Home Home > GIT Browse > SLE12-SP4-AZURE
summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorOlaf Hering <ohering@suse.de>2019-05-15 09:33:09 +0200
committerOlaf Hering <ohering@suse.de>2019-05-15 09:33:09 +0200
commit91069920eb620bb45fb3478e6e2ce79b9b7567c3 (patch)
treeb8f84eac6e577d80cada6d8d5e7b7b25e95a7140
parent905f12b808fa3763c37c0cc5e37542a48a792894 (diff)
parent8b16e0fd7e6d70d674d56636fabb77d437dae06a (diff)
Merge remote-tracking branch 'kerncvs/SLE12-SP4' into SLE12-SP4-AZURESLE12-SP4-AZURE
-rw-r--r--Documentation/ABI/testing/sysfs-devices-system-cpu1
-rw-r--r--Documentation/admin-guide/kernel-parameters.txt26
-rw-r--r--Documentation/devicetree/bindings/net/ethernet.txt2
-rw-r--r--Documentation/driver-api/usb/power-management.rst14
-rw-r--r--Documentation/index.rst1
-rw-r--r--Documentation/kmsg/IPVS3
-rw-r--r--Documentation/kmsg/ism2
-rw-r--r--Documentation/kmsg/s390/aes_s3901
-rw-r--r--Documentation/kmsg/s390/af_iucv1
-rw-r--r--Documentation/kmsg/s390/appldata1
-rw-r--r--Documentation/kmsg/s390/bpf_jit1
-rw-r--r--Documentation/kmsg/s390/cio1
-rw-r--r--Documentation/kmsg/s390/cpcmd1
-rw-r--r--Documentation/kmsg/s390/cpu1
-rw-r--r--Documentation/kmsg/s390/crc32-vx1
-rw-r--r--Documentation/kmsg/s390/ctcm1
-rw-r--r--Documentation/kmsg/s390/dasd1
-rw-r--r--Documentation/kmsg/s390/dasd-eckd42
-rw-r--r--Documentation/kmsg/s390/diag288_wdt1
-rw-r--r--Documentation/kmsg/s390/extmem1
-rw-r--r--Documentation/kmsg/s390/hmcdrv1
-rw-r--r--Documentation/kmsg/s390/hugetlb1
-rw-r--r--Documentation/kmsg/s390/hypfs1
-rw-r--r--Documentation/kmsg/s390/lcs1
-rw-r--r--Documentation/kmsg/s390/monwriter1
-rw-r--r--Documentation/kmsg/s390/netiucv1
-rw-r--r--Documentation/kmsg/s390/paes_s3903
-rw-r--r--Documentation/kmsg/s390/perf1
-rw-r--r--Documentation/kmsg/s390/qeth1
-rw-r--r--Documentation/kmsg/s390/setup1
-rw-r--r--Documentation/kmsg/s390/vmur1
-rw-r--r--Documentation/kmsg/s390/zfcp2
-rw-r--r--Documentation/kmsg/s390/zpci1
-rw-r--r--Documentation/kmsg/s390/zram2
-rw-r--r--Documentation/kmsg/sbp_target3
-rw-r--r--Documentation/kmsg/smc4
-rw-r--r--Documentation/x86/conf.py10
-rw-r--r--Documentation/x86/index.rst8
-rw-r--r--Documentation/x86/mds.rst224
-rw-r--r--arch/arm/crypto/aes-neonbs-glue.c2
-rw-r--r--arch/x86/crypto/crct10dif-pclmul_glue.c13
-rw-r--r--arch/x86/entry/common.c3
-rw-r--r--arch/x86/events/intel/core.c18
-rw-r--r--arch/x86/events/intel/cstate.c4
-rw-r--r--arch/x86/events/msr.c4
-rw-r--r--arch/x86/include/asm/cpufeatures.h3
-rw-r--r--arch/x86/include/asm/intel-family.h30
-rw-r--r--arch/x86/include/asm/irqflags.h4
-rw-r--r--arch/x86/include/asm/msr-index.h39
-rw-r--r--arch/x86/include/asm/mwait.h6
-rw-r--r--arch/x86/include/asm/nospec-branch.h50
-rw-r--r--arch/x86/include/asm/processor.h6
-rw-r--r--arch/x86/kernel/cpu/bugs.c132
-rw-r--r--arch/x86/kernel/cpu/common.c134
-rw-r--r--arch/x86/kernel/nmi.c4
-rw-r--r--arch/x86/kernel/traps.c8
-rw-r--r--arch/x86/kernel/tsc.c2
-rw-r--r--arch/x86/kvm/cpuid.c6
-rw-r--r--arch/x86/kvm/vmx.c3
-rw-r--r--arch/x86/platform/atom/punit_atom_debug.c4
-rw-r--r--arch/x86/platform/intel-mid/device_libs/platform_bt.c2
-rw-r--r--block/genhd.c50
-rw-r--r--crypto/Kconfig4
-rw-r--r--crypto/ccm.c44
-rw-r--r--crypto/chacha20poly1305.c4
-rw-r--r--crypto/crct10dif_generic.c11
-rw-r--r--crypto/gcm.c34
-rw-r--r--crypto/skcipher.c9
-rw-r--r--drivers/acpi/acpi_lpss.c2
-rw-r--r--drivers/acpi/apei/ghes.c14
-rw-r--r--drivers/acpi/x86/utils.c2
-rw-r--r--drivers/ata/libata-zpodd.c34
-rw-r--r--drivers/base/cpu.c8
-rw-r--r--drivers/block/DAC960.c1
-rw-r--r--drivers/block/amiflop.c1
-rw-r--r--drivers/block/ataflop.c1
-rw-r--r--drivers/block/floppy.c1
-rw-r--r--drivers/block/paride/pcd.c1
-rw-r--r--drivers/block/paride/pd.c1
-rw-r--r--drivers/block/paride/pf.c1
-rw-r--r--drivers/block/swim.c1
-rw-r--r--drivers/block/swim3.c1
-rw-r--r--drivers/block/virtio_blk.c2
-rw-r--r--drivers/block/xsysace.c1
-rw-r--r--drivers/cdrom/gdrom.c1
-rw-r--r--drivers/char/ipmi/ipmi_ssif.c6
-rw-r--r--drivers/clk/rockchip/clk-rk3288.c4
-rw-r--r--drivers/clk/rockchip/clk-rk3328.c18
-rw-r--r--drivers/cpufreq/intel_pstate.c4
-rw-r--r--drivers/crypto/ccp/psp-dev.c2
-rw-r--r--drivers/crypto/sunxi-ss/sun4i-ss-hash.c5
-rw-r--r--drivers/crypto/vmx/aesp8-ppc.pl4
-rw-r--r--drivers/dma/dma-axi-dmac.c2
-rw-r--r--drivers/dma/tegra210-adma.c1
-rw-r--r--drivers/edac/ghes_edac.c6
-rw-r--r--drivers/edac/pnd2_edac.c2
-rw-r--r--drivers/gpio/gpio-aspeed.c2
-rw-r--r--drivers/gpu/drm/drm_fb_helper.c11
-rw-r--r--drivers/gpu/drm/i915/gvt/mmio_context.c4
-rw-r--r--drivers/gpu/drm/mediatek/mtk_hdmi.c1
-rw-r--r--drivers/gpu/drm/meson/meson_drv.c14
-rw-r--r--drivers/gpu/drm/rockchip/rockchip_drm_drv.c9
-rw-r--r--drivers/gpu/drm/ttm/ttm_bo_vm.c2
-rw-r--r--drivers/hid/hid-debug.c5
-rw-r--r--drivers/hid/hid-input.c1
-rw-r--r--drivers/hid/hid-logitech-hidpp.c8
-rw-r--r--drivers/hwmon/f71805f.c15
-rw-r--r--drivers/hwmon/pc87427.c14
-rw-r--r--drivers/hwmon/smsc47b397.c13
-rw-r--r--drivers/hwmon/smsc47m1.c28
-rw-r--r--drivers/hwmon/vt1211.c15
-rw-r--r--drivers/hwmon/w83627hf.c42
-rw-r--r--drivers/hwtracing/intel_th/msu.c35
-rw-r--r--drivers/hwtracing/intel_th/pci.c5
-rw-r--r--drivers/hwtracing/stm/core.c13
-rw-r--r--drivers/ide/ide-cd.c1
-rw-r--r--drivers/ide/ide-cd_ioctl.c5
-rw-r--r--drivers/ide/ide-gd.c6
-rw-r--r--drivers/idle/intel_idle.c18
-rw-r--r--drivers/iommu/intel-iommu.c18
-rw-r--r--drivers/leds/led-class.c1
-rw-r--r--drivers/leds/led-core.c5
-rw-r--r--drivers/md/bcache/Kconfig7
-rw-r--r--drivers/md/bcache/alloc.c41
-rw-r--r--drivers/md/bcache/bcache.h237
-rw-r--r--drivers/md/bcache/bset.c205
-rw-r--r--drivers/md/bcache/bset.h146
-rw-r--r--drivers/md/bcache/btree.c77
-rw-r--r--drivers/md/bcache/btree.h106
-rw-r--r--drivers/md/bcache/closure.c6
-rw-r--r--drivers/md/bcache/closure.h9
-rw-r--r--drivers/md/bcache/debug.c34
-rw-r--r--drivers/md/bcache/debug.h6
-rw-r--r--drivers/md/bcache/extents.c52
-rw-r--r--drivers/md/bcache/extents.h6
-rw-r--r--drivers/md/bcache/io.c24
-rw-r--r--drivers/md/bcache/journal.c35
-rw-r--r--drivers/md/bcache/journal.h28
-rw-r--r--drivers/md/bcache/movinggc.c14
-rw-r--r--drivers/md/bcache/request.c79
-rw-r--r--drivers/md/bcache/request.h20
-rw-r--r--drivers/md/bcache/stats.c17
-rw-r--r--drivers/md/bcache/stats.h15
-rw-r--r--drivers/md/bcache/super.c397
-rw-r--r--drivers/md/bcache/sysfs.c221
-rw-r--r--drivers/md/bcache/sysfs.h29
-rw-r--r--drivers/md/bcache/util.c168
-rw-r--r--drivers/md/bcache/util.h46
-rw-r--r--drivers/md/bcache/writeback.c60
-rw-r--r--drivers/md/bcache/writeback.h34
-rw-r--r--drivers/media/i2c/ov2659.c2
-rw-r--r--drivers/media/pci/cx18/cx18-fileops.c2
-rw-r--r--drivers/media/pci/cx23885/cx23885-dvb.c5
-rw-r--r--drivers/media/pci/ivtv/ivtv-fileops.c2
-rw-r--r--drivers/media/pci/tw5864/tw5864-video.c4
-rw-r--r--drivers/media/platform/davinci/isif.c9
-rw-r--r--drivers/media/platform/vivid/vivid-vid-cap.c2
-rw-r--r--drivers/media/radio/wl128x/fmdrv_common.c12
-rw-r--r--drivers/media/rc/serial_ir.c9
-rw-r--r--drivers/media/usb/pvrusb2/pvrusb2-hdw.c2
-rw-r--r--drivers/media/usb/pvrusb2/pvrusb2-hdw.h1
-rw-r--r--drivers/mmc/core/host.c2
-rw-r--r--drivers/mmc/host/sdhci-acpi.c2
-rw-r--r--drivers/mtd/devices/docg3.c7
-rw-r--r--drivers/mtd/mtdpart.c2
-rw-r--r--drivers/mtd/spi-nor/intel-spi.c8
-rw-r--r--drivers/net/ethernet/ibm/ibmvnic.c62
-rw-r--r--drivers/net/ethernet/ibm/ibmvnic.h2
-rw-r--r--drivers/net/usb/qmi_wwan.c1
-rw-r--r--drivers/net/wireless/atmel/at76c50x-usb.c4
-rw-r--r--drivers/net/wireless/broadcom/b43/phy_lp.c6
-rw-r--r--drivers/net/wireless/broadcom/brcm80211/brcmfmac/vendor.c5
-rw-r--r--drivers/net/wireless/marvell/mwifiex/cfg80211.c6
-rw-r--r--drivers/net/wireless/marvell/mwifiex/cfp.c3
-rw-r--r--drivers/net/wireless/marvell/mwl8k.c13
-rw-r--r--drivers/net/wireless/ralink/rt2x00/rt2x00.h1
-rw-r--r--drivers/net/wireless/ralink/rt2x00/rt2x00mac.c10
-rw-r--r--drivers/net/wireless/ralink/rt2x00/rt2x00queue.c15
-rw-r--r--drivers/net/wireless/realtek/rtlwifi/rtl8723ae/hw.c1
-rw-r--r--drivers/pci/pci-mid.c4
-rw-r--r--drivers/phy/allwinner/phy-sun4i-usb.c4
-rw-r--r--drivers/platform/x86/alienware-wmi.c2
-rw-r--r--drivers/platform/x86/dell-rbtn.c2
-rw-r--r--drivers/platform/x86/intel_int0002_vgpio.c2
-rw-r--r--drivers/platform/x86/intel_mid_powerbtn.c4
-rw-r--r--drivers/platform/x86/intel_pmc_ipc.c6
-rw-r--r--drivers/platform/x86/intel_punit_ipc.c8
-rw-r--r--drivers/platform/x86/pmc_atom.c2
-rw-r--r--drivers/platform/x86/sony-laptop.c8
-rw-r--r--drivers/powercap/intel_rapl.c10
-rw-r--r--drivers/pwm/core.c10
-rw-r--r--drivers/pwm/pwm-meson.c34
-rw-r--r--drivers/pwm/pwm-tiehrpwm.c2
-rw-r--r--drivers/pwm/sysfs.c14
-rw-r--r--drivers/regulator/tps65086-regulator.c4
-rw-r--r--drivers/s390/net/ism_drv.c12
-rw-r--r--drivers/scsi/lpfc/lpfc_scsi.c3
-rw-r--r--drivers/scsi/qla2xxx/qla_dfs.c2
-rw-r--r--drivers/scsi/qla2xxx/qla_isr.c2
-rw-r--r--drivers/scsi/qla2xxx/qla_target.c24
-rw-r--r--drivers/scsi/sd.c3
-rw-r--r--drivers/scsi/sr.c3
-rw-r--r--drivers/soc/tegra/pmc.c8
-rw-r--r--drivers/spi/spi-armada-3700.c5
-rw-r--r--drivers/spi/spi-bcm2835aux.c58
-rw-r--r--drivers/spi/spi-rspi.c9
-rw-r--r--drivers/ssb/bridge_pcmcia_80211.c9
-rw-r--r--drivers/staging/rtl8188eu/core/rtw_xmit.c9
-rw-r--r--drivers/staging/rtl8188eu/include/rtw_xmit.h2
-rw-r--r--drivers/staging/rtl8723bs/core/rtw_xmit.c14
-rw-r--r--drivers/staging/rtl8723bs/include/rtw_xmit.h2
-rw-r--r--drivers/thermal/int340x_thermal/int3400_thermal.c21
-rw-r--r--drivers/thermal/intel_soc_dts_thermal.c2
-rw-r--r--drivers/tty/n_r3964.c16
-rw-r--r--drivers/tty/serial/8250/8250_pxa.c4
-rw-r--r--drivers/tty/serial/ar933x_uart.c24
-rw-r--r--drivers/tty/serial/sc16is7xx.c14
-rw-r--r--drivers/tty/serial/xilinx_uartps.c2
-rw-r--r--drivers/tty/tty_buffer.c2
-rw-r--r--drivers/tty/vt/vt.c2
-rw-r--r--drivers/usb/class/cdc-acm.c32
-rw-r--r--drivers/usb/core/driver.c13
-rw-r--r--drivers/usb/core/message.c4
-rw-r--r--drivers/usb/dwc2/gadget.c1
-rw-r--r--drivers/usb/dwc3/core.c2
-rw-r--r--drivers/usb/gadget/udc/net2272.c1
-rw-r--r--drivers/usb/gadget/udc/net2280.c8
-rw-r--r--drivers/usb/host/u132-hcd.c3
-rw-r--r--drivers/usb/misc/usb251xb.c2
-rw-r--r--drivers/usb/misc/yurex.c1
-rw-r--r--drivers/usb/serial/f81232.c39
-rw-r--r--drivers/usb/serial/generic.c39
-rw-r--r--drivers/usb/storage/realtek_cr.c13
-rw-r--r--drivers/usb/storage/scsiglue.c26
-rw-r--r--drivers/usb/storage/uas.c35
-rw-r--r--drivers/usb/usbip/stub_rx.c12
-rw-r--r--drivers/usb/usbip/usbip_common.h7
-rw-r--r--drivers/vfio/mdev/mdev_core.c11
-rw-r--r--drivers/vfio/pci/vfio_pci.c23
-rw-r--r--drivers/vhost/vsock.c22
-rw-r--r--drivers/video/fbdev/omap2/omapfb/dss/omapdss-boot-init.c4
-rw-r--r--drivers/virtio/virtio_pci_common.c8
-rw-r--r--drivers/virtio/virtio_ring.c2
-rw-r--r--drivers/w1/masters/ds2490.c6
-rw-r--r--fs/block_dev.c3
-rw-r--r--fs/btrfs/backref.c9
-rw-r--r--fs/btrfs/delayed-ref.c475
-rw-r--r--fs/btrfs/delayed-ref.h163
-rw-r--r--fs/btrfs/disk-io.c22
-rw-r--r--fs/btrfs/extent-tree.c410
-rw-r--r--fs/btrfs/root-tree.c13
-rw-r--r--fs/ceph/dir.c6
-rw-r--r--fs/ceph/inode.c2
-rw-r--r--fs/ceph/mds_client.c70
-rw-r--r--fs/ceph/snap.c7
-rw-r--r--fs/ext4/super.c4
-rw-r--r--fs/nfs/nfs4proc.c9
-rw-r--r--fs/proc/base.c6
-rw-r--r--fs/proc/kcore.c23
-rw-r--r--fs/xfs/libxfs/xfs_sb.c21
-rw-r--r--fs/xfs/xfs_bmap_util.c11
-rw-r--r--fs/xfs/xfs_file.c50
-rw-r--r--fs/xfs/xfs_inode.h4
-rw-r--r--fs/xfs/xfs_iops.c4
-rw-r--r--fs/xfs/xfs_mount.c80
-rw-r--r--fs/xfs/xfs_mount.h1
-rw-r--r--include/acpi/ghes.h2
-rw-r--r--include/linux/bitops.h21
-rw-r--r--include/linux/bits.h26
-rw-r--r--include/linux/cpu.h2
-rw-r--r--include/linux/crc64.h11
-rw-r--r--include/linux/genhd.h7
-rw-r--r--include/linux/kernel.h4
-rw-r--r--include/linux/platform_data/elm.h2
-rw-r--r--include/linux/pwm.h5
-rw-r--r--include/linux/usb.h3
-rw-r--r--include/linux/virtio_ring.h2
-rw-r--r--include/net/bluetooth/hci_core.h3
-rw-r--r--include/net/sctp/sctp.h3
-rw-r--r--include/net/smc.h3
-rw-r--r--include/sound/core.h16
-rw-r--r--include/sound/seq_kernel.h5
-rw-r--r--include/trace/events/bcache.h27
-rw-r--r--include/trace/events/btrfs.h13
-rw-r--r--include/uapi/drm/i915_drm.h2
-rw-r--r--include/uapi/linux/bcache.h12
-rw-r--r--include/uapi/linux/input-event-codes.h1
-rw-r--r--kernel/auditsc.c10
-rw-r--r--kernel/sysctl.c16
-rw-r--r--lib/.gitignore2
-rw-r--r--lib/Kconfig8
-rw-r--r--lib/Makefile11
-rw-r--r--lib/crc64.c56
-rw-r--r--lib/gen_crc64table.c66
-rw-r--r--net/bluetooth/hci_conn.c8
-rw-r--r--net/bluetooth/hidp/sock.c1
-rw-r--r--net/bridge/netfilter/ebt_among.c55
-rw-r--r--net/core/dev.c2
-rw-r--r--net/dsa/legacy.c4
-rw-r--r--net/ipv4/esp4.c1
-rw-r--r--net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c14
-rw-r--r--net/ipv4/netfilter/nf_socket_ipv4.c6
-rw-r--r--net/ipv6/esp6.c3
-rw-r--r--net/ipv6/netfilter/nf_socket_ipv6.c6
-rw-r--r--net/openvswitch/conntrack.c6
-rw-r--r--net/openvswitch/flow_netlink.c4
-rw-r--r--net/packet/af_packet.c24
-rw-r--r--net/rds/tcp.c2
-rw-r--r--net/sctp/outqueue.c6
-rw-r--r--net/sctp/socket.c29
-rw-r--r--net/smc/af_smc.c125
-rw-r--r--net/smc/smc_cdc.c52
-rw-r--r--net/smc/smc_cdc.h62
-rw-r--r--net/smc/smc_clc.c2
-rw-r--r--net/smc/smc_close.c16
-rw-r--r--net/smc/smc_core.c17
-rw-r--r--net/smc/smc_core.h20
-rw-r--r--net/smc/smc_ib.c31
-rw-r--r--net/smc/smc_ib.h4
-rw-r--r--net/smc/smc_llc.c3
-rw-r--r--net/smc/smc_netns.h20
-rw-r--r--net/smc/smc_pnet.c671
-rw-r--r--net/smc/smc_pnet.h13
-rw-r--r--net/smc/smc_tx.c81
-rw-r--r--net/smc/smc_wr.c56
-rw-r--r--net/smc/smc_wr.h1
-rw-r--r--net/vmw_vsock/virtio_transport.c29
-rw-r--r--net/vmw_vsock/virtio_transport_common.c22
-rw-r--r--net/xfrm/xfrm_policy.c8
-rw-r--r--net/xfrm/xfrm_state.c1
-rwxr-xr-xscripts/recordmcount.pl2
-rw-r--r--scripts/selinux/genheaders/genheaders.c1
-rw-r--r--scripts/selinux/mdp/mdp.c1
-rw-r--r--security/selinux/include/classmap.h1
-rw-r--r--sound/core/init.c22
-rw-r--r--sound/core/oss/mixer_oss.c16
-rw-r--r--sound/core/seq/oss/seq_oss_device.h10
-rw-r--r--sound/core/seq/oss/seq_oss_rw.c11
-rw-r--r--sound/core/seq/oss/seq_oss_writeq.c2
-rw-r--r--sound/core/seq/seq_clientmgr.c128
-rw-r--r--sound/core/seq/seq_clientmgr.h8
-rw-r--r--sound/core/seq/seq_fifo.c14
-rw-r--r--sound/core/seq/seq_memory.c20
-rw-r--r--sound/core/seq/seq_ports.c30
-rw-r--r--sound/core/seq/seq_ports.h5
-rw-r--r--sound/core/sound.c5
-rw-r--r--sound/core/timer.c181
-rw-r--r--sound/last.c10
-rw-r--r--sound/pci/emu10k1/emu10k1_main.c16
-rw-r--r--sound/pci/hda/hda_intel.c6
-rw-r--r--sound/pci/hda/patch_hdmi.c11
-rw-r--r--sound/pci/hda/patch_realtek.c5
-rw-r--r--sound/soc/codecs/cs4270.c1
-rw-r--r--sound/soc/codecs/hdmi-codec.c118
-rw-r--r--sound/soc/codecs/max98090.c12
-rw-r--r--sound/soc/codecs/nau8810.c4
-rw-r--r--sound/soc/codecs/nau8824.c46
-rw-r--r--sound/soc/codecs/rt5677-spi.c35
-rw-r--r--sound/soc/codecs/tlv320aic32x4.c2
-rw-r--r--sound/soc/codecs/wm_adsp.c11
-rw-r--r--sound/soc/fsl/fsl_esai.c1
-rw-r--r--sound/soc/intel/common/sst-firmware.c8
-rw-r--r--sound/soc/samsung/odroid.c4
-rw-r--r--sound/soc/soc-pcm.c11
-rw-r--r--sound/soc/stm/stm32_sai_sub.c2
-rw-r--r--sound/usb/line6/toneport.c8
-rw-r--r--sound/usb/mixer.c6
-rw-r--r--sound/usb/usx2y/usbusx2y.c4
-rw-r--r--tools/power/x86/turbostat/Makefile2
-rw-r--r--tools/power/x86/turbostat/turbostat.c46
370 files changed, 5422 insertions, 2963 deletions
diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu
index 6cae60929cb6..1afba2acce34 100644
--- a/Documentation/ABI/testing/sysfs-devices-system-cpu
+++ b/Documentation/ABI/testing/sysfs-devices-system-cpu
@@ -380,6 +380,7 @@ What: /sys/devices/system/cpu/vulnerabilities
/sys/devices/system/cpu/vulnerabilities/spectre_v2
/sys/devices/system/cpu/vulnerabilities/spec_store_bypass
/sys/devices/system/cpu/vulnerabilities/l1tf
+ /sys/devices/system/cpu/vulnerabilities/mds
Date: January 2018
Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org>
Description: Information about CPU vulnerabilities
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index b557af2832a8..9fb9ea189121 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -2209,6 +2209,30 @@
Format: <first>,<last>
Specifies range of consoles to be captured by the MDA.
+ mds= [X86,INTEL]
+ Control mitigation for the Micro-architectural Data
+ Sampling (MDS) vulnerability.
+
+ Certain CPUs are vulnerable to an exploit against CPU
+ internal buffers which can forward information to a
+ disclosure gadget under certain conditions.
+
+ In vulnerable processors, the speculatively
+ forwarded data can be used in a cache side channel
+ attack, to access data to which the attacker does
+ not have direct access.
+
+ This parameter controls the MDS mitigation. The
+ options are:
+
+ full - Enable MDS mitigation on vulnerable CPUs
+ full,nosmt - Enable MDS mitigation and disable
+ SMT on vulnerable CPUs
+ off - Unconditionally disable MDS mitigation
+
+ Not specifying this option is equivalent to
+ mds=full.
+
mem=nn[KMG] [KNL,BOOT] Force usage of a specific amount of memory
Amount of memory to be used when the kernel is not able
to see the whole system memory or for test.
@@ -2374,6 +2398,7 @@
spectre_v2_user=off [X86]
spec_store_bypass_disable=off [X86,PPC]
l1tf=off [X86]
+ mds=off [X86]
auto (default)
Mitigate all CPU vulnerabilities, but leave SMT
@@ -2388,6 +2413,7 @@
if needed. This is for users who always want to
be fully mitigated, even if it means losing SMT.
Equivalent to: l1tf=flush,nosmt [X86]
+ mds=full,nosmt [X86]
mminit_loglevel=
[KNL] When CONFIG_DEBUG_MEMORY_INIT is set, this
diff --git a/Documentation/devicetree/bindings/net/ethernet.txt b/Documentation/devicetree/bindings/net/ethernet.txt
index d4abe9a98109..905c87565d24 100644
--- a/Documentation/devicetree/bindings/net/ethernet.txt
+++ b/Documentation/devicetree/bindings/net/ethernet.txt
@@ -29,7 +29,7 @@ The following properties are common to the Ethernet controllers:
* "smii"
* "xgmii"
* "trgmii"
- * "2000base-x",
+ * "1000base-x",
* "2500base-x",
* "rxaui"
* "xaui"
diff --git a/Documentation/driver-api/usb/power-management.rst b/Documentation/driver-api/usb/power-management.rst
index 79beb807996b..4a74cf6f2797 100644
--- a/Documentation/driver-api/usb/power-management.rst
+++ b/Documentation/driver-api/usb/power-management.rst
@@ -370,11 +370,15 @@ autosuspend the interface's device. When the usage counter is = 0
then the interface is considered to be idle, and the kernel may
autosuspend the device.
-Drivers need not be concerned about balancing changes to the usage
-counter; the USB core will undo any remaining "get"s when a driver
-is unbound from its interface. As a corollary, drivers must not call
-any of the ``usb_autopm_*`` functions after their ``disconnect``
-routine has returned.
+Drivers must be careful to balance their overall changes to the usage
+counter. Unbalanced "get"s will remain in effect when a driver is
+unbound from its interface, preventing the device from going into
+runtime suspend should the interface be bound to a driver again. On
+the other hand, drivers are allowed to achieve this balance by calling
+the ``usb_autopm_*`` functions even after their ``disconnect`` routine
+has returned -- say from within a work-queue routine -- provided they
+retain an active reference to the interface (via ``usb_get_intf`` and
+``usb_put_intf``).
Drivers using the async routines are responsible for their own
synchronization and mutual exclusion.
diff --git a/Documentation/index.rst b/Documentation/index.rst
index bc67dbf76eb0..102bb6987a9e 100644
--- a/Documentation/index.rst
+++ b/Documentation/index.rst
@@ -34,6 +34,7 @@ the kernel interface as seen by application developers.
:maxdepth: 2
userspace-api/index
+ x86/index
Introduction to kernel development
diff --git a/Documentation/kmsg/IPVS b/Documentation/kmsg/IPVS
index b5ee24309a79..39dd5b30a70d 100644
--- a/Documentation/kmsg/IPVS
+++ b/Documentation/kmsg/IPVS
@@ -79,3 +79,6 @@
/*? Text: "%s selects TX queue %d, but real number of TX queues is %d\n" */
/*? Text: "Unknown mcast interface: %s\n" */
/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */
+/*? Text: "%s: SME is active, device will require DMA bounce buffers\n" */
+/*? Text: "%s(): request for already hashed, called from %pS\n" */
+/*? Text: "%s(): request for unhash flagged, called from %pS\n" */
diff --git a/Documentation/kmsg/ism b/Documentation/kmsg/ism
new file mode 100644
index 000000000000..9612e30a12c2
--- /dev/null
+++ b/Documentation/kmsg/ism
@@ -0,0 +1,2 @@
+/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */
+/*? Text: "%s: SME is active, device will require DMA bounce buffers\n" */
diff --git a/Documentation/kmsg/s390/aes_s390 b/Documentation/kmsg/s390/aes_s390
index e1a7451b1c77..eb1a0acbcd2c 100644
--- a/Documentation/kmsg/s390/aes_s390
+++ b/Documentation/kmsg/s390/aes_s390
@@ -43,3 +43,4 @@
* None.
*/
/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */
+/*? Text: "%s: SME is active, device will require DMA bounce buffers\n" */
diff --git a/Documentation/kmsg/s390/af_iucv b/Documentation/kmsg/s390/af_iucv
index 6d5b39ade745..4332ce15dafb 100644
--- a/Documentation/kmsg/s390/af_iucv
+++ b/Documentation/kmsg/s390/af_iucv
@@ -21,3 +21,4 @@
/*? Text: "flen=%u proglen=%u pass=%u image=%pK from=%s pid=%d\n" */
/*? Text: "%s selects TX queue %d, but real number of TX queues is %d\n" */
/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */
+/*? Text: "%s: SME is active, device will require DMA bounce buffers\n" */
diff --git a/Documentation/kmsg/s390/appldata b/Documentation/kmsg/s390/appldata
index 1129f96c313c..4d354c94aaa4 100644
--- a/Documentation/kmsg/s390/appldata
+++ b/Documentation/kmsg/s390/appldata
@@ -89,3 +89,4 @@
/*? Text: "netif_stop_queue() cannot be called before register_netdev()\n" */
/*? Text: "%s selects TX queue %d, but real number of TX queues is %d\n" */
/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */
+/*? Text: "%s: SME is active, device will require DMA bounce buffers\n" */
diff --git a/Documentation/kmsg/s390/bpf_jit b/Documentation/kmsg/s390/bpf_jit
index da2fb17c6783..df7fb48ee02b 100644
--- a/Documentation/kmsg/s390/bpf_jit
+++ b/Documentation/kmsg/s390/bpf_jit
@@ -14,3 +14,4 @@
* Report this problem and the error message to your support organization.
*/
/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */
+/*? Text: "%s: SME is active, device will require DMA bounce buffers\n" */
diff --git a/Documentation/kmsg/s390/cio b/Documentation/kmsg/s390/cio
index e90aae08d87b..6ee5518d1650 100644
--- a/Documentation/kmsg/s390/cio
+++ b/Documentation/kmsg/s390/cio
@@ -245,3 +245,4 @@
* Report the problem to your support organization.
*/
/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */
+/*? Text: "%s: SME is active, device will require DMA bounce buffers\n" */
diff --git a/Documentation/kmsg/s390/cpcmd b/Documentation/kmsg/s390/cpcmd
index 4a1a308249e7..f9b5f84d4739 100644
--- a/Documentation/kmsg/s390/cpcmd
+++ b/Documentation/kmsg/s390/cpcmd
@@ -15,3 +15,4 @@
* machine.
*/
/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */
+/*? Text: "%s: SME is active, device will require DMA bounce buffers\n" */
diff --git a/Documentation/kmsg/s390/cpu b/Documentation/kmsg/s390/cpu
index d4701972e1b6..34b533677845 100644
--- a/Documentation/kmsg/s390/cpu
+++ b/Documentation/kmsg/s390/cpu
@@ -52,3 +52,4 @@
* does not include all CPU information.
*/
/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */
+/*? Text: "%s: SME is active, device will require DMA bounce buffers\n" */
diff --git a/Documentation/kmsg/s390/crc32-vx b/Documentation/kmsg/s390/crc32-vx
index 4553d8b236cc..9612e30a12c2 100644
--- a/Documentation/kmsg/s390/crc32-vx
+++ b/Documentation/kmsg/s390/crc32-vx
@@ -1 +1,2 @@
/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */
+/*? Text: "%s: SME is active, device will require DMA bounce buffers\n" */
diff --git a/Documentation/kmsg/s390/ctcm b/Documentation/kmsg/s390/ctcm
index 9437da9c9ffe..3a7d2b1956f0 100644
--- a/Documentation/kmsg/s390/ctcm
+++ b/Documentation/kmsg/s390/ctcm
@@ -200,3 +200,4 @@
/*? Text: "flen=%u proglen=%u pass=%u image=%pK from=%s pid=%d\n" */
/*? Text: "%s selects TX queue %d, but real number of TX queues is %d\n" */
/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */
+/*? Text: "%s: SME is active, device will require DMA bounce buffers\n" */
diff --git a/Documentation/kmsg/s390/dasd b/Documentation/kmsg/s390/dasd
index 8326344c27cb..a4a9bced1bfa 100644
--- a/Documentation/kmsg/s390/dasd
+++ b/Documentation/kmsg/s390/dasd
@@ -691,3 +691,4 @@
* or set the sysfs 'use_diag' attribute of the DASD to 0 to switch off DIAG.
*/
/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */
+/*? Text: "%s: SME is active, device will require DMA bounce buffers\n" */
diff --git a/Documentation/kmsg/s390/dasd-eckd b/Documentation/kmsg/s390/dasd-eckd
index ab1f2f08a34e..402cdb20795b 100644
--- a/Documentation/kmsg/s390/dasd-eckd
+++ b/Documentation/kmsg/s390/dasd-eckd
@@ -2163,4 +2163,46 @@
* to the path_reset sysfs attribute of the device.
* If the problem persists, report it to your support organization.
*/
+
/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */
+
+/*?
+ * Text: "%s: Path %x.%02x (pathmask %02x) is operational despite excessive IFCCs\n"
+ * Severity: Error
+ * Parameter:
+ * @1: bus ID of the DASD
+ * @2: cssid
+ * @3: chpid
+ * @4: logical path mask
+ * Description:
+ * The threshold value for interface or channel control checks (IFCCs) for the
+ * channel path was exceeded.
+ * The channel path remains operational because the autodisable feature for
+ * defective channel paths is not active.
+ * Defective channel paths can adversely affect performance.
+ * User action:
+ * Ensure that the cabling between the storage server and the mainframe
+ * system is securely in place.
+ * If you observe performance impacts, consider setting the channel path offline.
+ * By default, the DASD device driver disables defective channel paths for you.
+ * You can restore this default, for example, by writing '1' to the
+ * path_autodisable sysfs attribute.
+ * If the problem persists, report it to your support organization.
+ */
+
+/*?
+ * Text: "%s: Last path %x.%02x (pathmask %02x) is operational despite excessive IFCCs\n"
+ * Severity: Error
+ * Parameter:
+ * @1: bus ID of the DASD
+ * @2: cssid
+ * @3: chpid
+ * @4: logical path mask
+ * Description:
+ * The threshold value for interface or channel control checks (IFCCs) for the channel path was exceeded.
+ * The channel path was not removed from regular operations because it is the last remaining channel path for the DASD.
+ * User action:
+ * Ensure that the cabling between the storage server and the mainframe
+ * system is securely in place.
+ * If the problem persists, report it to your support organization.
+ */
diff --git a/Documentation/kmsg/s390/diag288_wdt b/Documentation/kmsg/s390/diag288_wdt
index 7334dac2ed15..e24de4901e92 100644
--- a/Documentation/kmsg/s390/diag288_wdt
+++ b/Documentation/kmsg/s390/diag288_wdt
@@ -64,3 +64,4 @@
* contact your support organization.
*/
/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */
+/*? Text: "%s: SME is active, device will require DMA bounce buffers\n" */
diff --git a/Documentation/kmsg/s390/extmem b/Documentation/kmsg/s390/extmem
index 2e76ede358eb..eefc7bfd603a 100644
--- a/Documentation/kmsg/s390/extmem
+++ b/Documentation/kmsg/s390/extmem
@@ -292,3 +292,4 @@
* Ensure that the DCSS range is defined below the kernel mapping range.
*/
/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */
+/*? Text: "%s: SME is active, device will require DMA bounce buffers\n" */
diff --git a/Documentation/kmsg/s390/hmcdrv b/Documentation/kmsg/s390/hmcdrv
index 402244284cd9..265b12113af1 100644
--- a/Documentation/kmsg/s390/hmcdrv
+++ b/Documentation/kmsg/s390/hmcdrv
@@ -20,3 +20,4 @@
* the cache size specification.
*/
/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */
+/*? Text: "%s: SME is active, device will require DMA bounce buffers\n" */
diff --git a/Documentation/kmsg/s390/hugetlb b/Documentation/kmsg/s390/hugetlb
index 64856a89fa1b..639bd5ab4f76 100644
--- a/Documentation/kmsg/s390/hugetlb
+++ b/Documentation/kmsg/s390/hugetlb
@@ -11,3 +11,4 @@
* Specify "2G" for 2 GB huge pages. These are supported as of zEC12
* and zBC12 machines.
*/
+/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */
diff --git a/Documentation/kmsg/s390/hypfs b/Documentation/kmsg/s390/hypfs
index 428f9390c8da..fef7cff029a0 100644
--- a/Documentation/kmsg/s390/hypfs
+++ b/Documentation/kmsg/s390/hypfs
@@ -55,3 +55,4 @@
/*? Text: "Hypervisor filesystem mounted\n" */
/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */
+/*? Text: "%s: SME is active, device will require DMA bounce buffers\n" */
diff --git a/Documentation/kmsg/s390/lcs b/Documentation/kmsg/s390/lcs
index 6b9c68b56bf3..75c25fd4b42b 100644
--- a/Documentation/kmsg/s390/lcs
+++ b/Documentation/kmsg/s390/lcs
@@ -167,3 +167,4 @@
/*? Text: "flen=%u proglen=%u pass=%u image=%pK from=%s pid=%d\n" */
/*? Text: "%s selects TX queue %d, but real number of TX queues is %d\n" */
/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */
+/*? Text: "%s: SME is active, device will require DMA bounce buffers\n" */
diff --git a/Documentation/kmsg/s390/monwriter b/Documentation/kmsg/s390/monwriter
index aaddda3e80e0..998ded58e24d 100644
--- a/Documentation/kmsg/s390/monwriter
+++ b/Documentation/kmsg/s390/monwriter
@@ -15,3 +15,4 @@
* in "z/VM CP Programming Services".
*/
/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */
+/*? Text: "%s: SME is active, device will require DMA bounce buffers\n" */
diff --git a/Documentation/kmsg/s390/netiucv b/Documentation/kmsg/s390/netiucv
index e805b1c12139..1ad8c5ee5194 100644
--- a/Documentation/kmsg/s390/netiucv
+++ b/Documentation/kmsg/s390/netiucv
@@ -154,3 +154,4 @@
/*? Text: "flen=%u proglen=%u pass=%u image=%pK from=%s pid=%d\n" */
/*? Text: "%s selects TX queue %d, but real number of TX queues is %d\n" */
/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */
+/*? Text: "%s: SME is active, device will require DMA bounce buffers\n" */
diff --git a/Documentation/kmsg/s390/paes_s390 b/Documentation/kmsg/s390/paes_s390
index f28333858ac7..9612e30a12c2 100644
--- a/Documentation/kmsg/s390/paes_s390
+++ b/Documentation/kmsg/s390/paes_s390
@@ -1 +1,2 @@
-/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */ \ No newline at end of file
+/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */
+/*? Text: "%s: SME is active, device will require DMA bounce buffers\n" */
diff --git a/Documentation/kmsg/s390/perf b/Documentation/kmsg/s390/perf
index 13325a6f5121..1a0fb32ec40b 100644
--- a/Documentation/kmsg/s390/perf
+++ b/Documentation/kmsg/s390/perf
@@ -88,3 +88,4 @@
* process has ended.
*/
/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */
+/*? Text: "%s: SME is active, device will require DMA bounce buffers\n" */
diff --git a/Documentation/kmsg/s390/qeth b/Documentation/kmsg/s390/qeth
index 09ae28c2e5fd..68b7c64fff33 100644
--- a/Documentation/kmsg/s390/qeth
+++ b/Documentation/kmsg/s390/qeth
@@ -966,3 +966,4 @@
* sysfs attribute of the device.
*/
/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */
+/*? Text: "%s: SME is active, device will require DMA bounce buffers\n" */
diff --git a/Documentation/kmsg/s390/setup b/Documentation/kmsg/s390/setup
index c90e60317648..df12da42896a 100644
--- a/Documentation/kmsg/s390/setup
+++ b/Documentation/kmsg/s390/setup
@@ -163,3 +163,4 @@
* None.
*/
/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */
+/*? Text: "%s: SME is active, device will require DMA bounce buffers\n" */
diff --git a/Documentation/kmsg/s390/vmur b/Documentation/kmsg/s390/vmur
index 50ef00d48ffa..db9f7cf9fe6d 100644
--- a/Documentation/kmsg/s390/vmur
+++ b/Documentation/kmsg/s390/vmur
@@ -46,3 +46,4 @@
/*? Text: "%s loaded.\n" */
/*? Text: "%s unloaded.\n" */
/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */
+/*? Text: "%s: SME is active, device will require DMA bounce buffers\n" */
diff --git a/Documentation/kmsg/s390/zfcp b/Documentation/kmsg/s390/zfcp
index 9d271b2e4c80..95e43dca46ab 100644
--- a/Documentation/kmsg/s390/zfcp
+++ b/Documentation/kmsg/s390/zfcp
@@ -707,3 +707,5 @@
* support organization of the storage system.
*/
/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */
+/*? Text: "%s: SME is active, device will require DMA bounce buffers\n" */
+/*? Text: "Invalid address limit on user-mode return" */
diff --git a/Documentation/kmsg/s390/zpci b/Documentation/kmsg/s390/zpci
index aa3310206a62..aafe2f5e350a 100644
--- a/Documentation/kmsg/s390/zpci
+++ b/Documentation/kmsg/s390/zpci
@@ -40,3 +40,4 @@
* If the problem persists, contact your support organization.
*/
/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */
+/*? Text: "%s: SME is active, device will require DMA bounce buffers\n" */
diff --git a/Documentation/kmsg/s390/zram b/Documentation/kmsg/s390/zram
new file mode 100644
index 000000000000..ba0784553a6c
--- /dev/null
+++ b/Documentation/kmsg/s390/zram
@@ -0,0 +1,2 @@
+/*? Text: "Can't setup backing device for initialized device\n" */
+/*? Text: "setup backing device %s\n" */
diff --git a/Documentation/kmsg/sbp_target b/Documentation/kmsg/sbp_target
index e9356cf802ac..dda016beff08 100644
--- a/Documentation/kmsg/sbp_target
+++ b/Documentation/kmsg/sbp_target
@@ -46,4 +46,5 @@
/*? Text: "unlink LUN: failed to update unit directory\n" */
/*? Text: "flen=%u proglen=%u pass=%u image=%pK from=%s pid=%d\n" */
/*? Text: "%s selects TX queue %d, but real number of TX queues is %d\n" */
-/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */ \ No newline at end of file
+/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */
+/*? Text: "%s: SME is active, device will require DMA bounce buffers\n" */
diff --git a/Documentation/kmsg/smc b/Documentation/kmsg/smc
index 12f591b1ffa4..815c3820c009 100644
--- a/Documentation/kmsg/smc
+++ b/Documentation/kmsg/smc
@@ -1,8 +1,10 @@
/*? Text: "%s: smc_cdc_init fails with %d\n" */
-/*? Text: "%s: proto_register fails with %d\n" */
+/*? Text: "%s: proto_register(v4) fails with %d\n" */
+/*? Text: "%s: proto_register(v6) fails with %d\n" */
/*? Text: "%s: smc_llc_init fails with %d\n" */
/*? Text: "%s: %d output lines suppressed due to ratelimiting\n" */
/*? Text: "flen=%u proglen=%u pass=%u image=%pK from=%s pid=%d\n" */
/*? Text: "%s selects TX queue %d, but real number of TX queues is %d\n" */
/*? Text: "%s: sock_register fails with %d\n" */
/*? Text: "%s: ib_register fails with %d\n" */
+/*? Text: "%s: SME is active, device will require DMA bounce buffers\n" */
diff --git a/Documentation/x86/conf.py b/Documentation/x86/conf.py
new file mode 100644
index 000000000000..33c5c3142e20
--- /dev/null
+++ b/Documentation/x86/conf.py
@@ -0,0 +1,10 @@
+# -*- coding: utf-8; mode: python -*-
+
+project = "X86 architecture specific documentation"
+
+tags.add("subproject")
+
+latex_documents = [
+ ('index', 'x86.tex', project,
+ 'The kernel development community', 'manual'),
+]
diff --git a/Documentation/x86/index.rst b/Documentation/x86/index.rst
new file mode 100644
index 000000000000..ef389dcf1b1d
--- /dev/null
+++ b/Documentation/x86/index.rst
@@ -0,0 +1,8 @@
+==========================
+x86 architecture specifics
+==========================
+
+.. toctree::
+ :maxdepth: 1
+
+ mds
diff --git a/Documentation/x86/mds.rst b/Documentation/x86/mds.rst
new file mode 100644
index 000000000000..7e5b1d2fc29c
--- /dev/null
+++ b/Documentation/x86/mds.rst
@@ -0,0 +1,224 @@
+Microarchitectural Data Sampling (MDS) mitigation
+=================================================
+
+.. _mds:
+
+Overview
+--------
+
+Microarchitectural Data Sampling (MDS) is a family of side channel attacks
+on internal buffers in Intel CPUs. The variants are:
+
+ - Microarchitectural Store Buffer Data Sampling (MSBDS) (CVE-2018-12126)
+ - Microarchitectural Fill Buffer Data Sampling (MFBDS) (CVE-2018-12130)
+ - Microarchitectural Load Port Data Sampling (MLPDS) (CVE-2018-12127)
+
+MSBDS leaks Store Buffer Entries which can be speculatively forwarded to a
+dependent load (store-to-load forwarding) as an optimization. The forward
+can also happen to a faulting or assisting load operation for a different
+memory address, which can be exploited under certain conditions. Store
+buffers are partitioned between Hyper-Threads so cross thread forwarding is
+not possible. But if a thread enters or exits a sleep state the store
+buffer is repartitioned which can expose data from one thread to the other.
+
+MFBDS leaks Fill Buffer Entries. Fill buffers are used internally to manage
+L1 miss situations and to hold data which is returned or sent in response
+to a memory or I/O operation. Fill buffers can forward data to a load
+operation and also write data to the cache. When the fill buffer is
+deallocated it can retain the stale data of the preceding operations which
+can then be forwarded to a faulting or assisting load operation, which can
+be exploited under certain conditions. Fill buffers are shared between
+Hyper-Threads so cross thread leakage is possible.
+
+MLPDS leaks Load Port Data. Load ports are used to perform load operations
+from memory or I/O. The received data is then forwarded to the register
+file or a subsequent operation. In some implementations the Load Port can
+contain stale data from a previous operation which can be forwarded to
+faulting or assisting loads under certain conditions, which again can be
+exploited eventually. Load ports are shared between Hyper-Threads so cross
+thread leakage is possible.
+
+
+Exposure assumptions
+--------------------
+
+It is assumed that attack code resides in user space or in a guest with one
+exception. The rationale behind this assumption is that the code construct
+needed for exploiting MDS requires:
+
+ - to control the load to trigger a fault or assist
+
+ - to have a disclosure gadget which exposes the speculatively accessed
+ data for consumption through a side channel.
+
+ - to control the pointer through which the disclosure gadget exposes the
+ data
+
+The existence of such a construct in the kernel cannot be excluded with
+100% certainty, but the complexity involved makes it extremly unlikely.
+
+There is one exception, which is untrusted BPF. The functionality of
+untrusted BPF is limited, but it needs to be thoroughly investigated
+whether it can be used to create such a construct.
+
+
+Mitigation strategy
+-------------------
+
+All variants have the same mitigation strategy at least for the single CPU
+thread case (SMT off): Force the CPU to clear the affected buffers.
+
+This is achieved by using the otherwise unused and obsolete VERW
+instruction in combination with a microcode update. The microcode clears
+the affected CPU buffers when the VERW instruction is executed.
+
+For virtualization there are two ways to achieve CPU buffer
+clearing. Either the modified VERW instruction or via the L1D Flush
+command. The latter is issued when L1TF mitigation is enabled so the extra
+VERW can be avoided. If the CPU is not affected by L1TF then VERW needs to
+be issued.
+
+If the VERW instruction with the supplied segment selector argument is
+executed on a CPU without the microcode update there is no side effect
+other than a small number of pointlessly wasted CPU cycles.
+
+This does not protect against cross Hyper-Thread attacks except for MSBDS
+which is only exploitable cross Hyper-thread when one of the Hyper-Threads
+enters a C-state.
+
+The kernel provides a function to invoke the buffer clearing:
+
+ mds_clear_cpu_buffers()
+
+The mitigation is invoked on kernel/userspace, hypervisor/guest and C-state
+(idle) transitions.
+
+As a special quirk to address virtualization scenarios where the host has
+the microcode updated, but the hypervisor does not (yet) expose the
+MD_CLEAR CPUID bit to guests, the kernel issues the VERW instruction in the
+hope that it might actually clear the buffers. The state is reflected
+accordingly.
+
+According to current knowledge additional mitigations inside the kernel
+itself are not required because the necessary gadgets to expose the leaked
+data cannot be controlled in a way which allows exploitation from malicious
+user space or VM guests.
+
+Kernel internal mitigation modes
+--------------------------------
+
+ ======= ============================================================
+ off Mitigation is disabled. Either the CPU is not affected or
+ mds=off is supplied on the kernel command line
+
+ full Mitigation is eanbled. CPU is affected and MD_CLEAR is
+ advertised in CPUID.
+
+ vmwerv Mitigation is enabled. CPU is affected and MD_CLEAR is not
+ advertised in CPUID. That is mainly for virtualization
+ scenarios where the host has the updated microcode but the
+ hypervisor does not expose MD_CLEAR in CPUID. It's a best
+ effort approach without guarantee.
+
+ full,nosmt The same as mds=full, with SMT disabled on vulnerable
+ CPUs. This is the complete mitigation.
+
+ ======= ============================================================
+
+If the CPU is affected and mds=off is not supplied on the kernel command
+line then the kernel selects the appropriate mitigation mode depending on
+the availability of the MD_CLEAR CPUID bit.
+
+Mitigation points
+-----------------
+
+1. Return to user space
+^^^^^^^^^^^^^^^^^^^^^^^
+
+ When transitioning from kernel to user space the CPU buffers are flushed
+ on affected CPUs when the mitigation is not disabled on the kernel
+ command line. The migitation is enabled through the static key
+ mds_user_clear.
+
+ The mitigation is invoked in prepare_exit_to_usermode() which covers
+ most of the kernel to user space transitions. There are a few exceptions
+ which are not invoking prepare_exit_to_usermode() on return to user
+ space. These exceptions use the paranoid exit code.
+
+ - Non Maskable Interrupt (NMI):
+
+ Access to sensible data like keys, credentials in the NMI context is
+ mostly theoretical: The CPU can do prefetching or execute a
+ misspeculated code path and thereby fetching data which might end up
+ leaking through a buffer.
+
+ But for mounting other attacks the kernel stack address of the task is
+ already valuable information. So in full mitigation mode, the NMI is
+ mitigated on the return from do_nmi() to provide almost complete
+ coverage.
+
+ - Double fault (#DF):
+
+ A double fault is usually fatal, but the ESPFIX workaround, which can
+ be triggered from user space through modify_ldt(2) is a recoverable
+ double fault. #DF uses the paranoid exit path, so explicit mitigation
+ in the double fault handler is required.
+
+ - Machine Check Exception (#MC):
+
+ Another corner case is a #MC which hits between the CPU buffer clear
+ invocation and the actual return to user. As this still is in kernel
+ space it takes the paranoid exit path which does not clear the CPU
+ buffers. So the #MC handler repopulates the buffers to some
+ extent. Machine checks are not reliably controllable and the window is
+ extremly small so mitigation would just tick a checkbox that this
+ theoretical corner case is covered. To keep the amount of special
+ cases small, ignore #MC.
+
+ - Debug Exception (#DB):
+
+ This takes the paranoid exit path only when the INT1 breakpoint is in
+ kernel space. #DB on a user space address takes the regular exit path,
+ so no extra mitigation required.
+
+
+2. C-State transition
+^^^^^^^^^^^^^^^^^^^^^
+
+ When a CPU goes idle and enters a C-State the CPU buffers need to be
+ cleared on affected CPUs when SMT is active. This addresses the
+ repartitioning of the store buffer when one of the Hyper-Threads enters
+ a C-State.
+
+ When SMT is inactive, i.e. either the CPU does not support it or all
+ sibling threads are offline CPU buffer clearing is not required.
+
+ The idle clearing is enabled on CPUs which are only affected by MSBDS
+ and not by any other MDS variant. The other MDS variants cannot be
+ protected against cross Hyper-Thread attacks because the Fill Buffer and
+ the Load Ports are shared. So on CPUs affected by other variants, the
+ idle clearing would be a window dressing exercise and is therefore not
+ activated.
+
+ The invocation is controlled by the static key mds_idle_clear which is
+ switched depending on the chosen mitigation mode and the SMT state of
+ the system.
+
+ The buffer clear is only invoked before entering the C-State to prevent
+ that stale data from the idling CPU from spilling to the Hyper-Thread
+ sibling after the store buffer got repartitioned and all entries are
+ available to the non idle sibling.
+
+ When coming out of idle the store buffer is partitioned again so each
+ sibling has half of it available. The back from idle CPU could be then
+ speculatively exposed to contents of the sibling. The buffers are
+ flushed either on exit to user space or on VMENTER so malicious code
+ in user space or the guest cannot speculatively access them.
+
+ The mitigation is hooked into all variants of halt()/mwait(), but does
+ not cover the legacy ACPI IO-Port mechanism because the ACPI idle driver
+ has been superseded by the intel_idle driver around 2010 and is
+ preferred on all affected CPUs which are expected to gain the MD_CLEAR
+ functionality in microcode. Aside of that the IO-Port mechanism is a
+ legacy interface which is only used on older systems which are either
+ not affected or do not receive microcode updates anymore.
diff --git a/arch/arm/crypto/aes-neonbs-glue.c b/arch/arm/crypto/aes-neonbs-glue.c
index c76377961444..1bd27ccc2ad0 100644
--- a/arch/arm/crypto/aes-neonbs-glue.c
+++ b/arch/arm/crypto/aes-neonbs-glue.c
@@ -281,6 +281,8 @@ static int __xts_crypt(struct skcipher_request *req,
int err;
err = skcipher_walk_virt(&walk, req, true);
+ if (err)
+ return err;
crypto_cipher_encrypt_one(ctx->tweak_tfm, walk.iv, walk.iv);
diff --git a/arch/x86/crypto/crct10dif-pclmul_glue.c b/arch/x86/crypto/crct10dif-pclmul_glue.c
index cd4df9322501..7bbfe7d35da7 100644
--- a/arch/x86/crypto/crct10dif-pclmul_glue.c
+++ b/arch/x86/crypto/crct10dif-pclmul_glue.c
@@ -76,15 +76,14 @@ static int chksum_final(struct shash_desc *desc, u8 *out)
return 0;
}
-static int __chksum_finup(__u16 *crcp, const u8 *data, unsigned int len,
- u8 *out)
+static int __chksum_finup(__u16 crc, const u8 *data, unsigned int len, u8 *out)
{
if (irq_fpu_usable()) {
kernel_fpu_begin();
- *(__u16 *)out = crc_t10dif_pcl(*crcp, data, len);
+ *(__u16 *)out = crc_t10dif_pcl(crc, data, len);
kernel_fpu_end();
} else
- *(__u16 *)out = crc_t10dif_generic(*crcp, data, len);
+ *(__u16 *)out = crc_t10dif_generic(crc, data, len);
return 0;
}
@@ -93,15 +92,13 @@ static int chksum_finup(struct shash_desc *desc, const u8 *data,
{
struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
- return __chksum_finup(&ctx->crc, data, len, out);
+ return __chksum_finup(ctx->crc, data, len, out);
}
static int chksum_digest(struct shash_desc *desc, const u8 *data,
unsigned int length, u8 *out)
{
- struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
-
- return __chksum_finup(&ctx->crc, data, length, out);
+ return __chksum_finup(0, data, length, out);
}
static struct shash_alg alg = {
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index b84b94ebdab4..60920243d703 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -30,6 +30,7 @@
#include <asm/vdso.h>
#include <linux/uaccess.h>
#include <asm/cpufeature.h>
+#include <asm/nospec-branch.h>
#define CREATE_TRACE_POINTS
#include <trace/events/syscalls.h>
@@ -208,6 +209,8 @@ __visible inline void prepare_exit_to_usermode(struct pt_regs *regs)
#endif
user_enter_irqoff();
+
+ mds_user_clear_cpu_buffers();
}
#define SYSCALL_EXIT_WORK_FLAGS \
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index e597853ee884..9b7b777176bf 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3871,11 +3871,11 @@ __init int intel_pmu_init(void)
pr_cont("Nehalem events, ");
break;
- case INTEL_FAM6_ATOM_PINEVIEW:
- case INTEL_FAM6_ATOM_LINCROFT:
- case INTEL_FAM6_ATOM_PENWELL:
- case INTEL_FAM6_ATOM_CLOVERVIEW:
- case INTEL_FAM6_ATOM_CEDARVIEW:
+ case INTEL_FAM6_ATOM_BONNELL:
+ case INTEL_FAM6_ATOM_BONNELL_MID:
+ case INTEL_FAM6_ATOM_SALTWELL:
+ case INTEL_FAM6_ATOM_SALTWELL_MID:
+ case INTEL_FAM6_ATOM_SALTWELL_TABLET:
memcpy(hw_cache_event_ids, atom_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
@@ -3887,9 +3887,11 @@ __init int intel_pmu_init(void)
pr_cont("Atom events, ");
break;
- case INTEL_FAM6_ATOM_SILVERMONT1:
- case INTEL_FAM6_ATOM_SILVERMONT2:
+ case INTEL_FAM6_ATOM_SILVERMONT:
+ case INTEL_FAM6_ATOM_SILVERMONT_X:
+ case INTEL_FAM6_ATOM_SILVERMONT_MID:
case INTEL_FAM6_ATOM_AIRMONT:
+ case INTEL_FAM6_ATOM_AIRMONT_MID:
memcpy(hw_cache_event_ids, slm_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
memcpy(hw_cache_extra_regs, slm_hw_cache_extra_regs,
@@ -3906,7 +3908,7 @@ __init int intel_pmu_init(void)
break;
case INTEL_FAM6_ATOM_GOLDMONT:
- case INTEL_FAM6_ATOM_DENVERTON:
+ case INTEL_FAM6_ATOM_GOLDMONT_X:
memcpy(hw_cache_event_ids, glm_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
memcpy(hw_cache_extra_regs, glm_hw_cache_extra_regs,
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index 53da7f3aa6e0..37b48ec31c79 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -531,8 +531,8 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
X86_CSTATES_MODEL(INTEL_FAM6_HASWELL_ULT, hswult_cstates),
- X86_CSTATES_MODEL(INTEL_FAM6_ATOM_SILVERMONT1, slm_cstates),
- X86_CSTATES_MODEL(INTEL_FAM6_ATOM_SILVERMONT2, slm_cstates),
+ X86_CSTATES_MODEL(INTEL_FAM6_ATOM_SILVERMONT, slm_cstates),
+ X86_CSTATES_MODEL(INTEL_FAM6_ATOM_SILVERMONT_X, slm_cstates),
X86_CSTATES_MODEL(INTEL_FAM6_ATOM_AIRMONT, slm_cstates),
X86_CSTATES_MODEL(INTEL_FAM6_BROADWELL_CORE, snb_cstates),
diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c
index be0b1968d60a..68144a341903 100644
--- a/arch/x86/events/msr.c
+++ b/arch/x86/events/msr.c
@@ -61,8 +61,8 @@ static bool test_intel(int idx)
case INTEL_FAM6_BROADWELL_GT3E:
case INTEL_FAM6_BROADWELL_X:
- case INTEL_FAM6_ATOM_SILVERMONT1:
- case INTEL_FAM6_ATOM_SILVERMONT2:
+ case INTEL_FAM6_ATOM_SILVERMONT:
+ case INTEL_FAM6_ATOM_SILVERMONT_X:
case INTEL_FAM6_ATOM_AIRMONT:
if (idx == PERF_MSR_SMI)
return true;
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 995d1b8e36e6..e283be0d79bd 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -342,6 +342,7 @@
#define X86_FEATURE_AVX512_4VNNIW (18*32+ 2) /* AVX-512 Neural Network Instructions */
#define X86_FEATURE_AVX512_4FMAPS (18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */
#define X86_FEATURE_TSX_FORCE_ABORT (18*32+13) /* "" TSX_FORCE_ABORT */
+#define X86_FEATURE_MD_CLEAR (18*32+10) /* VERW clears CPU buffers */
#define X86_FEATURE_PCONFIG (18*32+18) /* Intel PCONFIG */
#define X86_FEATURE_SPEC_CTRL (18*32+26) /* "" Speculation Control (IBRS + IBPB) */
#define X86_FEATURE_INTEL_STIBP (18*32+27) /* "" Single Thread Indirect Branch Predictors */
@@ -379,4 +380,6 @@
#define X86_BUG_SPECTRE_V2 X86_BUG(16) /* CPU is affected by Spectre variant 2 attack with indirect branches */
#define X86_BUG_SPEC_STORE_BYPASS X86_BUG(17) /* CPU is affected by speculative store bypass attack */
#define X86_BUG_L1TF X86_BUG(18) /* CPU is affected by L1 Terminal Fault */
+#define X86_BUG_MDS X86_BUG(19) /* CPU is affected by Microarchitectural data sampling */
+#define X86_BUG_MSBDS_ONLY X86_BUG(20) /* CPU is only affected by the MSDBS variant of BUG_MDS */
#endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index bd00c57a3b2c..2d3649de0fac 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -50,19 +50,23 @@
/* "Small Core" Processors (Atom) */
-#define INTEL_FAM6_ATOM_PINEVIEW 0x1C
-#define INTEL_FAM6_ATOM_LINCROFT 0x26
-#define INTEL_FAM6_ATOM_PENWELL 0x27
-#define INTEL_FAM6_ATOM_CLOVERVIEW 0x35
-#define INTEL_FAM6_ATOM_CEDARVIEW 0x36
-#define INTEL_FAM6_ATOM_SILVERMONT1 0x37 /* BayTrail/BYT / Valleyview */
-#define INTEL_FAM6_ATOM_SILVERMONT2 0x4D /* Avaton/Rangely */
-#define INTEL_FAM6_ATOM_AIRMONT 0x4C /* CherryTrail / Braswell */
-#define INTEL_FAM6_ATOM_MERRIFIELD 0x4A /* Tangier */
-#define INTEL_FAM6_ATOM_MOOREFIELD 0x5A /* Anniedale */
-#define INTEL_FAM6_ATOM_GOLDMONT 0x5C
-#define INTEL_FAM6_ATOM_DENVERTON 0x5F /* Goldmont Microserver */
-#define INTEL_FAM6_ATOM_GEMINI_LAKE 0x7A
+#define INTEL_FAM6_ATOM_BONNELL 0x1C /* Diamondville, Pineview */
+#define INTEL_FAM6_ATOM_BONNELL_MID 0x26 /* Silverthorne, Lincroft */
+
+#define INTEL_FAM6_ATOM_SALTWELL 0x36 /* Cedarview */
+#define INTEL_FAM6_ATOM_SALTWELL_MID 0x27 /* Penwell */
+#define INTEL_FAM6_ATOM_SALTWELL_TABLET 0x35 /* Cloverview */
+
+#define INTEL_FAM6_ATOM_SILVERMONT 0x37 /* Bay Trail, Valleyview */
+#define INTEL_FAM6_ATOM_SILVERMONT_X 0x4D /* Avaton, Rangely */
+#define INTEL_FAM6_ATOM_SILVERMONT_MID 0x4A /* Merriefield */
+
+#define INTEL_FAM6_ATOM_AIRMONT 0x4C /* Cherry Trail, Braswell */
+#define INTEL_FAM6_ATOM_AIRMONT_MID 0x5A /* Moorefield */
+
+#define INTEL_FAM6_ATOM_GOLDMONT 0x5C /* Apollo Lake */
+#define INTEL_FAM6_ATOM_GOLDMONT_X 0x5F /* Denverton */
+#define INTEL_FAM6_ATOM_GOLDMONT_PLUS 0x7A /* Gemini Lake */
#define INTEL_FAM6_ATOM_TREMONT_X 0x86 /* Jacobswille */
/* Xeon Phi */
diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h
index d937781e1047..f6e182f34501 100644
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -5,6 +5,8 @@
#ifndef __ASSEMBLY__
+#include <asm/nospec-branch.h>
+
/* Provide __cpuidle; we can't safely include <linux/cpu.h> */
#define __cpuidle __attribute__((__section__(".cpuidle.text")))
@@ -50,11 +52,13 @@ static inline void native_irq_enable(void)
static inline __cpuidle void native_safe_halt(void)
{
+ mds_idle_clear_cpu_buffers();
asm volatile("sti; hlt": : :"memory");
}
static inline __cpuidle void native_halt(void)
{
+ mds_idle_clear_cpu_buffers();
asm volatile("hlt": : :"memory");
}
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 812fef2839e8..207dc68a9434 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -1,6 +1,8 @@
#ifndef _ASM_X86_MSR_INDEX_H
#define _ASM_X86_MSR_INDEX_H
+#include <linux/bits.h>
+
/*
* CPU model specific register (MSR) numbers.
*
@@ -39,14 +41,14 @@
/* Intel MSRs. Some also available on other CPUs */
#define MSR_IA32_SPEC_CTRL 0x00000048 /* Speculation Control */
-#define SPEC_CTRL_IBRS (1 << 0) /* Indirect Branch Restricted Speculation */
+#define SPEC_CTRL_IBRS BIT(0) /* Indirect Branch Restricted Speculation */
#define SPEC_CTRL_STIBP_SHIFT 1 /* Single Thread Indirect Branch Predictor (STIBP) bit */
-#define SPEC_CTRL_STIBP (1 << SPEC_CTRL_STIBP_SHIFT) /* STIBP mask */
+#define SPEC_CTRL_STIBP BIT(SPEC_CTRL_STIBP_SHIFT) /* STIBP mask */
#define SPEC_CTRL_SSBD_SHIFT 2 /* Speculative Store Bypass Disable bit */
-#define SPEC_CTRL_SSBD (1 << SPEC_CTRL_SSBD_SHIFT) /* Speculative Store Bypass Disable */
+#define SPEC_CTRL_SSBD BIT(SPEC_CTRL_SSBD_SHIFT) /* Speculative Store Bypass Disable */
#define MSR_IA32_PRED_CMD 0x00000049 /* Prediction Command */
-#define PRED_CMD_IBPB (1 << 0) /* Indirect Branch Prediction Barrier */
+#define PRED_CMD_IBPB BIT(0) /* Indirect Branch Prediction Barrier */
#define MSR_PPIN_CTL 0x0000004e
#define MSR_PPIN 0x0000004f
@@ -68,20 +70,25 @@
#define MSR_MTRRcap 0x000000fe
#define MSR_IA32_ARCH_CAPABILITIES 0x0000010a
-#define ARCH_CAP_RDCL_NO (1 << 0) /* Not susceptible to Meltdown */
-#define ARCH_CAP_IBRS_ALL (1 << 1) /* Enhanced IBRS support */
-#define ARCH_CAP_SKIP_VMENTRY_L1DFLUSH (1 << 3) /* Skip L1D flush on vmentry */
-#define ARCH_CAP_SSB_NO (1 << 4) /*
- * Not susceptible to Speculative Store Bypass
- * attack, so no Speculative Store Bypass
- * control required.
- */
+#define ARCH_CAP_RDCL_NO BIT(0) /* Not susceptible to Meltdown */
+#define ARCH_CAP_IBRS_ALL BIT(1) /* Enhanced IBRS support */
+#define ARCH_CAP_SKIP_VMENTRY_L1DFLUSH BIT(3) /* Skip L1D flush on vmentry */
+#define ARCH_CAP_SSB_NO BIT(4) /*
+ * Not susceptible to Speculative Store Bypass
+ * attack, so no Speculative Store Bypass
+ * control required.
+ */
+#define ARCH_CAP_MDS_NO BIT(5) /*
+ * Not susceptible to
+ * Microarchitectural Data
+ * Sampling (MDS) vulnerabilities.
+ */
#define MSR_IA32_FLUSH_CMD 0x0000010b
-#define L1D_FLUSH (1 << 0) /*
- * Writeback and invalidate the
- * L1 data cache.
- */
+#define L1D_FLUSH BIT(0) /*
+ * Writeback and invalidate the
+ * L1 data cache.
+ */
#define MSR_IA32_BBL_CR_CTL 0x00000119
#define MSR_IA32_BBL_CR_CTL3 0x0000011e
diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h
index e2cea24bfec9..634e144c0f75 100644
--- a/arch/x86/include/asm/mwait.h
+++ b/arch/x86/include/asm/mwait.h
@@ -40,6 +40,8 @@ static inline void __monitorx(const void *eax, unsigned long ecx,
static inline void __mwait(unsigned long eax, unsigned long ecx)
{
+ mds_idle_clear_cpu_buffers();
+
/* "mwait %eax, %ecx;" */
asm volatile(".byte 0x0f, 0x01, 0xc9;"
:: "a" (eax), "c" (ecx));
@@ -74,6 +76,8 @@ static inline void __mwait(unsigned long eax, unsigned long ecx)
static inline void __mwaitx(unsigned long eax, unsigned long ebx,
unsigned long ecx)
{
+ /* No MDS buffer clear as this is AMD/HYGON only */
+
/* "mwaitx %eax, %ebx, %ecx;" */
asm volatile(".byte 0x0f, 0x01, 0xfb;"
:: "a" (eax), "b" (ebx), "c" (ecx));
@@ -81,6 +85,8 @@ static inline void __mwaitx(unsigned long eax, unsigned long ebx,
static inline void __sti_mwait(unsigned long eax, unsigned long ecx)
{
+ mds_idle_clear_cpu_buffers();
+
trace_hardirqs_on();
/* "mwait %eax, %ecx;" */
asm volatile("sti; .byte 0x0f, 0x01, 0xc9;"
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 849acf1cdd5f..279c4e44b112 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -352,6 +352,56 @@ DECLARE_STATIC_KEY_FALSE(switch_to_cond_stibp);
DECLARE_STATIC_KEY_FALSE(switch_mm_cond_ibpb);
DECLARE_STATIC_KEY_FALSE(switch_mm_always_ibpb);
+DECLARE_STATIC_KEY_FALSE(mds_user_clear);
+DECLARE_STATIC_KEY_FALSE(mds_idle_clear);
+
+#include <asm/segment.h>
+
+/**
+ * mds_clear_cpu_buffers - Mitigation for MDS vulnerability
+ *
+ * This uses the otherwise unused and obsolete VERW instruction in
+ * combination with microcode which triggers a CPU buffer flush when the
+ * instruction is executed.
+ */
+static inline void mds_clear_cpu_buffers(void)
+{
+ static const u16 ds = __KERNEL_DS;
+
+ /*
+ * Has to be the memory-operand variant because only that
+ * guarantees the CPU buffer flush functionality according to
+ * documentation. The register-operand variant does not.
+ * Works with any segment selector, but a valid writable
+ * data segment is the fastest variant.
+ *
+ * "cc" clobber is required because VERW modifies ZF.
