC, 13, __u32) #define RIO_GET_EVENT_MASK \ - _IOR(RIO_MPORT_DRV_MAGIC, 14, unsigned int) + _IOR(RIO_MPORT_DRV_MAGIC, 14, __u32) #define RIO_MAP_OUTBOUND \ _IOWR(RIO_MPORT_DRV_MAGIC, 15, struct rio_mmap) #define RIO_UNMAP_OUTBOUND \ @@ -254,11 +260,11 @@ struct rio_rdev_info { #define RIO_MAP_INBOUND \ _IOWR(RIO_MPORT_DRV_MAGIC, 17, struct rio_mmap) #define RIO_UNMAP_INBOUND \ - _IOW(RIO_MPORT_DRV_MAGIC, 18, uint64_t) + _IOW(RIO_MPORT_DRV_MAGIC, 18, __u64) #define RIO_ALLOC_DMA \ _IOWR(RIO_MPORT_DRV_MAGIC, 19, struct rio_dma_mem) #define RIO_FREE_DMA \ - _IOW(RIO_MPORT_DRV_MAGIC, 20, uint64_t) + _IOW(RIO_MPORT_DRV_MAGIC, 20, __u64) #define RIO_TRANSFER \ _IOWR(RIO_MPORT_DRV_MAGIC, 21, struct rio_transaction) #define RIO_WAIT_FOR_ASYNC \ diff --git a/include/uapi/linux/swab.h b/include/uapi/linux/swab.h index 3f10e5317b46..8f3a8f606fd9 100644 --- a/include/uapi/linux/swab.h +++ b/include/uapi/linux/swab.h @@ -45,9 +45,7 @@ static inline __attribute_const__ __u16 __fswab16(__u16 val) { -#ifdef __HAVE_BUILTIN_BSWAP16__ - return __builtin_bswap16(val); -#elif defined (__arch_swab16) +#if defined (__arch_swab16) return __arch_swab16(val); #else return ___constant_swab16(val); @@ -56,9 +54,7 @@ static inline __attribute_const__ __u16 __fswab16(__u16 val) static inline __attribute_const__ __u32 __fswab32(__u32 val) { -#ifdef __HAVE_BUILTIN_BSWAP32__ - return __builtin_bswap32(val); -#elif defined(__arch_swab32) +#if defined(__arch_swab32) return __arch_swab32(val); #else return ___constant_swab32(val); @@ -67,9 +63,7 @@ static inline __attribute_const__ __u32 __fswab32(__u32 val) static inline __attribute_const__ __u64 __fswab64(__u64 val) { -#ifdef __HAVE_BUILTIN_BSWAP64__ - return __builtin_bswap64(val); -#elif defined (__arch_swab64) +#if defined (__arch_swab64) return __arch_swab64(val); #elif defined(__SWAB_64_THRU_32__) __u32 h = val >> 32; @@ -102,28 +96,40 @@ static inline __attribute_const__ __u32 __fswahb32(__u32 val) * __swab16 - return a byteswapped 16-bit value * @x: value to byteswap */ +#ifdef __HAVE_BUILTIN_BSWAP16__ +#define __swab16(x) (__u16)__builtin_bswap16((__u16)(x)) +#else #define __swab16(x) \ (__builtin_constant_p((__u16)(x)) ? \ ___constant_swab16(x) : \ __fswab16(x)) +#endif /** * __swab32 - return a byteswapped 32-bit value * @x: value to byteswap */ +#ifdef __HAVE_BUILTIN_BSWAP32__ +#define __swab32(x) (__u32)__builtin_bswap32((__u32)(x)) +#else #define __swab32(x) \ (__builtin_constant_p((__u32)(x)) ? \ ___constant_swab32(x) : \ __fswab32(x)) +#endif /** * __swab64 - return a byteswapped 64-bit value * @x: value to byteswap */ +#ifdef __HAVE_BUILTIN_BSWAP64__ +#define __swab64(x) (__u64)__builtin_bswap64((__u64)(x)) +#else #define __swab64(x) \ (__builtin_constant_p((__u64)(x)) ? \ ___constant_swab64(x) : \ __fswab64(x)) +#endif /** * __swahw32 - return a word-swapped 32-bit value diff --git a/include/uapi/linux/v4l2-dv-timings.h b/include/uapi/linux/v4l2-dv-timings.h index c039f1d68a09..086168e18ca8 100644 --- a/include/uapi/linux/v4l2-dv-timings.h +++ b/include/uapi/linux/v4l2-dv-timings.h @@ -183,7 +183,8 @@ #define V4L2_DV_BT_CEA_3840X2160P24 { \ .type = V4L2_DV_BT_656_1120, \ - V4L2_INIT_BT_TIMINGS(3840, 2160, 0, V4L2_DV_HSYNC_POS_POL, \ + V4L2_INIT_BT_TIMINGS(3840, 2160, 0, \ + V4L2_DV_HSYNC_POS_POL | V4L2_DV_VSYNC_POS_POL, \ 297000000, 1276, 88, 296, 8, 10, 72, 0, 0, 0, \ V4L2_DV_BT_STD_CEA861, \ V4L2_DV_FL_CAN_REDUCE_FPS | V4L2_DV_FL_IS_CE_VIDEO) \ @@ -191,14 +192,16 @@ #define V4L2_DV_BT_CEA_3840X2160P25 { \ .type = V4L2_DV_BT_656_1120, \ - V4L2_INIT_BT_TIMINGS(3840, 2160, 0, V4L2_DV_HSYNC_POS_POL, \ + V4L2_INIT_BT_TIMINGS(3840, 2160, 0, \ + V4L2_DV_HSYNC_POS_POL | V4L2_DV_VSYNC_POS_POL, \ 297000000, 1056, 88, 296, 8, 10, 72, 0, 0, 0, \ V4L2_DV_BT_STD_CEA861, V4L2_DV_FL_IS_CE_VIDEO) \ } #define V4L2_DV_BT_CEA_3840X2160P30 { \ .type = V4L2_DV_BT_656_1120, \ - V4L2_INIT_BT_TIMINGS(3840, 2160, 0, V4L2_DV_HSYNC_POS_POL, \ + V4L2_INIT_BT_TIMINGS(3840, 2160, 0, \ + V4L2_DV_HSYNC_POS_POL | V4L2_DV_VSYNC_POS_POL, \ 297000000, 176, 88, 296, 8, 10, 72, 0, 0, 0, \ V4L2_DV_BT_STD_CEA861, \ V4L2_DV_FL_CAN_REDUCE_FPS | V4L2_DV_FL_IS_CE_VIDEO) \ @@ -206,14 +209,16 @@ #define V4L2_DV_BT_CEA_3840X2160P50 { \ .type = V4L2_DV_BT_656_1120, \ - V4L2_INIT_BT_TIMINGS(3840, 2160, 0, V4L2_DV_HSYNC_POS_POL, \ + V4L2_INIT_BT_TIMINGS(3840, 2160, 0, \ + V4L2_DV_HSYNC_POS_POL | V4L2_DV_VSYNC_POS_POL, \ 594000000, 1056, 88, 296, 8, 10, 72, 0, 0, 0, \ V4L2_DV_BT_STD_CEA861, V4L2_DV_FL_IS_CE_VIDEO) \ } #define V4L2_DV_BT_CEA_3840X2160P60 { \ .type = V4L2_DV_BT_656_1120, \ - V4L2_INIT_BT_TIMINGS(3840, 2160, 0, V4L2_DV_HSYNC_POS_POL, \ + V4L2_INIT_BT_TIMINGS(3840, 2160, 0, \ + V4L2_DV_HSYNC_POS_POL | V4L2_DV_VSYNC_POS_POL, \ 594000000, 176, 88, 296, 8, 10, 72, 0, 0, 0, \ V4L2_DV_BT_STD_CEA861, \ V4L2_DV_FL_CAN_REDUCE_FPS | V4L2_DV_FL_IS_CE_VIDEO) \ @@ -221,7 +226,8 @@ #define V4L2_DV_BT_CEA_4096X2160P24 { \ .type = V4L2_DV_BT_656_1120, \ - V4L2_INIT_BT_TIMINGS(4096, 2160, 0, V4L2_DV_HSYNC_POS_POL, \ + V4L2_INIT_BT_TIMINGS(4096, 2160, 0, \ + V4L2_DV_HSYNC_POS_POL | V4L2_DV_VSYNC_POS_POL, \ 297000000, 1020, 88, 296, 8, 10, 72, 0, 0, 0, \ V4L2_DV_BT_STD_CEA861, \ V4L2_DV_FL_CAN_REDUCE_FPS | V4L2_DV_FL_IS_CE_VIDEO) \ @@ -229,14 +235,16 @@ #define V4L2_DV_BT_CEA_4096X2160P25 { \ .type = V4L2_DV_BT_656_1120, \ - V4L2_INIT_BT_TIMINGS(4096, 2160, 0, V4L2_DV_HSYNC_POS_POL, \ + V4L2_INIT_BT_TIMINGS(4096, 2160, 0, \ + V4L2_DV_HSYNC_POS_POL | V4L2_DV_VSYNC_POS_POL, \ 297000000, 968, 88, 128, 8, 10, 72, 0, 0, 0, \ V4L2_DV_BT_STD_CEA861, V4L2_DV_FL_IS_CE_VIDEO) \ } #define V4L2_DV_BT_CEA_4096X2160P30 { \ .type = V4L2_DV_BT_656_1120, \ - V4L2_INIT_BT_TIMINGS(4096, 2160, 0, V4L2_DV_HSYNC_POS_POL, \ + V4L2_INIT_BT_TIMINGS(4096, 2160, 0, \ + V4L2_DV_HSYNC_POS_POL | V4L2_DV_VSYNC_POS_POL, \ 297000000, 88, 88, 128, 8, 10, 72, 0, 0, 0, \ V4L2_DV_BT_STD_CEA861, \ V4L2_DV_FL_CAN_REDUCE_FPS | V4L2_DV_FL_IS_CE_VIDEO) \ @@ -244,14 +252,16 @@ #define V4L2_DV_BT_CEA_4096X2160P50 { \ .type = V4L2_DV_BT_656_1120, \ - V4L2_INIT_BT_TIMINGS(4096, 2160, 0, V4L2_DV_HSYNC_POS_POL, \ + V4L2_INIT_BT_TIMINGS(4096, 2160, 0, \ + V4L2_DV_HSYNC_POS_POL | V4L2_DV_VSYNC_POS_POL, \ 594000000, 968, 88, 128, 8, 10, 72, 0, 0, 0, \ V4L2_DV_BT_STD_CEA861, V4L2_DV_FL_IS_CE_VIDEO) \ } #define V4L2_DV_BT_CEA_4096X2160P60 { \ .type = V4L2_DV_BT_656_1120, \ - V4L2_INIT_BT_TIMINGS(4096, 2160, 0, V4L2_DV_HSYNC_POS_POL, \ + V4L2_INIT_BT_TIMINGS(4096, 2160, 0, \ + V4L2_DV_HSYNC_POS_POL | V4L2_DV_VSYNC_POS_POL, \ 594000000, 88, 88, 128, 8, 10, 72, 0, 0, 0, \ V4L2_DV_BT_STD_CEA861, \ V4L2_DV_FL_CAN_REDUCE_FPS | V4L2_DV_FL_IS_CE_VIDEO) \ diff --git a/include/xen/page.h b/include/xen/page.h index 96294ac93755..9dc46cb8a0fd 100644 --- a/include/xen/page.h +++ b/include/xen/page.h @@ -15,9 +15,9 @@ */ #define xen_pfn_to_page(xen_pfn) \ - ((pfn_to_page(((unsigned long)(xen_pfn) << XEN_PAGE_SHIFT) >> PAGE_SHIFT))) + (pfn_to_page((unsigned long)(xen_pfn) >> (PAGE_SHIFT - XEN_PAGE_SHIFT))) #define page_to_xen_pfn(page) \ - (((page_to_pfn(page)) << PAGE_SHIFT) >> XEN_PAGE_SHIFT) + ((page_to_pfn(page)) << (PAGE_SHIFT - XEN_PAGE_SHIFT)) #define XEN_PFN_PER_PAGE (PAGE_SIZE / XEN_PAGE_SIZE) diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index f2ece3c174a5..8f94ca1860cf 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -31,10 +31,10 @@ static void *bpf_any_get(void *raw, enum bpf_type type) { switch (type) { case BPF_TYPE_PROG: - atomic_inc(&((struct bpf_prog *)raw)->aux->refcnt); + raw = bpf_prog_inc(raw); break; case BPF_TYPE_MAP: - bpf_map_inc(raw, true); + raw = bpf_map_inc(raw, true); break; default: WARN_ON_ONCE(1); @@ -297,7 +297,8 @@ static void *bpf_obj_do_get(const struct filename *pathname, goto out; raw = bpf_any_get(inode->i_private, *type); - touch_atime(&path); + if (!IS_ERR(raw)) + touch_atime(&path); path_put(&path); return raw; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index adc5e4bd74f8..cf5e9f7ad13a 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -218,11 +218,18 @@ struct bpf_map *__bpf_map_get(struct fd f) return f.file->private_data; } -void bpf_map_inc(struct bpf_map *map, bool uref) +/* prog's and map's refcnt limit */ +#define BPF_MAX_REFCNT 32768 + +struct bpf_map *bpf_map_inc(struct bpf_map *map, bool uref) { - atomic_inc(&map->refcnt); + if (atomic_inc_return(&map->refcnt) > BPF_MAX_REFCNT) { + atomic_dec(&map->refcnt); + return ERR_PTR(-EBUSY); + } if (uref) atomic_inc(&map->usercnt); + return map; } struct bpf_map *bpf_map_get_with_uref(u32 ufd) @@ -234,7 +241,7 @@ struct bpf_map *bpf_map_get_with_uref(u32 ufd) if (IS_ERR(map)) return map; - bpf_map_inc(map, true); + map = bpf_map_inc(map, true); fdput(f); return map; @@ -658,6 +665,15 @@ static struct bpf_prog *__bpf_prog_get(struct fd f) return f.file->private_data; } +struct bpf_prog *bpf_prog_inc(struct bpf_prog *prog) +{ + if (atomic_inc_return(&prog->aux->refcnt) > BPF_MAX_REFCNT) { + atomic_dec(&prog->aux->refcnt); + return ERR_PTR(-EBUSY); + } + return prog; +} + /* called by sockets/tracing/seccomp before attaching program to an event * pairs with bpf_prog_put() */ @@ -670,7 +686,7 @@ struct bpf_prog *bpf_prog_get(u32 ufd) if (IS_ERR(prog)) return prog; - atomic_inc(&prog->aux->refcnt); + prog = bpf_prog_inc(prog); fdput(f); return prog; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 618ef77c302a..c5c17a62f509 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -239,16 +239,6 @@ static const char * const reg_type_str[] = { [CONST_IMM] = "imm", }; -static const struct { - int map_type; - int func_id; -} func_limit[] = { - {BPF_MAP_TYPE_PROG_ARRAY, BPF_FUNC_tail_call}, - {BPF_MAP_TYPE_PERF_EVENT_ARRAY, BPF_FUNC_perf_event_read}, - {BPF_MAP_TYPE_PERF_EVENT_ARRAY, BPF_FUNC_perf_event_output}, - {BPF_MAP_TYPE_STACK_TRACE, BPF_FUNC_get_stackid}, -}; - static void print_verifier_state(struct verifier_env *env) { enum bpf_reg_type t; @@ -921,27 +911,52 @@ static int check_func_arg(struct verifier_env *env, u32 regno, static int check_map_func_compatibility(struct bpf_map *map, int func_id) { - bool bool_map, bool_func; - int i; - if (!map) return 0; - for (i = 0; i < ARRAY_SIZE(func_limit); i++) { - bool_map = (map->map_type == func_limit[i].map_type); - bool_func = (func_id == func_limit[i].func_id); - /* only when map & func pair match it can continue. - * don't allow any other map type to be passed into - * the special func; - */ - if (bool_func && bool_map != bool_func) { - verbose("cannot pass map_type %d into func %d\n", - map->map_type, func_id); - return -EINVAL; - } + /* We need a two way check, first is from map perspective ... */ + switch (map->map_type) { + case BPF_MAP_TYPE_PROG_ARRAY: + if (func_id != BPF_FUNC_tail_call) + goto error; + break; + case BPF_MAP_TYPE_PERF_EVENT_ARRAY: + if (func_id != BPF_FUNC_perf_event_read && + func_id != BPF_FUNC_perf_event_output) + goto error; + break; + case BPF_MAP_TYPE_STACK_TRACE: + if (func_id != BPF_FUNC_get_stackid) + goto error; + break; + default: + break; + } + + /* ... and second from the function itself. */ + switch (func_id) { + case BPF_FUNC_tail_call: + if (map->map_type != BPF_MAP_TYPE_PROG_ARRAY) + goto error; + break; + case BPF_FUNC_perf_event_read: + case BPF_FUNC_perf_event_output: + if (map->map_type != BPF_MAP_TYPE_PERF_EVENT_ARRAY) + goto error; + break; + case BPF_FUNC_get_stackid: + if (map->map_type != BPF_MAP_TYPE_STACK_TRACE) + goto error; + break; + default: + break; } return 0; +error: + verbose("cannot pass map_type %d into func %d\n", + map->map_type, func_id); + return -EINVAL; } static int check_call(struct verifier_env *env, int func_id) @@ -2030,7 +2045,6 @@ static int replace_map_fd_with_map_ptr(struct verifier_env *env) if (IS_ERR(map)) { verbose("fd %d is not pointing to valid bpf_map\n", insn->imm); - fdput(f); return PTR_ERR(map); } @@ -2050,15 +2064,18 @@ static int replace_map_fd_with_map_ptr(struct verifier_env *env) return -E2BIG; } - /* remember this map */ - env->used_maps[env->used_map_cnt++] = map; - /* hold the map. If the program is rejected by verifier, * the map will be released by release_maps() or it * will be used by the valid program until it's unloaded * and all maps are released in free_bpf_prog_info() */ - bpf_map_inc(map, false); + map = bpf_map_inc(map, false); + if (IS_ERR(map)) { + fdput(f); + return PTR_ERR(map); + } + env->used_maps[env->used_map_cnt++] = map; + fdput(f); next_insn: insn++; diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 671dc05c0b0f..909a7d31ffd3 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -2825,9 +2825,10 @@ static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off, bool threadgroup) { struct task_struct *tsk; + struct cgroup_subsys *ss; struct cgroup *cgrp; pid_t pid; - int ret; + int ssid, ret; if (kstrtoint(strstrip(buf), 0, &pid) || pid < 0) return -EINVAL; @@ -2875,8 +2876,10 @@ out_unlock_rcu: rcu_read_unlock(); out_unlock_threadgroup: percpu_up_write(&cgroup_threadgroup_rwsem); + for_each_subsys(ss, ssid) + if (ss->post_attach) + ss->post_attach(); cgroup_kn_unlock(of->kn); - cpuset_post_attach_flush(); return ret ?: nbytes; } diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 00ab5c2b7c5b..1902956baba1 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -58,7 +58,6 @@ #include <asm/uaccess.h> #include <linux/atomic.h> #include <linux/mutex.h> -#include <linux/workqueue.h> #include <linux/cgroup.h> #include <linux/wait.h> @@ -1016,7 +1015,7 @@ static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from, } } -void cpuset_post_attach_flush(void) +static void cpuset_post_attach(void) { flush_workqueue(cpuset_migrate_mm_wq); } @@ -2087,6 +2086,7 @@ struct cgroup_subsys cpuset_cgrp_subsys = { .can_attach = cpuset_can_attach, .cancel_attach = cpuset_cancel_attach, .attach = cpuset_attach, + .post_attach = cpuset_post_attach, .bind = cpuset_bind, .legacy_cftypes = files, .early_init = true, diff --git a/kernel/events/core.c b/kernel/events/core.c index 52bedc5a5aaa..4e2ebf6f2f1f 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -412,7 +412,8 @@ int perf_cpu_time_max_percent_handler(struct ctl_table *table, int write, if (ret || !write) return ret; - if (sysctl_perf_cpu_time_max_percent == 100) { + if (sysctl_perf_cpu_time_max_percent == 100 || + sysctl_perf_cpu_time_max_percent == 0) { printk(KERN_WARNING "perf: Dynamic interrupt throttling disabled, can hang your system!\n"); WRITE_ONCE(perf_sample_allowed_ns, 0); @@ -1105,6 +1106,7 @@ static void put_ctx(struct perf_event_context *ctx) * function. * * Lock order: + * cred_guard_mutex * task_struct::perf_event_mutex * perf_event_context::mutex * perf_event::child_mutex; @@ -3420,7 +3422,6 @@ static struct task_struct * find_lively_task_by_vpid(pid_t vpid) { struct task_struct *task; - int err; rcu_read_lock(); if (!vpid) @@ -3434,16 +3435,7 @@ find_lively_task_by_vpid(pid_t vpid) if (!task) return ERR_PTR(-ESRCH); - /* Reuse ptrace permission checks for now. */ - err = -EACCES; - if (!ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS)) - goto errout; - return task; -errout: - put_task_struct(task); - return ERR_PTR(err); - } /* @@ -8413,6 +8405,24 @@ SYSCALL_DEFINE5(perf_event_open, get_online_cpus(); + if (task) { + err = mutex_lock_interruptible(&task->signal->cred_guard_mutex); + if (err) + goto err_cpus; + + /* + * Reuse ptrace permission checks for now. + * + * We must hold cred_guard_mutex across this and any potential + * perf_install_in_context() call for this new event to + * serialize against exec() altering our credentials (and the + * perf_event_exit_task() that could imply). + */ + err = -EACCES; + if (!ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS)) + goto err_cred; + } + if (flags & PERF_FLAG_PID_CGROUP) cgroup_fd = pid; @@ -8420,7 +8430,7 @@ SYSCALL_DEFINE5(perf_event_open, NULL, NULL, cgroup_fd); if (IS_ERR(event)) { err = PTR_ERR(event); - goto err_cpus; + goto err_cred; } if (is_sampling_event(event)) { @@ -8479,11 +8489,6 @@ SYSCALL_DEFINE5(perf_event_open, goto err_context; } - if (task) { - put_task_struct(task); - task = NULL; - } - /* * Look up the group leader (we will attach this event to it): */ @@ -8581,6 +8586,11 @@ SYSCALL_DEFINE5(perf_event_open, WARN_ON_ONCE(ctx->parent_ctx); + /* + * This is the point on no return; we cannot fail hereafter. This is + * where we start modifying current state. + */ + if (move_group) { /* * See perf_event_ctx_lock() for comments on the details @@ -8652,6 +8662,11 @@ SYSCALL_DEFINE5(perf_event_open, mutex_unlock(&gctx->mutex); mutex_unlock(&ctx->mutex); + if (task) { + mutex_unlock(&task->signal->cred_guard_mutex); + put_task_struct(task); + } + put_online_cpus(); mutex_lock(¤t->perf_event_mutex); @@ -8684,6 +8699,9 @@ err_alloc: */ if (!event_file) free_event(event); +err_cred: + if (task) + mutex_unlock(&task->signal->cred_guard_mutex); err_cpus: put_online_cpus(); err_task: @@ -8968,6 +8986,9 @@ static void perf_event_exit_task_context(struct task_struct *child, int ctxn) /* * When a child task exits, feed back event values to parent events. + * + * Can be called with cred_guard_mutex held when called from + * install_exec_creds(). */ void perf_event_exit_task(struct task_struct *child) { diff --git a/kernel/kcov.c b/kernel/kcov.c index 3efbee0834a8..a02f2dddd1d7 100644 --- a/kernel/kcov.c +++ b/kernel/kcov.c @@ -1,5 +1,6 @@ #define pr_fmt(fmt) "kcov: " fmt +#define DISABLE_BRANCH_PROFILING #include <linux/compiler.h> #include <linux/types.h> #include <linux/file.h> @@ -43,7 +44,7 @@ struct kcov { * Entry point from instrumented code. * This is called once per basic-block/edge. */ -void __sanitizer_cov_trace_pc(void) +void notrace __sanitizer_cov_trace_pc(void) { struct task_struct *t; enum kcov_mode mode; diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index 8d34308ea449..1391d3ee3b86 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -1415,6 +1415,9 @@ static int __init crash_save_vmcoreinfo_init(void) VMCOREINFO_OFFSET(page, lru); VMCOREINFO_OFFSET(page, _mapcount); VMCOREINFO_OFFSET(page, private); + VMCOREINFO_OFFSET(page, compound_dtor); + VMCOREINFO_OFFSET(page, compound_order); + VMCOREINFO_OFFSET(page, compound_head); VMCOREINFO_OFFSET(pglist_data, node_zones); VMCOREINFO_OFFSET(pglist_data, nr_zones); #ifdef CONFIG_FLAT_NODE_MEM_MAP @@ -1447,8 +1450,8 @@ static int __init crash_save_vmcoreinfo_init(void) #ifdef CONFIG_X86 VMCOREINFO_NUMBER(KERNEL_IMAGE_SIZE); #endif -#ifdef CONFIG_HUGETLBFS - VMCOREINFO_SYMBOL(free_huge_page); +#ifdef CONFIG_HUGETLB_PAGE + VMCOREINFO_NUMBER(HUGETLB_PAGE_DTOR); #endif arch_crash_save_vmcoreinfo(); diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index ed9410936a22..78c1c0ee6dc1 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -2176,15 +2176,37 @@ cache_hit: chain->irq_context = hlock->irq_context; i = get_first_held_lock(curr, hlock); chain->depth = curr->lockdep_depth + 1 - i; + + BUILD_BUG_ON((1UL << 24) <= ARRAY_SIZE(chain_hlocks)); + BUILD_BUG_ON((1UL << 6) <= ARRAY_SIZE(curr->held_locks)); + BUILD_BUG_ON((1UL << 8*sizeof(chain_hlocks[0])) <= ARRAY_SIZE(lock_classes)); + if (likely(nr_chain_hlocks + chain->depth <= MAX_LOCKDEP_CHAIN_HLOCKS)) { chain->base = nr_chain_hlocks; - nr_chain_hlocks += chain->depth; for (j = 0; j < chain->depth - 1; j++, i++) { int lock_id = curr->held_locks[i].class_idx - 1; chain_hlocks[chain->base + j] = lock_id; } chain_hlocks[chain->base + j] = class - lock_classes; } + + if (nr_chain_hlocks < MAX_LOCKDEP_CHAIN_HLOCKS) + nr_chain_hlocks += chain->depth; + +#ifdef CONFIG_DEBUG_LOCKDEP + /* + * Important for check_no_collision(). + */ + if (unlikely(nr_chain_hlocks > MAX_LOCKDEP_CHAIN_HLOCKS)) { + if (debug_locks_off_graph_unlock()) + return 0; + + print_lockdep_off("BUG: MAX_LOCKDEP_CHAIN_HLOCKS too low!"); + dump_stack(); + return 0; + } +#endif + hlist_add_head_rcu(&chain->entry, hash_head); debug_atomic_inc(chain_lookup_misses); inc_chains(); @@ -2932,6 +2954,11 @@ static int mark_irqflags(struct task_struct *curr, struct held_lock *hlock) return 1; } +static inline unsigned int task_irq_context(struct task_struct *task) +{ + return 2 * !!task->hardirq_context + !!task->softirq_context; +} + static int separate_irq_context(struct task_struct *curr, struct held_lock *hlock) { @@ -2940,8 +2967,6 @@ static int separate_irq_context(struct task_struct *curr, /* * Keep track of points where we cross into an interrupt context: */ - hlock->irq_context = 2*(curr->hardirq_context ? 1 : 0) + - curr->softirq_context; if (depth) { struct held_lock *prev_hlock; @@ -2973,6 +2998,11 @@ static inline int mark_irqflags(struct task_struct *curr, return 1; } +static inline unsigned int task_irq_context(struct task_struct *task) +{ + return 0; +} + static inline int separate_irq_context(struct task_struct *curr, struct held_lock *hlock) { @@ -3241,6 +3271,7 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass, hlock->acquire_ip = ip; hlock->instance = lock; hlock->nest_lock = nest_lock; + hlock->irq_context = task_irq_context(curr); hlock->trylock = trylock; hlock->read = read; hlock->check = check; diff --git a/kernel/locking/lockdep_proc.c b/kernel/locking/lockdep_proc.c index dbb61a302548..a0f61effad25 100644 --- a/kernel/locking/lockdep_proc.c +++ b/kernel/locking/lockdep_proc.c @@ -141,6 +141,8 @@ static int lc_show(struct seq_file *m, void *v) int i; if (v == SEQ_START_TOKEN) { + if (nr_chain_hlocks > MAX_LOCKDEP_CHAIN_HLOCKS) + seq_printf(m, "(buggered) "); seq_printf(m, "all lock chains:\n"); return 0; } diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 8b489fcac37b..d1f7149f8704 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -596,17 +596,8 @@ bool sched_can_stop_tick(struct rq *rq) return false; /* - * FIFO realtime policy runs the highest priority task (after DEADLINE). - * Other runnable tasks are of a lower priority. The scheduler tick - * isn't needed. - */ - fifo_nr_running = rq->rt.rt_nr_running - rq->rt.rr_nr_running; - if (fifo_nr_running) - return true; - - /* - * Round-robin realtime tasks time slice with other tasks at the same - * realtime priority. + * If there are more than one RR tasks, we need the tick to effect the + * actual RR behaviour. */ if (rq->rt.rr_nr_running) { if (rq->rt.rr_nr_running == 1) @@ -615,8 +606,20 @@ bool sched_can_stop_tick(struct rq *rq) return false; } - /* Normal multitasking need periodic preemption checks */ - if (rq->cfs.nr_running > 1) + /* + * If there's no RR tasks, but FIFO tasks, we can skip the tick, no + * forced preemption between FIFO tasks. + */ + fifo_nr_running = rq->rt.rt_nr_running - rq->rt.rr_nr_running; + if (fifo_nr_running) + return true; + + /* + * If there are no DL,RR/FIFO tasks, there must only be CFS tasks left; + * if there's more than one we need the tick for involuntary + * preemption. + */ + if (rq->nr_running > 1) return false; return true; diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 05ddc0820771..6f965864cc02 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -2095,8 +2095,13 @@ event_create_dir(struct dentry *parent, struct trace_event_file *file) trace_create_file("filter", 0644, file->dir, file, &ftrace_event_filter_fops); - trace_create_file("trigger", 0644, file->dir, file, - &event_trigger_fops); + /* + * Only event directories that can be enabled should have + * triggers. + */ + if (!(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE)) + trace_create_file("trigger", 0644, file->dir, file, + &event_trigger_fops); trace_create_file("format", 0444, file->dir, call, &ftrace_event_format_fops); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 2232ae3e3ad6..3bfdff06eea7 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -666,6 +666,35 @@ static void set_work_pool_and_clear_pending(struct work_struct *work, */ smp_wmb(); set_work_data(work, (unsigned long)pool_id << WORK_OFFQ_POOL_SHIFT, 0); + /* + * The following mb guarantees that previous clear of a PENDING bit + * will not be reordered with any speculative LOADS or STORES from + * work->current_func, which is executed afterwards. This possible + * reordering can lead to a missed execution on attempt to qeueue + * the same @work. E.g. consider this case: + * + * CPU#0 CPU#1 + * ---------------------------- -------------------------------- + * + * 1 STORE event_indicated + * 2 queue_work_on() { + * 3 test_and_set_bit(PENDING) + * 4 } set_..._and_clear_pending() { + * 5 set_work_data() # clear bit + * 6 smp_mb() + * 7 work->current_func() { + * 8 LOAD event_indicated + * } + * + * Without an explicit full barrier speculative LOAD on line 8 can + * be executed before CPU#0 does STORE on line 1. If that happens, + * CPU#0 observes the PENDING bit is still set and new execution of + * a @work is not queued in a hope, that CPU#1 will eventually + * finish the queued @work. Meanwhile CPU#1 does not see + * event_indicated is set, because speculative LOAD was executed + * before actual STORE. + */ + smp_mb(); } static void clear_work_data(struct work_struct *work) diff --git a/lib/stackdepot.c b/lib/stackdepot.c index 654c9d87e83a..53ad6c0831ae 100644 --- a/lib/stackdepot.c +++ b/lib/stackdepot.c @@ -42,12 +42,14 @@ #define DEPOT_STACK_BITS (sizeof(depot_stack_handle_t) * 8) +#define STACK_ALLOC_NULL_PROTECTION_BITS 1 #define STACK_ALLOC_ORDER 2 /* 'Slab' size order for stack depot, 4 pages */ #define STACK_ALLOC_SIZE (1LL << (PAGE_SHIFT + STACK_ALLOC_ORDER)) #define STACK_ALLOC_ALIGN 4 #define STACK_ALLOC_OFFSET_BITS (STACK_ALLOC_ORDER + PAGE_SHIFT - \ STACK_ALLOC_ALIGN) -#define STACK_ALLOC_INDEX_BITS (DEPOT_STACK_BITS - STACK_ALLOC_OFFSET_BITS) +#define STACK_ALLOC_INDEX_BITS (DEPOT_STACK_BITS - \ + STACK_ALLOC_NULL_PROTECTION_BITS - STACK_ALLOC_OFFSET_BITS) #define STACK_ALLOC_SLABS_CAP 1024 #define STACK_ALLOC_MAX_SLABS \ (((1LL << (STACK_ALLOC_INDEX_BITS)) < STACK_ALLOC_SLABS_CAP) ? \ @@ -59,6 +61,7 @@ union handle_parts { struct { u32 slabindex : STACK_ALLOC_INDEX_BITS; u32 offset : STACK_ALLOC_OFFSET_BITS; + u32 valid : STACK_ALLOC_NULL_PROTECTION_BITS; }; }; @@ -136,6 +139,7 @@ static struct stack_record *depot_alloc_stack(unsigned long *entries, int size, stack->size = size; stack->handle.slabindex = depot_index; stack->handle.offset = depot_offset >> STACK_ALLOC_ALIGN; + stack->handle.valid = 1; memcpy(stack->entries, entries, size * sizeof(unsigned long)); depot_offset += required_size; @@ -210,10 +214,6 @@ depot_stack_handle_t depot_save_stack(struct stack_trace *trace, goto fast_exit; hash = hash_stack(trace->entries, trace->nr_entries); - /* Bad luck, we won't store this stack. */ - if (hash == 0) - goto exit; - bucket = &stack_table[hash & STACK_HASH_MASK]; /* diff --git a/mm/compaction.c b/mm/compaction.c index ccf97b02b85f..8fa254043801 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -852,16 +852,8 @@ isolate_migratepages_range(struct compact_control *cc, unsigned long start_pfn, pfn = isolate_migratepages_block(cc, pfn, block_end_pfn, ISOLATE_UNEVICTABLE); - /* - * In case of fatal failure, release everything that might - * have been isolated in the previous iteration, and signal - * the failure back to caller. - */ - if (!pfn) { - putback_movable_pages(&cc->migratepages); - cc->nr_migratepages = 0; + if (!pfn) break; - } if (cc->nr_migratepages == COMPACT_CLUSTER_MAX) break; @@ -1741,7 +1733,7 @@ void compaction_unregister_node(struct node *node) static inline bool kcompactd_work_requested(pg_data_t *pgdat) { - return pgdat->kcompactd_max_order > 0; + return pgdat->kcompactd_max_order > 0 || kthread_should_stop(); } static bool kcompactd_node_suitable(pg_data_t *pgdat) @@ -1805,6 +1797,8 @@ static void kcompactd_do_work(pg_data_t *pgdat) INIT_LIST_HEAD(&cc.freepages); INIT_LIST_HEAD(&cc.migratepages); + if (kthread_should_stop()) + return; status = compact_zone(zone, &cc); if (zone_watermark_ok(zone, cc.order, low_wmark_pages(zone), diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 86f9f8b82f8e..f7daa7de8f48 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -232,7 +232,7 @@ retry: return READ_ONCE(huge_zero_page); } -static void put_huge_zero_page(void) +void put_huge_zero_page(void) { /* * Counter should never go to zero here. Only shrinker can put @@ -1684,12 +1684,12 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, if (vma_is_dax(vma)) { spin_unlock(ptl); if (is_huge_zero_pmd(orig_pmd)) - put_huge_zero_page(); + tlb_remove_page(tlb, pmd_page(orig_pmd)); } else if (is_huge_zero_pmd(orig_pmd)) { pte_free(tlb->mm, pgtable_trans_huge_withdraw(tlb->mm, pmd)); atomic_long_dec(&tlb->mm->nr_ptes); spin_unlock(ptl); - put_huge_zero_page(); + tlb_remove_page(tlb, pmd_page(orig_pmd)); } else { struct page *page = pmd_page(orig_pmd); page_remove_rmap(page, true); @@ -1960,10 +1960,9 @@ int khugepaged_enter_vma_merge(struct vm_area_struct *vma, * page fault if needed. */ return 0; - if (vma->vm_ops) + if (vma->vm_ops || (vm_flags & VM_NO_THP)) /* khugepaged not yet working on file or special mappings */ return 0; - VM_BUG_ON_VMA(vm_flags & VM_NO_THP, vma); hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK; hend = vma->vm_end & HPAGE_PMD_MASK; if (hstart < hend) @@ -2352,8 +2351,7 @@ static bool hugepage_vma_check(struct vm_area_struct *vma) return false; if (is_vma_temporary_stack(vma)) return false; - VM_BUG_ON_VMA(vma->vm_flags & VM_NO_THP, vma); - return true; + return !(vma->vm_flags & VM_NO_THP); } static void collapse_huge_page(struct mm_struct *mm, @@ -3454,7 +3452,7 @@ next: } } - pr_info("%lu of %lu THP split", split, total); + pr_info("%lu of %lu THP split\n", split, total); return 0; } @@ -3465,7 +3463,7 @@ static int __init split_huge_pages_debugfs(void) { void *ret; - ret = debugfs_create_file("split_huge_pages", 0644, NULL, NULL, + ret = debugfs_create_file("split_huge_pages", 0200, NULL, NULL, &split_huge_pages_fops); if (!ret) pr_warn("Failed to create split_huge_pages in debugfs"); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 36db05fa8acb..fe787f5c41bd 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -207,6 +207,7 @@ static void mem_cgroup_oom_notify(struct mem_cgroup *memcg); /* "mc" and its members are protected by cgroup_mutex */ static struct move_charge_struct { spinlock_t lock; /* for from, to */ + struct mm_struct *mm; struct mem_cgroup *from; struct mem_cgroup *to; unsigned long flags; @@ -4667,6 +4668,8 @@ static void __mem_cgroup_clear_mc(void) static void mem_cgroup_clear_mc(void) { + struct mm_struct *mm = mc.mm; + /* * we must clear moving_task before waking up waiters at the end of * task migration. @@ -4676,7 +4679,10 @@ static void mem_cgroup_clear_mc(void) spin_lock(&mc.lock); mc.from = NULL; mc.to = NULL; + mc.mm = NULL; spin_unlock(&mc.lock); + + mmput(mm); } static int mem_cgroup_can_attach(struct cgroup_taskset *tset) @@ -4733,6 +4739,7 @@ static int mem_cgroup_can_attach(struct cgroup_taskset *tset) VM_BUG_ON(mc.moved_swap); spin_lock(&mc.lock); + mc.mm = mm; mc.from = from; mc.to = memcg; mc.flags = move_flags; @@ -4742,8 +4749,9 @@ static int mem_cgroup_can_attach(struct cgroup_taskset *tset) ret = mem_cgroup_precharge_mc(mm); if (ret) mem_cgroup_clear_mc(); + } else { + mmput(mm); } - mmput(mm); return ret; } @@ -4852,11 +4860,11 @@ put: /* get_mctgt_type() gets the page */ return ret; } -static void mem_cgroup_move_charge(struct mm_struct *mm) +static void mem_cgroup_move_charge(void) { struct mm_walk mem_cgroup_move_charge_walk = { .pmd_entry = mem_cgroup_move_charge_pte_range, - .mm = mm, + .mm = mc.mm, }; lru_add_drain_all(); @@ -4868,7 +4876,7 @@ static void mem_cgroup_move_charge(struct mm_struct *mm) atomic_inc(&mc.from->moving_account); synchronize_rcu(); retry: - if (unlikely(!down_read_trylock(&mm->mmap_sem))) { + if (unlikely(!down_read_trylock(&mc.mm->mmap_sem))) { /* * Someone who are holding the mmap_sem might be waiting in * waitq. So we cancel all extra charges, wake up all waiters, @@ -4885,23 +4893,16 @@ retry: * additional charge, the page walk just aborts. */ walk_page_range(0, ~0UL, &mem_cgroup_move_charge_walk); - up_read(&mm->mmap_sem); + up_read(&mc.mm->mmap_sem); atomic_dec(&mc.from->moving_account); } -static void mem_cgroup_move_task(struct cgroup_taskset *tset) +static void mem_cgroup_move_task(void) { - struct cgroup_subsys_state *css; - struct task_struct *p = cgroup_taskset_first(tset, &css); - struct mm_struct *mm = get_task_mm(p); - - if (mm) { - if (mc.to) - mem_cgroup_move_charge(mm); - mmput(mm); - } - if (mc.to) + if (mc.to) { + mem_cgroup_move_charge(); mem_cgroup_clear_mc(); + } } #else /* !CONFIG_MMU */ static int mem_cgroup_can_attach(struct cgroup_taskset *tset) @@ -4911,7 +4912,7 @@ static int mem_cgroup_can_attach(struct cgroup_taskset *tset) static void mem_cgroup_cancel_attach(struct cgroup_taskset *tset) { } -static void mem_cgroup_move_task(struct cgroup_taskset *tset) +static void mem_cgroup_move_task(void) { } #endif @@ -5195,7 +5196,7 @@ struct cgroup_subsys memory_cgrp_subsys = { .css_reset = mem_cgroup_css_reset, .can_attach = mem_cgroup_can_attach, .cancel_attach = mem_cgroup_cancel_attach, - .attach = mem_cgroup_move_task, + .post_attach = mem_cgroup_move_task, .bind = mem_cgroup_bind, .dfl_cftypes = memory_files, .legacy_cftypes = mem_cgroup_legacy_files, diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 78f5f2641b91..ca5acee53b7a 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -888,7 +888,15 @@ int get_hwpoison_page(struct page *page) } } - return get_page_unless_zero(head); + if (get_page_unless_zero(head)) { + if (head == compound_head(page)) + return 1; + + pr_info("MCE: %#lx cannot catch tail\n", page_to_pfn(page)); + put_page(head); + } + + return 0; } EXPORT_SYMBOL_GPL(get_hwpoison_page); diff --git a/mm/memory.c b/mm/memory.c index 93897f23cc11..52c218e2b724 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -789,6 +789,46 @@ out: return pfn_to_page(pfn); } +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr, + pmd_t pmd) +{ + unsigned long pfn = pmd_pfn(pmd); + + /* + * There is no pmd_special() but there may be special pmds, e.g. + * in a direct-access (dax) mapping, so let's just replicate the + * !HAVE_PTE_SPECIAL case from vm_normal_page() here. + */ + if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) { + if (vma->vm_flags & VM_MIXEDMAP) { + if (!pfn_valid(pfn)) + return NULL; + goto out; + } else { + unsigned long off; + off = (addr - vma->vm_start) >> PAGE_SHIFT; + if (pfn == vma->vm_pgoff + off) + return NULL; + if (!is_cow_mapping(vma->vm_flags)) + return NULL; + } + } + + if (is_zero_pfn(pfn)) + return NULL; + if (unlikely(pfn > highest_memmap_pfn)) + return NULL; + + /* + * NOTE! We still have PageReserved() pages in the page tables. + * eg. VDSO mappings can cause them to exist. + */ +out: + return pfn_to_page(pfn); +} +#endif + /* * copy one vm_area from one task to the other. Assumes the page tables * already present in the new task to be cleared in the whole range @@ -1182,15 +1222,8 @@ static inline unsigned long zap_pmd_range(struct mmu_gather *tlb, next = pmd_addr_end(addr, end); if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) { if (next - addr != HPAGE_PMD_SIZE) { -#ifdef CONFIG_DEBUG_VM - if (!rwsem_is_locked(&tlb->mm->mmap_sem)) { - pr_err("%s: mmap_sem is unlocked! addr=0x%lx end=0x%lx vma->vm_start=0x%lx vma->vm_end=0x%lx\n", - __func__, addr, end, - vma->vm_start, - vma->vm_end); - BUG(); - } -#endif + VM_BUG_ON_VMA(vma_is_anonymous(vma) && + !rwsem_is_locked(&tlb->mm->mmap_sem), vma); split_huge_pmd(vma, pmd, addr); } else if (zap_huge_pmd(tlb, vma, pmd, addr)) goto next; diff --git a/mm/migrate.c b/mm/migrate.c index 6c822a7b27e0..f9dfb18a4eba 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -975,7 +975,13 @@ out: dec_zone_page_state(page, NR_ISOLATED_ANON + page_is_file_cache(page)); /* Soft-offlined page shouldn't go through lru cache list */ - if (reason == MR_MEMORY_FAILURE) { + if (reason == MR_MEMORY_FAILURE && rc == MIGRATEPAGE_SUCCESS) { + /* + * With this release, we free successfully migrated + * page and set PG_HWPoison on just freed page + * intentionally. Although it's rather weird, it's how + * HWPoison flag works at the moment. + */ put_page(page); if (!test_set_page_hwpoison(page)) num_poisoned_pages_inc(); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 999792d35ccc..bc5149d5ec38 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -1910,7 +1910,8 @@ bool wb_over_bg_thresh(struct bdi_writeback *wb) if (gdtc->dirty > gdtc->bg_thresh) return true; - if (wb_stat(wb, WB_RECLAIMABLE) > __wb_calc_thresh(gdtc)) + if (wb_stat(wb, WB_RECLAIMABLE) > + wb_calc_thresh(gdtc->wb, gdtc->bg_thresh)) return true; if (mdtc) { @@ -1924,7 +1925,8 @@ bool wb_over_bg_thresh(struct bdi_writeback *wb) if (mdtc->dirty > mdtc->bg_thresh) return true; - if (wb_stat(wb, WB_RECLAIMABLE) > __wb_calc_thresh(mdtc)) + if (wb_stat(wb, WB_RECLAIMABLE) > + wb_calc_thresh(mdtc->wb, mdtc->bg_thresh)) return true; } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 59de90d5d3a3..c1069efcc4d7 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -6485,7 +6485,7 @@ int __meminit init_per_zone_wmark_min(void) setup_per_zone_inactive_ratio(); return 0; } -module_init(init_per_zone_wmark_min) +core_initcall(init_per_zone_wmark_min) /* * min_free_kbytes_sysctl_handler - just a wrapper around proc_dointvec() so diff --git a/mm/page_io.c b/mm/page_io.c index cd92e3d67a32..985f23cfa79b 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -353,7 +353,11 @@ int swap_readpage(struct page *page) ret = bdev_read_page(sis->bdev, swap_page_sector(page), page); if (!ret) { - swap_slot_free_notify(page); + if (trylock_page(page)) { + swap_slot_free_notify(page); + unlock_page(page); + } + count_vm_event(PSWPIN); return 0; } diff --git a/mm/swap.c b/mm/swap.c index a0bc206b4ac6..03aacbcb013f 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -728,6 +728,11 @@ void release_pages(struct page **pages, int nr, bool cold) zone = NULL; } + if (is_huge_zero_page(page)) { + put_huge_zero_page(); + continue; + } + page = compound_head(page); if (!put_page_testzero(page)) continue; diff --git a/mm/vmscan.c b/mm/vmscan.c index b934223eaa45..142cb61f4822 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2553,7 +2553,7 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc) sc->gfp_mask |= __GFP_HIGHMEM; for_each_zone_zonelist_nodemask(zone, z, zonelist, - requested_highidx, sc->nodemask) { + gfp_zone(sc->gfp_mask), sc->nodemask) { enum zone_type classzone_idx; if (!populated_zone(zone)) @@ -3318,6 +3318,20 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order, /* Try to sleep for a short interval */ if (prepare_kswapd_sleep(pgdat, order, remaining, balanced_classzone_idx)) { + /* + * Compaction records what page blocks it recently failed to + * isolate pages from and skips them in the future scanning. + * When kswapd is going to sleep, it is reasonable to assume + * that pages and compaction may succeed so reset the cache. + */ + reset_isolation_suitable(pgdat); + + /* + * We have freed the memory, now we should compact it to make + * allocation of the requested order possible. + */ + wakeup_kcompactd(pgdat, order, classzone_idx); + remaining = schedule_timeout(HZ/10); finish_wait(&pgdat->kswapd_wait, &wait); prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE); @@ -3341,20 +3355,6 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order, */ set_pgdat_percpu_threshold(pgdat, calculate_normal_threshold); - /* - * Compaction records what page blocks it recently failed to - * isolate pages from and skips them in the future scanning. - * When kswapd is going to sleep, it is reasonable to assume - * that pages and compaction may succeed so reset the cache. - */ - reset_isolation_suitable(pgdat); - - /* - * We have freed the memory, now we should compact it to make - * allocation of the requested order possible. - */ - wakeup_kcompactd(pgdat, order, classzone_idx); - if (!kthread_should_stop()) schedule(); diff --git a/mm/zswap.c b/mm/zswap.c index 91dad80d068b..de0f119b1780 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -170,6 +170,8 @@ static struct zswap_tree *zswap_trees[MAX_SWAPFILES]; static LIST_HEAD(zswap_pools); /* protects zswap_pools list modification */ static DEFINE_SPINLOCK(zswap_pools_lock); +/* pool counter to provide unique names to zpool */ +static atomic_t zswap_pools_count = ATOMIC_INIT(0); /* used by param callback function */ static bool zswap_init_started; @@ -565,6 +567,7 @@ static struct zswap_pool *zswap_pool_find_get(char *type, char *compressor) static struct zswap_pool *zswap_pool_create(char *type, char *compressor) { struct zswap_pool *pool; + char name[38]; /* 'zswap' + 32 char (max) num + \0 */ gfp_t gfp = __GFP_NORETRY | __GFP_NOWARN | __GFP_KSWAPD_RECLAIM; pool = kzalloc(sizeof(*pool), GFP_KERNEL); @@ -573,7 +576,10 @@ static struct zswap_pool *zswap_pool_create(char *type, char *compressor) return NULL; } - pool->zpool = zpool_create_pool(type, "zswap", gfp, &zswap_zpool_ops); + /* unique name for each pool specifically required by zsmalloc */ + snprintf(name, 38, "zswap%x", atomic_inc_return(&zswap_pools_count)); + + pool->zpool = zpool_create_pool(type, name, gfp, &zswap_zpool_ops); if (!pool->zpool) { pr_err("%s zpool not available\n", type); goto error; diff --git a/net/batman-adv/bat_v.c b/net/batman-adv/bat_v.c index 3315b9a598af..4026f198a734 100644 --- a/net/batman-adv/bat_v.c +++ b/net/batman-adv/bat_v.c @@ -32,10 +32,21 @@ #include "bat_v_elp.h" #include "bat_v_ogm.h" +#include "hard-interface.h" #include "hash.h" #include "originator.h" #include "packet.h" +static void batadv_v_iface_activate(struct batadv_hard_iface *hard_iface) +{ + /* B.A.T.M.A.N. V does not use any queuing mechanism, therefore it can + * set the interface as ACTIVE right away, without any risk of race + * condition + */ + if (hard_iface->if_status == BATADV_IF_TO_BE_ACTIVATED) + hard_iface->if_status = BATADV_IF_ACTIVE; +} + static int batadv_v_iface_enable(struct batadv_hard_iface *hard_iface) { int ret; @@ -274,6 +285,7 @@ static bool batadv_v_neigh_is_sob(struct batadv_neigh_node *neigh1, static struct batadv_algo_ops batadv_batman_v __read_mostly = { .name = "BATMAN_V", + .bat_iface_activate = batadv_v_iface_activate, .bat_iface_enable = batadv_v_iface_enable, .bat_iface_disable = batadv_v_iface_disable, .bat_iface_update_mac = batadv_v_iface_update_mac, diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c index e96d7c745b4a..3e6b2624f980 100644 --- a/net/batman-adv/distributed-arp-table.c +++ b/net/batman-adv/distributed-arp-table.c @@ -568,6 +568,7 @@ static void batadv_choose_next_candidate(struct batadv_priv *bat_priv, * be sent to * @bat_priv: the bat priv with all the soft interface information * @ip_dst: ipv4 to look up in the DHT + * @vid: VLAN identifier * * An originator O is selected if and only if its DHT_ID value is one of three * closest values (from the LEFT, with wrap around if needed) then the hash @@ -576,7 +577,8 @@ static void batadv_choose_next_candidate(struct batadv_priv *bat_priv, * Return: the candidate array of size BATADV_DAT_CANDIDATE_NUM. */ static struct batadv_dat_candidate * -batadv_dat_select_candidates(struct batadv_priv *bat_priv, __be32 ip_dst) +batadv_dat_select_candidates(struct batadv_priv *bat_priv, __be32 ip_dst, + unsigned short vid) { int select; batadv_dat_addr_t last_max = BATADV_DAT_ADDR_MAX, ip_key; @@ -592,7 +594,7 @@ batadv_dat_select_candidates(struct batadv_priv *bat_priv, __be32 ip_dst) return NULL; dat.ip = ip_dst; - dat.vid = 0; + dat.vid = vid; ip_key = (batadv_dat_addr_t)batadv_hash_dat(&dat, BATADV_DAT_ADDR_MAX); @@ -612,6 +614,7 @@ batadv_dat_select_candidates(struct batadv_priv *bat_priv, __be32 ip_dst) * @bat_priv: the bat priv with all the soft interface information * @skb: payload to send * @ip: the DHT key + * @vid: VLAN identifier * @packet_subtype: unicast4addr packet subtype to use * * This function copies the skb with pskb_copy() and is sent as unicast packet @@ -622,7 +625,7 @@ batadv_dat_select_candidates(struct batadv_priv *bat_priv, __be32 ip_dst) */ static bool batadv_dat_send_data(struct batadv_priv *bat_priv, struct sk_buff *skb, __be32 ip, - int packet_subtype) + unsigned short vid, int packet_subtype) { int i; bool ret = false; @@ -631,7 +634,7 @@ static bool batadv_dat_send_data(struct batadv_priv *bat_priv, struct sk_buff *tmp_skb; struct batadv_dat_candidate *cand; - cand = batadv_dat_select_candidates(bat_priv, ip); + cand = batadv_dat_select_candidates(bat_priv, ip, vid); if (!cand) goto out; @@ -1022,7 +1025,7 @@ bool batadv_dat_snoop_outgoing_arp_request(struct batadv_priv *bat_priv, ret = true; } else { /* Send the request to the DHT */ - ret = batadv_dat_send_data(bat_priv, skb, ip_dst, + ret = batadv_dat_send_data(bat_priv, skb, ip_dst, vid, BATADV_P_DAT_DHT_GET); } out: @@ -1150,8 +1153,8 @@ void batadv_dat_snoop_outgoing_arp_reply(struct batadv_priv *bat_priv, /* Send the ARP reply to the candidates for both the IP addresses that * the node obtained from the ARP reply */ - batadv_dat_send_data(bat_priv, skb, ip_src, BATADV_P_DAT_DHT_PUT); - batadv_dat_send_data(bat_priv, skb, ip_dst, BATADV_P_DAT_DHT_PUT); + batadv_dat_send_data(bat_priv, skb, ip_src, vid, BATADV_P_DAT_DHT_PUT); + batadv_dat_send_data(bat_priv, skb, ip_dst, vid, BATADV_P_DAT_DHT_PUT); } /** diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index b22b2775a0a5..0a7deaf2670a 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -407,6 +407,9 @@ batadv_hardif_activate_interface(struct batadv_hard_iface *hard_iface) batadv_update_min_mtu(hard_iface->soft_iface); + if (bat_priv->bat_algo_ops->bat_iface_activate) + bat_priv->bat_algo_ops->bat_iface_activate(hard_iface); + out: if (primary_if) batadv_hardif_put(primary_if); @@ -572,8 +575,7 @@ void batadv_hardif_disable_interface(struct batadv_hard_iface *hard_iface, struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); struct batadv_hard_iface *primary_if = NULL; - if (hard_iface->if_status == BATADV_IF_ACTIVE) - batadv_hardif_deactivate_interface(hard_iface); + batadv_hardif_deactivate_interface(hard_iface); if (hard_iface->if_status != BATADV_IF_INACTIVE) goto out; diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index e4cbb0753e37..c355a824713c 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -250,7 +250,6 @@ static void batadv_neigh_node_release(struct kref *ref) { struct hlist_node *node_tmp; struct batadv_neigh_node *neigh_node; - struct batadv_hardif_neigh_node *hardif_neigh; struct batadv_neigh_ifinfo *neigh_ifinfo; struct batadv_algo_ops *bao; @@ -262,13 +261,7 @@ static void batadv_neigh_node_release(struct kref *ref) batadv_neigh_ifinfo_put(neigh_ifinfo); } - hardif_neigh = batadv_hardif_neigh_get(neigh_node->if_incoming, - neigh_node->addr); - if (hardif_neigh) { - /* batadv_hardif_neigh_get() increases refcount too */ - batadv_hardif_neigh_put(hardif_neigh); - batadv_hardif_neigh_put(hardif_neigh); - } + batadv_hardif_neigh_put(neigh_node->hardif_neigh); if (bao->bat_neigh_free) bao->bat_neigh_free(neigh_node); @@ -663,6 +656,11 @@ batadv_neigh_node_new(struct batadv_orig_node *orig_node, ether_addr_copy(neigh_node->addr, neigh_addr); neigh_node->if_incoming = hard_iface; neigh_node->orig_node = orig_node; + neigh_node->last_seen = jiffies; + + /* increment unique neighbor refcount */ + kref_get(&hardif_neigh->refcount); + neigh_node->hardif_neigh = hardif_neigh; /* extra reference for return */ kref_init(&neigh_node->refcount); @@ -672,9 +670,6 @@ batadv_neigh_node_new(struct batadv_orig_node *orig_node, hlist_add_head_rcu(&neigh_node->list, &orig_node->neigh_list); spin_unlock_bh(&orig_node->neigh_list_lock); - /* increment unique neighbor refcount */ - kref_get(&hardif_neigh->refcount); - batadv_dbg(BATADV_DBG_BATMAN, orig_node->bat_priv, "Creating new neighbor %pM for orig_node %pM on interface %s\n", neigh_addr, orig_node->orig, hard_iface->net_dev->name); diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index 4dd646a52f1a..b781bf753250 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -105,6 +105,15 @@ static void _batadv_update_route(struct batadv_priv *bat_priv, neigh_node = NULL; spin_lock_bh(&orig_node->neigh_list_lock); + /* curr_router used earlier may not be the current orig_ifinfo->router + * anymore because it was dereferenced outside of the neigh_list_lock + * protected region. After the new best neighbor has replace the current + * best neighbor the reference