+ */
+ asm volatile("verw %[ds]" : : [ds] "m" (ds) : "cc");
+}
+
+/**
+ * mds_user_clear_cpu_buffers - Mitigation for MDS vulnerability
+ *
+ * Clear CPU buffers if the corresponding static key is enabled
+ */
+static inline void mds_user_clear_cpu_buffers(void)
+{
+ if (static_branch_likely(&mds_user_clear))
+ mds_clear_cpu_buffers();
+}
+
+/**
+ * mds_idle_clear_cpu_buffers - Mitigation for MDS vulnerability
+ *
+ * Clear CPU buffers if the corresponding static key is enabled
+ */
+static inline void mds_idle_clear_cpu_buffers(void)
+{
+ if (static_branch_likely(&mds_idle_clear))
+ mds_clear_cpu_buffers();
+}
+
#endif /* __ASSEMBLY__ */
/*
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index dbf37888ca14..7ea25d8700f7 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -982,4 +982,10 @@ enum l1tf_mitigations {
extern enum l1tf_mitigations l1tf_mitigation;
+enum mds_mitigations {
+ MDS_MITIGATION_OFF,
+ MDS_MITIGATION_FULL,
+ MDS_MITIGATION_VMWERV,
+};
+
#endif /* _ASM_X86_PROCESSOR_H */
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 8a080b942074..c1023744d228 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -34,6 +34,7 @@
static void __init spectre_v2_select_mitigation(void);
static void __init ssb_select_mitigation(void);
static void __init l1tf_select_mitigation(void);
+static void __init mds_select_mitigation(void);
/* The base value of the SPEC_CTRL MSR that always has to be preserved. */
u64 x86_spec_ctrl_base;
@@ -60,6 +61,13 @@ DEFINE_STATIC_KEY_FALSE(switch_mm_cond_ibpb);
/* Control unconditional IBPB in switch_mm() */
DEFINE_STATIC_KEY_FALSE(switch_mm_always_ibpb);
+/* Control MDS CPU buffer clear before returning to user space */
+DEFINE_STATIC_KEY_FALSE(mds_user_clear);
+EXPORT_SYMBOL_GPL(mds_user_clear);
+/* Control MDS CPU buffer clear before idling (halt, mwait) */
+DEFINE_STATIC_KEY_FALSE(mds_idle_clear);
+EXPORT_SYMBOL_GPL(mds_idle_clear);
+
void __init check_bugs(void)
{
identify_boot_cpu();
@@ -98,6 +106,10 @@ void __init check_bugs(void)
l1tf_select_mitigation();
+ mds_select_mitigation();
+
+ arch_smt_update();
+
#ifdef CONFIG_X86_32
/*
* Check whether we are able to run this kernel safely on SMP.
@@ -328,6 +340,61 @@ early_param("l1tf", l1tf_cmdline);
#undef pr_fmt
+#define pr_fmt(fmt) "MDS: " fmt
+
+/* Default mitigation for L1TF-affected CPUs */
+static enum mds_mitigations mds_mitigation __ro_after_init = MDS_MITIGATION_FULL;
+static bool mds_nosmt __ro_after_init = false;
+
+static const char * const mds_strings[] = {
+ [MDS_MITIGATION_OFF] = "Vulnerable",
+ [MDS_MITIGATION_FULL] = "Mitigation: Clear CPU buffers",
+ [MDS_MITIGATION_VMWERV] = "Vulnerable: Clear CPU buffers attempted, no microcode",
+};
+
+static void __init mds_select_mitigation(void)
+{
+ if (!boot_cpu_has_bug(X86_BUG_MDS) || cpu_mitigations_off()) {
+ mds_mitigation = MDS_MITIGATION_OFF;
+ return;
+ }
+
+ if (mds_mitigation == MDS_MITIGATION_FULL) {
+ if (!boot_cpu_has(X86_FEATURE_MD_CLEAR))
+ mds_mitigation = MDS_MITIGATION_VMWERV;
+
+ static_branch_enable(&mds_user_clear);
+
+ if (!boot_cpu_has(X86_BUG_MSBDS_ONLY) &&
+ (mds_nosmt || cpu_mitigations_auto_nosmt()))
+ cpu_smt_disable(false);
+ }
+
+ pr_info("%s\n", mds_strings[mds_mitigation]);
+}
+
+static int __init mds_cmdline(char *str)
+{
+ if (!boot_cpu_has_bug(X86_BUG_MDS))
+ return 0;
+
+ if (!str)
+ return -EINVAL;
+
+ if (!strcmp(str, "off"))
+ mds_mitigation = MDS_MITIGATION_OFF;
+ else if (!strcmp(str, "full"))
+ mds_mitigation = MDS_MITIGATION_FULL;
+ else if (!strcmp(str, "full,nosmt")) {
+ mds_mitigation = MDS_MITIGATION_FULL;
+ mds_nosmt = true;
+ }
+
+ return 0;
+}
+early_param("mds", mds_cmdline);
+
+#undef pr_fmt
#define pr_fmt(fmt) "Spectre V2 : " fmt
static enum spectre_v2_mitigation spectre_v2_enabled __ro_after_init =
@@ -694,9 +761,6 @@ specv2_set_mode:
/* Set up IBPB and STIBP depending on the general spectre V2 command */
spectre_v2_user_select_mitigation(cmd);
-
- /* Enable STIBP if appropriate */
- arch_smt_update();
}
static void update_stibp_msr(void * __unused)
@@ -730,6 +794,31 @@ static void update_indir_branch_cond(void)
static_branch_disable(&switch_to_cond_stibp);
}
+#undef pr_fmt
+#define pr_fmt(fmt) fmt
+
+/* Update the static key controlling the MDS CPU buffer clear in idle */
+static void update_mds_branch_idle(void)
+{
+ /*
+ * Enable the idle clearing if SMT is active on CPUs which are
+ * affected only by MSBDS and not any other MDS variant.
+ *
+ * The other variants cannot be mitigated when SMT is enabled, so
+ * clearing the buffers on idle just to prevent the Store Buffer
+ * repartitioning leak would be a window dressing exercise.
+ */
+ if (!boot_cpu_has_bug(X86_BUG_MSBDS_ONLY))
+ return;
+
+ if (sched_smt_active())
+ static_branch_enable(&mds_idle_clear);
+ else
+ static_branch_disable(&mds_idle_clear);
+}
+
+#define MDS_MSG_SMT "MDS CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/mds.html for more details.\n"
+
void arch_smt_update(void)
{
/* Enhanced IBRS implies STIBP. No update required. */
@@ -750,6 +839,17 @@ void arch_smt_update(void)
break;
}
+ switch (mds_mitigation) {
+ case MDS_MITIGATION_FULL:
+ case MDS_MITIGATION_VMWERV:
+ if (sched_smt_active() && !boot_cpu_has(X86_BUG_MSBDS_ONLY))
+ pr_warn_once(MDS_MSG_SMT);
+ update_mds_branch_idle();
+ break;
+ case MDS_MITIGATION_OFF:
+ break;
+ }
+
mutex_unlock(&spec_ctrl_mutex);
}
@@ -1093,6 +1193,23 @@ static ssize_t l1tf_show_state(char *buf)
}
#endif
+static ssize_t mds_show_state(char *buf)
+{
+ if (!hypervisor_is_type(X86_HYPER_NATIVE)) {
+ return sprintf(buf, "%s; SMT Host state unknown\n",
+ mds_strings[mds_mitigation]);
+ }
+
+ if (boot_cpu_has(X86_BUG_MSBDS_ONLY)) {
+ return sprintf(buf, "%s; SMT %s\n", mds_strings[mds_mitigation],
+ (mds_mitigation == MDS_MITIGATION_OFF ? "vulnerable" :
+ sched_smt_active() ? "mitigated" : "disabled"));
+ }
+
+ return sprintf(buf, "%s; SMT %s\n", mds_strings[mds_mitigation],
+ sched_smt_active() ? "vulnerable" : "disabled");
+}
+
static char *stibp_state(void)
{
if (spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED)
@@ -1159,6 +1276,10 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr
return l1tf_show_state(buf);
break;
+
+ case X86_BUG_MDS:
+ return mds_show_state(buf);
+
default:
break;
}
@@ -1190,4 +1311,9 @@ ssize_t cpu_show_l1tf(struct device *dev, struct device_attribute *attr, char *b
{
return cpu_show_common(dev, attr, buf, X86_BUG_L1TF);
}
+
+ssize_t cpu_show_mds(struct device *dev, struct device_attribute *attr, char *buf)
+{
+ return cpu_show_common(dev, attr, buf, X86_BUG_MDS);
+}
#endif
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index d6fe81bfa28a..1b53caf30805 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -898,85 +898,95 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c)
#endif
}
-static const __initconst struct x86_cpu_id cpu_no_speculation[] = {
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_CEDARVIEW, X86_FEATURE_ANY },
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_CLOVERVIEW, X86_FEATURE_ANY },
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_LINCROFT, X86_FEATURE_ANY },
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_PENWELL, X86_FEATURE_ANY },
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_PINEVIEW, X86_FEATURE_ANY },
- { X86_VENDOR_CENTAUR, 5 },
- { X86_VENDOR_INTEL, 5 },
- { X86_VENDOR_NSC, 5 },
- { X86_VENDOR_ANY, 4 },
+#define NO_SPECULATION BIT(0)
+#define NO_MELTDOWN BIT(1)
+#define NO_SSB BIT(2)
+#define NO_L1TF BIT(3)
+#define NO_MDS BIT(4)
+#define MSBDS_ONLY BIT(5)
+
+#define VULNWL(_vendor, _family, _model, _whitelist) \
+ { X86_VENDOR_##_vendor, _family, _model, X86_FEATURE_ANY, _whitelist }
+
+#define VULNWL_INTEL(model, whitelist) \
+ VULNWL(INTEL, 6, INTEL_FAM6_##model, whitelist)
+
+#define VULNWL_AMD(family, whitelist) \
+ VULNWL(AMD, family, X86_MODEL_ANY, whitelist)
+
+static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
+ VULNWL(ANY, 4, X86_MODEL_ANY, NO_SPECULATION),
+ VULNWL(CENTAUR, 5, X86_MODEL_ANY, NO_SPECULATION),
+ VULNWL(INTEL, 5, X86_MODEL_ANY, NO_SPECULATION),
+ VULNWL(NSC, 5, X86_MODEL_ANY, NO_SPECULATION),
+
+ /* Intel Family 6 */
+ VULNWL_INTEL(ATOM_SALTWELL, NO_SPECULATION),
+ VULNWL_INTEL(ATOM_SALTWELL_TABLET, NO_SPECULATION),
+ VULNWL_INTEL(ATOM_SALTWELL_MID, NO_SPECULATION),
+ VULNWL_INTEL(ATOM_BONNELL, NO_SPECULATION),
+ VULNWL_INTEL(ATOM_BONNELL_MID, NO_SPECULATION),
+
+ VULNWL_INTEL(ATOM_SILVERMONT, NO_SSB | NO_L1TF | MSBDS_ONLY),
+ VULNWL_INTEL(ATOM_SILVERMONT_X, NO_SSB | NO_L1TF | MSBDS_ONLY),
+ VULNWL_INTEL(ATOM_SILVERMONT_MID, NO_SSB | NO_L1TF | MSBDS_ONLY),
+ VULNWL_INTEL(ATOM_AIRMONT, NO_SSB | NO_L1TF | MSBDS_ONLY),
+ VULNWL_INTEL(XEON_PHI_KNL, NO_SSB | NO_L1TF | MSBDS_ONLY),
+ VULNWL_INTEL(XEON_PHI_KNM, NO_SSB | NO_L1TF | MSBDS_ONLY),
+
+ VULNWL_INTEL(CORE_YONAH, NO_SSB),
+
+ VULNWL_INTEL(ATOM_AIRMONT_MID, NO_L1TF | MSBDS_ONLY),
+
+ VULNWL_INTEL(ATOM_GOLDMONT, NO_MDS | NO_L1TF),
+ VULNWL_INTEL(ATOM_GOLDMONT_X, NO_MDS | NO_L1TF),
+ VULNWL_INTEL(ATOM_GOLDMONT_PLUS, NO_MDS | NO_L1TF),
+
+ /* AMD Family 0xf - 0x12 */
+ VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS),
+ VULNWL_AMD(0x10, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS),
+ VULNWL_AMD(0x11, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS),
+ VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS),
+
+ /* FAMILY_ANY must be last, otherwise 0x0f - 0x12 matches won't work */
+ VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS),
{}
};
-static const __initconst struct x86_cpu_id cpu_no_meltdown[] = {
- { X86_VENDOR_AMD },
- {}
-};
-
-static const __initconst struct x86_cpu_id cpu_no_spec_store_bypass[] = {
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_PINEVIEW },
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_LINCROFT },
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_PENWELL },
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_CLOVERVIEW },
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_CEDARVIEW },
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT1 },
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_AIRMONT },
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT2 },
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_MERRIFIELD },
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_CORE_YONAH },
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_XEON_PHI_KNL },
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_XEON_PHI_KNM },
- { X86_VENDOR_CENTAUR, 5, },
- { X86_VENDOR_INTEL, 5, },
- { X86_VENDOR_NSC, 5, },
- { X86_VENDOR_AMD, 0x12, },
- { X86_VENDOR_AMD, 0x11, },
- { X86_VENDOR_AMD, 0x10, },
- { X86_VENDOR_AMD, 0xf, },
- { X86_VENDOR_ANY, 4, },
- {}
-};
+static bool __init cpu_matches(unsigned long which)
+{
+ const struct x86_cpu_id *m = x86_match_cpu(cpu_vuln_whitelist);
-static const __initconst struct x86_cpu_id cpu_no_l1tf[] = {
- /* in addition to cpu_no_speculation */
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT1 },
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT2 },
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_AIRMONT },
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_MERRIFIELD },
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_MOOREFIELD },
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_GOLDMONT },
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_DENVERTON },
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_GEMINI_LAKE },
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_XEON_PHI_KNL },
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_XEON_PHI_KNM },
- {}
-};
+ return m && !!(m->driver_data & which);
+}
static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
{
u64 ia32_cap = 0;
+ if (cpu_matches(NO_SPECULATION))
+ return;
+
+ setup_force_cpu_bug(X86_BUG_SPECTRE_V1);
+ setup_force_cpu_bug(X86_BUG_SPECTRE_V2);
+
if (cpu_has(c, X86_FEATURE_ARCH_CAPABILITIES))
rdmsrl(MSR_IA32_ARCH_CAPABILITIES, ia32_cap);
- if (!x86_match_cpu(cpu_no_spec_store_bypass) &&
- !(ia32_cap & ARCH_CAP_SSB_NO) &&
+ if (!cpu_matches(NO_SSB) && !(ia32_cap & ARCH_CAP_SSB_NO) &&
!cpu_has(c, X86_FEATURE_AMD_SSB_NO))
setup_force_cpu_bug(X86_BUG_SPEC_STORE_BYPASS);
- if (x86_match_cpu(cpu_no_speculation))
- return;
-
- setup_force_cpu_bug(X86_BUG_SPECTRE_V1);
- setup_force_cpu_bug(X86_BUG_SPECTRE_V2);
-
if (ia32_cap & ARCH_CAP_IBRS_ALL)
setup_force_cpu_cap(X86_FEATURE_IBRS_ENHANCED);
- if (x86_match_cpu(cpu_no_meltdown))
+ if (!cpu_matches(NO_MDS) && !(ia32_cap & ARCH_CAP_MDS_NO)) {
+ setup_force_cpu_bug(X86_BUG_MDS);
+ if (cpu_matches(MSBDS_ONLY))
+ setup_force_cpu_bug(X86_BUG_MSBDS_ONLY);
+ }
+
+ if (cpu_matches(NO_MELTDOWN))
return;
/* Rogue Data Cache Load? No! */
@@ -985,7 +995,7 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN);
- if (x86_match_cpu(cpu_no_l1tf))
+ if (cpu_matches(NO_L1TF))
return;
setup_force_cpu_bug(X86_BUG_L1TF);
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index 18bc9b51ac9b..086cf1d1d71d 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -34,6 +34,7 @@
#include <asm/x86_init.h>
#include <asm/reboot.h>
#include <asm/cache.h>
+#include <asm/nospec-branch.h>
#define CREATE_TRACE_POINTS
#include <trace/events/nmi.h>
@@ -533,6 +534,9 @@ nmi_restart:
write_cr2(this_cpu_read(nmi_cr2));
if (this_cpu_dec_return(nmi_state))
goto nmi_restart;
+
+ if (user_mode(regs))
+ mds_user_clear_cpu_buffers();
}
NOKPROBE_SYMBOL(do_nmi);
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 2501816f5d8b..68f65420ad0c 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -59,6 +59,7 @@
#include <asm/alternative.h>
#include <asm/fpu/xstate.h>
#include <asm/trace/mpx.h>
+#include <asm/nospec-branch.h>
#include <asm/mpx.h>
#include <asm/vm86.h>
@@ -393,6 +394,13 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
regs->ip = (unsigned long)general_protection;
regs->sp = (unsigned long)&gpregs->orig_ax;
+ /*
+ * This situation can be triggered by userspace via
+ * modify_ldt(2) and the return does not take the regular
+ * user space exit, so a CPU buffer clear is required when
+ * MDS mitigation is enabled.
+ */
+ mds_user_clear_cpu_buffers();
return;
}
#endif
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index a3633285a2e5..692c1cf24faf 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -620,7 +620,7 @@ unsigned long native_calibrate_tsc(void)
case INTEL_FAM6_KABYLAKE_DESKTOP:
crystal_khz = 24000; /* 24.0 MHz */
break;
- case INTEL_FAM6_ATOM_DENVERTON:
+ case INTEL_FAM6_ATOM_GOLDMONT_X:
crystal_khz = 25000; /* 25.0 MHz */
break;
case INTEL_FAM6_ATOM_GOLDMONT:
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 6157cb51bf0d..ea2422ced61a 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -367,7 +367,8 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
/* cpuid 0x80000008.ebx */
const u32 kvm_cpuid_8000_0008_ebx_x86_features =
- F(AMD_IBPB) | F(AMD_IBRS) | F(AMD_SSBD) | F(VIRT_SSBD) | F(AMD_SSB_NO);
+ F(AMD_IBPB) | F(AMD_IBRS) | F(AMD_SSBD) | F(VIRT_SSBD) |
+ F(AMD_SSB_NO) | F(AMD_STIBP);
/* cpuid 0xC0000001.edx */
const u32 kvm_cpuid_C000_0001_edx_x86_features =
@@ -396,7 +397,8 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
/* cpuid 7.0.edx*/
const u32 kvm_cpuid_7_0_edx_x86_features =
F(AVX512_4VNNIW) | F(AVX512_4FMAPS) | F(SPEC_CTRL) |
- F(SPEC_CTRL_SSBD) | F(ARCH_CAPABILITIES);
+ F(SPEC_CTRL_SSBD) | F(ARCH_CAPABILITIES) | F(INTEL_STIBP) |
+ F(MD_CLEAR);
/* all calls to cpuid_count() should be made on the same cpu */
get_cpu();
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 2e37c1158312..4601ed5816f8 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -9720,8 +9720,11 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
vmx->__launched = vmx->loaded_vmcs->launched;
+ /* L1D Flush includes CPU buffer clear to mitigate MDS */
if (static_branch_unlikely(&vmx_l1d_should_flush))
vmx_l1d_flush(vcpu);
+ else if (static_branch_unlikely(&mds_user_clear))
+ mds_clear_cpu_buffers();
asm(
/* Store host registers */
diff --git a/arch/x86/platform/atom/punit_atom_debug.c b/arch/x86/platform/atom/punit_atom_debug.c
index d49d3be81953..ecb5866aaf84 100644
--- a/arch/x86/platform/atom/punit_atom_debug.c
+++ b/arch/x86/platform/atom/punit_atom_debug.c
@@ -154,8 +154,8 @@ static void punit_dbgfs_unregister(void)
(kernel_ulong_t)&drv_data }
static const struct x86_cpu_id intel_punit_cpu_ids[] = {
- ICPU(INTEL_FAM6_ATOM_SILVERMONT1, punit_device_byt),
- ICPU(INTEL_FAM6_ATOM_MERRIFIELD, punit_device_tng),
+ ICPU(INTEL_FAM6_ATOM_SILVERMONT, punit_device_byt),
+ ICPU(INTEL_FAM6_ATOM_SILVERMONT_MID, punit_device_tng),
ICPU(INTEL_FAM6_ATOM_AIRMONT, punit_device_cht),
{}
};
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_bt.c b/arch/x86/platform/intel-mid/device_libs/platform_bt.c
index 5a0483e7bf66..31dce781364c 100644
--- a/arch/x86/platform/intel-mid/device_libs/platform_bt.c
+++ b/arch/x86/platform/intel-mid/device_libs/platform_bt.c
@@ -68,7 +68,7 @@ static struct bt_sfi_data tng_bt_sfi_data __initdata = {
{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (kernel_ulong_t)&ddata }
static const struct x86_cpu_id bt_sfi_cpu_ids[] = {
- ICPU(INTEL_FAM6_ATOM_MERRIFIELD, tng_bt_sfi_data),
+ ICPU(INTEL_FAM6_ATOM_SILVERMONT_MID, tng_bt_sfi_data),
{}
};
diff --git a/block/genhd.c b/block/genhd.c
index 9ceeb9e16f98..dff0f28feb54 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -1577,7 +1577,8 @@ static unsigned long disk_events_poll_jiffies(struct gendisk *disk)
*/
if (ev->poll_msecs >= 0)
intv_msecs = ev->poll_msecs;
- else if (disk->events & ~disk->async_events)
+ else if (disk->events & DISK_EVENT_FLAG_POLL
+ && disk->events & ~disk->async_events)
intv_msecs = disk_events_dfl_poll_msecs;
return msecs_to_jiffies(intv_msecs);
@@ -1787,11 +1788,13 @@ static void disk_check_events(struct disk_events *ev,
/*
* Tell userland about new events. Only the events listed in
- * @disk->events are reported. Unlisted events are processed the
- * same internally but never get reported to userland.
+ * @disk->events are reported, and only if DISK_EVENT_FLAG_UEVENT
+ * is set. Otherwise, events are processed internally but never
+ * get reported to userland.
*/
for (i = 0; i < ARRAY_SIZE(disk_uevents); i++)
- if (events & disk->events & (1 << i))
+ if (events & disk->events & (1 << i) &&
+ disk->events & DISK_EVENT_FLAG_UEVENT)
envp[nr_events++] = disk_uevents[i];
if (nr_events)
@@ -1828,7 +1831,10 @@ static ssize_t disk_events_show(struct device *dev,
{
struct gendisk *disk = dev_to_disk(dev);
- return __disk_events_show(disk->events, buf);
+ if (!(disk->events & DISK_EVENT_FLAG_UEVENT))
+ return 0;
+
+ return __disk_events_show(disk->events & DISK_EVENT_TYPES_MASK, buf);
}
static ssize_t disk_events_async_show(struct device *dev,
@@ -1836,7 +1842,11 @@ static ssize_t disk_events_async_show(struct device *dev,
{
struct gendisk *disk = dev_to_disk(dev);
- return __disk_events_show(disk->async_events, buf);
+ if (!(disk->events & DISK_EVENT_FLAG_UEVENT))
+ return 0;
+
+ return __disk_events_show(disk->async_events & DISK_EVENT_TYPES_MASK,
+ buf);
}
static ssize_t disk_events_poll_msecs_show(struct device *dev,
@@ -1845,6 +1855,9 @@ static ssize_t disk_events_poll_msecs_show(struct device *dev,
{
struct gendisk *disk = dev_to_disk(dev);
+ if (!disk->ev)
+ return sprintf(buf, "-1\n");
+
return sprintf(buf, "%ld\n", disk->ev->poll_msecs);
}
@@ -1861,6 +1874,9 @@ static ssize_t disk_events_poll_msecs_store(struct device *dev,
if (intv < 0 && intv != -1)
return -EINVAL;
+ if (!disk->ev)
+ return -ENODEV;
+
disk_block_events(disk);
disk->ev->poll_msecs = intv;
__disk_unblock_events(disk, true);
@@ -1925,7 +1941,8 @@ static void disk_alloc_events(struct gendisk *disk)
{
struct disk_events *ev;
- if (!disk->fops->check_events)
+ if (!disk->fops->check_events ||
+ !(disk->events & DISK_EVENT_TYPES_MASK))
return;
ev = kzalloc(sizeof(*ev), GFP_KERNEL);
@@ -1947,14 +1964,14 @@ static void disk_alloc_events(struct gendisk *disk)
static void disk_add_events(struct gendisk *disk)
{
- if (!disk->ev)
- return;
-
/* FIXME: error handling */
if (sysfs_create_files(&disk_to_dev(disk)->kobj, disk_events_attrs) < 0)
pr_warn("%s: failed to create sysfs files for events\n",
disk->disk_name);
+ if (!disk->ev)
+ return;
+
mutex_lock(&disk_events_mutex);
list_add_tail(&disk->ev->node, &disk_events);
mutex_unlock(&disk_events_mutex);
@@ -1968,14 +1985,13 @@ static void disk_add_events(struct gendisk *disk)
static void disk_del_events(struct gendisk *disk)
{
- if (!disk->ev)
- return;
+ if (disk->ev) {
+ disk_block_events(disk);
- disk_block_events(disk);
-
- mutex_lock(&disk_events_mutex);
- list_del_init(&disk->ev->node);
- mutex_unlock(&disk_events_mutex);
+ mutex_lock(&disk_events_mutex);
+ list_del_init(&disk->ev->node);
+ mutex_unlock(&disk_events_mutex);
+ }
sysfs_remove_files(&disk_to_dev(disk)->kobj, disk_events_attrs);
}
diff --git a/crypto/Kconfig b/crypto/Kconfig
index 65b8845c5939..0e535e7c4ae4 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -26,8 +26,8 @@ config CRYPTO_FIPS
depends on (CRYPTO_ANSI_CPRNG || CRYPTO_DRBG) && !CRYPTO_MANAGER_DISABLE_TESTS
depends on (MODULE_SIG || !MODULES)
help
- This options enables the fips boot option which is
- required if you want to system to operate in a FIPS 200
+ This option enables the fips boot option which is
+ required if you want the system to operate in a FIPS 200
certification. You should say no unless you know what
this is.
diff --git a/crypto/ccm.c b/crypto/ccm.c
index 0a083342ec8c..8104c564dd31 100644
--- a/crypto/ccm.c
+++ b/crypto/ccm.c
@@ -455,7 +455,6 @@ static void crypto_ccm_free(struct aead_instance *inst)
static int crypto_ccm_create_common(struct crypto_template *tmpl,
struct rtattr **tb,
- const char *full_name,
const char *ctr_name,
const char *mac_name)
{
@@ -483,7 +482,8 @@ static int crypto_ccm_create_common(struct crypto_template *tmpl,
mac = __crypto_hash_alg_common(mac_alg);
err = -EINVAL;
- if (mac->digestsize != 16)
+ if (strncmp(mac->base.cra_name, "cbcmac(", 7) != 0 ||
+ mac->digestsize != 16)
goto out_put_mac;
inst = kzalloc(sizeof(*inst) + sizeof(*ictx), GFP_KERNEL);
@@ -506,23 +506,27 @@ static int crypto_ccm_create_common(struct crypto_template *tmpl,
ctr = crypto_spawn_skcipher_alg(&ictx->ctr);
- /* Not a stream cipher? */
+ /* The skcipher algorithm must be CTR mode, using 16-byte blocks. */
err = -EINVAL;
- if (ctr->base.cra_blocksize != 1)
+ if (strncmp(ctr->base.cra_name, "ctr(", 4) != 0 ||
+ crypto_skcipher_alg_ivsize(ctr) != 16 ||
+ ctr->base.cra_blocksize != 1)
goto err_drop_ctr;
- /* We want the real thing! */
- if (crypto_skcipher_alg_ivsize(ctr) != 16)
+ /* ctr and cbcmac must use the same underlying block cipher. */
+ if (strcmp(ctr->base.cra_name + 4, mac->base.cra_name + 7) != 0)
goto err_drop_ctr;
err = -ENAMETOOLONG;
+ if (snprintf(inst->alg.base.cra_name, CRYPTO_MAX_ALG_NAME,
+ "ccm(%s", ctr->base.cra_name + 4) >= CRYPTO_MAX_ALG_NAME)
+ goto err_drop_ctr;
+
if (snprintf(inst->alg.base.cra_driver_name, CRYPTO_MAX_ALG_NAME,
"ccm_base(%s,%s)", ctr->base.cra_driver_name,
mac->base.cra_driver_name) >= CRYPTO_MAX_ALG_NAME)
goto err_drop_ctr;
- memcpy(inst->alg.base.cra_name, full_name, CRYPTO_MAX_ALG_NAME);
-
inst->alg.base.cra_flags = ctr->base.cra_flags & CRYPTO_ALG_ASYNC;
inst->alg.base.cra_priority = (mac->base.cra_priority +
ctr->base.cra_priority) / 2;
@@ -564,7 +568,6 @@ static int crypto_ccm_create(struct crypto_template *tmpl, struct rtattr **tb)
const char *cipher_name;
char ctr_name[CRYPTO_MAX_ALG_NAME];
char mac_name[CRYPTO_MAX_ALG_NAME];
- char full_name[CRYPTO_MAX_ALG_NAME];
cipher_name = crypto_attr_alg_name(tb[1]);
if (IS_ERR(cipher_name))
@@ -578,12 +581,7 @@ static int crypto_ccm_create(struct crypto_template *tmpl, struct rtattr **tb)
cipher_name) >= CRYPTO_MAX_ALG_NAME)
return -ENAMETOOLONG;
- if (snprintf(full_name, CRYPTO_MAX_ALG_NAME, "ccm(%s)", cipher_name) >=
- CRYPTO_MAX_ALG_NAME)
- return -ENAMETOOLONG;
-
- return crypto_ccm_create_common(tmpl, tb, full_name, ctr_name,
- mac_name);
+ return crypto_ccm_create_common(tmpl, tb, ctr_name, mac_name);
}
static struct crypto_template crypto_ccm_tmpl = {
@@ -596,23 +594,17 @@ static int crypto_ccm_base_create(struct crypto_template *tmpl,
struct rtattr **tb)
{
const char *ctr_name;
- const char *cipher_name;
- char full_name[CRYPTO_MAX_ALG_NAME];
+ const char *mac_name;
ctr_name = crypto_attr_alg_name(tb[1]);
if (IS_ERR(ctr_name))
return PTR_ERR(ctr_name);
- cipher_name = crypto_attr_alg_name(tb[2]);
- if (IS_ERR(cipher_name))
- return PTR_ERR(cipher_name);
-
- if (snprintf(full_name, CRYPTO_MAX_ALG_NAME, "ccm_base(%s,%s)",
- ctr_name, cipher_name) >= CRYPTO_MAX_ALG_NAME)
- return -ENAMETOOLONG;
+ mac_name = crypto_attr_alg_name(tb[2]);
+ if (IS_ERR(mac_name))
+ return PTR_ERR(mac_name);
- return crypto_ccm_create_common(tmpl, tb, full_name, ctr_name,
- cipher_name);
+ return crypto_ccm_create_common(tmpl, tb, ctr_name, mac_name);
}
static struct crypto_template crypto_ccm_base_tmpl = {
diff --git a/crypto/chacha20poly1305.c b/crypto/chacha20poly1305.c
index 600afa99941f..4d6f51bcdfab 100644
--- a/crypto/chacha20poly1305.c
+++ b/crypto/chacha20poly1305.c
@@ -647,8 +647,8 @@ static int chachapoly_create(struct crypto_template *tmpl, struct rtattr **tb,
err = -ENAMETOOLONG;
if (snprintf(inst->alg.base.cra_name, CRYPTO_MAX_ALG_NAME,
- "%s(%s,%s)", name, chacha_name,
- poly_name) >= CRYPTO_MAX_ALG_NAME)
+ "%s(%s,%s)", name, chacha->base.cra_name,
+ poly->cra_name) >= CRYPTO_MAX_ALG_NAME)
goto out_drop_chacha;
if (snprintf(inst->alg.base.cra_driver_name, CRYPTO_MAX_ALG_NAME,
"%s(%s,%s)", name, chacha->base.cra_driver_name,
diff --git a/crypto/crct10dif_generic.c b/crypto/crct10dif_generic.c
index 8e94e29dc6fc..d08048ae5552 100644
--- a/crypto/crct10dif_generic.c
+++ b/crypto/crct10dif_generic.c
@@ -65,10 +65,9 @@ static int chksum_final(struct shash_desc *desc, u8 *out)
return 0;
}
-static int __chksum_finup(__u16 *crcp, const u8 *data, unsigned int len,
- u8 *out)
+static int __chksum_finup(__u16 crc, const u8 *data, unsigned int len, u8 *out)
{
- *(__u16 *)out = crc_t10dif_generic(*crcp, data, len);
+ *(__u16 *)out = crc_t10dif_generic(crc, data, len);
return 0;
}
@@ -77,15 +76,13 @@ static int chksum_finup(struct shash_desc *desc, const u8 *data,
{
struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
- return __chksum_finup(&ctx->crc, data, len, out);
+ return __chksum_finup(ctx->crc, data, len, out);
}
static int chksum_digest(struct shash_desc *desc, const u8 *data,
unsigned int length, u8 *out)
{
- struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
-
- return __chksum_finup(&ctx->crc, data, length, out);
+ return __chksum_finup(0, data, length, out);
}
static struct shash_alg alg = {
diff --git a/crypto/gcm.c b/crypto/gcm.c
index 3841b5eafa7e..45b34a1144b8 100644
--- a/crypto/gcm.c
+++ b/crypto/gcm.c
@@ -616,7 +616,6 @@ static void crypto_gcm_free(struct aead_instance *inst)
static int crypto_gcm_create_common(struct crypto_template *tmpl,
struct rtattr **tb,
- const char *full_name,
const char *ctr_name,
const char *ghash_name)
{
@@ -657,7 +656,8 @@ static int crypto_gcm_create_common(struct crypto_template *tmpl,
goto err_free_inst;
err = -EINVAL;
- if (ghash->digestsize != 16)
+ if (strcmp(ghash->base.cra_name, "ghash") != 0 ||
+ ghash->digestsize != 16)
goto err_drop_ghash;
crypto_set_skcipher_spawn(&ctx->ctr, aead_crypto_instance(inst));
@@ -669,24 +669,24 @@ static int crypto_gcm_create_common(struct crypto_template *tmpl,
ctr = crypto_spawn_skcipher_alg(&ctx->ctr);
- /* We only support 16-byte blocks. */
+ /* The skcipher algorithm must be CTR mode, using 16-byte blocks. */
err = -EINVAL;
- if (crypto_skcipher_alg_ivsize(ctr) != 16)
+ if (strncmp(ctr->base.cra_name, "ctr(", 4) != 0 ||
+ crypto_skcipher_alg_ivsize(ctr) != 16 ||
+ ctr->base.cra_blocksize != 1)
goto out_put_ctr;
- /* Not a stream cipher? */
- if (ctr->base.cra_blocksize != 1)
+ err = -ENAMETOOLONG;
+ if (snprintf(inst->alg.base.cra_name, CRYPTO_MAX_ALG_NAME,
+ "gcm(%s", ctr->base.cra_name + 4) >= CRYPTO_MAX_ALG_NAME)
goto out_put_ctr;
- err = -ENAMETOOLONG;
if (snprintf(inst->alg.base.cra_driver_name, CRYPTO_MAX_ALG_NAME,
"gcm_base(%s,%s)", ctr->base.cra_driver_name,
ghash_alg->cra_driver_name) >=
CRYPTO_MAX_ALG_NAME)
goto out_put_ctr;
- memcpy(inst->alg.base.cra_name, full_name, CRYPTO_MAX_ALG_NAME);
-
inst->alg.base.cra_flags = (ghash->base.cra_flags |
ctr->base.cra_flags) & CRYPTO_ALG_ASYNC;
inst->alg.base.cra_priority = (ghash->base.cra_priority +
@@ -728,7 +728,6 @@ static int crypto_gcm_create(struct crypto_template *tmpl, struct rtattr **tb)
{
const char *cipher_name;
char ctr_name[CRYPTO_MAX_ALG_NAME];
- char full_name[CRYPTO_MAX_ALG_NAME];
cipher_name = crypto_attr_alg_name(tb[1]);
if (IS_ERR(cipher_name))
@@ -738,12 +737,7 @@ static int crypto_gcm_create(struct crypto_template *tmpl, struct rtattr **tb)
CRYPTO_MAX_ALG_NAME)
return -ENAMETOOLONG;
- if (snprintf(full_name, CRYPTO_MAX_ALG_NAME, "gcm(%s)", cipher_name) >=
- CRYPTO_MAX_ALG_NAME)
- return -ENAMETOOLONG;
-
- return crypto_gcm_create_common(tmpl, tb, full_name,
- ctr_name, "ghash");
+ return crypto_gcm_create_common(tmpl, tb, ctr_name, "ghash");
}
static struct crypto_template crypto_gcm_tmpl = {
@@ -757,7 +751,6 @@ static int crypto_gcm_base_create(struct crypto_template *tmpl,
{
const char *ctr_name;
const char *ghash_name;
- char full_name[CRYPTO_MAX_ALG_NAME];
ctr_name = crypto_attr_alg_name(tb[1]);
if (IS_ERR(ctr_name))
@@ -767,12 +760,7 @@ static int crypto_gcm_base_create(struct crypto_template *tmpl,
if (IS_ERR(ghash_name))
return PTR_ERR(ghash_name);
- if (snprintf(full_name, CRYPTO_MAX_ALG_NAME, "gcm_base(%s,%s)",
- ctr_name, ghash_name) >= CRYPTO_MAX_ALG_NAME)
- return -ENAMETOOLONG;
-
- return crypto_gcm_create_common(tmpl, tb, full_name,
- ctr_name, ghash_name);
+ return crypto_gcm_create_common(tmpl, tb, ctr_name, ghash_name);
}
static struct crypto_template crypto_gcm_base_tmpl = {
diff --git a/crypto/skcipher.c b/crypto/skcipher.c
index e319421a32e7..c5501404f145 100644
--- a/crypto/skcipher.c
+++ b/crypto/skcipher.c
@@ -131,8 +131,13 @@ unmap_src:
memcpy(walk->dst.virt.addr, walk->page, n);
skcipher_unmap_dst(walk);
} else if (unlikely(walk->flags & SKCIPHER_WALK_SLOW)) {
- if (WARN_ON(err)) {
- /* unexpected case; didn't process all bytes */
+ if (err) {
+ /*
+ * Didn't process all bytes. Either the algorithm is
+ * broken, or this was the last step and it turned out
+ * the message wasn't evenly divisible into blocks but
+ * the algorithm requires it.
+ */
err = -EINVAL;
goto finish;
}
diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c
index b85dadb4501b..0a06872f1719 100644
--- a/drivers/acpi/acpi_lpss.c
+++ b/drivers/acpi/acpi_lpss.c
@@ -291,7 +291,7 @@ static const struct lpss_device_desc bsw_spi_dev_desc = {
#define ICPU(model) { X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, }
static const struct x86_cpu_id lpss_cpu_ids[] = {
- ICPU(INTEL_FAM6_ATOM_SILVERMONT1), /* Valleyview, Bay Trail */
+ ICPU(INTEL_FAM6_ATOM_SILVERMONT), /* Valleyview, Bay Trail */
ICPU(INTEL_FAM6_ATOM_AIRMONT), /* Braswell, Cherry Trail */
{}
};
diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index a538ffe3c8e8..56527c6dbf67 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -1074,10 +1074,6 @@ static int ghes_probe(struct platform_device *ghes_dev)
goto err;
}
- rc = ghes_edac_register(ghes, &ghes_dev->dev);
- if (rc < 0)
- goto err;
-
switch (generic->notify.type) {
case ACPI_HEST_NOTIFY_POLLED:
setup_deferrable_timer(&ghes->timer, ghes_poll_func,
@@ -1090,14 +1086,14 @@ static int ghes_probe(struct platform_device *ghes_dev)
if (rc) {
pr_err(GHES_PFX "Failed to map GSI to IRQ for generic hardware error source: %d\n",
generic->header.source_id);
- goto err_edac_unreg;
+ goto err;
}
rc = request_irq(ghes->irq, ghes_irq_func, IRQF_SHARED,
"GHES IRQ", ghes);
if (rc) {
pr_err(GHES_PFX "Failed to register IRQ for generic hardware error source: %d\n",
generic->header.source_id);
- goto err_edac_unreg;
+ goto err;
}
break;
@@ -1120,14 +1116,16 @@ static int ghes_probe(struct platform_device *ghes_dev)
default:
BUG();
}
+
platform_set_drvdata(ghes_dev, ghes);
+ ghes_edac_register(ghes, &ghes_dev->dev);
+
/* Handle any pending errors right away */
ghes_proc(ghes);
return 0;
-err_edac_unreg:
- ghes_edac_unregister(ghes);
+
err:
if (ghes) {
ghes_fini(ghes);
diff --git a/drivers/acpi/x86/utils.c b/drivers/acpi/x86/utils.c
index 95444f5f00a0..9997eac8fdec 100644
--- a/drivers/acpi/x86/utils.c
+++ b/drivers/acpi/x86/utils.c
@@ -54,7 +54,7 @@ static const struct always_present_id always_present_ids[] = {
* Bay / Cherry Trail PWM directly poked by GPU driver in win10,
* but Linux uses a separate PWM driver, harmless if not used.
*/
- ENTRY("80860F09", "1", ICPU(INTEL_FAM6_ATOM_SILVERMONT1), {}),
+ ENTRY("80860F09", "1", ICPU(INTEL_FAM6_ATOM_SILVERMONT), {}),
ENTRY("80862288", "1", ICPU(INTEL_FAM6_ATOM_AIRMONT), {}),
/*
* The INT0002 device is necessary to clear wakeup interrupt sources
diff --git a/drivers/ata/libata-zpodd.c b/drivers/ata/libata-zpodd.c
index 0ad96c647541..7017a81d53cf 100644
--- a/drivers/ata/libata-zpodd.c
+++ b/drivers/ata/libata-zpodd.c
@@ -51,38 +51,52 @@ static int eject_tray(struct ata_device *dev)
/* Per the spec, only slot type and drawer type ODD can be supported */
static enum odd_mech_type zpodd_get_mech_type(struct ata_device *dev)
{
- char buf[16];
+ char *buf;
unsigned int ret;
- struct rm_feature_desc *desc = (void *)(buf + 8);
+ struct rm_feature_desc *desc;
struct ata_taskfile tf;
static const char cdb[] = { GPCMD_GET_CONFIGURATION,
2, /* only 1 feature descriptor requested */
0, 3, /* 3, removable medium feature */
0, 0, 0,/* reserved */
- 0, sizeof(buf),
+ 0, 16,
0, 0, 0,
};
+ buf = kzalloc(16, GFP_KERNEL);
+ if (!buf)
+ return ODD_MECH_TYPE_UNSUPPORTED;
+ desc = (void *)(buf + 8);
+
ata_tf_init(dev, &tf);
tf.flags = ATA_TFLAG_ISADDR | ATA_TFLAG_DEVICE;
tf.command = ATA_CMD_PACKET;
tf.protocol = ATAPI_PROT_PIO;
- tf.lbam = sizeof(buf);
+ tf.lbam = 16;
ret = ata_exec_internal(dev, &tf, cdb, DMA_FROM_DEVICE,
- buf, sizeof(buf), 0);
- if (ret)
+ buf, 16, 0);
+ if (ret) {
+ kfree(buf);
return ODD_MECH_TYPE_UNSUPPORTED;
+ }
- if (be16_to_cpu(desc->feature_code) != 3)
+ if (be16_to_cpu(desc->feature_code) != 3) {
+ kfree(buf);
return ODD_MECH_TYPE_UNSUPPORTED;
+ }
- if (desc->mech_type == 0 && desc->load == 0 && desc->eject == 1)
+ if (desc->mech_type == 0 && desc->load == 0 && desc->eject == 1) {
+ kfree(buf);
return ODD_MECH_TYPE_SLOT;
- else if (desc->mech_type == 1 && desc->load == 0 && desc->eject == 1)
+ } else if (desc->mech_type == 1 && desc->load == 0 &&
+ desc->eject == 1) {
+ kfree(buf);
return ODD_MECH_TYPE_DRAWER;
- else
+ } else {
+ kfree(buf);
return ODD_MECH_TYPE_UNSUPPORTED;
+ }
}
/* Test if ODD is zero power ready by sense code */
diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index 93758b528d8f..32b52e6bd13b 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -533,11 +533,18 @@ ssize_t __weak cpu_show_l1tf(struct device *dev,
return sprintf(buf, "Not affected\n");
}
+ssize_t __weak cpu_show_mds(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ return sprintf(buf, "Not affected\n");
+}
+
static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL);
static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL);
static DEVICE_ATTR(spectre_v2, 0444, cpu_show_spectre_v2, NULL);
static DEVICE_ATTR(spec_store_bypass, 0444, cpu_show_spec_store_bypass, NULL);
static DEVICE_ATTR(l1tf, 0444, cpu_show_l1tf, NULL);
+static DEVICE_ATTR(mds, 0444, cpu_show_mds, NULL);
static struct attribute *cpu_root_vulnerabilities_attrs[] = {
&dev_attr_meltdown.attr,
@@ -545,6 +552,7 @@ static struct attribute *cpu_root_vulnerabilities_attrs[] = {
&dev_attr_spectre_v2.attr,
&dev_attr_spec_store_bypass.attr,
&dev_attr_l1tf.attr,
+ &dev_attr_mds.attr,
NULL
};
diff --git a/drivers/block/DAC960.c b/drivers/block/DAC960.c
index 245a879b036e..9d0bf8b8b902 100644
--- a/drivers/block/DAC960.c
+++ b/drivers/block/DAC960.c
@@ -2548,6 +2548,7 @@ static bool DAC960_RegisterBlockDevice(DAC960_Controller_T *Controller)
disk->major = MajorNumber;
disk->first_minor = n << DAC960_MaxPartitionsBits;
disk->fops = &DAC960_BlockDeviceOperations;
+ disk->events = DISK_EVENT_MEDIA_CHANGE;
}
/*
Indicate the Block Device Registration completed successfully,
diff --git a/drivers/block/amiflop.c b/drivers/block/amiflop.c
index 49908c74bfcb..12631bd8495d 100644
--- a/drivers/block/amiflop.c
+++ b/drivers/block/amiflop.c
@@ -1735,6 +1735,7 @@ static int __init fd_probe_drives(void)
disk->major = FLOPPY_MAJOR;
disk->first_minor = drive;
disk->fops = &floppy_fops;
+ disk->events = DISK_EVENT_MEDIA_CHANGE;
sprintf(disk->disk_name, "fd%d", drive);
disk->private_data = &unit[drive];
set_capacity(disk, 880*2);
diff --git a/drivers/block/ataflop.c b/drivers/block/ataflop.c
index 1dacc42e2dcf..9ba088707d32 100644
--- a/drivers/block/ataflop.c
+++ b/drivers/block/ataflop.c
@@ -1970,6 +1970,7 @@ static int __init atari_floppy_init (void)
unit[i].disk->first_minor = i;
sprintf(unit[i].disk->disk_name, "fd%d", i);
unit[i].disk->fops = &floppy_fops;
+ unit[i].disk->events = DISK_EVENT_MEDIA_CHANGE;
unit[i].disk->private_data = &unit[i];
set_capacity(unit[i].disk, MAX_DISK_SIZE * 2);
add_disk(unit[i].disk);
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index 3cfa5d578d12..d8ade9ca32e8 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -4212,6 +4212,7 @@ static int __init do_floppy_init(void)
disks[drive]->major = FLOPPY_MAJOR;
disks[drive]->first_minor = TOMINOR(drive);
disks[drive]->fops = &floppy_fops;
+ disks[drive]->events = DISK_EVENT_MEDIA_CHANGE;
sprintf(disks[drive]->disk_name, "fd%d", drive);
setup_timer(&motor_off_timer[drive], motor_off_callback, drive);
diff --git a/drivers/block/paride/pcd.c b/drivers/block/paride/pcd.c
index a026211afb51..e94d2816194c 100644
--- a/drivers/block/paride/pcd.c
+++ b/drivers/block/paride/pcd.c
@@ -329,6 +329,7 @@ static void pcd_init_units(void)
strcpy(disk->disk_name, cd->name); /* umm... */
disk->fops = &pcd_bdops;
disk->flags = GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE;
+ disk->events = DISK_EVENT_MEDIA_CHANGE;
}
}
diff --git a/drivers/block/paride/pd.c b/drivers/block/paride/pd.c
index 27a44b97393a..e5ede556f5c9 100644
--- a/drivers/block/paride/pd.c
+++ b/drivers/block/paride/pd.c
@@ -854,6 +854,7 @@ static void pd_probe_drive(struct pd_unit *disk)
p->fops = &pd_fops;
p->major = major;
p->first_minor = (disk - pd) << PD_BITS;
+ p->events = DISK_EVENT_MEDIA_CHANGE;
disk->gd = p;
p->private_data = disk;
p->queue = blk_init_queue(do_pd_request, &pd_lock);
diff --git a/drivers/block/paride/pf.c b/drivers/block/paride/pf.c
index eef7a91f667d..97b0dbae9369 100644
--- a/drivers/block/paride/pf.c
+++ b/drivers/block/paride/pf.c
@@ -304,6 +304,7 @@ static void __init pf_init_units(void)
disk->first_minor = unit;
strcpy(disk->disk_name, pf->name);
disk->fops = &pf_fops;
+ disk->events = DISK_EVENT_MEDIA_CHANGE;
if (!(*drives[unit])[D_PRT])
pf_drive_count++;
}
diff --git a/drivers/block/swim.c b/drivers/block/swim.c
index 0e902ad1c27b..3099226a55e5 100644
--- a/drivers/block/swim.c
+++ b/drivers/block/swim.c
@@ -875,6 +875,7 @@ static int swim_floppy_init(struct swim_priv *swd)
swd->unit[drive].disk->first_minor = drive;
sprintf(swd->unit[drive].disk->disk_name, "fd%d", drive);
swd->unit[drive].disk->fops = &floppy_fops;
+ swd->unit[drive].disk->events = DISK_EVENT_MEDIA_CHANGE;
swd->unit[drive].disk->private_data = &swd->unit[drive];
set_capacity(swd->unit[drive].disk, 2880);
add_disk(swd->unit[drive].disk);
diff --git a/drivers/block/swim3.c b/drivers/block/swim3.c
index 25a601507446..19c4666535d2 100644
--- a/drivers/block/swim3.c
+++ b/drivers/block/swim3.c
@@ -1242,6 +1242,7 @@ static int swim3_attach(struct macio_dev *mdev,
disk->first_minor = index;
disk->fops = &floppy_fops;
disk->private_data = &floppy_states[index];
+ disk->events = DISK_EVENT_MEDIA_CHANGE;
disk->flags |= GENHD_FL_REMOVABLE;
sprintf(disk->disk_name, "fd%d", index);
set_capacity(disk, 2880);
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 98d3e8f37cc0..a51044c8dfca 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -433,6 +433,8 @@ static int init_vq(struct virtio_blk *vblk)
if (err)
num_vqs = 1;
+ num_vqs = min_t(unsigned int, nr_cpu_ids, num_vqs);
+
vblk->vqs = kmalloc_array(num_vqs, sizeof(*vblk->vqs), GFP_KERNEL);
if (!vblk->vqs)
return -ENOMEM;
diff --git a/drivers/block/xsysace.c b/drivers/block/xsysace.c
index 14459d66ef0c..76aa86af96bf 100644
--- a/drivers/block/xsysace.c
+++ b/drivers/block/xsysace.c
@@ -1005,6 +1005,7 @@ static int ace_setup(struct ace_device *ace)
ace->gd->major = ace_major;
ace->gd->first_minor = ace->id * ACE_NUM_MINORS;
ace->gd->fops = &ace_fops;
+ ace->gd->events = DISK_EVENT_MEDIA_CHANGE;
ace->gd->queue = ace->queue;
ace->gd->private_data = ace;
snprintf(ace->gd->disk_name, 32, "xs%c", ace->id + 'a');
diff --git a/drivers/cdrom/gdrom.c b/drivers/cdrom/gdrom.c
index 72cd96a8eb19..eff92053a3bf 100644
--- a/drivers/cdrom/gdrom.c
+++ b/drivers/cdrom/gdrom.c
@@ -807,6 +807,7 @@ static int probe_gdrom(struct platform_device *devptr)
goto probe_fail_cdrom_register;
}
gd.disk->fops = &gdrom_bdops;
+ gd.disk->events = DISK_EVENT_MEDIA_CHANGE;
/* latch on to the interrupt */
err = gdrom_set_interrupt_handlers();
if (err)
diff --git a/drivers/char/ipmi/ipmi_ssif.c b/drivers/char/ipmi/ipmi_ssif.c
index 42d936779f64..d3a4c8298129 100644
--- a/drivers/char/ipmi/ipmi_ssif.c
+++ b/drivers/char/ipmi/ipmi_ssif.c
@@ -705,12 +705,16 @@ static void msg_done_handler(struct ssif_info *ssif_info, int result,
/* End of read */
len = ssif_info->multi_len;
data = ssif_info->data;
- } else if (blocknum != ssif_info->multi_pos) {
+ } else if (blocknum + 1 != ssif_info->multi_pos) {
/*
* Out of sequence block, just abort. Block
* numbers start at zero for the second block,
* but multi_pos starts at one, so the +1.
*/
+ if (ssif_info->ssif_debug & SSIF_DEBUG_MSG)
+ dev_dbg(&ssif_info->client->dev,
+ "Received message out of sequence, expected %u, got %u\n",
+ ssif_info->multi_pos - 1, blocknum);
result = -EIO;
} else {
ssif_inc_stat(ssif_info, received_message_parts);
diff --git a/drivers/clk/rockchip/clk-rk3288.c b/drivers/clk/rockchip/clk-rk3288.c
index 68ba7d4105e7..04a963d9392a 100644
--- a/drivers/clk/rockchip/clk-rk3288.c
+++ b/drivers/clk/rockchip/clk-rk3288.c
@@ -198,7 +198,7 @@ PNAME(mux_hsadcout_p) = { "hsadc_src", "ext_hsadc" };
PNAME(mux_edp_24m_p) = { "ext_edp_24m", "xin24m" };
PNAME(mux_tspout_p) = { "cpll", "gpll", "npll", "xin27m" };
-PNAME(mux_aclk_vcodec_pre_p) = { "aclk_vepu", "aclk_vdpu" };
+PNAME(mux_aclk_vcodec_pre_p) = { "aclk_vdpu", "aclk_vepu" };
PNAME(mux_usbphy480m_p) = { "sclk_otgphy1_480m", "sclk_otgphy2_480m",
"sclk_otgphy0_480m" };
PNAME(mux_hsicphy480m_p) = { "cpll", "gpll", "usbphy480m_src" };
@@ -399,7 +399,7 @@ static struct rockchip_clk_branch rk3288_clk_branches[] __initdata = {
COMPOSITE(0, "aclk_vdpu", mux_pll_src_cpll_gpll_usb480m_p, 0,
RK3288_CLKSEL_CON(32), 14, 2, MFLAGS, 8, 5, DFLAGS,
RK3288_CLKGATE_CON(3), 11, GFLAGS),
- MUXGRF(0, "aclk_vcodec_pre", mux_aclk_vcodec_pre_p, 0,
+ MUXGRF(0, "aclk_vcodec_pre", mux_aclk_vcodec_pre_p, CLK_SET_RATE_PARENT,
RK3288_GRF_SOC_CON(0), 7, 1, MFLAGS),
GATE(ACLK_VCODEC, "aclk_vcodec", "aclk_vcodec_pre", 0,
RK3288_CLKGATE_CON(9), 0, GFLAGS),
diff --git a/drivers/clk/rockchip/clk-rk3328.c b/drivers/clk/rockchip/clk-rk3328.c
index 559abf76891e..33d1cf4e6d80 100644
--- a/drivers/clk/rockchip/clk-rk3328.c
+++ b/drivers/clk/rockchip/clk-rk3328.c
@@ -458,7 +458,7 @@ static struct rockchip_clk_branch rk3328_clk_branches[] __initdata = {
RK3328_CLKSEL_CON(35), 15, 1, MFLAGS, 8, 7, DFLAGS,
RK3328_CLKGATE_CON(2), 12, GFLAGS),
COMPOSITE(SCLK_CRYPTO, "clk_crypto", mux_2plls_p, 0,
- RK3328_CLKSEL_CON(20), 7, 1, MFLAGS, 0, 7, DFLAGS,
+ RK3328_CLKSEL_CON(20), 7, 1, MFLAGS, 0, 5, DFLAGS,
RK3328_CLKGATE_CON(2), 4, GFLAGS),
COMPOSITE_NOMUX(SCLK_TSADC, "clk_tsadc", "clk_24m", 0,
RK3328_CLKSEL_CON(22), 0, 10, DFLAGS,
@@ -550,15 +550,15 @@ static struct rockchip_clk_branch rk3328_clk_branches[] __initdata = {
GATE(0, "hclk_rkvenc_niu", "hclk_rkvenc", CLK_IGNORE_UNUSED,
RK3328_CLKGATE_CON(25), 1, GFLAGS),
GATE(ACLK_H265, "aclk_h265", "aclk_rkvenc", 0,
- RK3328_CLKGATE_CON(25), 0, GFLAGS),
+ RK3328_CLKGATE_CON(25), 2, GFLAGS),
GATE(PCLK_H265, "pclk_h265", "hclk_rkvenc", 0,
- RK3328_CLKGATE_CON(25), 1, GFLAGS),
+ RK3328_CLKGATE_CON(25), 3, GFLAGS),
GATE(ACLK_H264, "aclk_h264", "aclk_rkvenc", 0,
- RK3328_CLKGATE_CON(25), 0, GFLAGS),
+ RK3328_CLKGATE_CON(25), 4, GFLAGS),
GATE(HCLK_H264, "hclk_h264", "hclk_rkvenc", 0,
- RK3328_CLKGATE_CON(25), 1, GFLAGS),
+ RK3328_CLKGATE_CON(25), 5, GFLAGS),
GATE(ACLK_AXISRAM, "aclk_axisram", "aclk_rkvenc", CLK_IGNORE_UNUSED,
- RK3328_CLKGATE_CON(25), 0, GFLAGS),
+ RK3328_CLKGATE_CON(25), 6, GFLAGS),
COMPOSITE(SCLK_VENC_CORE, "sclk_venc_core", mux_4plls_p, 0,
RK3328_CLKSEL_CON(51), 14, 2, MFLAGS, 8, 5, DFLAGS,
@@ -663,7 +663,7 @@ static struct rockchip_clk_branch rk3328_clk_branches[] __initdata = {
/* PD_GMAC */
COMPOSITE(ACLK_GMAC, "aclk_gmac", mux_2plls_hdmiphy_p, 0,
- RK3328_CLKSEL_CON(35), 6, 2, MFLAGS, 0, 5, DFLAGS,
+ RK3328_CLKSEL_CON(25), 6, 2, MFLAGS, 0, 5, DFLAGS,
RK3328_CLKGATE_CON(3), 2, GFLAGS),
COMPOSITE_NOMUX(PCLK_GMAC, "pclk_gmac", "aclk_gmac", 0,
RK3328_CLKSEL_CON(25), 8, 3, DFLAGS,
@@ -733,7 +733,7 @@ static struct rockchip_clk_branch rk3328_clk_branches[] __initdata = {
/* PD_PERI */
GATE(0, "aclk_peri_noc", "aclk_peri", CLK_IGNORE_UNUSED, RK3328_CLKGATE_CON(19), 11, GFLAGS),
- GATE(ACLK_USB3OTG, "aclk_usb3otg", "aclk_peri", 0, RK3328_CLKGATE_CON(19), 4, GFLAGS),
+ GATE(ACLK_USB3OTG, "aclk_usb3otg", "aclk_peri", 0, RK3328_CLKGATE_CON(19), 14, GFLAGS),
GATE(HCLK_SDMMC, "hclk_sdmmc", "hclk_peri", 0, RK3328_CLKGATE_CON(19), 0, GFLAGS),
GATE(HCLK_SDIO, "hclk_sdio", "hclk_peri", 0, RK3328_CLKGATE_CON(19), 1, GFLAGS),
@@ -894,7 +894,7 @@ static void __init rk3328_clk_init(struct device_node *np)
&rk3328_cpuclk_data, rk3328_cpuclk_rates,
ARRAY_SIZE(rk3328_cpuclk_rates));
- rockchip_register_softrst(np, 11, reg_base + RK3328_SOFTRST_CON(0),
+ rockchip_register_softrst(np, 12, reg_base + RK3328_SOFTRST_CON(0),
ROCKCHIP_SOFTRST_HIWORD_MASK);
rockchip_register_restart_notifier(ctx, RK3328_GLB_SRST_FST, NULL);
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index b97c7afe970e..6f8f913f096e 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -2052,7 +2052,7 @@ static const struct pstate_funcs knl_funcs = {
static const struct x86_cpu_id intel_pstate_cpu_ids[] = {
ICPU(INTEL_FAM6_SANDYBRIDGE, core_funcs),
ICPU(INTEL_FAM6_SANDYBRIDGE_X, core_funcs),
- ICPU(INTEL_FAM6_ATOM_SILVERMONT1, silvermont_funcs),
+ ICPU(INTEL_FAM6_ATOM_SILVERMONT, silvermont_funcs),
ICPU(INTEL_FAM6_IVYBRIDGE, core_funcs),
ICPU(INTEL_FAM6_HASWELL_CORE, core_funcs),
ICPU(INTEL_FAM6_BROADWELL_CORE, core_funcs),
@@ -2069,7 +2069,7 @@ static const struct x86_cpu_id intel_pstate_cpu_ids[] = {
ICPU(INTEL_FAM6_XEON_PHI_KNL, knl_funcs),
ICPU(INTEL_FAM6_XEON_PHI_KNM, knl_funcs),
ICPU(INTEL_FAM6_ATOM_GOLDMONT, core_funcs),
- ICPU(INTEL_FAM6_ATOM_GEMINI_LAKE, core_funcs),
+ ICPU(INTEL_FAM6_ATOM_GOLDMONT_PLUS, core_funcs),
ICPU(INTEL_FAM6_SKYLAKE_X, core_funcs),
{}
};
diff --git a/drivers/crypto/ccp/psp-dev.c b/drivers/crypto/ccp/psp-dev.c
index 6c65dbe3f8b0..c961569a9407 100644
--- a/drivers/crypto/ccp/psp-dev.c
+++ b/drivers/crypto/ccp/psp-dev.c
@@ -984,7 +984,7 @@ void psp_pci_init(void)
rc = sev_platform_init(&error);
if (rc) {
dev_err(sp->dev, "SEV: failed to INIT error %#x\n", error);
- goto err;
+ return;
}
dev_info(sp->dev, "SEV API:%d.%d build:%d\n", psp_master->api_major,
diff --git a/drivers/crypto/sunxi-ss/sun4i-ss-hash.c b/drivers/crypto/sunxi-ss/sun4i-ss-hash.c
index 0de2f62d51ff..ec16ec2e284d 100644
--- a/drivers/crypto/sunxi-ss/sun4i-ss-hash.c
+++ b/drivers/crypto/sunxi-ss/sun4i-ss-hash.c
@@ -250,7 +250,10 @@ static int sun4i_hash(struct ahash_request *areq)
}
} else {
/* Since we have the flag final, we can go up to modulo 4 */
- end = ((areq->nbytes + op->len) / 4) * 4 - op->len;
+ if (areq->nbytes < 4)
+ end = 0;
+ else
+ end = ((areq->nbytes + op->len) / 4) * 4 - op->len;
}
/* TODO if SGlen % 4 and op->len == 0 then DMA */
diff --git a/drivers/crypto/vmx/aesp8-ppc.pl b/drivers/crypto/vmx/aesp8-ppc.pl
index d6a9f63d65ba..de78282b8f44 100644
--- a/drivers/crypto/vmx/aesp8-ppc.pl
+++ b/drivers/crypto/vmx/aesp8-ppc.pl
@@ -1854,7 +1854,7 @@ Lctr32_enc8x_three:
stvx_u $out1,$x10,$out
stvx_u $out2,$x20,$out
addi $out,$out,0x30
- b Lcbc_dec8x_done
+ b Lctr32_enc8x_done
.align 5
Lctr32_enc8x_two:
@@ -1866,7 +1866,7 @@ Lctr32_enc8x_two:
stvx_u $out0,$x00,$out
stvx_u $out1,$x10,$out
addi $out,$out,0x20
- b Lcbc_dec8x_done
+ b Lctr32_enc8x_done
.align 5
Lctr32_enc8x_one:
diff --git a/drivers/dma/dma-axi-dmac.c b/drivers/dma/dma-axi-dmac.c
index 7f0b9aa15867..9887f2a14aa9 100644
--- a/drivers/dma/dma-axi-dmac.c
+++ b/drivers/dma/dma-axi-dmac.c
@@ -451,7 +451,7 @@ static struct dma_async_tx_descriptor *axi_dmac_prep_interleaved(
if (chan->hw_2d) {
if (!axi_dmac_check_len(chan, xt->sgl[0].size) ||
- !axi_dmac_check_len(chan, xt->numf))
+ xt->numf == 0)
return NULL;
if (xt->sgl[0].size + dst_icg > chan->max_length ||
xt->sgl[0].size + src_icg > chan->max_length)
diff --git a/drivers/dma/tegra210-adma.c b/drivers/dma/tegra210-adma.c
index b26256f23d67..08b10274284a 100644
--- a/drivers/dma/tegra210-adma.c
+++ b/drivers/dma/tegra210-adma.c
@@ -786,6 +786,7 @@ static int tegra_adma_remove(struct platform_device *pdev)
struct tegra_adma *tdma = platform_get_drvdata(pdev);
int i;
+ of_dma_controller_free(pdev->dev.of_node);
dma_async_device_unregister(&tdma->dma_dev);
for (i = 0; i < tdma->nr_channels; ++i)
diff --git a/drivers/edac/ghes_edac.c b/drivers/edac/ghes_edac.c
index 6718d66fe2e3..89c90c1a2da6 100644
--- a/drivers/edac/ghes_edac.c
+++ b/drivers/edac/ghes_edac.c
@@ -195,10 +195,8 @@ void ghes_edac_report_mem_error(struct ghes *ghes, int sev,
char *p;
u8 grain_bits;
- if (!pvt) {
- pr_err("Internal error: Can't find EDAC structure\n");
+ if (!pvt)
return;
- }
/*
* We can do the locking below because GHES defers error processing
@@ -451,7 +449,7 @@ int ghes_edac_register(struct ghes *ghes, struct device *dev)
/* Check if safe to enable on this system */
idx = acpi_match_platform_list(plat_list);
if (!force_load && idx < 0)
- return 0;
+ return -ENODEV;
/*
* We have only one logical memory controller to which all DIMMs belong.