counter needs to decrease. Consequently, + * the code needs to ensure the curr_router variable contains a pointer + * to the replaced best neighbor. + */ + curr_router = rcu_dereference_protected(orig_ifinfo->router, true); + rcu_assign_pointer(orig_ifinfo->router, neigh_node); spin_unlock_bh(&orig_node->neigh_list_lock); batadv_orig_ifinfo_put(orig_ifinfo); diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c index 3ce06e0a91b1..76417850d3fc 100644 --- a/net/batman-adv/send.c +++ b/net/batman-adv/send.c @@ -675,6 +675,9 @@ batadv_purge_outstanding_packets(struct batadv_priv *bat_priv, if (pending) { hlist_del(&forw_packet->list); + if (!forw_packet->own) + atomic_inc(&bat_priv->bcast_queue_left); + batadv_forw_packet_free(forw_packet); } } @@ -702,6 +705,9 @@ batadv_purge_outstanding_packets(struct batadv_priv *bat_priv, if (pending) { hlist_del(&forw_packet->list); + if (!forw_packet->own) + atomic_inc(&bat_priv->batman_queue_left); + batadv_forw_packet_free(forw_packet); } } diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 0710379491bf..8a136b6a1ff0 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -408,11 +408,17 @@ void batadv_interface_rx(struct net_device *soft_iface, */ nf_reset(skb); + if (unlikely(!pskb_may_pull(skb, ETH_HLEN))) + goto dropped; + vid = batadv_get_vid(skb, 0); ethhdr = eth_hdr(skb); switch (ntohs(ethhdr->h_proto)) { case ETH_P_8021Q: + if (!pskb_may_pull(skb, VLAN_ETH_HLEN)) + goto dropped; + vhdr = (struct vlan_ethhdr *)skb->data; if (vhdr->h_vlan_encapsulated_proto != ethertype) @@ -424,8 +430,6 @@ void batadv_interface_rx(struct net_device *soft_iface, } /* skb->dev & skb->pkt_type are set here */ - if (unlikely(!pskb_may_pull(skb, ETH_HLEN))) - goto dropped; skb->protocol = eth_type_trans(skb, soft_iface); /* should not be necessary anymore as we use skb_pull_rcsum() diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 0b43e86328a5..9b4551a86535 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -215,6 +215,8 @@ static void batadv_tt_local_entry_release(struct kref *ref) tt_local_entry = container_of(ref, struct batadv_tt_local_entry, common.refcount); + batadv_softif_vlan_put(tt_local_entry->vlan); + kfree_rcu(tt_local_entry, common.rcu); } @@ -673,6 +675,7 @@ bool batadv_tt_local_add(struct net_device *soft_iface, const u8 *addr, kref_get(&tt_local->common.refcount); tt_local->last_seen = jiffies; tt_local->common.added_at = tt_local->last_seen; + tt_local->vlan = vlan; /* the batman interface mac and multicast addresses should never be * purged @@ -991,7 +994,6 @@ int batadv_tt_local_seq_print_text(struct seq_file *seq, void *offset) struct batadv_tt_common_entry *tt_common_entry; struct batadv_tt_local_entry *tt_local; struct batadv_hard_iface *primary_if; - struct batadv_softif_vlan *vlan; struct hlist_head *head; unsigned short vid; u32 i; @@ -1027,14 +1029,6 @@ int batadv_tt_local_seq_print_text(struct seq_file *seq, void *offset) last_seen_msecs = last_seen_msecs % 1000; no_purge = tt_common_entry->flags & np_flag; - - vlan = batadv_softif_vlan_get(bat_priv, vid); - if (!vlan) { - seq_printf(seq, "Cannot retrieve VLAN %d\n", - BATADV_PRINT_VID(vid)); - continue; - } - seq_printf(seq, " * %pM %4i [%c%c%c%c%c%c] %3u.%03u (%#.8x)\n", tt_common_entry->addr, @@ -1052,9 +1046,7 @@ int batadv_tt_local_seq_print_text(struct seq_file *seq, void *offset) BATADV_TT_CLIENT_ISOLA) ? 'I' : '.'), no_purge ? 0 : last_seen_secs, no_purge ? 0 : last_seen_msecs, - vlan->tt.crc); - - batadv_softif_vlan_put(vlan); + tt_local->vlan->tt.crc); } rcu_read_unlock(); } @@ -1099,7 +1091,6 @@ u16 batadv_tt_local_remove(struct batadv_priv *bat_priv, const u8 *addr, { struct batadv_tt_local_entry *tt_local_entry; u16 flags, curr_flags = BATADV_NO_FLAGS; - struct batadv_softif_vlan *vlan; void *tt_entry_exists; tt_local_entry = batadv_tt_local_hash_find(bat_priv, addr, vid); @@ -1139,14 +1130,6 @@ u16 batadv_tt_local_remove(struct batadv_priv *bat_priv, const u8 *addr, /* extra call to free the local tt entry */ batadv_tt_local_entry_put(tt_local_entry); - /* decrease the reference held for this vlan */ - vlan = batadv_softif_vlan_get(bat_priv, vid); - if (!vlan) - goto out; - - batadv_softif_vlan_put(vlan); - batadv_softif_vlan_put(vlan); - out: if (tt_local_entry) batadv_tt_local_entry_put(tt_local_entry); @@ -1219,7 +1202,6 @@ static void batadv_tt_local_table_free(struct batadv_priv *bat_priv) spinlock_t *list_lock; /* protects write access to the hash lists */ struct batadv_tt_common_entry *tt_common_entry; struct batadv_tt_local_entry *tt_local; - struct batadv_softif_vlan *vlan; struct hlist_node *node_tmp; struct hlist_head *head; u32 i; @@ -1241,14 +1223,6 @@ static void batadv_tt_local_table_free(struct batadv_priv *bat_priv) struct batadv_tt_local_entry, common); - /* decrease the reference held for this vlan */ - vlan = batadv_softif_vlan_get(bat_priv, - tt_common_entry->vid); - if (vlan) { - batadv_softif_vlan_put(vlan); - batadv_softif_vlan_put(vlan); - } - batadv_tt_local_entry_put(tt_local); } spin_unlock_bh(list_lock); @@ -3309,7 +3283,6 @@ static void batadv_tt_local_purge_pending_clients(struct batadv_priv *bat_priv) struct batadv_hashtable *hash = bat_priv->tt.local_hash; struct batadv_tt_common_entry *tt_common; struct batadv_tt_local_entry *tt_local; - struct batadv_softif_vlan *vlan; struct hlist_node *node_tmp; struct hlist_head *head; spinlock_t *list_lock; /* protects write access to the hash lists */ @@ -3339,13 +3312,6 @@ static void batadv_tt_local_purge_pending_clients(struct batadv_priv *bat_priv) struct batadv_tt_local_entry, common); - /* decrease the reference held for this vlan */ - vlan = batadv_softif_vlan_get(bat_priv, tt_common->vid); - if (vlan) { - batadv_softif_vlan_put(vlan); - batadv_softif_vlan_put(vlan); - } - batadv_tt_local_entry_put(tt_local); } spin_unlock_bh(list_lock); diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index 9abfb3e73c34..1e47fbe8bb7b 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -433,6 +433,7 @@ struct batadv_hardif_neigh_node { * @ifinfo_lock: lock protecting private ifinfo members and list * @if_incoming: pointer to incoming hard-interface * @last_seen: when last packet via this neighbor was received + * @hardif_neigh: hardif_neigh of this neighbor * @refcount: number of contexts the object is used * @rcu: struct used for freeing in an RCU-safe manner */ @@ -444,6 +445,7 @@ struct batadv_neigh_node { spinlock_t ifinfo_lock; /* protects ifinfo_list and its members */ struct batadv_hard_iface *if_incoming; unsigned long last_seen; + struct batadv_hardif_neigh_node *hardif_neigh; struct kref refcount; struct rcu_head rcu; }; @@ -1073,10 +1075,12 @@ struct batadv_tt_common_entry { * struct batadv_tt_local_entry - translation table local entry data * @common: general translation table data * @last_seen: timestamp used for purging stale tt local entries + * @vlan: soft-interface vlan of the entry */ struct batadv_tt_local_entry { struct batadv_tt_common_entry common; unsigned long last_seen; + struct batadv_softif_vlan *vlan; }; /** @@ -1250,6 +1254,8 @@ struct batadv_forw_packet { * struct batadv_algo_ops - mesh algorithm callbacks * @list: list node for the batadv_algo_list * @name: name of the algorithm + * @bat_iface_activate: start routing mechanisms when hard-interface is brought + * up * @bat_iface_enable: init routing info when hard-interface is enabled * @bat_iface_disable: de-init routing info when hard-interface is disabled * @bat_iface_update_mac: (re-)init mac addresses of the protocol information @@ -1277,6 +1283,7 @@ struct batadv_forw_packet { struct batadv_algo_ops { struct hlist_node list; char *name; + void (*bat_iface_activate)(struct batadv_hard_iface *hard_iface); int (*bat_iface_enable)(struct batadv_hard_iface *hard_iface); void (*bat_iface_disable)(struct batadv_hard_iface *hard_iface); void (*bat_iface_update_mac)(struct batadv_hard_iface *hard_iface); diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index 253bc77eda3b..7dbc80d01eb0 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -61,6 +61,19 @@ static void __mdb_entry_fill_flags(struct br_mdb_entry *e, unsigned char flags) e->flags |= MDB_FLAGS_OFFLOAD; } +static void __mdb_entry_to_br_ip(struct br_mdb_entry *entry, struct br_ip *ip) +{ + memset(ip, 0, sizeof(struct br_ip)); + ip->vid = entry->vid; + ip->proto = entry->addr.proto; + if (ip->proto == htons(ETH_P_IP)) + ip->u.ip4 = entry->addr.u.ip4; +#if IS_ENABLED(CONFIG_IPV6) + else + ip->u.ip6 = entry->addr.u.ip6; +#endif +} + static int br_mdb_fill_info(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev) { @@ -243,9 +256,45 @@ static inline size_t rtnl_mdb_nlmsg_size(void) + nla_total_size(sizeof(struct br_mdb_entry)); } -static void __br_mdb_notify(struct net_device *dev, struct br_mdb_entry *entry, - int type, struct net_bridge_port_group *pg) +struct br_mdb_complete_info { + struct net_bridge_port *port; + struct br_ip ip; +}; + +static void br_mdb_complete(struct net_device *dev, int err, void *priv) { + struct br_mdb_complete_info *data = priv; + struct net_bridge_port_group __rcu **pp; + struct net_bridge_port_group *p; + struct net_bridge_mdb_htable *mdb; + struct net_bridge_mdb_entry *mp; + struct net_bridge_port *port = data->port; + struct net_bridge *br = port->br; + + if (err) + goto err; + + spin_lock_bh(&br->multicast_lock); + mdb = mlock_dereference(br->mdb, br); + mp = br_mdb_ip_get(mdb, &data->ip); + if (!mp) + goto out; + for (pp = &mp->ports; (p = mlock_dereference(*pp, br)) != NULL; + pp = &p->next) { + if (p->port != port) + continue; + p->flags |= MDB_PG_FLAGS_OFFLOAD; + } +out: + spin_unlock_bh(&br->multicast_lock); +err: + kfree(priv); +} + +static void __br_mdb_notify(struct net_device *dev, struct net_bridge_port *p, + struct br_mdb_entry *entry, int type) +{ + struct br_mdb_complete_info *complete_info; struct switchdev_obj_port_mdb mdb = { .obj = { .id = SWITCHDEV_OBJ_ID_PORT_MDB, @@ -268,9 +317,14 @@ static void __br_mdb_notify(struct net_device *dev, struct br_mdb_entry *entry, mdb.obj.orig_dev = port_dev; if (port_dev && type == RTM_NEWMDB) { - err = switchdev_port_obj_add(port_dev, &mdb.obj); - if (!err && pg) - pg->flags |= MDB_PG_FLAGS_OFFLOAD; + complete_info = kmalloc(sizeof(*complete_info), GFP_ATOMIC); + if (complete_info) { + complete_info->port = p; + __mdb_entry_to_br_ip(entry, &complete_info->ip); + mdb.obj.complete_priv = complete_info; + mdb.obj.complete = br_mdb_complete; + switchdev_port_obj_add(port_dev, &mdb.obj); + } } else if (port_dev && type == RTM_DELMDB) { switchdev_port_obj_del(port_dev, &mdb.obj); } @@ -291,21 +345,21 @@ errout: rtnl_set_sk_err(net, RTNLGRP_MDB, err); } -void br_mdb_notify(struct net_device *dev, struct net_bridge_port_group *pg, - int type) +void br_mdb_notify(struct net_device *dev, struct net_bridge_port *port, + struct br_ip *group, int type, u8 flags) { struct br_mdb_entry entry; memset(&entry, 0, sizeof(entry)); - entry.ifindex = pg->port->dev->ifindex; - entry.addr.proto = pg->addr.proto; - entry.addr.u.ip4 = pg->addr.u.ip4; + entry.ifindex = port->dev->ifindex; + entry.addr.proto = group->proto; + entry.addr.u.ip4 = group->u.ip4; #if IS_ENABLED(CONFIG_IPV6) - entry.addr.u.ip6 = pg->addr.u.ip6; + entry.addr.u.ip6 = group->u.ip6; #endif - entry.vid = pg->addr.vid; - __mdb_entry_fill_flags(&entry, pg->flags); - __br_mdb_notify(dev, &entry, type, pg); + entry.vid = group->vid; + __mdb_entry_fill_flags(&entry, flags); + __br_mdb_notify(dev, port, &entry, type); } static int nlmsg_populate_rtr_fill(struct sk_buff *skb, @@ -450,8 +504,7 @@ static int br_mdb_parse(struct sk_buff *skb, struct nlmsghdr *nlh, } static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port, - struct br_ip *group, unsigned char state, - struct net_bridge_port_group **pg) + struct br_ip *group, unsigned char state) { struct net_bridge_mdb_entry *mp; struct net_bridge_port_group *p; @@ -482,7 +535,6 @@ static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port, if (unlikely(!p)) return -ENOMEM; rcu_assign_pointer(*pp, p); - *pg = p; if (state == MDB_TEMPORARY) mod_timer(&p->timer, now + br->multicast_membership_interval); @@ -490,8 +542,7 @@ static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port, } static int __br_mdb_add(struct net *net, struct net_bridge *br, - struct br_mdb_entry *entry, - struct net_bridge_port_group **pg) + struct br_mdb_entry *entry) { struct br_ip ip; struct net_device *dev; @@ -509,18 +560,10 @@ static int __br_mdb_add(struct net *net, struct net_bridge *br, if (!p || p->br != br || p->state == BR_STATE_DISABLED) return -EINVAL; - memset(&ip, 0, sizeof(ip)); - ip.vid = entry->vid; - ip.proto = entry->addr.proto; - if (ip.proto == htons(ETH_P_IP)) - ip.u.ip4 = entry->addr.u.ip4; -#if IS_ENABLED(CONFIG_IPV6) - else - ip.u.ip6 = entry->addr.u.ip6; -#endif + __mdb_entry_to_br_ip(entry, &ip); spin_lock_bh(&br->multicast_lock); - ret = br_mdb_add_group(br, p, &ip, entry->state, pg); + ret = br_mdb_add_group(br, p, &ip, entry->state); spin_unlock_bh(&br->multicast_lock); return ret; } @@ -528,7 +571,6 @@ static int __br_mdb_add(struct net *net, struct net_bridge *br, static int br_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh) { struct net *net = sock_net(skb->sk); - struct net_bridge_port_group *pg; struct net_bridge_vlan_group *vg; struct net_device *dev, *pdev; struct br_mdb_entry *entry; @@ -558,15 +600,15 @@ static int br_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh) if (br_vlan_enabled(br) && vg && entry->vid == 0) { list_for_each_entry(v, &vg->vlan_list, vlist) { entry->vid = v->vid; - err = __br_mdb_add(net, br, entry, &pg); + err = __br_mdb_add(net, br, entry); if (err) break; - __br_mdb_notify(dev, entry, RTM_NEWMDB, pg); + __br_mdb_notify(dev, p, entry, RTM_NEWMDB); } } else { - err = __br_mdb_add(net, br, entry, &pg); + err = __br_mdb_add(net, br, entry); if (!err) - __br_mdb_notify(dev, entry, RTM_NEWMDB, pg); + __br_mdb_notify(dev, p, entry, RTM_NEWMDB); } return err; @@ -584,15 +626,7 @@ static int __br_mdb_del(struct net_bridge *br, struct br_mdb_entry *entry) if (!netif_running(br->dev) || br->multicast_disabled) return -EINVAL; - memset(&ip, 0, sizeof(ip)); - ip.vid = entry->vid; - ip.proto = entry->addr.proto; - if (ip.proto == htons(ETH_P_IP)) - ip.u.ip4 = entry->addr.u.ip4; -#if IS_ENABLED(CONFIG_IPV6) - else - ip.u.ip6 = entry->addr.u.ip6; -#endif + __mdb_entry_to_br_ip(entry, &ip); spin_lock_bh(&br->multicast_lock); mdb = mlock_dereference(br->mdb, br); @@ -662,12 +696,12 @@ static int br_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh) entry->vid = v->vid; err = __br_mdb_del(br, entry); if (!err) - __br_mdb_notify(dev, entry, RTM_DELMDB, NULL); + __br_mdb_notify(dev, p, entry, RTM_DELMDB); } } else { err = __br_mdb_del(br, entry); if (!err) - __br_mdb_notify(dev, entry, RTM_DELMDB, NULL); + __br_mdb_notify(dev, p, entry, RTM_DELMDB); } return err; diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index a4c15df2b792..191ea66e4d92 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -283,7 +283,8 @@ static void br_multicast_del_pg(struct net_bridge *br, rcu_assign_pointer(*pp, p->next); hlist_del_init(&p->mglist); del_timer(&p->timer); - br_mdb_notify(br->dev, p, RTM_DELMDB); + br_mdb_notify(br->dev, p->port, &pg->addr, RTM_DELMDB, + p->flags); call_rcu_bh(&p->rcu, br_multicast_free_pg); if (!mp->ports && !mp->mglist && @@ -705,7 +706,7 @@ static int br_multicast_add_group(struct net_bridge *br, if (unlikely(!p)) goto err; rcu_assign_pointer(*pp, p); - br_mdb_notify(br->dev, p, RTM_NEWMDB); + br_mdb_notify(br->dev, port, group, RTM_NEWMDB, 0); found: mod_timer(&p->timer, now + br->multicast_membership_interval); @@ -1461,7 +1462,8 @@ br_multicast_leave_group(struct net_bridge *br, hlist_del_init(&p->mglist); del_timer(&p->timer); call_rcu_bh(&p->rcu, br_multicast_free_pg); - br_mdb_notify(br->dev, p, RTM_DELMDB); + br_mdb_notify(br->dev, port, group, RTM_DELMDB, + p->flags); if (!mp->ports && !mp->mglist && netif_running(br->dev)) diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 1b5d145dfcbf..d9da857182ef 