diff --git a/drivers/edac/pnd2_edac.c b/drivers/edac/pnd2_edac.c
index df28b65358d2..903a4f1fadcc 100644
--- a/drivers/edac/pnd2_edac.c
+++ b/drivers/edac/pnd2_edac.c
@@ -1541,7 +1541,7 @@ static struct dunit_ops dnv_ops = {
static const struct x86_cpu_id pnd2_cpuids[] = {
{ X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_GOLDMONT, 0, (kernel_ulong_t)&apl_ops },
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_DENVERTON, 0, (kernel_ulong_t)&dnv_ops },
+ { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_GOLDMONT_X, 0, (kernel_ulong_t)&dnv_ops },
{ }
};
MODULE_DEVICE_TABLE(x86cpu, pnd2_cpuids);
diff --git a/drivers/gpio/gpio-aspeed.c b/drivers/gpio/gpio-aspeed.c
index f18b6dd07af5..eb190f68387c 100644
--- a/drivers/gpio/gpio-aspeed.c
+++ b/drivers/gpio/gpio-aspeed.c
@@ -861,6 +861,8 @@ static int __init aspeed_gpio_probe(struct platform_device *pdev)
gpio->offset_timer =
devm_kzalloc(&pdev->dev, gpio->chip.ngpio, GFP_KERNEL);
+ if (!gpio->offset_timer)
+ return -ENOMEM;
return aspeed_gpio_setup_irqs(gpio, pdev);
}
diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c
index 3f8654a6bee5..b7550e0e576a 100644
--- a/drivers/gpu/drm/drm_fb_helper.c
+++ b/drivers/gpu/drm/drm_fb_helper.c
@@ -607,20 +607,19 @@ static struct sysrq_key_op sysrq_drm_fb_helper_restore_op = { };
static void dpms_legacy(struct drm_fb_helper *fb_helper, int dpms_mode)
{
struct drm_device *dev = fb_helper->dev;
- struct drm_crtc *crtc;
struct drm_connector *connector;
+ struct drm_mode_set *modeset;
int i, j;
drm_modeset_lock_all(dev);
for (i = 0; i < fb_helper->crtc_count; i++) {
- crtc = fb_helper->crtc_info[i].mode_set.crtc;
+ modeset = &fb_helper->crtc_info[i].mode_set;
- if (!crtc->enabled)
+ if (!modeset->crtc->enabled)
continue;
- /* Walk the connectors & encoders on this fb turning them on/off */
- drm_fb_helper_for_each_connector(fb_helper, j) {
- connector = fb_helper->connector_info[j]->connector;
+ for (j = 0; j < modeset->num_connectors; j++) {
+ connector = modeset->connectors[j];
connector->funcs->dpms(connector, dpms_mode);
drm_object_property_set_value(&connector->base,
dev->mode_config.dpms_property, dpms_mode);
diff --git a/drivers/gpu/drm/i915/gvt/mmio_context.c b/drivers/gpu/drm/i915/gvt/mmio_context.c
index c563457de000..3d2d36df3603 100644
--- a/drivers/gpu/drm/i915/gvt/mmio_context.c
+++ b/drivers/gpu/drm/i915/gvt/mmio_context.c
@@ -79,7 +79,7 @@ static struct engine_mmio gen8_engine_mmio_list[] __cacheline_aligned = {
{BCS, RING_MI_MODE(BLT_RING_BASE), 0xffff, false}, /* 0x2209c */
{BCS, RING_INSTPM(BLT_RING_BASE), 0xffff, false}, /* 0x220c0 */
{BCS, RING_HWSTAM(BLT_RING_BASE), 0x0, false}, /* 0x22098 */
- {BCS, RING_EXCC(BLT_RING_BASE), 0x0, false}, /* 0x22028 */
+ {BCS, RING_EXCC(BLT_RING_BASE), 0xffff, false}, /* 0x22028 */
{RCS, INVALID_MMIO_REG, 0, false } /* Terminated */
};
@@ -130,7 +130,7 @@ static struct engine_mmio gen9_engine_mmio_list[] __cacheline_aligned = {
{BCS, RING_MI_MODE(BLT_RING_BASE), 0xffff, false}, /* 0x2209c */
{BCS, RING_INSTPM(BLT_RING_BASE), 0xffff, false}, /* 0x220c0 */
{BCS, RING_HWSTAM(BLT_RING_BASE), 0x0, false}, /* 0x22098 */
- {BCS, RING_EXCC(BLT_RING_BASE), 0x0, false}, /* 0x22028 */
+ {BCS, RING_EXCC(BLT_RING_BASE), 0xffff, false}, /* 0x22028 */
{VCS2, RING_EXCC(GEN8_BSD2_RING_BASE), 0xffff, false}, /* 0x1c028 */
diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi.c b/drivers/gpu/drm/mediatek/mtk_hdmi.c
index bcfe885c1453..61fb3d4f974b 100644
--- a/drivers/gpu/drm/mediatek/mtk_hdmi.c
+++ b/drivers/gpu/drm/mediatek/mtk_hdmi.c
@@ -1509,6 +1509,7 @@ static int mtk_hdmi_dt_parse_pdata(struct mtk_hdmi *hdmi,
of_node_put(remote);
hdmi->ddc_adpt = of_find_i2c_adapter_by_node(i2c_np);
+ of_node_put(i2c_np);
if (!hdmi->ddc_adpt) {
dev_err(dev, "Failed to get ddc i2c adapter by node\n");
return -EINVAL;
diff --git a/drivers/gpu/drm/meson/meson_drv.c b/drivers/gpu/drm/meson/meson_drv.c
index 6c2b31595dce..246c950a4f4f 100644
--- a/drivers/gpu/drm/meson/meson_drv.c
+++ b/drivers/gpu/drm/meson/meson_drv.c
@@ -93,6 +93,18 @@ static irqreturn_t meson_irq(int irq, void *arg)
return IRQ_HANDLED;
}
+static int meson_dumb_create(struct drm_file *file, struct drm_device *dev,
+ struct drm_mode_create_dumb *args)
+{
+ /*
+ * We need 64bytes aligned stride, and PAGE aligned size
+ */
+ args->pitch = ALIGN(DIV_ROUND_UP(args->width * args->bpp, 8), SZ_64);
+ args->size = PAGE_ALIGN(args->pitch * args->height);
+
+ return drm_gem_cma_dumb_create_internal(file, dev, args);
+}
+
DEFINE_DRM_GEM_CMA_FOPS(fops);
static struct drm_driver meson_driver = {
@@ -115,7 +127,7 @@ static struct drm_driver meson_driver = {
.gem_prime_mmap = drm_gem_cma_prime_mmap,
/* GEM Ops */
- .dumb_create = drm_gem_cma_dumb_create,
+ .dumb_create = meson_dumb_create,
.dumb_destroy = drm_gem_dumb_destroy,
.dumb_map_offset = drm_gem_cma_dumb_map_offset,
.gem_free_object_unlocked = drm_gem_cma_free_object,
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c
index 76d63de5921d..e7dda3089cc0 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c
@@ -427,6 +427,14 @@ static int rockchip_drm_platform_remove(struct platform_device *pdev)
return 0;
}
+static void rockchip_drm_platform_shutdown(struct platform_device *pdev)
+{
+ struct drm_device *drm = platform_get_drvdata(pdev);
+
+ if (drm)
+ drm_atomic_helper_shutdown(drm);
+}
+
static const struct of_device_id rockchip_drm_dt_ids[] = {
{ .compatible = "rockchip,display-subsystem", },
{ /* sentinel */ },
@@ -436,6 +444,7 @@ MODULE_DEVICE_TABLE(of, rockchip_drm_dt_ids);
static struct platform_driver rockchip_drm_platform_driver = {
.probe = rockchip_drm_platform_probe,
.remove = rockchip_drm_platform_remove,
+ .shutdown = rockchip_drm_platform_shutdown,
.driver = {
.name = "rockchip-drm",
.of_match_table = rockchip_drm_dt_ids,
diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c
index 622dab6c4347..90a56c6724b5 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_vm.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c
@@ -284,8 +284,6 @@ static void ttm_bo_vm_open(struct vm_area_struct *vma)
struct ttm_buffer_object *bo =
(struct ttm_buffer_object *)vma->vm_private_data;
- WARN_ON(bo->bdev->dev_mapping != vma->vm_file->f_mapping);
-
(void)ttm_bo_reference(bo);
}
diff --git a/drivers/hid/hid-debug.c b/drivers/hid/hid-debug.c
index ef34696abcd7..ebe252f81b5c 100644
--- a/drivers/hid/hid-debug.c
+++ b/drivers/hid/hid-debug.c
@@ -1059,10 +1059,15 @@ static int hid_debug_rdesc_show(struct seq_file *f, void *p)
seq_printf(f, "\n\n");
/* dump parsed data and input mappings */
+ if (down_interruptible(&hdev->driver_input_lock))
+ return 0;
+
hid_dump_device(hdev, f);
seq_printf(f, "\n");
hid_dump_input_mapping(hdev, f);
+ up(&hdev->driver_input_lock);
+
return 0;
}
diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c
index b80a8301dff5..676b9fa7748e 100644
--- a/drivers/hid/hid-input.c
+++ b/drivers/hid/hid-input.c
@@ -890,6 +890,7 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel
case 0x1b8: map_key_clear(KEY_VIDEO); break;
case 0x1bc: map_key_clear(KEY_MESSENGER); break;
case 0x1bd: map_key_clear(KEY_INFO); break;
+ case 0x1cb: map_key_clear(KEY_ASSISTANT); break;
case 0x201: map_key_clear(KEY_NEW); break;
case 0x202: map_key_clear(KEY_OPEN); break;
case 0x203: map_key_clear(KEY_CLOSE); break;
diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c
index 41b39464ded8..fc740f6a34f5 100644
--- a/drivers/hid/hid-logitech-hidpp.c
+++ b/drivers/hid/hid-logitech-hidpp.c
@@ -1907,6 +1907,13 @@ static int hidpp_ff_init(struct hidpp_device *hidpp, u8 feature_index)
kfree(data);
return -ENOMEM;
}
+ data->wq = create_singlethread_workqueue("hidpp-ff-sendqueue");
+ if (!data->wq) {
+ kfree(data->effect_ids);
+ kfree(data);
+ return -ENOMEM;
+ }
+
data->hidpp = hidpp;
data->feature_index = feature_index;
data->version = version;
@@ -1951,7 +1958,6 @@ static int hidpp_ff_init(struct hidpp_device *hidpp, u8 feature_index)
/* ignore boost value at response.fap.params[2] */
/* init the hardware command queue */
- data->wq = create_singlethread_workqueue("hidpp-ff-sendqueue");
atomic_set(&data->workqueue_size, 0);
/* initialize with zero autocenter to get wheel in usable state */
diff --git a/drivers/hwmon/f71805f.c b/drivers/hwmon/f71805f.c
index 73c681162653..623736d2a7c1 100644
--- a/drivers/hwmon/f71805f.c
+++ b/drivers/hwmon/f71805f.c
@@ -96,17 +96,23 @@ superio_select(int base, int ld)
outb(ld, base + 1);
}
-static inline void
+static inline int
superio_enter(int base)
{
+ if (!request_muxed_region(base, 2, DRVNAME))
+ return -EBUSY;
+
outb(0x87, base);
outb(0x87, base);
+
+ return 0;
}
static inline void
superio_exit(int base)
{
outb(0xaa, base);
+ release_region(base, 2);
}
/*
@@ -1561,7 +1567,7 @@ exit:
static int __init f71805f_find(int sioaddr, unsigned short *address,
struct f71805f_sio_data *sio_data)
{
- int err = -ENODEV;
+ int err;
u16 devid;
static const char * const names[] = {
@@ -1569,8 +1575,11 @@ static int __init f71805f_find(int sioaddr, unsigned short *address,
"F71872F/FG or F71806F/FG",
};
- superio_enter(sioaddr);
+ err = superio_enter(sioaddr);
+ if (err)
+ return err;
+ err = -ENODEV;
devid = superio_inw(sioaddr, SIO_REG_MANID);
if (devid != SIO_FINTEK_ID)
goto exit;
diff --git a/drivers/hwmon/pc87427.c b/drivers/hwmon/pc87427.c
index dc5a9d5ada51..81a05cd1a512 100644
--- a/drivers/hwmon/pc87427.c
+++ b/drivers/hwmon/pc87427.c
@@ -106,6 +106,13 @@ static const char *logdev_str[2] = { DRVNAME " FMC", DRVNAME " HMC" };
#define LD_IN 1
#define LD_TEMP 1
+static inline int superio_enter(int sioaddr)
+{
+ if (!request_muxed_region(sioaddr, 2, DRVNAME))
+ return -EBUSY;
+ return 0;
+}
+
static inline void superio_outb(int sioaddr, int reg, int val)
{
outb(reg, sioaddr);
@@ -122,6 +129,7 @@ static inline void superio_exit(int sioaddr)
{
outb(0x02, sioaddr);
outb(0x02, sioaddr + 1);
+ release_region(sioaddr, 2);
}
/*
@@ -1220,7 +1228,11 @@ static int __init pc87427_find(int sioaddr, struct pc87427_sio_data *sio_data)
{
u16 val;
u8 cfg, cfg_b;
- int i, err = 0;
+ int i, err;
+
+ err = superio_enter(sioaddr);
+ if (err)
+ return err;
/* Identify device */
val = force_id ? force_id : superio_inb(sioaddr, SIOREG_DEVID);
diff --git a/drivers/hwmon/smsc47b397.c b/drivers/hwmon/smsc47b397.c
index 6bd200756560..cbdb5c4991ae 100644
--- a/drivers/hwmon/smsc47b397.c
+++ b/drivers/hwmon/smsc47b397.c
@@ -72,14 +72,19 @@ static inline void superio_select(int ld)
superio_outb(0x07, ld);
}
-static inline void superio_enter(void)
+static inline int superio_enter(void)
{
+ if (!request_muxed_region(REG, 2, DRVNAME))
+ return -EBUSY;
+
outb(0x55, REG);
+ return 0;
}
static inline void superio_exit(void)
{
outb(0xAA, REG);
+ release_region(REG, 2);
}
#define SUPERIO_REG_DEVID 0x20
@@ -300,8 +305,12 @@ static int __init smsc47b397_find(void)
u8 id, rev;
char *name;
unsigned short addr;
+ int err;
+
+ err = superio_enter();
+ if (err)
+ return err;
- superio_enter();
id = force_id ? force_id : superio_inb(SUPERIO_REG_DEVID);
switch (id) {
diff --git a/drivers/hwmon/smsc47m1.c b/drivers/hwmon/smsc47m1.c
index c7b6a425e2c0..5eeac9853d0a 100644
--- a/drivers/hwmon/smsc47m1.c
+++ b/drivers/hwmon/smsc47m1.c
@@ -73,16 +73,21 @@ superio_inb(int reg)
/* logical device for fans is 0x0A */
#define superio_select() superio_outb(0x07, 0x0A)
-static inline void
+static inline int
superio_enter(void)
{
+ if (!request_muxed_region(REG, 2, DRVNAME))
+ return -EBUSY;
+
outb(0x55, REG);
+ return 0;
}
static inline void
superio_exit(void)
{
outb(0xAA, REG);
+ release_region(REG, 2);
}
#define SUPERIO_REG_ACT 0x30
@@ -531,8 +536,12 @@ static int __init smsc47m1_find(struct smsc47m1_sio_data *sio_data)
{
u8 val;
unsigned short addr;
+ int err;
+
+ err = superio_enter();
+ if (err)
+ return err;
- superio_enter();
val = force_id ? force_id : superio_inb(SUPERIO_REG_DEVID);
/*
@@ -608,13 +617,14 @@ static int __init smsc47m1_find(struct smsc47m1_sio_data *sio_data)
static void smsc47m1_restore(const struct smsc47m1_sio_data *sio_data)
{
if ((sio_data->activate & 0x01) == 0) {
- superio_enter();
- superio_select();
-
- pr_info("Disabling device\n");
- superio_outb(SUPERIO_REG_ACT, sio_data->activate);
-
- superio_exit();
+ if (!superio_enter()) {
+ superio_select();
+ pr_info("Disabling device\n");
+ superio_outb(SUPERIO_REG_ACT, sio_data->activate);
+ superio_exit();
+ } else {
+ pr_warn("Failed to disable device\n");
+ }
}
}
diff --git a/drivers/hwmon/vt1211.c b/drivers/hwmon/vt1211.c
index 3a6bfa51cb94..95d5e8ec8b7f 100644
--- a/drivers/hwmon/vt1211.c
+++ b/drivers/hwmon/vt1211.c
@@ -226,15 +226,21 @@ static inline void superio_select(int sio_cip, int ldn)
outb(ldn, sio_cip + 1);
}
-static inline void superio_enter(int sio_cip)
+static inline int superio_enter(int sio_cip)
{
+ if (!request_muxed_region(sio_cip, 2, DRVNAME))
+ return -EBUSY;
+
outb(0x87, sio_cip);
outb(0x87, sio_cip);
+
+ return 0;
}
static inline void superio_exit(int sio_cip)
{
outb(0xaa, sio_cip);
+ release_region(sio_cip, 2);
}
/* ---------------------------------------------------------------------
@@ -1282,11 +1288,14 @@ EXIT:
static int __init vt1211_find(int sio_cip, unsigned short *address)
{
- int err = -ENODEV;
+ int err;
int devid;
- superio_enter(sio_cip);
+ err = superio_enter(sio_cip);
+ if (err)
+ return err;
+ err = -ENODEV;
devid = force_id ? force_id : superio_inb(sio_cip, SIO_VT1211_DEVID);
if (devid != SIO_VT1211_ID)
goto EXIT;
diff --git a/drivers/hwmon/w83627hf.c b/drivers/hwmon/w83627hf.c
index 8ac89d0781cc..a575e1cdb81a 100644
--- a/drivers/hwmon/w83627hf.c
+++ b/drivers/hwmon/w83627hf.c
@@ -130,17 +130,23 @@ superio_select(struct w83627hf_sio_data *sio, int ld)
outb(ld, sio->sioaddr + 1);
}
-static inline void
+static inline int
superio_enter(struct w83627hf_sio_data *sio)
{
+ if (!request_muxed_region(sio->sioaddr, 2, DRVNAME))
+ return -EBUSY;
+
outb(0x87, sio->sioaddr);
outb(0x87, sio->sioaddr);
+
+ return 0;
}
static inline void
superio_exit(struct w83627hf_sio_data *sio)
{
outb(0xAA, sio->sioaddr);
+ release_region(sio->sioaddr, 2);
}
#define W627_DEVID 0x52
@@ -1278,7 +1284,7 @@ static DEVICE_ATTR_RO(name);
static int __init w83627hf_find(int sioaddr, unsigned short *addr,
struct w83627hf_sio_data *sio_data)
{
- int err = -ENODEV;
+ int err;
u16 val;
static __initconst char *const names[] = {
@@ -1290,7 +1296,11 @@ static int __init w83627hf_find(int sioaddr, unsigned short *addr,
};
sio_data->sioaddr = sioaddr;
- superio_enter(sio_data);
+ err = superio_enter(sio_data);
+ if (err)
+ return err;
+
+ err = -ENODEV;
val = force_id ? force_id : superio_inb(sio_data, DEVID);
switch (val) {
case W627_DEVID:
@@ -1644,9 +1654,21 @@ static int w83627thf_read_gpio5(struct platform_device *pdev)
struct w83627hf_sio_data *sio_data = dev_get_platdata(&pdev->dev);
int res = 0xff, sel;
- superio_enter(sio_data);
+ if (superio_enter(sio_data)) {
+ /*
+ * Some other driver reserved the address space for itself.
+ * We don't want to fail driver instantiation because of that,
+ * so display a warning and keep going.
+ */
+ dev_warn(&pdev->dev,
+ "Can not read VID data: Failed to enable SuperIO access\n");
+ return res;
+ }
+
superio_select(sio_data, W83627HF_LD_GPIO5);
+ res = 0xff;
+
/* Make sure these GPIO pins are enabled */
if (!(superio_inb(sio_data, W83627THF_GPIO5_EN) & (1<<3))) {
dev_dbg(&pdev->dev, "GPIO5 disabled, no VID function\n");
@@ -1677,7 +1699,17 @@ static int w83687thf_read_vid(struct platform_device *pdev)
struct w83627hf_sio_data *sio_data = dev_get_platdata(&pdev->dev);
int res = 0xff;
- superio_enter(sio_data);
+ if (superio_enter(sio_data)) {
+ /*
+ * Some other driver reserved the address space for itself.
+ * We don't want to fail driver instantiation because of that,
+ * so display a warning and keep going.
+ */
+ dev_warn(&pdev->dev,
+ "Can not read VID data: Failed to enable SuperIO access\n");
+ return res;
+ }
+
superio_select(sio_data, W83627HF_LD_HWM);
/* Make sure these GPIO pins are enabled */
diff --git a/drivers/hwtracing/intel_th/msu.c b/drivers/hwtracing/intel_th/msu.c
index 82f2b70ca5bf..36016c09dd96 100644
--- a/drivers/hwtracing/intel_th/msu.c
+++ b/drivers/hwtracing/intel_th/msu.c
@@ -92,6 +92,7 @@ struct msc_iter {
* @reg_base: register window base address
* @thdev: intel_th_device pointer
* @win_list: list of windows in multiblock mode
+ * @single_sgt: single mode buffer
* @nr_pages: total number of pages allocated for this buffer
* @single_sz: amount of data in single mode
* @single_wrap: single mode wrap occurred
@@ -112,6 +113,7 @@ struct msc {
struct intel_th_device *thdev;
struct list_head win_list;
+ struct sg_table single_sgt;
unsigned long nr_pages;
unsigned long single_sz;
unsigned int single_wrap : 1;
@@ -625,22 +627,45 @@ static void intel_th_msc_deactivate(struct intel_th_device *thdev)
*/
static int msc_buffer_contig_alloc(struct msc *msc, unsigned long size)
{
+ unsigned long nr_pages = size >> PAGE_SHIFT;
unsigned int order = get_order(size);
struct page *page;
+ int ret;
if (!size)
return 0;
+ ret = sg_alloc_table(&msc->single_sgt, 1, GFP_KERNEL);
+ if (ret)
+ goto err_out;
+
+ ret = -ENOMEM;
page = alloc_pages(GFP_KERNEL | __GFP_ZERO, order);
if (!page)
- return -ENOMEM;
+ goto err_free_sgt;
split_page(page, order);
- msc->nr_pages = size >> PAGE_SHIFT;
+ sg_set_buf(msc->single_sgt.sgl, page_address(page), size);
+
+ ret = dma_map_sg(msc_dev(msc)->parent->parent, msc->single_sgt.sgl, 1,
+ DMA_FROM_DEVICE);
+ if (ret < 0)
+ goto err_free_pages;
+
+ msc->nr_pages = nr_pages;
msc->base = page_address(page);
- msc->base_addr = page_to_phys(page);
+ msc->base_addr = sg_dma_address(msc->single_sgt.sgl);
return 0;
+
+err_free_pages:
+ __free_pages(page, order);
+
+err_free_sgt:
+ sg_free_table(&msc->single_sgt);
+
+err_out:
+ return ret;
}
/**
@@ -651,6 +676,10 @@ static void msc_buffer_contig_free(struct msc *msc)
{
unsigned long off;
+ dma_unmap_sg(msc_dev(msc)->parent->parent, msc->single_sgt.sgl,
+ 1, DMA_FROM_DEVICE);
+ sg_free_table(&msc->single_sgt);
+
for (off = 0; off < msc->nr_pages << PAGE_SHIFT; off += PAGE_SIZE) {
struct page *page = virt_to_page(msc->base + off);
diff --git a/drivers/hwtracing/intel_th/pci.c b/drivers/hwtracing/intel_th/pci.c
index ef699477d94a..eb8444faa14e 100644
--- a/drivers/hwtracing/intel_th/pci.c
+++ b/drivers/hwtracing/intel_th/pci.c
@@ -173,6 +173,11 @@ static const struct pci_device_id intel_th_pci_id_table[] = {
PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x34a6),
.driver_data = (kernel_ulong_t)&intel_th_2x,
},
+ {
+ /* Comet Lake */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x02a6),
+ .driver_data = (kernel_ulong_t)&intel_th_2x,
+ },
{ 0 },
};
diff --git a/drivers/hwtracing/stm/core.c b/drivers/hwtracing/stm/core.c
index 736862967e32..f4530b08b1e5 100644
--- a/drivers/hwtracing/stm/core.c
+++ b/drivers/hwtracing/stm/core.c
@@ -226,8 +226,8 @@ stm_output_disclaim(struct stm_device *stm, struct stm_output *output)
bitmap_release_region(&master->chan_map[0], output->channel,
ilog2(output->nr_chans));
- output->nr_chans = 0;
master->nr_free += output->nr_chans;
+ output->nr_chans = 0;
}
/*
@@ -252,6 +252,9 @@ static int find_free_channels(unsigned long *bitmap, unsigned int start,
;
if (i == width)
return pos;
+
+ /* step over [pos..pos+i) to continue search */
+ pos += i;
}
return -1;
@@ -558,7 +561,7 @@ static int stm_char_policy_set_ioctl(struct stm_file *stmf, void __user *arg)
{
struct stm_device *stm = stmf->stm;
struct stp_policy_id *id;
- int ret = -EINVAL;
+ int ret = -EINVAL, wlimit = 1;
u32 size;
if (stmf->output.nr_chans)
@@ -586,8 +589,10 @@ static int stm_char_policy_set_ioctl(struct stm_file *stmf, void __user *arg)
if (id->__reserved_0 || id->__reserved_1)
goto err_free;
- if (id->width < 1 ||
- id->width > PAGE_SIZE / stm->data->sw_mmiosz)
+ if (stm->data->sw_mmiosz)
+ wlimit = PAGE_SIZE / stm->data->sw_mmiosz;
+
+ if (id->width < 1 || id->width > wlimit)
goto err_free;
ret = stm_file_assign(stmf, id->id, id->width);
diff --git a/drivers/ide/ide-cd.c b/drivers/ide/ide-cd.c
index d1609a507354..0794df0116db 100644
--- a/drivers/ide/ide-cd.c
+++ b/drivers/ide/ide-cd.c
@@ -1796,6 +1796,7 @@ static int ide_cd_probe(ide_drive_t *drive)
ide_cd_read_toc(drive, &sense);
g->fops = &idecd_ops;
g->flags |= GENHD_FL_REMOVABLE | GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE;
+ g->events = DISK_EVENT_MEDIA_CHANGE;
device_add_disk(&drive->gendev, g);
return 0;
diff --git a/drivers/ide/ide-cd_ioctl.c b/drivers/ide/ide-cd_ioctl.c
index 9d26c9737e21..18e07adb02d4 100644
--- a/drivers/ide/ide-cd_ioctl.c
+++ b/drivers/ide/ide-cd_ioctl.c
@@ -81,8 +81,9 @@ int ide_cdrom_drive_status(struct cdrom_device_info *cdi, int slot_nr)
/*
* ide-cd always generates media changed event if media is missing, which
- * makes it impossible to use for proper event reporting, so disk->events
- * is cleared to 0 and the following function is used only to trigger
+ * makes it impossible to use for proper event reporting, so
+ * DISK_EVENT_FLAG_UEVENT is cleared in disk->events
+ * and the following function is used only to trigger
* revalidation and never propagated to userland.
*/
unsigned int ide_cdrom_check_events_real(struct cdrom_device_info *cdi,
diff --git a/drivers/ide/ide-gd.c b/drivers/ide/ide-gd.c
index e823394ed543..b6d80b2bbda2 100644
--- a/drivers/ide/ide-gd.c
+++ b/drivers/ide/ide-gd.c
@@ -299,8 +299,9 @@ static unsigned int ide_gd_check_events(struct gendisk *disk,
/*
* The following is used to force revalidation on the first open on
* removeable devices, and never gets reported to userland as
- * genhd->events is 0. This is intended as removeable ide disk
- * can't really detect MEDIA_CHANGE events.
+ * DISK_EVENT_FLAG_UEVENT isn't set in genhd->events.
+ * This is intended as removeable ide disk can't really detect
+ * MEDIA_CHANGE events.
*/
ret = drive->dev_flags & IDE_DFLAG_MEDIA_CHANGED;
drive->dev_flags &= ~IDE_DFLAG_MEDIA_CHANGED;
@@ -416,6 +417,7 @@ static int ide_gd_probe(ide_drive_t *drive)
if (drive->dev_flags & IDE_DFLAG_REMOVABLE)
g->flags = GENHD_FL_REMOVABLE;
g->fops = &ide_gd_ops;
+ g->events = DISK_EVENT_MEDIA_CHANGE;
device_add_disk(&drive->gendev, g);
return 0;
diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index 008eb4d58a86..ec95c0d56fa7 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -1069,14 +1069,14 @@ static const struct x86_cpu_id intel_idle_ids[] __initconst = {
ICPU(INTEL_FAM6_WESTMERE, idle_cpu_nehalem),
ICPU(INTEL_FAM6_WESTMERE_EP, idle_cpu_nehalem),
ICPU(INTEL_FAM6_NEHALEM_EX, idle_cpu_nehalem),
- ICPU(INTEL_FAM6_ATOM_PINEVIEW, idle_cpu_atom),
- ICPU(INTEL_FAM6_ATOM_LINCROFT, idle_cpu_lincroft),
+ ICPU(INTEL_FAM6_ATOM_BONNELL, idle_cpu_atom),
+ ICPU(INTEL_FAM6_ATOM_BONNELL_MID, idle_cpu_lincroft),
ICPU(INTEL_FAM6_WESTMERE_EX, idle_cpu_nehalem),
ICPU(INTEL_FAM6_SANDYBRIDGE, idle_cpu_snb),
ICPU(INTEL_FAM6_SANDYBRIDGE_X, idle_cpu_snb),
- ICPU(INTEL_FAM6_ATOM_CEDARVIEW, idle_cpu_atom),
- ICPU(INTEL_FAM6_ATOM_SILVERMONT1, idle_cpu_byt),
- ICPU(INTEL_FAM6_ATOM_MERRIFIELD, idle_cpu_tangier),
+ ICPU(INTEL_FAM6_ATOM_SALTWELL, idle_cpu_atom),
+ ICPU(INTEL_FAM6_ATOM_SILVERMONT, idle_cpu_byt),
+ ICPU(INTEL_FAM6_ATOM_SILVERMONT_MID, idle_cpu_tangier),
ICPU(INTEL_FAM6_ATOM_AIRMONT, idle_cpu_cht),
ICPU(INTEL_FAM6_IVYBRIDGE, idle_cpu_ivb),
ICPU(INTEL_FAM6_IVYBRIDGE_X, idle_cpu_ivt),
@@ -1084,7 +1084,7 @@ static const struct x86_cpu_id intel_idle_ids[] __initconst = {
ICPU(INTEL_FAM6_HASWELL_X, idle_cpu_hsw),
ICPU(INTEL_FAM6_HASWELL_ULT, idle_cpu_hsw),
ICPU(INTEL_FAM6_HASWELL_GT3E, idle_cpu_hsw),
- ICPU(INTEL_FAM6_ATOM_SILVERMONT2, idle_cpu_avn),
+ ICPU(INTEL_FAM6_ATOM_SILVERMONT_X, idle_cpu_avn),
ICPU(INTEL_FAM6_BROADWELL_CORE, idle_cpu_bdw),
ICPU(INTEL_FAM6_BROADWELL_GT3E, idle_cpu_bdw),
ICPU(INTEL_FAM6_BROADWELL_X, idle_cpu_bdw),
@@ -1097,8 +1097,8 @@ static const struct x86_cpu_id intel_idle_ids[] __initconst = {
ICPU(INTEL_FAM6_XEON_PHI_KNL, idle_cpu_knl),
ICPU(INTEL_FAM6_XEON_PHI_KNM, idle_cpu_knl),
ICPU(INTEL_FAM6_ATOM_GOLDMONT, idle_cpu_bxt),
- ICPU(INTEL_FAM6_ATOM_GEMINI_LAKE, idle_cpu_bxt),
- ICPU(INTEL_FAM6_ATOM_DENVERTON, idle_cpu_dnv),
+ ICPU(INTEL_FAM6_ATOM_GOLDMONT_PLUS, idle_cpu_bxt),
+ ICPU(INTEL_FAM6_ATOM_GOLDMONT_X, idle_cpu_dnv),
ICPU(INTEL_FAM6_ATOM_TREMONT_X, idle_cpu_dnv),
{}
};
@@ -1311,7 +1311,7 @@ static void intel_idle_state_table_update(void)
ivt_idle_state_table_update();
break;
case INTEL_FAM6_ATOM_GOLDMONT:
- case INTEL_FAM6_ATOM_GEMINI_LAKE:
+ case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
bxt_idle_state_table_update();
break;
case INTEL_FAM6_SKYLAKE_DESKTOP:
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index e079c1652902..30a528fa841f 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -3335,9 +3335,12 @@ static int __init init_dmars(void)
iommu_identity_mapping |= IDENTMAP_ALL;
#ifdef CONFIG_INTEL_IOMMU_BROKEN_GFX_WA
- iommu_identity_mapping |= IDENTMAP_GFX;
+ dmar_map_gfx = 0;
#endif
+ if (!dmar_map_gfx)
+ iommu_identity_mapping |= IDENTMAP_GFX;
+
check_tylersburg_isoch();
if (iommu_identity_mapping) {
@@ -3419,7 +3422,13 @@ domains_done:
#ifdef CONFIG_INTEL_IOMMU_SVM
if (pasid_enabled(iommu) && ecap_prs(iommu->ecap)) {
+ /*
+ * Call dmar_alloc_hwirq() with dmar_global_lock held,
+ * could cause possible lock race condition.
+ */
+ up_write(&dmar_global_lock);
ret = intel_svm_enable_prq(iommu);
+ down_write(&dmar_global_lock);
if (ret)
goto free_iommu;
}
@@ -4001,9 +4010,7 @@ static void __init init_no_remapping_devices(void)
/* This IOMMU has *only* gfx devices. Either bypass it or
set the gfx_mapped flag, as appropriate */
- if (dmar_map_gfx) {
- intel_iommu_gfx_mapped = 1;
- } else {
+ if (!dmar_map_gfx) {
drhd->ignored = 1;
for_each_active_dev_scope(drhd->devices,
drhd->devices_cnt, i, dev)
@@ -4802,6 +4809,9 @@ int __init intel_iommu_init(void)
goto out_free_reserved_range;
}
+ if (dmar_map_gfx)
+ intel_iommu_gfx_mapped = 1;
+
init_no_remapping_devices();
ret = init_dmars();
diff --git a/drivers/leds/led-class.c b/drivers/leds/led-class.c
index b0e2d55acbd6..80374c6c943a 100644
--- a/drivers/leds/led-class.c
+++ b/drivers/leds/led-class.c
@@ -57,6 +57,7 @@ static ssize_t brightness_store(struct device *dev,
if (state == LED_OFF)
led_trigger_remove(led_cdev);
led_set_brightness(led_cdev, state);
+ flush_work(&led_cdev->set_brightness_work);
ret = size;
unlock:
diff --git a/drivers/leds/led-core.c b/drivers/leds/led-core.c
index 9ce6b32f52a1..cb84c35d64f9 100644
--- a/drivers/leds/led-core.c
+++ b/drivers/leds/led-core.c
@@ -162,6 +162,11 @@ static void led_blink_setup(struct led_classdev *led_cdev,
unsigned long *delay_on,
unsigned long *delay_off)
{
+ /*
+ * If "set brightness to 0" is pending in workqueue, we don't
+ * want that to be reordered after blink_set()
+ */
+ flush_work(&led_cdev->set_brightness_work);
if (!test_bit(LED_BLINK_ONESHOT, &led_cdev->work_flags) &&
led_cdev->blink_set &&
!led_cdev->blink_set(led_cdev, delay_on, delay_off))
diff --git a/drivers/md/bcache/Kconfig b/drivers/md/bcache/Kconfig
index 4d200883c505..071beadf44bb 100644
--- a/drivers/md/bcache/Kconfig
+++ b/drivers/md/bcache/Kconfig
@@ -1,7 +1,8 @@
config BCACHE
tristate "Block device as cache"
- ---help---
+ select CRC64
+ help
Allows a block device to be used as cache for other devices; uses
a btree for indexing and the layout is optimized for SSDs.
@@ -10,7 +11,7 @@ config BCACHE
config BCACHE_DEBUG
bool "Bcache debugging"
depends on BCACHE
- ---help---
+ help
Don't select this option unless you're a developer
Enables extra debugging tools, allows expensive runtime checks to be
@@ -20,7 +21,7 @@ config BCACHE_CLOSURES_DEBUG
bool "Debug closures"
depends on BCACHE
select DEBUG_FS
- ---help---
+ help
Keeps all active closures in a linked list and provides a debugfs
interface to list them, which makes it possible to see asynchronous
operations that get stuck.
diff --git a/drivers/md/bcache/alloc.c b/drivers/md/bcache/alloc.c
index 2859f1f363a7..56a06375978e 100644
--- a/drivers/md/bcache/alloc.c
+++ b/drivers/md/bcache/alloc.c
@@ -86,8 +86,8 @@ void bch_rescale_priorities(struct cache_set *c, int sectors)
{
struct cache *ca;
struct bucket *b;
- unsigned next = c->nbuckets * c->sb.bucket_size / 1024;
- unsigned i;
+ unsigned int next = c->nbuckets * c->sb.bucket_size / 1024;
+ unsigned int i;
int r;
atomic_sub(sectors, &c->rescale);
@@ -168,7 +168,7 @@ static void bch_invalidate_one_bucket(struct cache *ca, struct bucket *b)
#define bucket_prio(b) \
({ \
- unsigned min_prio = (INITIAL_PRIO - ca->set->min_prio) / 8; \
+ unsigned int min_prio = (INITIAL_PRIO - ca->set->min_prio) / 8; \
\
(b->prio - ca->set->min_prio + min_prio) * GC_SECTORS_USED(b); \
})
@@ -243,6 +243,7 @@ static void invalidate_buckets_random(struct cache *ca)
while (!fifo_full(&ca->free_inc)) {
size_t n;
+
get_random_bytes(&n, sizeof(n));
n %= (size_t) (ca->sb.nbuckets - ca->sb.first_bucket);
@@ -300,7 +301,7 @@ do { \
static int bch_allocator_push(struct cache *ca, long bucket)
{
- unsigned i;
+ unsigned int i;
/* Prios/gens are actually the most important reserve */
if (fifo_push(&ca->free[RESERVE_PRIO], bucket))
@@ -384,7 +385,7 @@ out:
/* Allocation */
-long bch_bucket_alloc(struct cache *ca, unsigned reserve, bool wait)
+long bch_bucket_alloc(struct cache *ca, unsigned int reserve, bool wait)
{
DEFINE_WAIT(w);
struct bucket *b;
@@ -420,7 +421,7 @@ out:
if (expensive_debug_checks(ca->set)) {
size_t iter;
long i;
- unsigned j;
+ unsigned int j;
for (iter = 0; iter < prio_buckets(ca) * 2; iter++)
BUG_ON(ca->prio_buckets[iter] == (uint64_t) r);
@@ -469,20 +470,20 @@ void __bch_bucket_free(struct cache *ca, struct bucket *b)
void bch_bucket_free(struct cache_set *c, struct bkey *k)
{
- unsigned i;
+ unsigned int i;
for (i = 0; i < KEY_PTRS(k); i++)
__bch_bucket_free(PTR_CACHE(c, k, i),
PTR_BUCKET(c, k, i));
}
-int __bch_bucket_alloc_set(struct cache_set *c, unsigned reserve,
+int __bch_bucket_alloc_set(struct cache_set *c, unsigned int reserve,
struct bkey *k, int n, bool wait)
{
int i;
lockdep_assert_held(&c->bucket_lock);
- BUG_ON(!n || n > c->caches_loaded || n > 8);
+ BUG_ON(!n || n > c->caches_loaded || n > MAX_CACHES_PER_SET);
bkey_init(k);
@@ -509,10 +510,11 @@ err:
return -1;
}
-int bch_bucket_alloc_set(struct cache_set *c, unsigned reserve,
+int bch_bucket_alloc_set(struct cache_set *c, unsigned int reserve,
struct bkey *k, int n, bool wait)
{
int ret;
+
mutex_lock(&c->bucket_lock);
ret = __bch_bucket_alloc_set(c, reserve, k, n, wait);
mutex_unlock(&c->bucket_lock);
@@ -523,8 +525,8 @@ int bch_bucket_alloc_set(struct cache_set *c, unsigned reserve,
struct open_bucket {
struct list_head list;
- unsigned last_write_point;
- unsigned sectors_free;
+ unsigned int last_write_point;
+ unsigned int sectors_free;
BKEY_PADDED(key);
};
@@ -555,7 +557,7 @@ struct open_bucket {
*/
static struct open_bucket *pick_data_bucket(struct cache_set *c,
const struct bkey *search,
- unsigned write_point,
+ unsigned int write_point,
struct bkey *alloc)
{
struct open_bucket *ret, *ret_task = NULL;
@@ -594,12 +596,16 @@ found:
*
* If s->writeback is true, will not fail.
*/
-bool bch_alloc_sectors(struct cache_set *c, struct bkey *k, unsigned sectors,
- unsigned write_point, unsigned write_prio, bool wait)
+bool bch_alloc_sectors(struct cache_set *c,
+ struct bkey *k,
+ unsigned int sectors,
+ unsigned int write_point,
+ unsigned int write_prio,
+ bool wait)
{
struct open_bucket *b;
BKEY_PADDED(key) alloc;
- unsigned i;
+ unsigned int i;
/*
* We might have to allocate a new bucket, which we can't do with a
@@ -612,7 +618,7 @@ bool bch_alloc_sectors(struct cache_set *c, struct bkey *k, unsigned sectors,
spin_lock(&c->data_bucket_lock);
while (!(b = pick_data_bucket(c, k, write_point, &alloc.key))) {
- unsigned watermark = write_prio
+ unsigned int watermark = write_prio
? RESERVE_MOVINGGC
: RESERVE_NONE;
@@ -701,6 +707,7 @@ int bch_open_buckets_alloc(struct cache_set *c)
for (i = 0; i < MAX_OPEN_BUCKETS; i++) {
struct open_bucket *b = kzalloc(sizeof(*b), GFP_KERNEL);
+
if (!b)
return -ENOMEM;
diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index a52a7e958b74..2f6c60d140b3 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -251,7 +251,7 @@ struct bcache_device {
struct kobject kobj;
struct cache_set *c;
- unsigned id;
+ unsigned int id;
#define BCACHEDEVNAME_SIZE 12
char name[BCACHEDEVNAME_SIZE];
@@ -263,18 +263,19 @@ struct bcache_device {
#define BCACHE_DEV_UNLINK_DONE 2
#define BCACHE_DEV_WB_RUNNING 3
#define BCACHE_DEV_RATE_DW_RUNNING 4
- unsigned nr_stripes;
- unsigned stripe_size;
+ unsigned int nr_stripes;
+ unsigned int stripe_size;
atomic_t *stripe_sectors_dirty;
unsigned long *full_dirty_stripes;
struct bio_set *bio_split;
- unsigned data_csum:1;
+ unsigned int data_csum:1;
- int (*cache_miss)(struct btree *, struct search *,
- struct bio *, unsigned);
- int (*ioctl) (struct bcache_device *, fmode_t, unsigned, unsigned long);
+ int (*cache_miss)(struct btree *b, struct search *s,
+ struct bio *bio, unsigned int sectors);
+ int (*ioctl)(struct bcache_device *d, fmode_t mode,
+ unsigned int cmd, unsigned long arg);
};
struct io {
@@ -283,7 +284,7 @@ struct io {
struct list_head lru;
unsigned long jiffies;
- unsigned sequential;
+ unsigned int sequential;
sector_t last;
};
@@ -337,6 +338,7 @@ struct cached_dev {
struct keybuf writeback_keys;
+ struct task_struct *status_update_thread;
/*
* Order the write-half of writeback operations strongly in dispatch
* order. (Maintain LBA order; don't allow reads completing out of
@@ -356,18 +358,18 @@ struct cached_dev {
struct cache_accounting accounting;
/* The rest of this all shows up in sysfs */
- unsigned sequential_cutoff;
- unsigned readahead;
+ unsigned int sequential_cutoff;
+ unsigned int readahead;
- unsigned io_disable:1;
- unsigned verify:1;
- unsigned bypass_torture_test:1;
+ unsigned int io_disable:1;
+ unsigned int verify:1;
+ unsigned int bypass_torture_test:1;
- unsigned partial_stripes_expensive:1;
- unsigned writeback_metadata:1;
- unsigned writeback_running:1;
+ unsigned int partial_stripes_expensive:1;
+ unsigned int writeback_metadata:1;
+ unsigned int writeback_running:1;
unsigned char writeback_percent;
- unsigned writeback_delay;
+ unsigned int writeback_delay;
uint64_t writeback_rate_target;
int64_t writeback_rate_proportional;
@@ -375,15 +377,16 @@ struct cached_dev {
int64_t writeback_rate_integral_scaled;
int32_t writeback_rate_change;
- unsigned writeback_rate_update_seconds;
- unsigned writeback_rate_i_term_inverse;
- unsigned writeback_rate_p_term_inverse;
- unsigned writeback_rate_minimum;
+ unsigned int writeback_rate_update_seconds;
+ unsigned int writeback_rate_i_term_inverse;
+ unsigned int writeback_rate_p_term_inverse;
+ unsigned int writeback_rate_minimum;
enum stop_on_failure stop_when_cache_set_failed;
#define DEFAULT_CACHED_DEV_ERROR_LIMIT 64
atomic_t io_errors;
- unsigned error_limit;
+ unsigned int error_limit;
+ unsigned int offline_seconds;
char backing_dev_name[BDEVNAME_SIZE];
};
@@ -413,9 +416,9 @@ struct cache {
/*
* When allocating new buckets, prio_write() gets first dibs - since we
* may not be allocate at all without writing priorities and gens.
- * prio_buckets[] contains the last buckets we wrote priorities to (so
- * gc can mark them as metadata), prio_next[] contains the buckets
- * allocated for the next prio write.
+ * prio_last_buckets[] contains the last buckets we wrote priorities to
+ * (so gc can mark them as metadata), prio_buckets[] contains the
+ * buckets allocated for the next prio write.
*/
uint64_t *prio_buckets;
uint64_t *prio_last_buckets;
@@ -444,7 +447,7 @@ struct cache {
* until a gc finishes - otherwise we could pointlessly burn a ton of
* cpu
*/
- unsigned invalidate_needs_gc;
+ unsigned int invalidate_needs_gc;
bool discard; /* Get rid of? */
@@ -469,7 +472,7 @@ struct gc_stat {
size_t nkeys;
uint64_t data; /* sectors */
- unsigned in_use; /* percent */
+ unsigned int in_use; /* percent */
};
/*
@@ -515,7 +518,7 @@ struct cache_set {
int caches_loaded;
struct bcache_device **devices;
- unsigned devices_max_used;
+ unsigned int devices_max_used;
atomic_t attached_dev_nr;
struct list_head cached_devs;
uint64_t cached_dev_sectors;
@@ -545,7 +548,7 @@ struct cache_set {
* Default number of pages for a new btree node - may be less than a
* full bucket
*/
- unsigned btree_pages;
+ unsigned int btree_pages;
/*
* Lists of struct btrees; lru is the list for structs that have memory
@@ -568,7 +571,7 @@ struct cache_set {
struct list_head btree_cache_freed;
/* Number of elements in btree_cache + btree_cache_freeable lists */
- unsigned btree_cache_used;
+ unsigned int btree_cache_used;
/*
* If we need to allocate memory for a new btree node and that
@@ -610,8 +613,8 @@ struct cache_set {
uint16_t min_prio;
/*
- * max(gen - last_gc) for all buckets. When it gets too big we have to gc
- * to keep gens from wrapping around.
+ * max(gen - last_gc) for all buckets. When it gets too big we have to
+ * gc to keep gens from wrapping around.
*/
uint8_t need_gc;
struct gc_stat gc_stats;
@@ -623,6 +626,20 @@ struct cache_set {
struct bkey gc_done;
/*
+ * For automatical garbage collection after writeback completed, this
+ * varialbe is used as bit fields,
+ * - 0000 0001b (BCH_ENABLE_AUTO_GC): enable gc after writeback
+ * - 0000 0010b (BCH_DO_AUTO_GC): do gc after writeback
+ * This is an optimization for following write request after writeback
+ * finished, but read hit rate dropped due to clean data on cache is
+ * discarded. Unless user explicitly sets it via sysfs, it won't be
+ * enabled.
+ */
+#define BCH_ENABLE_AUTO_GC 1
+#define BCH_DO_AUTO_GC 2
+ uint8_t gc_after_writeback;
+
+ /*
* The allocation code needs gc_mark in struct bucket to be correct, but
* it's not while a gc is in progress. Protected by bucket_lock.
*/
@@ -646,7 +663,7 @@ struct cache_set {
struct mutex verify_lock;
#endif
- unsigned nr_uuids;
+ unsigned int nr_uuids;
struct uuid_entry *uuids;
BKEY_PADDED(uuid_bucket);
struct closure uuid_write;
@@ -654,7 +671,11 @@ struct cache_set {
/*
* A btree node on disk could have too many bsets for an iterator to fit
- * on the stack - have to dynamically allocate them
+ * on the stack - have to dynamically allocate them.
+ * bch_cache_set_alloc() will make sure the pool can allocate iterators
+ * equipped with enough room that can host
+ * (sb.bucket_size / sb.block_size)
+ * btree_iter_sets, which is more than static MAX_BSETS.
*/
mempool_t *fill_iter;
@@ -667,12 +688,12 @@ struct cache_set {
struct journal journal;
#define CONGESTED_MAX 1024
- unsigned congested_last_us;
+ unsigned int congested_last_us;
atomic_t congested;
/* The rest of this all shows up in sysfs */
- unsigned congested_read_threshold_us;
- unsigned congested_write_threshold_us;
+ unsigned int congested_read_threshold_us;
+ unsigned int congested_write_threshold_us;
struct time_stats btree_gc_time;
struct time_stats btree_split_time;
@@ -691,16 +712,16 @@ struct cache_set {
ON_ERROR_PANIC,
} on_error;
#define DEFAULT_IO_ERROR_LIMIT 8
- unsigned error_limit;
- unsigned error_decay;
+ unsigned int error_limit;
+ unsigned int error_decay;
unsigned short journal_delay_ms;
bool expensive_debug_checks;
- unsigned verify:1;
- unsigned key_merging_disabled:1;
- unsigned gc_always_rewrite:1;
- unsigned shrinker_disabled:1;
- unsigned copy_gc_enabled:1;
+ unsigned int verify:1;
+ unsigned int key_merging_disabled:1;
+ unsigned int gc_always_rewrite:1;
+ unsigned int shrinker_disabled:1;
+ unsigned int copy_gc_enabled:1;
#define BUCKET_HASH_BITS 12
struct hlist_head bucket_hash[1 << BUCKET_HASH_BITS];
@@ -709,7 +730,7 @@ struct cache_set {
};
struct bbio {
- unsigned submit_time_us;
+ unsigned int submit_time_us;
union {
struct bkey key;
uint64_t _pad[3];
@@ -726,10 +747,10 @@ struct bbio {
#define btree_bytes(c) ((c)->btree_pages * PAGE_SIZE)
#define btree_blocks(b) \
- ((unsigned) (KEY_SIZE(&b->key) >> (b)->c->block_bits))
+ ((unsigned int) (KEY_SIZE(&b->key) >> (b)->c->block_bits))
#define btree_default_blocks(c) \
- ((unsigned) ((PAGE_SECTORS * (c)->btree_pages) >> (c)->block_bits))
+ ((unsigned int) ((PAGE_SECTORS * (c)->btree_pages) >> (c)->block_bits))
#define bucket_pages(c) ((c)->sb.bucket_size / PAGE_SECTORS)
#define bucket_bytes(c) ((c)->sb.bucket_size << 9)
@@ -758,21 +779,21 @@ static inline sector_t bucket_remainder(struct cache_set *c, sector_t s)
static inline struct cache *PTR_CACHE(struct cache_set *c,
const struct bkey *k,
- unsigned ptr)
+ unsigned int ptr)
{
return c->cache[PTR_DEV(k, ptr)];
}
static inline size_t PTR_BUCKET_NR(struct cache_set *c,
const struct bkey *k,
- unsigned ptr)
+ unsigned int ptr)
{
return sector_to_bucket(c, PTR_OFFSET(k, ptr));
}
static inline struct bucket *PTR_BUCKET(struct cache_set *c,
const struct bkey *k,
- unsigned ptr)
+ unsigned int ptr)
{
return PTR_CACHE(c, k, ptr)->buckets + PTR_BUCKET_NR(c, k, ptr);
}
@@ -780,17 +801,18 @@ static inline struct bucket *PTR_BUCKET(struct cache_set *c,
static inline uint8_t gen_after(uint8_t a, uint8_t b)
{
uint8_t r = a - b;
+
return r > 128U ? 0 : r;
}
static inline uint8_t ptr_stale(struct cache_set *c, const struct bkey *k,
- unsigned i)
+ unsigned int i)
{
return gen_after(PTR_BUCKET(c, k, i)->gen, PTR_GEN(k, i));
}
static inline bool ptr_available(struct cache_set *c, const struct bkey *k,
- unsigned i)
+ unsigned int i)
{
return (PTR_DEV(k, i) < MAX_CACHES_PER_SET) && PTR_CACHE(c, k, i);
}
@@ -876,16 +898,16 @@ static inline uint8_t bucket_gc_gen(struct bucket *b)
#define BUCKET_GC_GEN_MAX 96U
#define kobj_attribute_write(n, fn) \
- static struct kobj_attribute ksysfs_##n = __ATTR(n, S_IWUSR, NULL, fn)
+ static struct kobj_attribute ksysfs_##n = __ATTR(n, 0200, NULL, fn)
#define kobj_attribute_rw(n, show, store) \
static struct kobj_attribute ksysfs_##n = \
- __ATTR(n, S_IWUSR|S_IRUSR, show, store)
+ __ATTR(n, 0600, show, store)
static inline void wake_up_allocators(struct cache_set *c)
{
struct cache *ca;
- unsigned i;
+ unsigned int i;
for_each_cache(ca, c, i)
wake_up_process(ca->alloc_thread);
@@ -921,44 +943,46 @@ static inline void wait_for_kthread_stop(void)
/* Forward declarations */
void bch_count_backing_io_errors(struct cached_dev *dc, struct bio *bio);
-void bch_count_io_errors(struct cache *, blk_status_t, int, const char *);
-void bch_bbio_count_io_errors(struct cache_set *, struct bio *,
- blk_status_t, const char *);
-void bch_bbio_endio(struct cache_set *, struct bio *, blk_status_t,
- const char *);
-void bch_bbio_free(struct bio *, struct cache_set *);
-struct bio *bch_bbio_alloc(struct cache_set *);
-
-void __bch_submit_bbio(struct bio *, struct cache_set *);
-void bch_submit_bbio(struct bio *, struct cache_set *, struct bkey *, unsigned);
-
-uint8_t bch_inc_gen(struct cache *, struct bucket *);
-void bch_rescale_priorities(struct cache_set *, int);
-
-bool bch_can_invalidate_bucket(struct cache *, struct bucket *);
-void __bch_invalidate_one_bucket(struct cache *, struct bucket *);
-
-void __bch_bucket_free(struct cache *, struct bucket *);
-void bch_bucket_free(struct cache_set *, struct bkey *);
-
-long bch_bucket_alloc(struct cache *, unsigned, bool);
-int __bch_bucket_alloc_set(struct cache_set *, unsigned,
- struct bkey *, int, bool);
-int bch_bucket_alloc_set(struct cache_set *, unsigned,
- struct bkey *, int, bool);
-bool bch_alloc_sectors(struct cache_set *, struct bkey *, unsigned,
- unsigned, unsigned, bool);
+void bch_count_io_errors(struct cache *ca, blk_status_t error,
+ int is_read, const char *m);
+void bch_bbio_count_io_errors(struct cache_set *c, struct bio *bio,
+ blk_status_t error, const char *m);
+void bch_bbio_endio(struct cache_set *c, struct bio *bio,
+ blk_status_t error, const char *m);
+void bch_bbio_free(struct bio *bio, struct cache_set *c);
+struct bio *bch_bbio_alloc(struct cache_set *c);
+
+void __bch_submit_bbio(struct bio *bio, struct cache_set *c);
+void bch_submit_bbio(struct bio *bio, struct cache_set *c,
+ struct bkey *k, unsigned int ptr);
+
+uint8_t bch_inc_gen(struct cache *ca, struct bucket *b);
+void bch_rescale_priorities(struct cache_set *c, int sectors);
+
+bool bch_can_invalidate_bucket(struct cache *ca, struct bucket *b);
+void __bch_invalidate_one_bucket(struct cache *ca, struct bucket *b);
+
+void __bch_bucket_free(struct cache *ca, struct bucket *b);
+void bch_bucket_free(struct cache_set *c, struct bkey *k);
+
+long bch_bucket_alloc(struct cache *ca, unsigned int reserve, bool wait);
+int __bch_bucket_alloc_set(struct cache_set *c, unsigned int reserve,
+ struct bkey *k, int n, bool wait);
+int bch_bucket_alloc_set(struct cache_set *c, unsigned int reserve,
+ struct bkey *k, int n, bool wait);
+bool bch_alloc_sectors(struct cache_set *c, struct bkey *k,
+ unsigned int sectors, unsigned int write_point,
+ unsigned int write_prio, bool wait);
bool bch_cached_dev_error(struct cached_dev *dc);
__printf(2, 3)
-bool bch_cache_set_error(struct cache_set *, const char *, ...);
+bool bch_cache_set_error(struct cache_set *c, const char *fmt, ...);
-void bch_prio_write(struct cache *);
-void bch_write_bdev_super(struct cached_dev *, struct closure *);
+void bch_prio_write(struct cache *ca);
+void bch_write_bdev_super(struct cached_dev *dc, struct closure *parent);
extern struct workqueue_struct *bcache_wq;
-extern const char * const bch_cache_modes[];
-extern const char * const bch_stop_on_failure_modes[];
+extern struct workqueue_struct *bch_journal_wq;
extern struct mutex bch_register_lock;
extern struct list_head bch_cache_sets;
@@ -968,35 +992,36 @@ extern struct kobj_type bch_cache_set_ktype;
extern struct kobj_type bch_cache_set_internal_ktype;
extern struct kobj_type bch_cache_ktype;
-void bch_cached_dev_release(struct kobject *);
-void bch_flash_dev_release(struct kobject *);
-void bch_cache_set_release(struct kobject *);
-void bch_cache_release(struct kobject *);
+void bch_cached_dev_release(struct kobject *kobj);
+void bch_flash_dev_release(struct kobject *kobj);
+void bch_cache_set_release(struct kobject *kobj);
+void bch_cache_release(struct kobject *kobj);
-int bch_uuid_write(struct cache_set *);
-void bcache_write_super(struct cache_set *);
+int bch_uuid_write(struct cache_set *c);
+void bcache_write_super(struct cache_set *c);
int bch_flash_dev_create(struct cache_set *c, uint64_t size);
-int bch_cached_dev_attach(struct cached_dev *, struct cache_set *, uint8_t *);
-void bch_cached_dev_detach(struct cached_dev *);
-void bch_cached_dev_run(struct cached_dev *);
-void bcache_device_stop(struct bcache_device *);
+int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c,
+ uint8_t *set_uuid);
+void bch_cached_dev_detach(struct cached_dev *dc);
+void bch_cached_dev_run(struct cached_dev *dc);
+void bcache_device_stop(struct bcache_device *d);
-void bch_cache_set_unregister(struct cache_set *);
-void bch_cache_set_stop(struct cache_set *);
+void bch_cache_set_unregister(struct cache_set *c);
+void bch_cache_set_stop(struct cache_set *c);
-struct cache_set *bch_cache_set_alloc(struct cache_sb *);
-void bch_btree_cache_free(struct cache_set *);
-int bch_btree_cache_alloc(struct cache_set *);
-void bch_moving_init_cache_set(struct cache_set *);
-int bch_open_buckets_alloc(struct cache_set *);
-void bch_open_buckets_free(struct cache_set *);
+struct cache_set *bch_cache_set_alloc(struct cache_sb *sb);
+void bch_btree_cache_free(struct cache_set *c);
+int bch_btree_cache_alloc(struct cache_set *c);
+void bch_moving_init_cache_set(struct cache_set *c);
+int bch_open_buckets_alloc(struct cache_set *c);
+void bch_open_buckets_free(struct cache_set *c);
int bch_cache_allocator_start(struct cache *ca);
void bch_debug_exit(void);
-void bch_debug_init(struct kobject *kobj);
+void bch_debug_init(void);
void bch_request_exit(void);
int bch_request_init(void);
diff --git a/drivers/md/bcache/bset.c b/drivers/md/bcache/bset.c
index cebf4f030c86..1b895b4fed60 100644
--- a/drivers/md/bcache/bset.c
+++ b/drivers/md/bcache/bset.c
@@ -17,31 +17,31 @@
#ifdef CONFIG_BCACHE_DEBUG
-void bch_dump_bset(struct btree_keys *b, struct bset *i, unsigned set)
+void bch_dump_bset(struct btree_keys *b, struct bset *i, unsigned int set)
{
struct bkey *k, *next;
for (k = i->start; k < bset_bkey_last(i); k = next) {
next = bkey_next(k);
- printk(KERN_ERR "block %u key %u/%u: ", set,
- (unsigned) ((u64 *) k - i->d), i->keys);
+ pr_err("block %u key %u/%u: ", set,
+ (unsigned int) ((u64 *) k - i->d), i->keys);
if (b->ops->key_dump)
b->ops->key_dump(b, k);
else
- printk("%llu:%llu\n", KEY_INODE(k), KEY_OFFSET(k));
+ pr_err("%llu:%llu\n", KEY_INODE(k), KEY_OFFSET(k));
if (next < bset_bkey_last(i) &&
bkey_cmp(k, b->ops->is_extents ?
&START_KEY(next) : next) > 0)
- printk(KERN_ERR "Key skipped backwards\n");
+ pr_err("Key skipped backwards\n");
}
}
void bch_dump_bucket(struct btree_keys *b)
{
- unsigned i;
+ unsigned int i;
console_lock();
for (i = 0; i <= b->nsets; i++)
@@ -52,7 +52,7 @@ void bch_dump_bucket(struct btree_keys *b)
int __bch_count_data(struct btree_keys *b)
{
- unsigned ret = 0;
+ unsigned int ret = 0;
struct btree_iter iter;
struct bkey *k;
@@ -127,7 +127,7 @@ static inline void bch_btree_iter_next_check(struct btree_iter *iter) {}
/* Keylists */
-int __bch_keylist_realloc(struct keylist *l, unsigned u64s)
+int __bch_keylist_realloc(struct keylist *l, unsigned int u64s)
{
size_t oldsize = bch_keylist_nkeys(l);
size_t newsize = oldsize + u64s;
@@ -179,7 +179,7 @@ void bch_keylist_pop_front(struct keylist *l)
/* Key/pointer manipulation */
void bch_bkey_copy_single_ptr(struct bkey *dest, const struct bkey *src,
- unsigned i)
+ unsigned int i)
{
BUG_ON(i > KEY_PTRS(src));
@@ -193,7 +193,7 @@ void bch_bkey_copy_single_ptr(struct bkey *dest, const struct bkey *src,
bool __bch_cut_front(const struct bkey *where, struct bkey *k)
{
- unsigned i, len = 0;
+ unsigned int i, len = 0;
if (bkey_cmp(where, &START_KEY(k)) <= 0)
return false;
@@ -213,7 +213,7 @@ bool __bch_cut_front(const struct bkey *where, struct bkey *k)
bool __bch_cut_back(const struct bkey *where, struct bkey *k)
{
- unsigned len = 0;
+ unsigned int len = 0;
if (bkey_cmp(where, k) >= 0)
return false;
@@ -239,9 +239,9 @@ bool __bch_cut_back(const struct bkey *where, struct bkey *k)
#define BKEY_MANTISSA_MASK ((1 << BKEY_MANTISSA_BITS) - 1)
struct bkey_float {
- unsigned exponent:BKEY_EXPONENT_BITS;
- unsigned m:BKEY_MID_BITS;
- unsigned mantissa:BKEY_MANTISSA_BITS;
+ unsigned int exponent:BKEY_EXPONENT_BITS;
+ unsigned int m:BKEY_MID_BITS;
+ unsigned int mantissa:BKEY_MANTISSA_BITS;
} __packed;
/*
@@ -310,7 +310,9 @@ void bch_btree_keys_free(struct btree_keys *b)
}
EXPORT_SYMBOL(bch_btree_keys_free);
-int bch_btree_keys_alloc(struct btree_keys *b, unsigned page_order, gfp_t gfp)
+int bch_btree_keys_alloc(struct btree_keys *b,
+ unsigned int page_order,
+ gfp_t gfp)
{
struct bset_tree *t = b->set;
@@ -344,7 +346,7 @@ EXPORT_SYMBOL(bch_btree_keys_alloc);
void bch_btree_keys_init(struct btree_keys *b, const struct btree_keys_ops *ops,
bool *expensive_debug_checks)
{
- unsigned i;
+ unsigned int i;
b->ops = ops;
b->expensive_debug_checks = expensive_debug_checks;
@@ -365,7 +367,11 @@ EXPORT_SYMBOL(bch_btree_keys_init);
/* Binary tree stuff for auxiliary search trees */
-static unsigned inorder_next(unsigned j, unsigned size)
+/*
+ * return array index next to j when does in-order traverse
+ * of a binary tree which is stored in a linear array
+ */
+static unsigned int inorder_next(unsigned int j, unsigned int size)
{
if (j * 2 + 1 < size) {
j = j * 2 + 1;
@@ -378,7 +384,11 @@ static unsigned inorder_next(unsigned j, unsigned size)
return j;
}
-static unsigned inorder_prev(unsigned j, unsigned size)
+/*
+ * return array index previous to j when does in-order traverse
+ * of a binary tree which is stored in a linear array
+ */
+static unsigned int inorder_prev(unsigned int j, unsigned int size)
{
if (j * 2 < size) {
j = j * 2;
@@ -391,7 +401,8 @@ static unsigned inorder_prev(unsigned j, unsigned size)
return j;
}
-/* I have no idea why this code works... and I'm the one who wrote it
+/*
+ * I have no idea why this code works... and I'm the one who wrote it
*
* However, I do know what it does:
* Given a binary tree constructed in an array (i.e. how you normally implement
@@ -404,10 +415,12 @@ static unsigned inorder_prev(unsigned j, unsigned size)
* extra is a function of size:
* extra = (size - rounddown_pow_of_two(size - 1)) << 1;
*/
-static unsigned __to_inorder(unsigned j, unsigned size, unsigned extra)
+static unsigned int __to_inorder(unsigned int j,
+ unsigned int size,
+ unsigned int extra)
{
- unsigned b = fls(j);
- unsigned shift = fls(size - 1) - b;
+ unsigned int b = fls(j);
+ unsigned int shift = fls(size - 1) - b;
j ^= 1U << (b - 1);
j <<= 1;
@@ -420,14 +433,20 @@ static unsigned __to_inorder(unsigned j, unsigned size, unsigned extra)
return j;
}
-static unsigned to_inorder(unsigned j, struct bset_tree *t)
+/*
+ * Return the cacheline index in bset_tree->data, where j is index
+ * from a linear array which stores the auxiliar binary tree
+ */
+static unsigned int to_inorder(unsigned int j, struct bset_tree *t)
{
return __to_inorder(j, t->size, t->extra);
}
-static unsigned __inorder_to_tree(unsigned j, unsigned size, unsigned extra)
+static unsigned int __inorder_to_tree(unsigned int j,
+ unsigned int size,
+ unsigned int extra)
{
- unsigned shift;
+ unsigned int shift;
if (j > extra)
j += j - extra;
@@ -440,7 +459,11 @@ static unsigned __inorder_to_tree(unsigned j, unsigned size, unsigned extra)
return j;
}
-static unsigned inorder_to_tree(unsigned j, struct bset_tree *t)
+/*
+ * Return an index from a linear array which stores the auxiliar binary
+ * tree, j is the cacheline index of t->data.
+ */
+static unsigned int inorder_to_tree(unsigned int j, struct bset_tree *t)
{
return __inorder_to_tree(j, t->size, t->extra);
}
@@ -451,14 +474,15 @@ void inorder_test(void)
unsigned long done = 0;
ktime_t start = ktime_get();
- for (unsigned size = 2;
+ for (unsigned int size = 2;
size < 65536000;
size++) {
- unsigned extra = (size - rounddown_pow_of_two(size - 1)) << 1;
- unsigned i = 1, j = rounddown_pow_of_two(size - 1);
+ unsigned int extra =
+ (size - rounddown_pow_of_two(size - 1)) << 1;
+ unsigned int i = 1, j = rounddown_pow_of_two(size - 1);
if (!(size % 4096))
- printk(KERN_NOTICE "loop %u, %llu per us\n", size,
+ pr_notice("loop %u, %llu per us\n", size,
done / ktime_us_delta(ktime_get(), start));
while (1) {
@@ -501,30 +525,31 @@ void inorder_test(void)
* of the previous key so we can walk backwards to it from t->tree[j]'s key.
*/
-static struct bkey *cacheline_to_bkey(struct bset_tree *t, unsigned cacheline,
- unsigned offset)
+static struct bkey *cacheline_to_bkey(struct bset_tree *t,
+ unsigned int cacheline,
+ unsigned int offset)
{
return ((void *) t->data) + cacheline * BSET_CACHELINE + offset * 8;
}
-static unsigned bkey_to_cacheline(struct bset_tree *t, struct bkey *k)
+static unsigned int bkey_to_cacheline(struct bset_tree *t, struct bkey *k)
{
return ((void *) k - (void *) t->data) / BSET_CACHELINE;
}
-static unsigned bkey_to_cacheline_offset(struct bset_tree *t,
- unsigned cacheline,
+static unsigned int bkey_to_cacheline_offset(struct bset_tree *t,
+ unsigned int cacheline,
struct bkey *k)
{
return (u64 *) k - (u64 *) cacheline_to_bkey(t, cacheline, 0);
}
-static struct bkey *tree_to_bkey(struct bset_tree *t, unsigned j)
+static struct bkey *tree_to_bkey(struct bset_tree *t, unsigned int j)
{
return cacheline_to_bkey(t, to_inorder(j, t), t->tree[j].m);
}
-static struct bkey *tree_to_prev_bkey(struct bset_tree *t, unsigned j)
+static struct bkey *tree_to_prev_bkey(struct bset_tree *t, unsigned int j)
{
return (void *) (((uint64_t *) tree_to_bkey(t, j)) - t->prev[j]);
}
@@ -533,7 +558,7 @@ static struct bkey *tree_to_prev_bkey(struct bset_tree *t, unsigned j)
* For the write set - the one we're currently inserting keys into - we don't
* maintain a full search tree, we just keep a simple lookup table in t->prev.
*/
-static struct bkey *table_to_bkey(struct bset_tree *t, unsigned cacheline)
+static struct bkey *table_to_bkey(struct bset_tree *t, unsigned int cacheline)
{
return cacheline_to_bkey(t, cacheline, t->prev[cacheline]);
}
@@ -545,14 +570,29 @@ static inline uint64_t shrd128(uint64_t high, uint64_t low, uint8_t shift)
return low;
}
-static inline unsigned bfloat_mantissa(const struct bkey *k,
+/*
+ * Calculate mantissa value for struct bkey_float.
+ * If most significant bit of f->exponent is not set, then
+ * - f->exponent >> 6 is 0
+ * - p[0] points to bkey->low
+ * - p[-1] borrows bits from KEY_INODE() of bkey->high
+ * if most isgnificant bits of f->exponent is set, then
+ * - f->exponent >> 6 is 1
+ * - p[0] points to bits from KEY_INODE() of bkey->high
+ * - p[-1] points to other bits from KEY_INODE() of
+ * bkey->high too.
+ * See make_bfloat() to check when most significant bit of f->exponent
+ * is set or not.
+ */
+static inline unsigned int bfloat_mantissa(const struct bkey *k,
struct bkey_float *f)
{
const uint64_t *p = &k->low - (f->exponent >> 6);
+
return shrd128(p[-1], p[0], f->exponent & 63) & BKEY_MANTISSA_MASK;
}
-static void make_bfloat(struct bset_tree *t, unsigned j)
+static void make_bfloat(struct bset_tree *t, unsigned int j)
{
struct bkey_float *f = &t->tree[j];
struct bkey *m = tree_to_bkey(t, j);
@@ -569,6 +609,16 @@ static void make_bfloat(struct bset_tree *t, unsigned j)
BUG_ON(m < l || m > r);
BUG_ON(bkey_next(p) != m);
+ /*
+ * If l and r have different KEY_INODE values (different backing
+ * device), f->exponent records how many least significant bits
+ * are different in KEY_INODE values and sets most significant
+ * bits to 1 (by +64).
+ * If l and r have same KEY_INODE value, f->exponent records
+ * how many different bits in least significant bits of bkey->low.
+ * See bfloat_mantiss() how the most significant bit of
+ * f->exponent is used to calculate bfloat mantissa value.
+ */
if (KEY_INODE(l) != KEY_INODE(r))
f->exponent = fls64(KEY_INODE(r) ^ KEY_INODE(l)) + 64;
else
@@ -590,7 +640,7 @@ static void make_bfloat(struct bset_tree *t, unsigned j)
static void bset_alloc_tree(struct btree_keys *b, struct bset_tree *t)
{
if (t != b->set) {
- unsigned j = roundup(t[-1].size,
+ unsigned int j = roundup(t[-1].size,
64 / sizeof(struct bkey_float));
t->tree = t[-1].tree + j;
@@ -632,17 +682,26 @@ void bch_bset_init_next(struct btree_keys *b, struct bset *i, uint64_t magic)
}
EXPORT_SYMBOL(bch_bset_init_next);
+/*
+ * Build auxiliary binary tree 'struct bset_tree *t', this tree is used to
+ * accelerate bkey search in a btree node (pointed by bset_tree->data in
+ * memory). After search in the auxiliar tree by calling bset_search_tree(),
+ * a struct bset_search_iter is returned which indicates range [l, r] from
+ * bset_tree->data where the searching bkey might be inside. Then a followed
+ * linear comparison does the exact search, see __bch_bset_search() for how
+ * the auxiliary tree is used.
+ */
void bch_bset_build_written_tree(struct btree_keys *b)
{
struct bset_tree *t = bset_tree_last(b);
struct bkey *prev = NULL, *k = t->data->start;
- unsigned j, cacheline = 1;
+ unsigned int j, cacheline = 1;
b->last_set_unwritten = 0;
bset_alloc_tree(b, t);
- t->size = min_t(unsigned,
+ t->size = min_t(unsigned int,
bkey_to_cacheline(t, bset_bkey_last(t->data)),
b->set->tree + btree_keys_cachelines(b) - t->tree);
@@ -682,7 +741,7 @@ EXPORT_SYMBOL(bch_bset_build_written_tree);
void bch_bset_fix_invalidated_key(struct btree_keys *b, struct bkey *k)
{
struct bset_tree *t;
- unsigned inorder, j = 1;
+ unsigned int inorder, j = 1;
for (t = b->set; t <= bset_tree_last(b); t++)
if (k < bset_bkey_last(t->data))
@@ -729,14 +788,15 @@ static void bch_bset_fix_lookup_table(struct btree_keys *b,
struct bset_tree *t,
struct bkey *k)
{
- unsigned shift = bkey_u64s(k);
- unsigned j = bkey_to_cacheline(t, k);
+ unsigned int shift = bkey_u64s(k);
+ unsigned int j = bkey_to_cacheline(t, k);
/* We're getting called from btree_split() or btree_gc, just bail out */
if (!t->size)
return;
- /* k is the key we just inserted; we need to find the entry in the
+ /*
+ * k is the key we just inserted; we need to find the entry in the
* lookup table for the first key that is strictly greater than k:
* it's either k's cacheline or the next one
*/
@@ -744,7 +804,8 @@ static void bch_bset_fix_lookup_table(struct btree_keys *b,
table_to_bkey(t, j) <= k)
j++;
- /* Adjust all the lookup table entries, and find a new key for any that
+ /*
+ * Adjust all the lookup table entries, and find a new key for any that
* have gotten too big
*/
for (; j < t->size; j++) {
@@ -769,7 +830,8 @@ static void bch_bset_fix_lookup_table(struct btree_keys *b,
k != bset_bkey_last(t->data);
k = bkey_next(k))
if (t->size == bkey_to_cacheline(t, k)) {
- t->prev[t->size] = bkey_to_cacheline_offset(t, t->size, k);
+ t->prev[t->size] =
+ bkey_to_cacheline_offset(t, t->size, k);
t->size++;
}
}
@@ -817,10 +879,10 @@ void bch_bset_insert(struct btree_keys *b, struct bkey *where,
}
EXPORT_SYMBOL(bch_bset_insert);
-unsigned bch_btree_insert_key(struct btree_keys *b, struct bkey *k,
+unsigned int bch_btree_insert_key(struct btree_keys *b, struct bkey *k,
struct bkey *replace_key)
{
- unsigned status = BTREE_INSERT_STATUS_NO_INSERT;
+ unsigned int status = BTREE_INSERT_STATUS_NO_INSERT;
struct bset *i = bset_tree_last(b)->data;
struct bkey *m, *prev = NULL;
struct btree_iter iter;
@@ -872,10 +934,10 @@ struct bset_search_iter {
static struct bset_search_iter bset_search_write_set(struct bset_tree *t,
const struct bkey *search)
{
- unsigned li = 0, ri = t->size;
+ unsigned int li = 0, ri = t->size;
while (li + 1 != ri) {
- unsigned m = (li + ri) >> 1;
+ unsigned int m = (li + ri) >> 1;
if (bkey_cmp(table_to_bkey(t, m), search) > 0)
ri = m;
@@ -894,10 +956,22 @@ static struct bset_search_iter bset_search_tree(struct bset_tree *t,
{
struct bkey *l, *r;
struct bkey_float *f;
- unsigned inorder, j, n = 1;
+ unsigned int inorder, j, n = 1;
do {
- unsigned p = n << 4;
+ /*
+ * A bit trick here.
+ * If p < t->size, (int)(p - t->size) is a minus value and
+ * the most significant bit is set, right shifting 31 bits
+ * gets 1. If p >= t->size, the most significant bit is
+ * not set, right shifting 31 bits gets 0.
+ * So the following 2 lines equals to
+ * if (p >= t->size)
+ * p = 0;
+ * but a branch instruction is avoided.
+ */
+ unsigned int p = n << 4;
+
p &= ((int) (p - t->size)) >> 31;
prefetch(&t->tree[p]);
@@ -906,6 +980,9 @@ static struct bset_search_iter bset_search_tree(struct bset_tree *t,
f = &t->tree[j];
/*
+ * Similar bit trick, use subtract operation to avoid a branch
+ * instruction.