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -560,8 +560,8 @@ br_multicast_new_port_group(struct net_bridge_port *port, struct br_ip *group, unsigned char flags); void br_mdb_init(void); void br_mdb_uninit(void); -void br_mdb_notify(struct net_device *dev, struct net_bridge_port_group *pg, - int type); +void br_mdb_notify(struct net_device *dev, struct net_bridge_port *port, + struct br_ip *group, int type, u8 flags); void br_rtr_notify(struct net_device *dev, struct net_bridge_port *port, int type); diff --git a/net/ceph/auth.c b/net/ceph/auth.c index 6b923bcaa2a4..2bc5965fdd1e 100644 --- a/net/ceph/auth.c +++ b/net/ceph/auth.c @@ -293,13 +293,9 @@ int ceph_auth_create_authorizer(struct ceph_auth_client *ac, } EXPORT_SYMBOL(ceph_auth_create_authorizer); -void ceph_auth_destroy_authorizer(struct ceph_auth_client *ac, - struct ceph_authorizer *a) +void ceph_auth_destroy_authorizer(struct ceph_authorizer *a) { - mutex_lock(&ac->mutex); - if (ac->ops && ac->ops->destroy_authorizer) - ac->ops->destroy_authorizer(ac, a); - mutex_unlock(&ac->mutex); + a->destroy(a); } EXPORT_SYMBOL(ceph_auth_destroy_authorizer); diff --git a/net/ceph/auth_none.c b/net/ceph/auth_none.c index 8c93fa8d81bc..5f836f02ae36 100644 --- a/net/ceph/auth_none.c +++ b/net/ceph/auth_none.c @@ -16,7 +16,6 @@ static void reset(struct ceph_auth_client *ac) struct ceph_auth_none_info *xi = ac->private; xi->starting = true; - xi->built_authorizer = false; } static void destroy(struct ceph_auth_client *ac) @@ -39,6 +38,27 @@ static int should_authenticate(struct ceph_auth_client *ac) return xi->starting; } +static int ceph_auth_none_build_authorizer(struct ceph_auth_client *ac, + struct ceph_none_authorizer *au) +{ + void *p = au->buf; + void *const end = p + sizeof(au->buf); + int ret; + + ceph_encode_8_safe(&p, end, 1, e_range); + ret = ceph_entity_name_encode(ac->name, &p, end); + if (ret < 0) + return ret; + + ceph_encode_64_safe(&p, end, ac->global_id, e_range); + au->buf_len = p - (void *)au->buf; + dout("%s built authorizer len %d\n", __func__, au->buf_len); + return 0; + +e_range: + return -ERANGE; +} + static int build_request(struct ceph_auth_client *ac, void *buf, void *end) { return 0; @@ -57,32 +77,32 @@ static int handle_reply(struct ceph_auth_client *ac, int result, return result; } +static void ceph_auth_none_destroy_authorizer(struct ceph_authorizer *a) +{ + kfree(a); +} + /* - * build an 'authorizer' with our entity_name and global_id. we can - * reuse a single static copy since it is identical for all services - * we connect to. + * build an 'authorizer' with our entity_name and global_id. it is + * identical for all services we connect to. */ static int ceph_auth_none_create_authorizer( struct ceph_auth_client *ac, int peer_type, struct ceph_auth_handshake *auth) { - struct ceph_auth_none_info *ai = ac->private; - struct ceph_none_authorizer *au = &ai->au; - void *p, *end; + struct ceph_none_authorizer *au; int ret; - if (!ai->built_authorizer) { - p = au->buf; - end = p + sizeof(au->buf); - ceph_encode_8(&p, 1); - ret = ceph_entity_name_encode(ac->name, &p, end - 8); - if (ret < 0) - goto bad; - ceph_decode_need(&p, end, sizeof(u64), bad2); - ceph_encode_64(&p, ac->global_id); - au->buf_len = p - (void *)au->buf; - ai->built_authorizer = true; - dout("built authorizer len %d\n", au->buf_len); + au = kmalloc(sizeof(*au), GFP_NOFS); + if (!au) + return -ENOMEM; + + au->base.destroy = ceph_auth_none_destroy_authorizer; + + ret = ceph_auth_none_build_authorizer(ac, au); + if (ret) { + kfree(au); + return ret; } auth->authorizer = (struct ceph_authorizer *) au; @@ -92,17 +112,6 @@ static int ceph_auth_none_create_authorizer( auth->authorizer_reply_buf_len = sizeof (au->reply_buf); return 0; - -bad2: - ret = -ERANGE; -bad: - return ret; -} - -static void ceph_auth_none_destroy_authorizer(struct ceph_auth_client *ac, - struct ceph_authorizer *a) -{ - /* nothing to do */ } static const struct ceph_auth_client_ops ceph_auth_none_ops = { @@ -114,7 +123,6 @@ static const struct ceph_auth_client_ops ceph_auth_none_ops = { .build_request = build_request, .handle_reply = handle_reply, .create_authorizer = ceph_auth_none_create_authorizer, - .destroy_authorizer = ceph_auth_none_destroy_authorizer, }; int ceph_auth_none_init(struct ceph_auth_client *ac) @@ -127,7 +135,6 @@ int ceph_auth_none_init(struct ceph_auth_client *ac) return -ENOMEM; xi->starting = true; - xi->built_authorizer = false; ac->protocol = CEPH_AUTH_NONE; ac->private = xi; diff --git a/net/ceph/auth_none.h b/net/ceph/auth_none.h index 059a3ce4b53f..62021535ae4a 100644 --- a/net/ceph/auth_none.h +++ b/net/ceph/auth_none.h @@ -12,6 +12,7 @@ */ struct ceph_none_authorizer { + struct ceph_authorizer base; char buf[128]; int buf_len; char reply_buf[0]; @@ -19,8 +20,6 @@ struct ceph_none_authorizer { struct ceph_auth_none_info { bool starting; - bool built_authorizer; - struct ceph_none_authorizer au; /* we only need one; it's static */ }; int ceph_auth_none_init(struct ceph_auth_client *ac); diff --git a/net/ceph/auth_x.c b/net/ceph/auth_x.c index 9e43a315e662..a0905f04bd13 100644 --- a/net/ceph/auth_x.c +++ b/net/ceph/auth_x.c @@ -565,6 +565,14 @@ static int ceph_x_handle_reply(struct ceph_auth_client *ac, int result, return -EAGAIN; } +static void ceph_x_destroy_authorizer(struct ceph_authorizer *a) +{ + struct ceph_x_authorizer *au = (void *)a; + + ceph_x_authorizer_cleanup(au); + kfree(au); +} + static int ceph_x_create_authorizer( struct ceph_auth_client *ac, int peer_type, struct ceph_auth_handshake *auth) @@ -581,6 +589,8 @@ static int ceph_x_create_authorizer( if (!au) return -ENOMEM; + au->base.destroy = ceph_x_destroy_authorizer; + ret = ceph_x_build_authorizer(ac, th, au); if (ret) { kfree(au); @@ -643,16 +653,6 @@ static int ceph_x_verify_authorizer_reply(struct ceph_auth_client *ac, return ret; } -static void ceph_x_destroy_authorizer(struct ceph_auth_client *ac, - struct ceph_authorizer *a) -{ - struct ceph_x_authorizer *au = (void *)a; - - ceph_x_authorizer_cleanup(au); - kfree(au); -} - - static void ceph_x_reset(struct ceph_auth_client *ac) { struct ceph_x_info *xi = ac->private; @@ -770,7 +770,6 @@ static const struct ceph_auth_client_ops ceph_x_ops = { .create_authorizer = ceph_x_create_authorizer, .update_authorizer = ceph_x_update_authorizer, .verify_authorizer_reply = ceph_x_verify_authorizer_reply, - .destroy_authorizer = ceph_x_destroy_authorizer, .invalidate_authorizer = ceph_x_invalidate_authorizer, .reset = ceph_x_reset, .destroy = ceph_x_destroy, diff --git a/net/ceph/auth_x.h b/net/ceph/auth_x.h index 40b1a3cf7397..21a5af904bae 100644 --- a/net/ceph/auth_x.h +++ b/net/ceph/auth_x.h @@ -26,6 +26,7 @@ struct ceph_x_ticket_handler { struct ceph_x_authorizer { + struct ceph_authorizer base; struct ceph_crypto_key session_key; struct ceph_buffer *buf; unsigned int service; diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 32355d9d0103..40a53a70efdf 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -1087,10 +1087,8 @@ static void put_osd(struct ceph_osd *osd) dout("put_osd %p %d -> %d\n", osd, atomic_read(&osd->o_ref), atomic_read(&osd->o_ref) - 1); if (atomic_dec_and_test(&osd->o_ref)) { - struct ceph_auth_client *ac = osd->o_osdc->client->monc.auth; - if (osd->o_auth.authorizer) - ceph_auth_destroy_authorizer(ac, osd->o_auth.authorizer); + ceph_auth_destroy_authorizer(osd->o_auth.authorizer); kfree(osd); } } @@ -2984,7 +2982,7 @@ static struct ceph_auth_handshake *get_authorizer(struct ceph_connection *con, struct ceph_auth_handshake *auth = &o->o_auth; if (force_new && auth->authorizer) { - ceph_auth_destroy_authorizer(ac, auth->authorizer); + ceph_auth_destroy_authorizer(auth->authorizer); auth->authorizer = NULL; } if (!auth->authorizer) { diff --git a/net/core/dev.c b/net/core/dev.c index 77a71cd68535..5c925ac50b95 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2802,7 +2802,7 @@ static netdev_features_t harmonize_features(struct sk_buff *skb, if (skb->ip_summed != CHECKSUM_NONE && !can_checksum_protocol(features, type)) { - features &= ~NETIF_F_CSUM_MASK; + features &= ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); } else if (illegal_highdma(skb->dev, skb)) { features &= ~NETIF_F_SG; } diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 8a9246deccfe..63566ec54794 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -904,7 +904,11 @@ void fib_del_ifaddr(struct in_ifaddr *ifa, struct in_ifaddr *iprim) if (ifa->ifa_flags & IFA_F_SECONDARY) { prim = inet_ifa_byprefix(in_dev, any, ifa->ifa_mask); if (!prim) { - pr_warn("%s: bug: prim == NULL\n", __func__); + /* if the device has been deleted, we don't perform + * address promotion + */ + if (!in_dev->dead) + pr_warn("%s: bug: prim == NULL\n", __func__); return; } if (iprim && iprim != prim) { diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index bc68eced0105..0d9e9d7bb029 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -470,6 +470,7 @@ static int inet_reuseport_add_sock(struct sock *sk, const struct sock *sk2, bool match_wildcard)) { + struct inet_bind_bucket *tb = inet_csk(sk)->icsk_bind_hash; struct sock *sk2; struct hlist_nulls_node *node; kuid_t uid = sock_i_uid(sk); @@ -479,6 +480,7 @@ static int inet_reuseport_add_sock(struct sock *sk, sk2->sk_family == sk->sk_family && ipv6_only_sock(sk2) == ipv6_only_sock(sk) && sk2->sk_bound_dev_if == sk->sk_bound_dev_if && + inet_csk(sk2)->icsk_bind_hash == tb && sk2->sk_reuseport && uid_eq(uid, sock_i_uid(sk2)) && saddr_same(sk, sk2, false)) return reuseport_add_sock(sk, sk2); diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index af5d1f38217f..205a2b8a5a84 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -179,6 +179,7 @@ static __be16 tnl_flags_to_gre_flags(__be16 tflags) return flags; } +/* Fills in tpi and returns header length to be pulled. */ static int parse_gre_header(struct sk_buff *skb, struct tnl_ptk_info *tpi, bool *csum_err) { @@ -238,7 +239,7 @@ static int parse_gre_header(struct sk_buff *skb, struct tnl_ptk_info *tpi, return -EINVAL; } } - return iptunnel_pull_header(skb, hdr_len, tpi->proto, false); + return hdr_len; } static void ipgre_err(struct sk_buff *skb, u32 info, @@ -341,7 +342,7 @@ static void gre_err(struct sk_buff *skb, u32 info) struct tnl_ptk_info tpi; bool csum_err = false; - if (parse_gre_header(skb, &tpi, &csum_err)) { + if (parse_gre_header(skb, &tpi, &csum_err) < 0) { if (!csum_err) /* ignore csum errors. */ return; } @@ -419,6 +420,7 @@ static int gre_rcv(struct sk_buff *skb) { struct tnl_ptk_info tpi; bool csum_err = false; + int hdr_len; #ifdef CONFIG_NET_IPGRE_BROADCAST if (ipv4_is_multicast(ip_hdr(skb)->daddr)) { @@ -428,7 +430,10 @@ static int gre_rcv(struct sk_buff *skb) } #endif - if (parse_gre_header(skb, &tpi, &csum_err) < 0) + hdr_len = parse_gre_header(skb, &tpi, &csum_err); + if (hdr_len < 0) + goto drop; + if (iptunnel_pull_header(skb, hdr_len, tpi.proto, false) < 0) goto drop; if (ipgre_rcv(skb, &tpi) == PACKET_RCVD) @@ -523,7 +528,8 @@ static struct rtable *gre_get_rt(struct sk_buff *skb, return ip_route_output_key(net, fl); } -static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev) +static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev, + __be16 proto) { struct ip_tunnel_info *tun_info; const struct ip_tunnel_key *key; @@ -575,7 +581,7 @@ static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev) } flags = tun_info->key.tun_flags & (TUNNEL_CSUM | TUNNEL_KEY); - build_header(skb, tunnel_hlen, flags, htons(ETH_P_TEB), + build_header(skb, tunnel_hlen, flags, proto, tunnel_id_to_key(tun_info->key.tun_id), 0); df = key->tun_flags & TUNNEL_DONT_FRAGMENT ? htons(IP_DF) : 0; @@ -616,7 +622,7 @@ static netdev_tx_t ipgre_xmit(struct sk_buff *skb, const struct iphdr *tnl_params; if (tunnel->collect_md) { - gre_fb_xmit(skb, dev); + gre_fb_xmit(skb, dev, skb->protocol); return NETDEV_TX_OK; } @@ -660,7 +666,7 @@ static netdev_tx_t gre_tap_xmit(struct sk_buff *skb, struct ip_tunnel *tunnel = netdev_priv(dev); if (tunnel->collect_md) { - gre_fb_xmit(skb, dev); + gre_fb_xmit(skb, dev, htons(ETH_P_TEB)); return NETDEV_TX_OK; } @@ -893,7 +899,7 @@ static int ipgre_tunnel_init(struct net_device *dev) netif_keep_dst(dev); dev->addr_len = 4; - if (iph->daddr) { + if (iph->daddr && !tunnel->collect_md) { #ifdef CONFIG_NET_IPGRE_BROADCAST if (ipv4_is_multicast(iph->daddr)) { if (!iph->saddr) @@ -902,8 +908,9 @@ static int ipgre_tunnel_init(struct net_device *dev) dev->header_ops = &ipgre_header_ops; } #endif - } else + } else if (!tunnel->collect_md) { dev->header_ops = &ipgre_header_ops; + } return ip_tunnel_init(dev); } @@ -946,6 +953,11 @@ static int ipgre_tunnel_validate(struct nlattr *tb[], struct nlattr *data[]) if (flags & (GRE_VERSION|GRE_ROUTING)) return -EINVAL; + if (data[IFLA_GRE_COLLECT_METADATA] && + data[IFLA_GRE_ENCAP_TYPE] && + nla_get_u16(data[IFLA_GRE_ENCAP_TYPE]) != TUNNEL_ENCAP_NONE) + return -EINVAL; + return 0; } diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 6aad0192443d..a69ed94bda1b 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -326,12 +326,12 @@ static int ip_tunnel_bind_dev(struct net_device *dev) if (!IS_ERR(rt)) { tdev = rt->dst.dev; - dst_cache_set_ip4(&tunnel->dst_cache, &rt->dst, - fl4.saddr); ip_rt_put(rt); } if (dev->type != ARPHRD_ETHER) dev->flags |= IFF_POINTOPOINT; + + dst_cache_reset(&tunnel->dst_cache); } if (!tdev && tunnel->parms.link) diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 23cec53b568a..8ec4b3089e20 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -3176,35 +3176,9 @@ static void addrconf_gre_config(struct net_device *dev) } #endif -#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) -/* If the host route is cached on the addr struct make sure it is associated - * with the proper table. e.g., enslavement can change and if so the cached - * host route needs to move to the new table. - */ -static void l3mdev_check_host_rt(struct inet6_dev *idev, - struct inet6_ifaddr *ifp) -{ - if (ifp->rt) { - u32 tb_id = l3mdev_fib_table(idev->dev) ? : RT6_TABLE_LOCAL; - - if (tb_id != ifp->rt->rt6i_table->tb6_id) { - ip6_del_rt(ifp->rt); - ifp->rt = NULL; - } - } -} -#else -static void l3mdev_check_host_rt(struct inet6_dev *idev, - struct inet6_ifaddr *ifp) -{ -} -#endif - static int fixup_permanent_addr(struct inet6_dev *idev, struct inet6_ifaddr *ifp) { - l3mdev_check_host_rt(idev, ifp); - if (!ifp->rt) { struct rt6_info *rt; @@ -3304,6 +3278,9 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, break; if (event == NETDEV_UP) { + /* restore routes for permanent addresses */ + addrconf_permanent_addr(dev); + if (!addrconf_qdisc_ok(dev)) { /* device is not ready yet. */ pr_info("ADDRCONF(NETDEV_UP): %s: link is not ready\n", @@ -3337,9 +3314,6 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, run_pending = 1; } - /* restore routes for permanent addresses */ - addrconf_permanent_addr(dev); - switch (dev->type) { #if IS_ENABLED(CONFIG_IPV6_SIT) case ARPHRD_SIT: @@ -3556,6 +3530,8 @@ restart: INIT_LIST_HEAD(&del_list); list_for_each_entry_safe(ifa, tmp, &idev->addr_list, if_list) { + struct rt6_info *rt = NULL; + addrconf_del_dad_work(ifa); write_unlock_bh(&idev->lock); @@ -3568,6 +3544,9 @@ restart: ifa->state = 0; if (!(ifa->flags & IFA_F_NODAD)) ifa->flags |= IFA_F_TENTATIVE; + + rt = ifa->rt; + ifa->rt = NULL; } else { state = ifa->state; ifa->state = INET6_IFADDR_STATE_DEAD; @@ -3578,6 +3557,9 @@ restart: spin_unlock_bh(&ifa->lock); + if (rt) + ip6_del_rt(rt); + if (state != INET6_IFADDR_STATE_DEAD) { __ipv6_ifa_notify(RTM_DELADDR, ifa); inet6addr_notifier_call_chain(NETDEV_DOWN, ifa); @@ -5343,10 +5325,10 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) if (rt) ip6_del_rt(rt); } - dst_hold(&ifp->rt->dst); - - ip6_del_rt(ifp->rt); - + if (ifp->rt) { + dst_hold(&ifp->rt->dst); + ip6_del_rt(ifp->rt); + } rt_genid_bump_ipv6(net); break; } diff --git a/net/ipv6/ila/ila_lwt.c b/net/ipv6/ila/ila_lwt.c index 2ae3c4fd8aab..41f18de5dcc2 100644 --- a/net/ipv6/ila/ila_lwt.c +++ b/net/ipv6/ila/ila_lwt.c @@ -120,8 +120,7 @@ nla_put_failure: static int ila_encap_nlsize(struct lwtunnel_state *lwtstate) { - /* No encapsulation overhead */ - return 0; + return nla_total_size(sizeof(u64)); /* ILA_ATTR_LOCATOR */ } static int ila_encap_cmp(struct lwtunnel_state *a, struct lwtunnel_state *b) diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index afca2eb4dfa7..6edfa9980314 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -1376,9 +1376,9 @@ static int l2tp_tunnel_sock_create(struct net *net, memcpy(&udp_conf.peer_ip6, cfg->peer_ip6, sizeof(udp_conf.peer_ip6)); udp_conf.use_udp6_tx_checksums = - cfg->udp6_zero_tx_checksums; + ! cfg->udp6_zero_tx_checksums; udp_conf.use_udp6_rx_checksums = - cfg->udp6_zero_rx_checksums; + ! cfg->udp6_zero_rx_checksums; } else #endif { diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 453b4e741780..e1cb22c16530 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -1761,7 +1761,7 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name, ret = dev_alloc_name(ndev, ndev->name); if (ret < 0) { - free_netdev(ndev); + ieee80211_if_free(ndev); return ret; } @@ -1847,7 +1847,7 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name, ret = register_netdevice(ndev); if (ret) { - free_netdev(ndev); + ieee80211_if_free(ndev); return ret; } } diff --git a/net/rds/tcp.c b/net/rds/tcp.c index 61ed2a8764ba..86187dad1440 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -127,7 +127,7 @@ void rds_tcp_restore_callbacks(struct socket *sock, /* * This is the only path that sets tc->t_sock. Send and receive trust that - * it is set. The RDS_CONN_CONNECTED bit protects those paths from being + * it is set. The RDS_CONN_UP bit protects those paths from being * called while it isn't set. */ void rds_tcp_set_callbacks(struct socket *sock, struct rds_connection *conn) @@ -216,6 +216,7 @@ static int rds_tcp_conn_alloc(struct rds_connection *conn, gfp_t gfp) if (!tc) return -ENOMEM; + mutex_init(&tc->t_conn_lock); tc->t_sock = NULL; tc->t_tinc = NULL; tc->t_tinc_hdr_rem = sizeof(struct rds_header); diff --git a/net/rds/tcp.h b/net/rds/tcp.h index 64f873c0c6b6..41c228300525 100644 --- a/net/rds/tcp.h +++ b/net/rds/tcp.h @@ -12,6 +12,10 @@ struct rds_tcp_connection { struct list_head t_tcp_node; struct rds_connection *conn; + /* t_conn_lock synchronizes the connection establishment between + * rds_tcp_accept_one and rds_tcp_conn_connect + */ + struct mutex t_conn_lock; struct socket *t_sock; void *t_orig_write_space; void *t_orig_data_ready; diff --git a/net/rds/tcp_connect.c b/net/rds/tcp_connect.c index 5cb16875c460..49a3fcfed360 100644 --- a/net/rds/tcp_connect.c +++ b/net/rds/tcp_connect.c @@ -78,7 +78,14 @@ int rds_tcp_conn_connect(struct rds_connection *conn) struct socket *sock = NULL; struct sockaddr_in src, dest; int ret; + struct rds_tcp_connection *tc = conn->c_transport_data; + + mutex_lock(&tc->t_conn_lock); + if (rds_conn_up(conn)) { + mutex_unlock(&tc->t_conn_lock); + return 0; + } ret = sock_create_kern(rds_conn_net(conn), PF_INET, SOCK_STREAM, IPPROTO_TCP, &sock); if (ret < 0) @@ -120,6 +127,7 @@ int rds_tcp_conn_connect(struct rds_connection *conn) } out: + mutex_unlock(&tc->t_conn_lock); if (sock) sock_release(sock); return ret; diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c index 0936a4a32b47..be263cdf268b 100644 --- a/net/rds/tcp_listen.c +++ b/net/rds/tcp_listen.c @@ -76,7 +76,9 @@ int rds_tcp_accept_one(struct socket *sock) struct rds_connection *conn; int ret; struct inet_sock *inet; - struct rds_tcp_connection *rs_tcp; + struct rds_tcp_connection *rs_tcp = NULL; + int conn_state; + struct sock *nsk; ret = sock_create_kern(sock_net(sock->sk), sock->sk->sk_family, sock->sk->sk_type, sock->sk->sk_protocol, @@ -115,28 +117,44 @@ int rds_tcp_accept_one(struct socket *sock) * rds_tcp_state_change() will do that cleanup */ rs_tcp = (struct rds_tcp_connection *)conn->c_transport_data; - if (rs_tcp->t_sock && - ntohl(inet->inet_saddr) < ntohl(inet->inet_daddr)) { - struct sock *nsk = new_sock->sk; - - nsk->sk_user_data = NULL; - nsk->sk_prot->disconnect(nsk, 0); - tcp_done(nsk); - new_sock = NULL; - ret = 0; - goto out; - } else if (rs_tcp->t_sock) { - rds_tcp_restore_callbacks(rs_tcp->t_sock, rs_tcp); - conn->c_outgoing = 0; - } - rds_conn_transition(conn, RDS_CONN_DOWN, RDS_CONN_CONNECTING); + mutex_lock(&rs_tcp->t_conn_lock); + conn_state = rds_conn_state(conn); + if (conn_state != RDS_CONN_CONNECTING && conn_state != RDS_CONN_UP) + goto rst_nsk; + if (rs_tcp->t_sock) { + /* Need to resolve a duelling SYN between peers. + * We have an outstanding SYN to this peer, which may + * potentially have transitioned to the RDS_CONN_UP state, + * so we must quiesce any send threads before resetting + * c_transport_data. + */ + wait_event(conn->c_waitq, + !test_bit(RDS_IN_XMIT, &conn->c_flags)); + if (ntohl(inet->inet_saddr) < ntohl(inet->inet_daddr)) { + goto rst_nsk; + } else if (rs_tcp->t_sock) { + rds_tcp_restore_callbacks(rs_tcp->t_sock, rs_tcp); + conn->c_outgoing = 0; + } + } rds_tcp_set_callbacks(new_sock, conn); - rds_connect_complete(conn); + rds_connect_complete(conn); /* marks RDS_CONN_UP */ + new_sock = NULL; + ret = 0; + goto out; +rst_nsk: + /* reset the newly returned accept sock and bail */ + nsk = new_sock->sk; + rds_tcp_stats_inc(s_tcp_listen_closed_stale); + nsk->sk_user_data = NULL; + nsk->sk_prot->disconnect(nsk, 0); + tcp_done(nsk); new_sock = NULL; ret = 0; - out: + if (rs_tcp) + mutex_unlock(&rs_tcp->t_conn_lock); if (new_sock) sock_release(new_sock); return ret; diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 9640bb39a5d2..4befe97a9034 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -395,6 +395,25 @@ static void tfifo_enqueue(struct sk_buff *nskb, struct Qdisc *sch) sch->q.qlen++; } +/* netem can't properly corrupt a megapacket (like we get from GSO), so instead + * when we statistically choose to corrupt one, we instead segment it, returning + * the first packet to be corrupted, and re-enqueue the remaining frames + */ +static struct sk_buff *netem_segment(struct sk_buff *skb, struct Qdisc *sch) +{ + struct sk_buff *segs; + netdev_features_t features = netif_skb_features(skb); + + segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK); + + if (IS_ERR_OR_NULL(segs)) { + qdisc_reshape_fail(skb, sch); + return NULL; + } + consume_skb(skb); + return segs; +} + /* * Insert one skb into qdisc. * Note: parent depends on return value to account for queue length. @@ -407,7 +426,11 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch) /* We don't fill cb now as skb_unshare() may invalidate it */ struct netem_skb_cb *cb; struct sk_buff *skb2; + struct sk_buff *segs = NULL; + unsigned int len = 0, last_len, prev_len = qdisc_pkt_len(skb); + int nb = 0; int count = 1; + int rc = NET_XMIT_SUCCESS; /* Random duplication */ if (q->duplicate && q->duplicate >= get_crandom(&q->dup_cor)) @@ -453,10 +476,23 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch) * do it now in software before we mangle it. */ if (q->corrupt && q->corrupt >= get_crandom(&q->corrupt_cor)) { + if (skb_is_gso(skb)) { + segs = netem_segment(skb, sch); + if (!segs) + return NET_XMIT_DROP; + } else { + segs = skb; + } + + skb = segs; + segs = segs->next; + if (!(skb = skb_unshare(skb, GFP_ATOMIC)) || (skb->ip_summed == CHECKSUM_PARTIAL && - skb_checksum_help(skb))) - return qdisc_drop(skb, sch); + skb_checksum_help(skb))) { + rc = qdisc_drop(skb, sch); + goto finish_segs; + } skb->data[prandom_u32() % skb_headlen(skb)] ^= 1<<(prandom_u32() % 8); @@ -516,6 +552,27 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch) sch->qstats.requeues++; } +finish_segs: + if (segs) { + while (segs) { + skb2 = segs->next; + segs->next = NULL; + qdisc_skb_cb(segs)->pkt_len = segs->len; + last_len = segs->len; + rc = qdisc_enqueue(segs, sch); + if (rc != NET_XMIT_SUCCESS) { + if (net_xmit_drop_count(rc)) + qdisc_qstats_drop(sch); + } else { + nb++; + len += last_len; + } + segs = skb2; + } + sch->q.qlen += nb; + if (nb > 1) + qdisc_tree_reduce_backlog(sch, 1 - nb, prev_len - len); + } return NET_XMIT_SUCCESS; } diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 2b9b98f1c2ff..b7e01d88bdc5 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -305,6 +305,8 @@ static void switchdev_port_attr_set_deferred(struct net_device *dev, if (err && err != -EOPNOTSUPP) netdev_err(dev, "failed (err=%d) to set attribute (id=%d)\n", err, attr->id); + if (attr->complete) + attr->complete(dev, err, attr->complete_priv); } static int switchdev_port_attr_set_defer(struct net_device *dev, @@ -434,6 +436,8 @@ static void switchdev_port_obj_add_deferred(struct net_device *dev, if (err && err != -EOPNOTSUPP) netdev_err(dev, "failed (err=%d) to add object (id=%d)\n", err, obj->id); + if (obj->complete) + obj->complete(dev, err, obj->complete_priv); } static int switchdev_port_obj_add_defer(struct net_device *dev, @@ -502,6 +506,8 @@ static void switchdev_port_obj_del_deferred(struct net_device *dev, if (err && err != -EOPNOTSUPP) netdev_err(dev, "failed (err=%d) to del object (id=%d)\n", err, obj->id); + if (obj->complete) + obj->complete(dev, err, obj->complete_priv); } static int switchdev_port_obj_del_defer(struct net_device *dev, diff --git a/net/tipc/node.c b/net/tipc/node.c index ace178fd3850..9aaa1bc566ae 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -1444,6 +1444,7 @@ void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b) int bearer_id = b->identity; struct tipc_link_entry *le; u16 bc_ack = msg_bcast_ack(hdr); + u32 self = tipc_own_addr(net); int rc = 0; __skb_queue_head_init(&xmitq); @@ -1460,6 +1461,10 @@ void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b) return tipc_node_bc_rcv(net, skb, bearer_id); } + /* Discard unicast link messages destined for another node */ + if (unlikely(!msg_short(hdr) && (msg_destnode(hdr) != self))) + goto discard; + /* Locate neighboring node that sent packet */ n = tipc_node_find(net, msg_prevnode(hdr)); if (unlikely(!n)) diff --git a/samples/bpf/trace_output_kern.c b/samples/bpf/trace_output_kern.c index 8d8d1ec429eb..9b96f4fb8cea 100644 --- a/samples/bpf/trace_output_kern.c +++ b/samples/bpf/trace_output_kern.c @@ -18,7 +18,6 @@ int bpf_prog1(struct pt_regs *ctx) u64 cookie; } data; - memset(&data, 0, sizeof(data)); data.pid = bpf_get_current_pid_tgid(); data.cookie = 0x12345678; diff --git a/scripts/mod/file2alias.c b/scripts/mod/file2alias.c index 161dd0d67da8..a9155077feef 100644 --- a/scripts/mod/file2alias.c +++ b/scripts/mod/file2alias.c @@ -371,6 +371,49 @@ static void do_usb_table(void *symval, unsigned long size, do_usb_entry_multi(symval + i, mod); } +static void do_of_entry_multi(void *symval, struct module *mod) +{ + char alias[500]; + int len; + char *tmp; + + DEF_FIELD_ADDR(symval, of_device_id, name); + DEF_FIELD_ADDR(symval, of_device_id, type); + DEF_FIELD_ADDR(symval, of_device_id, compatible); + + len = sprintf(alias, "of:N%sT%s", (*name)[0] ? *name : "*", + (*type)[0] ? *type : "*"); + + if (compatible[0]) + sprintf(&alias[len], "%sC%s", (*type)[0] ? "*" : "", + *compatible); + + /* Replace all whitespace with underscores */ + for (tmp = alias; tmp && *tmp; tmp++) + if (isspace(*tmp)) + *tmp = '_'; + + buf_printf(&mod->dev_table_buf, "MODULE_ALIAS(\"%s\");\n", alias); + strcat(alias, "C"); + add_wildcard(alias); + buf_printf(&mod->dev_table_buf, "MODULE_ALIAS(\"%s\");\n", alias); +} + +static void do_of_table(void *symval, unsigned long size, + struct module *mod) +{ + unsigned int i; + const unsigned long id_size = SIZE_of_device_id; + + device_id_check(mod->name, "of", size, id_size, symval); + + /* Leave last one: it's the terminator. */ + size -= id_size; + + for (i = 0; i < size; i += id_size) + do_of_entry_multi(symval + i, mod); +} + /* Looks like: hid:bNvNpN */ static int do_hid_entry(const char *filename, void *symval, char *alias) @@ -684,30 +727,6 @@ static int do_pcmcia_entry(const char *filename, } ADD_TO_DEVTABLE("pcmcia", pcmcia_device_id, do_pcmcia_entry); -static int do_of_entry (const char *filename, void *symval, char *alias) -{ - int len; - char *tmp; - DEF_FIELD_ADDR(symval, of_device_id, name); - DEF_FIELD_ADDR(symval, of_device_id, type); - DEF_FIELD_ADDR(symval, of_device_id, compatible); - - len = sprintf(alias, "of:N%sT%s", (*name)[0] ? *name : "*", - (*type)[0] ? *type : "*"); - - if (compatible[0]) - sprintf(&alias[len], "%sC%s", (*type)[0] ? "*" : "", - *compatible); - - /* Replace all whitespace with underscores */ - for (tmp = alias; tmp && *tmp; tmp++) - if (isspace (*tmp)) - *tmp = '_'; - - return 1; -} -ADD_TO_DEVTABLE("of", of_device_id, do_of_entry); - static int do_vio_entry(const char *filename, void *symval, char *alias) { @@ -1348,6 +1367,8 @@ void handle_moddevtable(struct module *mod, struct elf_info *info, /* First handle the "special" cases */ if (sym_is(name, namelen, "usb")) do_usb_table(symval, sym->st_size, mod); + if (sym_is(name, namelen, "of")) + do_of_table(symval, sym->st_size, mod); else if (sym_is(name, namelen, "pnp")) do_pnp_device_entry(symval, sym->st_size, mod); else if (sym_is(name, namelen, "pnp_card")) diff --git a/security/integrity/ima/ima_policy.c b/security/integrity/ima/ima_policy.c index be09e2cacf82..3cd0a58672dd 100644 --- a/security/integrity/ima/ima_policy.c +++ b/security/integrity/ima/ima_policy.c @@ -884,10 +884,10 @@ static char *func_tokens[] = { "BPRM_CHECK", "MODULE_CHECK", "FIRMWARE_CHECK", + "POST_SETATTR", "KEXEC_KERNEL_CHECK", "KEXEC_INITRAMFS_CHECK", - "POLICY_CHECK", - "POST_SETATTR" + "POLICY_CHECK" }; void *ima_policy_start(struct seq_file *m, loff_t *pos) diff --git a/sound/hda/ext/hdac_ext_stream.c b/sound/hda/ext/hdac_ext_stream.c index 023cc4cad5c1..626f3bb24c55 100644 --- a/sound/hda/ext/hdac_ext_stream.c +++ b/sound/hda/ext/hdac_ext_stream.c @@ -104,12 +104,11 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_stream_init_all); */ void snd_hdac_stream_free_all(struct hdac_ext_bus *ebus) { - struct hdac_stream *s; + struct hdac_stream *s, *_s; struct hdac_ext_stream *stream; struct hdac_bus *bus = ebus_to_hbus(ebus); - while (!list_empty(&bus->stream_list)) { - s = list_first_entry(&bus->stream_list, struct hdac_stream, list); + list_for_each_entry_safe(s, _s, &bus->stream_list, list) { stream = stream_to_hdac_ext_stream(s); snd_hdac_ext_stream_decouple(ebus, stream, false); list_del(&s->list); diff --git a/sound/hda/hdac_i915.c b/sound/hda/hdac_i915.c index 54babe1c0b16..607bbeaebddf 100644 --- a/sound/hda/hdac_i915.c +++ b/sound/hda/hdac_i915.c @@ -20,6 +20,7 @@ #include <sound/core.h> #include <sound/hdaudio.h> #include <sound/hda_i915.h> +#include <sound/hda_register.h> static struct i915_audio_component *hdac_acomp; @@ -97,26 +98,65 @@ int snd_hdac_display_power(struct hdac_bus *bus, bool enable) } EXPORT_SYMBOL_GPL(snd_hdac_display_power); +#define CONTROLLER_IN_GPU(pci) (((pci)->device == 0x0a0c) || \ + ((pci)->device == 0x0c0c) || \ + ((pci)->device == 0x0d0c) || \ + ((pci)->device == 0x160c)) + /** - * snd_hdac_get_display_clk - Get CDCLK in kHz + * snd_hdac_i915_set_bclk - Reprogram BCLK for HSW/BDW * @bus: HDA core bus * - * This function is supposed to be used only by a HD-audio controller - * driver that needs the interaction with i915 graphics. + * Intel HSW/BDW display HDA controller is in GPU. Both its power and link BCLK + * depends on GPU. Two Extended Mode registers EM4 (M value) and EM5 (N Value) + * are used to convert CDClk (Core Display Clock) to 24MHz BCLK: + * BCLK = CDCLK * M / N + * The values will be lost when the display power well is disabled and need to + * be restored to avoid abnormal playback speed. * - * This function queries CDCLK value in kHz from the graphics driver and - * returns the value. A negative code is returned in error. + * Call this function at initializing and changing power well, as well as + * at ELD notifier for the hotplug. */ -int snd_hdac_get_display_clk(struct hdac_bus *bus) +void snd_hdac_i915_set_bclk(struct hdac_bus *bus) { struct i915_audio_component *acomp = bus->audio_component; + struct pci_dev *pci = to_pci_dev(bus->dev); + int cdclk_freq; + unsigned int bclk_m, bclk_n; + + if (!acomp || !acomp->ops || !acomp->ops->get_cdclk_freq) + return; /* only for