+ *
* n = (f->mantissa > bfloat_mantissa())
* ? j * 2
* : j * 2 + 1;
@@ -914,7 +991,7 @@ static struct bset_search_iter bset_search_tree(struct bset_tree *t,
* to work - that's done in make_bfloat()
*/
if (likely(f->exponent != 127))
- n = j * 2 + (((unsigned)
+ n = j * 2 + (((unsigned int)
(f->mantissa -
bfloat_mantissa(search, f))) >> 31);
else
@@ -1045,6 +1122,7 @@ static struct bkey *__bch_btree_iter_init(struct btree_keys *b,
struct bset_tree *start)
{
struct bkey *ret = NULL;
+
iter->size = ARRAY_SIZE(iter->data);
iter->used = 0;
@@ -1121,7 +1199,8 @@ void bch_bset_sort_state_free(struct bset_sort_state *state)
mempool_destroy(state->pool);
}
-int bch_bset_sort_state_init(struct bset_sort_state *state, unsigned page_order)
+int bch_bset_sort_state_init(struct bset_sort_state *state,
+ unsigned int page_order)
{
spin_lock_init(&state->time.lock);
@@ -1178,7 +1257,7 @@ static void btree_mergesort(struct btree_keys *b, struct bset *out,
}
static void __btree_sort(struct btree_keys *b, struct btree_iter *iter,
- unsigned start, unsigned order, bool fixup,
+ unsigned int start, unsigned int order, bool fixup,
struct bset_sort_state *state)
{
uint64_t start_time;
@@ -1229,7 +1308,7 @@ static void __btree_sort(struct btree_keys *b, struct btree_iter *iter,
bch_time_stats_update(&state->time, start_time);
}
-void bch_btree_sort_partial(struct btree_keys *b, unsigned start,
+void bch_btree_sort_partial(struct btree_keys *b, unsigned int start,
struct bset_sort_state *state)
{
size_t order = b->page_order, keys = 0;
@@ -1239,7 +1318,7 @@ void bch_btree_sort_partial(struct btree_keys *b, unsigned start,
__bch_btree_iter_init(b, &iter, NULL, &b->set[start]);
if (start) {
- unsigned i;
+ unsigned int i;
for (i = start; i <= b->nsets; i++)
keys += b->set[i].data->keys;
@@ -1264,8 +1343,8 @@ void bch_btree_sort_into(struct btree_keys *b, struct btree_keys *new,
struct bset_sort_state *state)
{
uint64_t start_time = local_clock();
-
struct btree_iter iter;
+
bch_btree_iter_init(b, &iter, NULL);
btree_mergesort(b, new->set->data, &iter, false, true);
@@ -1279,7 +1358,7 @@ void bch_btree_sort_into(struct btree_keys *b, struct btree_keys *new,
void bch_btree_sort_lazy(struct btree_keys *b, struct bset_sort_state *state)
{
- unsigned crit = SORT_CRIT;
+ unsigned int crit = SORT_CRIT;
int i;
/* Don't sort if nothing to do */
@@ -1308,7 +1387,7 @@ EXPORT_SYMBOL(bch_btree_sort_lazy);
void bch_btree_keys_stats(struct btree_keys *b, struct bset_stats *stats)
{
- unsigned i;
+ unsigned int i;
for (i = 0; i <= b->nsets; i++) {
struct bset_tree *t = &b->set[i];
diff --git a/drivers/md/bcache/bset.h b/drivers/md/bcache/bset.h
index d758d444be76..fe584622d8dc 100644
--- a/drivers/md/bcache/bset.h
+++ b/drivers/md/bcache/bset.h
@@ -162,10 +162,10 @@ struct bset_tree {
*/
/* size of the binary tree and prev array */
- unsigned size;
+ unsigned int size;
/* function of size - precalculated for to_inorder() */
- unsigned extra;
+ unsigned int extra;
/* copy of the last key in the set */
struct bkey end;
@@ -186,18 +186,25 @@ struct bset_tree {
};
struct btree_keys_ops {
- bool (*sort_cmp)(struct btree_iter_set,
- struct btree_iter_set);
- struct bkey *(*sort_fixup)(struct btree_iter *, struct bkey *);
- bool (*insert_fixup)(struct btree_keys *, struct bkey *,
- struct btree_iter *, struct bkey *);
- bool (*key_invalid)(struct btree_keys *,
- const struct bkey *);
- bool (*key_bad)(struct btree_keys *, const struct bkey *);
- bool (*key_merge)(struct btree_keys *,
- struct bkey *, struct bkey *);
- void (*key_to_text)(char *, size_t, const struct bkey *);
- void (*key_dump)(struct btree_keys *, const struct bkey *);
+ bool (*sort_cmp)(struct btree_iter_set l,
+ struct btree_iter_set r);
+ struct bkey *(*sort_fixup)(struct btree_iter *iter,
+ struct bkey *tmp);
+ bool (*insert_fixup)(struct btree_keys *b,
+ struct bkey *insert,
+ struct btree_iter *iter,
+ struct bkey *replace_key);
+ bool (*key_invalid)(struct btree_keys *bk,
+ const struct bkey *k);
+ bool (*key_bad)(struct btree_keys *bk,
+ const struct bkey *k);
+ bool (*key_merge)(struct btree_keys *bk,
+ struct bkey *l, struct bkey *r);
+ void (*key_to_text)(char *buf,
+ size_t size,
+ const struct bkey *k);
+ void (*key_dump)(struct btree_keys *keys,
+ const struct bkey *k);
/*
* Only used for deciding whether to use START_KEY(k) or just the key
@@ -210,7 +217,7 @@ struct btree_keys {
const struct btree_keys_ops *ops;
uint8_t page_order;
uint8_t nsets;
- unsigned last_set_unwritten:1;
+ unsigned int last_set_unwritten:1;
bool *expensive_debug_checks;
/*
@@ -238,12 +245,14 @@ static inline bool bkey_written(struct btree_keys *b, struct bkey *k)
return !b->last_set_unwritten || k < b->set[b->nsets].data->start;
}
-static inline unsigned bset_byte_offset(struct btree_keys *b, struct bset *i)
+static inline unsigned int bset_byte_offset(struct btree_keys *b,
+ struct bset *i)
{
return ((size_t) i) - ((size_t) b->set->data);
}
-static inline unsigned bset_sector_offset(struct btree_keys *b, struct bset *i)
+static inline unsigned int bset_sector_offset(struct btree_keys *b,
+ struct bset *i)
{
return bset_byte_offset(b, i) >> 9;
}
@@ -272,25 +281,27 @@ static inline size_t bch_btree_keys_u64s_remaining(struct btree_keys *b)
}
static inline struct bset *bset_next_set(struct btree_keys *b,
- unsigned block_bytes)
+ unsigned int block_bytes)
{
struct bset *i = bset_tree_last(b)->data;
return ((void *) i) + roundup(set_bytes(i), block_bytes);
}
-void bch_btree_keys_free(struct btree_keys *);
-int bch_btree_keys_alloc(struct btree_keys *, unsigned, gfp_t);
-void bch_btree_keys_init(struct btree_keys *, const struct btree_keys_ops *,
- bool *);
-
-void bch_bset_init_next(struct btree_keys *, struct bset *, uint64_t);
-void bch_bset_build_written_tree(struct btree_keys *);
-void bch_bset_fix_invalidated_key(struct btree_keys *, struct bkey *);
-bool bch_bkey_try_merge(struct btree_keys *, struct bkey *, struct bkey *);
-void bch_bset_insert(struct btree_keys *, struct bkey *, struct bkey *);
-unsigned bch_btree_insert_key(struct btree_keys *, struct bkey *,
- struct bkey *);
+void bch_btree_keys_free(struct btree_keys *b);
+int bch_btree_keys_alloc(struct btree_keys *b, unsigned int page_order,
+ gfp_t gfp);
+void bch_btree_keys_init(struct btree_keys *b, const struct btree_keys_ops *ops,
+ bool *expensive_debug_checks);
+
+void bch_bset_init_next(struct btree_keys *b, struct bset *i, uint64_t magic);
+void bch_bset_build_written_tree(struct btree_keys *b);
+void bch_bset_fix_invalidated_key(struct btree_keys *b, struct bkey *k);
+bool bch_bkey_try_merge(struct btree_keys *b, struct bkey *l, struct bkey *r);
+void bch_bset_insert(struct btree_keys *b, struct bkey *where,
+ struct bkey *insert);
+unsigned int bch_btree_insert_key(struct btree_keys *b, struct bkey *k,
+ struct bkey *replace_key);
enum {
BTREE_INSERT_STATUS_NO_INSERT = 0,
@@ -312,18 +323,21 @@ struct btree_iter {
} data[MAX_BSETS];
};
-typedef bool (*ptr_filter_fn)(struct btree_keys *, const struct bkey *);
+typedef bool (*ptr_filter_fn)(struct btree_keys *b, const struct bkey *k);
-struct bkey *bch_btree_iter_next(struct btree_iter *);
-struct bkey *bch_btree_iter_next_filter(struct btree_iter *,
- struct btree_keys *, ptr_filter_fn);
+struct bkey *bch_btree_iter_next(struct btree_iter *iter);
+struct bkey *bch_btree_iter_next_filter(struct btree_iter *iter,
+ struct btree_keys *b,
+ ptr_filter_fn fn);
-void bch_btree_iter_push(struct btree_iter *, struct bkey *, struct bkey *);
-struct bkey *bch_btree_iter_init(struct btree_keys *, struct btree_iter *,
- struct bkey *);
+void bch_btree_iter_push(struct btree_iter *iter, struct bkey *k,
+ struct bkey *end);
+struct bkey *bch_btree_iter_init(struct btree_keys *b,
+ struct btree_iter *iter,
+ struct bkey *search);
-struct bkey *__bch_bset_search(struct btree_keys *, struct bset_tree *,
- const struct bkey *);
+struct bkey *__bch_bset_search(struct btree_keys *b, struct bset_tree *t,
+ const struct bkey *search);
/*
* Returns the first key that is strictly greater than search
@@ -348,21 +362,23 @@ static inline struct bkey *bch_bset_search(struct btree_keys *b,
struct bset_sort_state {
mempool_t *pool;
- unsigned page_order;
- unsigned crit_factor;
+ unsigned int page_order;
+ unsigned int crit_factor;
struct time_stats time;
};
-void bch_bset_sort_state_free(struct bset_sort_state *);
-int bch_bset_sort_state_init(struct bset_sort_state *, unsigned);
-void bch_btree_sort_lazy(struct btree_keys *, struct bset_sort_state *);
-void bch_btree_sort_into(struct btree_keys *, struct btree_keys *,
- struct bset_sort_state *);
-void bch_btree_sort_and_fix_extents(struct btree_keys *, struct btree_iter *,
- struct bset_sort_state *);
-void bch_btree_sort_partial(struct btree_keys *, unsigned,
- struct bset_sort_state *);
+void bch_bset_sort_state_free(struct bset_sort_state *state);
+int bch_bset_sort_state_init(struct bset_sort_state *state,
+ unsigned int page_order);
+void bch_btree_sort_lazy(struct btree_keys *b, struct bset_sort_state *state);
+void bch_btree_sort_into(struct btree_keys *b, struct btree_keys *new,
+ struct bset_sort_state *state);
+void bch_btree_sort_and_fix_extents(struct btree_keys *b,
+ struct btree_iter *iter,
+ struct bset_sort_state *state);
+void bch_btree_sort_partial(struct btree_keys *b, unsigned int start,
+ struct bset_sort_state *state);
static inline void bch_btree_sort(struct btree_keys *b,
struct bset_sort_state *state)
@@ -376,13 +392,13 @@ struct bset_stats {
size_t floats, failed;
};
-void bch_btree_keys_stats(struct btree_keys *, struct bset_stats *);
+void bch_btree_keys_stats(struct btree_keys *b, struct bset_stats *state);
/* Bkey utility code */
#define bset_bkey_last(i) bkey_idx((struct bkey *) (i)->d, (i)->keys)
-static inline struct bkey *bset_bkey_idx(struct bset *i, unsigned idx)
+static inline struct bkey *bset_bkey_idx(struct bset *i, unsigned int idx)
{
return bkey_idx(i->start, idx);
}
@@ -400,10 +416,10 @@ static __always_inline int64_t bkey_cmp(const struct bkey *l,
: (int64_t) KEY_OFFSET(l) - (int64_t) KEY_OFFSET(r);
}
-void bch_bkey_copy_single_ptr(struct bkey *, const struct bkey *,
- unsigned);
-bool __bch_cut_front(const struct bkey *, struct bkey *);
-bool __bch_cut_back(const struct bkey *, struct bkey *);
+void bch_bkey_copy_single_ptr(struct bkey *dest, const struct bkey *src,
+ unsigned int i);
+bool __bch_cut_front(const struct bkey *where, struct bkey *k);
+bool __bch_cut_back(const struct bkey *where, struct bkey *k);
static inline bool bch_cut_front(const struct bkey *where, struct bkey *k)
{
@@ -521,18 +537,20 @@ static inline size_t bch_keylist_bytes(struct keylist *l)
return bch_keylist_nkeys(l) * sizeof(uint64_t);
}
-struct bkey *bch_keylist_pop(struct keylist *);
-void bch_keylist_pop_front(struct keylist *);
-int __bch_keylist_realloc(struct keylist *, unsigned);
+struct bkey *bch_keylist_pop(struct keylist *l);
+void bch_keylist_pop_front(struct keylist *l);
+int __bch_keylist_realloc(struct keylist *l, unsigned int u64s);
/* Debug stuff */
#ifdef CONFIG_BCACHE_DEBUG
-int __bch_count_data(struct btree_keys *);
-void __printf(2, 3) __bch_check_keys(struct btree_keys *, const char *, ...);
-void bch_dump_bset(struct btree_keys *, struct bset *, unsigned);
-void bch_dump_bucket(struct btree_keys *);
+int __bch_count_data(struct btree_keys *b);
+void __printf(2, 3) __bch_check_keys(struct btree_keys *b,
+ const char *fmt,
+ ...);
+void bch_dump_bset(struct btree_keys *b, struct bset *i, unsigned int set);
+void bch_dump_bucket(struct btree_keys *b);
#else
@@ -540,7 +558,7 @@ static inline int __bch_count_data(struct btree_keys *b) { return -1; }
static inline void __printf(2, 3)
__bch_check_keys(struct btree_keys *b, const char *fmt, ...) {}
static inline void bch_dump_bucket(struct btree_keys *b) {}
-void bch_dump_bset(struct btree_keys *, struct bset *, unsigned);
+void bch_dump_bset(struct btree_keys *b, struct bset *i, unsigned int set);
#endif
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index 4f5278b43f25..4c1b976fc2da 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -182,7 +182,7 @@ static void bch_btree_init_next(struct btree *b)
void bkey_put(struct cache_set *c, struct bkey *k)
{
- unsigned i;
+ unsigned int i;
for (i = 0; i < KEY_PTRS(k); i++)
if (ptr_available(c, k, i))
@@ -206,6 +206,11 @@ void bch_btree_node_read_done(struct btree *b)
struct bset *i = btree_bset_first(b);
struct btree_iter *iter;
+ /*
+ * c->fill_iter can allocate an iterator with more memory space
+ * than static MAX_BSETS.
+ * See the comment arount cache_set->fill_iter.
+ */
iter = mempool_alloc(b->c->fill_iter, GFP_NOIO);
iter->size = b->c->sb.bucket_size / b->c->sb.block_size;
iter->used = 0;
@@ -286,6 +291,7 @@ err:
static void btree_node_read_endio(struct bio *bio)
{
struct closure *cl = bio->bi_private;
+
closure_put(cl);
}
@@ -434,7 +440,10 @@ static void do_btree_node_write(struct btree *b)
continue_at(cl, btree_node_write_done, NULL);
} else {
- /* No problem for multipage bvec since the bio is just allocated */
+ /*
+ * No problem for multipage bvec since the bio is
+ * just allocated
+ */
b->bio->bi_vcnt = 0;
bch_bio_map(b->bio, i);
@@ -478,7 +487,7 @@ void __bch_btree_node_write(struct btree *b, struct closure *parent)
void bch_btree_node_write(struct btree *b, struct closure *parent)
{
- unsigned nsets = b->keys.nsets;
+ unsigned int nsets = b->keys.nsets;
lockdep_assert_held(&b->lock);
@@ -580,7 +589,7 @@ static void mca_bucket_free(struct btree *b)
list_move(&b->list, &b->c->btree_cache_freeable);
}
-static unsigned btree_order(struct bkey *k)
+static unsigned int btree_order(struct bkey *k)
{
return ilog2(KEY_SIZE(k) / PAGE_SECTORS ?: 1);
}
@@ -588,7 +597,7 @@ static unsigned btree_order(struct bkey *k)
static void mca_data_alloc(struct btree *b, struct bkey *k, gfp_t gfp)
{
if (!bch_btree_keys_alloc(&b->keys,
- max_t(unsigned,
+ max_t(unsigned int,
ilog2(b->c->btree_pages),
btree_order(k)),
gfp)) {
@@ -603,6 +612,7 @@ static struct btree *mca_bucket_alloc(struct cache_set *c,
struct bkey *k, gfp_t gfp)
{
struct btree *b = kzalloc(sizeof(struct btree), gfp);
+
if (!b)
return NULL;
@@ -619,7 +629,7 @@ static struct btree *mca_bucket_alloc(struct cache_set *c,
return b;
}
-static int mca_reap(struct btree *b, unsigned min_order, bool flush)
+static int mca_reap(struct btree *b, unsigned int min_order, bool flush)
{
struct closure cl;
@@ -745,6 +755,7 @@ void bch_btree_cache_free(struct cache_set *c)
{
struct btree *b;
struct closure cl;
+
closure_init_stack(&cl);
if (c->shrink.list.next)
@@ -785,7 +796,7 @@ void bch_btree_cache_free(struct cache_set *c)
int bch_btree_cache_alloc(struct cache_set *c)
{
- unsigned i;
+ unsigned int i;
for (i = 0; i < mca_reserve(c); i++)
if (!mca_bucket_alloc(c, &ZERO_KEY, GFP_KERNEL))
@@ -1123,6 +1134,7 @@ static struct btree *btree_node_alloc_replacement(struct btree *b,
struct btree_op *op)
{
struct btree *n = bch_btree_node_alloc(b->c, op, b->level, b->parent);
+
if (!IS_ERR_OR_NULL(n)) {
mutex_lock(&n->write_lock);
bch_btree_sort_into(&b->keys, &n->keys, &b->c->sort);
@@ -1135,7 +1147,7 @@ static struct btree *btree_node_alloc_replacement(struct btree *b,
static void make_btree_freeing_key(struct btree *b, struct bkey *k)
{
- unsigned i;
+ unsigned int i;
mutex_lock(&b->c->bucket_lock);
@@ -1156,7 +1168,7 @@ static int btree_check_reserve(struct btree *b, struct btree_op *op)
{
struct cache_set *c = b->c;
struct cache *ca;
- unsigned i, reserve = (c->root->level - b->level) * 2 + 1;
+ unsigned int i, reserve = (c->root->level - b->level) * 2 + 1;
mutex_lock(&c->bucket_lock);
@@ -1180,7 +1192,7 @@ static uint8_t __bch_btree_mark_key(struct cache_set *c, int level,
struct bkey *k)
{
uint8_t stale = 0;
- unsigned i;
+ unsigned int i;
struct bucket *g;
/*
@@ -1218,7 +1230,7 @@ static uint8_t __bch_btree_mark_key(struct cache_set *c, int level,
SET_GC_MARK(g, GC_MARK_RECLAIMABLE);
/* guard against overflow */
- SET_GC_SECTORS_USED(g, min_t(unsigned,
+ SET_GC_SECTORS_USED(g, min_t(unsigned int,
GC_SECTORS_USED(g) + KEY_SIZE(k),
MAX_GC_SECTORS_USED));
@@ -1232,7 +1244,7 @@ static uint8_t __bch_btree_mark_key(struct cache_set *c, int level,
void bch_initial_mark_key(struct cache_set *c, int level, struct bkey *k)
{
- unsigned i;
+ unsigned int i;
for (i = 0; i < KEY_PTRS(k); i++)
if (ptr_available(c, k, i) &&
@@ -1258,7 +1270,7 @@ void bch_update_bucket_in_use(struct cache_set *c, struct gc_stat *stats)
static bool btree_gc_mark_node(struct btree *b, struct gc_stat *gc)
{
uint8_t stale = 0;
- unsigned keys = 0, good_keys = 0;
+ unsigned int keys = 0, good_keys = 0;
struct bkey *k;
struct btree_iter iter;
struct bset_tree *t;
@@ -1301,16 +1313,18 @@ static bool btree_gc_mark_node(struct btree *b, struct gc_stat *gc)
struct gc_merge_info {
struct btree *b;
- unsigned keys;
+ unsigned int keys;
};
-static int bch_btree_insert_node(struct btree *, struct btree_op *,
- struct keylist *, atomic_t *, struct bkey *);
+static int bch_btree_insert_node(struct btree *b, struct btree_op *op,
+ struct keylist *insert_keys,
+ atomic_t *journal_ref,
+ struct bkey *replace_key);
static int btree_gc_coalesce(struct btree *b, struct btree_op *op,
struct gc_stat *gc, struct gc_merge_info *r)
{
- unsigned i, nodes = 0, keys = 0, blocks;
+ unsigned int i, nodes = 0, keys = 0, blocks;
struct btree *new_nodes[GC_MERGE_NODES];
struct keylist keylist;
struct closure cl;
@@ -1510,11 +1524,11 @@ static int btree_gc_rewrite_node(struct btree *b, struct btree_op *op,
return -EINTR;
}
-static unsigned btree_gc_count_keys(struct btree *b)
+static unsigned int btree_gc_count_keys(struct btree *b)
{
struct bkey *k;
struct btree_iter iter;
- unsigned ret = 0;
+ unsigned int ret = 0;
for_each_key_filter(&b->keys, k, &iter, bch_ptr_bad)
ret += bkey_u64s(k);
@@ -1677,7 +1691,7 @@ static void btree_gc_start(struct cache_set *c)
{
struct cache *ca;
struct bucket *b;
- unsigned i;
+ unsigned int i;
if (!c->gc_mark_valid)
return;
@@ -1703,7 +1717,7 @@ static void bch_btree_gc_finish(struct cache_set *c)
{
struct bucket *b;
struct cache *ca;
- unsigned i;
+ unsigned int i;
mutex_lock(&c->bucket_lock);
@@ -1721,7 +1735,7 @@ static void bch_btree_gc_finish(struct cache_set *c)
struct bcache_device *d = c->devices[i];
struct cached_dev *dc;
struct keybuf_key *w, *n;
- unsigned j;
+ unsigned int j;
if (!d || UUID_FLASH_ONLY(&c->uuids[i]))
continue;
@@ -1813,7 +1827,7 @@ static void bch_btree_gc(struct cache_set *c)
static bool gc_should_run(struct cache_set *c)
{
struct cache *ca;
- unsigned i;
+ unsigned int i;
for_each_cache(ca, c, i)
if (ca->invalidate_needs_gc)
@@ -1904,7 +1918,7 @@ void bch_initial_gc_finish(struct cache_set *c)
{
struct cache *ca;
struct bucket *b;
- unsigned i;
+ unsigned int i;
bch_btree_gc_finish(c);
@@ -1944,7 +1958,7 @@ void bch_initial_gc_finish(struct cache_set *c)
static bool btree_insert_key(struct btree *b, struct bkey *k,
struct bkey *replace_key)
{
- unsigned status;
+ unsigned int status;
BUG_ON(bkey_cmp(k, &b->key) > 0);
@@ -2043,7 +2057,7 @@ static int btree_split(struct btree *b, struct btree_op *op,
block_bytes(n1->c)) > (btree_blocks(b) * 4) / 5;
if (split) {
- unsigned keys = 0;
+ unsigned int keys = 0;
trace_bcache_btree_node_split(b, btree_bset_first(n1)->keys);
@@ -2221,10 +2235,10 @@ int bch_btree_insert_check_key(struct btree *b, struct btree_op *op,
rw_lock(true, b, b->level);
if (b->key.ptr[0] != btree_ptr ||
- b->seq != seq + 1) {
+ b->seq != seq + 1) {
op->lock = b->level;
goto out;
- }
+ }
}
SET_KEY_PTRS(check_key, 1);
@@ -2299,7 +2313,7 @@ int bch_btree_insert(struct cache_set *c, struct keylist *keys,
void bch_btree_set_root(struct btree *b)
{
- unsigned i;
+ unsigned int i;
struct closure cl;
closure_init_stack(&cl);
@@ -2411,7 +2425,7 @@ static inline int keybuf_nonoverlapping_cmp(struct keybuf_key *l,
struct refill {
struct btree_op op;
- unsigned nr_found;
+ unsigned int nr_found;
struct keybuf *buf;
struct bkey *end;
keybuf_pred_fn *pred;
@@ -2487,6 +2501,7 @@ void bch_refill_keybuf(struct cache_set *c, struct keybuf *buf,
if (!RB_EMPTY_ROOT(&buf->keys)) {
struct keybuf_key *w;
+
w = RB_FIRST(&buf->keys, struct keybuf_key, node);
buf->start = START_KEY(&w->key);
@@ -2518,6 +2533,7 @@ bool bch_keybuf_check_overlapping(struct keybuf *buf, struct bkey *start,
{
bool ret = false;
struct keybuf_key *p, *w, s;
+
s.key = *start;
if (bkey_cmp(end, &buf->start) <= 0 ||
@@ -2544,6 +2560,7 @@ bool bch_keybuf_check_overlapping(struct keybuf *buf, struct bkey *start,
struct keybuf_key *bch_keybuf_next(struct keybuf *buf)
{
struct keybuf_key *w;
+
spin_lock(&buf->lock);
w = RB_FIRST(&buf->keys, struct keybuf_key, node);
diff --git a/drivers/md/bcache/btree.h b/drivers/md/bcache/btree.h
index 4073aca09a49..e9432b4d33a8 100644
--- a/drivers/md/bcache/btree.h
+++ b/drivers/md/bcache/btree.h
@@ -151,7 +151,7 @@ static inline bool btree_node_ ## flag(struct btree *b) \
{ return test_bit(BTREE_NODE_ ## flag, &b->flags); } \
\
static inline void set_btree_node_ ## flag(struct btree *b) \
-{ set_bit(BTREE_NODE_ ## flag, &b->flags); } \
+{ set_bit(BTREE_NODE_ ## flag, &b->flags); }
enum btree_flags {
BTREE_NODE_io_error,
@@ -183,7 +183,7 @@ static inline struct bset *btree_bset_last(struct btree *b)
return bset_tree_last(&b->keys)->data;
}
-static inline unsigned bset_block_offset(struct btree *b, struct bset *i)
+static inline unsigned int bset_block_offset(struct btree *b, struct bset *i)
{
return bset_sector_offset(&b->keys, i) >> b->c->block_bits;
}
@@ -212,7 +212,7 @@ struct btree_op {
/* Btree level at which we start taking write locks */
short lock;
- unsigned insert_collision:1;
+ unsigned int insert_collision:1;
};
static inline void bch_btree_op_init(struct btree_op *op, int write_lock_level)
@@ -237,32 +237,52 @@ static inline void rw_unlock(bool w, struct btree *b)
(w ? up_write : up_read)(&b->lock);
}
-void bch_btree_node_read_done(struct btree *);
-void __bch_btree_node_write(struct btree *, struct closure *);
-void bch_btree_node_write(struct btree *, struct closure *);
-
-void bch_btree_set_root(struct btree *);
-struct btree *__bch_btree_node_alloc(struct cache_set *, struct btree_op *,
- int, bool, struct btree *);
-struct btree *bch_btree_node_get(struct cache_set *, struct btree_op *,
- struct bkey *, int, bool, struct btree *);
-
-int bch_btree_insert_check_key(struct btree *, struct btree_op *,
- struct bkey *);
-int bch_btree_insert(struct cache_set *, struct keylist *,
- atomic_t *, struct bkey *);
-
-int bch_gc_thread_start(struct cache_set *);
-void bch_initial_gc_finish(struct cache_set *);
-void bch_moving_gc(struct cache_set *);
-int bch_btree_check(struct cache_set *);
-void bch_initial_mark_key(struct cache_set *, int, struct bkey *);
+void bch_btree_node_read_done(struct btree *b);
+void __bch_btree_node_write(struct btree *b, struct closure *parent);
+void bch_btree_node_write(struct btree *b, struct closure *parent);
+
+void bch_btree_set_root(struct btree *b);
+struct btree *__bch_btree_node_alloc(struct cache_set *c, struct btree_op *op,
+ int level, bool wait,
+ struct btree *parent);
+struct btree *bch_btree_node_get(struct cache_set *c, struct btree_op *op,
+ struct bkey *k, int level, bool write,
+ struct btree *parent);
+
+int bch_btree_insert_check_key(struct btree *b, struct btree_op *op,
+ struct bkey *check_key);
+int bch_btree_insert(struct cache_set *c, struct keylist *keys,
+ atomic_t *journal_ref, struct bkey *replace_key);
+
+int bch_gc_thread_start(struct cache_set *c);
+void bch_initial_gc_finish(struct cache_set *c);
+void bch_moving_gc(struct cache_set *c);
+int bch_btree_check(struct cache_set *c);
+void bch_initial_mark_key(struct cache_set *c, int level, struct bkey *k);
static inline void wake_up_gc(struct cache_set *c)
{
wake_up(&c->gc_wait);
}
+static inline void force_wake_up_gc(struct cache_set *c)
+{
+ /*
+ * Garbage collection thread only works when sectors_to_gc < 0,
+ * calling wake_up_gc() won't start gc thread if sectors_to_gc is
+ * not a nagetive value.
+ * Therefore sectors_to_gc is set to -1 here, before waking up
+ * gc thread by calling wake_up_gc(). Then gc_should_run() will
+ * give a chance to permit gc thread to run. "Give a chance" means
+ * before going into gc_should_run(), there is still possibility
+ * that c->sectors_to_gc being set to other positive value. So
+ * this routine won't 100% make sure gc thread will be woken up
+ * to run.
+ */
+ atomic_set(&c->sectors_to_gc, -1);
+ wake_up_gc(c);
+}
+
#define MAP_DONE 0
#define MAP_CONTINUE 1
@@ -271,9 +291,9 @@ static inline void wake_up_gc(struct cache_set *c)
#define MAP_END_KEY 1
-typedef int (btree_map_nodes_fn)(struct btree_op *, struct btree *);
-int __bch_btree_map_nodes(struct btree_op *, struct cache_set *,
- struct bkey *, btree_map_nodes_fn *, int);
+typedef int (btree_map_nodes_fn)(struct btree_op *b_op, struct btree *b);
+int __bch_btree_map_nodes(struct btree_op *op, struct cache_set *c,
+ struct bkey *from, btree_map_nodes_fn *fn, int flags);
static inline int bch_btree_map_nodes(struct btree_op *op, struct cache_set *c,
struct bkey *from, btree_map_nodes_fn *fn)
@@ -289,21 +309,23 @@ static inline int bch_btree_map_leaf_nodes(struct btree_op *op,
return __bch_btree_map_nodes(op, c, from, fn, MAP_LEAF_NODES);
}
-typedef int (btree_map_keys_fn)(struct btree_op *, struct btree *,
- struct bkey *);
-int bch_btree_map_keys(struct btree_op *, struct cache_set *,
- struct bkey *, btree_map_keys_fn *, int);
-
-typedef bool (keybuf_pred_fn)(struct keybuf *, struct bkey *);
-
-void bch_keybuf_init(struct keybuf *);
-void bch_refill_keybuf(struct cache_set *, struct keybuf *,
- struct bkey *, keybuf_pred_fn *);
-bool bch_keybuf_check_overlapping(struct keybuf *, struct bkey *,
- struct bkey *);
-void bch_keybuf_del(struct keybuf *, struct keybuf_key *);
-struct keybuf_key *bch_keybuf_next(struct keybuf *);
-struct keybuf_key *bch_keybuf_next_rescan(struct cache_set *, struct keybuf *,
- struct bkey *, keybuf_pred_fn *);
+typedef int (btree_map_keys_fn)(struct btree_op *op, struct btree *b,
+ struct bkey *k);
+int bch_btree_map_keys(struct btree_op *op, struct cache_set *c,
+ struct bkey *from, btree_map_keys_fn *fn, int flags);
+
+typedef bool (keybuf_pred_fn)(struct keybuf *buf, struct bkey *k);
+
+void bch_keybuf_init(struct keybuf *buf);
+void bch_refill_keybuf(struct cache_set *c, struct keybuf *buf,
+ struct bkey *end, keybuf_pred_fn *pred);
+bool bch_keybuf_check_overlapping(struct keybuf *buf, struct bkey *start,
+ struct bkey *end);
+void bch_keybuf_del(struct keybuf *buf, struct keybuf_key *w);
+struct keybuf_key *bch_keybuf_next(struct keybuf *buf);
+struct keybuf_key *bch_keybuf_next_rescan(struct cache_set *c,
+ struct keybuf *buf,
+ struct bkey *end,
+ keybuf_pred_fn *pred);
void bch_update_bucket_in_use(struct cache_set *c, struct gc_stat *stats);
#endif
diff --git a/drivers/md/bcache/closure.c b/drivers/md/bcache/closure.c
index 618253683d40..73f5319295bc 100644
--- a/drivers/md/bcache/closure.c
+++ b/drivers/md/bcache/closure.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* Asynchronous refcounty things
*
@@ -162,12 +163,13 @@ static struct dentry *closure_debug;
static int debug_seq_show(struct seq_file *f, void *data)
{
struct closure *cl;
+
spin_lock_irq(&closure_list_lock);
list_for_each_entry(cl, &closure_list, all) {
int r = atomic_read(&cl->remaining);
- seq_printf(f, "%p: %pF -> %pf p %p r %i ",
+ seq_printf(f, "%p: %pS -> %pS p %p r %i ",
cl, (void *) cl->ip, cl->fn, cl->parent,
r & CLOSURE_REMAINING_MASK);
@@ -177,7 +179,7 @@ static int debug_seq_show(struct seq_file *f, void *data)
r & CLOSURE_RUNNING ? "R" : "");
if (r & CLOSURE_WAITING)
- seq_printf(f, " W %pF\n",
+ seq_printf(f, " W %pS\n",
(void *) cl->waiting_on);
seq_printf(f, "\n");
diff --git a/drivers/md/bcache/closure.h b/drivers/md/bcache/closure.h
index 4b2c467f544e..45c8ba88e247 100644
--- a/drivers/md/bcache/closure.h
+++ b/drivers/md/bcache/closure.h
@@ -158,7 +158,7 @@ struct closure {
#define CLOSURE_MAGIC_DEAD 0xc054dead
#define CLOSURE_MAGIC_ALIVE 0xc054a11e
- unsigned magic;
+ unsigned int magic;
struct list_head all;
unsigned long ip;
unsigned long waiting_on;
@@ -288,10 +288,12 @@ static inline void closure_init_stack(struct closure *cl)
}
/**
- * closure_wake_up - wake up all closures on a wait list.
+ * closure_wake_up - wake up all closures on a wait list,
+ * with memory barrier
*/
static inline void closure_wake_up(struct closure_waitlist *list)
{
+ /* Memory barrier for the wait list */
smp_mb();
__closure_wake_up(list);
}
@@ -342,7 +344,8 @@ do { \
} while (0)
/**
- * closure_return - finish execution of a closure, with destructor
+ * closure_return_with_destructor - finish execution of a closure,
+ * with destructor
*
* Works like closure_return(), except @destructor will be called when all
* outstanding refs on @cl have been dropped; @destructor may be used to safely
diff --git a/drivers/md/bcache/debug.c b/drivers/md/bcache/debug.c
index 78b010a0679b..b6cce77696b5 100644
--- a/drivers/md/bcache/debug.c
+++ b/drivers/md/bcache/debug.c
@@ -66,34 +66,35 @@ void bch_btree_verify(struct btree *b)
if (inmemory->keys != sorted->keys ||
memcmp(inmemory->start,
sorted->start,
- (void *) bset_bkey_last(inmemory) - (void *) inmemory->start)) {
+ (void *) bset_bkey_last(inmemory) -
+ (void *) inmemory->start)) {
struct bset *i;
- unsigned j;
+ unsigned int j;
console_lock();
- printk(KERN_ERR "*** in memory:\n");
+ pr_err("*** in memory:\n");
bch_dump_bset(&b->keys, inmemory, 0);
- printk(KERN_ERR "*** read back in:\n");
+ pr_err("*** read back in:\n");
bch_dump_bset(&v->keys, sorted, 0);
for_each_written_bset(b, ondisk, i) {
- unsigned block = ((void *) i - (void *) ondisk) /
+ unsigned int block = ((void *) i - (void *) ondisk) /
block_bytes(b->c);
- printk(KERN_ERR "*** on disk block %u:\n", block);
+ pr_err("*** on disk block %u:\n", block);
bch_dump_bset(&b->keys, i, block);
}
- printk(KERN_ERR "*** block %zu not written\n",
+ pr_err("*** block %zu not written\n",
((void *) i - (void *) ondisk) / block_bytes(b->c));
for (j = 0; j < inmemory->keys; j++)
if (inmemory->d[j] != sorted->d[j])
break;
- printk(KERN_ERR "b->written %u\n", b->written);
+ pr_err("b->written %u\n", b->written);
console_unlock();
panic("verify failed at %u\n", j);
@@ -109,11 +110,15 @@ void bch_data_verify(struct cached_dev *dc, struct bio *bio)
struct bio_vec bv, cbv;
struct bvec_iter iter, citer = { 0 };
- check = bio_clone_kmalloc(bio, GFP_NOIO);
+ check = bio_kmalloc(GFP_NOIO, bio_segments(bio));
if (!check)
return;
+ check->bi_disk = bio->bi_disk;
check->bi_opf = REQ_OP_READ;
+ check->bi_iter.bi_sector = bio->bi_iter.bi_sector;
+ check->bi_iter.bi_size = bio->bi_iter.bi_size;
+ bch_bio_map(check, NULL);
if (bio_alloc_pages(check, GFP_NOIO))
goto out_put;
@@ -171,9 +176,9 @@ static ssize_t bch_dump_read(struct file *file, char __user *buf,
while (size) {
struct keybuf_key *w;
- unsigned bytes = min(i->bytes, size);
-
+ unsigned int bytes = min(i->bytes, size);
int err = copy_to_user(buf, i->buf, bytes);
+
if (err)
return err;
@@ -232,8 +237,8 @@ void bch_debug_init_cache_set(struct cache_set *c)
{
if (!IS_ERR_OR_NULL(bcache_debug)) {
char name[50];
- snprintf(name, 50, "bcache-%pU", c->sb.set_uuid);
+ snprintf(name, 50, "bcache-%pU", c->sb.set_uuid);
c->debug = debugfs_create_file(name, 0400, bcache_debug, c,
&cache_set_debug_ops);
}
@@ -243,11 +248,10 @@ void bch_debug_init_cache_set(struct cache_set *c)
void bch_debug_exit(void)
{
- if (!IS_ERR_OR_NULL(bcache_debug))
- debugfs_remove_recursive(bcache_debug);
+ debugfs_remove_recursive(bcache_debug);
}
-void __init bch_debug_init(struct kobject *kobj)
+void __init bch_debug_init(void)
{
/*
* it is unnecessary to check return value of
diff --git a/drivers/md/bcache/debug.h b/drivers/md/bcache/debug.h
index 1f63c195d247..6c8b7eee7a46 100644
--- a/drivers/md/bcache/debug.h
+++ b/drivers/md/bcache/debug.h
@@ -7,8 +7,8 @@ struct cache_set;
#ifdef CONFIG_BCACHE_DEBUG
-void bch_btree_verify(struct btree *);
-void bch_data_verify(struct cached_dev *, struct bio *);
+void bch_btree_verify(struct btree *b);
+void bch_data_verify(struct cached_dev *dc, struct bio *bio);
#define expensive_debug_checks(c) ((c)->expensive_debug_checks)
#define key_merging_disabled(c) ((c)->key_merging_disabled)
@@ -26,7 +26,7 @@ static inline void bch_data_verify(struct cached_dev *dc, struct bio *bio) {}
#endif
#ifdef CONFIG_DEBUG_FS
-void bch_debug_init_cache_set(struct cache_set *);
+void bch_debug_init_cache_set(struct cache_set *c);
#else
static inline void bch_debug_init_cache_set(struct cache_set *c) {}
#endif
diff --git a/drivers/md/bcache/extents.c b/drivers/md/bcache/extents.c
index a1d536d3a971..0f29ada088da 100644
--- a/drivers/md/bcache/extents.c
+++ b/drivers/md/bcache/extents.c
@@ -45,7 +45,7 @@ static bool bch_key_sort_cmp(struct btree_iter_set l,
static bool __ptr_invalid(struct cache_set *c, const struct bkey *k)
{
- unsigned i;
+ unsigned int i;
for (i = 0; i < KEY_PTRS(k); i++)
if (ptr_available(c, k, i)) {
@@ -66,7 +66,7 @@ static bool __ptr_invalid(struct cache_set *c, const struct bkey *k)
static const char *bch_ptr_status(struct cache_set *c, const struct bkey *k)
{
- unsigned i;
+ unsigned int i;
for (i = 0; i < KEY_PTRS(k); i++)
if (ptr_available(c, k, i)) {
@@ -95,7 +95,7 @@ static const char *bch_ptr_status(struct cache_set *c, const struct bkey *k)
void bch_extent_to_text(char *buf, size_t size, const struct bkey *k)
{
- unsigned i = 0;
+ unsigned int i = 0;
char *out = buf, *end = buf + size;
#define p(...) (out += scnprintf(out, end - out, __VA_ARGS__))
@@ -125,22 +125,22 @@ void bch_extent_to_text(char *buf, size_t size, const struct bkey *k)
static void bch_bkey_dump(struct btree_keys *keys, const struct bkey *k)
{
struct btree *b = container_of(keys, struct btree, keys);
- unsigned j;
+ unsigned int j;
char buf[80];
bch_extent_to_text(buf, sizeof(buf), k);
- printk(" %s", buf);
+ pr_err(" %s", buf);
for (j = 0; j < KEY_PTRS(k); j++) {
size_t n = PTR_BUCKET_NR(b->c, k, j);
- printk(" bucket %zu", n);
+ pr_err(" bucket %zu", n);
if (n >= b->c->sb.first_bucket && n < b->c->sb.nbuckets)
- printk(" prio %i",
+ pr_err(" prio %i",
PTR_BUCKET(b->c, k, j)->prio);
}
- printk(" %s\n", bch_ptr_status(b->c, k));
+ pr_err(" %s\n", bch_ptr_status(b->c, k));
}
/* Btree ptrs */
@@ -165,12 +165,13 @@ bad:
static bool bch_btree_ptr_invalid(struct btree_keys *bk, const struct bkey *k)
{
struct btree *b = container_of(bk, struct btree, keys);
+
return __bch_btree_ptr_invalid(b->c, k);
}
static bool btree_ptr_bad_expensive(struct btree *b, const struct bkey *k)
{
- unsigned i;
+ unsigned int i;
char buf[80];
struct bucket *g;
@@ -203,7 +204,7 @@ err:
static bool bch_btree_ptr_bad(struct btree_keys *bk, const struct bkey *k)
{
struct btree *b = container_of(bk, struct btree, keys);
- unsigned i;
+ unsigned int i;
if (!bkey_cmp(k, &ZERO_KEY) ||
!KEY_PTRS(k) ||
@@ -326,13 +327,14 @@ static bool bch_extent_insert_fixup(struct btree_keys *b,
struct cache_set *c = container_of(b, struct btree, keys)->c;
uint64_t old_offset;
- unsigned old_size, sectors_found = 0;
+ unsigned int old_size, sectors_found = 0;
BUG_ON(!KEY_OFFSET(insert));
BUG_ON(!KEY_SIZE(insert));
while (1) {
struct bkey *k = bch_btree_iter_next(iter);
+
if (!k)
break;
@@ -362,7 +364,7 @@ static bool bch_extent_insert_fixup(struct btree_keys *b,
* k might have been split since we inserted/found the
* key we're replacing
*/
- unsigned i;
+ unsigned int i;
uint64_t offset = KEY_START(k) -
KEY_START(replace_key);
@@ -497,11 +499,12 @@ bad:
static bool bch_extent_invalid(struct btree_keys *bk, const struct bkey *k)
{
struct btree *b = container_of(bk, struct btree, keys);
+
return __bch_extent_invalid(b->c, k);
}
static bool bch_extent_bad_expensive(struct btree *b, const struct bkey *k,
- unsigned ptr)
+ unsigned int ptr)
{
struct bucket *g = PTR_BUCKET(b->c, k, ptr);
char buf[80];
@@ -533,7 +536,8 @@ err:
static bool bch_extent_bad(struct btree_keys *bk, const struct bkey *k)
{
struct btree *b = container_of(bk, struct btree, keys);
- unsigned i, stale;
+ unsigned int i, stale;
+ char buf[80];
if (!KEY_PTRS(k) ||
bch_extent_invalid(bk, k))
@@ -543,19 +547,19 @@ static bool bch_extent_bad(struct btree_keys *bk, const struct bkey *k)
if (!ptr_available(b->c, k, i))
return true;
- if (!expensive_debug_checks(b->c) && KEY_DIRTY(k))
- return false;
-
for (i = 0; i < KEY_PTRS(k); i++) {
stale = ptr_stale(b->c, k, i);
- btree_bug_on(stale > 96, b,
+ if (stale && KEY_DIRTY(k)) {
+ bch_extent_to_text(buf, sizeof(buf), k);
+ pr_info("stale dirty pointer, stale %u, key: %s",
+ stale, buf);
+ }
+
+ btree_bug_on(stale > BUCKET_GC_GEN_MAX, b,
"key too stale: %i, need_gc %u",
stale, b->c->need_gc);
- btree_bug_on(stale && KEY_DIRTY(k) && KEY_SIZE(k),
- b, "stale dirty pointer");
-
if (stale)
return true;
@@ -573,10 +577,12 @@ static uint64_t merge_chksums(struct bkey *l, struct bkey *r)
~((uint64_t)1 << 63);
}
-static bool bch_extent_merge(struct btree_keys *bk, struct bkey *l, struct bkey *r)
+static bool bch_extent_merge(struct btree_keys *bk,
+ struct bkey *l,
+ struct bkey *r)
{
struct btree *b = container_of(bk, struct btree, keys);
- unsigned i;
+ unsigned int i;
if (key_merging_disabled(b->c))
return false;
diff --git a/drivers/md/bcache/extents.h b/drivers/md/bcache/extents.h
index e2ed54054e7a..c44e838b33d0 100644
--- a/drivers/md/bcache/extents.h
+++ b/drivers/md/bcache/extents.h
@@ -7,8 +7,8 @@ extern const struct btree_keys_ops bch_extent_keys_ops;
struct bkey;
struct cache_set;
-void bch_extent_to_text(char *, size_t, const struct bkey *);
-bool __bch_btree_ptr_invalid(struct cache_set *, const struct bkey *);
-bool __bch_extent_invalid(struct cache_set *, const struct bkey *);
+void bch_extent_to_text(char *buf, size_t size, const struct bkey *k);
+bool __bch_btree_ptr_invalid(struct cache_set *c, const struct bkey *k);
+bool __bch_extent_invalid(struct cache_set *c, const struct bkey *k);
#endif /* _BCACHE_EXTENTS_H */
diff --git a/drivers/md/bcache/io.c b/drivers/md/bcache/io.c
index 1356d3185750..47b7e54180ed 100644
--- a/drivers/md/bcache/io.c
+++ b/drivers/md/bcache/io.c
@@ -16,6 +16,7 @@
void bch_bbio_free(struct bio *bio, struct cache_set *c)
{
struct bbio *b = container_of(bio, struct bbio, bio);
+
mempool_free(b, c->bio_meta);
}
@@ -41,9 +42,10 @@ void __bch_submit_bbio(struct bio *bio, struct cache_set *c)
}
void bch_submit_bbio(struct bio *bio, struct cache_set *c,
- struct bkey *k, unsigned ptr)
+ struct bkey *k, unsigned int ptr)
{
struct bbio *b = container_of(bio, struct bbio, bio);
+
bch_bkey_copy_single_ptr(&b->key, k, ptr);
__bch_submit_bbio(bio, c);
}
@@ -51,7 +53,7 @@ void bch_submit_bbio(struct bio *bio, struct cache_set *c,
/* IO errors */
void bch_count_backing_io_errors(struct cached_dev *dc, struct bio *bio)
{
- unsigned errors;
+ unsigned int errors;
WARN_ONCE(!dc, "NULL pointer of struct cached_dev");
@@ -74,16 +76,16 @@ void bch_count_io_errors(struct cache *ca,
*/
if (ca->set->error_decay) {
- unsigned count = atomic_inc_return(&ca->io_count);
+ unsigned int count = atomic_inc_return(&ca->io_count);
while (count > ca->set->error_decay) {
- unsigned errors;
- unsigned old = count;
- unsigned new = count - ca->set->error_decay;
+ unsigned int errors;
+ unsigned int old = count;
+ unsigned int new = count - ca->set->error_decay;
/*
* First we subtract refresh from count; each time we
- * succesfully do so, we rescale the errors once:
+ * successfully do so, we rescale the errors once:
*/
count = atomic_cmpxchg(&ca->io_count, old, new);
@@ -103,7 +105,7 @@ void bch_count_io_errors(struct cache *ca,
}
if (error) {
- unsigned errors = atomic_add_return(1 << IO_ERROR_SHIFT,
+ unsigned int errors = atomic_add_return(1 << IO_ERROR_SHIFT,
&ca->io_errors);
errors >>= IO_ERROR_SHIFT;
@@ -125,18 +127,18 @@ void bch_bbio_count_io_errors(struct cache_set *c, struct bio *bio,
struct cache *ca = PTR_CACHE(c, &b->key, 0);
int is_read = (bio_data_dir(bio) == READ ? 1 : 0);
- unsigned threshold = op_is_write(bio_op(bio))
+ unsigned int threshold = op_is_write(bio_op(bio))
? c->congested_write_threshold_us
: c->congested_read_threshold_us;
if (threshold) {
- unsigned t = local_clock_us();
-
+ unsigned int t = local_clock_us();
int us = t - b->submit_time_us;
int congested = atomic_read(&c->congested);
if (us > (int) threshold) {
int ms = us / 1024;
+
c->congested_last_us = t;
ms = min(ms, CONGESTED_MAX + congested);
diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c
index 95c64d281e67..5cf9df00eefc 100644
--- a/drivers/md/bcache/journal.c
+++ b/drivers/md/bcache/journal.c
@@ -27,11 +27,12 @@
static void journal_read_endio(struct bio *bio)
{
struct closure *cl = bio->bi_private;
+
closure_put(cl);
}
static int journal_read_bucket(struct cache *ca, struct list_head *list,
- unsigned bucket_index)
+ unsigned int bucket_index)
{
struct journal_device *ja = &ca->journal;
struct bio *bio = &ja->bio;
@@ -39,7 +40,7 @@ static int journal_read_bucket(struct cache *ca, struct list_head *list,
struct journal_replay *i;
struct jset *j, *data = ca->set->journal.w[0].data;
struct closure cl;
- unsigned len, left, offset = 0;
+ unsigned int len, left, offset = 0;
int ret = 0;
sector_t bucket = bucket_to_sector(ca->set, ca->sb.d[bucket_index]);
@@ -49,7 +50,7 @@ static int journal_read_bucket(struct cache *ca, struct list_head *list,
while (offset < ca->sb.bucket_size) {
reread: left = ca->sb.bucket_size - offset;
- len = min_t(unsigned, left, PAGE_SECTORS << JSET_BITS);
+ len = min_t(unsigned int, left, PAGE_SECTORS << JSET_BITS);
bio_reset(bio);
bio->bi_iter.bi_sector = bucket + offset;
@@ -153,12 +154,12 @@ int bch_journal_read(struct cache_set *c, struct list_head *list)
})
struct cache *ca;
- unsigned iter;
+ unsigned int iter;
for_each_cache(ca, c, iter) {
struct journal_device *ja = &ca->journal;
DECLARE_BITMAP(bitmap, SB_JOURNAL_BUCKETS);
- unsigned i, l, r, m;
+ unsigned int i, l, r, m;
uint64_t seq;
bitmap_zero(bitmap, SB_JOURNAL_BUCKETS);
@@ -191,7 +192,8 @@ int bch_journal_read(struct cache_set *c, struct list_head *list)
for (l = find_first_zero_bit(bitmap, ca->sb.njournal_buckets);
l < ca->sb.njournal_buckets;
- l = find_next_zero_bit(bitmap, ca->sb.njournal_buckets, l + 1))
+ l = find_next_zero_bit(bitmap, ca->sb.njournal_buckets,
+ l + 1))
if (read_bucket(l))
goto bsearch;
@@ -303,7 +305,7 @@ void bch_journal_mark(struct cache_set *c, struct list_head *list)
k < bset_bkey_last(&i->j);
k = bkey_next(k))
if (!__bch_extent_invalid(c, k)) {
- unsigned j;
+ unsigned int j;
for (j = 0; j < KEY_PTRS(k); j++)
if (ptr_available(c, k, j))
@@ -482,7 +484,7 @@ static void do_journal_discard(struct cache *ca)
closure_get(&ca->set->cl);
INIT_WORK(&ja->discard_work, journal_discard_work);
- schedule_work(&ja->discard_work);
+ queue_work(bch_journal_wq, &ja->discard_work);
}
}
@@ -491,7 +493,7 @@ static void journal_reclaim(struct cache_set *c)
struct bkey *k = &c->journal.key;
struct cache *ca;
uint64_t last_seq;
- unsigned iter, n = 0;
+ unsigned int iter, n = 0;
atomic_t p __maybe_unused;
atomic_long_inc(&c->reclaim);
@@ -525,7 +527,7 @@ static void journal_reclaim(struct cache_set *c)
for_each_cache(ca, c, iter) {
struct journal_device *ja = &ca->journal;
- unsigned next = (ja->cur_idx + 1) % ca->sb.njournal_buckets;
+ unsigned int next = (ja->cur_idx + 1) % ca->sb.njournal_buckets;
/* No space available on this device */
if (next == ja->discard_idx)
@@ -579,7 +581,7 @@ static void journal_write_endio(struct bio *bio)
closure_put(&w->c->journal.io);
}
-static void journal_write(struct closure *);
+static void journal_write(struct closure *cl);
static void journal_write_done(struct closure *cl)
{
@@ -589,7 +591,7 @@ static void journal_write_done(struct closure *cl)
: &j->w[0];
__closure_wake_up(&w->wait);
- continue_at_nobarrier(cl, journal_write, system_wq);
+ continue_at_nobarrier(cl, journal_write, bch_journal_wq);
}
static void journal_write_unlock(struct closure *cl)
@@ -608,11 +610,12 @@ static void journal_write_unlocked(struct closure *cl)
struct cache *ca;
struct journal_write *w = c->journal.cur;
struct bkey *k = &c->journal.key;
- unsigned i, sectors = set_blocks(w->data, block_bytes(c)) *
+ unsigned int i, sectors = set_blocks(w->data, block_bytes(c)) *
c->sb.block_size;
struct bio *bio;
struct bio_list list;
+
bio_list_init(&list);
if (!w->need_write) {
@@ -623,7 +626,7 @@ static void journal_write_unlocked(struct closure *cl)
spin_unlock(&c->journal.lock);
btree_flush_write(c);
- continue_at(cl, journal_write, system_wq);
+ continue_at(cl, journal_write, bch_journal_wq);
return;
}
@@ -659,7 +662,7 @@ static void journal_write_unlocked(struct closure *cl)
REQ_SYNC|REQ_META|REQ_PREFLUSH|REQ_FUA);
bch_bio_map(bio, w->data);
- trace_bcache_journal_write(bio);
+ trace_bcache_journal_write(bio, w->data->keys);
bio_list_add(&list, bio);
SET_PTR_OFFSET(k, i, PTR_OFFSET(k, i) + sectors);
@@ -704,7 +707,7 @@ static void journal_try_write(struct cache_set *c)
}
static struct journal_write *journal_wait_for_write(struct cache_set *c,
- unsigned nkeys)
+ unsigned int nkeys)
__acquires(&c->journal.lock)
{
size_t sectors;
diff --git a/drivers/md/bcache/journal.h b/drivers/md/bcache/journal.h
index e3c39457afbb..85f0d0fe904d 100644
--- a/drivers/md/bcache/journal.h
+++ b/drivers/md/bcache/journal.h
@@ -109,7 +109,7 @@ struct journal {
struct delayed_work work;
/* Number of blocks free in the bucket(s) we're currently writing to */
- unsigned blocks_free;
+ unsigned int blocks_free;
uint64_t seq;
DECLARE_FIFO(atomic_t, pin);
@@ -130,13 +130,13 @@ struct journal_device {
uint64_t seq[SB_JOURNAL_BUCKETS];
/* Journal bucket we're currently writing to */
- unsigned cur_idx;
+ unsigned int cur_idx;
/* Last journal bucket that still contains an open journal entry */
- unsigned last_idx;
+ unsigned int last_idx;
/* Next journal bucket to be discarded */
- unsigned discard_idx;
+ unsigned int discard_idx;
#define DISCARD_READY 0
#define DISCARD_IN_FLIGHT 1
@@ -166,14 +166,16 @@ struct cache_set;
struct btree_op;
struct keylist;
-atomic_t *bch_journal(struct cache_set *, struct keylist *, struct closure *);
-void bch_journal_next(struct journal *);
-void bch_journal_mark(struct cache_set *, struct list_head *);
-void bch_journal_meta(struct cache_set *, struct closure *);
-int bch_journal_read(struct cache_set *, struct list_head *);
-int bch_journal_replay(struct cache_set *, struct list_head *);
-
-void bch_journal_free(struct cache_set *);
-int bch_journal_alloc(struct cache_set *);
+atomic_t *bch_journal(struct cache_set *c,
+ struct keylist *keys,
+ struct closure *parent);
+void bch_journal_next(struct journal *j);
+void bch_journal_mark(struct cache_set *c, struct list_head *list);
+void bch_journal_meta(struct cache_set *c, struct closure *cl);
+int bch_journal_read(struct cache_set *c, struct list_head *list);
+int bch_journal_replay(struct cache_set *c, struct list_head *list);
+
+void bch_journal_free(struct cache_set *c);
+int bch_journal_alloc(struct cache_set *c);
#endif /* _BCACHE_JOURNAL_H */
diff --git a/drivers/md/bcache/movinggc.c b/drivers/md/bcache/movinggc.c
index f633b30c962e..ad161a8d17e9 100644
--- a/drivers/md/bcache/movinggc.c
+++ b/drivers/md/bcache/movinggc.c
@@ -22,7 +22,7 @@ static bool moving_pred(struct keybuf *buf, struct bkey *k)
{
struct cache_set *c = container_of(buf, struct cache_set,
moving_gc_keys);
- unsigned i;
+ unsigned int i;
for (i = 0; i < KEY_PTRS(k); i++)
if (ptr_available(c, k, i) &&
@@ -37,6 +37,7 @@ static bool moving_pred(struct keybuf *buf, struct bkey *k)
static void moving_io_destructor(struct closure *cl)
{
struct moving_io *io = container_of(cl, struct moving_io, cl);
+
kfree(io);
}
@@ -185,9 +186,10 @@ static bool bucket_cmp(struct bucket *l, struct bucket *r)
return GC_SECTORS_USED(l) < GC_SECTORS_USED(r);
}
-static unsigned bucket_heap_top(struct cache *ca)
+static unsigned int bucket_heap_top(struct cache *ca)
{
struct bucket *b;
+
return (b = heap_peek(&ca->heap)) ? GC_SECTORS_USED(b) : 0;
}
@@ -195,7 +197,7 @@ void bch_moving_gc(struct cache_set *c)
{
struct cache *ca;
struct bucket *b;
- unsigned i;
+ unsigned int i;
if (!c->copy_gc_enabled)
return;
@@ -203,9 +205,9 @@ void bch_moving_gc(struct cache_set *c)
mutex_lock(&c->bucket_lock);
for_each_cache(ca, c, i) {
- unsigned sectors_to_move = 0;
- unsigned reserve_sectors = ca->sb.bucket_size *
- fifo_used(&ca->free[RESERVE_MOVINGGC]);
+ unsigned int sectors_to_move = 0;
+ unsigned int reserve_sectors = ca->sb.bucket_size *
+ fifo_used(&ca->free[RESERVE_MOVINGGC]);
ca->heap.used = 0;
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index 26500c81b060..528205b1b7c9 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -24,9 +24,9 @@
struct kmem_cache *bch_search_cache;
-static void bch_data_insert_start(struct closure *);
+static void bch_data_insert_start(struct closure *cl);
-static unsigned cache_mode(struct cached_dev *dc)
+static unsigned int cache_mode(struct cached_dev *dc)
{
return BDEV_CACHE_MODE(&dc->sb);
}
@@ -44,6 +44,7 @@ static void bio_csum(struct bio *bio, struct bkey *k)
bio_for_each_segment(bv, bio, iter) {
void *d = kmap(bv.bv_page) + bv.bv_offset;
+
csum = bch_crc64_update(csum, d, bv.bv_len);
kunmap(bv.bv_page);
}
@@ -97,7 +98,7 @@ static void bch_data_insert_keys(struct closure *cl)
closure_return(cl);
}
-static int bch_keylist_realloc(struct keylist *l, unsigned u64s,
+static int bch_keylist_realloc(struct keylist *l, unsigned int u64s,
struct cache_set *c)
{
size_t oldsize = bch_keylist_nkeys(l);
@@ -106,7 +107,7 @@ static int bch_keylist_realloc(struct keylist *l, unsigned u64s,
/*
* The journalling code doesn't handle the case where the keys to insert
* is bigger than an empty write: If we just return -ENOMEM here,
- * bio_insert() and bio_invalidate() will insert the keys created so far
+ * bch_data_insert_keys() will insert the keys created so far
* and finish the rest when the keylist is empty.
*/
if (newsize * sizeof(uint64_t) > block_bytes(c) - sizeof(struct jset))
@@ -124,7 +125,7 @@ static void bch_data_invalidate(struct closure *cl)
bio_sectors(bio), (uint64_t) bio->bi_iter.bi_sector);
while (bio_sectors(bio)) {
- unsigned sectors = min(bio_sectors(bio),
+ unsigned int sectors = min(bio_sectors(bio),
1U << (KEY_SIZE_BITS - 1));
if (bch_keylist_realloc(&op->insert_keys, 2, op->c))
@@ -134,7 +135,9 @@ static void bch_data_invalidate(struct closure *cl)
bio->bi_iter.bi_size -= sectors << 9;
bch_keylist_add(&op->insert_keys,
- &KEY(op->inode, bio->bi_iter.bi_sector, sectors));
+ &KEY(op->inode,
+ bio->bi_iter.bi_sector,
+ sectors));
}
op->insert_data_done = true;
@@ -150,7 +153,7 @@ static void bch_data_insert_error(struct closure *cl)
/*
* Our data write just errored, which means we've got a bunch of keys to
- * insert that point to data that wasn't succesfully written.
+ * insert that point to data that wasn't successfully written.
*
* We don't have to insert those keys but we still have to invalidate
* that region of the cache - so, if we just strip off all the pointers
@@ -210,7 +213,7 @@ static void bch_data_insert_start(struct closure *cl)
bio->bi_opf &= ~(REQ_PREFLUSH|REQ_FUA);
do {
- unsigned i;
+ unsigned int i;
struct bkey *k;
struct bio_set *split = op->c->bio_split;
@@ -307,11 +310,11 @@ err:
* data is written it calls bch_journal, and after the keys have been added to
* the next journal write they're inserted into the btree.
*
- * It inserts the data in s->cache_bio; bi_sector is used for the key offset,
+ * It inserts the data in op->bio; bi_sector is used for the key offset,
* and op->inode is used for the key inode.
*
- * If s->bypass is true, instead of inserting the data it invalidates the
- * region of the cache represented by s->cache_bio and op->inode.
+ * If op->bypass is true, instead of inserting the data it invalidates the
+ * region of the cache represented by op->bio and op->inode.
*/
void bch_data_insert(struct closure *cl)
{
@@ -327,7 +330,7 @@ void bch_data_insert(struct closure *cl)
/* Congested? */
-unsigned bch_get_congested(struct cache_set *c)
+unsigned int bch_get_congested(struct cache_set *c)
{
int i;
long rand;
@@ -371,8 +374,8 @@ static struct hlist_head *iohash(struct cached_dev *dc, uint64_t k)
static bool check_should_bypass(struct cached_dev *dc, struct bio *bio)
{
struct cache_set *c = dc->disk.c;
- unsigned mode = cache_mode(dc);
- unsigned sectors, congested = bch_get_congested(c);
+ unsigned int mode = cache_mode(dc);
+ unsigned int sectors, congested = bch_get_congested(c);
struct task_struct *task = current;
struct io *i;
@@ -388,10 +391,11 @@ static bool check_should_bypass(struct cached_dev *dc, struct bio *bio)
/*
* Flag for bypass if the IO is for read-ahead or background,
- * unless the read-ahead request is for metadata (eg, for gfs2).
+ * unless the read-ahead request is for metadata
+ * (eg, for gfs2 or xfs).
*/
if (bio->bi_opf & (REQ_RAHEAD|REQ_BACKGROUND) &&
- !(bio->bi_opf & REQ_META))
+ !(bio->bi_opf & (REQ_META|REQ_PRIO)))
goto skip;
if (bio->bi_iter.bi_sector & (c->sb.block_size - 1) ||
@@ -468,11 +472,11 @@ struct search {
struct bio *cache_miss;
struct bcache_device *d;
- unsigned insert_bio_sectors;
- unsigned recoverable:1;
- unsigned write:1;
- unsigned read_dirty_data:1;
- unsigned cache_missed:1;
+ unsigned int insert_bio_sectors;
+ unsigned int recoverable:1;
+ unsigned int write:1;
+ unsigned int read_dirty_data:1;
+ unsigned int cache_missed:1;
unsigned long start_time;
@@ -513,20 +517,20 @@ static int cache_lookup_fn(struct btree_op *op, struct btree *b, struct bkey *k)
struct search *s = container_of(op, struct search, op);
struct bio *n, *bio = &s->bio.bio;
struct bkey *bio_key;
- unsigned ptr;
+ unsigned int ptr;
if (bkey_cmp(k, &KEY(s->iop.inode, bio->bi_iter.bi_sector, 0)) <= 0)
return MAP_CONTINUE;
if (KEY_INODE(k) != s->iop.inode ||
KEY_START(k) > bio->bi_iter.bi_sector) {
- unsigned bio_sectors = bio_sectors(bio);
- unsigned sectors = KEY_INODE(k) == s->iop.inode
+ unsigned int bio_sectors = bio_sectors(bio);
+ unsigned int sectors = KEY_INODE(k) == s->iop.inode
? min_t(uint64_t, INT_MAX,
KEY_START(k) - bio->bi_iter.bi_sector)
: INT_MAX;
-
int ret = s->d->cache_miss(b, s, bio, sectors);
+
if (ret != MAP_CONTINUE)
return ret;
@@ -622,6 +626,7 @@ static void request_endio(struct bio *bio)
if (bio->bi_status) {
struct search *s = container_of(cl, struct search, cl);
+
s->iop.status = bio->bi_status;
/* Only cache read errors are recoverable */
s->recoverable = false;
@@ -813,7 +818,8 @@ static void cached_dev_read_done(struct closure *cl)
if (s->iop.bio) {
bio_reset(s->iop.bio);
- s->iop.bio->bi_iter.bi_sector = s->cache_miss->bi_iter.bi_sector;
+ s->iop.bio->bi_iter.bi_sector =
+ s->cache_miss->bi_iter.bi_sector;
bio_copy_dev(s->iop.bio, s->cache_miss);
s->iop.bio->bi_iter.bi_size = s->insert_bio_sectors << 9;
bch_bio_map(s->iop.bio, NULL);
@@ -856,10 +862,10 @@ static void cached_dev_read_done_bh(struct closure *cl)
}
static int cached_dev_cache_miss(struct btree *b, struct search *s,
- struct bio *bio, unsigned sectors)
+ struct bio *bio, unsigned int sectors)
{
int ret = MAP_CONTINUE;
- unsigned reada = 0;
+ unsigned int reada = 0;
struct cached_dev *dc = container_of(s->d, struct cached_dev, disk);
struct bio *miss, *cache_bio;
@@ -872,7 +878,7 @@ static int cached_dev_cache_miss(struct btree *b, struct search *s,
}
if (!(bio->bi_opf & REQ_RAHEAD) &&
- !(bio->bi_opf & REQ_META) &&
+ !(bio->bi_opf & (REQ_META|REQ_PRIO)) &&
s->iop.c->gc_stats.in_use < CUTOFF_CACHE_READA)
reada = min_t(sector_t, dc->readahead >> 9,
get_capacity(bio->bi_disk) - bio_end_sector(bio));
@@ -1210,6 +1216,10 @@ static int cached_dev_ioctl(struct bcache_device *d, fmode_t mode,
unsigned int cmd, unsigned long arg)
{
struct cached_dev *dc = container_of(d, struct cached_dev, disk);
+
+ if (dc->io_disable)
+ return -EIO;
+
return __blkdev_driver_ioctl(dc->bdev, mode, cmd, arg);
}
@@ -1224,7 +1234,7 @@ static int cached_dev_congested(void *data, int bits)
return 1;
if (cached_dev_get(dc)) {
- unsigned i;
+ unsigned int i;
struct cache *ca;
for_each_cache(ca, d->c, i) {
@@ -1251,9 +1261,9 @@ void bch_cached_dev_request_init(struct cached_dev *dc)
/* Flash backed devices */
static int flash_dev_cache_miss(struct btree *b, struct search *s,
- struct bio *bio, unsigned sectors)
+ struct bio *bio, unsigned int sectors)
{
- unsigned bytes = min(sectors, bio_sectors(bio)) << 9;
+ unsigned int bytes = min(sectors, bio_sectors(bio)) << 9;
swap(bio->bi_iter.bi_size, bytes);
zero_fill_bio(bio);
@@ -1337,7 +1347,7 @@ static int flash_dev_congested(void *data, int bits)
struct bcache_device *d = data;
struct request_queue *q;
struct cache *ca;
- unsigned i;
+ unsigned int i;
int ret = 0;
for_each_cache(ca, d->c, i) {
@@ -1360,8 +1370,7 @@ void bch_flash_dev_request_init(struct bcache_device *d)
void bch_request_exit(void)
{
- if (bch_search_cache)
- kmem_cache_destroy(bch_search_cache);
+ kmem_cache_destroy(bch_search_cache);
}
int __init bch_request_init(void)
diff --git a/drivers/md/bcache/request.h b/drivers/md/bcache/request.h
index 7689176951ce..4177c0437286 100644
--- a/drivers/md/bcache/request.h
+++ b/drivers/md/bcache/request.h
@@ -7,7 +7,7 @@ struct data_insert_op {
struct bio *bio;
struct workqueue_struct *wq;
- unsigned inode;
+ unsigned int inode;
uint16_t write_point;
uint16_t write_prio;
blk_status_t status;
@@ -16,15 +16,15 @@ struct data_insert_op {
uint16_t flags;
struct {
- unsigned bypass:1;
- unsigned writeback:1;
- unsigned flush_journal:1;
- unsigned csum:1;
+ unsigned int bypass:1;
+ unsigned int writeback:1;
+ unsigned int flush_journal:1;
+ unsigned int csum:1;
- unsigned replace:1;
- unsigned replace_collision:1;
+ unsigned int replace:1;
+ unsigned int replace_collision:1;
- unsigned insert_data_done:1;
+ unsigned int insert_data_done:1;
};
};
@@ -32,12 +32,12 @@ struct data_insert_op {
BKEY_PADDED(replace_key);
};
-unsigned bch_get_congested(struct cache_set *);
+unsigned int bch_get_congested(struct cache_set *c);
void bch_data_insert(struct closure *cl);
void bch_cached_dev_request_init(struct cached_dev *dc);
void bch_flash_dev_request_init(struct bcache_device *d);
-extern struct kmem_cache *bch_search_cache, *bch_passthrough_cache;
+extern struct kmem_cache *bch_search_cache;
#endif /* _BCACHE_REQUEST_H_ */
diff --git a/drivers/md/bcache/stats.c b/drivers/md/bcache/stats.c
index 0ca072c20d0d..11c4d0e4edea 100644
--- a/drivers/md/bcache/stats.c
+++ b/drivers/md/bcache/stats.c
@@ -32,11 +32,11 @@
* stored left shifted by 16, and scaled back in the sysfs show() function.
*/
-static const unsigned DAY_RESCALE = 288;
-static const unsigned HOUR_RESCALE = 12;
-static const unsigned FIVE_MINUTE_RESCALE = 1;
-static const unsigned accounting_delay = (HZ * 300) / 22;
-static const unsigned accounting_weight = 32;
+static const unsigned int DAY_RESCALE = 288;
+static const unsigned int HOUR_RESCALE = 12;
+static const unsigned int FIVE_MINUTE_RESCALE = 1;
+static const unsigned int accounting_delay = (HZ * 300) / 22;
+static const unsigned int accounting_weight = 32;
/* sysfs reading/writing */
@@ -110,7 +110,7 @@ void bch_cache_accounting_clear(struct cache_accounting *acc)
{
memset(&acc->total.cache_hits,
0,
- sizeof(unsigned long) * 7);
+ sizeof(struct cache_stats));
}
void bch_cache_accounting_destroy(struct cache_accounting *acc)
@@ -151,7 +151,7 @@ static void scale_accounting(unsigned long data)
struct cache_accounting *acc = (struct cache_accounting *) data;
#define move_stat(name) do { \
- unsigned t = atomic_xchg(&acc->collector.name, 0); \
+ unsigned int t = atomic_xchg(&acc->collector.name, 0); \
t <<= 16; \
acc->five_minute.name += t; \
acc->hour.name += t; \
@@ -199,6 +199,7 @@ void bch_mark_cache_accounting(struct cache_set *c, struct bcache_device *d,
bool hit, bool bypass)
{
struct cached_dev *dc = container_of(d, struct cached_dev, disk);
+
mark_cache_stats(&dc->accounting.collector, hit, bypass);
mark_cache_stats(&c->accounting.collector, hit, bypass);
}
@@ -206,6 +207,7 @@ void bch_mark_cache_accounting(struct cache_set *c, struct bcache_device *d,
void bch_mark_cache_readahead(struct cache_set *c, struct bcache_device *d)
{
struct cached_dev *dc = container_of(d, struct cached_dev, disk);
+
atomic_inc(&dc->accounting.collector.cache_readaheads);
atomic_inc(&c->accounting.collector.cache_readaheads);
}
@@ -213,6 +215,7 @@ void bch_mark_cache_readahead(struct cache_set *c, struct bcache_device *d)
void bch_mark_cache_miss_collision(struct cache_set *c, struct bcache_device *d)
{
struct cached_dev *dc = container_of(d, struct cached_dev, disk);
+
atomic_inc(&dc->accounting.collector.cache_miss_collisions);
atomic_inc(&c->accounting.collector.cache_miss_collisions);
}
diff --git a/drivers/md/bcache/stats.h b/drivers/md/bcache/stats.h
index adbff141c887..a42c0ae3dbc2 100644
--- a/drivers/md/bcache/stats.h
+++ b/drivers/md/bcache/stats.h
@@ -22,7 +22,7 @@ struct cache_stats {
unsigned long cache_miss_collisions;
unsigned long sectors_bypassed;
- unsigned rescale;
+ unsigned int rescale;
};
struct cache_accounting {
@@ -52,10 +52,13 @@ void bch_cache_accounting_clear(struct cache_accounting *acc);
void bch_cache_accounting_destroy(struct cache_accounting *acc);
-void bch_mark_cache_accounting(struct cache_set *, struct bcache_device *,
- bool, bool);
-void bch_mark_cache_readahead(struct cache_set *, struct bcache_device *);
-void bch_mark_cache_miss_collision(struct cache_set *, struct bcache_device *);
-void bch_mark_sectors_bypassed(struct cache_set *, struct cached_dev *, int);
+void bch_mark_cache_accounting(struct cache_set *c, struct bcache_device *d,
+ bool hit, bool bypass);
+void bch_mark_cache_readahead(struct cache_set *c, struct bcache_device *d);
+void bch_mark_cache_miss_collision(struct cache_set *c,
+ struct bcache_device *d);
+void bch_mark_sectors_bypassed(struct cache_set *c,
+ struct cached_dev *dc,
+ int sectors);
#endif /* _BCACHE_STATS_H_ */
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index a9fb9654d198..a363ad5d8348 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* bcache setup/teardown code, and some metadata io - read a superblock and
* figure out what to do with it.
@@ -23,9 +24,10 @@
#include <linux/random.h>
#include <linux/reboot.h>
#include <linux/sysfs.h>
+#include <linux/overflow.h>
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Kent Overstreet <kent.overstreet@gmail.com>");
+unsigned int bch_cutoff_writeback;
+unsigned int bch_cutoff_writeback_sync;
static const char bcache_magic[] = {
0xc6, 0x85, 0x73, 0xf6, 0x4e, 0x1a, 0x45, 0xca,
@@ -37,24 +39,6 @@ static const char invalid_uuid[] = {
0xc8, 0x50, 0xfc, 0x5e, 0xcb, 0x16, 0xcd, 0x99
};
-/* Default is -1; we skip past it for struct cached_dev's cache mode */
-const char * const bch_cache_modes[] = {
- "default",
- "writethrough",
- "writeback",
- "writearound",
- "none",
- NULL
-};
-
-/* Default is -1; we skip past it for stop_when_cache_set_failed */
-const char * const bch_stop_on_failure_modes[] = {
- "default",
- "auto",
- "always",
- NULL
-};
-
static struct kobject *bcache_kobj;
struct mutex bch_register_lock;
LIST_HEAD(bch_cache_sets);
@@ -64,6 +48,7 @@ static int bcache_major;
static DEFINE_IDA(bcache_device_idx);
static wait_queue_head_t unregister_wait;
struct workqueue_struct *bcache_wq;
+struct workqueue_struct *bch_journal_wq;
#define BTREE_MAX_PAGES (256 * 1024 / PAGE_SIZE)
/* limitation of partitions number on single bcache device */
@@ -79,7 +64,7 @@ static const char *read_super(struct cache_sb *sb, struct block_device *bdev,
const char *err;
struct cache_sb *s;
struct buffer_head *bh = __bread(bdev, 1, SB_SIZE);
- unsigned i;
+ unsigned int i;
if (!bh)
return "IO error";
@@ -167,7 +152,8 @@ static const char *read_super(struct cache_sb *sb, struct block_device *bdev,
goto err;
err = "Invalid superblock: device too small";
- if (get_capacity(bdev->bd_disk) < sb->bucket_size * sb->nbuckets)
+ if (get_capacity(bdev->bd_disk) <
+ sb->bucket_size * sb->nbuckets)
goto err;
err = "Bad UUID";
@@ -199,7 +185,7 @@ static const char *read_super(struct cache_sb *sb, struct block_device *bdev,
goto err;
}
- sb->last_mount = get_seconds();
+ sb->last_mount = (u32)ktime_get_real_seconds();
err = NULL;
get_page(bh->b_page);
@@ -220,7 +206,7 @@ static void write_bdev_super_endio(struct bio *bio)
static void __write_super(struct cache_sb *sb, struct bio *bio)
{
struct cache_sb *out = page_address(bio->bi_io_vec[0].bv_page);
- unsigned i;
+ unsigned int i;
bio->bi_iter.bi_sector = SB_SECTOR;
bio->bi_iter.bi_size = SB_SIZE;
@@ -300,7 +286,7 @@ void bcache_write_super(struct cache_set *c)
{
struct closure *cl = &c->sb_write;
struct cache *ca;
- unsigned i;
+ unsigned int i;
down(&c->sb_write_mutex);
closure_init(cl, &c->cl);
@@ -352,7 +338,7 @@ static void uuid_io(struct cache_set *c, int op, unsigned long op_flags,
{
struct closure *cl = &c->uuid_write;
struct uuid_entry *u;
- unsigned i;
+ unsigned int i;
char buf[80];
BUG_ON(!parent);
@@ -433,8 +419,9 @@ static int __uuid_write(struct cache_set *c)
{
BKEY_PADDED(key) k;
struct closure cl;
- closure_init_stack(&cl);
+ struct cache *ca;
+ closure_init_stack(&cl);
lockdep_assert_held(&bch_register_lock);
if (bch_bucket_alloc_set(c, RESERVE_BTREE, &k.key, 1, true))
@@ -444,6 +431,10 @@ static int __uuid_write(struct cache_set *c)
uuid_io(c, REQ_OP_WRITE, 0, &k.key, &cl);
closure_sync(&cl);
+ /* Only one bucket used for uuid write */
+ ca = PTR_CACHE(c, &k.key, 0);
+ atomic_long_add(ca->sb.bucket_size, &ca->meta_sectors_written);
+
bkey_copy(&c->uuid_bucket, &k.key);
bkey_put(c, &k.key);
return 0;
@@ -474,6 +465,7 @@ static struct uuid_entry *uuid_find(struct cache_set *c, const char *uuid)
static struct uuid_entry *uuid_find_empty(struct cache_set *c)
{
static const char zero_uuid[16] = "\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0";
+
return uuid_find(c, zero_uuid);
}
@@ -481,8 +473,8 @@ static struct uuid_entry *uuid_find_empty(struct cache_set *c)
* Bucket priorities/gens:
*
* For each bucket, we store on disk its
- * 8 bit gen
- * 16 bit priority
+ * 8 bit gen
+ * 16 bit priority
*
* See alloc.c for an explanation of the gen. The priority is used to implement
* lru (and in the future other) cache replacement policies; for most purposes
@@ -605,7 +597,7 @@ static void prio_read(struct cache *ca, uint64_t bucket)
struct prio_set *p = ca->disk_buckets;
struct bucket_disk *d = p->data + prios_per_bucket(ca), *end = d;
struct bucket *b;
- unsigned bucket_nr = 0;
+ unsigned int bucket_nr = 0;
for (b = ca->buckets;
b < ca->buckets + ca->sb.nbuckets;
@@ -617,7 +609,8 @@ static void prio_read(struct cache *ca, uint64_t bucket)
prio_io(ca, bucket, REQ_OP_READ, 0);
- if (p->csum != bch_crc64(&p->magic, bucket_bytes(ca) - 8))
+ if (p->csum !=
+ bch_crc64(&p->magic, bucket_bytes(ca) - 8))
pr_warn("bad csum reading priorities");
if (p->magic != pset_magic(&ca->sb))
@@ -637,6 +630,7 @@ static void prio_read(struct cache *ca, uint64_t bucket)
static int open_dev(struct block_device *b, fmode_t mode)
{
struct bcache_device *d = b->bd_disk->private_data;
+
if (test_bit(BCACHE_DEV_CLOSING, &d->flags))
return -ENXIO;
@@ -647,6 +641,7 @@ static int open_dev(struct block_device *b, fmode_t mode)
static void release_dev(struct gendisk *b, fmode_t mode)
{
struct bcache_device *d = b->private_data;
+
closure_put(&d->cl);
}
@@ -654,6 +649,7 @@ static int ioctl_dev(struct block_device *b, fmode_t mode,
unsigned int cmd, unsigned long arg)
{
struct bcache_device *d = b->bd_disk->private_data;
+
return d->ioctl(d, mode, cmd, arg);
}
@@ -675,7 +671,7 @@ static void bcache_device_unlink(struct bcache_device *d)
lockdep_assert_held(&bch_register_lock);
if (d->c && !test_and_set_bit(BCACHE_DEV_UNLINK_DONE, &d->flags)) {
- unsigned i;
+ unsigned int i;
struct cache *ca;
sysfs_remove_link(&d->c->kobj, d->name);
@@ -689,7 +685,7 @@ static void bcache_device_unlink(struct bcache_device *d)
static void bcache_device_link(struct bcache_device *d, struct cache_set *c,
const char *name)
{
- unsigned i;
+ unsigned int i;
struct cache *ca;
for_each_cache(ca, d->c, i)
@@ -716,7 +712,7 @@ static void bcache_device_detach(struct bcache_device *d)
SET_UUID_FLASH_ONLY(u, 0);
memcpy(u->uuid, invalid_uuid, 16);
- u->invalidated = cpu_to_le32(get_seconds());
+ u->invalidated = cpu_to_le32((u32)ktime_get_real_seconds());
bch_uuid_write(d->c);
}
@@ -728,7 +724,7 @@ static void bcache_device_detach(struct bcache_device *d)
}
static void bcache_device_attach(struct bcache_device *d, struct cache_set *c,
- unsigned id)
+ unsigned int id)
{
d->id = id;
d->c = c;
@@ -776,7 +772,7 @@ static void bcache_device_free(struct bcache_device *d)
closure_debug_destroy(&d->cl);
}
-static int bcache_device_init(struct bcache_device *d, unsigned block_size,
+static int bcache_device_init(struct bcache_device *d, unsigned int block_size,
sector_t sectors)
{
struct request_queue *q;
@@ -792,7 +788,7 @@ static int bcache_device_init(struct bcache_device *d, unsigned block_size,
if (!d->nr_stripes || d->nr_stripes > max_stripes) {
pr_err("nr_stripes too large or invalid: %u (start sector beyond end of disk?)",
- (unsigned)d->nr_stripes);
+ (unsigned int)d->nr_stripes);
return -ENOMEM;
}
@@ -866,6 +862,44 @@ static void calc_cached_dev_sectors(struct cache_set *c)
c->cached_dev_sectors = sectors;
}
+#define BACKING_DEV_OFFLINE_TIMEOUT 5
+static int cached_dev_status_update(void *arg)
+{
+ struct cached_dev *dc = arg;
+ struct request_queue *q;
+
+ /*
+ * If this delayed worker is stopping outside, directly quit here.
+ * dc->io_disable might be set via sysfs interface, so check it
+ * here too.
+ */
+ while (!kthread_should_stop() && !dc->io_disable) {
+ q = bdev_get_queue(dc->bdev);
+ if (blk_queue_dying(q))
+ dc->offline_seconds++;
+ else
+ dc->offline_seconds = 0;
+
+ if (dc->offline_seconds >= BACKING_DEV_OFFLINE_TIMEOUT) {
+ pr_err("%s: device offline for %d seconds",
+ dc->backing_dev_name,
+ BACKING_DEV_OFFLINE_TIMEOUT);
+ pr_err("%s: disable I/O request due to backing "
+ "device offline", dc->disk.name);
+ dc->io_disable = true;
+ /* let others know earlier that io_disable is true */
+ smp_mb();
+ bcache_device_stop(&dc->disk);
+ break;
+ }
+ schedule_timeout_interruptible(HZ);
+ }
+
+ wait_for_kthread_stop();
+ return 0;
+}
+
+
void bch_cached_dev_run(struct cached_dev *dc)
{
struct bcache_device *d = &dc->disk;
@@ -890,6 +924,7 @@ void bch_cached_dev_run(struct cached_dev *dc)
if (!d->c &&
BDEV_STATE(&dc->sb) != BDEV_STATE_NONE) {
struct closure cl;
+
closure_init_stack(&cl);
SET_BDEV_STATE(&dc->sb, BDEV_STATE_STALE);
@@ -899,8 +934,10 @@ void bch_cached_dev_run(struct cached_dev *dc)
add_disk(d->disk);
bd_link_disk_holder(dc->bdev, dc->disk.disk);
- /* won't show up in the uevent file, use udevadm monitor -e instead
- * only class / kset properties are persistent */
+ /*
+ * won't show up in the uevent file, use udevadm monitor -e instead
+ * only class / kset properties are persistent
+ */
kobject_uevent_env(&disk_to_dev(d->disk)->kobj, KOBJ_CHANGE, env);
kfree(env[1]);
kfree(env[2]);
@@ -908,6 +945,14 @@ void bch_cached_dev_run(struct cached_dev *dc)
if (sysfs_create_link(&d->kobj, &disk_to_dev(d->disk)->kobj, "dev") ||
sysfs_create_link(&disk_to_dev(d->disk)->kobj, &d->kobj, "bcache"))
pr_debug("error creating sysfs link");
+
+ dc->status_update_thread = kthread_run(cached_dev_status_update,
+ dc, "bcache_status_update");
+ if (IS_ERR(dc->status_update_thread)) {
+ pr_warn("failed to create bcache_status_update kthread, "
+ "continue to run without monitoring backing "
+ "device status");
+ }
}
/*
@@ -939,6 +984,7 @@ static void cached_dev_detach_finish(struct work_struct *w)
{
struct cached_dev *dc = container_of(w, struct cached_dev, detach);
struct closure cl;
+
closure_init_stack(&cl);
BUG_ON(!test_bit(BCACHE_DEV_DETACHING, &dc->disk.flags));
@@ -960,6 +1006,7 @@ static void cached_dev_detach_finish(struct work_struct *w)
bch_write_bdev_super(dc, &cl);
closure_sync(&cl);
+ calc_cached_dev_sectors(dc->disk.c);
bcache_device_detach(&dc->disk);
list_move(&dc->list, &uncached_devices);
@@ -998,7 +1045,7 @@ void bch_cached_dev_detach(struct cached_dev *dc)
int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c,
uint8_t *set_uuid)
{
- uint32_t rtime = cpu_to_le32(get_seconds());
+ uint32_t rtime = cpu_to_le32((u32)ktime_get_real_seconds());
struct uuid_entry *u;
struct cached_dev *exist_dc, *t;
@@ -1041,7 +1088,7 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c,
(BDEV_STATE(&dc->sb) == BDEV_STATE_STALE ||
BDEV_STATE(&dc->sb) == BDEV_STATE_NONE)) {
memcpy(u->uuid, invalid_uuid, 16);
- u->invalidated = cpu_to_le32(get_seconds());
+ u->invalidated = cpu_to_le32((u32)ktime_get_real_seconds());
u = NULL;
}
@@ -1060,12 +1107,14 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c,
}
}
- /* Deadlocks since we're called via sysfs...
- sysfs_remove_file(&dc->kobj, &sysfs_attach);
+ /*
+ * Deadlocks since we're called via sysfs...
+ * sysfs_remove_file(&dc->kobj, &sysfs_attach);
*/
if (bch_is_zero(u->uuid, 16)) {
struct closure cl;
+
closure_init_stack(&cl);
memcpy(u->uuid, dc->sb.uuid, 16);
@@ -1087,11 +1136,11 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c,
list_move(&dc->list, &c->cached_devs);
calc_cached_dev_sectors(c);
- smp_wmb();
/*
* dc->c must be set before dc->count != 0 - paired with the mb in
* cached_dev_get()
*/
+ smp_wmb();
refcount_set(&dc->count, 1);
/* Block writeback thread, but spawn it */
@@ -1102,11 +1151,12 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c,
}
if (BDEV_STATE(&dc->sb) == BDEV_STATE_DIRTY) {
- bch_sectors_dirty_init(&dc->disk);
atomic_set(&dc->has_dirty, 1);
bch_writeback_queue(dc);
}
+ bch_sectors_dirty_init(&dc->disk);
+
bch_cached_dev_run(dc);
bcache_device_link(&dc->disk, c, "bdev");
atomic_inc(&c->attached_dev_nr);
@@ -1142,6 +1192,8 @@ static void cached_dev_free(struct closure *cl)
kthread_stop(dc->writeback_thread);
if (dc->writeback_write_wq)
destroy_workqueue(dc->writeback_write_wq);
+ if (!IS_ERR_OR_NULL(dc->status_update_thread))
+ kthread_stop(dc->status_update_thread);
if (atomic_read(&dc->running))
bd_unlink_disk_holder(dc->bdev, dc->disk.disk);
@@ -1173,7 +1225,7 @@ static void cached_dev_flush(struct closure *cl)
continue_at(cl, cached_dev_free, system_wq);
}
-static int cached_dev_init(struct cached_dev *dc, unsigned block_size)
+static int cached_dev_init(struct cached_dev *dc, unsigned int block_size)
{
int ret;
struct io *io;
@@ -1255,6 +1307,7 @@ static void register_bdev(struct cache_sb *sb, struct page *sb_page,
pr_info("registered backing device %s", dc->backing_dev_name);
list_add(&dc->list, &uncached_devices);
+ /* attach to a matched cache set if it exists */
list_for_each_entry(c, &bch_cache_sets, list)
bch_cached_dev_attach(dc, c, NULL);
@@ -1280,6 +1333,7 @@ void bch_flash_dev_release(struct kobject *kobj)
static void flash_dev_free(struct closure *cl)
{
struct bcache_device *d = container_of(cl, struct bcache_device, cl);
+
mutex_lock(&bch_register_lock);
atomic_long_sub(bcache_dev_sectors_dirty(d),
&d->c->flash_dev_dirty_sectors);
@@ -1362,7 +1416,7 @@ int bch_flash_dev_create(struct cache_set *c, uint64_t size)
get_random_bytes(u->uuid, 16);
memset(u->label, 0, 32);
- u->first_reg = u->last_reg = cpu_to_le32(get_seconds());
+ u->first_reg = u->last_reg = cpu_to_le32((u32)ktime_get_real_seconds());
SET_UUID_FLASH_ONLY(u, 1);
u->sectors = size >> 9;
@@ -1419,17 +1473,18 @@ bool bch_cache_set_error(struct cache_set *c, const char *fmt, ...)
if (test_and_set_bit(CACHE_SET_IO_DISABLE, &c->flags))
pr_info("CACHE_SET_IO_DISABLE already set");
- /* XXX: we can be called from atomic context
- acquire_console_sem();
- */
+ /*
+ * XXX: we can be called from atomic context
+ * acquire_console_sem();
+ */
- printk(KERN_ERR "bcache: error on %pU: ", c->sb.set_uuid);
+ pr_err("bcache: error on %pU: ", c->sb.set_uuid);
va_start(args, fmt);
vprintk(fmt, args);
va_end(args);
- printk(", disabling caching\n");
+ pr_err(", disabling caching\n");
if (c->on_error == ON_ERROR_PANIC)
panic("panic forced after error\n");
@@ -1441,6 +1496,7 @@ bool bch_cache_set_error(struct cache_set *c, const char *fmt, ...)
void bch_cache_set_release(struct kobject *kobj)
{
struct cache_set *c = container_of(kobj, struct cache_set, kobj);
+
kfree(c);
module_put(THIS_MODULE);
}
@@ -1449,10 +1505,9 @@ static void cache_set_free(struct closure *cl)
{
struct cache_set *c = container_of(cl, struct cache_set, cl);
struct cache *ca;
- unsigned i;
+ unsigned int i;
- if (!IS_ERR_OR_NULL(c->debug))
- debugfs_remove(c->debug);
+ debugfs_remove(c->debug);
bch_open_buckets_free(c);
bch_btree_cache_free(c);
@@ -1496,7 +1551,7 @@ static void cache_set_flush(struct closure *cl)
struct cache_set *c = container_of(cl, struct cache_set, caching);
struct cache *ca;
struct btree *b;
- unsigned i;
+ unsigned int i;
bch_cache_accounting_destroy(&c->accounting);
@@ -1561,21 +1616,21 @@ static void conditional_stop_bcache_device(struct cache_set *c,
*/
pr_warn("stop_when_cache_set_failed of %s is \"auto\" and cache is dirty, stop it to avoid potential data corruption.",
d->disk->disk_name);
- /*
- * There might be a small time gap that cache set is
- * released but bcache device is not. Inside this time
- * gap, regular I/O requests will directly go into
- * backing device as no cache set attached to. This
- * behavior may also introduce potential inconsistence
- * data in writeback mode while cache is dirty.
- * Therefore before calling bcache_device_stop() due
- * to a broken cache device, dc->io_disable should be
- * explicitly set to true.
- */
- dc->io_disable = true;
- /* make others know io_disable is true earlier */
- smp_mb();
- bcache_device_stop(d);
+ /*
+ * There might be a small time gap that cache set is
+ * released but bcache device is not. Inside this time
+ * gap, regular I/O requests will directly go into
+ * backing device as no cache set attached to. This
+ * behavior may also introduce potential inconsistence
+ * data in writeback mode while cache is dirty.
+ * Therefore before calling bcache_device_stop() due
+ * to a broken cache device, dc->io_disable should be
+ * explicitly set to true.
+ */
+ dc->io_disable = true;
+ /* make others know io_disable is true earlier */
+ smp_mb();
+ bcache_device_stop(d);
} else {
/*
* dc->stop_when_cache_set_failed == BCH_CACHED_STOP_AUTO
@@ -1635,6 +1690,7 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb)
{
int iter_size;
struct cache_set *c = kzalloc(sizeof(struct cache_set), GFP_KERNEL);
+
if (!c)
return NULL;
@@ -1730,7 +1786,7 @@ static void run_cache_set(struct cache_set *c)
struct cached_dev *dc, *t;
struct cache *ca;
struct closure cl;
- unsigned i;
+ unsigned int i;
closure_init_stack(&cl);
@@ -1772,7 +1828,9 @@ static void run_cache_set(struct cache_set *c)
goto err;
err = "error reading btree root";
- c->root = bch_btree_node_get(c, NULL, k, j->btree_level, true, NULL);
+ c->root = bch_btree_node_get(c, NULL, k,
+ j->btree_level,
+ true, NULL);
if (IS_ERR_OR_NULL(c->root))
goto err;
@@ -1821,7 +1879,7 @@ static void run_cache_set(struct cache_set *c)
pr_notice("invalidating existing data");
for_each_cache(ca, c, i) {
- unsigned j;
+ unsigned int j;
ca->sb.keys = clamp_t(int, ca->sb.nbuckets >> 7,
2, SB_JOURNAL_BUCKETS);
@@ -1875,7 +1933,7 @@ static void run_cache_set(struct cache_set *c)
goto err;
closure_sync(&cl);
- c->sb.last_mount = get_seconds();
+ c->sb.last_mount = (u32)ktime_get_real_seconds();
bcache_write_super(c);
list_for_each_entry_safe(dc, t, &uncached_devices, list)
@@ -1966,7 +2024,7 @@ err:
void bch_cache_release(struct kobject *kobj)
{
struct cache *ca = container_of(kobj, struct cache, kobj);
- unsigned i;
+ unsigned int i;
if (ca->set) {
BUG_ON(ca->set->cache[ca->sb.nr_this_dev] != ca);
@@ -1998,6 +2056,8 @@ static int cache_alloc(struct cache *ca)
size_t free;
size_t btree_buckets;
struct bucket *b;
+ int ret = -ENOMEM;
+ const char *err = NULL;
__module_get(THIS_MODULE);
kobject_init(&ca->kobj, &bch_cache_ktype);
@@ -2015,19 +2075,64 @@ static int cache_alloc(struct cache *ca)
*/
btree_buckets = ca->sb.njournal_buckets ?: 8;
free = roundup_pow_of_two(ca->sb.nbuckets) >> 10;
+ if (!free) {
+ ret = -EPERM;
+ err = "ca->sb.nbuckets is too small";
+ goto err_free;
+ }
- if (!init_fifo(&ca->free[RESERVE_BTREE], btree_buckets, GFP_KERNEL) ||
- !init_fifo_exact(&ca->free[RESERVE_PRIO], prio_buckets(ca), GFP_KERNEL) ||
- !init_fifo(&ca->free[RESERVE_MOVINGGC], free, GFP_KERNEL) ||
- !init_fifo(&ca->free[RESERVE_NONE], free, GFP_KERNEL) ||
- !init_fifo(&ca->free_inc, free << 2, GFP_KERNEL) ||
- !init_heap(&ca->heap, free << 3, GFP_KERNEL) ||
- !(ca->buckets = vzalloc(sizeof(struct bucket) *
- ca->sb.nbuckets)) ||
- !(ca->prio_buckets = kzalloc(sizeof(uint64_t) * prio_buckets(ca) *
- 2, GFP_KERNEL)) ||
- !(ca->disk_buckets = alloc_bucket_pages(GFP_KERNEL, ca)))
- return -ENOMEM;
+ if (!init_fifo(&ca->free[RESERVE_BTREE], btree_buckets,
+ GFP_KERNEL)) {
+ err = "ca->free[RESERVE_BTREE] alloc failed";
+ goto err_btree_alloc;
+ }
+
+ if (!init_fifo_exact(&ca->free[RESERVE_PRIO], prio_buckets(ca),
+ GFP_KERNEL)) {
+ err = "ca->free[RESERVE_PRIO] alloc failed";
+ goto err_prio_alloc;
+ }
+
+ if (!init_fifo(&ca->free[RESERVE_MOVINGGC], free, GFP_KERNEL)) {
+ err = "ca->free[RESERVE_MOVINGGC] alloc failed";
+ goto err_movinggc_alloc;
+ }
+
+ if (!init_fifo(&ca->free[RESERVE_NONE], free, GFP_KERNEL)) {
+ err = "ca->free[RESERVE_NONE] alloc failed";
+ goto err_none_alloc;
+ }
+
+ if (!init_fifo(&ca->free_inc, free << 2, GFP_KERNEL)) {
+ err = "ca->free_inc alloc failed";
+ goto err_free_inc_alloc;
+ }
+
+ if (!init_heap(&ca->heap, free << 3, GFP_KERNEL)) {
+ err = "ca->heap alloc failed";
+ goto err_heap_alloc;
+ }
+
+ ca->buckets = vzalloc(array_size(sizeof(struct bucket),
+ ca->sb.nbuckets));
+ if (!ca->buckets) {
+ err = "ca->buckets alloc failed";
+ goto err_buckets_alloc;
+ }
+
+ ca->prio_buckets = kzalloc(array3_size(sizeof(uint64_t),
+ prio_buckets(ca), 2),
+ GFP_KERNEL);
+ if (!ca->prio_buckets) {
+ err = "ca->prio_buckets alloc failed";
+ goto err_prio_buckets_alloc;
+ }
+
+ ca->disk_buckets = alloc_bucket_pages(GFP_KERNEL, ca);
+ if (!ca->disk_buckets) {
+ err = "ca->disk_buckets alloc failed";
+ goto err_disk_buckets_alloc;
+ }
ca->prio_last_buckets = ca->prio_buckets + prio_buckets(ca);
@@ -2035,6 +2140,29 @@ static int cache_alloc(struct cache *ca)
atomic_set(&b->pin, 0);
return 0;
+
+err_disk_buckets_alloc:
+ kfree(ca->prio_buckets);
+err_prio_buckets_alloc:
+ vfree(ca->buckets);
+err_buckets_alloc:
+ free_heap(&ca->heap);
+err_heap_alloc:
+ free_fifo(&ca->free_inc);
+err_free_inc_alloc:
+ free_fifo(&ca->free[RESERVE_NONE]);
+err_none_alloc:
+ free_fifo(&ca->free[RESERVE_MOVINGGC]);
+err_movinggc_alloc:
+ free_fifo(&ca->free[RESERVE_PRIO]);
+err_prio_alloc:
+ free_fifo(&ca->free[RESERVE_BTREE]);
+err_btree_alloc:
+err_free:
+ module_put(THIS_MODULE);
+ if (err)
+ pr_notice("error %s: %s", ca->cache_dev_name, err);
+ return ret;
}
static int register_cache(struct cache_sb *sb, struct page *sb_page,
@@ -2060,12 +2188,16 @@ static int register_cache(struct cache_sb *sb, struct page *sb_page,
blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
if (ret == -ENOMEM)
err = "cache_alloc(): -ENOMEM";
+ else if (ret == -EPERM)
+ err = "cache_alloc(): cache device is too small";
else
err = "cache_alloc(): unknown error";
goto err;
}
- if (kobject_add(&ca->kobj, &part_to_dev(bdev->bd_part)->kobj, "bcache")) {
+ if (kobject_add(&ca->kobj,
+ &part_to_dev(bdev->bd_part)->kobj,
+ "bcache")) {
err = "error calling kobject_add";
ret = -ENOMEM;
goto out;
@@ -2094,13 +2226,14 @@ err:
/* Global interfaces/init */
-static ssize_t register_bcache(struct kobject *, struct kobj_attribute *,
- const char *, size_t);
+static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
+ const char *buffer, size_t size);
kobj_attribute_write(register, register_bcache);
kobj_attribute_write(register_quiet, register_bcache);
-static bool bch_is_open_backing(struct block_device *bdev) {
+static bool bch_is_open_backing(struct block_device *bdev)
+{
struct cache_set *c, *tc;
struct cached_dev *dc, *t;
@@ -2114,10 +2247,11 @@ static bool bch_is_open_backing(struct block_device *bdev) {
return false;
}
-static bool bch_is_open_cache(struct block_device *bdev) {
+static bool bch_is_open_cache(struct block_device *bdev)
+{
struct cache_set *c, *tc;
struct cache *ca;
- unsigned i;
+ unsigned int i;
list_for_each_entry_safe(c, tc, &bch_cache_sets, list)
for_each_cache(ca, c, i)
@@ -2126,7 +2260,8 @@ static bool bch_is_open_cache(struct block_device *bdev) {
return false;
}
-static bool bch_is_open(struct block_device *bdev) {
+static bool bch_is_open(struct block_device *bdev)
+{
return bch_is_open_cache(bdev) || bch_is_open_backing(bdev);
}
@@ -2143,8 +2278,12 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
if (!try_module_get(THIS_MODULE))
return -EBUSY;
- if (!(path = kstrndup(buffer, size, GFP_KERNEL)) ||
- !(sb = kmalloc(sizeof(struct cache_sb), GFP_KERNEL)))
+ path = kstrndup(buffer, size, GFP_KERNEL);
+ if (!path)
+ goto err;
+
+ sb = kmalloc(sizeof(struct cache_sb), GFP_KERNEL);
+ if (!sb)
goto err;
err = "failed to open device";
@@ -2179,6 +2318,7 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
err = "failed to register device";
if (SB_IS_BDEV(sb)) {
struct cached_dev *dc = kzalloc(sizeof(*dc), GFP_KERNEL);
+
if (!dc)
goto err_close;
@@ -2187,6 +2327,7 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
mutex_unlock(&bch_register_lock);
} else {
struct cache *ca = kzalloc(sizeof(*ca), GFP_KERNEL);
+
if (!ca)
goto err_close;
@@ -2279,12 +2420,41 @@ static void bcache_exit(void)
kobject_put(bcache_kobj);
if (bcache_wq)
destroy_workqueue(bcache_wq);
+ if (bch_journal_wq)
+ destroy_workqueue(bch_journal_wq);
+
if (bcache_major)
unregister_blkdev(bcache_major, "bcache");
unregister_reboot_notifier(&reboot);
mutex_destroy(&bch_register_lock);
}
+/* Check and fixup module parameters */
+static void check_module_parameters(void)
+{
+ if (bch_cutoff_writeback_sync == 0)
+ bch_cutoff_writeback_sync = CUTOFF_WRITEBACK_SYNC;
+ else if (bch_cutoff_writeback_sync > CUTOFF_WRITEBACK_SYNC_MAX) {
+ pr_warn("set bch_cutoff_writeback_sync (%u) to max value %u",
+ bch_cutoff_writeback_sync, CUTOFF_WRITEBACK_SYNC_MAX);
+ bch_cutoff_writeback_sync = CUTOFF_WRITEBACK_SYNC_MAX;
+ }
+
+ if (bch_cutoff_writeback == 0)
+ bch_cutoff_writeback = CUTOFF_WRITEBACK;
+ else if (bch_cutoff_writeback > CUTOFF_WRITEBACK_MAX) {
+ pr_warn("set bch_cutoff_writeback (%u) to max value %u",
+ bch_cutoff_writeback, CUTOFF_WRITEBACK_MAX);
+ bch_cutoff_writeback = CUTOFF_WRITEBACK_MAX;
+ }
+
+ if (bch_cutoff_writeback > bch_cutoff_writeback_sync) {
+ pr_warn("set bch_cutoff_writeback (%u) to %u",
+ bch_cutoff_writeback, bch_cutoff_writeback_sync);
+ bch_cutoff_writeback = bch_cutoff_writeback_sync;
+ }
+}
+
static int __init bcache_init(void)
{
static const struct attribute *files[] = {
@@ -2293,6 +2463,8 @@ static int __init bcache_init(void)
NULL
};
+ check_module_parameters();
+
mutex_init(&bch_register_lock);
init_waitqueue_head(&unregister_wait);
register_reboot_notifier(&reboot);
@@ -2304,13 +2476,23 @@ static int __init bcache_init(void)
return bcache_major;
}
- if (!(bcache_wq = alloc_workqueue("bcache", WQ_MEM_RECLAIM, 0)) ||
- !(bcache_kobj = kobject_create_and_add("bcache", fs_kobj)) ||
- bch_request_init() ||
+ bcache_wq = alloc_workqueue("bcache", WQ_MEM_RECLAIM, 0);
+ if (!bcache_wq)
+ goto err;
+
+ bch_journal_wq = alloc_workqueue("bch_journal", WQ_MEM_RECLAIM, 0);
+ if (!bch_journal_wq)
+ goto err;
+
+ bcache_kobj = kobject_create_and_add("bcache", fs_kobj);
+ if (!bcache_kobj)
+ goto err;
+
+ if (bch_request_init() ||
sysfs_create_files(bcache_kobj, files))
goto err;
- bch_debug_init(bcache_kobj);
+ bch_debug_init();
closure_debug_init();
return 0;
@@ -2319,5 +2501,18 @@ err:
return -ENOMEM;
}
+/*
+ * Module hooks
+ */
module_exit(bcache_exit);
module_init(bcache_init);
+
+module_param(bch_cutoff_writeback, uint, 0);
+MODULE_PARM_DESC(bch_cutoff_writeback, "threshold to cutoff writeback");
+
+module_param(bch_cutoff_writeback_sync, uint, 0);
+MODULE_PARM_DESC(bch_cutoff_writeback_sync, "hard threshold to cutoff writeback");
+
+MODULE_DESCRIPTION("Bcache: a Linux block layer cache");
+MODULE_AUTHOR("Kent Overstreet <kent.overstreet@gmail.com>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c
index 1d5371865e0f..00095344a23d 100644
--- a/drivers/md/bcache/sysfs.c
+++ b/drivers/md/bcache/sysfs.c
@@ -15,6 +15,22 @@
#include <linux/sort.h>
#include <linux/sched/clock.h>
+/* Default is 0 ("writethrough") */
+static const char * const bch_cache_modes[] = {
+ "writethrough",
+ "writeback",
+ "writearound",
+ "none",
+ NULL
+};
+
+/* Default is 0 ("auto") */
+static const char * const bch_stop_on_failure_modes[] = {
+ "auto",
+ "always",
+ NULL
+};
+
static const char * const cache_replacement_policies[] = {
"lru",
"fifo",
@@ -50,6 +66,8 @@ read_attribute(written);
read_attribute(btree_written);
read_attribute(metadata_written);
read_attribute(active_journal_entries);
+read_attribute(backing_dev_name);
+read_attribute(backing_dev_uuid);
sysfs_time_stats_attribute(btree_gc, sec, ms);
sysfs_time_stats_attribute(btree_split, sec, us);
@@ -71,6 +89,8 @@ read_attribute(writeback_keys_done);
read_attribute(writeback_keys_failed);
read_attribute(io_errors);
read_attribute(congested);
+read_attribute(cutoff_writeback);
+read_attribute(cutoff_writeback_sync);
rw_attribute(congested_read_threshold_us);
rw_attribute(congested_write_threshold_us);
@@ -111,25 +131,42 @@ rw_attribute(expensive_debug_checks);
rw_attribute(cache_replacement_policy);
rw_attribute(btree_shrinker_disabled);
rw_attribute(copy_gc_enabled);
+rw_attribute(gc_after_writeback);
rw_attribute(size);
+static ssize_t bch_snprint_string_list(char *buf,
+ size_t size,
+ const char * const list[],
+ size_t selected)
+{
+ char *out = buf;
+ size_t i;
+
+ for (i = 0; list[i]; i++)
+ out += snprintf(out, buf + size - out,
+ i == selected ? "[%s] " : "%s ", list[i]);
+
+ out[-1] = '\n';
+ return out - buf;
+}
+
SHOW(__bch_cached_dev)
{
struct cached_dev *dc = container_of(kobj, struct cached_dev,
disk.kobj);
- const char *states[] = { "no cache", "clean", "dirty", "inconsistent" };
+ char const *states[] = { "no cache", "clean", "dirty", "inconsistent" };
int wb = dc->writeback_running;
#define var(stat) (dc->stat)
if (attr == &sysfs_cache_mode)
return bch_snprint_string_list(buf, PAGE_SIZE,
- bch_cache_modes + 1,
+ bch_cache_modes,
BDEV_CACHE_MODE(&dc->sb));
if (attr == &sysfs_stop_when_cache_set_failed)
return bch_snprint_string_list(buf, PAGE_SIZE,
- bch_stop_on_failure_modes + 1,
+ bch_stop_on_failure_modes,
dc->stop_when_cache_set_failed);
@@ -207,6 +244,19 @@ SHOW(__bch_cached_dev)
return strlen(buf);
}
+ if (attr == &sysfs_backing_dev_name) {
+ snprintf(buf, BDEVNAME_SIZE + 1, "%s", dc->backing_dev_name);
+ strcat(buf, "\n");
+ return strlen(buf);
+ }
+
+ if (attr == &sysfs_backing_dev_uuid) {
+ /* convert binary uuid into 36-byte string plus '\0' */
+ snprintf(buf, 36+1, "%pU", dc->sb.uuid);
+ strcat(buf, "\n");
+ return strlen(buf);
+ }
+
#undef var
return 0;
}
@@ -226,12 +276,13 @@ STORE(__cached_dev)
sysfs_strtoul(data_csum, dc->disk.data_csum);
d_strtoul(verify);
- d_strtoul(bypass_torture_test);
- d_strtoul(writeback_metadata);
- d_strtoul(writeback_running);
- d_strtoul(writeback_delay);
+ sysfs_strtoul_bool(bypass_torture_test, dc->bypass_torture_test);
+ sysfs_strtoul_bool(writeback_metadata, dc->writeback_metadata);
+ sysfs_strtoul_bool(writeback_running, dc->writeback_running);
+ sysfs_strtoul_clamp(writeback_delay, dc->writeback_delay, 0, UINT_MAX);
- sysfs_strtoul_clamp(writeback_percent, dc->writeback_percent, 0, 40);
+ sysfs_strtoul_clamp(writeback_percent, dc->writeback_percent,
+ 0, bch_cutoff_writeback);
if (attr == &sysfs_writeback_rate) {
ssize_t ret;
@@ -250,8 +301,15 @@ STORE(__cached_dev)
sysfs_strtoul_clamp(writeback_rate_update_seconds,
dc->writeback_rate_update_seconds,
1, WRITEBACK_RATE_UPDATE_SECS_MAX);
- d_strtoul(writeback_rate_i_term_inverse);
- d_strtoul_nonzero(writeback_rate_p_term_inverse);
+ sysfs_strtoul_clamp(writeback_rate_i_term_inverse,
+ dc->writeback_rate_i_term_inverse,
+ 1, UINT_MAX);
+ sysfs_strtoul_clamp(writeback_rate_p_term_inverse,
+ dc->writeback_rate_p_term_inverse,
+ 1, UINT_MAX);
+ sysfs_strtoul_clamp(writeback_rate_minimum,
+ dc->writeback_rate_minimum,
+ 1, UINT_MAX);
sysfs_strtoul_clamp(io_error_limit, dc->error_limit, 0, INT_MAX);
@@ -261,7 +319,9 @@ STORE(__cached_dev)
dc->io_disable = v ? 1 : 0;
}
- d_strtoi_h(sequential_cutoff);
+ sysfs_strtoul_clamp(sequential_cutoff,
+ dc->sequential_cutoff,
+ 0, UINT_MAX);
d_strtoi_h(readahead);
if (attr == &sysfs_clear_stats)
@@ -272,20 +332,18 @@ STORE(__cached_dev)
bch_cached_dev_run(dc);
if (attr == &sysfs_cache_mode) {
- v = bch_read_string_list(buf, bch_cache_modes + 1);
-
+ v = __sysfs_match_string(bch_cache_modes, -1, buf);
if (v < 0)
return v;
- if ((unsigned) v != BDEV_CACHE_MODE(&dc->sb)) {
+ if ((unsigned int) v != BDEV_CACHE_MODE(&dc->sb)) {
SET_BDEV_CACHE_MODE(&dc->sb, v);
bch_write_bdev_super(dc, NULL);
}
}
if (attr == &sysfs_stop_when_cache_set_failed) {
- v = bch_read_string_list(buf, bch_stop_on_failure_modes + 1);
-
+ v = __sysfs_match_string(bch_stop_on_failure_modes, -1, buf);
if (v < 0)
return v;
@@ -312,8 +370,9 @@ STORE(__cached_dev)
add_uevent_var(env, "DRIVER=bcache");
add_uevent_var(env, "CACHED_UUID=%pU", dc->sb.uuid),
add_uevent_var(env, "CACHED_LABEL=%s", buf);
- kobject_uevent_env(
- &disk_to_dev(dc->disk.disk)->kobj, KOBJ_CHANGE, env->envp);
+ kobject_uevent_env(&disk_to_dev(dc->disk.disk)->kobj,
+ KOBJ_CHANGE,
+ env->envp);
kfree(env);
}
@@ -351,8 +410,25 @@ STORE(bch_cached_dev)
mutex_lock(&bch_register_lock);
size = __cached_dev_store(kobj, attr, buf, size);
- if (attr == &sysfs_writeback_running)
- bch_writeback_queue(dc);
+ if (attr == &sysfs_writeback_running) {
+ /* dc->writeback_running changed in __cached_dev_store() */
+ if (IS_ERR_OR_NULL(dc->writeback_thread)) {
+ /*
+ * reject setting it to 1 via sysfs if writeback
+ * kthread is not created yet.
+ */
+ if (dc->writeback_running) {
+ dc->writeback_running = false;
+ pr_err("%s: failed to run non-existent writeback thread",
+ dc->disk.disk->disk_name);
+ }
+ } else
+ /*
+ * writeback kthread will check if dc->writeback_running
+ * is true or false.
+ */
+ bch_writeback_queue(dc);
+ }
if (attr == &sysfs_writeback_percent)
if (!test_and_set_bit(BCACHE_DEV_WB_RUNNING, &dc->disk.flags))
@@ -380,6 +456,7 @@ static struct attribute *bch_cached_dev_files[] = {
&sysfs_writeback_rate_update_seconds,
&sysfs_writeback_rate_i_term_inverse,
&sysfs_writeback_rate_p_term_inverse,
+ &sysfs_writeback_rate_minimum,
&sysfs_writeback_rate_debug,
&sysfs_errors,
&sysfs_io_error_limit,
@@ -397,6 +474,8 @@ static struct attribute *bch_cached_dev_files[] = {
&sysfs_verify,
&sysfs_bypass_torture_test,
#endif
+ &sysfs_backing_dev_name,
+ &sysfs_backing_dev_uuid,
NULL
};
KTYPE(bch_cached_dev);
@@ -430,6 +509,7 @@ STORE(__bch_flash_dev)
if (attr == &sysfs_size) {
uint64_t v;
+
strtoi_h_or_return(buf, v);
u->sectors = v >> 9;
@@ -504,9 +584,9 @@ static int bch_bset_print_stats(struct cache_set *c, char *buf)
op.stats.floats, op.stats.failed);
}
-static unsigned bch_root_usage(struct cache_set *c)
+static unsigned int bch_root_usage(struct cache_set *c)
{
- unsigned bytes = 0;
+ unsigned int bytes = 0;
struct bkey *k;
struct btree *b;
struct btree_iter iter;
@@ -541,9 +621,9 @@ static size_t bch_cache_size(struct cache_set *c)
return ret;
}
-static unsigned bch_cache_max_chain(struct cache_set *c)
+static unsigned int bch_cache_max_chain(struct cache_set *c)
{
- unsigned ret = 0;
+ unsigned int ret = 0;
struct hlist_head *h;
mutex_lock(&c->bucket_lock);
@@ -551,7 +631,7 @@ static unsigned bch_cache_max_chain(struct cache_set *c)
for (h = c->bucket_hash;
h < c->bucket_hash + (1 << BUCKET_HASH_BITS);
h++) {
- unsigned i = 0;
+ unsigned int i = 0;
struct hlist_node *p;
hlist_for_each(p, h)
@@ -564,13 +644,13 @@ static unsigned bch_cache_max_chain(struct cache_set *c)
return ret;
}
-static unsigned bch_btree_used(struct cache_set *c)
+static unsigned int bch_btree_used(struct cache_set *c)
{
return div64_u64(c->gc_stats.key_bytes * 100,
(c->gc_stats.nodes ?: 1) * btree_bytes(c));
}
-static unsigned bch_average_key_size(struct cache_set *c)
+static unsigned int bch_average_key_size(struct cache_set *c)
{
return c->gc_stats.nkeys
? div64_u64(c->gc_stats.data, c->gc_stats.nkeys)
@@ -633,6 +713,9 @@ SHOW(__bch_cache_set)
sysfs_print(congested_write_threshold_us,
c->congested_write_threshold_us);
+ sysfs_print(cutoff_writeback, bch_cutoff_writeback);
+ sysfs_print(cutoff_writeback_sync, bch_cutoff_writeback_sync);
+
sysfs_print(active_journal_entries, fifo_used(&c->journal.pin));
sysfs_printf(verify, "%i", c->verify);
sysfs_printf(key_merging_disabled, "%i", c->key_merging_disabled);
@@ -641,6 +724,7 @@ SHOW(__bch_cache_set)
sysfs_printf(gc_always_rewrite, "%i", c->gc_always_rewrite);
sysfs_printf(btree_shrinker_disabled, "%i", c->shrinker_disabled);
sysfs_printf(copy_gc_enabled, "%i", c->copy_gc_enabled);
+ sysfs_printf(gc_after_writeback, "%i", c->gc_after_writeback);
sysfs_printf(io_disable, "%i",
test_bit(CACHE_SET_IO_DISABLE, &c->flags));
@@ -654,6 +738,7 @@ SHOW_LOCKED(bch_cache_set)
STORE(__bch_cache_set)
{
struct cache_set *c = container_of(kobj, struct cache_set, kobj);
+ ssize_t v;
if (attr == &sysfs_unregister)
bch_cache_set_unregister(c);
@@ -673,6 +758,7 @@ STORE(__bch_cache_set)
if (attr == &sysfs_flash_vol_create) {
int r;
uint64_t v;
+
strtoi_h_or_return(buf, v);
r = bch_flash_dev_create(c, v);
@@ -688,53 +774,49 @@ STORE(__bch_cache_set)
bch_cache_accounting_clear(&c->accounting);
}
- if (attr == &sysfs_trigger_gc) {
- /*
- * Garbage collection thread only works when sectors_to_gc < 0,
- * when users write to sysfs entry trigger_gc, most of time
- * they want to forcibly triger gargage collection. Here -1 is
- * set to c->sectors_to_gc, to make gc_should_run() give a
- * chance to permit gc thread to run. "give a chance" means
- * before going into gc_should_run(), there is still chance
- * that c->sectors_to_gc being set to other positive value. So
- * writing sysfs entry trigger_gc won't always make sure gc
- * thread takes effect.
- */
- atomic_set(&c->sectors_to_gc, -1);
- wake_up_gc(c);
- }
+ if (attr == &sysfs_trigger_gc)
+ force_wake_up_gc(c);
if (attr == &sysfs_prune_cache) {
struct shrink_control sc;
+
sc.gfp_mask = GFP_KERNEL;
sc.nr_to_scan = strtoul_or_return(buf);
c->shrink.scan_objects(&c->shrink, &sc);
}
- sysfs_strtoul(congested_read_threshold_us,
- c->congested_read_threshold_us);
- sysfs_strtoul(congested_write_threshold_us,
- c->congested_write_threshold_us);
+ sysfs_strtoul_clamp(congested_read_threshold_us,
+ c->congested_read_threshold_us,
+ 0, UINT_MAX);
+ sysfs_strtoul_clamp(congested_write_threshold_us,
+ c->congested_write_threshold_us,
+ 0, UINT_MAX);
if (attr == &sysfs_errors) {
- ssize_t v = bch_read_string_list(buf, error_actions);
-
+ v = __sysfs_match_string(error_actions, -1, buf);
if (v < 0)
return v;
c->on_error = v;
}
- if (attr == &sysfs_io_error_limit)
- c->error_limit = strtoul_or_return(buf);
+ sysfs_strtoul_clamp(io_error_limit, c->error_limit, 0, UINT_MAX);
/* See count_io_errors() for why 88 */
- if (attr == &sysfs_io_error_halflife)
- c->error_decay = strtoul_or_return(buf) / 88;
+ if (attr == &sysfs_io_error_halflife) {
+ unsigned long v = 0;
+ ssize_t ret;
- if (attr == &sysfs_io_disable) {
- int v = strtoul_or_return(buf);
+ ret = strtoul_safe_clamp(buf, v, 0, UINT_MAX);
+ if (!ret) {
+ c->error_decay = v / 88;
+ return size;
+ }
+ return ret;
+ }
+ if (attr == &sysfs_io_disable) {
+ v = strtoul_or_return(buf);
if (v) {
if (test_and_set_bit(CACHE_SET_IO_DISABLE,
&c->flags))
@@ -746,13 +828,21 @@ STORE(__bch_cache_set)
}
}
- sysfs_strtoul(journal_delay_ms, c->journal_delay_ms);
- sysfs_strtoul(verify, c->verify);
- sysfs_strtoul(key_merging_disabled, c->key_merging_disabled);
+ sysfs_strtoul_clamp(journal_delay_ms,
+ c->journal_delay_ms,
+ 0, USHRT_MAX);
+ sysfs_strtoul_bool(verify, c->verify);
+ sysfs_strtoul_bool(key_merging_disabled, c->key_merging_disabled);
sysfs_strtoul(expensive_debug_checks, c->expensive_debug_checks);
- sysfs_strtoul(gc_always_rewrite, c->gc_always_rewrite);
- sysfs_strtoul(btree_shrinker_disabled, c->shrinker_disabled);
- sysfs_strtoul(copy_gc_enabled, c->copy_gc_enabled);
+ sysfs_strtoul_bool(gc_always_rewrite, c->gc_always_rewrite);
+ sysfs_strtoul_bool(btree_shrinker_disabled, c->shrinker_disabled);
+ sysfs_strtoul_bool(copy_gc_enabled, c->copy_gc_enabled);
+ /*
+ * write gc_after_writeback here may overwrite an already set
+ * BCH_DO_AUTO_GC, it doesn't matter because this flag will be
+ * set in next chance.
+ */
+ sysfs_strtoul_clamp(gc_after_writeback, c->gc_after_writeback, 0, 1);
return size;
}
@@ -761,12 +851,14 @@ STORE_LOCKED(bch_cache_set)
SHOW(bch_cache_set_internal)
{
struct cache_set *c = container_of(kobj, struct cache_set, internal);
+
return bch_cache_set_show(&c->kobj, attr, buf);
}
STORE(bch_cache_set_internal)
{
struct cache_set *c = container_of(kobj, struct cache_set, internal);
+
return bch_cache_set_store(&c->kobj, attr, buf, size);
}
@@ -831,7 +923,10 @@ static struct attribute *bch_cache_set_internal_files[] = {
&sysfs_gc_always_rewrite,
&sysfs_btree_shrinker_disabled,
&sysfs_copy_gc_enabled,
+ &sysfs_gc_after_writeback,
&sysfs_io_disable,
+ &sysfs_cutoff_writeback,
+ &sysfs_cutoff_writeback_sync,
NULL
};
KTYPE(bch_cache_set_internal);
@@ -948,6 +1043,7 @@ SHOW_LOCKED(bch_cache)
STORE(__bch_cache)
{
struct cache *ca = container_of(kobj, struct cache, kobj);
+ ssize_t v;
if (attr == &sysfs_discard) {
bool v = strtoul_or_return(buf);
@@ -962,12 +1058,11 @@ STORE(__bch_cache)
}
if (attr == &sysfs_cache_replacement_policy) {
- ssize_t v = bch_read_string_list(buf, cache_replacement_policies);
-
+ v = __sysfs_match_string(cache_replacement_policies, -1, buf);
if (v < 0)
return v;
- if ((unsigned) v != CACHE_REPLACEMENT(&ca->sb)) {
+ if ((unsigned int) v != CACHE_REPLACEMENT(&ca->sb)) {
mutex_lock(&ca->set->bucket_lock);
SET_CACHE_REPLACEMENT(&ca->sb, v);
mutex_unlock(&ca->set->bucket_lock);
diff --git a/drivers/md/bcache/sysfs.h b/drivers/md/bcache/sysfs.h
index 0526fe92a683..c4687f23f38c 100644
--- a/drivers/md/bcache/sysfs.h
+++ b/drivers/md/bcache/sysfs.h
@@ -43,9 +43,9 @@ STORE(fn) \
static struct attribute sysfs_##_name = \
{ .name = #_name, .mode = _mode }
-#define write_attribute(n) __sysfs_attribute(n, S_IWUSR)
-#define read_attribute(n) __sysfs_attribute(n, S_IRUGO)
-#define rw_attribute(n) __sysfs_attribute(n, S_IRUGO|S_IWUSR)
+#define write_attribute(n) __sysfs_attribute(n, 0200)
+#define read_attribute(n) __sysfs_attribute(n, 0444)
+#define rw_attribute(n) __sysfs_attribute(n, 0644)
#define sysfs_printf(file, fmt, ...) \
do { \
@@ -78,11 +78,28 @@ do { \
return strtoul_safe(buf, var) ?: (ssize_t) size; \
} while (0)
+#define sysfs_strtoul_bool(file, var) \
+do { \
+ if (attr == &sysfs_ ## file) { \
+ unsigned long v = strtoul_or_return(buf); \
+ \
+ var = v ? 1 : 0; \
+ return size; \
+ } \
+} while (0)
+
#define sysfs_strtoul_clamp(file, var, min, max) \
do { \
- if (attr == &sysfs_ ## file) \
- return strtoul_safe_clamp(buf, var, min, max) \
- ?: (ssize_t) size; \
+ if (attr == &sysfs_ ## file) { \
+ unsigned long v = 0; \
+ ssize_t ret; \
+ ret = strtoul_safe_clamp(buf, v, min, max); \
+ if (!ret) { \
+ var = v; \
+ return size; \
+ } \
+ return ret; \
+ } \
} while (0)
#define strtoul_or_return(cp) \
diff --git a/drivers/md/bcache/util.c b/drivers/md/bcache/util.c
index a3cd3ad28a42..36c436c03f5d 100644
--- a/drivers/md/bcache/util.c
+++ b/drivers/md/bcache/util.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
/*
* random utiility code, for bcache but in theory not specific to bcache
*
@@ -120,41 +121,6 @@ ssize_t bch_hprint(char *buf, int64_t v)
return sprintf(buf, "%llu.%i%c", q, t * 10 / 1024, units[u]);
}
-ssize_t bch_snprint_string_list(char *buf, size_t size, const char * const list[],
- size_t selected)
-{
- char *out = buf;
- size_t i;
-
- for (i = 0; list[i]; i++)
- out += snprintf(out, buf + size - out,
- i == selected ? "[%s] " : "%s ", list[i]);
-
- out[-1] = '\n';
- return out - buf;
-}
-
-ssize_t bch_read_string_list(const char *buf, const char * const list[])
-{
- size_t i;
- char *s, *d = kstrndup(buf, PAGE_SIZE - 1, GFP_KERNEL);
- if (!d)
- return -ENOMEM;
-
- s = strim(d);
-
- for (i = 0; list[i]; i++)
- if (!strcmp(list[i], s))
- break;
-
- kfree(d);
-
- if (!list[i])
- return -EINVAL;
-
- return i;
-}
-
bool bch_is_zero(const char *p, size_t n)
{
size_t i;
@@ -168,6 +134,7 @@ bool bch_is_zero(const char *p, size_t n)
int bch_parse_uuid(const char *s, char *uuid)
{
size_t i, j, x;
+
memset(uuid, 0, 16);
for (i = 0, j = 0;
@@ -287,134 +254,3 @@ start: bv->bv_len = min_t(size_t, PAGE_SIZE - bv->bv_offset,
size -= bv->bv_len;
}
}
-
-/*
- * Portions Copyright (c) 1996-2001, PostgreSQL Global Development Group (Any
- * use permitted, subject to terms of PostgreSQL license; see.)
-
- * If we have a 64-bit integer type, then a 64-bit CRC looks just like the
- * usual sort of implementation. (See Ross Williams' excellent introduction
- * A PAINLESS GUIDE TO CRC ERROR DETECTION ALGORITHMS, available from
- * ftp://ftp.rocksoft.com/papers/crc_v3.txt or several other net sites.)
- * If we have no working 64-bit type, then fake it with two 32-bit registers.
- *
- * The present implementation is a normal (not "reflected", in Williams'
- * terms) 64-bit CRC, using initial all-ones register contents and a final
- * bit inversion. The chosen polynomial is borrowed from the DLT1 spec
- * (ECMA-182, available from http://www.ecma.ch/ecma1/STAND/ECMA-182.HTM):
- *
- * x^64 + x^62 + x^57 + x^55 + x^54 + x^53 + x^52 + x^47 + x^46 + x^45 +
- * x^40 + x^39 + x^38 + x^37 + x^35 + x^33 + x^32 + x^31 + x^29 + x^27 +
- * x^24 + x^23 + x^22 + x^21 + x^19 + x^17 + x^13 + x^12 + x^10 + x^9 +
- * x^7 + x^4 + x + 1
-*/
-
-static const uint64_t crc_table[256] = {
- 0x0000000000000000ULL, 0x42F0E1EBA9EA3693ULL, 0x85E1C3D753D46D26ULL,
- 0xC711223CFA3E5BB5ULL, 0x493366450E42ECDFULL, 0x0BC387AEA7A8DA4CULL,
- 0xCCD2A5925D9681F9ULL, 0x8E224479F47CB76AULL, 0x9266CC8A1C85D9BEULL,
- 0xD0962D61B56FEF2DULL, 0x17870F5D4F51B498ULL, 0x5577EEB6E6BB820BULL,
- 0xDB55AACF12C73561ULL, 0x99A54B24BB2D03F2ULL, 0x5EB4691841135847ULL,
- 0x1C4488F3E8F96ED4ULL, 0x663D78FF90E185EFULL, 0x24CD9914390BB37CULL,
- 0xE3DCBB28C335E8C9ULL, 0xA12C5AC36ADFDE5AULL, 0x2F0E1EBA9EA36930ULL,
- 0x6DFEFF5137495FA3ULL, 0xAAEFDD6DCD770416ULL, 0xE81F3C86649D3285ULL,
- 0xF45BB4758C645C51ULL, 0xB6AB559E258E6AC2ULL, 0x71BA77A2DFB03177ULL,
- 0x334A9649765A07E4ULL, 0xBD68D2308226B08EULL, 0xFF9833DB2BCC861DULL,
- 0x388911E7D1F2DDA8ULL, 0x7A79F00C7818EB3BULL, 0xCC7AF1FF21C30BDEULL,
- 0x8E8A101488293D4DULL, 0x499B3228721766F8ULL, 0x0B6BD3C3DBFD506BULL,
- 0x854997BA2F81E701ULL, 0xC7B97651866BD192ULL, 0x00A8546D7C558A27ULL,
- 0x4258B586D5BFBCB4ULL, 0x5E1C3D753D46D260ULL, 0x1CECDC9E94ACE4F3ULL,
- 0xDBFDFEA26E92BF46ULL, 0x990D1F49C77889D5ULL, 0x172F5B3033043EBFULL,
- 0x55DFBADB9AEE082CULL, 0x92CE98E760D05399ULL, 0xD03E790CC93A650AULL,
- 0xAA478900B1228E31ULL, 0xE8B768EB18C8B8A2ULL, 0x2FA64AD7E2F6E317ULL,
- 0x6D56AB3C4B1CD584ULL, 0xE374EF45BF6062EEULL, 0xA1840EAE168A547DULL,
- 0x66952C92ECB40FC8ULL, 0x2465CD79455E395BULL, 0x3821458AADA7578FULL,
- 0x7AD1A461044D611CULL, 0xBDC0865DFE733AA9ULL, 0xFF3067B657990C3AULL,
- 0x711223CFA3E5BB50ULL, 0x33E2C2240A0F8DC3ULL, 0xF4F3E018F031D676ULL,
- 0xB60301F359DBE0E5ULL, 0xDA050215EA6C212FULL, 0x98F5E3FE438617BCULL,
- 0x5FE4C1C2B9B84C09ULL, 0x1D14202910527A9AULL, 0x93366450E42ECDF0ULL,
- 0xD1C685BB4DC4FB63ULL, 0x16D7A787B7FAA0D6ULL, 0x5427466C1E109645ULL,
- 0x4863CE9FF6E9F891ULL, 0x0A932F745F03CE02ULL, 0xCD820D48A53D95B7ULL,
- 0x8F72ECA30CD7A324ULL, 0x0150A8DAF8AB144EULL, 0x43A04931514122DDULL,
- 0x84B16B0DAB7F7968ULL, 0xC6418AE602954FFBULL, 0xBC387AEA7A8DA4C0ULL,
- 0xFEC89B01D3679253ULL, 0x39D9B93D2959C9E6ULL, 0x7B2958D680B3FF75ULL,
- 0xF50B1CAF74CF481FULL, 0xB7FBFD44DD257E8CULL, 0x70EADF78271B2539ULL,
- 0x321A3E938EF113AAULL, 0x2E5EB66066087D7EULL, 0x6CAE578BCFE24BEDULL,
- 0xABBF75B735DC1058ULL, 0xE94F945C9C3626CBULL, 0x676DD025684A91A1ULL,
- 0x259D31CEC1A0A732ULL, 0xE28C13F23B9EFC87ULL, 0xA07CF2199274CA14ULL,
- 0x167FF3EACBAF2AF1ULL, 0x548F120162451C62ULL, 0x939E303D987B47D7ULL,
- 0xD16ED1D631917144ULL, 0x5F4C95AFC5EDC62EULL, 0x1DBC74446C07F0BDULL,
- 0xDAAD56789639AB08ULL, 0x985DB7933FD39D9BULL, 0x84193F60D72AF34FULL,
- 0xC6E9DE8B7EC0C5DCULL, 0x01F8FCB784FE9E69ULL, 0x43081D5C2D14A8FAULL,
- 0xCD2A5925D9681F90ULL, 0x8FDAB8CE70822903ULL, 0x48CB9AF28ABC72B6ULL,
- 0x0A3B7B1923564425ULL, 0x70428B155B4EAF1EULL, 0x32B26AFEF2A4998DULL,
- 0xF5A348C2089AC238ULL, 0xB753A929A170F4ABULL, 0x3971ED50550C43C1ULL,
- 0x7B810CBBFCE67552ULL, 0xBC902E8706D82EE7ULL, 0xFE60CF6CAF321874ULL,
- 0xE224479F47CB76A0ULL, 0xA0D4A674EE214033ULL, 0x67C58448141F1B86ULL,
- 0x253565A3BDF52D15ULL, 0xAB1721DA49899A7FULL, 0xE9E7C031E063ACECULL,
- 0x2EF6E20D1A5DF759ULL, 0x6C0603E6B3B7C1CAULL, 0xF6FAE5C07D3274CDULL,
- 0xB40A042BD4D8425EULL, 0x731B26172EE619EBULL, 0x31EBC7FC870C2F78ULL,
- 0xBFC9838573709812ULL, 0xFD39626EDA9AAE81ULL, 0x3A28405220A4F534ULL,
- 0x78D8A1B9894EC3A7ULL, 0x649C294A61B7AD73ULL, 0x266CC8A1C85D9BE0ULL,
- 0xE17DEA9D3263C055ULL, 0xA38D0B769B89F6C6ULL, 0x2DAF4F0F6FF541ACULL,
- 0x6F5FAEE4C61F773FULL, 0xA84E8CD83C212C8AULL, 0xEABE6D3395CB1A19ULL,
- 0x90C79D3FEDD3F122ULL, 0xD2377CD44439C7B1ULL, 0x15265EE8BE079C04ULL,
- 0x57D6BF0317EDAA97ULL, 0xD9F4FB7AE3911DFDULL, 0x9B041A914A7B2B6EULL,
- 0x5C1538ADB04570DBULL, 0x1EE5D94619AF4648ULL, 0x02A151B5F156289CULL,
- 0x4051B05E58BC1E0FULL, 0x87409262A28245BAULL, 0xC5B073890B687329ULL,
- 0x4B9237F0FF14C443ULL, 0x0962D61B56FEF2D0ULL, 0xCE73F427ACC0A965ULL,
- 0x8C8315CC052A9FF6ULL, 0x3A80143F5CF17F13ULL, 0x7870F5D4F51B4980ULL,
- 0xBF61D7E80F251235ULL, 0xFD913603A6CF24A6ULL, 0x73B3727A52B393CCULL,
- 0x31439391FB59A55FULL, 0xF652B1AD0167FEEAULL, 0xB4A25046A88DC879ULL,
- 0xA8E6D8B54074A6ADULL, 0xEA16395EE99E903EULL, 0x2D071B6213A0CB8BULL,
- 0x6FF7FA89BA4AFD18ULL, 0xE1D5BEF04E364A72ULL, 0xA3255F1BE7DC7CE1ULL,
- 0x64347D271DE22754ULL, 0x26C49CCCB40811C7ULL, 0x5CBD6CC0CC10FAFCULL,
- 0x1E4D8D2B65FACC6FULL, 0xD95CAF179FC497DAULL, 0x9BAC4EFC362EA149ULL,
- 0x158E0A85C2521623ULL, 0x577EEB6E6BB820B0ULL, 0x906FC95291867B05ULL,
- 0xD29F28B9386C4D96ULL, 0xCEDBA04AD0952342ULL, 0x8C2B41A1797F15D1ULL,
- 0x4B3A639D83414E64ULL, 0x09CA82762AAB78F7ULL, 0x87E8C60FDED7CF9DULL,
- 0xC51827E4773DF90EULL, 0x020905D88D03A2BBULL, 0x40F9E43324E99428ULL,
- 0x2CFFE7D5975E55E2ULL, 0x6E0F063E3EB46371ULL, 0xA91E2402C48A38C4ULL,
- 0xEBEEC5E96D600E57ULL, 0x65CC8190991CB93DULL, 0x273C607B30F68FAEULL,
- 0xE02D4247CAC8D41BULL, 0xA2DDA3AC6322E288ULL, 0xBE992B5F8BDB8C5CULL,
- 0xFC69CAB42231BACFULL, 0x3B78E888D80FE17AULL, 0x7988096371E5D7E9ULL,
- 0xF7AA4D1A85996083ULL, 0xB55AACF12C735610ULL, 0x724B8ECDD64D0DA5ULL,
- 0x30BB6F267FA73B36ULL, 0x4AC29F2A07BFD00DULL, 0x08327EC1AE55E69EULL,
- 0xCF235CFD546BBD2BULL, 0x8DD3BD16FD818BB8ULL, 0x03F1F96F09FD3CD2ULL,
- 0x41011884A0170A41ULL, 0x86103AB85A2951F4ULL, 0xC4E0DB53F3C36767ULL,
- 0xD8A453A01B3A09B3ULL, 0x9A54B24BB2D03F20ULL, 0x5D45907748EE6495ULL,
- 0x1FB5719CE1045206ULL, 0x919735E51578E56CULL, 0xD367D40EBC92D3FFULL,
- 0x1476F63246AC884AULL, 0x568617D9EF46BED9ULL, 0xE085162AB69D5E3CULL,
- 0xA275F7C11F7768AFULL, 0x6564D5FDE549331AULL, 0x279434164CA30589ULL,
- 0xA9B6706FB8DFB2E3ULL, 0xEB46918411358470ULL, 0x2C57B3B8EB0BDFC5ULL,
- 0x6EA7525342E1E956ULL, 0x72E3DAA0AA188782ULL, 0x30133B4B03F2B111ULL,
- 0xF7021977F9CCEAA4ULL, 0xB5F2F89C5026DC37ULL, 0x3BD0BCE5A45A6B5DULL,
- 0x79205D0E0DB05DCEULL, 0xBE317F32F78E067BULL, 0xFCC19ED95E6430E8ULL,
- 0x86B86ED5267CDBD3ULL, 0xC4488F3E8F96ED40ULL, 0x0359AD0275A8B6F5ULL,
- 0x41A94CE9DC428066ULL, 0xCF8B0890283E370CULL, 0x8D7BE97B81D4019FULL,
- 0x4A6ACB477BEA5A2AULL, 0x089A2AACD2006CB9ULL, 0x14DEA25F3AF9026DULL,
- 0x562E43B4931334FEULL, 0x913F6188692D6F4BULL, 0xD3CF8063C0C759D8ULL,
- 0x5DEDC41A34BBEEB2ULL, 0x1F1D25F19D51D821ULL, 0xD80C07CD676F8394ULL,
- 0x9AFCE626CE85B507ULL,
-};
-
-uint64_t bch_crc64_update(uint64_t crc, const void *_data, size_t len)
-{
- const unsigned char *data = _data;
-
- while (len--) {
- int i = ((int) (crc >> 56) ^ *data++) & 0xFF;
- crc = crc_table[i] ^ (crc << 8);
- }
-
- return crc;
-}
-
-uint64_t bch_crc64(const void *data, size_t len)
-{
- uint64_t crc = 0xffffffffffffffffULL;
-
- crc = bch_crc64_update(crc, data, len);
-
- return crc ^ 0xffffffffffffffffULL;
-}
diff --git a/drivers/md/bcache/util.h b/drivers/md/bcache/util.h
index ab3939253b3d..a421b63c0990 100644
--- a/drivers/md/bcache/util.h
+++ b/drivers/md/bcache/util.h
@@ -10,6 +10,7 @@
#include <linux/ratelimit.h>
#include <linux/vmalloc.h>
#include <linux/workqueue.h>
+#include <linux/crc64.h>
#include "closure.h"
@@ -287,10 +288,10 @@ do { \
#define ANYSINT_MAX(t) \
((((t) 1 << (sizeof(t) * 8 - 2)) - (t) 1) * (t) 2 + (t) 1)
-int bch_strtoint_h(const char *, int *);
-int bch_strtouint_h(const char *, unsigned int *);
-int bch_strtoll_h(const char *, long long *);
-int bch_strtoull_h(const char *, unsigned long long *);
+int bch_strtoint_h(const char *cp, int *res);
+int bch_strtouint_h(const char *cp, unsigned int *res);
+int bch_strtoll_h(const char *cp, long long *res);
+int bch_strtoull_h(const char *cp, unsigned long long *res);
static inline int bch_strtol_h(const char *cp, long *res)
{
@@ -346,7 +347,7 @@ static inline int bch_strtoul_h(const char *cp, long *res)
snprintf(buf, size, \
__builtin_types_compatible_p(typeof(var), int) \
? "%i\n" : \
- __builtin_types_compatible_p(typeof(var), unsigned) \
+ __builtin_types_compatible_p(typeof(var), unsigned int) \
? "%u\n" : \
__builtin_types_compatible_p(typeof(var), long) \
? "%li\n" : \
@@ -364,11 +365,6 @@ ssize_t bch_hprint(char *buf, int64_t v);
bool bch_is_zero(const char *p, size_t n);
int bch_parse_uuid(const char *s, char *uuid);
-ssize_t bch_snprint_string_list(char *buf, size_t size, const char * const list[],
- size_t selected);
-
-ssize_t bch_read_string_list(const char *buf, const char * const list[]);
-
struct time_stats {
spinlock_t lock;
/*
@@ -383,7 +379,7 @@ struct time_stats {
void bch_time_stats_update(struct time_stats *stats, uint64_t time);
-static inline unsigned local_clock_us(void)
+static inline unsigned int local_clock_us(void)
{
return local_clock() >> 10;
}
@@ -406,7 +402,8 @@ do { \
__print_time_stat(stats, name, \
average_duration, duration_units); \
sysfs_print(name ## _ ##max_duration ## _ ## duration_units, \
- div_u64((stats)->max_duration, NSEC_PER_ ## duration_units));\
+ div_u64((stats)->max_duration, \
+ NSEC_PER_ ## duration_units)); \
\
sysfs_print(name ## _last_ ## frequency_units, (stats)->last \
? div_s64(local_clock() - (stats)->last, \
@@ -546,10 +543,27 @@ dup: \
#define RB_PREV(ptr, member) \
container_of_or_null(rb_prev(&(ptr)->member), typeof(*ptr), member)
+static inline uint64_t bch_crc64(const void *p, size_t len)
+{
+ uint64_t crc = 0xffffffffffffffffULL;
+
+ crc = crc64_be(crc, p, len);
+ return crc ^ 0xffffffffffffffffULL;
+}
+
+static inline uint64_t bch_crc64_update(uint64_t crc,
+ const void *p,
+ size_t len)
+{
+ crc = crc64_be(crc, p, len);
+ return crc;
+}
+
/* Does linear interpolation between powers of two */
-static inline unsigned fract_exp_two(unsigned x, unsigned fract_bits)
+static inline unsigned int fract_exp_two(unsigned int x,
+ unsigned int fract_bits)
{
- unsigned fract = x & ~(~0 << fract_bits);
+ unsigned int fract = x & ~(~0 << fract_bits);
x >>= fract_bits;
x = 1 << x;
@@ -564,8 +578,4 @@ static inline sector_t bdev_sectors(struct block_device *bdev)
{
return bdev->bd_inode->i_size >> 9;
}
-
-uint64_t bch_crc64_update(uint64_t, const void *, size_t);
-uint64_t bch_crc64(const void *, size_t);
-
#endif /* _BCACHE_UTIL_H */
diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c
index 0083b908392a..2c1b47a599c7 100644
--- a/drivers/md/bcache/writeback.c
+++ b/drivers/md/bcache/writeback.c
@@ -16,6 +16,15 @@
#include <linux/sched/clock.h>
#include <trace/events/bcache.h>
+static void update_gc_after_writeback(struct cache_set *c)
+{
+ if (c->gc_after_writeback != (BCH_ENABLE_AUTO_GC) ||
+ c->gc_stats.in_use < BCH_AUTO_GC_DIRTY_THRESHOLD)
+ return;
+
+ c->gc_after_writeback |= BCH_DO_AUTO_GC;
+}
+
/* Rate limiting */
static uint64_t __calc_target_rate(struct cached_dev *dc)
{
@@ -190,6 +199,7 @@ static void update_writeback_rate(struct work_struct *work)
if (!set_at_max_writeback_rate(c, dc)) {
down_read(&dc->writeback_lock);
__update_writeback_rate(dc);
+ update_gc_after_writeback(c);
up_read(&dc->writeback_lock);
}
}
@@ -214,7 +224,8 @@ static void update_writeback_rate(struct work_struct *work)
smp_mb();
}
-static unsigned writeback_delay(struct cached_dev *dc, unsigned sectors)
+static unsigned int writeback_delay(struct cached_dev *dc,
+ unsigned int sectors)
{
if (test_bit(BCACHE_DEV_DETACHING, &dc->disk.flags) ||
!dc->writeback_percent)
@@ -248,6 +259,7 @@ static void dirty_init(struct keybuf_key *w)
static void dirty_io_destructor(struct closure *cl)
{
struct dirty_io *io = container_of(cl, struct dirty_io, cl);
+
kfree(io);
}
@@ -262,7 +274,7 @@ static void write_dirty_finish(struct closure *cl)
/* This is kind of a dumb way of signalling errors. */
if (KEY_DIRTY(&w->key)) {
int ret;
- unsigned i;
+ unsigned int i;
struct keylist keys;
bch_keylist_init(&keys);
@@ -376,7 +388,7 @@ static void read_dirty_submit(struct closure *cl)
static void read_dirty(struct cached_dev *dc)
{
- unsigned delay = 0;
+ unsigned int delay = 0;
struct keybuf_key *next, *keys[MAX_WRITEBACKS_IN_PASS], *w;
size_t size;
int nk, i;
@@ -441,7 +453,8 @@ static void read_dirty(struct cached_dev *dc)
io = kzalloc(sizeof(struct dirty_io) +
sizeof(struct bio_vec) *
- DIV_ROUND_UP(KEY_SIZE(&w->key), PAGE_SECTORS),
+ DIV_ROUND_UP(KEY_SIZE(&w->key),
+ PAGE_SECTORS),
GFP_KERNEL);
if (!io)
goto err;
@@ -464,7 +477,8 @@ static void read_dirty(struct cached_dev *dc)
down(&dc->in_flight);
- /* We've acquired a semaphore for the maximum
+ /*
+ * We've acquired a semaphore for the maximum
* simultaneous number of writebacks; from here
* everything happens asynchronously.