i915 binding */ + if (!CONTROLLER_IN_GPU(pci)) + return; /* only HSW/BDW */ + + cdclk_freq = acomp->ops->get_cdclk_freq(acomp->dev); + switch (cdclk_freq) { + case 337500: + bclk_m = 16; + bclk_n = 225; + break; + + case 450000: + default: /* default CDCLK 450MHz */ + bclk_m = 4; + bclk_n = 75; + break; + + case 540000: + bclk_m = 4; + bclk_n = 90; + break; + + case 675000: + bclk_m = 8; + bclk_n = 225; + break; + } - if (!acomp || !acomp->ops) - return -ENODEV; - - return acomp->ops->get_cdclk_freq(acomp->dev); + snd_hdac_chip_writew(bus, HSW_EM4, bclk_m); + snd_hdac_chip_writew(bus, HSW_EM5, bclk_n); } -EXPORT_SYMBOL_GPL(snd_hdac_get_display_clk); +EXPORT_SYMBOL_GPL(snd_hdac_i915_set_bclk); /* There is a fixed mapping between audio pin node and display port * on current Intel platforms: diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 637b8a0e2a91..9a0d1445ca5c 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -857,50 +857,6 @@ static int param_set_xint(const char *val, const struct kernel_param *kp) #define azx_del_card_list(chip) /* NOP */ #endif /* CONFIG_PM */ -/* Intel HSW/BDW display HDA controller is in GPU. Both its power and link BCLK - * depends on GPU. Two Extended Mode registers EM4 (M value) and EM5 (N Value) - * are used to convert CDClk (Core Display Clock) to 24MHz BCLK: - * BCLK = CDCLK * M / N - * The values will be lost when the display power well is disabled and need to - * be restored to avoid abnormal playback speed. - */ -static void haswell_set_bclk(struct hda_intel *hda) -{ - struct azx *chip = &hda->chip; - int cdclk_freq; - unsigned int bclk_m, bclk_n; - - if (!hda->need_i915_power) - return; - - cdclk_freq = snd_hdac_get_display_clk(azx_bus(chip)); - switch (cdclk_freq) { - case 337500: - bclk_m = 16; - bclk_n = 225; - break; - - case 450000: - default: /* default CDCLK 450MHz */ - bclk_m = 4; - bclk_n = 75; - break; - - case 540000: - bclk_m = 4; - bclk_n = 90; - break; - - case 675000: - bclk_m = 8; - bclk_n = 225; - break; - } - - azx_writew(chip, HSW_EM4, bclk_m); - azx_writew(chip, HSW_EM5, bclk_n); -} - #if defined(CONFIG_PM_SLEEP) || defined(SUPPORT_VGA_SWITCHEROO) /* * power management @@ -958,7 +914,7 @@ static int azx_resume(struct device *dev) if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL && hda->need_i915_power) { snd_hdac_display_power(azx_bus(chip), true); - haswell_set_bclk(hda); + snd_hdac_i915_set_bclk(azx_bus(chip)); } if (chip->msi) if (pci_enable_msi(pci) < 0) @@ -1058,7 +1014,7 @@ static int azx_runtime_resume(struct device *dev) bus = azx_bus(chip); if (hda->need_i915_power) { snd_hdac_display_power(bus, true); - haswell_set_bclk(hda); + snd_hdac_i915_set_bclk(bus); } else { /* toggle codec wakeup bit for STATESTS read */ snd_hdac_set_codec_wakeup(bus, true); @@ -1796,12 +1752,8 @@ static int azx_first_init(struct azx *chip) /* initialize chip */ azx_init_pci(chip); - if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL) { - struct hda_intel *hda; - - hda = container_of(chip, struct hda_intel, chip); - haswell_set_bclk(hda); - } + if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL) + snd_hdac_i915_set_bclk(bus); hda_intel_init_chip(chip, (probe_only[dev] & 2) == 0); diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index 40933aa33afe..1483f85999ec 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -2232,6 +2232,7 @@ static void intel_pin_eld_notify(void *audio_ptr, int port) if (atomic_read(&(codec)->core.in_pm)) return; + snd_hdac_i915_set_bclk(&codec->bus->core); check_presence_and_report(codec, pin_nid); } diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 810bceee4fd2..ac4490a96863 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -5584,6 +5584,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x5034, "Thinkpad T450", ALC292_FIXUP_TPT440_DOCK), SND_PCI_QUIRK(0x17aa, 0x5036, "Thinkpad T450s", ALC292_FIXUP_TPT440_DOCK), SND_PCI_QUIRK(0x17aa, 0x503c, "Thinkpad L450", ALC292_FIXUP_TPT440_DOCK), + SND_PCI_QUIRK(0x17aa, 0x504a, "ThinkPad X260", ALC292_FIXUP_TPT440_DOCK), SND_PCI_QUIRK(0x17aa, 0x504b, "Thinkpad", ALC293_FIXUP_LENOVO_SPK_NOISE), SND_PCI_QUIRK(0x17aa, 0x5109, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x17aa, 0x3bf8, "Quanta FL1", ALC269_FIXUP_PCM_44K), diff --git a/sound/soc/codecs/Kconfig b/sound/soc/codecs/Kconfig index 649e92a252ae..7ef3a0c16478 100644 --- a/sound/soc/codecs/Kconfig +++ b/sound/soc/codecs/Kconfig @@ -629,6 +629,7 @@ config SND_SOC_RT5514 config SND_SOC_RT5616 tristate "Realtek RT5616 CODEC" + depends on I2C config SND_SOC_RT5631 tristate "Realtek ALC5631/RT5631 CODEC" diff --git a/sound/soc/codecs/arizona.c b/sound/soc/codecs/arizona.c index 92d22a018d68..83959312f7a0 100644 --- a/sound/soc/codecs/arizona.c +++ b/sound/soc/codecs/arizona.c @@ -249,6 +249,18 @@ int arizona_init_spk(struct snd_soc_codec *codec) } EXPORT_SYMBOL_GPL(arizona_init_spk); +int arizona_free_spk(struct snd_soc_codec *codec) +{ + struct arizona_priv *priv = snd_soc_codec_get_drvdata(codec); + struct arizona *arizona = priv->arizona; + + arizona_free_irq(arizona, ARIZONA_IRQ_SPK_OVERHEAT_WARN, arizona); + arizona_free_irq(arizona, ARIZONA_IRQ_SPK_OVERHEAT, arizona); + + return 0; +} +EXPORT_SYMBOL_GPL(arizona_free_spk); + static const struct snd_soc_dapm_route arizona_mono_routes[] = { { "OUT1R", NULL, "OUT1L" }, { "OUT2R", NULL, "OUT2L" }, diff --git a/sound/soc/codecs/arizona.h b/sound/soc/codecs/arizona.h index 1ea8e4ecf8d4..ce0531b8c632 100644 --- a/sound/soc/codecs/arizona.h +++ b/sound/soc/codecs/arizona.h @@ -307,6 +307,8 @@ extern int arizona_init_spk(struct snd_soc_codec *codec); extern int arizona_init_gpio(struct snd_soc_codec *codec); extern int arizona_init_mono(struct snd_soc_codec *codec); +extern int arizona_free_spk(struct snd_soc_codec *codec); + extern int arizona_init_dai(struct arizona_priv *priv, int dai); int arizona_set_output_mode(struct snd_soc_codec *codec, int output, diff --git a/sound/soc/codecs/cs35l32.c b/sound/soc/codecs/cs35l32.c index 44c30fe3e315..287d13740be4 100644 --- a/sound/soc/codecs/cs35l32.c +++ b/sound/soc/codecs/cs35l32.c @@ -274,7 +274,9 @@ static int cs35l32_handle_of_data(struct i2c_client *i2c_client, if (of_property_read_u32(np, "cirrus,sdout-share", &val) >= 0) pdata->sdout_share = val; - of_property_read_u32(np, "cirrus,boost-manager", &val); + if (of_property_read_u32(np, "cirrus,boost-manager", &val)) + val = -1u; + switch (val) { case CS35L32_BOOST_MGR_AUTO: case CS35L32_BOOST_MGR_AUTO_AUDIO: @@ -282,13 +284,15 @@ static int cs35l32_handle_of_data(struct i2c_client *i2c_client, case CS35L32_BOOST_MGR_FIXED: pdata->boost_mng = val; break; + case -1u: default: dev_err(&i2c_client->dev, "Wrong cirrus,boost-manager DT value %d\n", val); pdata->boost_mng = CS35L32_BOOST_MGR_BYPASS; } - of_property_read_u32(np, "cirrus,sdout-datacfg", &val); + if (of_property_read_u32(np, "cirrus,sdout-datacfg", &val)) + val = -1u; switch (val) { case CS35L32_DATA_CFG_LR_VP: case CS35L32_DATA_CFG_LR_STAT: @@ -296,13 +300,15 @@ static int cs35l32_handle_of_data(struct i2c_client *i2c_client, case CS35L32_DATA_CFG_LR_VPSTAT: pdata->sdout_datacfg = val; break; + case -1u: default: dev_err(&i2c_client->dev, "Wrong cirrus,sdout-datacfg DT value %d\n", val); pdata->sdout_datacfg = CS35L32_DATA_CFG_LR; } - of_property_read_u32(np, "cirrus,battery-threshold", &val); + if (of_property_read_u32(np, "cirrus,battery-threshold", &val)) + val = -1u; switch (val) { case CS35L32_BATT_THRESH_3_1V: case CS35L32_BATT_THRESH_3_2V: @@ -310,13 +316,15 @@ static int cs35l32_handle_of_data(struct i2c_client *i2c_client, case CS35L32_BATT_THRESH_3_4V: pdata->batt_thresh = val; break; + case -1u: default: dev_err(&i2c_client->dev, "Wrong cirrus,battery-threshold DT value %d\n", val); pdata->batt_thresh = CS35L32_BATT_THRESH_3_3V; } - of_property_read_u32(np, "cirrus,battery-recovery", &val); + if (of_property_read_u32(np, "cirrus,battery-recovery", &val)) + val = -1u; switch (val) { case CS35L32_BATT_RECOV_3_1V: case CS35L32_BATT_RECOV_3_2V: @@ -326,6 +334,7 @@ static int cs35l32_handle_of_data(struct i2c_client *i2c_client, case CS35L32_BATT_RECOV_3_6V: pdata->batt_recov = val; break; + case -1u: default: dev_err(&i2c_client->dev, "Wrong cirrus,battery-recovery DT value %d\n", val); diff --git a/sound/soc/codecs/cs47l24.c b/sound/soc/codecs/cs47l24.c index 576087bda330..00e9b6fc1b5c 100644 --- a/sound/soc/codecs/cs47l24.c +++ b/sound/soc/codecs/cs47l24.c @@ -1108,6 +1108,9 @@ static int cs47l24_codec_remove(struct snd_soc_codec *codec) priv->core.arizona->dapm = NULL; arizona_free_irq(arizona, ARIZONA_IRQ_DSP_IRQ1, priv); + + arizona_free_spk(codec); + return 0; } diff --git a/sound/soc/codecs/hdac_hdmi.c b/sound/soc/codecs/hdac_hdmi.c index 26f9459cb3bc..aaa038ffc8a5 100644 --- a/sound/soc/codecs/hdac_hdmi.c +++ b/sound/soc/codecs/hdac_hdmi.c @@ -1420,32 +1420,39 @@ static int hdmi_codec_remove(struct snd_soc_codec *codec) } #ifdef CONFIG_PM -static int hdmi_codec_resume(struct snd_soc_codec *codec) +static int hdmi_codec_prepare(struct device *dev) { - struct hdac_ext_device *edev = snd_soc_codec_get_drvdata(codec); + struct hdac_ext_device *edev = to_hda_ext_device(dev); + struct hdac_device *hdac = &edev->hdac; + + pm_runtime_get_sync(&edev->hdac.dev); + + /* + * Power down afg. + * codec_read is preferred over codec_write to set the power state. + * This way verb is send to set the power state and response + * is received. So setting power state is ensured without using loop + * to read the state. + */ + snd_hdac_codec_read(hdac, hdac->afg, 0, AC_VERB_SET_POWER_STATE, + AC_PWRST_D3); + + return 0; +} + +static void hdmi_codec_complete(struct device *dev) +{ + struct hdac_ext_device *edev = to_hda_ext_device(dev); struct hdac_hdmi_priv *hdmi = edev->private_data; struct hdac_hdmi_pin *pin; struct hdac_device *hdac = &edev->hdac; - struct hdac_bus *bus = hdac->bus; - int err; - unsigned long timeout; - - hdac_hdmi_skl_enable_all_pins(&edev->hdac); - hdac_hdmi_skl_enable_dp12(&edev->hdac); /* Power up afg */ - if (!snd_hdac_check_power_state(hdac, hdac->afg, AC_PWRST_D0)) { - - snd_hdac_codec_write(hdac, hdac->afg, 0, - AC_VERB_SET_POWER_STATE, AC_PWRST_D0); + snd_hdac_codec_read(hdac, hdac->afg, 0, AC_VERB_SET_POWER_STATE, + AC_PWRST_D0); - /* Wait till power state is set to D0 */ - timeout = jiffies + msecs_to_jiffies(1000); - while (!snd_hdac_check_power_state(hdac, hdac->afg, AC_PWRST_D0) - && time_before(jiffies, timeout)) { - msleep(50); - } - } + hdac_hdmi_skl_enable_all_pins(&edev->hdac); + hdac_hdmi_skl_enable_dp12(&edev->hdac); /* * As the ELD notify callback request is not entertained while the @@ -1455,28 +1462,16 @@ static int hdmi_codec_resume(struct snd_soc_codec *codec) list_for_each_entry(pin, &hdmi->pin_list, head) hdac_hdmi_present_sense(pin, 1); - /* - * Codec power is turned ON during controller resume. - * Turn it OFF here - */ - err = snd_hdac_display_power(bus, false); - if (err < 0) { - dev_err(bus->dev, - "Cannot turn OFF display power on i915, err: %d\n", - err); - return err; - } - - return 0; + pm_runtime_put_sync(&edev->hdac.dev); } #else -#define hdmi_codec_resume NULL +#define hdmi_codec_prepare NULL +#define hdmi_codec_complete NULL #endif static struct snd_soc_codec_driver hdmi_hda_codec = { .probe = hdmi_codec_probe, .remove = hdmi_codec_remove, - .resume = hdmi_codec_resume, .idle_bias_off = true, }; @@ -1561,7 +1556,6 @@ static int hdac_hdmi_runtime_suspend(struct device *dev) struct hdac_ext_device *edev = to_hda_ext_device(dev); struct hdac_device *hdac = &edev->hdac; struct hdac_bus *bus = hdac->bus; - unsigned long timeout; int err; dev_dbg(dev, "Enter: %s\n", __func__); @@ -1570,20 +1564,15 @@ static int hdac_hdmi_runtime_suspend(struct device *dev) if (!bus) return 0; - /* Power down afg */ - if (!snd_hdac_check_power_state(hdac, hdac->afg, AC_PWRST_D3)) { - snd_hdac_codec_write(hdac, hdac->afg, 0, - AC_VERB_SET_POWER_STATE, AC_PWRST_D3); - - /* Wait till power state is set to D3 */ - timeout = jiffies + msecs_to_jiffies(1000); - while (!snd_hdac_check_power_state(hdac, hdac->afg, AC_PWRST_D3) - && time_before(jiffies, timeout)) { - - msleep(50); - } - } - + /* + * Power down afg. + * codec_read is preferred over codec_write to set the power state. + * This way verb is send to set the power state and response + * is received. So setting power state is ensured without using loop + * to read the state. + */ + snd_hdac_codec_read(hdac, hdac->afg, 0, AC_VERB_SET_POWER_STATE, + AC_PWRST_D3); err = snd_hdac_display_power(bus, false); if (err < 0) { dev_err(bus->dev, "Cannot turn on display power on i915\n"); @@ -1616,9 +1605,8 @@ static int hdac_hdmi_runtime_resume(struct device *dev) hdac_hdmi_skl_enable_dp12(&edev->hdac); /* Power up afg */ - if (!snd_hdac_check_power_state(hdac, hdac->afg, AC_PWRST_D0)) - snd_hdac_codec_write(hdac, hdac->afg, 0, - AC_VERB_SET_POWER_STATE, AC_PWRST_D0); + snd_hdac_codec_read(hdac, hdac->afg, 0, AC_VERB_SET_POWER_STATE, + AC_PWRST_D0); return 0; } @@ -1629,6 +1617,8 @@ static int hdac_hdmi_runtime_resume(struct device *dev) static const struct dev_pm_ops hdac_hdmi_pm = { SET_RUNTIME_PM_OPS(hdac_hdmi_runtime_suspend, hdac_hdmi_runtime_resume, NULL) + .prepare = hdmi_codec_prepare, + .complete = hdmi_codec_complete, }; static const struct hda_device_id hdmi_list[] = { diff --git a/sound/soc/codecs/nau8825.c b/sound/soc/codecs/nau8825.c index 1c8729984c2b..683769f0f246 100644 --- a/sound/soc/codecs/nau8825.c +++ b/sound/soc/codecs/nau8825.c @@ -343,9 +343,12 @@ static const struct snd_soc_dapm_widget nau8825_dapm_widgets[] = { SND_SOC_DAPM_SUPPLY("ADC Power", NAU8825_REG_ANALOG_ADC_2, 6, 0, NULL, 0), - /* ADC for button press detection */ - SND_SOC_DAPM_ADC("SAR", NULL, NAU8825_REG_SAR_CTRL, - NAU8825_SAR_ADC_EN_SFT, 0), + /* ADC for button press detection. A dapm supply widget is used to + * prevent dapm_power_widgets keeping the codec at SND_SOC_BIAS_ON + * during suspend. + */ + SND_SOC_DAPM_SUPPLY("SAR", NAU8825_REG_SAR_CTRL, + NAU8825_SAR_ADC_EN_SFT, 0, NULL, 0), SND_SOC_DAPM_PGA_S("ADACL", 2, NAU8825_REG_RDAC, 12, 0, NULL, 0), SND_SOC_DAPM_PGA_S("ADACR", 2, NAU8825_REG_RDAC, 13, 0, NULL, 0), @@ -607,6 +610,16 @@ static bool nau8825_is_jack_inserted(struct regmap *regmap) static void nau8825_restart_jack_detection(struct regmap *regmap) { + /* Chip needs one FSCLK cycle in order to generate interrupts, + * as we cannot guarantee one will be provided by the system. Turning + * master mode on then off enables us to generate that FSCLK cycle + * with a minimum of contention on the clock bus. + */ + regmap_update_bits(regmap, NAU8825_REG_I2S_PCM_CTRL2, + NAU8825_I2S_MS_MASK, NAU8825_I2S_MS_MASTER); + regmap_update_bits(regmap, NAU8825_REG_I2S_PCM_CTRL2, + NAU8825_I2S_MS_MASK, NAU8825_I2S_MS_SLAVE); + /* this will restart the entire jack detection process including MIC/GND * switching and create interrupts. We have to go from 0 to 1 and back * to 0 to restart. @@ -728,7 +741,10 @@ static irqreturn_t nau8825_interrupt(int irq, void *data) struct regmap *regmap = nau8825->regmap; int active_irq, clear_irq = 0, event = 0, event_mask = 0; - regmap_read(regmap, NAU8825_REG_IRQ_STATUS, &active_irq); + if (regmap_read(regmap, NAU8825_REG_IRQ_STATUS, &active_irq)) { + dev_err(nau8825->dev, "failed to read irq status\n"); + return IRQ_NONE; + } if ((active_irq & NAU8825_JACK_EJECTION_IRQ_MASK) == NAU8825_JACK_EJECTION_DETECTED) { @@ -1141,33 +1157,74 @@ static int nau8825_set_bias_level(struct snd_soc_codec *codec, return ret; } } - - ret = regcache_sync(nau8825->regmap); - if (ret) { - dev_err(codec->dev, - "Failed to sync cache: %d\n", ret); - return ret; - } } - break; case SND_SOC_BIAS_OFF: if (nau8825->mclk_freq) clk_disable_unprepare(nau8825->mclk); - - regcache_mark_dirty(nau8825->regmap); break; } return 0; } +#ifdef CONFIG_PM +static int nau8825_suspend(struct snd_soc_codec *codec) +{ + struct nau8825 *nau8825 = snd_soc_codec_get_drvdata(codec); + + disable_irq(nau8825->irq); + regcache_cache_only(nau8825->regmap, true); + regcache_mark_dirty(nau8825->regmap); + + return 0; +} + +static int nau8825_resume(struct