*/
@@ -497,11 +511,11 @@ err:
/* Scan for dirty data */
-void bcache_dev_sectors_dirty_add(struct cache_set *c, unsigned inode,
+void bcache_dev_sectors_dirty_add(struct cache_set *c, unsigned int inode,
uint64_t offset, int nr_sectors)
{
struct bcache_device *d = c->devices[inode];
- unsigned stripe_offset, stripe, sectors_dirty;
+ unsigned int stripe_offset, stripe, sectors_dirty;
if (!d)
return;
@@ -513,7 +527,7 @@ void bcache_dev_sectors_dirty_add(struct cache_set *c, unsigned inode,
stripe_offset = offset & (d->stripe_size - 1);
while (nr_sectors) {
- int s = min_t(unsigned, abs(nr_sectors),
+ int s = min_t(unsigned int, abs(nr_sectors),
d->stripe_size - stripe_offset);
if (nr_sectors < 0)
@@ -537,7 +551,9 @@ void bcache_dev_sectors_dirty_add(struct cache_set *c, unsigned inode,
static bool dirty_pred(struct keybuf *buf, struct bkey *k)
{
- struct cached_dev *dc = container_of(buf, struct cached_dev, writeback_keys);
+ struct cached_dev *dc = container_of(buf,
+ struct cached_dev,
+ writeback_keys);
BUG_ON(KEY_INODE(k) != dc->disk.id);
@@ -547,7 +563,7 @@ static bool dirty_pred(struct keybuf *buf, struct bkey *k)
static void refill_full_stripes(struct cached_dev *dc)
{
struct keybuf *buf = &dc->writeback_keys;
- unsigned start_stripe, stripe, next_stripe;
+ unsigned int start_stripe, stripe, next_stripe;
bool wrapped = false;
stripe = offset_to_stripe(&dc->disk, KEY_OFFSET(&buf->last_scanned));
@@ -682,6 +698,23 @@ static int bch_writeback_thread(void *arg)
up_write(&dc->writeback_lock);
break;
}
+
+ /*
+ * When dirty data rate is high (e.g. 50%+), there might
+ * be heavy buckets fragmentation after writeback
+ * finished, which hurts following write performance.
+ * If users really care about write performance they
+ * may set BCH_ENABLE_AUTO_GC via sysfs, then when
+ * BCH_DO_AUTO_GC is set, garbage collection thread
+ * will be wake up here. After moving gc, the shrunk
+ * btree and discarded free buckets SSD space may be
+ * helpful for following write requests.
+ */
+ if (c->gc_after_writeback ==
+ (BCH_ENABLE_AUTO_GC|BCH_DO_AUTO_GC)) {
+ c->gc_after_writeback &= ~BCH_DO_AUTO_GC;
+ force_wake_up_gc(c);
+ }
}
up_write(&dc->writeback_lock);
@@ -689,7 +722,7 @@ static int bch_writeback_thread(void *arg)
read_dirty(dc);
if (searched_full_index) {
- unsigned delay = dc->writeback_delay * HZ;
+ unsigned int delay = dc->writeback_delay * HZ;
while (delay &&
!kthread_should_stop() &&
@@ -713,7 +746,7 @@ static int bch_writeback_thread(void *arg)
struct sectors_dirty_init {
struct btree_op op;
- unsigned inode;
+ unsigned int inode;
size_t count;
struct bkey start;
};
@@ -770,7 +803,7 @@ void bch_cached_dev_writeback_init(struct cached_dev *dc)
bch_keybuf_init(&dc->writeback_keys);
dc->writeback_metadata = true;
- dc->writeback_running = true;
+ dc->writeback_running = false;
dc->writeback_percent = 10;
dc->writeback_delay = 30;
atomic_long_set(&dc->writeback_rate.rate, 1024);
@@ -798,6 +831,7 @@ int bch_cached_dev_writeback_start(struct cached_dev *dc)
cached_dev_put(dc);
return PTR_ERR(dc->writeback_thread);
}
+ dc->writeback_running = true;
WARN_ON(test_and_set_bit(BCACHE_DEV_WB_RUNNING, &dc->disk.flags));
schedule_delayed_work(&dc->writeback_rate_update,
diff --git a/drivers/md/bcache/writeback.h b/drivers/md/bcache/writeback.h
index 203056dd23e6..acf9949d8ce5 100644
--- a/drivers/md/bcache/writeback.h
+++ b/drivers/md/bcache/writeback.h
@@ -4,12 +4,17 @@
#define CUTOFF_WRITEBACK 40
#define CUTOFF_WRITEBACK_SYNC 70
+#define CUTOFF_WRITEBACK_MAX 70
+#define CUTOFF_WRITEBACK_SYNC_MAX 90
+
#define MAX_WRITEBACKS_IN_PASS 5
#define MAX_WRITESIZE_IN_PASS 5000 /* *512b */
#define WRITEBACK_RATE_UPDATE_SECS_MAX 60
#define WRITEBACK_RATE_UPDATE_SECS_DEFAULT 5
+#define BCH_AUTO_GC_DIRTY_THRESHOLD 50
+
/*
* 14 (16384ths) is chosen here as something that each backing device
* should be a reasonable fraction of the share, and not to blow up
@@ -27,7 +32,7 @@ static inline uint64_t bcache_dev_sectors_dirty(struct bcache_device *d)
return ret;
}
-static inline unsigned offset_to_stripe(struct bcache_device *d,
+static inline unsigned int offset_to_stripe(struct bcache_device *d,
uint64_t offset)
{
do_div(offset, d->stripe_size);
@@ -36,9 +41,9 @@ static inline unsigned offset_to_stripe(struct bcache_device *d,
static inline bool bcache_dev_stripe_dirty(struct cached_dev *dc,
uint64_t offset,
- unsigned nr_sectors)
+ unsigned int nr_sectors)
{
- unsigned stripe = offset_to_stripe(&dc->disk, offset);
+ unsigned int stripe = offset_to_stripe(&dc->disk, offset);
while (1) {
if (atomic_read(dc->disk.stripe_sectors_dirty + stripe))
@@ -52,14 +57,20 @@ static inline bool bcache_dev_stripe_dirty(struct cached_dev *dc,
}
}
+extern unsigned int bch_cutoff_writeback;
+extern unsigned int bch_cutoff_writeback_sync;
+
static inline bool should_writeback(struct cached_dev *dc, struct bio *bio,
- unsigned cache_mode, bool would_skip)
+ unsigned int cache_mode, bool would_skip)
{
- unsigned in_use = dc->disk.c->gc_stats.in_use;
+ unsigned int in_use = dc->disk.c->gc_stats.in_use;
if (cache_mode != CACHE_MODE_WRITEBACK ||
test_bit(BCACHE_DEV_DETACHING, &dc->disk.flags) ||
- in_use > CUTOFF_WRITEBACK_SYNC)
+ in_use > bch_cutoff_writeback_sync)
+ return false;
+
+ if (bio_op(bio) == REQ_OP_DISCARD)
return false;
if (dc->partial_stripes_expensive &&
@@ -72,7 +83,7 @@ static inline bool should_writeback(struct cached_dev *dc, struct bio *bio,
return (op_is_sync(bio->bi_opf) ||
bio->bi_opf & (REQ_META|REQ_PRIO) ||
- in_use <= CUTOFF_WRITEBACK);
+ in_use <= bch_cutoff_writeback);
}
static inline void bch_writeback_queue(struct cached_dev *dc)
@@ -95,10 +106,11 @@ static inline void bch_writeback_add(struct cached_dev *dc)
}
}
-void bcache_dev_sectors_dirty_add(struct cache_set *, unsigned, uint64_t, int);
+void bcache_dev_sectors_dirty_add(struct cache_set *c, unsigned int inode,
+ uint64_t offset, int nr_sectors);
-void bch_sectors_dirty_init(struct bcache_device *);
-void bch_cached_dev_writeback_init(struct cached_dev *);
-int bch_cached_dev_writeback_start(struct cached_dev *);
+void bch_sectors_dirty_init(struct bcache_device *d);
+void bch_cached_dev_writeback_init(struct cached_dev *dc);
+int bch_cached_dev_writeback_start(struct cached_dev *dc);
#endif
diff --git a/drivers/media/i2c/ov2659.c b/drivers/media/i2c/ov2659.c
index 6e6367214d40..a2f35ab73d89 100644
--- a/drivers/media/i2c/ov2659.c
+++ b/drivers/media/i2c/ov2659.c
@@ -1130,7 +1130,7 @@ static int ov2659_set_fmt(struct v4l2_subdev *sd,
mf = v4l2_subdev_get_try_format(sd, cfg, fmt->pad);
*mf = fmt->format;
#else
- return -ENOTTY;
+ ret = -ENOTTY;
#endif
} else {
s64 val;
diff --git a/drivers/media/pci/cx18/cx18-fileops.c b/drivers/media/pci/cx18/cx18-fileops.c
index 98467b2089fa..099d59b992c1 100644
--- a/drivers/media/pci/cx18/cx18-fileops.c
+++ b/drivers/media/pci/cx18/cx18-fileops.c
@@ -484,7 +484,7 @@ static ssize_t cx18_read_pos(struct cx18_stream *s, char __user *ubuf,
CX18_DEBUG_HI_FILE("read %zd from %s, got %zd\n", count, s->name, rc);
if (rc > 0)
- pos += rc;
+ *pos += rc;
return rc;
}
diff --git a/drivers/media/pci/cx23885/cx23885-dvb.c b/drivers/media/pci/cx23885/cx23885-dvb.c
index 979b66627f60..cc9d43cd5aa1 100644
--- a/drivers/media/pci/cx23885/cx23885-dvb.c
+++ b/drivers/media/pci/cx23885/cx23885-dvb.c
@@ -1460,8 +1460,9 @@ static int dvb_register(struct cx23885_tsport *port)
if (fe0->dvb.frontend != NULL) {
struct i2c_adapter *tun_i2c;
- fe0->dvb.frontend->sec_priv = kmalloc(sizeof(dib7000p_ops), GFP_KERNEL);
- memcpy(fe0->dvb.frontend->sec_priv, &dib7000p_ops, sizeof(dib7000p_ops));
+ fe0->dvb.frontend->sec_priv = kmemdup(&dib7000p_ops, sizeof(dib7000p_ops), GFP_KERNEL);
+ if (!fe0->dvb.frontend->sec_priv)
+ return -ENOMEM;
tun_i2c = dib7000p_ops.get_i2c_master(fe0->dvb.frontend, DIBX000_I2C_INTERFACE_TUNER, 1);
if (!dvb_attach(dib0070_attach, fe0->dvb.frontend, tun_i2c, &dib7070p_dib0070_config))
return -ENODEV;
diff --git a/drivers/media/pci/ivtv/ivtv-fileops.c b/drivers/media/pci/ivtv/ivtv-fileops.c
index c9bd018e53de..e2b19c3eaa87 100644
--- a/drivers/media/pci/ivtv/ivtv-fileops.c
+++ b/drivers/media/pci/ivtv/ivtv-fileops.c
@@ -420,7 +420,7 @@ static ssize_t ivtv_read_pos(struct ivtv_stream *s, char __user *ubuf, size_t co
IVTV_DEBUG_HI_FILE("read %zd from %s, got %zd\n", count, s->name, rc);
if (rc > 0)
- pos += rc;
+ *pos += rc;
return rc;
}
diff --git a/drivers/media/pci/tw5864/tw5864-video.c b/drivers/media/pci/tw5864/tw5864-video.c
index 2a044be729da..0684235b5d2b 100644
--- a/drivers/media/pci/tw5864/tw5864-video.c
+++ b/drivers/media/pci/tw5864/tw5864-video.c
@@ -1394,13 +1394,13 @@ static void tw5864_handle_frame(struct tw5864_h264_frame *frame)
input->vb = NULL;
spin_unlock_irqrestore(&input->slock, flags);
- v4l2_buf = to_vb2_v4l2_buffer(&vb->vb.vb2_buf);
-
if (!vb) { /* Gone because of disabling */
dev_dbg(&dev->pci->dev, "vb is empty, dropping frame\n");
return;
}
+ v4l2_buf = to_vb2_v4l2_buffer(&vb->vb.vb2_buf);
+
/*
* Check for space.
* Mind the overhead of startcode emulation prevention.
diff --git a/drivers/media/platform/davinci/isif.c b/drivers/media/platform/davinci/isif.c
index 5813b49391ed..cf282a679f1f 100644
--- a/drivers/media/platform/davinci/isif.c
+++ b/drivers/media/platform/davinci/isif.c
@@ -886,9 +886,7 @@ static int isif_set_hw_if_params(struct vpfe_hw_if_param *params)
static int isif_config_ycbcr(void)
{
struct isif_ycbcr_config *params = &isif_cfg.ycbcr;
- struct vpss_pg_frame_size frame_size;
u32 modeset = 0, ccdcfg = 0;
- struct vpss_sync_pol sync;
dev_dbg(isif_cfg.dev, "\nStarting isif_config_ycbcr...");
@@ -976,13 +974,6 @@ static int isif_config_ycbcr(void)
/* two fields are interleaved in memory */
regw(0x00000249, SDOFST);
- /* Setup test pattern if enabled */
- if (isif_cfg.bayer.config_params.test_pat_gen) {
- sync.ccdpg_hdpol = params->hd_pol;
- sync.ccdpg_vdpol = params->vd_pol;
- dm365_vpss_set_sync_pol(sync);
- dm365_vpss_set_pg_frame_size(frame_size);
- }
return 0;
}
diff --git a/drivers/media/platform/vivid/vivid-vid-cap.c b/drivers/media/platform/vivid/vivid-vid-cap.c
index a7a366093524..4ca3d600aa84 100644
--- a/drivers/media/platform/vivid/vivid-vid-cap.c
+++ b/drivers/media/platform/vivid/vivid-vid-cap.c
@@ -1007,7 +1007,7 @@ int vivid_vid_cap_s_selection(struct file *file, void *fh, struct v4l2_selection
v4l2_rect_map_inside(&s->r, &dev->fmt_cap_rect);
if (dev->bitmap_cap && (compose->width != s->r.width ||
compose->height != s->r.height)) {
- kfree(dev->bitmap_cap);
+ vfree(dev->bitmap_cap);
dev->bitmap_cap = NULL;
}
*compose = s->r;
diff --git a/drivers/media/radio/wl128x/fmdrv_common.c b/drivers/media/radio/wl128x/fmdrv_common.c
index ab3428bf63fe..2d20d908e280 100644
--- a/drivers/media/radio/wl128x/fmdrv_common.c
+++ b/drivers/media/radio/wl128x/fmdrv_common.c
@@ -489,7 +489,8 @@ int fmc_send_cmd(struct fmdev *fmdev, u8 fm_op, u16 type, void *payload,
return -EIO;
}
/* Send response data to caller */
- if (response != NULL && response_len != NULL && evt_hdr->dlen) {
+ if (response != NULL && response_len != NULL && evt_hdr->dlen &&
+ evt_hdr->dlen <= payload_len) {
/* Skip header info and copy only response data */
skb_pull(skb, sizeof(struct fm_event_msg_hdr));
memcpy(response, skb->data, evt_hdr->dlen);
@@ -583,6 +584,8 @@ static void fm_irq_handle_flag_getcmd_resp(struct fmdev *fmdev)
return;
fm_evt_hdr = (void *)skb->data;
+ if (fm_evt_hdr->dlen > sizeof(fmdev->irq_info.flag))
+ return;
/* Skip header info and copy only response data */
skb_pull(skb, sizeof(struct fm_event_msg_hdr));
@@ -1268,8 +1271,9 @@ static int fm_download_firmware(struct fmdev *fmdev, const u8 *fw_name)
switch (action->type) {
case ACTION_SEND_COMMAND: /* Send */
- if (fmc_send_cmd(fmdev, 0, 0, action->data,
- action->size, NULL, NULL))
+ ret = fmc_send_cmd(fmdev, 0, 0, action->data,
+ action->size, NULL, NULL);
+ if (ret)
goto rel_fw;
cmd_cnt++;
@@ -1308,7 +1312,7 @@ static int load_default_rx_configuration(struct fmdev *fmdev)
static int fm_power_up(struct fmdev *fmdev, u8 mode)
{
u16 payload;
- __be16 asic_id, asic_ver;
+ __be16 asic_id = 0, asic_ver = 0;
int resp_len, ret;
u8 fw_name[50];
diff --git a/drivers/media/rc/serial_ir.c b/drivers/media/rc/serial_ir.c
index 77d5d4cbed0a..ed28f2a3f8ff 100644
--- a/drivers/media/rc/serial_ir.c
+++ b/drivers/media/rc/serial_ir.c
@@ -780,8 +780,6 @@ static void serial_ir_exit(void)
static int __init serial_ir_init_module(void)
{
- int result;
-
switch (type) {
case IR_HOMEBREW:
case IR_IRDEO:
@@ -809,12 +807,7 @@ static int __init serial_ir_init_module(void)
if (sense != -1)
sense = !!sense;
- result = serial_ir_init();
- if (!result)
- return 0;
-
- serial_ir_exit();
- return result;
+ return serial_ir_init();
}
static void __exit serial_ir_exit_module(void)
diff --git a/drivers/media/usb/pvrusb2/pvrusb2-hdw.c b/drivers/media/usb/pvrusb2/pvrusb2-hdw.c
index 44975061b953..ddededc4ced4 100644
--- a/drivers/media/usb/pvrusb2/pvrusb2-hdw.c
+++ b/drivers/media/usb/pvrusb2/pvrusb2-hdw.c
@@ -666,6 +666,8 @@ static int ctrl_get_input(struct pvr2_ctrl *cptr,int *vp)
static int ctrl_check_input(struct pvr2_ctrl *cptr,int v)
{
+ if (v < 0 || v > PVR2_CVAL_INPUT_MAX)
+ return 0;
return ((1 << v) & cptr->hdw->input_allowed_mask) != 0;
}
diff --git a/drivers/media/usb/pvrusb2/pvrusb2-hdw.h b/drivers/media/usb/pvrusb2/pvrusb2-hdw.h
index 25648add77e5..bd2b7a67b732 100644
--- a/drivers/media/usb/pvrusb2/pvrusb2-hdw.h
+++ b/drivers/media/usb/pvrusb2/pvrusb2-hdw.h
@@ -50,6 +50,7 @@
#define PVR2_CVAL_INPUT_COMPOSITE 2
#define PVR2_CVAL_INPUT_SVIDEO 3
#define PVR2_CVAL_INPUT_RADIO 4
+#define PVR2_CVAL_INPUT_MAX PVR2_CVAL_INPUT_RADIO
enum pvr2_config {
pvr2_config_empty, /* No configuration */
diff --git a/drivers/mmc/core/host.c b/drivers/mmc/core/host.c
index 88fa03142e92..81a86b90bd75 100644
--- a/drivers/mmc/core/host.c
+++ b/drivers/mmc/core/host.c
@@ -369,8 +369,6 @@ struct mmc_host *mmc_alloc_host(int extra, struct device *dev)
if (mmc_gpio_alloc(host)) {
put_device(&host->class_dev);
- ida_simple_remove(&mmc_host_ida, host->index);
- kfree(host);
return NULL;
}
diff --git a/drivers/mmc/host/sdhci-acpi.c b/drivers/mmc/host/sdhci-acpi.c
index b3fb155f50e4..dd3cad2d4d65 100644
--- a/drivers/mmc/host/sdhci-acpi.c
+++ b/drivers/mmc/host/sdhci-acpi.c
@@ -128,7 +128,7 @@ static const struct sdhci_acpi_chip sdhci_acpi_chip_int = {
static bool sdhci_acpi_byt(void)
{
static const struct x86_cpu_id byt[] = {
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT1 },
+ { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT },
{}
};
diff --git a/drivers/mtd/devices/docg3.c b/drivers/mtd/devices/docg3.c
index b833e6cc684c..ba1313d258dc 100644
--- a/drivers/mtd/devices/docg3.c
+++ b/drivers/mtd/devices/docg3.c
@@ -1858,8 +1858,8 @@ static int __init doc_set_driver_info(int chip_id, struct mtd_info *mtd)
switch (chip_id) {
case DOC_CHIPID_G3:
- mtd->name = kasprintf(GFP_KERNEL, "docg3.%d",
- docg3->device_id);
+ mtd->name = devm_kasprintf(docg3->dev, GFP_KERNEL, "docg3.%d",
+ docg3->device_id);
if (!mtd->name)
return -ENOMEM;
docg3->max_block = 2047;
@@ -1965,7 +1965,7 @@ nomem3:
nomem2:
kfree(docg3);
nomem1:
- return ERR_PTR(ret);
+ return ret ? ERR_PTR(ret) : NULL;
}
/**
@@ -1979,7 +1979,6 @@ static void doc_release_device(struct mtd_info *mtd)
mtd_device_unregister(mtd);
kfree(docg3->bbt);
kfree(docg3);
- kfree(mtd->name);
kfree(mtd);
}
diff --git a/drivers/mtd/mtdpart.c b/drivers/mtd/mtdpart.c
index e930e9e10254..c5e595157c77 100644
--- a/drivers/mtd/mtdpart.c
+++ b/drivers/mtd/mtdpart.c
@@ -583,7 +583,7 @@ static ssize_t mtd_partition_offset_show(struct device *dev,
{
struct mtd_info *mtd = dev_get_drvdata(dev);
struct mtd_part *part = mtd_to_part(mtd);
- return snprintf(buf, PAGE_SIZE, "%lld\n", part->offset);
+ return snprintf(buf, PAGE_SIZE, "%llu\n", part->offset);
}
static DEVICE_ATTR(offset, S_IRUGO, mtd_partition_offset_show, NULL);
diff --git a/drivers/mtd/spi-nor/intel-spi.c b/drivers/mtd/spi-nor/intel-spi.c
index d655da57587a..445eb08e0299 100644
--- a/drivers/mtd/spi-nor/intel-spi.c
+++ b/drivers/mtd/spi-nor/intel-spi.c
@@ -509,6 +509,10 @@ static ssize_t intel_spi_read(struct spi_nor *nor, loff_t from, size_t len,
while (len > 0) {
block_size = min_t(size_t, len, INTEL_SPI_FIFO_SZ);
+ /* Read cannot cross 4K boundary */
+ block_size = min_t(loff_t, from + block_size,
+ round_up(from + 1, SZ_4K)) - from;
+
writel(from, ispi->base + FADDR);
val = readl(ispi->base + HSFSTS_CTL);
@@ -559,6 +563,10 @@ static ssize_t intel_spi_write(struct spi_nor *nor, loff_t to, size_t len,
while (len > 0) {
block_size = min_t(size_t, len, INTEL_SPI_FIFO_SZ);
+ /* Write cannot cross 4K boundary */
+ block_size = min_t(loff_t, to + block_size,
+ round_up(to + 1, SZ_4K)) - to;
+
writel(to, ispi->base + FADDR);
val = readl(ispi->base + HSFSTS_CTL);
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 1e60c84da5dc..0d17d5b6e744 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -118,7 +118,7 @@ static int init_sub_crq_irqs(struct ibmvnic_adapter *adapter);
static int ibmvnic_init(struct ibmvnic_adapter *);
static int ibmvnic_reset_init(struct ibmvnic_adapter *);
static void release_crq_queue(struct ibmvnic_adapter *);
-static int __ibmvnic_set_mac(struct net_device *netdev, struct sockaddr *p);
+static int __ibmvnic_set_mac(struct net_device *, u8 *);
static int init_crq_queue(struct ibmvnic_adapter *adapter);
static int send_query_phys_parms(struct ibmvnic_adapter *adapter);
@@ -852,11 +852,7 @@ static int ibmvnic_login(struct net_device *netdev)
}
} while (retry);
- /* handle pending MAC address changes after successful login */
- if (adapter->mac_change_pending) {
- __ibmvnic_set_mac(netdev, &adapter->desired.mac);
- adapter->mac_change_pending = false;
- }
+ __ibmvnic_set_mac(netdev, adapter->mac_addr);
return 0;
}
@@ -1118,7 +1114,6 @@ static int ibmvnic_open(struct net_device *netdev)
}
rc = __ibmvnic_open(netdev);
- netif_carrier_on(netdev);
return rc;
}
@@ -1689,28 +1684,40 @@ static void ibmvnic_set_multi(struct net_device *netdev)
}
}
-static int __ibmvnic_set_mac(struct net_device *netdev, struct sockaddr *p)
+static int __ibmvnic_set_mac(struct net_device *netdev, u8 *dev_addr)
{
struct ibmvnic_adapter *adapter = netdev_priv(netdev);
- struct sockaddr *addr = p;
union ibmvnic_crq crq;
int rc;
- if (!is_valid_ether_addr(addr->sa_data))
- return -EADDRNOTAVAIL;
+ if (!is_valid_ether_addr(dev_addr)) {
+ rc = -EADDRNOTAVAIL;
+ goto err;
+ }
memset(&crq, 0, sizeof(crq));
crq.change_mac_addr.first = IBMVNIC_CRQ_CMD;
crq.change_mac_addr.cmd = CHANGE_MAC_ADDR;
- ether_addr_copy(&crq.change_mac_addr.mac_addr[0], addr->sa_data);
+ ether_addr_copy(&crq.change_mac_addr.mac_addr[0], dev_addr);
init_completion(&adapter->fw_done);
rc = ibmvnic_send_crq(adapter, &crq);
- if (rc)
- return rc;
+ if (rc) {
+ rc = -EIO;
+ goto err;
+ }
+
wait_for_completion(&adapter->fw_done);
/* netdev->dev_addr is changed in handle_change_mac_rsp function */
- return adapter->fw_done_rc ? -EIO : 0;
+ if (adapter->fw_done_rc) {
+ rc = -EIO;
+ goto err;
+ }
+
+ return 0;
+err:
+ ether_addr_copy(adapter->mac_addr, netdev->dev_addr);
+ return rc;
}
static int ibmvnic_set_mac(struct net_device *netdev, void *p)
@@ -1719,13 +1726,10 @@ static int ibmvnic_set_mac(struct net_device *netdev, void *p)
struct sockaddr *addr = p;
int rc;
- if (adapter->state == VNIC_PROBED) {
- memcpy(&adapter->desired.mac, addr, sizeof(struct sockaddr));
- adapter->mac_change_pending = true;
- return 0;
- }
-
- rc = __ibmvnic_set_mac(netdev, addr);
+ rc = 0;
+ ether_addr_copy(adapter->mac_addr, addr->sa_data);
+ if (adapter->state != VNIC_PROBED)
+ rc = __ibmvnic_set_mac(netdev, addr->sa_data);
return rc;
}
@@ -1862,8 +1866,6 @@ static int do_reset(struct ibmvnic_adapter *adapter,
adapter->reset_reason != VNIC_RESET_CHANGE_PARAM)
call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, netdev);
- netif_carrier_on(netdev);
-
return 0;
}
@@ -1933,8 +1935,6 @@ static int do_hard_reset(struct ibmvnic_adapter *adapter,
return 0;
}
- netif_carrier_on(netdev);
-
return 0;
}
@@ -3938,8 +3938,8 @@ static int handle_change_mac_rsp(union ibmvnic_crq *crq,
dev_err(dev, "Error %ld in CHANGE_MAC_ADDR_RSP\n", rc);
goto out;
}
- memcpy(netdev->dev_addr, &crq->change_mac_addr_rsp.mac_addr[0],
- ETH_ALEN);
+ ether_addr_copy(netdev->dev_addr,
+ &crq->change_mac_addr_rsp.mac_addr[0]);
out:
complete(&adapter->fw_done);
return rc;
@@ -4476,6 +4476,10 @@ static void ibmvnic_handle_crq(union ibmvnic_crq *crq,
crq->link_state_indication.phys_link_state;
adapter->logical_link_state =
crq->link_state_indication.logical_link_state;
+ if (adapter->phys_link_state && adapter->logical_link_state)
+ netif_carrier_on(netdev);
+ else
+ netif_carrier_off(netdev);
break;
case CHANGE_MAC_ADDR_RSP:
netdev_dbg(netdev, "Got MAC address change Response\n");
@@ -4852,8 +4856,6 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id)
init_completion(&adapter->init_done);
adapter->resetting = false;
- adapter->mac_change_pending = false;
-
do {
rc = init_crq_queue(adapter);
if (rc) {
diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h
index d5260a206708..8e328d70ceb0 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.h
+++ b/drivers/net/ethernet/ibm/ibmvnic.h
@@ -967,7 +967,6 @@ struct ibmvnic_tunables {
u64 rx_entries;
u64 tx_entries;
u64 mtu;
- struct sockaddr mac;
};
struct ibmvnic_adapter {
@@ -1089,7 +1088,6 @@ struct ibmvnic_adapter {
bool resetting;
bool napi_enabled, from_passive_init;
- bool mac_change_pending;
bool failover_pending;
bool force_reset_recovery;
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 4ec8f1b7b822..c51f8eddc14c 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1203,6 +1203,7 @@ static const struct usb_device_id products[] = {
{QMI_FIXED_INTF(0x19d2, 0x2002, 4)}, /* ZTE (Vodafone) K3765-Z */
{QMI_FIXED_INTF(0x2001, 0x7e19, 4)}, /* D-Link DWM-221 B1 */
{QMI_FIXED_INTF(0x2001, 0x7e35, 4)}, /* D-Link DWM-222 */
+ {QMI_FIXED_INTF(0x2020, 0x2031, 4)}, /* Olicard 600 */
{QMI_FIXED_INTF(0x2020, 0x2033, 4)}, /* BroadMobi BM806U */
{QMI_FIXED_INTF(0x0f3d, 0x68a2, 8)}, /* Sierra Wireless MC7700 */
{QMI_FIXED_INTF(0x114f, 0x68a2, 8)}, /* Sierra Wireless MC7750 */
diff --git a/drivers/net/wireless/atmel/at76c50x-usb.c b/drivers/net/wireless/atmel/at76c50x-usb.c
index 09defbcedd5e..f39ac5d515bb 100644
--- a/drivers/net/wireless/atmel/at76c50x-usb.c
+++ b/drivers/net/wireless/atmel/at76c50x-usb.c
@@ -2585,8 +2585,8 @@ static int __init at76_mod_init(void)
if (result < 0)
printk(KERN_ERR DRIVER_NAME
": usb_register failed (status %d)\n", result);
-
- led_trigger_register_simple("at76_usb-tx", &ledtrig_tx);
+ else
+ led_trigger_register_simple("at76_usb-tx", &ledtrig_tx);
return result;
}
diff --git a/drivers/net/wireless/broadcom/b43/phy_lp.c b/drivers/net/wireless/broadcom/b43/phy_lp.c
index 6922cbb99a04..5a0699fb4b9a 100644
--- a/drivers/net/wireless/broadcom/b43/phy_lp.c
+++ b/drivers/net/wireless/broadcom/b43/phy_lp.c
@@ -1834,7 +1834,7 @@ static void lpphy_papd_cal(struct b43_wldev *dev, struct lpphy_tx_gains gains,
static void lpphy_papd_cal_txpwr(struct b43_wldev *dev)
{
struct b43_phy_lp *lpphy = dev->phy.lp;
- struct lpphy_tx_gains gains, oldgains;
+ struct lpphy_tx_gains oldgains;
int old_txpctl, old_afe_ovr, old_rf, old_bbmult;
lpphy_read_tx_pctl_mode_from_hardware(dev);
@@ -1848,9 +1848,9 @@ static void lpphy_papd_cal_txpwr(struct b43_wldev *dev)
lpphy_set_tx_power_control(dev, B43_LPPHY_TXPCTL_OFF);
if (dev->dev->chip_id == 0x4325 && dev->dev->chip_rev == 0)
- lpphy_papd_cal(dev, gains, 0, 1, 30);
+ lpphy_papd_cal(dev, oldgains, 0, 1, 30);
else
- lpphy_papd_cal(dev, gains, 0, 1, 65);
+ lpphy_papd_cal(dev, oldgains, 0, 1, 65);
if (old_afe_ovr)
lpphy_set_tx_gains(dev, oldgains);
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/vendor.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/vendor.c
index 8eff2753abad..d493021f6031 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/vendor.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/vendor.c
@@ -35,9 +35,10 @@ static int brcmf_cfg80211_vndr_cmds_dcmd_handler(struct wiphy *wiphy,
struct brcmf_if *ifp;
const struct brcmf_vndr_dcmd_hdr *cmdhdr = data;
struct sk_buff *reply;
- int ret, payload, ret_len;
+ unsigned int payload, ret_len;
void *dcmd_buf = NULL, *wr_pointer;
u16 msglen, maxmsglen = PAGE_SIZE - 0x100;
+ int ret;
if (len < sizeof(*cmdhdr)) {
brcmf_err("vendor command too short: %d\n", len);
@@ -65,7 +66,7 @@ static int brcmf_cfg80211_vndr_cmds_dcmd_handler(struct wiphy *wiphy,
brcmf_err("oversize return buffer %d\n", ret_len);
ret_len = BRCMF_DCMD_MAXLEN;
}
- payload = max(ret_len, len) + 1;
+ payload = max_t(unsigned int, ret_len, len) + 1;
dcmd_buf = vzalloc(payload);
if (NULL == dcmd_buf)
return -ENOMEM;
diff --git a/drivers/net/wireless/marvell/mwifiex/cfg80211.c b/drivers/net/wireless/marvell/mwifiex/cfg80211.c
index 1a9cbaa53540..e55af3ab0803 100644
--- a/drivers/net/wireless/marvell/mwifiex/cfg80211.c
+++ b/drivers/net/wireless/marvell/mwifiex/cfg80211.c
@@ -4035,16 +4035,20 @@ static int mwifiex_tm_cmd(struct wiphy *wiphy, struct wireless_dev *wdev,
if (mwifiex_send_cmd(priv, 0, 0, 0, hostcmd, true)) {
dev_err(priv->adapter->dev, "Failed to process hostcmd\n");
+ kfree(hostcmd);
return -EFAULT;
}
/* process hostcmd response*/
skb = cfg80211_testmode_alloc_reply_skb(wiphy, hostcmd->len);
- if (!skb)
+ if (!skb) {
+ kfree(hostcmd);
return -ENOMEM;
+ }
err = nla_put(skb, MWIFIEX_TM_ATTR_DATA,
hostcmd->len, hostcmd->cmd);
if (err) {
+ kfree(hostcmd);
kfree_skb(skb);
return -EMSGSIZE;
}
diff --git a/drivers/net/wireless/marvell/mwifiex/cfp.c b/drivers/net/wireless/marvell/mwifiex/cfp.c
index 1ff22055e54f..9ddaa767ea74 100644
--- a/drivers/net/wireless/marvell/mwifiex/cfp.c
+++ b/drivers/net/wireless/marvell/mwifiex/cfp.c
@@ -533,5 +533,8 @@ u8 mwifiex_adjust_data_rate(struct mwifiex_private *priv,
rate_index = (rx_rate > MWIFIEX_RATE_INDEX_OFDM0) ?
rx_rate - 1 : rx_rate;
+ if (rate_index >= MWIFIEX_MAX_AC_RX_RATES)
+ rate_index = MWIFIEX_MAX_AC_RX_RATES - 1;
+
return rate_index;
}
diff --git a/drivers/net/wireless/marvell/mwl8k.c b/drivers/net/wireless/marvell/mwl8k.c
index e813b2ca740c..a87ccf9ceb67 100644
--- a/drivers/net/wireless/marvell/mwl8k.c
+++ b/drivers/net/wireless/marvell/mwl8k.c
@@ -436,6 +436,9 @@ static const struct ieee80211_rate mwl8k_rates_50[] = {
#define MWL8K_CMD_UPDATE_STADB 0x1123
#define MWL8K_CMD_BASTREAM 0x1125
+#define MWL8K_LEGACY_5G_RATE_OFFSET \
+ (ARRAY_SIZE(mwl8k_rates_24) - ARRAY_SIZE(mwl8k_rates_50))
+
static const char *mwl8k_cmd_name(__le16 cmd, char *buf, int bufsize)
{
u16 command = le16_to_cpu(cmd);
@@ -1011,8 +1014,9 @@ mwl8k_rxd_ap_process(void *_rxd, struct ieee80211_rx_status *status,
if (rxd->channel > 14) {
status->band = NL80211_BAND_5GHZ;
- if (!(status->encoding == RX_ENC_HT))
- status->rate_idx -= 5;
+ if (!(status->encoding == RX_ENC_HT) &&
+ status->rate_idx >= MWL8K_LEGACY_5G_RATE_OFFSET)
+ status->rate_idx -= MWL8K_LEGACY_5G_RATE_OFFSET;
} else {
status->band = NL80211_BAND_2GHZ;
}
@@ -1119,8 +1123,9 @@ mwl8k_rxd_sta_process(void *_rxd, struct ieee80211_rx_status *status,
if (rxd->channel > 14) {
status->band = NL80211_BAND_5GHZ;
- if (!(status->encoding == RX_ENC_HT))
- status->rate_idx -= 5;
+ if (!(status->encoding == RX_ENC_HT) &&
+ status->rate_idx >= MWL8K_LEGACY_5G_RATE_OFFSET)
+ status->rate_idx -= MWL8K_LEGACY_5G_RATE_OFFSET;
} else {
status->band = NL80211_BAND_2GHZ;
}
diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00.h b/drivers/net/wireless/ralink/rt2x00/rt2x00.h
index 1bc353eafe37..d61ce05c4066 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2x00.h
+++ b/drivers/net/wireless/ralink/rt2x00/rt2x00.h
@@ -672,7 +672,6 @@ enum rt2x00_state_flags {
CONFIG_CHANNEL_HT40,
CONFIG_POWERSAVING,
CONFIG_HT_DISABLED,
- CONFIG_QOS_DISABLED,
CONFIG_MONITORING,
/*
diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00mac.c b/drivers/net/wireless/ralink/rt2x00/rt2x00mac.c
index 6fe0c6abe0d6..84728c281f46 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2x00mac.c
+++ b/drivers/net/wireless/ralink/rt2x00/rt2x00mac.c
@@ -670,19 +670,9 @@ void rt2x00mac_bss_info_changed(struct ieee80211_hw *hw,
rt2x00dev->intf_associated--;
rt2x00leds_led_assoc(rt2x00dev, !!rt2x00dev->intf_associated);
-
- clear_bit(CONFIG_QOS_DISABLED, &rt2x00dev->flags);
}
/*
- * Check for access point which do not support 802.11e . We have to
- * generate data frames sequence number in S/W for such AP, because
- * of H/W bug.
- */
- if (changes & BSS_CHANGED_QOS && !bss_conf->qos)
- set_bit(CONFIG_QOS_DISABLED, &rt2x00dev->flags);
-
- /*
* When the erp information has changed, we should perform
* additional configuration steps. For all other changes we are done.
*/
diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00queue.c b/drivers/net/wireless/ralink/rt2x00/rt2x00queue.c
index e1660b92b20c..1b0f2da8a10d 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2x00queue.c
+++ b/drivers/net/wireless/ralink/rt2x00/rt2x00queue.c
@@ -200,15 +200,18 @@ static void rt2x00queue_create_tx_descriptor_seq(struct rt2x00_dev *rt2x00dev,
if (!rt2x00_has_cap_flag(rt2x00dev, REQUIRE_SW_SEQNO)) {
/*
* rt2800 has a H/W (or F/W) bug, device incorrectly increase
- * seqno on retransmited data (non-QOS) frames. To workaround
- * the problem let's generate seqno in software if QOS is
- * disabled.
+ * seqno on retransmitted data (non-QOS) and management frames.
+ * To workaround the problem let's generate seqno in software.
+ * Except for beacons which are transmitted periodically by H/W
+ * hence hardware has to assign seqno for them.
*/
- if (test_bit(CONFIG_QOS_DISABLED, &rt2x00dev->flags))
- __clear_bit(ENTRY_TXD_GENERATE_SEQ, &txdesc->flags);
- else
+ if (ieee80211_is_beacon(hdr->frame_control)) {
+ __set_bit(ENTRY_TXD_GENERATE_SEQ, &txdesc->flags);
/* H/W will generate sequence number */
return;
+ }
+
+ __clear_bit(ENTRY_TXD_GENERATE_SEQ, &txdesc->flags);
}
/*
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/hw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/hw.c
index 859c045bd37c..c192d65a3d76 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/hw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/hw.c
@@ -1699,6 +1699,7 @@ static void _rtl8723e_read_adapter_info(struct ieee80211_hw *hw,
rtlhal->oem_id = RT_CID_819X_LENOVO;
break;
}
+ break;
case 0x1025:
rtlhal->oem_id = RT_CID_819X_ACER;
break;
diff --git a/drivers/pci/pci-mid.c b/drivers/pci/pci-mid.c
index 1c4af7227bca..a8e15e8c474c 100644
--- a/drivers/pci/pci-mid.c
+++ b/drivers/pci/pci-mid.c
@@ -71,8 +71,8 @@ static const struct pci_platform_pm_ops mid_pci_platform_pm = {
* arch/x86/platform/intel-mid/pwr.c.
*/
static const struct x86_cpu_id lpss_cpu_ids[] = {
- ICPU(INTEL_FAM6_ATOM_PENWELL),
- ICPU(INTEL_FAM6_ATOM_MERRIFIELD),
+ ICPU(INTEL_FAM6_ATOM_SALTWELL_MID),
+ ICPU(INTEL_FAM6_ATOM_SILVERMONT_MID),
{}
};
diff --git a/drivers/phy/allwinner/phy-sun4i-usb.c b/drivers/phy/allwinner/phy-sun4i-usb.c
index a8d465a52041..666d0cbda598 100644
--- a/drivers/phy/allwinner/phy-sun4i-usb.c
+++ b/drivers/phy/allwinner/phy-sun4i-usb.c
@@ -506,6 +506,7 @@ static void sun4i_usb_phy0_id_vbus_det_scan(struct work_struct *work)
struct sun4i_usb_phy_data *data =
container_of(work, struct sun4i_usb_phy_data, detect.work);
struct phy *phy0 = data->phys[0].phy;
+ struct sun4i_usb_phy *phy = phy_get_drvdata(phy0);
bool force_session_end, id_notify = false, vbus_notify = false;
int id_det, vbus_det;
@@ -562,6 +563,9 @@ static void sun4i_usb_phy0_id_vbus_det_scan(struct work_struct *work)
mutex_unlock(&phy0->mutex);
}
+ /* Enable PHY0 passby for host mode only. */
+ sun4i_usb_phy_passby(phy, !id_det);
+
/* Re-route PHY0 if necessary */
if (data->cfg->phy0_dual_route)
sun4i_usb_phy0_reroute(data, id_det);
diff --git a/drivers/platform/x86/alienware-wmi.c b/drivers/platform/x86/alienware-wmi.c
index ff45b5651161..b825fb554b7f 100644
--- a/drivers/platform/x86/alienware-wmi.c
+++ b/drivers/platform/x86/alienware-wmi.c
@@ -569,7 +569,7 @@ static ssize_t show_hdmi_source(struct device *dev,
return scnprintf(buf, PAGE_SIZE,
"input [gpu] unknown\n");
}
- pr_err("alienware-wmi: unknown HDMI source status: %d\n", out_data);
+ pr_err("alienware-wmi: unknown HDMI source status: %u\n", status);
return scnprintf(buf, PAGE_SIZE, "input gpu [unknown]\n");
}
diff --git a/drivers/platform/x86/dell-rbtn.c b/drivers/platform/x86/dell-rbtn.c
index dcd9f40a4b18..45d9355d0c57 100644
--- a/drivers/platform/x86/dell-rbtn.c
+++ b/drivers/platform/x86/dell-rbtn.c
@@ -18,6 +18,8 @@
#include <linux/rfkill.h>
#include <linux/input.h>
+#include "dell-rbtn.h"
+
enum rbtn_type {
RBTN_UNKNOWN,
RBTN_TOGGLE,
diff --git a/drivers/platform/x86/intel_int0002_vgpio.c b/drivers/platform/x86/intel_int0002_vgpio.c
index 92dc230ef5b2..08107731afe0 100644
--- a/drivers/platform/x86/intel_int0002_vgpio.c
+++ b/drivers/platform/x86/intel_int0002_vgpio.c
@@ -60,7 +60,7 @@ static const struct x86_cpu_id int0002_cpu_ids[] = {
/*
* Limit ourselves to Cherry Trail for now, until testing shows we
* need to handle the INT0002 device on Baytrail too.
- * ICPU(INTEL_FAM6_ATOM_SILVERMONT1), * Valleyview, Bay Trail *
+ * ICPU(INTEL_FAM6_ATOM_SILVERMONT), * Valleyview, Bay Trail *
*/
ICPU(INTEL_FAM6_ATOM_AIRMONT), /* Braswell, Cherry Trail */
{}
diff --git a/drivers/platform/x86/intel_mid_powerbtn.c b/drivers/platform/x86/intel_mid_powerbtn.c
index 871cfa682519..ee45d61127f1 100644
--- a/drivers/platform/x86/intel_mid_powerbtn.c
+++ b/drivers/platform/x86/intel_mid_powerbtn.c
@@ -125,8 +125,8 @@ static struct mid_pb_ddata mrfld_ddata = {
{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (kernel_ulong_t)&ddata }
static const struct x86_cpu_id mid_pb_cpu_ids[] = {
- ICPU(INTEL_FAM6_ATOM_PENWELL, mfld_ddata),
- ICPU(INTEL_FAM6_ATOM_MERRIFIELD, mrfld_ddata),
+ ICPU(INTEL_FAM6_ATOM_SALTWELL_MID, mfld_ddata),
+ ICPU(INTEL_FAM6_ATOM_SILVERMONT_MID, mrfld_ddata),
{}
};
diff --git a/drivers/platform/x86/intel_pmc_ipc.c b/drivers/platform/x86/intel_pmc_ipc.c
index e4d4dfe3e1d1..a9d6c7c2a22a 100644
--- a/drivers/platform/x86/intel_pmc_ipc.c
+++ b/drivers/platform/x86/intel_pmc_ipc.c
@@ -757,13 +757,17 @@ static int ipc_create_pmc_devices(void)
if (ret) {
dev_err(ipcdev.dev, "Failed to add punit platform device\n");
platform_device_unregister(ipcdev.tco_dev);
+ return ret;
}
if (!ipcdev.telem_res_inval) {
ret = ipc_create_telemetry_device();
- if (ret)
+ if (ret) {
dev_warn(ipcdev.dev,
"Failed to add telemetry platform device\n");
+ platform_device_unregister(ipcdev.punit_dev);
+ platform_device_unregister(ipcdev.tco_dev);
+ }
}
return ret;
diff --git a/drivers/platform/x86/intel_punit_ipc.c b/drivers/platform/x86/intel_punit_ipc.c
index b5b890127479..a47a41fc10ad 100644
--- a/drivers/platform/x86/intel_punit_ipc.c
+++ b/drivers/platform/x86/intel_punit_ipc.c
@@ -252,28 +252,28 @@ static int intel_punit_get_bars(struct platform_device *pdev)
* - GTDRIVER_IPC BASE_IFACE
*/
res = platform_get_resource(pdev, IORESOURCE_MEM, 2);
- if (res && resource_size(res) > 1) {
+ if (res) {
addr = devm_ioremap_resource(&pdev->dev, res);
if (!IS_ERR(addr))
punit_ipcdev->base[ISPDRIVER_IPC][BASE_DATA] = addr;
}
res = platform_get_resource(pdev, IORESOURCE_MEM, 3);
- if (res && resource_size(res) > 1) {
+ if (res) {
addr = devm_ioremap_resource(&pdev->dev, res);
if (!IS_ERR(addr))
punit_ipcdev->base[ISPDRIVER_IPC][BASE_IFACE] = addr;
}
res = platform_get_resource(pdev, IORESOURCE_MEM, 4);
- if (res && resource_size(res) > 1) {
+ if (res) {
addr = devm_ioremap_resource(&pdev->dev, res);
if (!IS_ERR(addr))
punit_ipcdev->base[GTDRIVER_IPC][BASE_DATA] = addr;
}
res = platform_get_resource(pdev, IORESOURCE_MEM, 5);
- if (res && resource_size(res) > 1) {
+ if (res) {
addr = devm_ioremap_resource(&pdev->dev, res);
if (!IS_ERR(addr))
punit_ipcdev->base[GTDRIVER_IPC][BASE_IFACE] = addr;
diff --git a/drivers/platform/x86/pmc_atom.c b/drivers/platform/x86/pmc_atom.c
index 75f69cf0d45f..50f2a125cd2c 100644
--- a/drivers/platform/x86/pmc_atom.c
+++ b/drivers/platform/x86/pmc_atom.c
@@ -426,7 +426,7 @@ static int pmc_dbgfs_register(struct pmc_dev *pmc)
* Some systems need one or more of their pmc_plt_clks to be
* marked as critical.
*/
-static const struct dmi_system_id critclk_systems[] __initconst = {
+static const struct dmi_system_id critclk_systems[] = {
{
.ident = "MPL CEC1x",
.matches = {
diff --git a/drivers/platform/x86/sony-laptop.c b/drivers/platform/x86/sony-laptop.c
index 07666dd1ad60..a4134a0c3e9b 100644
--- a/drivers/platform/x86/sony-laptop.c
+++ b/drivers/platform/x86/sony-laptop.c
@@ -4424,14 +4424,16 @@ sony_pic_read_possible_resource(struct acpi_resource *resource, void *context)
}
return AE_OK;
}
+
+ case ACPI_RESOURCE_TYPE_END_TAG:
+ return AE_OK;
+
default:
dprintk("Resource %d isn't an IRQ nor an IO port\n",
resource->type);
+ return AE_CTRL_TERMINATE;
- case ACPI_RESOURCE_TYPE_END_TAG:
- return AE_OK;
}
- return AE_CTRL_TERMINATE;
}
static int sony_pic_possible_resources(struct acpi_device *device)
diff --git a/drivers/powercap/intel_rapl.c b/drivers/powercap/intel_rapl.c
index 9ff30d1cddf6..225b50f01a13 100644
--- a/drivers/powercap/intel_rapl.c
+++ b/drivers/powercap/intel_rapl.c
@@ -1159,13 +1159,13 @@ static const struct x86_cpu_id rapl_ids[] __initconst = {
RAPL_CPU(INTEL_FAM6_KABYLAKE_MOBILE, rapl_defaults_core),
RAPL_CPU(INTEL_FAM6_KABYLAKE_DESKTOP, rapl_defaults_core),
- RAPL_CPU(INTEL_FAM6_ATOM_SILVERMONT1, rapl_defaults_byt),
+ RAPL_CPU(INTEL_FAM6_ATOM_SILVERMONT, rapl_defaults_byt),
RAPL_CPU(INTEL_FAM6_ATOM_AIRMONT, rapl_defaults_cht),
- RAPL_CPU(INTEL_FAM6_ATOM_MERRIFIELD, rapl_defaults_tng),
- RAPL_CPU(INTEL_FAM6_ATOM_MOOREFIELD, rapl_defaults_ann),
+ RAPL_CPU(INTEL_FAM6_ATOM_SILVERMONT_MID,rapl_defaults_tng),
+ RAPL_CPU(INTEL_FAM6_ATOM_AIRMONT_MID, rapl_defaults_ann),
RAPL_CPU(INTEL_FAM6_ATOM_GOLDMONT, rapl_defaults_core),
- RAPL_CPU(INTEL_FAM6_ATOM_GEMINI_LAKE, rapl_defaults_core),
- RAPL_CPU(INTEL_FAM6_ATOM_DENVERTON, rapl_defaults_core),
+ RAPL_CPU(INTEL_FAM6_ATOM_GOLDMONT_PLUS, rapl_defaults_core),
+ RAPL_CPU(INTEL_FAM6_ATOM_GOLDMONT_X, rapl_defaults_core),
RAPL_CPU(INTEL_FAM6_ATOM_TREMONT_X, rapl_defaults_core),
RAPL_CPU(INTEL_FAM6_XEON_PHI_KNL, rapl_defaults_hsw_server),
diff --git a/drivers/pwm/core.c b/drivers/pwm/core.c
index a0860b30bd93..f125bfa5c752 100644
--- a/drivers/pwm/core.c
+++ b/drivers/pwm/core.c
@@ -311,10 +311,12 @@ int pwmchip_add_with_polarity(struct pwm_chip *chip,
if (IS_ENABLED(CONFIG_OF))
of_pwmchip_add(chip);
- pwmchip_sysfs_export(chip);
-
out:
mutex_unlock(&pwm_lock);
+
+ if (!ret)
+ pwmchip_sysfs_export(chip);
+
return ret;
}
EXPORT_SYMBOL_GPL(pwmchip_add_with_polarity);
@@ -348,7 +350,7 @@ int pwmchip_remove(struct pwm_chip *chip)
unsigned int i;
int ret = 0;
- pwmchip_sysfs_unexport_children(chip);
+ pwmchip_sysfs_unexport(chip);
mutex_lock(&pwm_lock);
@@ -368,8 +370,6 @@ int pwmchip_remove(struct pwm_chip *chip)
free_pwms(chip);
- pwmchip_sysfs_unexport(chip);
-
out:
mutex_unlock(&pwm_lock);
return ret;
diff --git a/drivers/pwm/pwm-meson.c b/drivers/pwm/pwm-meson.c
index 0b0754e11a19..00ce2a4f58e5 100644
--- a/drivers/pwm/pwm-meson.c
+++ b/drivers/pwm/pwm-meson.c
@@ -110,6 +110,10 @@ struct meson_pwm {
const struct meson_pwm_data *data;
void __iomem *base;
u8 inverter_mask;
+ /*
+ * Protects register (write) access to the REG_MISC_AB register
+ * that is shared between the two PWMs.
+ */
spinlock_t lock;
};
@@ -183,7 +187,7 @@ static int meson_pwm_calc(struct meson_pwm *meson,
do_div(fin_ps, fin_freq);
/* Calc pre_div with the period */
- for (pre_div = 0; pre_div < MISC_CLK_DIV_MASK; pre_div++) {
+ for (pre_div = 0; pre_div <= MISC_CLK_DIV_MASK; pre_div++) {
cnt = DIV_ROUND_CLOSEST_ULL((u64)period * 1000,
fin_ps * (pre_div + 1));
dev_dbg(meson->chip.dev, "fin_ps=%llu pre_div=%u cnt=%u\n",
@@ -192,7 +196,7 @@ static int meson_pwm_calc(struct meson_pwm *meson,
break;
}
- if (pre_div == MISC_CLK_DIV_MASK) {
+ if (pre_div > MISC_CLK_DIV_MASK) {
dev_err(meson->chip.dev, "unable to get period pre_div\n");
return -EINVAL;
}
@@ -234,6 +238,7 @@ static void meson_pwm_enable(struct meson_pwm *meson,
{
u32 value, clk_shift, clk_enable, enable;
unsigned int offset;
+ unsigned long flags;
switch (id) {
case 0:
@@ -254,6 +259,8 @@ static void meson_pwm_enable(struct meson_pwm *meson,
return;
}
+ spin_lock_irqsave(&meson->lock, flags);
+
value = readl(meson->base + REG_MISC_AB);
value &= ~(MISC_CLK_DIV_MASK << clk_shift);
value |= channel->pre_div << clk_shift;
@@ -266,11 +273,14 @@ static void meson_pwm_enable(struct meson_pwm *meson,
value = readl(meson->base + REG_MISC_AB);
value |= enable;
writel(value, meson->base + REG_MISC_AB);
+
+ spin_unlock_irqrestore(&meson->lock, flags);
}
static void meson_pwm_disable(struct meson_pwm *meson, unsigned int id)
{
u32 value, enable;
+ unsigned long flags;
switch (id) {
case 0:
@@ -285,9 +295,13 @@ static void meson_pwm_disable(struct meson_pwm *meson, unsigned int id)
return;
}
+ spin_lock_irqsave(&meson->lock, flags);
+
value = readl(meson->base + REG_MISC_AB);
value &= ~enable;
writel(value, meson->base + REG_MISC_AB);
+
+ spin_unlock_irqrestore(&meson->lock, flags);
}
static int meson_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm,
@@ -295,29 +309,21 @@ static int meson_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm,
{
struct meson_pwm_channel *channel = pwm_get_chip_data(pwm);
struct meson_pwm *meson = to_meson_pwm(chip);
- unsigned long flags;
int err = 0;
if (!state)
return -EINVAL;
- spin_lock_irqsave(&meson->lock, flags);
-
if (!state->enabled) {
meson_pwm_disable(meson, pwm->hwpwm);
channel->state.enabled = false;
- goto unlock;
+ return 0;
}
if (state->period != channel->state.period ||
state->duty_cycle != channel->state.duty_cycle ||
state->polarity != channel->state.polarity) {
- if (channel->state.enabled) {
- meson_pwm_disable(meson, pwm->hwpwm);
- channel->state.enabled = false;
- }
-
if (state->polarity != channel->state.polarity) {
if (state->polarity == PWM_POLARITY_NORMAL)
meson->inverter_mask |= BIT(pwm->hwpwm);
@@ -328,7 +334,7 @@ static int meson_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm,
err = meson_pwm_calc(meson, channel, pwm->hwpwm,
state->duty_cycle, state->period);
if (err < 0)
- goto unlock;
+ return err;
channel->state.polarity = state->polarity;
channel->state.period = state->period;
@@ -340,9 +346,7 @@ static int meson_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm,
channel->state.enabled = true;
}
-unlock:
- spin_unlock_irqrestore(&meson->lock, flags);
- return err;
+ return 0;
}
static void meson_pwm_get_state(struct pwm_chip *chip, struct pwm_device *pwm,
diff --git a/drivers/pwm/pwm-tiehrpwm.c b/drivers/pwm/pwm-tiehrpwm.c
index 261ca74033bc..14d1d1f6554a 100644
--- a/drivers/pwm/pwm-tiehrpwm.c
+++ b/drivers/pwm/pwm-tiehrpwm.c
@@ -383,6 +383,8 @@ static void ehrpwm_pwm_disable(struct pwm_chip *chip, struct pwm_device *pwm)
}
/* Update shadow register first before modifying active register */
+ ehrpwm_modify(pc->mmio_base, AQSFRC, AQSFRC_RLDCSF_MASK,
+ AQSFRC_RLDCSF_ZRO);
ehrpwm_modify(pc->mmio_base, AQCSFRC, aqcsfrc_mask, aqcsfrc_val);
/*
* Changes to immediate action on Action Qualifier. This puts
diff --git a/drivers/pwm/sysfs.c b/drivers/pwm/sysfs.c
index a813239300c3..0850b11dfd83 100644
--- a/drivers/pwm/sysfs.c
+++ b/drivers/pwm/sysfs.c
@@ -399,19 +399,6 @@ void pwmchip_sysfs_export(struct pwm_chip *chip)
void pwmchip_sysfs_unexport(struct pwm_chip *chip)
{
struct device *parent;
-
- parent = class_find_device(&pwm_class, NULL, chip,
- pwmchip_sysfs_match);
- if (parent) {
- /* for class_find_device() */
- put_device(parent);
- device_unregister(parent);
- }
-}
-
-void pwmchip_sysfs_unexport_children(struct pwm_chip *chip)
-{
- struct device *parent;
unsigned int i;
parent = class_find_device(&pwm_class, NULL, chip,
@@ -427,6 +414,7 @@ void pwmchip_sysfs_unexport_children(struct pwm_chip *chip)
}
put_device(parent);
+ device_unregister(parent);
}
static int __init pwm_sysfs_init(void)
diff --git a/drivers/regulator/tps65086-regulator.c b/drivers/regulator/tps65086-regulator.c
index 45e96e154690..5a5e9b5bf4be 100644
--- a/drivers/regulator/tps65086-regulator.c
+++ b/drivers/regulator/tps65086-regulator.c
@@ -90,8 +90,8 @@ static const struct regulator_linear_range tps65086_buck345_25mv_ranges[] = {
static const struct regulator_linear_range tps65086_ldoa1_ranges[] = {
REGULATOR_LINEAR_RANGE(1350000, 0x0, 0x0, 0),
REGULATOR_LINEAR_RANGE(1500000, 0x1, 0x7, 100000),
- REGULATOR_LINEAR_RANGE(2300000, 0x8, 0xA, 100000),
- REGULATOR_LINEAR_RANGE(2700000, 0xB, 0xD, 150000),
+ REGULATOR_LINEAR_RANGE(2300000, 0x8, 0xB, 100000),
+ REGULATOR_LINEAR_RANGE(2850000, 0xC, 0xD, 150000),
REGULATOR_LINEAR_RANGE(3300000, 0xE, 0xE, 0),
};
diff --git a/drivers/s390/net/ism_drv.c b/drivers/s390/net/ism_drv.c
index 8684bcec8ff4..00cc96341411 100644
--- a/drivers/s390/net/ism_drv.c
+++ b/drivers/s390/net/ism_drv.c
@@ -141,10 +141,13 @@ static int register_ieq(struct ism_dev *ism)
static int unregister_sba(struct ism_dev *ism)
{
+ int ret;
+
if (!ism->sba)
return 0;
- if (ism_cmd_simple(ism, ISM_UNREG_SBA))
+ ret = ism_cmd_simple(ism, ISM_UNREG_SBA);
+ if (ret && ret != ISM_ERROR)
return -EIO;
dma_free_coherent(&ism->pdev->dev, PAGE_SIZE,
@@ -158,10 +161,13 @@ static int unregister_sba(struct ism_dev *ism)
static int unregister_ieq(struct ism_dev *ism)
{
+ int ret;
+
if (!ism->ieq)
return 0;
- if (ism_cmd_simple(ism, ISM_UNREG_IEQ))
+ ret = ism_cmd_simple(ism, ISM_UNREG_IEQ);
+ if (ret && ret != ISM_ERROR)
return -EIO;
dma_free_coherent(&ism->pdev->dev, PAGE_SIZE,
@@ -288,7 +294,7 @@ static int ism_unregister_dmb(struct smcd_dev *smcd, struct smcd_dmb *dmb)
cmd.request.dmb_tok = dmb->dmb_tok;
ret = ism_cmd(ism, &cmd);
- if (ret)
+ if (ret && ret != ISM_ERROR)
goto out;
ism_free_dmb(ism, dmb);
diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c
index 100a4a5a5b99..d1aab85f5102 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.c
+++ b/drivers/scsi/lpfc/lpfc_scsi.c
@@ -3932,7 +3932,8 @@ int lpfc_sli4_scmd_to_wqidx_distr(struct lpfc_hba *phba,
uint32_t tag;
uint16_t hwq;
- if (cmnd && shost_use_blk_mq(cmnd->device->host)) {
+ if (cmnd && shost_use_blk_mq(cmnd->device->host) &&
+ cmnd->request && cmnd->request->q) {
tag = blk_mq_unique_tag(cmnd->request);
hwq = blk_mq_unique_tag_to_hwq(tag);
diff --git a/drivers/scsi/qla2xxx/qla_dfs.c b/drivers/scsi/qla2xxx/qla_dfs.c
index 0b190082aa8d..d647760d4804 100644
--- a/drivers/scsi/qla2xxx/qla_dfs.c
+++ b/drivers/scsi/qla2xxx/qla_dfs.c
@@ -193,6 +193,8 @@ qla_dfs_tgt_counters_show(struct seq_file *s, void *unused)
for (i = 0; i < vha->hw->max_qpairs; i++) {
qpair = vha->hw->queue_pair_map[i];
+ if (!qpair)
+ continue;
qla_core_sbt_cmd += qpair->tgt_counters.qla_core_sbt_cmd;
core_qla_que_buf += qpair->tgt_counters.core_qla_que_buf;
qla_core_ret_ctio += qpair->tgt_counters.qla_core_ret_ctio;
diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c
index f3100472319d..7ca59386ab60 100644
--- a/drivers/scsi/qla2xxx/qla_isr.c
+++ b/drivers/scsi/qla2xxx/qla_isr.c
@@ -3405,7 +3405,7 @@ qla24xx_enable_msix(struct qla_hw_data *ha, struct rsp_que *rsp)
min_vecs++;
}
- if (USER_CTRL_IRQ(ha)) {
+ if (USER_CTRL_IRQ(ha) || !shost_use_blk_mq(vha->host)) {
/* user wants to control IRQ setting for target mode */
ret = pci_alloc_irq_vectors(ha->pdev, min_vecs,
ha->msix_count, PCI_IRQ_MSIX);
diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index 403f96583e3f..1339a647805a 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -7423,6 +7423,13 @@ int __init qlt_init(void)
return -EINVAL;
}
+ qla_tgt_wq = alloc_workqueue("qla_tgt_wq", 0, 0);
+ if (!qla_tgt_wq) {
+ ql_log(ql_log_fatal, NULL, 0xe06f,
+ "alloc_workqueue for qla_tgt_wq failed\n");
+ return -ENOMEM;
+ }
+
if (!QLA_TGT_MODE_ENABLED())
return 0;
@@ -7432,7 +7439,8 @@ int __init qlt_init(void)
if (!qla_tgt_mgmt_cmd_cachep) {
ql_log(ql_log_fatal, NULL, 0xd04b,
"kmem_cache_create for qla_tgt_mgmt_cmd_cachep failed\n");
- return -ENOMEM;
+ ret = -ENOMEM;
+ goto out_workqueue;
}
qla_tgt_plogi_cachep = kmem_cache_create("qla_tgt_plogi_cachep",
@@ -7455,33 +7463,27 @@ int __init qlt_init(void)
goto out_plogi_cachep;
}
- qla_tgt_wq = alloc_workqueue("qla_tgt_wq", 0, 0);
- if (!qla_tgt_wq) {
- ql_log(ql_log_fatal, NULL, 0xe06f,
- "alloc_workqueue for qla_tgt_wq failed\n");
- ret = -ENOMEM;
- goto out_cmd_mempool;
- }
/*
* Return 1 to signal that initiator-mode is being disabled
*/
return (ql2x_ini_mode == QLA2XXX_INI_MODE_DISABLED) ? 1 : 0;
-out_cmd_mempool:
- mempool_destroy(qla_tgt_mgmt_cmd_mempool);
out_plogi_cachep:
kmem_cache_destroy(qla_tgt_plogi_cachep);
out_mgmt_cmd_cachep:
kmem_cache_destroy(qla_tgt_mgmt_cmd_cachep);
+out_workqueue:
+ destroy_workqueue(qla_tgt_wq);
return ret;
}
void qlt_exit(void)
{
+ destroy_workqueue(qla_tgt_wq);
+
if (!QLA_TGT_MODE_ENABLED())
return;
- destroy_workqueue(qla_tgt_wq);
mempool_destroy(qla_tgt_mgmt_cmd_mempool);
kmem_cache_destroy(qla_tgt_plogi_cachep);
kmem_cache_destroy(qla_tgt_mgmt_cmd_cachep);
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index d9c03f894f55..10c940cf2cdc 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -3314,7 +3314,8 @@ static void sd_probe_async(void *data, async_cookie_t cookie)
gd->flags = GENHD_FL_EXT_DEVT;
if (sdp->removable) {
gd->flags |= GENHD_FL_REMOVABLE;
- gd->events |= DISK_EVENT_MEDIA_CHANGE;
+ gd->events |= DISK_EVENT_MEDIA_CHANGE |
+ DISK_EVENT_FLAG_POLL | DISK_EVENT_FLAG_UEVENT;
}
blk_pm_runtime_init(sdp->request_queue, dev);
diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c
index 20bd0c3ca2ba..1c8ff3562caf 100644
--- a/drivers/scsi/sr.c
+++ b/drivers/scsi/sr.c
@@ -712,7 +712,8 @@ static int sr_probe(struct device *dev)
sprintf(disk->disk_name, "sr%d", minor);
disk->fops = &sr_bdops;
disk->flags = GENHD_FL_CD | GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE;
- disk->events = DISK_EVENT_MEDIA_CHANGE | DISK_EVENT_EJECT_REQUEST;
+ disk->events = DISK_EVENT_MEDIA_CHANGE | DISK_EVENT_EJECT_REQUEST
+ | DISK_EVENT_FLAG_POLL | DISK_EVENT_FLAG_UEVENT;
blk_queue_rq_timeout(sdev->request_queue, SR_TIMEOUT);
diff --git a/drivers/soc/tegra/pmc.c b/drivers/soc/tegra/pmc.c
index 7e9ef3431bea..2422ed56895a 100644
--- a/drivers/soc/tegra/pmc.c
+++ b/drivers/soc/tegra/pmc.c
@@ -521,16 +521,10 @@ EXPORT_SYMBOL(tegra_powergate_power_off);
*/
int tegra_powergate_is_powered(unsigned int id)
{
- int status;
-
if (!tegra_powergate_is_valid(id))
return -EINVAL;
- mutex_lock(&pmc->powergates_lock);
- status = tegra_powergate_state(id);
- mutex_unlock(&pmc->powergates_lock);
-
- return status;
+ return tegra_powergate_state(id);
}
/**
diff --git a/drivers/spi/spi-armada-3700.c b/drivers/spi/spi-armada-3700.c
index 3848bde779d3..9eaa803195b2 100644
--- a/drivers/spi/spi-armada-3700.c
+++ b/drivers/spi/spi-armada-3700.c
@@ -668,6 +668,11 @@ static int a3700_spi_transfer_one(struct spi_master *master,
a3700_spi_pin_mode_set(a3700_spi, nbits, xfer->rx_buf ? true : false);
if (xfer->rx_buf) {
+ /* Clear WFIFO, since it's last 2 bytes are shifted out during
+ * a read operation
+ */
+ spireg_write(a3700_spi, A3700_SPI_DATA_OUT_REG, 0);
+
/* Set read data length */
spireg_write(a3700_spi, A3700_SPI_IF_DIN_CNT_REG,
a3700_spi->buf_len);
diff --git a/drivers/spi/spi-bcm2835aux.c b/drivers/spi/spi-bcm2835aux.c
index bd00b7cc8b78..430a0f226cc4 100644
--- a/drivers/spi/spi-bcm2835aux.c
+++ b/drivers/spi/spi-bcm2835aux.c
@@ -421,6 +421,50 @@ static void bcm2835aux_spi_handle_err(struct spi_master *master,
bcm2835aux_spi_reset_hw(bs);
}
+static int bcm2835aux_spi_setup(struct spi_device *spi)
+{
+ int ret;
+
+ /* sanity check for native cs */
+ if (spi->mode & SPI_NO_CS)
+ return 0;
+ if (gpio_is_valid(spi->cs_gpio)) {
+ /* with gpio-cs set the GPIO to the correct level
+ * and as output (in case the dt has the gpio not configured
+ * as output but native cs)
+ */
+ ret = gpio_direction_output(spi->cs_gpio,
+ (spi->mode & SPI_CS_HIGH) ? 0 : 1);
+ if (ret)
+ dev_err(&spi->dev,
+ "could not set gpio %i as output: %i\n",
+ spi->cs_gpio, ret);
+
+ return ret;
+ }
+
+ /* for dt-backwards compatibility: only support native on CS0
+ * known things not supported with broken native CS:
+ * * multiple chip-selects: cs0-cs2 are all
+ * simultaniously asserted whenever there is a transfer
+ * this even includes SPI_NO_CS
+ * * SPI_CS_HIGH: cs are always asserted low
+ * * cs_change: cs is deasserted after each spi_transfer
+ * * cs_delay_usec: cs is always deasserted one SCK cycle
+ * after the last transfer
+ * probably more...
+ */
+ dev_warn(&spi->dev,
+ "Native CS is not supported - please configure cs-gpio in device-tree\n");
+
+ if (spi->chip_select == 0)
+ return 0;
+
+ dev_warn(&spi->dev, "Native CS is not working for cs > 0\n");
+
+ return -EINVAL;
+}
+
static int bcm2835aux_spi_probe(struct platform_device *pdev)
{
struct spi_master *master;
@@ -438,7 +482,19 @@ static int bcm2835aux_spi_probe(struct platform_device *pdev)
platform_set_drvdata(pdev, master);
master->mode_bits = (SPI_CPOL | SPI_CS_HIGH | SPI_NO_CS);
master->bits_per_word_mask = SPI_BPW_MASK(8);
- master->num_chipselect = -1;
+ /* even though the driver never officially supported native CS
+ * allow a single native CS for legacy DT support purposes when
+ * no cs-gpio is configured.
+ * Known limitations for native cs are:
+ * * multiple chip-selects: cs0-cs2 are all simultaniously asserted
+ * whenever there is a transfer - this even includes SPI_NO_CS
+ * * SPI_CS_HIGH: is ignores - cs are always asserted low
+ * * cs_change: cs is deasserted after each spi_transfer
+ * * cs_delay_usec: cs is always deasserted one SCK cycle after
+ * a spi_transfer
+ */
+ master->num_chipselect = 1;
+ master->setup = bcm2835aux_spi_setup;
master->transfer_one = bcm2835aux_spi_transfer_one;
master->handle_err = bcm2835aux_spi_handle_err;
master->prepare_message = bcm2835aux_spi_prepare_message;
diff --git a/drivers/spi/spi-rspi.c b/drivers/spi/spi-rspi.c
index 20981e08ee97..f4a797a9d76e 100644
--- a/drivers/spi/spi-rspi.c
+++ b/drivers/spi/spi-rspi.c
@@ -279,7 +279,8 @@ static int rspi_set_config_register(struct rspi_data *rspi, int access_size)
/* Sets parity, interrupt mask */
rspi_write8(rspi, 0x00, RSPI_SPCR2);
- /* Sets SPCMD */
+ /* Resets sequencer */
+ rspi_write8(rspi, 0, RSPI_SPSCR);
rspi->spcmd |= SPCMD_SPB_8_TO_16(access_size);
rspi_write16(rspi, rspi->spcmd, RSPI_SPCMD0);
@@ -323,7 +324,8 @@ static int rspi_rz_set_config_register(struct rspi_data *rspi, int access_size)
rspi_write8(rspi, 0x00, RSPI_SSLND);
rspi_write8(rspi, 0x00, RSPI_SPND);
- /* Sets SPCMD */
+ /* Resets sequencer */
+ rspi_write8(rspi, 0, RSPI_SPSCR);
rspi->spcmd |= SPCMD_SPB_8_TO_16(access_size);
rspi_write16(rspi, rspi->spcmd, RSPI_SPCMD0);
@@ -374,7 +376,8 @@ static int qspi_set_config_register(struct rspi_data *rspi, int access_size)
/* Sets buffer to allow normal operation */
rspi_write8(rspi, 0x00, QSPI_SPBFCR);
- /* Sets SPCMD */
+ /* Resets sequencer */
+ rspi_write8(rspi, 0, RSPI_SPSCR);
rspi_write16(rspi, rspi->spcmd, RSPI_SPCMD0);
/* Enables SPI function in master mode */
diff --git a/drivers/ssb/bridge_pcmcia_80211.c b/drivers/ssb/bridge_pcmcia_80211.c
index d70568ea02d5..2ff7d90e166a 100644
--- a/drivers/ssb/bridge_pcmcia_80211.c
+++ b/drivers/ssb/bridge_pcmcia_80211.c
@@ -113,16 +113,21 @@ static struct pcmcia_driver ssb_host_pcmcia_driver = {
.resume = ssb_host_pcmcia_resume,
};
+static int pcmcia_init_failed;
+
/*
* These are not module init/exit functions!
* The module_pcmcia_driver() helper cannot be used here.
*/
int ssb_host_pcmcia_init(void)
{
- return pcmcia_register_driver(&ssb_host_pcmcia_driver);
+ pcmcia_init_failed = pcmcia_register_driver(&ssb_host_pcmcia_driver);
+
+ return pcmcia_init_failed;
}
void ssb_host_pcmcia_exit(void)
{
- pcmcia_unregister_driver(&ssb_host_pcmcia_driver);
+ if (!pcmcia_init_failed)
+ pcmcia_unregister_driver(&ssb_host_pcmcia_driver);
}
diff --git a/drivers/staging/rtl8188eu/core/rtw_xmit.c b/drivers/staging/rtl8188eu/core/rtw_xmit.c
index be2f46eb9f78..904b988ecc4e 100644
--- a/drivers/staging/rtl8188eu/core/rtw_xmit.c
+++ b/drivers/staging/rtl8188eu/core/rtw_xmit.c
@@ -188,7 +188,9 @@ s32 _rtw_init_xmit_priv(struct xmit_priv *pxmitpriv, struct adapter *padapter)
pxmitpriv->free_xmit_extbuf_cnt = num_xmit_extbuf;
- rtw_alloc_hwxmits(padapter);
+ res = rtw_alloc_hwxmits(padapter);
+ if (res == _FAIL)
+ goto exit;
rtw_init_hwxmits(pxmitpriv->hwxmits, pxmitpriv->hwxmit_entry);
for (i = 0; i < 4; i++)
@@ -1573,7 +1575,7 @@ exit:
return res;
}
-void rtw_alloc_hwxmits(struct adapter *padapter)
+s32 rtw_alloc_hwxmits(struct adapter *padapter)
{
struct hw_xmit *hwxmits;
struct xmit_priv *pxmitpriv = &padapter->xmitpriv;
@@ -1582,6 +1584,8 @@ void rtw_alloc_hwxmits(struct adapter *padapter)
pxmitpriv->hwxmits = kcalloc(pxmitpriv->hwxmit_entry,
sizeof(struct hw_xmit), GFP_KERNEL);
+ if (!pxmitpriv->hwxmits)
+ return _FAIL;
hwxmits = pxmitpriv->hwxmits;
@@ -1589,6 +1593,7 @@ void rtw_alloc_hwxmits(struct adapter *padapter)
hwxmits[1] .sta_queue = &pxmitpriv->vi_pending;
hwxmits[2] .sta_queue = &pxmitpriv->be_pending;
hwxmits[3] .sta_queue = &pxmitpriv->bk_pending;
+ return _SUCCESS;
}
void rtw_free_hwxmits(struct adapter *padapter)
diff --git a/drivers/staging/rtl8188eu/include/rtw_xmit.h b/drivers/staging/rtl8188eu/include/rtw_xmit.h
index dd6b7a9a8d4a..1be4b478475a 100644
--- a/drivers/staging/rtl8188eu/include/rtw_xmit.h
+++ b/drivers/staging/rtl8188eu/include/rtw_xmit.h
@@ -342,7 +342,7 @@ s32 rtw_txframes_sta_ac_pending(struct adapter *padapter,
void rtw_init_hwxmits(struct hw_xmit *phwxmit, int entry);
s32 _rtw_init_xmit_priv(struct xmit_priv *pxmitpriv, struct adapter *padapter);
void _rtw_free_xmit_priv(struct xmit_priv *pxmitpriv);
-void rtw_alloc_hwxmits(struct adapter *padapter);
+s32 rtw_alloc_hwxmits(struct adapter *padapter);
void rtw_free_hwxmits(struct adapter *padapter);
s32 rtw_xmit(struct adapter *padapter, struct sk_buff **pkt);
diff --git a/drivers/staging/rtl8723bs/core/rtw_xmit.c b/drivers/staging/rtl8723bs/core/rtw_xmit.c
index 8f2c9a6658bf..d8adc5d752e4 100644
--- a/drivers/staging/rtl8723bs/core/rtw_xmit.c
+++ b/drivers/staging/rtl8723bs/core/rtw_xmit.c
@@ -271,7 +271,9 @@ s32 _rtw_init_xmit_priv(struct xmit_priv *pxmitpriv, struct adapter *padapter)
}
}
- rtw_alloc_hwxmits(padapter);
+ res = rtw_alloc_hwxmits(padapter);
+ if (res == _FAIL)
+ goto exit;
rtw_init_hwxmits(pxmitpriv->hwxmits, pxmitpriv->hwxmit_entry);
for (i = 0; i < 4; i++) {
@@ -2157,7 +2159,7 @@ exit:
return res;
}
-void rtw_alloc_hwxmits(struct adapter *padapter)
+s32 rtw_alloc_hwxmits(struct adapter *padapter)
{
struct hw_xmit *hwxmits;
struct xmit_priv *pxmitpriv = &padapter->xmitpriv;
@@ -2168,10 +2170,8 @@ void rtw_alloc_hwxmits(struct adapter *padapter)
pxmitpriv->hwxmits = (struct hw_xmit *)rtw_zmalloc(sizeof(struct hw_xmit) * pxmitpriv->hwxmit_entry);
- if (pxmitpriv->hwxmits == NULL) {
- DBG_871X("alloc hwxmits fail!...\n");
- return;
- }
+ if (!pxmitpriv->hwxmits)
+ return _FAIL;
hwxmits = pxmitpriv->hwxmits;
@@ -2217,7 +2217,7 @@ void rtw_alloc_hwxmits(struct adapter *padapter)
}
-
+ return _SUCCESS;
}
void rtw_free_hwxmits(struct adapter *padapter)
diff --git a/drivers/staging/rtl8723bs/include/rtw_xmit.h b/drivers/staging/rtl8723bs/include/rtw_xmit.h
index 11571649cd2c..92236ca8a1ef 100644
--- a/drivers/staging/rtl8723bs/include/rtw_xmit.h
+++ b/drivers/staging/rtl8723bs/include/rtw_xmit.h
@@ -494,7 +494,7 @@ s32 _rtw_init_xmit_priv(struct xmit_priv *pxmitpriv, struct adapter *padapter);
void _rtw_free_xmit_priv (struct xmit_priv *pxmitpriv);
-void rtw_alloc_hwxmits(struct adapter *padapter);
+s32 rtw_alloc_hwxmits(struct adapter *padapter);
void rtw_free_hwxmits(struct adapter *padapter);
diff --git a/drivers/thermal/int340x_thermal/int3400_thermal.c b/drivers/thermal/int340x_thermal/int3400_thermal.c
index 26c263e9a5fa..faa9fff13245 100644
--- a/drivers/thermal/int340x_thermal/int3400_thermal.c
+++ b/drivers/thermal/int340x_thermal/int3400_thermal.c
@@ -20,6 +20,13 @@ enum int3400_thermal_uuid {
INT3400_THERMAL_PASSIVE_1,
INT3400_THERMAL_ACTIVE,
INT3400_THERMAL_CRITICAL,
+ INT3400_THERMAL_ADAPTIVE_PERFORMANCE,
+ INT3400_THERMAL_EMERGENCY_CALL_MODE,
+ INT3400_THERMAL_PASSIVE_2,
+ INT3400_THERMAL_POWER_BOSS,
+ INT3400_THERMAL_VIRTUAL_SENSOR,
+ INT3400_THERMAL_COOLING_MODE,
+ INT3400_THERMAL_HARDWARE_DUTY_CYCLING,
INT3400_THERMAL_MAXIMUM_UUID,
};
@@ -27,6 +34,13 @@ static char *int3400_thermal_uuids[INT3400_THERMAL_MAXIMUM_UUID] = {
"42A441D6-AE6A-462b-A84B-4A8CE79027D3",
"3A95C389-E4B8-4629-A526-C52C88626BAE",
"97C68AE7-15FA-499c-B8C9-5DA81D606E0A",
+ "63BE270F-1C11-48FD-A6F7-3AF253FF3E2D",
+ "5349962F-71E6-431D-9AE8-0A635B710AEE",
+ "9E04115A-AE87-4D1C-9500-0F3E340BFE75",
+ "F5A35014-C209-46A4-993A-EB56DE7530A1",
+ "6ED722A7-9240-48A5-B479-31EEF723D7CF",
+ "16CAF1B7-DD38-40ED-B1C1-1B8A1913D531",
+ "BE84BABF-C4D4-403D-B495-3128FD44dAC1",
};
struct int3400_thermal_priv {
@@ -271,10 +285,9 @@ static int int3400_thermal_probe(struct platform_device *pdev)
platform_set_drvdata(pdev, priv);
- if (priv->uuid_bitmap & 1 << INT3400_THERMAL_PASSIVE_1) {
- int3400_thermal_ops.get_mode = int3400_thermal_get_mode;
- int3400_thermal_ops.set_mode = int3400_thermal_set_mode;
- }
+ int3400_thermal_ops.get_mode = int3400_thermal_get_mode;
+ int3400_thermal_ops.set_mode = int3400_thermal_set_mode;
+
priv->thermal = thermal_zone_device_register("INT3400 Thermal", 0, 0,
priv, &int3400_thermal_ops,
&int3400_thermal_params, 0, 0);
diff --git a/drivers/thermal/intel_soc_dts_thermal.c b/drivers/thermal/intel_soc_dts_thermal.c
index c27868b2c6af..ce2722edd307 100644
--- a/drivers/thermal/intel_soc_dts_thermal.c
+++ b/drivers/thermal/intel_soc_dts_thermal.c
@@ -43,7 +43,7 @@ static irqreturn_t soc_irq_thread_fn(int irq, void *dev_data)
}
static const struct x86_cpu_id soc_thermal_ids[] = {
- { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT1, 0,
+ { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT, 0,
BYT_SOC_DTS_APIC_IRQ},
{}
};
diff --git a/drivers/tty/n_r3964.c b/drivers/tty/n_r3964.c
index 08ac04d08991..a90f44dfa14e 100644
--- a/drivers/tty/n_r3964.c
+++ b/drivers/tty/n_r3964.c
@@ -194,10 +194,20 @@ static void __exit r3964_exit(void)
}
}
+static bool force_load;
+module_param(force_load, bool, 0);
+MODULE_PARM_DESC(force_load, "Force module load, despite CVE holes");
+
static int __init r3964_init(void)
{
int status;
+ if (!force_load) {
+ pr_err("Refusing to load r3964 due to holes in this line discipline (see bnc#1133188)!\n");
+ pr_err("You can still force-load the driver by passing force_load=1 module parameter\n");
+ return -EINVAL;
+ }
+
printk("r3964: Philips r3964 Driver $Revision: 1.10 $\n");
/*
@@ -943,6 +953,12 @@ static int r3964_open(struct tty_struct *tty)
{
struct r3964_info *pInfo;
+ if (!force_load) {
+ pr_err("Refusing to open r3964 due to holes in this line discipline (see bnc#1133188)!\n");
+ pr_err("You can still force-open the discipline by passing force_load=1 module parameter\n");
+ return -EINVAL;
+ }
+
TRACE_L("open");
TRACE_L("tty=%p, PID=%d, disc_data=%p",
tty, current->pid, tty->disc_data);
diff --git a/drivers/tty/serial/8250/8250_pxa.c b/drivers/tty/serial/8250/8250_pxa.c
index 4d68731af534..de1372ba24b1 100644
--- a/drivers/tty/serial/8250/8250_pxa.c
+++ b/drivers/tty/serial/8250/8250_pxa.c
@@ -118,6 +118,10 @@ static int serial_pxa_probe(struct platform_device *pdev)
if (ret)
return ret;
+ ret = of_alias_get_id(pdev->dev.of_node, "serial");
+ if (ret >= 0)
+ uart.port.line = ret;
+
uart.port.type = PORT_XSCALE;
uart.port.iotype = UPIO_MEM32;
uart.port.mapbase = mmres->start;
diff --git a/drivers/tty/serial/ar933x_uart.c b/drivers/tty/serial/ar933x_uart.c
index decc7f3c1ab2..ed545a61413c 100644
--- a/drivers/tty/serial/ar933x_uart.c
+++ b/drivers/tty/serial/ar933x_uart.c
@@ -52,11 +52,6 @@ struct ar933x_uart_port {
struct clk *clk;
};
-static inline bool ar933x_uart_console_enabled(void)
-{
- return IS_ENABLED(CONFIG_SERIAL_AR933X_CONSOLE);
-}
-
static inline unsigned int ar933x_uart_read(struct ar933x_uart_port *up,
int offset)
{
@@ -511,6 +506,7 @@ static const struct uart_ops ar933x_uart_ops = {
.verify_port = ar933x_uart_verify_port,
};
+#ifdef CONFIG_SERIAL_AR933X_CONSOLE
static struct ar933x_uart_port *
ar933x_console_ports[CONFIG_SERIAL_AR933X_NR_UARTS];
@@ -607,14 +603,7 @@ static struct console ar933x_uart_console = {
.index = -1,
.data = &ar933x_uart_driver,
};
-
-static void ar933x_uart_add_console_port(struct ar933x_uart_port *up)
-{
- if (!ar933x_uart_console_enabled())
- return;
-
- ar933x_console_ports[up->port.line] = up;
-}
+#endif /* CONFIG_SERIAL_AR933X_CONSOLE */
static struct uart_driver ar933x_uart_driver = {
.owner = THIS_MODULE,
@@ -703,7 +692,9 @@ static int ar933x_uart_probe(struct platform_device *pdev)
baud = ar933x_uart_get_baud(port->uartclk, 0, AR933X_UART_MAX_STEP);
up->max_baud = min_t(unsigned int, baud, AR933X_UART_MAX_BAUD);
- ar933x_uart_add_console_port(up);
+#ifdef CONFIG_SERIAL_AR933X_CONSOLE
+ ar933x_console_ports[up->port.line] = up;
+#endif
ret = uart_add_one_port(&ar933x_uart_driver, &up->port);
if (ret)
@@ -752,8 +743,9 @@ static int __init ar933x_uart_init(void)
{
int ret;
- if (ar933x_uart_console_enabled())
- ar933x_uart_driver.cons = &ar933x_uart_console;
+#ifdef CONFIG_SERIAL_AR933X_CONSOLE
+ ar933x_uart_driver.cons = &ar933x_uart_console;
+#endif
ret = uart_register_driver(&ar933x_uart_driver);
if (ret)
diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c
index 1e3d2021c89f..8885e999160e 100644
--- a/drivers/tty/serial/sc16is7xx.c
+++ b/drivers/tty/serial/sc16is7xx.c
@@ -1486,7 +1486,7 @@ static int __init sc16is7xx_init(void)
ret = i2c_add_driver(&sc16is7xx_i2c_uart_driver);
if (ret < 0) {
pr_err("failed to init sc16is7xx i2c --> %d\n", ret);
- return ret;
+ goto err_i2c;
}
#endif
@@ -1494,10 +1494,20 @@ static int __init sc16is7xx_init(void)
ret = spi_register_driver(&sc16is7xx_spi_uart_driver);
if (ret < 0) {
pr_err("failed to init sc16is7xx spi --> %d\n", ret);
- return ret;
+ goto err_spi;
}
#endif
return ret;
+
+#ifdef CONFIG_SERIAL_SC16IS7XX_SPI
+err_spi:
+#endif
+#ifdef CONFIG_SERIAL_SC16IS7XX_I2C
+ i2c_del_driver(&sc16is7xx_i2c_uart_driver);
+err_i2c:
+#endif
+ uart_unregister_driver(&sc16is7xx_uart);
+ return ret;
}
module_init(sc16is7xx_init);
diff --git a/drivers/tty/serial/xilinx_uartps.c b/drivers/tty/serial/xilinx_uartps.c
index 22c90ff574a3..8fcc0e412c84 100644
--- a/drivers/tty/serial/xilinx_uartps.c
+++ b/drivers/tty/serial/xilinx_uartps.c
@@ -1269,7 +1269,7 @@ static void cdns_uart_console_write(struct console *co, const char *s,
*
* Return: 0 on success, negative errno otherwise.
*/
-static int __init cdns_uart_console_setup(struct console *co, char *options)
+static int cdns_uart_console_setup(struct console *co, char *options)
{
struct uart_port *port = &cdns_uart_port[co->index];
int baud = 9600;
diff --git a/drivers/tty/tty_buffer.c b/drivers/tty/tty_buffer.c
index 217114227f8d..cf11882d2602 100644
--- a/drivers/tty/tty_buffer.c
+++ b/drivers/tty/tty_buffer.c
@@ -25,7 +25,7 @@
* Byte threshold to limit memory consumption for flip buffers.
* The actual memory limit is > 2x this amount.
*/
-#define TTYB_DEFAULT_MEM_LIMIT 65536
+#define TTYB_DEFAULT_MEM_LIMIT (640 * 1024UL)
/*
* We default to dicing tty buffer allocations to this many characters
diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c
index bd00f002eac2..82ed578dd98e 100644
--- a/drivers/tty/vt/vt.c
+++ b/drivers/tty/vt/vt.c
@@ -3840,8 +3840,6 @@ void do_blank_screen(int entering_gfx)
return;
}
- if (blank_state != blank_normal_wait)
- return;
blank_state = blank_off;
/* don't blank graphics */
diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c
index 1e5b3ea757b2..022cc8b906fc 100644
--- a/drivers/usb/class/cdc-acm.c
+++ b/drivers/usb/class/cdc-acm.c
@@ -482,12 +482,12 @@ static void acm_read_bulk_callback(struct urb *urb)
struct acm *acm = rb->instance;
unsigned long flags;
int status = urb->status;
+ bool stopped = false;
+ bool stalled = false;
dev_vdbg(&acm->data->dev, "got urb %d, len %d, status %d\n",
rb->index, urb->actual_length, status);
- set_bit(rb->index, &acm->read_urbs_free);
-
if (!acm->dev) {
dev_dbg(&acm->data->dev, "%s - disconnected\n", __func__);
return;
@@ -500,15 +500,16 @@ static void acm_read_bulk_callback(struct urb *urb)
break;
case -EPIPE:
set_bit(EVENT_RX_STALL, &acm->flags);
- schedule_work(&acm->work);
- return;
+ stalled = true;
+ break;
case -ENOENT:
case -ECONNRESET:
case -ESHUTDOWN:
dev_dbg(&acm->data->dev,
"%s - urb shutting down with status: %d\n",
__func__, status);
- return;
+ stopped = true;
+ break;
default:
dev_dbg(&acm->data->dev,
"%s - nonzero urb status received: %d\n",
@@ -517,10 +518,24 @@ static void acm_read_bulk_callback(struct urb *urb)
}
/*
- * Unthrottle may run on another CPU which needs to see events
- * in the same order. Submission has an implict barrier
+ * Make sure URB processing is done before marking as free to avoid
+ * racing with unthrottle() on another CPU. Matches the barriers
+ * implied by the test_and_clear_bit() in acm_submit_read_urb().
*/
smp_mb__before_atomic();
+ set_bit(rb->index, &acm->read_urbs_free);
+ /*
+ * Make sure URB is marked as free before checking the throttled flag
+ * to avoid racing with unthrottle() on another CPU. Matches the
+ * smp_mb() in unthrottle().
+ */
+ smp_mb__after_atomic();
+
+ if (stopped || stalled) {
+ if (stalled)
+ schedule_work(&acm->work);
+ return;
+ }
/* throttle device if requested by tty */
spin_lock_irqsave(&acm->read_lock, flags);
@@ -854,6 +869,9 @@ static void acm_tty_unthrottle(struct tty_struct *tty)
acm->throttle_req = 0;
spin_unlock_irq(&acm->read_lock);
+ /* Matches the smp_mb__after_atomic() in acm_read_bulk_callback(). */
+ smp_mb();
+
if (was_throttled)
acm_submit_read_urbs(acm, GFP_KERNEL);
}
diff --git a/drivers/usb/core/driver.c b/drivers/usb/core/driver.c
index c635821c14cb..29bd353eaf73 100644
--- a/drivers/usb/core/driver.c
+++ b/drivers/usb/core/driver.c
@@ -473,11 +473,6 @@ static int usb_unbind_interface(struct device *dev)
pm_runtime_disable(dev);
pm_runtime_set_suspended(dev);
- /* Undo any residual pm_autopm_get_interface_* calls */
- for (r = atomic_read(&intf->pm_usage_cnt); r > 0; --r)
- usb_autopm_put_interface_no_suspend(intf);
- atomic_set(&intf->pm_usage_cnt, 0);
-
if (!error)
usb_autosuspend_device(udev);
@@ -1628,7 +1623,6 @@ void usb_autopm_put_interface(struct usb_interface *intf)
int status;
usb_mark_last_busy(udev);
- atomic_dec(&intf->pm_usage_cnt);
status = pm_runtime_put_sync(&intf->dev);
dev_vdbg(&intf->dev, "%s: cnt %d -> %d\n",
__func__, atomic_read(&intf->dev.power.usage_count),
@@ -1657,7 +1651,6 @@ void usb_autopm_put_interface_async(struct usb_interface *intf)
int status;
usb_mark_last_busy(udev);
- atomic_dec(&intf->pm_usage_cnt);
status = pm_runtime_put(&intf->dev);
dev_vdbg(&intf->dev, "%s: cnt %d -> %d\n",
__func__, atomic_read(&intf->dev.power.usage_count),
@@ -1679,7 +1672,6 @@ void usb_autopm_put_interface_no_suspend(struct usb_interface *intf)
struct usb_device *udev = interface_to_usbdev(intf);
usb_mark_last_busy(udev);
- atomic_dec(&intf->pm_usage_cnt);
pm_runtime_put_noidle(&intf->dev);
}
EXPORT_SYMBOL_GPL(usb_autopm_put_interface_no_suspend);
@@ -1710,8 +1702,6 @@ int usb_autopm_get_interface(struct usb_interface *intf)
status = pm_runtime_get_sync(&intf->dev);
if (status < 0)
pm_runtime_put_sync(&intf->dev);
- else
- atomic_inc(&intf->pm_usage_cnt);
dev_vdbg(&intf->dev, "%s: cnt %d -> %d\n",
__func__, atomic_read(&intf->dev.power.usage_count),
status);
@@ -1745,8 +1735,6 @@ int usb_autopm_get_interface_async(struct usb_interface *intf)
status = pm_runtime_get(&intf->dev);
if (status < 0 && status != -EINPROGRESS)
pm_runtime_put_noidle(&intf->dev);
- else
- atomic_inc(&intf->pm_usage_cnt);
dev_vdbg(&intf->dev, "%s: cnt %d -> %d\n",
__func__, atomic_read(&intf->dev.power.usage_count),
status);
@@ -1770,7 +1758,6 @@ void usb_autopm_get_interface_no_resume(struct usb_interface *intf)
struct usb_device *udev = interface_to_usbdev(intf);
usb_mark_last_busy(udev);
- atomic_inc(&intf->pm_usage_cnt);
pm_runtime_get_noresume(&intf->dev);
}
EXPORT_SYMBOL_GPL(usb_autopm_get_interface_no_resume);
diff --git a/drivers/usb/core/message.c b/drivers/usb/core/message.c
index 1fe3c5d3be5f..c3f3f6370f64 100644
--- a/drivers/usb/core/message.c
+++ b/drivers/usb/core/message.c
@@ -818,9 +818,11 @@ int usb_string(struct usb_device *dev, int index, char *buf, size_t size)
if (dev->state == USB_STATE_SUSPENDED)
return -EHOSTUNREACH;
- if (size <= 0 || !buf || !index)
+ if (size <= 0 || !buf)
return -EINVAL;
buf[0] = 0;
+ if (index <= 0 || index >= 256)
+ return -EINVAL;
tbuf = kmalloc(256, GFP_NOIO);
if (!tbuf)
return -ENOMEM;
diff --git a/drivers/usb/dwc2/gadget.c b/drivers/usb/dwc2/gadget.c
index 7921781cd770..2f90437f3cbb 100644
--- a/drivers/usb/dwc2/gadget.c
+++ b/drivers/usb/dwc2/gadget.c
@@ -2276,6 +2276,7 @@ static unsigned int dwc2_gadget_get_xfersize_ddma(struct dwc2_hsotg_ep *hs_ep)
if (status & DEV_DMA_STS_MASK)
dev_err(hsotg->dev, "descriptor %d closed with %x\n",
i, status & DEV_DMA_STS_MASK);
+ desc++;
}
return bytes_rem;
diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c
index 4dd1d300a3c7..72a72741b207 100644
--- a/drivers/usb/dwc3/core.c
+++ b/drivers/usb/dwc3/core.c
@@ -979,7 +979,7 @@ static void dwc3_get_properties(struct dwc3 *dwc)
u8 hird_threshold;
/* default to highest possible threshold */
- lpm_nyet_threshold = 0xff;
+ lpm_nyet_threshold = 0xf;
/* default to -3.5dB de-emphasis */
tx_de_emphasis = 1;
diff --git a/drivers/usb/gadget/udc/net2272.c b/drivers/usb/gadget/udc/net2272.c
index e0759a826b60..7fb31a3b53e6 100644
--- a/drivers/usb/gadget/udc/net2272.c
+++ b/drivers/usb/gadget/udc/net2272.c
@@ -958,6 +958,7 @@ net2272_dequeue(struct usb_ep *_ep, struct usb_request *_req)
break;
}
if (&req->req != _req) {
+ ep->stopped = stopped;
spin_unlock_irqrestore(&ep->dev->lock, flags);
return -EINVAL;
}
diff --git a/drivers/usb/gadget/udc/net2280.c b/drivers/usb/gadget/udc/net2280.c
index e21e9a6ff05a..cf18e7990f9b 100644
--- a/drivers/usb/gadget/udc/net2280.c
+++ b/drivers/usb/gadget/udc/net2280.c
@@ -870,9 +870,6 @@ static void start_queue(struct net2280_ep *ep, u32 dmactl, u32 td_dma)
(void) readl(&ep->dev->pci->pcimstctl);
writel(BIT(DMA_START), &dma->dmastat);
-
- if (!ep->is_in)
- stop_out_naking(ep);
}
static void start_dma(struct net2280_ep *ep, struct net2280_request *req)
@@ -911,6 +908,7 @@ static void start_dma(struct net2280_ep *ep, struct net2280_request *req)
writel(BIT(DMA_START), &dma->dmastat);
return;
}
+ stop_out_naking(ep);
}
tmp = dmactl_default;
@@ -1279,9 +1277,9 @@ static int net2280_dequeue(struct usb_ep *_ep, struct usb_request *_req)
break;
}
if (&req->req != _req) {
+ ep->stopped = stopped;
spin_unlock_irqrestore(&ep->dev->lock, flags);
- dev_err(&ep->dev->pdev->dev, "%s: Request mismatch\n",
- __func__);
+ ep_dbg(ep->dev, "%s: Request mismatch\n", __func__);
return -EINVAL;
}
diff --git a/drivers/usb/host/u132-hcd.c b/drivers/usb/host/u132-hcd.c
index 43618976d68a..3efb7b0e8269 100644
--- a/drivers/usb/host/u132-hcd.c
+++ b/drivers/usb/host/u132-hcd.c
@@ -3208,6 +3208,9 @@ static int __init u132_hcd_init(void)
printk(KERN_INFO "driver %s\n", hcd_name);
workqueue = create_singlethread_workqueue("u132");
retval = platform_driver_register(&u132_platform_driver);
+ if (retval)
+ destroy_workqueue(workqueue);
+
return retval;
}
diff --git a/drivers/usb/misc/usb251xb.c b/drivers/usb/misc/usb251xb.c
index 91f66d68bcb7..949ebb582735 100644
--- a/drivers/usb/misc/usb251xb.c
+++ b/drivers/usb/misc/usb251xb.c
@@ -531,7 +531,7 @@ static int usb251xb_probe(struct usb251xb *hub)
dev);
int err;
- if (np) {
+ if (np && of_id) {
err = usb251xb_get_ofdata(hub,
(struct usb251xb_data *)of_id->data);
if (err) {
diff --git a/drivers/usb/misc/yurex.c b/drivers/usb/misc/yurex.c
index 4f48f5730e12..8ee98bc6c468 100644
--- a/drivers/usb/misc/yurex.c
+++ b/drivers/usb/misc/yurex.c
@@ -318,6 +318,7 @@ static void yurex_disconnect(struct usb_interface *interface)
usb_deregister_dev(interface, &yurex_class);
/* prevent more I/O from starting */
+ usb_poison_urb(dev->urb);
mutex_lock(&dev->io_mutex);
dev->interface = NULL;
mutex_unlock(&dev->io_mutex);
diff --git a/drivers/usb/serial/f81232.c b/drivers/usb/serial/f81232.c
index 972f5a5fe577..1f20fa0a67c0 100644
--- a/drivers/usb/serial/f81232.c
+++ b/drivers/usb/serial/f81232.c
@@ -560,9 +560,12 @@ static int f81232_open(struct tty_struct *tty, struct usb_serial_port *port)
static void f81232_close(struct usb_serial_port *port)
{
+ struct f81232_private *port_priv = usb_get_serial_port_data(port);
+
f81232_port_disable(port);
usb_serial_generic_close(port);
usb_kill_urb(port->interrupt_in_urb);
+ flush_work(&port_priv->interrupt_work);
}
static void f81232_dtr_rts(struct usb_serial_port *port, int on)
@@ -656,6 +659,40 @@ static int f81232_port_remove(struct usb_serial_port *port)
return 0;
}
+static int f81232_suspend(struct usb_serial *serial, pm_message_t message)
+{
+ struct usb_serial_port *port = serial->port[0];
+ struct f81232_private *port_priv = usb_get_serial_port_data(port);
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(port->read_urbs); ++i)
+ usb_kill_urb(port->read_urbs[i]);
+
+ usb_kill_urb(port->interrupt_in_urb);
+
+ if (port_priv)
+ flush_work(&port_priv->interrupt_work);
+
+ return 0;
+}
+
+static int f81232_resume(struct usb_serial *serial)
+{
+ struct usb_serial_port *port = serial->port[0];
+ int result;
+
+ if (tty_port_initialized(&port->port)) {
+ result = usb_submit_urb(port->interrupt_in_urb, GFP_NOIO);
+ if (result) {
+ dev_err(&port->dev, "submit interrupt urb failed: %d\n",
+ result);
+ return result;
+ }
+ }
+
+ return usb_serial_generic_resume(serial);
+}
+
static struct usb_serial_driver f81232_device = {
.driver = {
.owner = THIS_MODULE,
@@ -679,6 +716,8 @@ static struct usb_serial_driver f81232_device = {
.read_int_callback = f81232_read_int_callback,
.port_probe = f81232_port_probe,
.port_remove = f81232_port_remove,
+ .suspend = f81232_suspend,
+ .resume = f81232_resume,
};
static struct usb_serial_driver * const serial_drivers[] = {
diff --git a/drivers/usb/serial/generic.c b/drivers/usb/serial/generic.c
index 35cb8c0e584f..efd7ce92878b 100644
--- a/drivers/usb/serial/generic.c
+++ b/drivers/usb/serial/generic.c
@@ -379,6 +379,7 @@ void usb_serial_generic_read_bulk_callback(struct urb *urb)
struct usb_serial_port *port = urb->context;
unsigned char *data = urb->transfer_buffer;
unsigned long flags;
+ bool stopped = false;
int status = urb->status;
int i;
@@ -386,33 +387,51 @@ void usb_serial_generic_read_bulk_callback(struct urb *urb)
if (urb == port->read_urbs[i])
break;
}
- set_bit(i, &port->read_urbs_free);
dev_dbg(&port->dev, "%s - urb %d, len %d\n", __func__, i,
urb->actual_length);
switch (status) {
case 0:
+ usb_serial_debug_data(&port->dev, __func__, urb->actual_length,
+ data);
+ port->serial->type->process_read_urb(urb);
break;
case -ENOENT:
case -ECONNRESET:
case -ESHUTDOWN:
dev_dbg(&port->dev, "%s - urb stopped: %d\n",
__func__, status);
- return;
+ stopped = true;
+ break;
case -EPIPE:
dev_err(&port->dev, "%s - urb stopped: %d\n",
__func__, status);
- return;
+ stopped = true;
+ break;
default:
dev_dbg(&port->dev, "%s - nonzero urb status: %d\n",
__func__, status);
- goto resubmit;
+ break;
}
- usb_serial_debug_data(&port->dev, __func__, urb->actual_length, data);
- port->serial->type->process_read_urb(urb);
+ /*
+ * Make sure URB processing is done before marking as free to avoid
+ * racing with unthrottle() on another CPU. Matches the barriers
+ * implied by the test_and_clear_bit() in
+ * usb_serial_generic_submit_read_urb().
+ */
+ smp_mb__before_atomic();
+ set_bit(i, &port->read_urbs_free);
+ /*
+ * Make sure URB is marked as free before checking the throttled flag
+ * to avoid racing with unthrottle() on another CPU. Matches the
+ * smp_mb() in unthrottle().
+ */
+ smp_mb__after_atomic();
+
+ if (stopped)
+ return;
-resubmit:
/* Throttle the device if requested by tty */
spin_lock_irqsave(&port->lock, flags);
port->throttled = port->throttle_req;
@@ -487,6 +506,12 @@ void usb_serial_generic_unthrottle(struct tty_struct *tty)
port->throttled = port->throttle_req = 0;
spin_unlock_irq(&port->lock);
+ /*
+ * Matches the smp_mb__after_atomic() in
+ * usb_serial_generic_read_bulk_callback().
+ */
+ smp_mb();
+
if (was_throttled)
usb_serial_generic_submit_read_urbs(port, GFP_KERNEL);
}
diff --git a/drivers/usb/storage/realtek_cr.c b/drivers/usb/storage/realtek_cr.c
index 4176d1af9bf2..fac3447021b2 100644
--- a/drivers/usb/storage/realtek_cr.c
+++ b/drivers/usb/storage/realtek_cr.c
@@ -776,18 +776,16 @@ static void rts51x_suspend_timer_fn(unsigned long data)
break;
case RTS51X_STAT_IDLE:
case RTS51X_STAT_SS:
- usb_stor_dbg(us, "RTS51X_STAT_SS, intf->pm_usage_cnt:%d, power.usage:%d\n",
- atomic_read(&us->pusb_intf->pm_usage_cnt),
+ usb_stor_dbg(us, "RTS51X_STAT_SS, power.usage:%d\n",
atomic_read(&us->pusb_intf->dev.power.usage_count));
- if (atomic_read(&us->pusb_intf->pm_usage_cnt) > 0) {
+ if (atomic_read(&us->pusb_intf->dev.power.usage_count) > 0) {
usb_stor_dbg(us, "Ready to enter SS state\n");
rts51x_set_stat(chip, RTS51X_STAT_SS);
/* ignore mass storage interface's children */
pm_suspend_ignore_children(&us->pusb_intf->dev, true);
usb_autopm_put_interface_async(us->pusb_intf);
- usb_stor_dbg(us, "RTS51X_STAT_SS 01, intf->pm_usage_cnt:%d, power.usage:%d\n",
- atomic_read(&us->pusb_intf->pm_usage_cnt),
+ usb_stor_dbg(us, "RTS51X_STAT_SS 01, power.usage:%d\n",
atomic_read(&us->pusb_intf->dev.power.usage_count));
}
break;
@@ -820,11 +818,10 @@ static void rts51x_invoke_transport(struct scsi_cmnd *srb, struct us_data *us)
int ret;
if (working_scsi(srb)) {
- usb_stor_dbg(us, "working scsi, intf->pm_usage_cnt:%d, power.usage:%d\n",
- atomic_read(&us->pusb_intf->pm_usage_cnt),
+ usb_stor_dbg(us, "working scsi, power.usage:%d\n",
atomic_read(&us->pusb_intf->dev.power.usage_count));
- if (atomic_read(&us->pusb_intf->pm_usage_cnt) <= 0) {
+ if (atomic_read(&us->pusb_intf->dev.power.usage_count) <= 0) {
ret = usb_autopm_get_interface(us->pusb_intf);
usb_stor_dbg(us, "working scsi, ret=%d\n", ret);
}
diff --git a/drivers/usb/storage/scsiglue.c b/drivers/usb/storage/scsiglue.c
index 13f2c051dbf2..afb4b0bf47b3 100644
--- a/drivers/usb/storage/scsiglue.c
+++ b/drivers/usb/storage/scsiglue.c
@@ -81,6 +81,7 @@ static const char* host_info(struct Scsi_Host *host)
static int slave_alloc (struct scsi_device *sdev)
{
struct us_data *us = host_to_us(sdev->host);
+ int maxp;
/*
* Set the INQUIRY transfer length to 36. We don't use any of
@@ -90,20 +91,17 @@ static int slave_alloc (struct scsi_device *sdev)
sdev->inquiry_len = 36;
/*
- * USB has unusual DMA-alignment requirements: Although the
- * starting address of each scatter-gather element doesn't matter,
- * the length of each element except the last must be divisible
- * by the Bulk maxpacket value. There's currently no way to
- * express this by block-layer constraints, so we'll cop out
- * and simply require addresses to be aligned at 512-byte
- * boundaries. This is okay since most block I/O involves
- * hardware sectors that are multiples of 512 bytes in length,
- * and since host controllers up through USB 2.0 have maxpacket
- * values no larger than 512.
- *
- * But it doesn't suffice for Wireless USB, where Bulk maxpacket
- * values can be as large as 2048. To make that work properly
- * will require changes to the block layer.
+ * USB has unusual scatter-gather requirements: the length of each
+ * scatterlist element except the last must be divisible by the
+ * Bulk maxpacket value. Fortunately this value is always a
+ * power of 2. Inform the block layer about this requirement.
+ */
+ maxp = usb_maxpacket(us->pusb_dev, us->recv_bulk_pipe, 0);
+ blk_queue_virt_boundary(sdev->request_queue, maxp - 1);
+
+ /*
+ * Some host controllers may have alignment requirements.
+ * We'll play it safe by requiring 512-byte alignment always.
*/
blk_queue_update_dma_alignment(sdev->request_queue, (512 - 1));
diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c
index 64af88977b03..97621e5bdad7 100644
--- a/drivers/usb/storage/uas.c
+++ b/drivers/usb/storage/uas.c
@@ -796,24 +796,33 @@ static int uas_slave_alloc(struct scsi_device *sdev)
{
struct uas_dev_info *devinfo =
(struct uas_dev_info *)sdev->host->hostdata;
+ int maxp;
sdev->hostdata = devinfo;
/*
- * USB has unusual DMA-alignment requirements: Although the
- * starting address of each scatter-gather element doesn't matter,
- * the length of each element except the last must be divisible
- * by the Bulk maxpacket value. There's currently no way to
- * express this by block-layer constraints, so we'll cop out
- * and simply require addresses to be aligned at 512-byte
- * boundaries. This is okay since most block I/O involves
- * hardware sectors that are multiples of 512 bytes in length,
- * and since host controllers up through USB 2.0 have maxpacket
- * values no larger than 512.
+ * We have two requirements here. We must satisfy the requirements
+ * of the physical HC and the demands of the protocol, as we
+ * definitely want no additional memory allocation in this path
+ * ruling out using bounce buffers.
*
- * But it doesn't suffice for Wireless USB, where Bulk maxpacket
- * values can be as large as 2048. To make that work properly
- * will require changes to the block layer.
+ * For a transmission on USB to continue we must never send
+ * a package that is smaller than maxpacket. Hence the length of each
+ * scatterlist element except the last must be divisible by the
+ * Bulk maxpacket value.
+ * If the HC does not ensure that through SG,
+ * the upper layer must do that. We must assume nothing
+ * about the capabilities off the HC, so we use the most
+ * pessimistic requirement.
+ */
+
+ maxp = usb_maxpacket(devinfo->udev, devinfo->data_in_pipe, 0);
+ blk_queue_virt_boundary(sdev->request_queue, maxp - 1);
+
+ /*
+ * The protocol has no requirements on alignment in the strict sense.
+ * Controllers may or may not have alignment restrictions.
+ * As this is not exported, we use an extremely conservative guess.
*/
blk_queue_update_dma_alignment(sdev->request_queue, (512 - 1));
diff --git a/drivers/usb/usbip/stub_rx.c b/drivers/usb/usbip/stub_rx.c
index 5b807185f79e..777a4058c407 100644
--- a/drivers/usb/usbip/stub_rx.c
+++ b/drivers/usb/usbip/stub_rx.c
@@ -383,16 +383,10 @@ static int get_pipe(struct stub_device *sdev, struct usbip_header *pdu)
}
if (usb_endpoint_xfer_isoc(epd)) {
- /* validate packet size and number of packets */
- unsigned int maxp, packets, bytes;
-
- maxp = usb_endpoint_maxp(epd);
- maxp *= usb_endpoint_maxp_mult(epd);
- bytes = pdu->u.cmd_submit.transfer_buffer_length;
- packets = DIV_ROUND_UP(bytes, maxp);
-
+ /* validate number of packets */
if (pdu->u.cmd_submit.number_of_packets < 0 ||
- pdu->u.cmd_submit.number_of_packets > packets) {
+ pdu->u.cmd_submit.number_of_packets >
+ USBIP_MAX_ISO_PACKETS) {
dev_err(&sdev->udev->dev,
"CMD_SUBMIT: isoc invalid num packets %d\n",
pdu->u.cmd_submit.number_of_packets);
diff --git a/drivers/usb/usbip/usbip_common.h b/drivers/usb/usbip/usbip_common.h
index fb7cb252e01c..ff9c7776e77a 100644
--- a/drivers/usb/usbip/usbip_common.h
+++ b/drivers/usb/usbip/usbip_common.h
@@ -137,6 +137,13 @@ extern struct device_attribute dev_attr_usbip_debug;
#define USBIP_DIR_OUT 0x00
#define USBIP_DIR_IN 0x01
+/*
+ * Arbitrary limit for the maximum number of isochronous packets in an URB,
+ * compare for example the uhci_submit_isochronous function in
+ * drivers/usb/host/uhci-q.c
+ */
+#define USBIP_MAX_ISO_PACKETS 1024
+
/**
* struct usbip_header_basic - data pertinent to every request
* @command: the usbip request type
diff --git a/drivers/vfio/mdev/mdev_core.c b/drivers/vfio/mdev/mdev_core.c
index 126991046eb7..4cc8b6281ffa 100644
--- a/drivers/vfio/mdev/mdev_core.c
+++ b/drivers/vfio/mdev/mdev_core.c
@@ -178,10 +178,10 @@ static int mdev_device_remove_ops(struct mdev_device *mdev, bool force_remove)
static int mdev_device_remove_cb(struct device *dev, void *data)
{
- if (!dev_is_mdev(dev))
- return 0;
+ if (dev_is_mdev(dev))
+ mdev_device_remove(dev, true);
- return mdev_device_remove(dev, data ? *(bool *)data : true);
+ return 0;
}
/*
@@ -210,6 +210,7 @@ int mdev_register_device(struct device *dev, const struct mdev_parent_ops *ops)
/* Check for duplicate */
parent = __find_parent_device(dev);
if (parent) {
+ parent = NULL;
ret = -EEXIST;
goto add_dev_err;
}
@@ -269,7 +270,6 @@ EXPORT_SYMBOL(mdev_register_device);
void mdev_unregister_device(struct device *dev)
{
struct mdev_parent *parent;
- bool force_remove = true;
mutex_lock(&parent_list_lock);
parent = __find_parent_device(dev);
@@ -283,8 +283,7 @@ void mdev_unregister_device(struct device *dev)
list_del(&parent->next);
class_compat_remove_link(mdev_bus_compat_class, dev, NULL);
- device_for_each_child(dev, (void *)&force_remove,
- mdev_device_remove_cb);
+ device_for_each_child(dev, NULL, mdev_device_remove_cb);
parent_remove_sysfs_files(parent);
diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index dcac1fffaee3..4041da199a43 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -697,6 +697,7 @@ static long vfio_pci_ioctl(void *device_data,
{
void __iomem *io;
size_t size;
+ u16 orig_cmd;
info.offset = VFIO_PCI_INDEX_TO_OFFSET(info.index);
info.flags = 0;
@@ -712,15 +713,23 @@ static long vfio_pci_ioctl(void *device_data,
break;
}
- /* Is it really there? */
+ /*
+ * Is it really there? Enable memory decode for
+ * implicit access in pci_map_rom().
+ */
+ pci_read_config_word(pdev, PCI_COMMAND, &orig_cmd);
+ pci_write_config_word(pdev, PCI_COMMAND,
+ orig_cmd | PCI_COMMAND_MEMORY);
+
io = pci_map_rom(pdev, &size);
- if (!io || !size) {
+ if (io) {
+ info.flags = VFIO_REGION_INFO_FLAG_READ;
+ pci_unmap_rom(pdev, io);
+ } else {
info.size = 0;
- break;
}
- pci_unmap_rom(pdev, io);
- info.flags = VFIO_REGION_INFO_FLAG_READ;
+ pci_write_config_word(pdev, PCI_COMMAND, orig_cmd);
break;
}
case VFIO_PCI_VGA_REGION_INDEX:
@@ -1436,11 +1445,11 @@ static void __init vfio_pci_fill_ids(void)
rc = pci_add_dynid(&vfio_pci_driver, vendor, device,
subvendor, subdevice, class, class_mask, 0);
if (rc)
- pr_warn("failed to add dynamic id [%04hx:%04hx[%04hx:%04hx]] class %#08x/%08x (%d)\n",
+ pr_warn("failed to add dynamic id [%04x:%04x[%04x:%04x]] class %#08x/%08x (%d)\n",
vendor, device, subvendor, subdevice,
class, class_mask, rc);
else
- pr_info("add [%04hx:%04hx[%04hx:%04hx]] class %#08x/%08x\n",
+ pr_info("add [%04x:%04x[%04x:%04x]] class %#08x/%08x\n",
vendor, device, subvendor, subdevice,
class, class_mask);
}
diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index 6db66c1e0a86..698b734b8a2e 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -563,13 +563,21 @@ static void vhost_vsock_reset_orphans(struct sock *sk)
* executing.
*/
- if (!vhost_vsock_get(vsk->remote_addr.svm_cid)) {
- sock_set_flag(sk, SOCK_DONE);
- vsk->peer_shutdown = SHUTDOWN_MASK;
- sk->sk_state = SS_UNCONNECTED;
- sk->sk_err = ECONNRESET;
- sk->sk_error_report(sk);
- }
+ /* If the peer is still valid, no need to reset connection */
+ if (vhost_vsock_get(vsk->remote_addr.svm_cid))
+ return;
+
+ /* If the close timeout is pending, let it expire. This avoids races
+ * with the timeout callback.
+ */
+ if (vsk->close_work_scheduled)
+ return;
+
+ sock_set_flag(sk, SOCK_DONE);
+ vsk->peer_shutdown = SHUTDOWN_MASK;
+ sk->sk_state = SS_UNCONNECTED;
+ sk->sk_err = ECONNRESET;
+ sk->sk_error_report(sk);
}
static int vhost_vsock_dev_release(struct inode *inode, struct file *file)
diff --git a/drivers/video/fbdev/omap2/omapfb/dss/omapdss-boot-init.c b/drivers/video/fbdev/omap2/omapfb/dss/omapdss-boot-init.c
index 136d30484d02..cb6acbac9c47 100644
--- a/drivers/video/fbdev/omap2/omapfb/dss/omapdss-boot-init.c
+++ b/drivers/video/fbdev/omap2/omapfb/dss/omapdss-boot-init.c
@@ -193,8 +193,10 @@ static int __init omapdss_boot_init(void)
dss = of_find_matching_node(NULL, omapdss_of_match);
- if (dss == NULL || !of_device_is_available(dss))
+ if (dss == NULL || !of_device_is_available(dss)) {
+ of_node_put(dss);
return 0;
+ }
omapdss_walk_device(dss, true);
diff --git a/drivers/virtio/virtio_pci_common.c b/drivers/virtio/virtio_pci_common.c
index 1c4797e53f68..80a3704939cd 100644
--- a/drivers/virtio/virtio_pci_common.c
+++ b/drivers/virtio/virtio_pci_common.c
@@ -254,9 +254,11 @@ void vp_del_vqs(struct virtio_device *vdev)
for (i = 0; i < vp_dev->msix_used_vectors; ++i)
free_irq(pci_irq_vector(vp_dev->pci_dev, i), vp_dev);
- for (i = 0; i < vp_dev->msix_vectors; i++)
- if (vp_dev->msix_affinity_masks[i])
- free_cpumask_var(vp_dev->msix_affinity_masks[i]);
+ if (vp_dev->msix_affinity_masks) {
+ for (i = 0; i < vp_dev->msix_vectors; i++)
+ if (vp_dev->msix_affinity_masks[i])
+ free_cpumask_var(vp_dev->msix_affinity_masks[i]);
+ }
if (vp_dev->msix_enabled) {
/* Disable the vector used for configuration */
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index 30bc03f2bf12..151dee26eaf4 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -1097,6 +1097,8 @@ struct virtqueue *vring_create_virtqueue(
GFP_KERNEL|__GFP_NOWARN|__GFP_ZERO);
if (queue)
break;
+ if (!may_reduce_num)
+ return NULL;
}
if (!num)
diff --git a/drivers/w1/masters/ds2490.c b/drivers/w1/masters/ds2490.c
index be77b7914fad..748713ad7870 100644
--- a/drivers/w1/masters/ds2490.c
+++ b/drivers/w1/masters/ds2490.c
@@ -1038,15 +1038,15 @@ static int ds_probe(struct usb_interface *intf,
/* alternative 3, 1ms interrupt (greatly speeds search), 64 byte bulk */
alt = 3;
err = usb_set_interface(dev->udev,
- intf->altsetting[alt].desc.bInterfaceNumber, alt);
+ intf->cur_altsetting->desc.bInterfaceNumber, alt);
if (err) {
dev_err(&dev->udev->dev, "Failed to set alternative setting %d "
"for %d interface: err=%d.\n", alt,
- intf->altsetting[alt].desc.bInterfaceNumber, err);
+ intf->cur_altsetting->desc.bInterfaceNumber, err);
goto err_out_clear;
}
- iface_desc = &intf->altsetting[alt];
+ iface_desc = intf->cur_altsetting;
if (iface_desc->desc.bNumEndpoints != NUM_EP-1) {
pr_info("Num endpoints=%d. It is not DS9490R.\n",
iface_desc->desc.bNumEndpoints);
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 4acd35663ae7..7a9a14df1d82 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -256,7 +256,6 @@ __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter,
task_io_account_write(ret);
}
- bio_get(&bio);
qc = submit_bio(&bio);
for (;;) {
set_current_state(TASK_UNINTERRUPTIBLE);
@@ -276,7 +275,7 @@ __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter,
if (unlikely(bio.bi_status))
ret = blk_status_to_errno(bio.bi_status);
- bio_put(&bio);
+
out:
if (vecs != inline_vecs)
kfree(vecs);
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index 5a5df0b29776..deaeae612f3a 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -770,6 +770,7 @@ static int add_delayed_refs(const struct btrfs_fs_info *fs_info,
struct btrfs_key key;
struct btrfs_key tmp_op_key;
struct btrfs_key *op_key = NULL;
+ struct rb_node *n;
int count;
int ret = 0;
@@ -779,7 +780,9 @@ static int add_delayed_refs(const struct btrfs_fs_info *fs_info,
}
spin_lock(&head->lock);
- list_for_each_entry(node, &head->ref_list, list) {
+ for (n = rb_first(&head->ref_tree); n; n = rb_next(n)) {
+ node = rb_entry(n, struct btrfs_delayed_ref_node,
+ ref_node);
if (node->seq > seq)
continue;
@@ -1175,7 +1178,7 @@ again:
head = btrfs_find_delayed_ref_head(delayed_refs, bytenr);
if (head) {
if (!mutex_trylock(&head->mutex)) {
- refcount_inc(&head->node.refs);
+ refcount_inc(&head->refs);
spin_unlock(&delayed_refs->lock);
btrfs_release_path(path);
@@ -1186,7 +1189,7 @@ again:
*/
mutex_lock(&head->mutex);
mutex_unlock(&head->mutex);
- btrfs_put_delayed_ref(&head->node);
+ btrfs_put_delayed_ref_head(head);
goto again;
}
spin_unlock(&delayed_refs->lock);
diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c
index 120a6d9fa064..39b397cb38c8 100644
--- a/fs/btrfs/delayed-ref.c
+++ b/fs/btrfs/delayed-ref.c
@@ -124,15 +124,43 @@ static struct btrfs_delayed_ref_head *htree_insert(struct rb_root *root,
u64 bytenr;
ins = rb_entry(node, struct btrfs_delayed_ref_head, href_node);
- bytenr = ins->node.bytenr;
+ bytenr = ins->bytenr;
while (*p) {
parent_node = *p;
entry = rb_entry(parent_node, struct btrfs_delayed_ref_head,
href_node);
- if (bytenr < entry->node.bytenr)
+ if (bytenr < entry->bytenr)
p = &(*p)->rb_left;
- else if (bytenr > entry->node.bytenr)
+ else if (bytenr > entry->bytenr)
+ p = &(*p)->rb_right;
+ else
+ return entry;
+ }
+
+ rb_link_node(node, parent_node, p);
+ rb_insert_color(node, root);
+ return NULL;
+}
+
+static struct btrfs_delayed_ref_node* tree_insert(struct rb_root *root,
+ struct btrfs_delayed_ref_node *ins)
+{
+ struct rb_node **p = &root->rb_node;
+ struct rb_node *node = &ins->ref_node;
+ struct rb_node *parent_node = NULL;
+ struct btrfs_delayed_ref_node *entry;
+
+ while (*p) {
+ int comp;
+
+ parent_node = *p;
+ entry = rb_entry(parent_node, struct btrfs_delayed_ref_node,
+ ref_node);
+ comp = comp_refs(ins, entry, true);
+ if (comp < 0)
+ p = &(*p)->rb_left;
+ else if (comp > 0)
p = &(*p)->rb_right;
else
return entry;
@@ -161,15 +189,15 @@ find_ref_head(struct rb_root *root, u64 bytenr,
while (n) {
entry = rb_entry(n, struct btrfs_delayed_ref_head, href_node);
- if (bytenr < entry->node.bytenr)
+ if (bytenr < entry->bytenr)
n = n->rb_left;
- else if (bytenr > entry->node.bytenr)
+ else if (bytenr > entry->bytenr)
n = n->rb_right;
else
return entry;
}
if (entry && return_bigger) {
- if (bytenr > entry->node.bytenr) {
+ if (bytenr > entry->bytenr) {
n = rb_next(&entry->href_node);
if (!n)
n = rb_first(root);
@@ -192,17 +220,17 @@ int btrfs_delayed_ref_lock(struct btrfs_trans_handle *trans,
if (mutex_trylock(&head->mutex))
return 0;
- refcount_inc(&head->node.refs);
+ refcount_inc(&head->refs);
spin_unlock(&delayed_refs->lock);
mutex_lock(&head->mutex);
spin_lock(&delayed_refs->lock);
- if (!head->node.in_tree) {
+ if (RB_EMPTY_NODE(&head->href_node)) {
mutex_unlock(&head->mutex);
- btrfs_put_delayed_ref(&head->node);
+ btrfs_put_delayed_ref_head(head);
return -EAGAIN;
}
- btrfs_put_delayed_ref(&head->node);
+ btrfs_put_delayed_ref_head(head);
return 0;
}
@@ -211,15 +239,11 @@ static inline void drop_delayed_ref(struct btrfs_trans_handle *trans,
struct btrfs_delayed_ref_head *head,
struct btrfs_delayed_ref_node *ref)
{
- if (btrfs_delayed_ref_is_head(ref)) {
- head = btrfs_delayed_node_to_head(ref);
- rb_erase(&head->href_node, &delayed_refs->href_root);
- } else {
- assert_spin_locked(&head->lock);
- list_del(&ref->list);
- if (!list_empty(&ref->add_list))
- list_del(&ref->add_list);
- }
+ assert_spin_locked(&head->lock);
+ rb_erase(&ref->ref_node, &head->ref_tree);
+ RB_CLEAR_NODE(&ref->ref_node);
+ if (!list_empty(&ref->add_list))
+ list_del(&ref->add_list);
ref->in_tree = 0;
btrfs_put_delayed_ref(ref);
atomic_dec(&delayed_refs->num_entries);
@@ -234,24 +258,18 @@ static bool merge_ref(struct btrfs_trans_handle *trans,
u64 seq)
{
struct btrfs_delayed_ref_node *next;
+ struct rb_node *node = rb_next(&ref->ref_node);
bool done = false;
- next = list_first_entry(&head->ref_list, struct btrfs_delayed_ref_node,
- list);
- while (!done && &next->list != &head->ref_list) {
+ while (!done && node) {
int mod;
- struct btrfs_delayed_ref_node *next2;
-
- next2 = list_next_entry(next, list);
-
- if (next == ref)
- goto next;
+ next = rb_entry(node, struct btrfs_delayed_ref_node, ref_node);
+ node = rb_next(node);
if (seq && next->seq >= seq)
- goto next;
-
+ break;
if (comp_refs(ref, next, false))
- goto next;
+ break;
if (ref->action == next->action) {
mod = next->ref_mod;
@@ -275,8 +293,6 @@ static bool merge_ref(struct btrfs_trans_handle *trans,
WARN_ON(ref->type == BTRFS_TREE_BLOCK_REF_KEY ||
ref->type == BTRFS_SHARED_BLOCK_REF_KEY);
}
-next:
- next = next2;
}
return done;
@@ -288,11 +304,12 @@ void btrfs_merge_delayed_refs(struct btrfs_trans_handle *trans,
struct btrfs_delayed_ref_head *head)
{
struct btrfs_delayed_ref_node *ref;
+ struct rb_node *node;
u64 seq = 0;
assert_spin_locked(&head->lock);
- if (list_empty(&head->ref_list))
+ if (RB_EMPTY_ROOT(&head->ref_tree))
return;
/* We don't have too many refs to merge for data. */
@@ -309,22 +326,13 @@ void btrfs_merge_delayed_refs(struct btrfs_trans_handle *trans,
}
spin_unlock(&fs_info->tree_mod_seq_lock);
- ref = list_first_entry(&head->ref_list, struct btrfs_delayed_ref_node,
- list);
- while (&ref->list != &head->ref_list) {
+again:
+ for (node = rb_first(&head->ref_tree); node; node = rb_next(node)) {
+ ref = rb_entry(node, struct btrfs_delayed_ref_node, ref_node);
if (seq && ref->seq >= seq)
- goto next;
-
- if (merge_ref(trans, delayed_refs, head, ref, seq)) {
- if (list_empty(&head->ref_list))
- break;
- ref = list_first_entry(&head->ref_list,
- struct btrfs_delayed_ref_node,
- list);
continue;
- }
-next:
- ref = list_next_entry(ref, list);
+ if (merge_ref(trans, delayed_refs, head, ref, seq))
+ goto again;
}
}
@@ -396,8 +404,8 @@ again:
head->processing = 1;
WARN_ON(delayed_refs->num_heads_ready == 0);
delayed_refs->num_heads_ready--;
- delayed_refs->run_delayed_start = head->node.bytenr +
- head->node.num_bytes;
+ delayed_refs->run_delayed_start = head->bytenr +
+ head->num_bytes;
return head;
}
@@ -407,25 +415,19 @@ again:
* Return 0 for insert.
* Return >0 for merge.
*/
-static int
-add_delayed_ref_tail_merge(struct btrfs_trans_handle *trans,
- struct btrfs_delayed_ref_root *root,
- struct btrfs_delayed_ref_head *href,
- struct btrfs_delayed_ref_node *ref)
+static int insert_delayed_ref(struct btrfs_trans_handle *trans,
+ struct btrfs_delayed_ref_root *root,
+ struct btrfs_delayed_ref_head *href,
+ struct btrfs_delayed_ref_node *ref)
{
struct btrfs_delayed_ref_node *exist;
int mod;
int ret = 0;
spin_lock(&href->lock);
- /* Check whether we can merge the tail node with ref */
- if (list_empty(&href->ref_list))
- goto add_tail;
- exist = list_entry(href->ref_list.prev, struct btrfs_delayed_ref_node,
- list);
- /* No need to compare bytenr nor is_head */
- if (comp_refs(exist, ref, true))
- goto add_tail;
+ exist = tree_insert(&href->ref_tree, ref);
+ if (!exist)
+ goto inserted;
/* Now we are sure we can merge */
ret = 1;
@@ -456,9 +458,7 @@ add_delayed_ref_tail_merge(struct btrfs_trans_handle *trans,
drop_delayed_ref(trans, root, href, exist);
spin_unlock(&href->lock);
return ret;
-
-add_tail:
- list_add_tail(&ref->list, &href->ref_list);
+inserted:
if (ref->action == BTRFS_ADD_DELAYED_REF)
list_add_tail(&ref->add_list, &href->ref_add_list);
atomic_inc(&root->num_entries);
@@ -473,20 +473,16 @@ add_tail:
*/
static noinline void
update_existing_head_ref(struct btrfs_delayed_ref_root *delayed_refs,
- struct btrfs_delayed_ref_node *existing,
- struct btrfs_delayed_ref_node *update,
+ struct btrfs_delayed_ref_head *existing,
+ struct btrfs_delayed_ref_head *update,
int *old_ref_mod_ret)
{
- struct btrfs_delayed_ref_head *existing_ref;
- struct btrfs_delayed_ref_head *ref;
int old_ref_mod;
- existing_ref = btrfs_delayed_node_to_head(existing);
- ref = btrfs_delayed_node_to_head(update);
- BUG_ON(existing_ref->is_data != ref->is_data);
+ BUG_ON(existing->is_data != update->is_data);
- spin_lock(&existing_ref->lock);
- if (ref->must_insert_reserved) {
+ spin_lock(&existing->lock);
+ if (update->must_insert_reserved) {
/* if the extent was freed and then
* reallocated before the delayed ref
* entries were processed, we can end up
@@ -494,7 +490,7 @@ update_existing_head_ref(struct btrfs_delayed_ref_root *delayed_refs,
* the must_insert_reserved flag set.
* Set it again here
*/
- existing_ref->must_insert_reserved = ref->must_insert_reserved;
+ existing->must_insert_reserved = update->must_insert_reserved;
/*
* update the num_bytes so we make sure the accounting
@@ -504,22 +500,22 @@ update_existing_head_ref(struct btrfs_delayed_ref_root *delayed_refs,
}
- if (ref->extent_op) {
- if (!existing_ref->extent_op) {
- existing_ref->extent_op = ref->extent_op;
+ if (update->extent_op) {
+ if (!existing->extent_op) {
+ existing->extent_op = update->extent_op;
} else {
- if (ref->extent_op->update_key) {
- memcpy(&existing_ref->extent_op->key,
- &ref->extent_op->key,
- sizeof(ref->extent_op->key));
- existing_ref->extent_op->update_key = true;
+ if (update->extent_op->update_key) {
+ memcpy(&existing->extent_op->key,
+ &update->extent_op->key,
+ sizeof(update->extent_op->key));
+ existing->extent_op->update_key = true;
}
- if (ref->extent_op->update_flags) {
- existing_ref->extent_op->flags_to_set |=
- ref->extent_op->flags_to_set;
- existing_ref->extent_op->update_flags = true;
+ if (update->extent_op->update_flags) {
+ existing->extent_op->flags_to_set |=
+ update->extent_op->flags_to_set;
+ existing->extent_op->update_flags = true;
}
- btrfs_free_delayed_extent_op(ref->extent_op);
+ btrfs_free_delayed_extent_op(update->extent_op);
}
}
/*
@@ -527,43 +523,31 @@ update_existing_head_ref(struct btrfs_delayed_ref_root *delayed_refs,
* only need the lock for this case cause we could be processing it
* currently, for refs we just added we know we're a-ok.
*/
- old_ref_mod = existing_ref->total_ref_mod;
+ old_ref_mod = existing->total_ref_mod;
if (old_ref_mod_ret)
*old_ref_mod_ret = old_ref_mod;
existing->ref_mod += update->ref_mod;
- existing_ref->total_ref_mod += update->ref_mod;
+ existing->total_ref_mod += update->ref_mod;
/*
* If we are going to from a positive ref mod to a negative or vice
* versa we need to make sure to adjust pending_csums accordingly.
*/
- if (existing_ref->is_data) {
- if (existing_ref->total_ref_mod >= 0 && old_ref_mod < 0)
+ if (existing->is_data) {
+ if (existing->total_ref_mod >= 0 && old_ref_mod < 0)
delayed_refs->pending_csums -= existing->num_bytes;
- if (existing_ref->total_ref_mod < 0 && old_ref_mod >= 0)
+ if (existing->total_ref_mod < 0 && old_ref_mod >= 0)
delayed_refs->pending_csums += existing->num_bytes;
}
- spin_unlock(&existing_ref->lock);
+ spin_unlock(&existing->lock);
}
-/*
- * helper function to actually insert a head node into the rbtree.
- * this does all the dirty work in terms of maintaining the correct
- * overall modification count.
- */
-static noinline struct btrfs_delayed_ref_head *
-add_delayed_ref_head(struct btrfs_fs_info *fs_info,
- struct btrfs_trans_handle *trans,
- struct btrfs_delayed_ref_node *ref,
- struct btrfs_qgroup_extent_record *qrecord,
- u64 bytenr, u64 num_bytes, u64 ref_root, u64 reserved,
- int action, int is_data, int is_system,
- int *old_ref_mod, int *new_ref_mod)
-
+static void init_delayed_ref_head(struct btrfs_delayed_ref_head *head_ref,
+ struct btrfs_qgroup_extent_record *qrecord,
+ u64 bytenr, u64 num_bytes, u64 ref_root,
+ u64 reserved, int action, bool is_data,
+ bool is_system)
{
- struct btrfs_delayed_ref_head *existing;
- struct btrfs_delayed_ref_head *head_ref = NULL;
- struct btrfs_delayed_ref_root *delayed_refs;
int count_mod = 1;
int must_insert_reserved = 0;
@@ -571,7 +555,7 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info,
BUG_ON(!is_data && reserved);
/*
- * the head node stores the sum of all the mods, so dropping a ref
+ * The head node stores the sum of all the mods, so dropping a ref
* should drop the sum in the head node by one.
*/
if (action == BTRFS_UPDATE_DELAYED_HEAD)
@@ -580,12 +564,11 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info,
count_mod = -1;
/*
- * BTRFS_ADD_DELAYED_EXTENT means that we need to update
- * the reserved accounting when the extent is finally added, or
- * if a later modification deletes the delayed ref without ever
- * inserting the extent into the extent allocation tree.
- * ref->must_insert_reserved is the flag used to record
- * that accounting mods are required.
+ * BTRFS_ADD_DELAYED_EXTENT means that we need to update the reserved
+ * accounting when the extent is finally added, or if a later
+ * modification deletes the delayed ref without ever inserting the
+ * extent into the extent allocation tree. ref->must_insert_reserved
+ * is the flag used to record that accounting mods are required.
*
* Once we record must_insert_reserved, switch the action to
* BTRFS_ADD_DELAYED_REF because other special casing is not required.
@@ -595,29 +578,21 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info,
else
must_insert_reserved = 0;
- delayed_refs = &trans->transaction->delayed_refs;
-
- /* first set the basic ref node struct up */
- refcount_set(&ref->refs, 1);
- ref->bytenr = bytenr;
- ref->num_bytes = num_bytes;
- ref->ref_mod = count_mod;
- ref->type = 0;
- ref->action = 0;
- ref->is_head = 1;
- ref->in_tree = 1;
- ref->seq = 0;
-
- head_ref = btrfs_delayed_node_to_head(ref);
+ refcount_set(&head_ref->refs, 1);
+ head_ref->bytenr = bytenr;
+ head_ref->num_bytes = num_bytes;
+ head_ref->ref_mod = count_mod;
head_ref->must_insert_reserved = must_insert_reserved;
head_ref->is_data = is_data;
head_ref->is_system = is_system;
- INIT_LIST_HEAD(&head_ref->ref_list);
+ head_ref->ref_tree = RB_ROOT;
INIT_LIST_HEAD(&head_ref->ref_add_list);
+ RB_CLEAR_NODE(&head_ref->href_node);
head_ref->processing = 0;
head_ref->total_ref_mod = count_mod;
+ spin_lock_init(&head_ref->lock);
+ mutex_init(&head_ref->mutex);
- /* Record qgroup extent info if provided */
if (qrecord) {
if (ref_root && reserved) {
qrecord->data_rsv = reserved;
@@ -627,21 +602,40 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info,
qrecord->bytenr = bytenr;
qrecord->num_bytes = num_bytes;
qrecord->old_roots = NULL;
+ }
+}
+
+/*
+ * helper function to actually insert a head node into the rbtree.
+ * this does all the dirty work in terms of maintaining the correct
+ * overall modification count.
+ */
+static noinline struct btrfs_delayed_ref_head *
+add_delayed_ref_head(struct btrfs_fs_info *fs_info,
+ struct btrfs_trans_handle *trans,
+ struct btrfs_delayed_ref_head *head_ref,
+ struct btrfs_qgroup_extent_record *qrecord,
+ int action, int *old_ref_mod, int *new_ref_mod)
+
+{
+ struct btrfs_delayed_ref_head *existing;
+ struct btrfs_delayed_ref_root *delayed_refs;
- if(btrfs_qgroup_trace_extent_nolock(fs_info,
+ delayed_refs = &trans->transaction->delayed_refs;
+
+ /* Record qgroup extent info if provided */
+ if (qrecord) {
+ if (btrfs_qgroup_trace_extent_nolock(fs_info,
delayed_refs, qrecord))
kfree(qrecord);
}
- spin_lock_init(&head_ref->lock);
- mutex_init(&head_ref->mutex);
-
- trace_add_delayed_ref_head(fs_info, ref, head_ref, action);
+ trace_add_delayed_ref_head(fs_info, head_ref, action);
existing = htree_insert(&delayed_refs->href_root,
&head_ref->href_node);
if (existing) {
- update_existing_head_ref(delayed_refs, &existing->node, ref,
+ update_existing_head_ref(delayed_refs, existing, head_ref,
old_ref_mod);
/*
* we've updated the existing ref, free the newly
@@ -652,8 +646,8 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info,
} else {
if (old_ref_mod)
*old_ref_mod = 0;
- if (is_data && count_mod < 0)
- delayed_refs->pending_csums += num_bytes;
+ if (head_ref->is_data && head_ref->ref_mod < 0)
+ delayed_refs->pending_csums += head_ref->num_bytes;
delayed_refs->num_heads++;
delayed_refs->num_heads_ready++;
atomic_inc(&delayed_refs->num_entries);
@@ -661,90 +655,48 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info,
}
if (new_ref_mod)
*new_ref_mod = head_ref->total_ref_mod;
- return head_ref;
-}
-/*
- * helper to insert a delayed tree ref into the rbtree.