snd_soc_codec *codec) +{ + struct nau8825 *nau8825 = snd_soc_codec_get_drvdata(codec); + + /* The chip may lose power and reset in S3. regcache_sync restores + * register values including configurations for sysclk, irq, and + * jack/button detection. + */ + regcache_cache_only(nau8825->regmap, false); + regcache_sync(nau8825->regmap); + + /* Check the jack plug status directly. If the headset is unplugged + * during S3 when the chip has no power, there will be no jack + * detection irq even after the nau8825_restart_jack_detection below, + * because the chip just thinks no headset has ever been plugged in. + */ + if (!nau8825_is_jack_inserted(nau8825->regmap)) { + nau8825_eject_jack(nau8825); + snd_soc_jack_report(nau8825->jack, 0, SND_JACK_HEADSET); + } + + enable_irq(nau8825->irq); + + /* Run jack detection to check the type (OMTP or CTIA) of the headset + * if there is one. This handles the case where a different type of + * headset is plugged in during S3. This triggers an IRQ iff a headset + * is already plugged in. + */ + nau8825_restart_jack_detection(nau8825->regmap); + + return 0; +} +#else +#define nau8825_suspend NULL +#define nau8825_resume NULL +#endif + static struct snd_soc_codec_driver nau8825_codec_driver = { .probe = nau8825_codec_probe, .set_sysclk = nau8825_set_sysclk, .set_pll = nau8825_set_pll, .set_bias_level = nau8825_set_bias_level, .suspend_bias_off = true, + .suspend = nau8825_suspend, + .resume = nau8825_resume, .controls = nau8825_controls, .num_controls = ARRAY_SIZE(nau8825_controls), @@ -1277,16 +1334,6 @@ static int nau8825_setup_irq(struct nau8825 *nau8825) regmap_update_bits(regmap, NAU8825_REG_ENA_CTRL, NAU8825_ENABLE_DACR, NAU8825_ENABLE_DACR); - /* Chip needs one FSCLK cycle in order to generate interrupts, - * as we cannot guarantee one will be provided by the system. Turning - * master mode on then off enables us to generate that FSCLK cycle - * with a minimum of contention on the clock bus. - */ - regmap_update_bits(regmap, NAU8825_REG_I2S_PCM_CTRL2, - NAU8825_I2S_MS_MASK, NAU8825_I2S_MS_MASTER); - regmap_update_bits(regmap, NAU8825_REG_I2S_PCM_CTRL2, - NAU8825_I2S_MS_MASK, NAU8825_I2S_MS_SLAVE); - ret = devm_request_threaded_irq(nau8825->dev, nau8825->irq, NULL, nau8825_interrupt, IRQF_TRIGGER_LOW | IRQF_ONESHOT, "nau8825", nau8825); @@ -1354,36 +1401,6 @@ static int nau8825_i2c_remove(struct i2c_client *client) return 0; } -#ifdef CONFIG_PM_SLEEP -static int nau8825_suspend(struct device *dev) -{ - struct i2c_client *client = to_i2c_client(dev); - struct nau8825 *nau8825 = dev_get_drvdata(dev); - - disable_irq(client->irq); - regcache_cache_only(nau8825->regmap, true); - regcache_mark_dirty(nau8825->regmap); - - return 0; -} - -static int nau8825_resume(struct device *dev) -{ - struct i2c_client *client = to_i2c_client(dev); - struct nau8825 *nau8825 = dev_get_drvdata(dev); - - regcache_cache_only(nau8825->regmap, false); - regcache_sync(nau8825->regmap); - enable_irq(client->irq); - - return 0; -} -#endif - -static const struct dev_pm_ops nau8825_pm = { - SET_SYSTEM_SLEEP_PM_OPS(nau8825_suspend, nau8825_resume) -}; - static const struct i2c_device_id nau8825_i2c_ids[] = { { "nau8825", 0 }, { } @@ -1410,7 +1427,6 @@ static struct i2c_driver nau8825_driver = { .name = "nau8825", .of_match_table = of_match_ptr(nau8825_of_ids), .acpi_match_table = ACPI_PTR(nau8825_acpi_match), - .pm = &nau8825_pm, }, .probe = nau8825_i2c_probe, .remove = nau8825_i2c_remove, diff --git a/sound/soc/codecs/rt5640.c b/sound/soc/codecs/rt5640.c index e8b5ba04417a..09e8988bbb2d 100644 --- a/sound/soc/codecs/rt5640.c +++ b/sound/soc/codecs/rt5640.c @@ -359,7 +359,7 @@ static const DECLARE_TLV_DB_RANGE(bst_tlv, /* Interface data select */ static const char * const rt5640_data_select[] = { - "Normal", "left copy to right", "right copy to left", "Swap"}; + "Normal", "Swap", "left copy to right", "right copy to left"}; static SOC_ENUM_SINGLE_DECL(rt5640_if1_dac_enum, RT5640_DIG_INF_DATA, RT5640_IF1_DAC_SEL_SFT, rt5640_data_select); diff --git a/sound/soc/codecs/rt5640.h b/sound/soc/codecs/rt5640.h index 1761c3a98b76..58b664b06c16 100644 --- a/sound/soc/codecs/rt5640.h +++ b/sound/soc/codecs/rt5640.h @@ -443,39 +443,39 @@ #define RT5640_IF1_DAC_SEL_MASK (0x3 << 14) #define RT5640_IF1_DAC_SEL_SFT 14 #define RT5640_IF1_DAC_SEL_NOR (0x0 << 14) -#define RT5640_IF1_DAC_SEL_L2R (0x1 << 14) -#define RT5640_IF1_DAC_SEL_R2L (0x2 << 14) -#define RT5640_IF1_DAC_SEL_SWAP (0x3 << 14) +#define RT5640_IF1_DAC_SEL_SWAP (0x1 << 14) +#define RT5640_IF1_DAC_SEL_L2R (0x2 << 14) +#define RT5640_IF1_DAC_SEL_R2L (0x3 << 14) #define RT5640_IF1_ADC_SEL_MASK (0x3 << 12) #define RT5640_IF1_ADC_SEL_SFT 12 #define RT5640_IF1_ADC_SEL_NOR (0x0 << 12) -#define RT5640_IF1_ADC_SEL_L2R (0x1 << 12) -#define RT5640_IF1_ADC_SEL_R2L (0x2 << 12) -#define RT5640_IF1_ADC_SEL_SWAP (0x3 << 12) +#define RT5640_IF1_ADC_SEL_SWAP (0x1 << 12) +#define RT5640_IF1_ADC_SEL_L2R (0x2 << 12) +#define RT5640_IF1_ADC_SEL_R2L (0x3 << 12) #define RT5640_IF2_DAC_SEL_MASK (0x3 << 10) #define RT5640_IF2_DAC_SEL_SFT 10 #define RT5640_IF2_DAC_SEL_NOR (0x0 << 10) -#define RT5640_IF2_DAC_SEL_L2R (0x1 << 10) -#define RT5640_IF2_DAC_SEL_R2L (0x2 << 10) -#define RT5640_IF2_DAC_SEL_SWAP (0x3 << 10) +#define RT5640_IF2_DAC_SEL_SWAP (0x1 << 10) +#define RT5640_IF2_DAC_SEL_L2R (0x2 << 10) +#define RT5640_IF2_DAC_SEL_R2L (0x3 << 10) #define RT5640_IF2_ADC_SEL_MASK (0x3 << 8) #define RT5640_IF2_ADC_SEL_SFT 8 #define RT5640_IF2_ADC_SEL_NOR (0x0 << 8) -#define RT5640_IF2_ADC_SEL_L2R (0x1 << 8) -#define RT5640_IF2_ADC_SEL_R2L (0x2 << 8) -#define RT5640_IF2_ADC_SEL_SWAP (0x3 << 8) +#define RT5640_IF2_ADC_SEL_SWAP (0x1 << 8) +#define RT5640_IF2_ADC_SEL_L2R (0x2 << 8) +#define RT5640_IF2_ADC_SEL_R2L (0x3 << 8) #define RT5640_IF3_DAC_SEL_MASK (0x3 << 6) #define RT5640_IF3_DAC_SEL_SFT 6 #define RT5640_IF3_DAC_SEL_NOR (0x0 << 6) -#define RT5640_IF3_DAC_SEL_L2R (0x1 << 6) -#define RT5640_IF3_DAC_SEL_R2L (0x2 << 6) -#define RT5640_IF3_DAC_SEL_SWAP (0x3 << 6) +#define RT5640_IF3_DAC_SEL_SWAP (0x1 << 6) +#define RT5640_IF3_DAC_SEL_L2R (0x2 << 6) +#define RT5640_IF3_DAC_SEL_R2L (0x3 << 6) #define RT5640_IF3_ADC_SEL_MASK (0x3 << 4) #define RT5640_IF3_ADC_SEL_SFT 4 #define RT5640_IF3_ADC_SEL_NOR (0x0 << 4) -#define RT5640_IF3_ADC_SEL_L2R (0x1 << 4) -#define RT5640_IF3_ADC_SEL_R2L (0x2 << 4) -#define RT5640_IF3_ADC_SEL_SWAP (0x3 << 4) +#define RT5640_IF3_ADC_SEL_SWAP (0x1 << 4) +#define RT5640_IF3_ADC_SEL_L2R (0x2 << 4) +#define RT5640_IF3_ADC_SEL_R2L (0x3 << 4) /* REC Left Mixer Control 1 (0x3b) */ #define RT5640_G_HP_L_RM_L_MASK (0x7 << 13) diff --git a/sound/soc/codecs/wm5102.c b/sound/soc/codecs/wm5102.c index a8b3e3f701f9..1bae17ee8817 100644 --- a/sound/soc/codecs/wm5102.c +++ b/sound/soc/codecs/wm5102.c @@ -1955,11 +1955,16 @@ err_adsp2_codec_probe: static int wm5102_codec_remove(struct snd_soc_codec *codec) { struct wm5102_priv *priv = snd_soc_codec_get_drvdata(codec); + struct arizona *arizona = priv->core.arizona; wm_adsp2_codec_remove(&priv->core.adsp[0], codec); priv->core.arizona->dapm = NULL; + arizona_free_irq(arizona, ARIZONA_IRQ_DSP_IRQ1, priv); + + arizona_free_spk(codec); + return 0; } diff --git a/sound/soc/codecs/wm5110.c b/sound/soc/codecs/wm5110.c index 83ba70fe16e6..2728ac545ffe 100644 --- a/sound/soc/codecs/wm5110.c +++ b/sound/soc/codecs/wm5110.c @@ -2298,6 +2298,8 @@ static int wm5110_codec_remove(struct snd_soc_codec *codec) arizona_free_irq(arizona, ARIZONA_IRQ_DSP_IRQ1, priv); + arizona_free_spk(codec); + return 0; } diff --git a/sound/soc/codecs/wm8962.c b/sound/soc/codecs/wm8962.c index 88223608a33f..720a14e0687d 100644 --- a/sound/soc/codecs/wm8962.c +++ b/sound/soc/codecs/wm8962.c @@ -2471,7 +2471,7 @@ static void wm8962_configure_bclk(struct snd_soc_codec *codec) break; default: dev_warn(codec->dev, "Unknown DSPCLK divisor read back\n"); - dspclk = wm8962->sysclk; + dspclk = wm8962->sysclk_rate; } dev_dbg(codec->dev, "DSPCLK is %dHz, BCLK %d\n", dspclk, wm8962->bclk); diff --git a/sound/soc/codecs/wm8997.c b/sound/soc/codecs/wm8997.c index 52d766efe14f..6b0785b5a5c5 100644 --- a/sound/soc/codecs/wm8997.c +++ b/sound/soc/codecs/wm8997.c @@ -1072,6 +1072,8 @@ static int wm8997_codec_remove(struct snd_soc_codec *codec) priv->core.arizona->dapm = NULL; + arizona_free_spk(codec); + return 0; } diff --git a/sound/soc/codecs/wm8998.c b/sound/soc/codecs/wm8998.c index 012396074a8a..449f66636205 100644 --- a/sound/soc/codecs/wm8998.c +++ b/sound/soc/codecs/wm8998.c @@ -1324,6 +1324,8 @@ static int wm8998_codec_remove(struct snd_soc_codec *codec) priv->core.arizona->dapm = NULL; + arizona_free_spk(codec); + return 0; } diff --git a/sound/soc/intel/Kconfig b/sound/soc/intel/Kconfig index b3e6c2300457..1120f4f4d011 100644 --- a/sound/soc/intel/Kconfig +++ b/sound/soc/intel/Kconfig @@ -163,7 +163,6 @@ config SND_SOC_INTEL_SKYLAKE tristate select SND_HDA_EXT_CORE select SND_SOC_TOPOLOGY - select SND_HDA_I915 select SND_SOC_INTEL_SST config SND_SOC_INTEL_SKL_RT286_MACH diff --git a/sound/soc/intel/haswell/sst-haswell-ipc.c b/sound/soc/intel/haswell/sst-haswell-ipc.c index ac60f1301e21..91565229d074 100644 --- a/sound/soc/intel/haswell/sst-haswell-ipc.c +++ b/sound/soc/intel/haswell/sst-haswell-ipc.c @@ -1345,7 +1345,7 @@ int sst_hsw_stream_reset(struct sst_hsw *hsw, struct sst_hsw_stream *stream) return 0; /* wait for pause to complete before we reset the stream */ - while (stream->running && tries--) + while (stream->running && --tries) msleep(1); if (!tries) { dev_err(hsw->dev, "error: reset stream %d still running\n", diff --git a/sound/soc/intel/skylake/skl-sst-dsp.c b/sound/soc/intel/skylake/skl-sst-dsp.c index a5267e8a96e0..2962ef22fc84 100644 --- a/sound/soc/intel/skylake/skl-sst-dsp.c +++ b/sound/soc/intel/skylake/skl-sst-dsp.c @@ -336,6 +336,11 @@ void skl_dsp_free(struct sst_dsp *dsp) skl_ipc_int_disable(dsp); free_irq(dsp->irq, dsp); + dsp->cl_dev.ops.cl_cleanup_controller(dsp); + skl_cldma_int_disable(dsp); + skl_ipc_op_int_disable(dsp); + skl_ipc_int_disable(dsp); + skl_dsp_disable_core(dsp); } EXPORT_SYMBOL_GPL(skl_dsp_free); diff --git a/sound/soc/intel/skylake/skl-topology.c b/sound/soc/intel/skylake/skl-topology.c index 545b4e77b8aa..cdb78b7e5a14 100644 --- a/sound/soc/intel/skylake/skl-topology.c +++ b/sound/soc/intel/skylake/skl-topology.c @@ -239,6 +239,7 @@ static void skl_tplg_update_buffer_size(struct skl_sst *ctx, { int multiplier = 1; struct skl_module_fmt *in_fmt, *out_fmt; + int in_rate, out_rate; /* Since fixups is applied to pin 0 only, ibs, obs needs @@ -249,15 +250,24 @@ static void skl_tplg_update_buffer_size(struct skl_sst *ctx, if (mcfg->m_type == SKL_MODULE_TYPE_SRCINT) multiplier = 5; - mcfg->ibs = (in_fmt->s_freq / 1000) * - (mcfg->in_fmt->channels) * - (mcfg->in_fmt->bit_depth >> 3) * - multiplier; - - mcfg->obs = (mcfg->out_fmt->s_freq / 1000) * - (mcfg->out_fmt->channels) * - (mcfg->out_fmt->bit_depth >> 3) * - multiplier; + + if (in_fmt->s_freq % 1000) + in_rate = (in_fmt->s_freq / 1000) + 1; + else + in_rate = (in_fmt->s_freq / 1000); + + mcfg->ibs = in_rate * (mcfg->in_fmt->channels) * + (mcfg->in_fmt->bit_depth >> 3) * + multiplier; + + if (mcfg->out_fmt->s_freq % 1000) + out_rate = (mcfg->out_fmt->s_freq / 1000) + 1; + else + out_rate = (mcfg->out_fmt->s_freq / 1000); + + mcfg->obs = out_rate * (mcfg->out_fmt->channels) * + (mcfg->out_fmt->bit_depth >> 3) * + multiplier; } static int skl_tplg_update_be_blob(struct snd_soc_dapm_widget *w, @@ -485,11 +495,15 @@ skl_tplg_init_pipe_modules(struct skl *skl, struct skl_pipe *pipe) if (!skl_is_pipe_mcps_avail(skl, mconfig)) return -ENOMEM; + skl_tplg_alloc_pipe_mcps(skl, mconfig); + if (mconfig->is_loadable && ctx->dsp->fw_ops.load_mod) { ret = ctx->dsp->fw_ops.load_mod(ctx->dsp, mconfig->id.module_id, mconfig->guid); if (ret < 0) return ret; + + mconfig->m_state = SKL_MODULE_LOADED; } /* update blob if blob is null for be with default value */ @@ -509,7 +523,6 @@ skl_tplg_init_pipe_modules(struct skl *skl, struct skl_pipe *pipe) ret = skl_tplg_set_module_params(w, ctx); if (ret < 0) return ret; - skl_tplg_alloc_pipe_mcps(skl, mconfig); } return 0; @@ -524,7 +537,8 @@ static int skl_tplg_unload_pipe_modules(struct skl_sst *ctx, list_for_each_entry(w_module, &pipe->w_list, node) { mconfig = w_module->w->priv; - if (mconfig->is_loadable && ctx->dsp->fw_ops.unload_mod) + if (mconfig->is_loadable && ctx->dsp->fw_ops.unload_mod && + mconfig->m_state > SKL_MODULE_UNINIT) return ctx->dsp->fw_ops.unload_mod(ctx->dsp, mconfig->id.module_id); } @@ -558,6 +572,9 @@ static int skl_tplg_mixer_dapm_pre_pmu_event(struct snd_soc_dapm_widget *w, if (!skl_is_pipe_mem_avail(skl, mconfig)) return -ENOMEM; + skl_tplg_alloc_pipe_mem(skl, mconfig); + skl_tplg_alloc_pipe_mcps(skl, mconfig); + /* * Create a list of modules for pipe. * This list contains modules from source to sink @@ -601,9 +618,6 @@ static int skl_tplg_mixer_dapm_pre_pmu_event(struct snd_soc_dapm_widget *w, src_module = dst_module; } - skl_tplg_alloc_pipe_mem(skl, mconfig); - skl_tplg_alloc_pipe_mcps(skl, mconfig); - return 0; } diff --git a/sound/soc/intel/skylake/skl-topology.h b/sound/soc/intel/skylake/skl-topology.h index de3c401284d9..d2d923002d5c 100644 --- a/sound/soc/intel/skylake/skl-topology.h +++ b/sound/soc/intel/skylake/skl-topology.h @@ -274,10 +274,10 @@ struct skl_pipe { enum skl_module_state { SKL_MODULE_UNINIT = 0, - SKL_MODULE_INIT_DONE = 1, - SKL_MODULE_LOADED = 2, - SKL_MODULE_UNLOADED = 3, - SKL_MODULE_BIND_DONE = 4 + SKL_MODULE_LOADED = 1, + SKL_MODULE_INIT_DONE = 2, + SKL_MODULE_BIND_DONE = 3, + SKL_MODULE_UNLOADED = 4, }; struct skl_module_cfg { diff --git a/sound/soc/intel/skylake/skl.c b/sound/soc/intel/skylake/skl.c index ab5e25aaeee3..3982f5536f2d 100644 --- a/sound/soc/intel/skylake/skl.c +++ b/sound/soc/intel/skylake/skl.c @@ -222,6 +222,7 @@ static int skl_suspend(struct device *dev) struct hdac_ext_bus *ebus = pci_get_drvdata(pci); struct skl *skl = ebus_to_skl(ebus); struct hdac_bus *bus = ebus_to_hbus(ebus); + int ret = 0; /* * Do not suspend if streams which are marked ignore suspend are @@ -232,10 +233,20 @@ static int skl_suspend(struct device *dev) enable_irq_wake(bus->irq); pci_save_state(pci); pci_disable_device(pci); - return 0; } else { - return _skl_suspend(ebus); + ret = _skl_suspend(ebus); + if (ret < 0) + return ret; + } + + if (IS_ENABLED(CONFIG_SND_SOC_HDAC_HDMI)) { + ret = snd_hdac_display_power(bus, false); + if (ret < 0) + dev_err(bus->dev, + "Cannot turn OFF display power on i915\n"); } + + return ret; } static int skl_resume(struct device *dev) @@ -316,17 +327,20 @@ static int skl_free(struct hdac_ext_bus *ebus) if (bus->irq >= 0) free_irq(bus->irq, (void *)bus); - if (bus->remap_addr) - iounmap(bus->remap_addr); - snd_hdac_bus_free_stream_pages(bus); snd_hdac_stream_free_all(ebus); snd_hdac_link_free_all(ebus); + + if (bus->remap_addr) + iounmap(bus->remap_addr); + pci_release_regions(skl->pci); pci_disable_device(skl->pci); snd_hdac_ext_bus_exit(ebus); + if (IS_ENABLED(CONFIG_SND_SOC_HDAC_HDMI)) + snd_hdac_i915_exit(&ebus->bus); return 0; } @@ -719,12 +733,12 @@ static void skl_remove(struct pci_dev *pci) if (skl->tplg) release_firmware(skl->tplg); - if (IS_ENABLED(CONFIG_SND_SOC_HDAC_HDMI)) - snd_hdac_i915_exit(&ebus->bus); - if (pci_dev_run_wake(pci)) pm_runtime_get_noresume(&pci->dev); - pci_dev_put(pci); + + /* codec removal, invoke bus_device_remove */ + snd_hdac_ext_bus_device_remove(ebus); + skl_platform_unregister(&pci->dev); skl_free_dsp(skl); skl_machine_device_unregister(skl); diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c index 801ae1a81dfd..c4464858bf01 100644 --- a/sound/soc/soc-dapm.c +++ b/sound/soc/soc-dapm.c @@ -2188,6 +2188,13 @@ static ssize_t dapm_widget_show_component(struct snd_soc_component *cmpnt, int count = 0; char *state = "not set"; + /* card won't be set for the dummy component, as a spot fix + * we're checking for that case specifically here but in future + * we will ensure that the dummy component looks like others. + */ + if (!cmpnt->card) + return 0; + list_for_each_entry(w, &cmpnt->card->widgets, list) { if (w->dapm != dapm) continue; |