- */
-static noinline void
-add_delayed_tree_ref(struct btrfs_fs_info *fs_info,
- struct btrfs_trans_handle *trans,
- struct btrfs_delayed_ref_head *head_ref,
- struct btrfs_delayed_ref_node *ref, u64 bytenr,
- u64 num_bytes, u64 parent, u64 ref_root, int level,
- int action)
-{
- struct btrfs_delayed_tree_ref *full_ref;
- struct btrfs_delayed_ref_root *delayed_refs;
- u64 seq = 0;
- int ret;
-
- if (action == BTRFS_ADD_DELAYED_EXTENT)
- action = BTRFS_ADD_DELAYED_REF;
-
- if (is_fstree(ref_root))
- seq = atomic64_read(&fs_info->tree_mod_seq);
- delayed_refs = &trans->transaction->delayed_refs;
-
- /* first set the basic ref node struct up */
- refcount_set(&ref->refs, 1);
- ref->bytenr = bytenr;
- ref->num_bytes = num_bytes;
- ref->ref_mod = 1;
- ref->action = action;
- ref->is_head = 0;
- ref->in_tree = 1;
- ref->seq = seq;
- INIT_LIST_HEAD(&ref->list);
- INIT_LIST_HEAD(&ref->add_list);
-
- full_ref = btrfs_delayed_node_to_tree_ref(ref);
- full_ref->parent = parent;
- full_ref->root = ref_root;
- if (parent)
- ref->type = BTRFS_SHARED_BLOCK_REF_KEY;
- else
- ref->type = BTRFS_TREE_BLOCK_REF_KEY;
- full_ref->level = level;
-
- trace_add_delayed_tree_ref(fs_info, ref, full_ref, action);
-
- ret = add_delayed_ref_tail_merge(trans, delayed_refs, head_ref, ref);
-
- /*
- * XXX: memory should be freed at the same level allocated.
- * But bad practice is anywhere... Follow it now. Need cleanup.
- */
- if (ret > 0)
- kmem_cache_free(btrfs_delayed_tree_ref_cachep, full_ref);
+ return head_ref;
}
/*
- * helper to insert a delayed data ref into the rbtree.
+ * init_delayed_ref_common - Initialize the structure which represents a
+ * modification to a an extent.
+ *
+ * @fs_info: Internal to the mounted filesystem mount structure.
+ *
+ * @ref: The structure which is going to be initialized.
+ *
+ * @bytenr: The logical address of the extent for which a modification is
+ * going to be recorded.
+ *
+ * @num_bytes: Size of the extent whose modification is being recorded.
+ *
+ * @ref_root: The id of the root where this modification has originated, this
+ * can be either one of the well-known metadata trees or the
+ * subvolume id which references this extent.
+ *
+ * @action: Can be one of BTRFS_ADD_DELAYED_REF/BTRFS_DROP_DELAYED_REF or
+ * BTRFS_ADD_DELAYED_EXTENT
+ *
+ * @ref_type: Holds the type of the extent which is being recorded, can be
+ * one of BTRFS_SHARED_BLOCK_REF_KEY/BTRFS_TREE_BLOCK_REF_KEY
+ * when recording a metadata extent or BTRFS_SHARED_DATA_REF_KEY/
+ * BTRFS_EXTENT_DATA_REF_KEY when recording data extent
*/
-static noinline void
-add_delayed_data_ref(struct btrfs_fs_info *fs_info,
- struct btrfs_trans_handle *trans,
- struct btrfs_delayed_ref_head *head_ref,
- struct btrfs_delayed_ref_node *ref, u64 bytenr,
- u64 num_bytes, u64 parent, u64 ref_root, u64 owner,
- u64 offset, int action)
+static void init_delayed_ref_common(struct btrfs_fs_info *fs_info,
+ struct btrfs_delayed_ref_node *ref,
+ u64 bytenr, u64 num_bytes, u64 ref_root,
+ int action, u8 ref_type)
{
- struct btrfs_delayed_data_ref *full_ref;
- struct btrfs_delayed_ref_root *delayed_refs;
u64 seq = 0;
- int ret;
if (action == BTRFS_ADD_DELAYED_EXTENT)
action = BTRFS_ADD_DELAYED_REF;
- delayed_refs = &trans->transaction->delayed_refs;
-
if (is_fstree(ref_root))
seq = atomic64_read(&fs_info->tree_mod_seq);
- /* first set the basic ref node struct up */
refcount_set(&ref->refs, 1);
ref->bytenr = bytenr;
ref->num_bytes = num_bytes;
@@ -753,26 +705,9 @@ add_delayed_data_ref(struct btrfs_fs_info *fs_info,
ref->is_head = 0;
ref->in_tree = 1;
ref->seq = seq;
- INIT_LIST_HEAD(&ref->list);
+ ref->type = ref_type;
+ RB_CLEAR_NODE(&ref->ref_node);
INIT_LIST_HEAD(&ref->add_list);
-
- full_ref = btrfs_delayed_node_to_data_ref(ref);
- full_ref->parent = parent;
- full_ref->root = ref_root;
- if (parent)
- ref->type = BTRFS_SHARED_DATA_REF_KEY;
- else
- ref->type = BTRFS_EXTENT_DATA_REF_KEY;
-
- full_ref->objectid = owner;
- full_ref->offset = offset;
-
- trace_add_delayed_data_ref(fs_info, ref, full_ref, action);
-
- ret = add_delayed_ref_tail_merge(trans, delayed_refs, head_ref, ref);
-
- if (ret > 0)
- kmem_cache_free(btrfs_delayed_data_ref_cachep, full_ref);
}
/*
@@ -791,13 +726,25 @@ int btrfs_add_delayed_tree_ref(struct btrfs_fs_info *fs_info,
struct btrfs_delayed_ref_head *head_ref;
struct btrfs_delayed_ref_root *delayed_refs;
struct btrfs_qgroup_extent_record *record = NULL;
- int is_system = (ref_root == BTRFS_CHUNK_TREE_OBJECTID);
+ bool is_system = (ref_root == BTRFS_CHUNK_TREE_OBJECTID);
+ int ret;
+ u8 ref_type;
BUG_ON(extent_op && extent_op->is_data);
ref = kmem_cache_alloc(btrfs_delayed_tree_ref_cachep, GFP_NOFS);
if (!ref)
return -ENOMEM;
+ if (parent)
+ ref_type = BTRFS_SHARED_BLOCK_REF_KEY;
+ else
+ ref_type = BTRFS_TREE_BLOCK_REF_KEY;
+ init_delayed_ref_common(fs_info, &ref->node, bytenr, num_bytes,
+ ref_root, action, ref_type);
+ ref->root = ref_root;
+ ref->parent = parent;
+ ref->level = level;
+
head_ref = kmem_cache_alloc(btrfs_delayed_ref_head_cachep, GFP_NOFS);
if (!head_ref)
goto free_ref;
@@ -809,6 +756,8 @@ int btrfs_add_delayed_tree_ref(struct btrfs_fs_info *fs_info,
goto free_head_ref;
}
+ init_delayed_ref_head(head_ref, record, bytenr, num_bytes,
+ ref_root, 0, action, false, is_system);
head_ref->extent_op = extent_op;
delayed_refs = &trans->transaction->delayed_refs;
@@ -818,14 +767,19 @@ int btrfs_add_delayed_tree_ref(struct btrfs_fs_info *fs_info,
* insert both the head node and the new ref without dropping
* the spin lock
*/
- head_ref = add_delayed_ref_head(fs_info, trans, &head_ref->node, record,
- bytenr, num_bytes, 0, 0, action, 0,
- is_system, old_ref_mod, new_ref_mod);
+ head_ref = add_delayed_ref_head(fs_info, trans, head_ref, record,
+ action, old_ref_mod, new_ref_mod);
- add_delayed_tree_ref(fs_info, trans, head_ref, &ref->node, bytenr,
- num_bytes, parent, ref_root, level, action);
+
+ ret = insert_delayed_ref(trans, delayed_refs, head_ref, &ref->node);
spin_unlock(&delayed_refs->lock);
+ trace_add_delayed_tree_ref(fs_info, &ref->node, ref,
+ action == BTRFS_ADD_DELAYED_EXTENT ?
+ BTRFS_ADD_DELAYED_REF : action);
+ if (ret > 0)
+ kmem_cache_free(btrfs_delayed_tree_ref_cachep, ref);
+
return 0;
free_head_ref:
@@ -850,11 +804,25 @@ int btrfs_add_delayed_data_ref(struct btrfs_fs_info *fs_info,
struct btrfs_delayed_ref_head *head_ref;
struct btrfs_delayed_ref_root *delayed_refs;
struct btrfs_qgroup_extent_record *record = NULL;
+ int ret;
+ u8 ref_type;
ref = kmem_cache_alloc(btrfs_delayed_data_ref_cachep, GFP_NOFS);
if (!ref)
return -ENOMEM;
+ if (parent)
+ ref_type = BTRFS_SHARED_DATA_REF_KEY;
+ else
+ ref_type = BTRFS_EXTENT_DATA_REF_KEY;
+ init_delayed_ref_common(fs_info, &ref->node, bytenr, num_bytes,
+ ref_root, action, ref_type);
+ ref->root = ref_root;
+ ref->parent = parent;
+ ref->objectid = owner;
+ ref->offset = offset;
+
+
head_ref = kmem_cache_alloc(btrfs_delayed_ref_head_cachep, GFP_NOFS);
if (!head_ref) {
kmem_cache_free(btrfs_delayed_data_ref_cachep, ref);
@@ -872,6 +840,8 @@ int btrfs_add_delayed_data_ref(struct btrfs_fs_info *fs_info,
}
}
+ init_delayed_ref_head(head_ref, record, bytenr, num_bytes, ref_root,
+ reserved, action, true, false);
head_ref->extent_op = NULL;
delayed_refs = &trans->transaction->delayed_refs;
@@ -881,15 +851,18 @@ int btrfs_add_delayed_data_ref(struct btrfs_fs_info *fs_info,
* insert both the head node and the new ref without dropping
* the spin lock
*/
- head_ref = add_delayed_ref_head(fs_info, trans, &head_ref->node, record,
- bytenr, num_bytes, ref_root, reserved,
- action, 1, 0, old_ref_mod, new_ref_mod);
+ head_ref = add_delayed_ref_head(fs_info, trans, head_ref, record,
+ action, old_ref_mod, new_ref_mod);
- add_delayed_data_ref(fs_info, trans, head_ref, &ref->node, bytenr,
- num_bytes, parent, ref_root, owner, offset,
- action);
+ ret = insert_delayed_ref(trans, delayed_refs, head_ref, &ref->node);
spin_unlock(&delayed_refs->lock);
+ trace_add_delayed_data_ref(trans->fs_info, &ref->node, ref,
+ action == BTRFS_ADD_DELAYED_EXTENT ?
+ BTRFS_ADD_DELAYED_REF : action);
+ if (ret > 0)
+ kmem_cache_free(btrfs_delayed_data_ref_cachep, ref);
+
return 0;
}
@@ -905,19 +878,17 @@ int btrfs_add_delayed_extent_op(struct btrfs_fs_info *fs_info,
if (!head_ref)
return -ENOMEM;
+ init_delayed_ref_head(head_ref, NULL, bytenr, num_bytes, 0, 0,
+ BTRFS_UPDATE_DELAYED_HEAD, extent_op->is_data,
+ false);
head_ref->extent_op = extent_op;
delayed_refs = &trans->transaction->delayed_refs;
spin_lock(&delayed_refs->lock);
- /*
- * extent_ops just modify the flags of an extent and they don't result
- * in ref count changes, hence it's safe to pass false/0 for is_system
- * argument
- */
- add_delayed_ref_head(fs_info, trans, &head_ref->node, NULL, bytenr,
- num_bytes, 0, 0, BTRFS_UPDATE_DELAYED_HEAD,
- extent_op->is_data, 0, NULL, NULL);
+ add_delayed_ref_head(fs_info, trans, head_ref, NULL,
+ BTRFS_UPDATE_DELAYED_HEAD,
+ NULL, NULL);
spin_unlock(&delayed_refs->lock);
return 0;
diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h
index 0a74a2d3e970..19e553863539 100644
--- a/fs/btrfs/delayed-ref.h
+++ b/fs/btrfs/delayed-ref.h
@@ -26,18 +26,8 @@
#define BTRFS_ADD_DELAYED_EXTENT 3 /* record a full extent allocation */
#define BTRFS_UPDATE_DELAYED_HEAD 4 /* not changing ref count on head ref */
-/*
- * XXX: Qu: I really hate the design that ref_head and tree/data ref shares the
- * same ref_node structure.
- * Ref_head is in a higher logic level than tree/data ref, and duplicated
- * bytenr/num_bytes in ref_node is really a waste or memory, they should be
- * referred from ref_head.
- * This gets more disgusting after we use list to store tree/data ref in
- * ref_head. Must clean this mess up later.
- */
struct btrfs_delayed_ref_node {
- /*data/tree ref use list, stored in ref_head->ref_list. */
- struct list_head list;
+ struct rb_node ref_node;
/*
* If action is BTRFS_ADD_DELAYED_REF, also link this node to
* ref_head->ref_add_list, then we do not need to iterate the
@@ -91,8 +81,9 @@ struct btrfs_delayed_extent_op {
* reference count modifications we've queued up.
*/
struct btrfs_delayed_ref_head {
- struct btrfs_delayed_ref_node node;
-
+ u64 bytenr;
+ u64 num_bytes;
+ refcount_t refs;
/*
* the mutex is held while running the refs, and it is also
* held when checking the sum of reference modifications.
@@ -100,7 +91,7 @@ struct btrfs_delayed_ref_head {
struct mutex mutex;
spinlock_t lock;
- struct list_head ref_list;
+ struct rb_root ref_tree;
/* accumulate add BTRFS_ADD_DELAYED_REF nodes to this ref_add_list. */
struct list_head ref_add_list;
@@ -116,6 +107,14 @@ struct btrfs_delayed_ref_head {
int total_ref_mod;
/*
+ * This is the current outstanding mod references for this bytenr. This
+ * is used with lookup_extent_info to get an accurate reference count
+ * for a bytenr, so it is adjusted as delayed refs are run so that any
+ * on disk reference count + ref_mod is accurate.
+ */
+ int ref_mod;
+
+ /*
* when a new extent is allocated, it is just reserved in memory
* The actual extent isn't inserted into the extent allocation tree
* until the delayed ref is processed. must_insert_reserved is
@@ -189,6 +188,83 @@ struct btrfs_delayed_ref_root {
u64 qgroup_to_skip;
};
+enum btrfs_ref_type {
+ BTRFS_REF_NOT_SET,
+ BTRFS_REF_DATA,
+ BTRFS_REF_METADATA,
+ BTRFS_REF_LAST,
+};
+
+struct btrfs_data_ref {
+ /* For EXTENT_DATA_REF */
+
+ /* Root which refers to this data extent */
+ u64 ref_root;
+
+ /* Inode which refers to this data extent */
+ u64 ino;
+
+ /*
+ * file_offset - extent_offset
+ *
+ * file_offset is the key.offset of the EXTENT_DATA key.
+ * extent_offset is btrfs_file_extent_offset() of the EXTENT_DATA data.
+ */
+ u64 offset;
+};
+
+struct btrfs_tree_ref {
+ /*
+ * Level of this tree block
+ *
+ * Shared for skinny (TREE_BLOCK_REF) and normal tree ref.
+ */
+ int level;
+
+ /*
+ * Root which refers to this tree block.
+ *
+ * For TREE_BLOCK_REF (skinny metadata, either inline or keyed)
+ */
+ u64 root;
+
+ /* For non-skinny metadata, no special member needed */
+};
+
+struct btrfs_ref {
+ enum btrfs_ref_type type;
+ int action;
+
+ /*
+ * Whether this extent should go through qgroup record.
+ *
+ * Normally false, but for certain cases like delayed subtree scan,
+ * setting this flag can hugely reduce qgroup overhead.
+ */
+ bool skip_qgroup;
+
+ /*
+ * Optional. For which root is this modification.
+ * Mostly used for qgroup optimization.
+ *
+ * When unset, data/tree ref init code will populate it.
+ * In certain cases, we're modifying reference for a different root.
+ * E.g. COW fs tree blocks for balance.
+ * In that case, tree_ref::root will be fs tree, but we're doing this
+ * for reloc tree, then we should set @real_root to reloc tree.
+ */
+ u64 real_root;
+ u64 bytenr;
+ u64 len;
+
+ /* Bytenr of the parent tree block */
+ u64 parent;
+ union {
+ struct btrfs_data_ref data_ref;
+ struct btrfs_tree_ref tree_ref;
+ };
+};
+
extern struct kmem_cache *btrfs_delayed_ref_head_cachep;
extern struct kmem_cache *btrfs_delayed_tree_ref_cachep;
extern struct kmem_cache *btrfs_delayed_data_ref_cachep;
@@ -197,6 +273,38 @@ extern struct kmem_cache *btrfs_delayed_extent_op_cachep;
int btrfs_delayed_ref_init(void);
void btrfs_delayed_ref_exit(void);
+static inline void btrfs_init_generic_ref(struct btrfs_ref *generic_ref,
+ int action, u64 bytenr, u64 len, u64 parent)
+{
+ generic_ref->action = action;
+ generic_ref->bytenr = bytenr;
+ generic_ref->len = len;
+ generic_ref->parent = parent;
+}
+
+static inline void btrfs_init_tree_ref(struct btrfs_ref *generic_ref,
+ int level, u64 root)
+{
+ /* If @real_root not set, use @root as fallback */
+ if (!generic_ref->real_root)
+ generic_ref->real_root = root;
+ generic_ref->tree_ref.level = level;
+ generic_ref->tree_ref.root = root;
+ generic_ref->type = BTRFS_REF_METADATA;
+}
+
+static inline void btrfs_init_data_ref(struct btrfs_ref *generic_ref,
+ u64 ref_root, u64 ino, u64 offset)
+{
+ /* If @real_root not set, use @root as fallback */
+ if (!generic_ref->real_root)
+ generic_ref->real_root = ref_root;
+ generic_ref->data_ref.ref_root = ref_root;
+ generic_ref->data_ref.ino = ino;
+ generic_ref->data_ref.offset = offset;
+ generic_ref->type = BTRFS_REF_DATA;
+}
+
static inline struct btrfs_delayed_extent_op *
btrfs_alloc_delayed_extent_op(void)
{
@@ -224,15 +332,18 @@ static inline void btrfs_put_delayed_ref(struct btrfs_delayed_ref_node *ref)
case BTRFS_SHARED_DATA_REF_KEY:
kmem_cache_free(btrfs_delayed_data_ref_cachep, ref);
break;
- case 0:
- kmem_cache_free(btrfs_delayed_ref_head_cachep, ref);
- break;
default:
BUG();
}
}
}
+static inline void btrfs_put_delayed_ref_head(struct btrfs_delayed_ref_head *head)
+{
+ if (refcount_dec_and_test(&head->refs))
+ kmem_cache_free(btrfs_delayed_ref_head_cachep, head);
+}
+
int btrfs_add_delayed_tree_ref(struct btrfs_fs_info *fs_info,
struct btrfs_trans_handle *trans,
u64 bytenr, u64 num_bytes, u64 parent,
@@ -273,35 +384,17 @@ int btrfs_check_delayed_seq(struct btrfs_fs_info *fs_info,
u64 seq);
/*
- * a node might live in a head or a regular ref, this lets you
- * test for the proper type to use.
- */
-static int btrfs_delayed_ref_is_head(struct btrfs_delayed_ref_node *node)
-{
- return node->is_head;
-}
-
-/*
* helper functions to cast a node into its container
*/
static inline struct btrfs_delayed_tree_ref *
btrfs_delayed_node_to_tree_ref(struct btrfs_delayed_ref_node *node)
{
- WARN_ON(btrfs_delayed_ref_is_head(node));
return container_of(node, struct btrfs_delayed_tree_ref, node);
}
static inline struct btrfs_delayed_data_ref *
btrfs_delayed_node_to_data_ref(struct btrfs_delayed_ref_node *node)
{
- WARN_ON(btrfs_delayed_ref_is_head(node));
return container_of(node, struct btrfs_delayed_data_ref, node);
}
-
-static inline struct btrfs_delayed_ref_head *
-btrfs_delayed_node_to_head(struct btrfs_delayed_ref_node *node)
-{
- WARN_ON(!btrfs_delayed_ref_is_head(node));
- return container_of(node, struct btrfs_delayed_ref_head, node);
-}
#endif
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index d64f92cbade2..a82243503743 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -4269,26 +4269,28 @@ static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
while ((node = rb_first(&delayed_refs->href_root)) != NULL) {
struct btrfs_delayed_ref_head *head;
- struct btrfs_delayed_ref_node *tmp;
+ struct rb_node *n;
bool pin_bytes = false;
head = rb_entry(node, struct btrfs_delayed_ref_head,
href_node);
if (!mutex_trylock(&head->mutex)) {
- refcount_inc(&head->node.refs);
+ refcount_inc(&head->refs);
spin_unlock(&delayed_refs->lock);
mutex_lock(&head->mutex);
mutex_unlock(&head->mutex);
- btrfs_put_delayed_ref(&head->node);
+ btrfs_put_delayed_ref_head(head);
spin_lock(&delayed_refs->lock);
continue;
}
spin_lock(&head->lock);
- list_for_each_entry_safe_reverse(ref, tmp, &head->ref_list,
- list) {
+ while ((n = rb_first(&head->ref_tree)) != NULL) {
+ ref = rb_entry(n, struct btrfs_delayed_ref_node,
+ ref_node);
ref->in_tree = 0;
- list_del(&ref->list);
+ rb_erase(&ref->ref_node, &head->ref_tree);
+ RB_CLEAR_NODE(&ref->ref_node);
if (!list_empty(&ref->add_list))
list_del(&ref->add_list);
atomic_dec(&delayed_refs->num_entries);
@@ -4301,16 +4303,16 @@ static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
if (head->processing == 0)
delayed_refs->num_heads_ready--;
atomic_dec(&delayed_refs->num_entries);
- head->node.in_tree = 0;
rb_erase(&head->href_node, &delayed_refs->href_root);
+ RB_CLEAR_NODE(&head->href_node);
spin_unlock(&head->lock);
spin_unlock(&delayed_refs->lock);
mutex_unlock(&head->mutex);
if (pin_bytes)
- btrfs_pin_extent(fs_info, head->node.bytenr,
- head->node.num_bytes, 1);
- btrfs_put_delayed_ref(&head->node);
+ btrfs_pin_extent(fs_info, head->bytenr,
+ head->num_bytes, 1);
+ btrfs_put_delayed_ref_head(head);
cond_resched();
spin_lock(&delayed_refs->lock);
}
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 64336bbeb998..e7498a453092 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -925,7 +925,7 @@ search_again:
head = btrfs_find_delayed_ref_head(delayed_refs, bytenr);
if (head) {
if (!mutex_trylock(&head->mutex)) {
- refcount_inc(&head->node.refs);
+ refcount_inc(&head->refs);
spin_unlock(&delayed_refs->lock);
btrfs_release_path(path);
@@ -936,7 +936,7 @@ search_again:
*/
mutex_lock(&head->mutex);
mutex_unlock(&head->mutex);
- btrfs_put_delayed_ref(&head->node);
+ btrfs_put_delayed_ref_head(head);
goto search_again;
}
spin_lock(&head->lock);
@@ -945,7 +945,7 @@ search_again:
else
BUG_ON(num_refs == 0);
- num_refs += head->node.ref_mod;
+ num_refs += head->ref_mod;
spin_unlock(&head->lock);
mutex_unlock(&head->mutex);
}
@@ -2266,7 +2266,7 @@ static void __run_delayed_extent_op(struct btrfs_delayed_extent_op *extent_op,
static int run_delayed_extent_op(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info,
- struct btrfs_delayed_ref_node *node,
+ struct btrfs_delayed_ref_head *head,
struct btrfs_delayed_extent_op *extent_op)
{
struct btrfs_key key;
@@ -2288,14 +2288,14 @@ static int run_delayed_extent_op(struct btrfs_trans_handle *trans,
if (!path)
return -ENOMEM;
- key.objectid = node->bytenr;
+ key.objectid = head->bytenr;
if (metadata) {
key.type = BTRFS_METADATA_ITEM_KEY;
key.offset = extent_op->level;
} else {
key.type = BTRFS_EXTENT_ITEM_KEY;
- key.offset = node->num_bytes;
+ key.offset = head->num_bytes;
}
again:
@@ -2312,17 +2312,17 @@ again:
path->slots[0]--;
btrfs_item_key_to_cpu(path->nodes[0], &key,
path->slots[0]);
- if (key.objectid == node->bytenr &&
+ if (key.objectid == head->bytenr &&
key.type == BTRFS_EXTENT_ITEM_KEY &&
- key.offset == node->num_bytes)
+ key.offset == head->num_bytes)
ret = 0;
}
if (ret > 0) {
btrfs_release_path(path);
metadata = 0;
- key.objectid = node->bytenr;
- key.offset = node->num_bytes;
+ key.objectid = head->bytenr;
+ key.offset = head->num_bytes;
key.type = BTRFS_EXTENT_ITEM_KEY;
goto again;
}
@@ -2429,47 +2429,6 @@ static int run_one_delayed_ref(struct btrfs_trans_handle *trans,
return 0;
}
- if (btrfs_delayed_ref_is_head(node)) {
- struct btrfs_delayed_ref_head *head;
- /*
- * we've hit the end of the chain and we were supposed
- * to insert this extent into the tree. But, it got
- * deleted before we ever needed to insert it, so all
- * we have to do is clean up the accounting
- */
- BUG_ON(extent_op);
- head = btrfs_delayed_node_to_head(node);
- trace_run_delayed_ref_head(fs_info, node, head, node->action);
-
- if (head->total_ref_mod < 0) {
- struct btrfs_space_info *space_info;
- u64 flags;
-
- if (head->is_data)
- flags = BTRFS_BLOCK_GROUP_DATA;
- else if (head->is_system)
- flags = BTRFS_BLOCK_GROUP_SYSTEM;
- else
- flags = BTRFS_BLOCK_GROUP_METADATA;
- space_info = __find_space_info(fs_info, flags);
- ASSERT(space_info);
- percpu_counter_add(&space_info->total_bytes_pinned,
- -node->num_bytes);
- }
-
- if (insert_reserved) {
- btrfs_pin_extent(fs_info, node->bytenr,
- node->num_bytes, 1);
- if (head->is_data) {
- ret = btrfs_del_csums(trans, fs_info,
- node->bytenr,
- node->num_bytes);
- }
- }
-
- return ret;
- }
-
if (node->type == BTRFS_TREE_BLOCK_REF_KEY ||
node->type == BTRFS_SHARED_BLOCK_REF_KEY)
ret = run_delayed_tree_ref(trans, fs_info, node, extent_op,
@@ -2488,7 +2447,7 @@ select_delayed_ref(struct btrfs_delayed_ref_head *head)
{
struct btrfs_delayed_ref_node *ref;
- if (list_empty(&head->ref_list))
+ if (RB_EMPTY_ROOT(&head->ref_tree))
return NULL;
/*
@@ -2501,12 +2460,116 @@ select_delayed_ref(struct btrfs_delayed_ref_head *head)
return list_first_entry(&head->ref_add_list,
struct btrfs_delayed_ref_node, add_list);
- ref = list_first_entry(&head->ref_list, struct btrfs_delayed_ref_node,
- list);
+ ref = rb_entry(rb_first(&head->ref_tree),
+ struct btrfs_delayed_ref_node, ref_node);
ASSERT(list_empty(&ref->add_list));
return ref;
}
+static void unselect_delayed_ref_head(struct btrfs_delayed_ref_root *delayed_refs,
+ struct btrfs_delayed_ref_head *head)
+{
+ spin_lock(&delayed_refs->lock);
+ head->processing = 0;
+ delayed_refs->num_heads_ready++;
+ spin_unlock(&delayed_refs->lock);
+ btrfs_delayed_ref_unlock(head);
+}
+
+static int cleanup_extent_op(struct btrfs_trans_handle *trans,
+ struct btrfs_fs_info *fs_info,
+ struct btrfs_delayed_ref_head *head)
+{
+ struct btrfs_delayed_extent_op *extent_op = head->extent_op;
+ int ret;
+
+ if (!extent_op)
+ return 0;
+ head->extent_op = NULL;
+ if (head->must_insert_reserved) {
+ btrfs_free_delayed_extent_op(extent_op);
+ return 0;
+ }
+ spin_unlock(&head->lock);
+ ret = run_delayed_extent_op(trans, fs_info, head, extent_op);
+ btrfs_free_delayed_extent_op(extent_op);
+ return ret ? ret : 1;
+}
+
+static int cleanup_ref_head(struct btrfs_trans_handle *trans,
+ struct btrfs_fs_info *fs_info,
+ struct btrfs_delayed_ref_head *head)
+{
+ struct btrfs_delayed_ref_root *delayed_refs;
+ int ret;
+
+ delayed_refs = &trans->transaction->delayed_refs;
+
+ ret = cleanup_extent_op(trans, fs_info, head);
+ if (ret < 0) {
+ unselect_delayed_ref_head(delayed_refs, head);
+ btrfs_debug(fs_info, "run_delayed_extent_op returned %d", ret);
+ return ret;
+ } else if (ret) {
+ return ret;
+ }
+
+ /*
+ * Need to drop our head ref lock and re-acquire the delayed ref lock
+ * and then re-check to make sure nobody got added.
+ */
+ spin_unlock(&head->lock);
+ spin_lock(&delayed_refs->lock);
+ spin_lock(&head->lock);
+ if (!RB_EMPTY_ROOT(&head->ref_tree) || head->extent_op) {
+ spin_unlock(&head->lock);
+ spin_unlock(&delayed_refs->lock);
+ return 1;
+ }
+ delayed_refs->num_heads--;
+ rb_erase(&head->href_node, &delayed_refs->href_root);
+ RB_CLEAR_NODE(&head->href_node);
+ spin_unlock(&delayed_refs->lock);
+ spin_unlock(&head->lock);
+ atomic_dec(&delayed_refs->num_entries);
+
+ trace_run_delayed_ref_head(fs_info, head, 0);
+
+ if (head->total_ref_mod < 0) {
+ struct btrfs_space_info *space_info;
+ u64 flags;
+
+ if (head->is_data)
+ flags = BTRFS_BLOCK_GROUP_DATA;
+ else if (head->is_system)
+ flags = BTRFS_BLOCK_GROUP_SYSTEM;
+ else
+ flags = BTRFS_BLOCK_GROUP_METADATA;
+ space_info = __find_space_info(fs_info, flags);
+ ASSERT(space_info);
+ percpu_counter_add(&space_info->total_bytes_pinned,
+ -head->num_bytes);
+ if (head->is_data) {
+ spin_lock(&delayed_refs->lock);
+ delayed_refs->pending_csums -= head->num_bytes;
+ spin_unlock(&delayed_refs->lock);
+ }
+ }
+
+ if (head->must_insert_reserved) {
+ btrfs_pin_extent(fs_info, head->bytenr,
+ head->num_bytes, 1);
+ if (head->is_data) {
+ ret = btrfs_del_csums(trans, fs_info, head->bytenr,
+ head->num_bytes);
+ }
+ }
+
+ btrfs_delayed_ref_unlock(head);
+ btrfs_put_delayed_ref_head(head);
+ return 0;
+}
+
/*
* Returns 0 on success or if called with an already aborted transaction.
* Returns -ENOMEM or -EIO on failure and will abort the transaction.
@@ -2580,11 +2643,7 @@ static noinline int __btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
if (ref && ref->seq &&
btrfs_check_delayed_seq(fs_info, delayed_refs, ref->seq)) {
spin_unlock(&locked_ref->lock);
- spin_lock(&delayed_refs->lock);
- locked_ref->processing = 0;
- delayed_refs->num_heads_ready++;
- spin_unlock(&delayed_refs->lock);
- btrfs_delayed_ref_unlock(locked_ref);
+ unselect_delayed_ref_head(delayed_refs, locked_ref);
locked_ref = NULL;
cond_resched();
count++;
@@ -2592,102 +2651,55 @@ static noinline int __btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
}
/*
- * record the must insert reserved flag before we
- * drop the spin lock.
+ * We're done processing refs in this ref_head, clean everything
+ * up and move on to the next ref_head.
*/
- must_insert_reserved = locked_ref->must_insert_reserved;
- locked_ref->must_insert_reserved = 0;
-
- extent_op = locked_ref->extent_op;
- locked_ref->extent_op = NULL;
-
if (!ref) {
-
-
- /* All delayed refs have been processed, Go ahead
- * and send the head node to run_one_delayed_ref,
- * so that any accounting fixes can happen
- */
- ref = &locked_ref->node;
-
- if (extent_op && must_insert_reserved) {
- btrfs_free_delayed_extent_op(extent_op);
- extent_op = NULL;
- }
-
- if (extent_op) {
- spin_unlock(&locked_ref->lock);
- ret = run_delayed_extent_op(trans, fs_info,
- ref, extent_op);
- btrfs_free_delayed_extent_op(extent_op);
-
- if (ret) {
- /*
- * Need to reset must_insert_reserved if
- * there was an error so the abort stuff
- * can cleanup the reserved space
- * properly.
- */
- if (must_insert_reserved)
- locked_ref->must_insert_reserved = 1;
- spin_lock(&delayed_refs->lock);
- locked_ref->processing = 0;
- delayed_refs->num_heads_ready++;
- spin_unlock(&delayed_refs->lock);
- btrfs_debug(fs_info,
- "run_delayed_extent_op returned %d",
- ret);
- btrfs_delayed_ref_unlock(locked_ref);
- return ret;
- }
+ ret = cleanup_ref_head(trans, fs_info, locked_ref);
+ if (ret > 0 ) {
+ /* We dropped our lock, we need to loop. */
+ ret = 0;
continue;
+ } else if (ret) {
+ return ret;
}
+ locked_ref = NULL;
+ count++;
+ continue;
+ }
- /*
- * Need to drop our head ref lock and re-acquire the
- * delayed ref lock and then re-check to make sure
- * nobody got added.
- */
- spin_unlock(&locked_ref->lock);
- spin_lock(&delayed_refs->lock);
- spin_lock(&locked_ref->lock);
- if (!list_empty(&locked_ref->ref_list) ||
- locked_ref->extent_op) {
- spin_unlock(&locked_ref->lock);
- spin_unlock(&delayed_refs->lock);
- continue;
- }
- ref->in_tree = 0;
- delayed_refs->num_heads--;
- rb_erase(&locked_ref->href_node,
- &delayed_refs->href_root);
- spin_unlock(&delayed_refs->lock);
- } else {
- actual_count++;
- ref->in_tree = 0;
- list_del(&ref->list);
- if (!list_empty(&ref->add_list))
- list_del(&ref->add_list);
+ actual_count++;
+ ref->in_tree = 0;
+ rb_erase(&ref->ref_node, &locked_ref->ref_tree);
+ RB_CLEAR_NODE(&ref->ref_node);
+ if (!list_empty(&ref->add_list))
+ list_del(&ref->add_list);
+ /*
+ * When we play the delayed ref, also correct the ref_mod on
+ * head
+ */
+ switch (ref->action) {
+ case BTRFS_ADD_DELAYED_REF:
+ case BTRFS_ADD_DELAYED_EXTENT:
+ locked_ref->ref_mod -= ref->ref_mod;
+ break;
+ case BTRFS_DROP_DELAYED_REF:
+ locked_ref->ref_mod += ref->ref_mod;
+ break;
+ default:
+ WARN_ON(1);
}
atomic_dec(&delayed_refs->num_entries);
- if (!btrfs_delayed_ref_is_head(ref)) {
- /*
- * when we play the delayed ref, also correct the
- * ref_mod on head
- */
- switch (ref->action) {
- case BTRFS_ADD_DELAYED_REF:
- case BTRFS_ADD_DELAYED_EXTENT:
- locked_ref->node.ref_mod -= ref->ref_mod;
- break;
- case BTRFS_DROP_DELAYED_REF:
- locked_ref->node.ref_mod += ref->ref_mod;
- break;
- default:
- WARN_ON(1);
- }
- }
+ /*
+ * Record the must-insert_reserved flag before we drop the spin
+ * lock.
+ */
+ must_insert_reserved = locked_ref->must_insert_reserved;
+ locked_ref->must_insert_reserved = 0;
+
+ extent_op = locked_ref->extent_op;
+ locked_ref->extent_op = NULL;
spin_unlock(&locked_ref->lock);
ret = run_one_delayed_ref(trans, fs_info, ref, extent_op,
@@ -2695,33 +2707,13 @@ static noinline int __btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
btrfs_free_delayed_extent_op(extent_op);
if (ret) {
- spin_lock(&delayed_refs->lock);
- locked_ref->processing = 0;
- delayed_refs->num_heads_ready++;
- spin_unlock(&delayed_refs->lock);
- btrfs_delayed_ref_unlock(locked_ref);
+ unselect_delayed_ref_head(delayed_refs, locked_ref);
btrfs_put_delayed_ref(ref);
btrfs_debug(fs_info, "run_one_delayed_ref returned %d",
ret);
return ret;
}
- /*
- * If this node is a head, that means all the refs in this head
- * have been dealt with, and we will pick the next head to deal
- * with, so we must unlock the head and drop it from the cluster
- * list before we release it.
- */
- if (btrfs_delayed_ref_is_head(ref)) {
- if (locked_ref->is_data &&
- locked_ref->total_ref_mod < 0) {
- spin_lock(&delayed_refs->lock);
- delayed_refs->pending_csums -= ref->num_bytes;
- spin_unlock(&delayed_refs->lock);
- }
- btrfs_delayed_ref_unlock(locked_ref);
- locked_ref = NULL;
- }
btrfs_put_delayed_ref(ref);
count++;
cond_resched();
@@ -3023,33 +3015,16 @@ again:
spin_unlock(&delayed_refs->lock);
goto out;
}
+ head = rb_entry(node, struct btrfs_delayed_ref_head,
+ href_node);
+ refcount_inc(&head->refs);
+ spin_unlock(&delayed_refs->lock);
- while (node) {
- head = rb_entry(node, struct btrfs_delayed_ref_head,
- href_node);
- if (btrfs_delayed_ref_is_head(&head->node)) {
- struct btrfs_delayed_ref_node *ref;
-
- ref = &head->node;
- refcount_inc(&ref->refs);
-
- spin_unlock(&delayed_refs->lock);
- /*
- * Mutex was contended, block until it's
- * released and try again
- */
- mutex_lock(&head->mutex);
- mutex_unlock(&head->mutex);
+ /* Mutex was contended, block until it's released and retry. */
+ mutex_lock(&head->mutex);
+ mutex_unlock(&head->mutex);
- btrfs_put_delayed_ref(ref);
- cond_resched();
- goto again;
- } else {
- WARN_ON(1);
- }
- node = rb_next(node);
- }
- spin_unlock(&delayed_refs->lock);
+ btrfs_put_delayed_ref_head(head);
cond_resched();
goto again;
}
@@ -3091,6 +3066,7 @@ static noinline int check_delayed_ref(struct btrfs_root *root,
struct btrfs_delayed_data_ref *data_ref;
struct btrfs_delayed_ref_root *delayed_refs;
struct btrfs_transaction *cur_trans;
+ struct rb_node *node;
int ret = 0;
spin_lock(&root->fs_info->trans_lock);
@@ -3111,7 +3087,7 @@ static noinline int check_delayed_ref(struct btrfs_root *root,
}
if (!mutex_trylock(&head->mutex)) {
- refcount_inc(&head->node.refs);
+ refcount_inc(&head->refs);
spin_unlock(&delayed_refs->lock);
btrfs_release_path(path);
@@ -3122,14 +3098,19 @@ static noinline int check_delayed_ref(struct btrfs_root *root,
*/
mutex_lock(&head->mutex);
mutex_unlock(&head->mutex);
- btrfs_put_delayed_ref(&head->node);
+ btrfs_put_delayed_ref_head(head);
btrfs_put_transaction(cur_trans);
return -EAGAIN;
}
spin_unlock(&delayed_refs->lock);
spin_lock(&head->lock);
- list_for_each_entry(ref, &head->ref_list, list) {
+ /*
+ * XXX: We should replace this with a proper search function in the
+ * future.
+ */
+ for (node = rb_first(&head->ref_tree); node; node = rb_next(node)) {
+ ref = rb_entry(node, struct btrfs_delayed_ref_node, ref_node);
/* If it's a shared ref we know a cross reference exists */
if (ref->type != BTRFS_EXTENT_DATA_REF_KEY) {
ret = 1;
@@ -3277,10 +3258,6 @@ static int __btrfs_mod_ref(struct btrfs_trans_handle *trans,
int i;
int level;
int ret = 0;
- int (*process_func)(struct btrfs_trans_handle *,
- struct btrfs_fs_info *,
- u64, u64, u64, u64, u64, u64);
-
if (btrfs_is_testing(fs_info))
return 0;
@@ -3292,11 +3269,6 @@ static int __btrfs_mod_ref(struct btrfs_trans_handle *trans,
if (!test_bit(BTRFS_ROOT_REF_COWS, &root->state) && level == 0)
return 0;
- if (inc)
- process_func = btrfs_inc_extent_ref;
- else
- process_func = btrfs_free_extent;
-
if (full_backref)
parent = buf->start;
else
@@ -3318,16 +3290,27 @@ static int __btrfs_mod_ref(struct btrfs_trans_handle *trans,
num_bytes = btrfs_file_extent_disk_num_bytes(buf, fi);
key.offset -= btrfs_file_extent_offset(buf, fi);
- ret = process_func(trans, fs_info, bytenr, num_bytes,
- parent, ref_root, key.objectid,
- key.offset);
+ if (inc)
+ ret = btrfs_inc_extent_ref(trans, fs_info, bytenr,
+ num_bytes, parent, ref_root,
+ key.objectid, key.offset);
+ else
+ ret = btrfs_free_extent(trans, fs_info, bytenr,
+ num_bytes, parent, ref_root,
+ key.objectid, key.offset);
if (ret)
goto fail;
} else {
bytenr = btrfs_node_blockptr(buf, i);
num_bytes = fs_info->nodesize;
- ret = process_func(trans, fs_info, bytenr, num_bytes,
- parent, ref_root, level - 1, 0);
+ if (inc)
+ ret = btrfs_inc_extent_ref(trans, fs_info, bytenr,
+ num_bytes, parent, ref_root,
+ level - 1, 0);
+ else
+ ret = btrfs_free_extent(trans, fs_info, bytenr,
+ num_bytes, parent, ref_root,
+ level - 1, 0);
if (ret)
goto fail;
}
@@ -7087,7 +7070,7 @@ static noinline int check_ref_cleanup(struct btrfs_trans_handle *trans,
goto out_delayed_unlock;
spin_lock(&head->lock);
- if (!list_empty(&head->ref_list))
+ if (!RB_EMPTY_ROOT(&head->ref_tree))
goto out;
if (head->extent_op) {
@@ -7108,9 +7091,8 @@ static noinline int check_ref_cleanup(struct btrfs_trans_handle *trans,
* at this point we have a head with no other entries. Go
* ahead and process it.
*/
- head->node.in_tree = 0;
rb_erase(&head->href_node, &delayed_refs->href_root);
-
+ RB_CLEAR_NODE(&head->href_node);
atomic_dec(&delayed_refs->num_entries);
/*
@@ -7129,7 +7111,7 @@ static noinline int check_ref_cleanup(struct btrfs_trans_handle *trans,
ret = 1;
mutex_unlock(&head->mutex);
- btrfs_put_delayed_ref(&head->node);
+ btrfs_put_delayed_ref_head(head);
return ret;
out:
spin_unlock(&head->lock);
diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c
index 1ae9869123f4..39e2b2417ed5 100644
--- a/fs/btrfs/root-tree.c
+++ b/fs/btrfs/root-tree.c
@@ -150,11 +150,14 @@ int btrfs_update_root(struct btrfs_trans_handle *trans, struct btrfs_root
goto out;
}
- if (ret != 0) {
- btrfs_print_leaf(fs_info, path->nodes[0]);
- btrfs_crit(fs_info, "unable to update root key %llu %u %llu",
- key->objectid, key->type, key->offset);
- BUG_ON(1);
+ if (ret > 0) {
+ btrfs_crit(fs_info,
+ "unable to find root key (%llu %u %llu) in tree %llu",
+ key->objectid, key->type, key->offset,
+ root->root_key.objectid);
+ ret = -EUCLEAN;
+ btrfs_abort_transaction(trans, ret);
+ goto out;
}
l = path->nodes[0];
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 782017d5e1ce..92db3fef0f0d 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -1466,6 +1466,7 @@ void ceph_dentry_lru_del(struct dentry *dn)
unsigned ceph_dentry_hash(struct inode *dir, struct dentry *dn)
{
struct ceph_inode_info *dci = ceph_inode(dir);
+ unsigned hash;
switch (dci->i_dir_layout.dl_dir_hash) {
case 0: /* for backward compat */
@@ -1473,8 +1474,11 @@ unsigned ceph_dentry_hash(struct inode *dir, struct dentry *dn)
return dn->d_name.hash;
default:
- return ceph_str_hash(dci->i_dir_layout.dl_dir_hash,
+ spin_lock(&dn->d_lock);
+ hash = ceph_str_hash(dci->i_dir_layout.dl_dir_hash,
dn->d_name.name, dn->d_name.len);
+ spin_unlock(&dn->d_lock);
+ return hash;
}
}
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 1ad3c64f517c..d8b40c0f4269 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -523,6 +523,7 @@ static void ceph_i_callback(struct rcu_head *head)
struct inode *inode = container_of(head, struct inode, i_rcu);
struct ceph_inode_info *ci = ceph_inode(inode);
+ kfree(ci->i_symlink);
kmem_cache_free(ceph_inode_cachep, ci);
}
@@ -560,7 +561,6 @@ void ceph_destroy_inode(struct inode *inode)
ceph_put_snap_realm(mdsc, realm);
}
- kfree(ci->i_symlink);
while ((n = rb_first(&ci->i_fragtree)) != NULL) {
frag = rb_entry(n, struct ceph_inode_frag, node);
rb_erase(n, &ci->i_fragtree);
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 82437ccf320d..e24c0dcb55f5 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -1259,6 +1259,15 @@ static int remove_session_caps_cb(struct inode *inode, struct ceph_cap *cap,
list_add(&ci->i_prealloc_cap_flush->i_list, &to_remove);
ci->i_prealloc_cap_flush = NULL;
}
+
+ if (drop &&
+ ci->i_wrbuffer_ref_head == 0 &&
+ ci->i_wr_ref == 0 &&
+ ci->i_dirty_caps == 0 &&
+ ci->i_flushing_caps == 0) {
+ ceph_put_snap_context(ci->i_head_snapc);
+ ci->i_head_snapc = NULL;
+ }
}
spin_unlock(&ci->i_ceph_lock);
while (!list_empty(&to_remove)) {
@@ -1912,10 +1921,39 @@ retry:
return path;
}
+/* Duplicate the dentry->d_name.name safely */
+static int clone_dentry_name(struct dentry *dentry, const char **ppath,
+ int *ppathlen)
+{
+ u32 len;
+ char *name;
+
+retry:
+ len = READ_ONCE(dentry->d_name.len);
+ name = kmalloc(len + 1, GFP_NOFS);
+ if (!name)
+ return -ENOMEM;
+
+ spin_lock(&dentry->d_lock);
+ if (dentry->d_name.len != len) {
+ spin_unlock(&dentry->d_lock);
+ kfree(name);
+ goto retry;
+ }
+ memcpy(name, dentry->d_name.name, len);
+ spin_unlock(&dentry->d_lock);
+
+ name[len] = '\0';
+ *ppath = name;
+ *ppathlen = len;
+ return 0;
+}
+
static int build_dentry_path(struct dentry *dentry, struct inode *dir,
const char **ppath, int *ppathlen, u64 *pino,
- int *pfreepath)
+ bool *pfreepath, bool parent_locked)
{
+ int ret;
char *path;
rcu_read_lock();
@@ -1924,8 +1962,15 @@ static int build_dentry_path(struct dentry *dentry, struct inode *dir,
if (dir && ceph_snap(dir) == CEPH_NOSNAP) {
*pino = ceph_ino(dir);
rcu_read_unlock();
- *ppath = dentry->d_name.name;
- *ppathlen = dentry->d_name.len;
+ if (parent_locked) {
+ *ppath = dentry->d_name.name;
+ *ppathlen = dentry->d_name.len;
+ } else {
+ ret = clone_dentry_name(dentry, ppath, ppathlen);
+ if (ret)
+ return ret;
+ *pfreepath = true;
+ }
return 0;
}
rcu_read_unlock();
@@ -1933,13 +1978,13 @@ static int build_dentry_path(struct dentry *dentry, struct inode *dir,
if (IS_ERR(path))
return PTR_ERR(path);
*ppath = path;
- *pfreepath = 1;
+ *pfreepath = true;
return 0;
}
static int build_inode_path(struct inode *inode,
const char **ppath, int *ppathlen, u64 *pino,
- int *pfreepath)
+ bool *pfreepath)
{
struct dentry *dentry;
char *path;
@@ -1955,7 +2000,7 @@ static int build_inode_path(struct inode *inode,
if (IS_ERR(path))
return PTR_ERR(path);
*ppath = path;
- *pfreepath = 1;
+ *pfreepath = true;
return 0;
}
@@ -1966,7 +2011,7 @@ static int build_inode_path(struct inode *inode,
static int set_request_path_attr(struct inode *rinode, struct dentry *rdentry,
struct inode *rdiri, const char *rpath,
u64 rino, const char **ppath, int *pathlen,
- u64 *ino, int *freepath)
+ u64 *ino, bool *freepath, bool parent_locked)
{
int r = 0;
@@ -1976,7 +2021,7 @@ static int set_request_path_attr(struct inode *rinode, struct dentry *rdentry,
ceph_snap(rinode));
} else if (rdentry) {
r = build_dentry_path(rdentry, rdiri, ppath, pathlen, ino,
- freepath);
+ freepath, parent_locked);
dout(" dentry %p %llx/%.*s\n", rdentry, *ino, *pathlen,
*ppath);
} else if (rpath || rino) {
@@ -2002,7 +2047,7 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc,
const char *path2 = NULL;
u64 ino1 = 0, ino2 = 0;
int pathlen1 = 0, pathlen2 = 0;
- int freepath1 = 0, freepath2 = 0;
+ bool freepath1 = false, freepath2 = false;
int len;
u16 releases;
void *p, *end;
@@ -2010,16 +2055,19 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc,
ret = set_request_path_attr(req->r_inode, req->r_dentry,
req->r_parent, req->r_path1, req->r_ino1.ino,
- &path1, &pathlen1, &ino1, &freepath1);
+ &path1, &pathlen1, &ino1, &freepath1,
+ test_bit(CEPH_MDS_R_PARENT_LOCKED,
+ &req->r_req_flags));
if (ret < 0) {
msg = ERR_PTR(ret);
goto out;
}
+ /* If r_old_dentry is set, then assume that its parent is locked */
ret = set_request_path_attr(NULL, req->r_old_dentry,
req->r_old_dentry_dir,
req->r_path2, req->r_ino2.ino,
- &path2, &pathlen2, &ino2, &freepath2);
+ &path2, &pathlen2, &ino2, &freepath2, true);
if (ret < 0) {
msg = ERR_PTR(ret);
goto out_free1;
diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c
index 10f8c55e294f..97cb280f1be5 100644
--- a/fs/ceph/snap.c
+++ b/fs/ceph/snap.c
@@ -567,7 +567,12 @@ void ceph_queue_cap_snap(struct ceph_inode_info *ci)
old_snapc = NULL;
update_snapc:
- if (ci->i_head_snapc) {
+ if (ci->i_wrbuffer_ref_head == 0 &&
+ ci->i_wr_ref == 0 &&
+ ci->i_dirty_caps == 0 &&
+ ci->i_flushing_caps == 0) {
+ ci->i_head_snapc = NULL;
+ } else {
ci->i_head_snapc = ceph_get_snap_context(new_snapc);
dout(" new snapc is %p\n", new_snapc);
}
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 05de247bb52d..356b2707023e 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1883,9 +1883,7 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token,
#endif
} else if (token == Opt_dax) {
#ifdef CONFIG_FS_DAX
- ext4_msg(sb, KERN_WARNING,
- "DAX enabled. Warning: EXPERIMENTAL, use at your own risk");
- sbi->s_mount_opt |= m->mount_opt;
+ sbi->s_mount_opt |= m->mount_opt;
#else
ext4_msg(sb, KERN_INFO, "dax option not supported");
return -1;
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 2f32230843e6..672875b37460 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -9302,11 +9302,6 @@ static const struct nfs4_minor_version_ops nfs_v4_0_minor_ops = {
};
#if defined(CONFIG_NFS_V4_1)
-static struct nfs_seqid *
-nfs_alloc_no_seqid(struct nfs_seqid_counter *arg1, gfp_t arg2)
-{
- return NULL;
-}
static const struct nfs4_minor_version_ops nfs_v4_1_minor_ops = {
.minor_version = 1,
@@ -9321,7 +9316,7 @@ static const struct nfs4_minor_version_ops nfs_v4_1_minor_ops = {
.find_root_sec = nfs41_find_root_sec,
.free_lock_state = nfs41_free_lock_state,
.test_and_free_expired = nfs41_test_and_free_expired_stateid,
- .alloc_seqid = nfs_alloc_no_seqid,
+ .alloc_seqid = nfs_alloc_seqid,
.session_trunk = nfs4_test_session_trunk,
.call_sync_ops = &nfs41_call_sync_ops,
.reboot_recovery_ops = &nfs41_reboot_recovery_ops,
@@ -9352,7 +9347,7 @@ static const struct nfs4_minor_version_ops nfs_v4_2_minor_ops = {
.free_lock_state = nfs41_free_lock_state,
.call_sync_ops = &nfs41_call_sync_ops,
.test_and_free_expired = nfs41_test_and_free_expired_stateid,
- .alloc_seqid = nfs_alloc_no_seqid,
+ .alloc_seqid = nfs_alloc_seqid,
.session_trunk = nfs4_test_session_trunk,
.reboot_recovery_ops = &nfs41_reboot_recovery_ops,
.nograce_recovery_ops = &nfs41_nograce_recovery_ops,
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 2b4fcb1570a2..4d4bbc95eda0 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1661,6 +1661,12 @@ void task_dump_owner(struct task_struct *task, mode_t mode,
kuid_t uid;
kgid_t gid;
+ if (unlikely(task->flags & PF_KTHREAD)) {
+ *ruid = GLOBAL_ROOT_UID;
+ *rgid = GLOBAL_ROOT_GID;
+ return;
+ }
+
/* Default to the tasks effective ownership */
rcu_read_lock();
cred = __task_cred(task);
diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c
index 82e6787d976e..08bf08a52e80 100644
--- a/fs/proc/kcore.c
+++ b/fs/proc/kcore.c
@@ -208,25 +208,34 @@ kclist_add_private(unsigned long pfn, unsigned long nr_pages, void *arg)
{
struct list_head *head = (struct list_head *)arg;
struct kcore_list *ent;
+ struct page *p;
+
+ if (!pfn_valid(pfn))
+ return 1;
+
+ p = pfn_to_page(pfn);
+ if (!memmap_valid_within(pfn, p, page_zone(p)))
+ return 1;
ent = kmalloc(sizeof(*ent), GFP_KERNEL);
if (!ent)
return -ENOMEM;
- ent->addr = (unsigned long)__va((pfn << PAGE_SHIFT));
+ ent->addr = (unsigned long)page_to_virt(p);
ent->size = nr_pages << PAGE_SHIFT;
- /* Sanity check: Can happen in 32bit arch...maybe */
- if (ent->addr < (unsigned long) __va(0))
+ if (!virt_addr_valid(ent->addr))
goto free_out;
/* cut not-mapped area. ....from ppc-32 code. */
if (ULONG_MAX - ent->addr < ent->size)
ent->size = ULONG_MAX - ent->addr;
- /* cut when vmalloc() area is higher than direct-map area */
- if (VMALLOC_START > (unsigned long)__va(0)) {
- if (ent->addr > VMALLOC_START)
- goto free_out;
+ /*
+ * We've already checked virt_addr_valid so we know this address
+ * is a valid pointer, therefore we can check against it to determine
+ * if we need to trim
+ */
+ if (VMALLOC_START > ent->addr) {
if (VMALLOC_START - ent->addr < ent->size)
ent->size = VMALLOC_START - ent->addr;
}
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index 9b5aae2bcc0b..bd1ad9667c5a 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -789,6 +789,7 @@ xfs_initialize_perag_data(
uint64_t bfree = 0;
uint64_t bfreelst = 0;
uint64_t btree = 0;
+ uint64_t fdblocks;
int error;
for (index = 0; index < agcount; index++) {
@@ -812,17 +813,31 @@ xfs_initialize_perag_data(
btree += pag->pagf_btreeblks;
xfs_perag_put(pag);
}
+ fdblocks = bfree + bfreelst + btree;
+
+ /*
+ * If the new summary counts are obviously incorrect, fail the
+ * mount operation because that implies the AGFs are also corrupt.
+ * Clear BAD_SUMMARY so that we don't unmount with a dirty log, which
+ * will prevent xfs_repair from fixing anything.
+ */
+ if (fdblocks > sbp->sb_dblocks || ifree > ialloc) {
+ xfs_alert(mp, "AGF corruption. Please run xfs_repair.");
+ error = -EFSCORRUPTED;
+ goto out;
+ }
/* Overwrite incore superblock counters with just-read data */
spin_lock(&mp->m_sb_lock);
sbp->sb_ifree = ifree;
sbp->sb_icount = ialloc;
- sbp->sb_fdblocks = bfree + bfreelst + btree;
+ sbp->sb_fdblocks = fdblocks;
spin_unlock(&mp->m_sb_lock);
xfs_reinit_percpu_counters(mp);
-
- return 0;
+out:
+ mp->m_flags &= ~XFS_MOUNT_BAD_SUMMARY;
+ return error;
}
/*
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 5df4fea3f59b..58bbb88114f2 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -1190,18 +1190,15 @@ xfs_free_file_space(
/*
* Now that we've unmap all full blocks we'll have to zero out any
- * partial block at the beginning and/or end. xfs_zero_range is
- * smart enough to skip any holes, including those we just created,
- * but we must take care not to zero beyond EOF and enlarge i_size.
+ * partial block at the beginning and/or end. iomap_zero_range is smart
+ * enough to skip any holes, including those we just created, but we
+ * must take care not to zero beyond EOF and enlarge i_size.
*/
-
if (offset >= XFS_ISIZE(ip))
return 0;
-
if (offset + len > XFS_ISIZE(ip))
len = XFS_ISIZE(ip) - offset;
-
- return xfs_zero_range(ip, offset, len, NULL);
+ return iomap_zero_range(VFS_I(ip), offset, len, NULL, &xfs_iomap_ops);
}
/*
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 5587a7bb6b1e..8239d52b0a9c 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -48,20 +48,6 @@
static const struct vm_operations_struct xfs_file_vm_ops;
-/*
- * Clear the specified ranges to zero through either the pagecache or DAX.
- * Holes and unwritten extents will be left as-is as they already are zeroed.
- */
-int
-xfs_zero_range(
- struct xfs_inode *ip,
- xfs_off_t pos,
- xfs_off_t count,
- bool *did_zero)
-{
- return iomap_zero_range(VFS_I(ip), pos, count, did_zero, &xfs_iomap_ops);
-}
-
int
xfs_update_prealloc_flags(
struct xfs_inode *ip,
@@ -294,31 +280,6 @@ xfs_file_read_iter(
}
/*
- * Zero any on disk space between the current EOF and the new, larger EOF.
- *
- * This handles the normal case of zeroing the remainder of the last block in
- * the file and the unusual case of zeroing blocks out beyond the size of the
- * file. This second case only happens with fixed size extents and when the
- * system crashes before the inode size was updated but after blocks were
- * allocated.
- *
- * Expects the iolock to be held exclusive, and will take the ilock internally.
- */
-int /* error (positive) */
-xfs_zero_eof(
- struct xfs_inode *ip,
- xfs_off_t offset, /* starting I/O offset */
- xfs_fsize_t isize, /* current inode size */
- bool *did_zeroing)
-{
- ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
- ASSERT(offset > isize);
-
- trace_xfs_zero_eof(ip, isize, offset - isize);
- return xfs_zero_range(ip, isize, offset - isize, did_zeroing);
-}
-
-/*
* Common pre-write limit and setup checks.
*
* Called with the iolocked held either shared and exclusive according to
@@ -337,6 +298,7 @@ xfs_file_aio_write_checks(
ssize_t error = 0;
size_t count = iov_iter_count(from);
bool drained_dio = false;
+ loff_t isize;
restart:
error = generic_write_checks(iocb, from);
@@ -373,9 +335,8 @@ restart:
* and hence be able to correctly determine if we need to run zeroing.
*/
spin_lock(&ip->i_flags_lock);
- if (iocb->ki_pos > i_size_read(inode)) {
- bool zero = false;
-
+ isize = i_size_read(inode);
+ if (iocb->ki_pos > isize) {
spin_unlock(&ip->i_flags_lock);
if (!drained_dio) {
if (*iolock == XFS_IOLOCK_SHARED) {
@@ -396,7 +357,10 @@ restart:
drained_dio = true;
goto restart;
}
- error = xfs_zero_eof(ip, iocb->ki_pos, i_size_read(inode), &zero);
+
+ trace_xfs_zero_eof(ip, isize, iocb->ki_pos - isize);
+ error = iomap_zero_range(inode, isize, iocb->ki_pos - isize,
+ NULL, &xfs_iomap_ops);
if (error)
return error;
} else
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 2a8e70986ac6..d237c29be2d0 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -456,10 +456,6 @@ enum xfs_prealloc_flags {
int xfs_update_prealloc_flags(struct xfs_inode *ip,
enum xfs_prealloc_flags flags);
-int xfs_zero_eof(struct xfs_inode *ip, xfs_off_t offset,
- xfs_fsize_t isize, bool *did_zeroing);
-int xfs_zero_range(struct xfs_inode *ip, xfs_off_t pos, xfs_off_t count,
- bool *did_zero);
int xfs_break_layouts(struct inode *inode, uint *iolock,
enum layout_break_reason reason);
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index 1e8e233e931b..2ce26cbe89b9 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -881,7 +881,9 @@ xfs_setattr_size(
* truncate.
*/
if (newsize > oldsize) {
- error = xfs_zero_eof(ip, newsize, oldsize, &did_zeroing);
+ trace_xfs_zero_eof(ip, oldsize, newsize - oldsize);
+ error = iomap_zero_range(inode, oldsize, newsize - oldsize,
+ &did_zeroing, &xfs_iomap_ops);
} else {
error = iomap_truncate_page(inode, newsize, &did_zeroing,
&xfs_iomap_ops);
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index d9a5f599f4ef..34550b60e98e 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -615,6 +615,56 @@ xfs_default_resblks(xfs_mount_t *mp)
return resblks;
}
+/* Ensure the summary counts are correct. */
+STATIC int
+xfs_check_summary_counts(
+ struct xfs_mount *mp)
+{
+ /*
+ * The AG0 superblock verifier rejects in-progress filesystems,
+ * so we should never see the flag set this far into mounting.
+ */
+ if (mp->m_sb.sb_inprogress) {
+ xfs_err(mp, "sb_inprogress set after log recovery??");
+ WARN_ON(1);
+ return -EFSCORRUPTED;
+ }
+
+ /*
+ * Now the log is mounted, we know if it was an unclean shutdown or
+ * not. If it was, with the first phase of recovery has completed, we
+ * have consistent AG blocks on disk. We have not recovered EFIs yet,
+ * but they are recovered transactionally in the second recovery phase
+ * later.
+ *
+ * If the log was clean when we mounted, we can check the summary
+ * counters. If any of them are obviously incorrect, we can recompute
+ * them from the AGF headers in the next step.
+ */
+ if (XFS_LAST_UNMOUNT_WAS_CLEAN(mp) &&
+ (mp->m_sb.sb_fdblocks > mp->m_sb.sb_dblocks ||
+ mp->m_sb.sb_ifree > mp->m_sb.sb_icount))
+ mp->m_flags |= XFS_MOUNT_BAD_SUMMARY;
+
+ /*
+ * We can safely re-initialise incore superblock counters from the
+ * per-ag data. These may not be correct if the filesystem was not
+ * cleanly unmounted, so we waited for recovery to finish before doing
+ * this.
+ *
+ * If the filesystem was cleanly unmounted or the previous check did
+ * not flag anything weird, then we can trust the values in the
+ * superblock to be correct and we don't need to do anything here.
+ * Otherwise, recalculate the summary counters.
+ */
+ if ((!xfs_sb_version_haslazysbcount(&mp->m_sb) ||
+ XFS_LAST_UNMOUNT_WAS_CLEAN(mp)) &&
+ !(mp->m_flags & XFS_MOUNT_BAD_SUMMARY))
+ return 0;
+
+ return xfs_initialize_perag_data(mp, mp->m_sb.sb_agcount);
+}
+
/*
* This function does the following on an initial mount of a file system:
* - reads the superblock from disk and init the mount struct
@@ -841,32 +891,10 @@ xfs_mountfs(
goto out_fail_wait;
}
- /*
- * Now the log is mounted, we know if it was an unclean shutdown or
- * not. If it was, with the first phase of recovery has completed, we
- * have consistent AG blocks on disk. We have not recovered EFIs yet,
- * but they are recovered transactionally in the second recovery phase
- * later.
- *
- * Hence we can safely re-initialise incore superblock counters from
- * the per-ag data. These may not be correct if the filesystem was not
- * cleanly unmounted, so we need to wait for recovery to finish before
- * doing this.
- *
- * If the filesystem was cleanly unmounted, then we can trust the
- * values in the superblock to be correct and we don't need to do
- * anything here.
- *
- * If we are currently making the filesystem, the initialisation will
- * fail as the perag data is in an undefined state.
- */
- if (xfs_sb_version_haslazysbcount(&mp->m_sb) &&
- !XFS_LAST_UNMOUNT_WAS_CLEAN(mp) &&
- !mp->m_sb.sb_inprogress) {
- error = xfs_initialize_perag_data(mp, sbp->sb_agcount);
- if (error)
- goto out_log_dealloc;
- }
+ /* Make sure the summary counts are ok. */
+ error = xfs_check_summary_counts(mp);
+ if (error)
+ goto out_log_dealloc;
/*
* Get and sanity-check the root inode.
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 68b487e0ddae..b7692467f4ab 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -217,6 +217,7 @@ typedef struct xfs_mount {
must be synchronous except
for space allocations */
#define XFS_MOUNT_UNMOUNTING (1ULL << 1) /* filesystem is unmounting */
+#define XFS_MOUNT_BAD_SUMMARY (1ULL << 2) /* summary counters are bad */
#define XFS_MOUNT_WAS_CLEAN (1ULL << 3)
#define XFS_MOUNT_FS_SHUTDOWN (1ULL << 4) /* atomic stop of all filesystem
operations, typically for
diff --git a/include/acpi/ghes.h b/include/acpi/ghes.h
index 9f26e01186ae..3e1fceb212ec 100644
--- a/include/acpi/ghes.h
+++ b/include/acpi/ghes.h
@@ -69,7 +69,7 @@ static inline void ghes_edac_report_mem_error(struct ghes *ghes, int sev,
static inline int ghes_edac_register(struct ghes *ghes, struct device *dev)
{
- return 0;
+ return -ENODEV;
}
static inline void ghes_edac_unregister(struct ghes *ghes)
diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index bc893785f4fa..c67ccfa0beaa 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -1,28 +1,9 @@
#ifndef _LINUX_BITOPS_H
#define _LINUX_BITOPS_H
#include <asm/types.h>
+#include <linux/bits.h>
-#ifdef __KERNEL__
-#define BIT(nr) (1UL << (nr))
-#define BIT_ULL(nr) (1ULL << (nr))
-#define BIT_MASK(nr) (1UL << ((nr) % BITS_PER_LONG))
-#define BIT_WORD(nr) ((nr) / BITS_PER_LONG)
-#define BIT_ULL_MASK(nr) (1ULL << ((nr) % BITS_PER_LONG_LONG))
-#define BIT_ULL_WORD(nr) ((nr) / BITS_PER_LONG_LONG)
-#define BITS_PER_BYTE 8
#define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long))
-#endif
-
-/*
- * Create a contiguous bitmask starting at bit position @l and ending at
- * position @h. For example
- * GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000.
- */
-#define GENMASK(h, l) \
- (((~0UL) << (l)) & (~0UL >> (BITS_PER_LONG - 1 - (h))))
-
-#define GENMASK_ULL(h, l) \
- (((~0ULL) << (l)) & (~0ULL >> (BITS_PER_LONG_LONG - 1 - (h))))
extern unsigned int __sw_hweight8(unsigned int w);
extern unsigned int __sw_hweight16(unsigned int w);
diff --git a/include/linux/bits.h b/include/linux/bits.h
new file mode 100644
index 000000000000..2b7b532c1d51
--- /dev/null
+++ b/include/linux/bits.h
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LINUX_BITS_H
+#define __LINUX_BITS_H
+#include <asm/bitsperlong.h>
+
+#define BIT(nr) (1UL << (nr))
+#define BIT_ULL(nr) (1ULL << (nr))
+#define BIT_MASK(nr) (1UL << ((nr) % BITS_PER_LONG))
+#define BIT_WORD(nr) ((nr) / BITS_PER_LONG)
+#define BIT_ULL_MASK(nr) (1ULL << ((nr) % BITS_PER_LONG_LONG))
+#define BIT_ULL_WORD(nr) ((nr) / BITS_PER_LONG_LONG)
+#define BITS_PER_BYTE 8
+
+/*
+ * Create a contiguous bitmask starting at bit position @l and ending at
+ * position @h. For example
+ * GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000.
+ */
+#define GENMASK(h, l) \
+ (((~0UL) - (1UL << (l)) + 1) & (~0UL >> (BITS_PER_LONG - 1 - (h))))
+
+#define GENMASK_ULL(h, l) \
+ (((~0ULL) - (1ULL << (l)) + 1) & \
+ (~0ULL >> (BITS_PER_LONG_LONG - 1 - (h))))
+
+#endif /* __LINUX_BITS_H */
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index cf5b0d9c4483..9bd30749d04f 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -56,6 +56,8 @@ extern ssize_t cpu_show_spec_store_bypass(struct device *dev,
struct device_attribute *attr, char *buf);
extern ssize_t cpu_show_l1tf(struct device *dev,
struct device_attribute *attr, char *buf);
+extern ssize_t cpu_show_mds(struct device *dev,
+ struct device_attribute *attr, char *buf);
extern __printf(4, 5)
struct device *cpu_device_create(struct device *parent, void *drvdata,
diff --git a/include/linux/crc64.h b/include/linux/crc64.h
new file mode 100644
index 000000000000..c756e65a1b58
--- /dev/null
+++ b/include/linux/crc64.h
@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * See lib/crc64.c for the related specification and polynomial arithmetic.
+ */
+#ifndef _LINUX_CRC64_H
+#define _LINUX_CRC64_H
+
+#include <linux/types.h>
+
+u64 __pure crc64_be(u64 crc, const void *p, size_t len);
+#endif /* _LINUX_CRC64_H */
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 234545fb4e66..7cd8ae671c06 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -145,8 +145,15 @@ struct hd_struct {
enum {
DISK_EVENT_MEDIA_CHANGE = 1 << 0, /* media changed */
DISK_EVENT_EJECT_REQUEST = 1 << 1, /* eject requested */
+ /* Poll even if events_poll_msecs is unset */
+ DISK_EVENT_FLAG_POLL = 1 << 16,
+ /* Forward events to udev */
+ DISK_EVENT_FLAG_UEVENT = 1 << 17,
};
+#define DISK_EVENT_TYPES_MASK \
+ (DISK_EVENT_MEDIA_CHANGE | DISK_EVENT_EJECT_REQUEST)
+
struct disk_part_tbl {
struct rcu_head rcu_head;
int len;
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 939b6bb5c0a7..e01ac6e19ab8 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -60,8 +60,8 @@
#define u64_to_user_ptr(x) ( \
{ \
- typecheck(u64, x); \
- (void __user *)(uintptr_t)x; \
+ typecheck(u64, (x)); \
+ (void __user *)(uintptr_t)(x); \
} \
)
diff --git a/include/linux/platform_data/elm.h b/include/linux/platform_data/elm.h
index b8686c00f15f..fef4b081b736 100644
--- a/include/linux/platform_data/elm.h
+++ b/include/linux/platform_data/elm.h
@@ -60,6 +60,6 @@ static inline int elm_config(struct device *dev, enum bch_ecc bch_type,
{
return -ENOSYS;
}
-#endif /* CONFIG_MTD_NAND_ECC_BCH */
+#endif /* CONFIG_MTD_NAND_OMAP_BCH */
#endif /* __ELM_H */
diff --git a/include/linux/pwm.h b/include/linux/pwm.h
index 08fad7c6a471..5c2e26a354bf 100644
--- a/include/linux/pwm.h
+++ b/include/linux/pwm.h
@@ -638,7 +638,6 @@ static inline void pwm_remove_table(struct pwm_lookup *table, size_t num)
#ifdef CONFIG_PWM_SYSFS
void pwmchip_sysfs_export(struct pwm_chip *chip);
void pwmchip_sysfs_unexport(struct pwm_chip *chip);
-void pwmchip_sysfs_unexport_children(struct pwm_chip *chip);
#else
static inline void pwmchip_sysfs_export(struct pwm_chip *chip)
{
@@ -647,10 +646,6 @@ static inline void pwmchip_sysfs_export(struct pwm_chip *chip)
static inline void pwmchip_sysfs_unexport(struct pwm_chip *chip)
{
}
-
-static inline void pwmchip_sysfs_unexport_children(struct pwm_chip *chip)
-{
-}
#endif /* CONFIG_PWM_SYSFS */
#endif /* __LINUX_PWM_H */
diff --git a/include/linux/usb.h b/include/linux/usb.h
index 8040c99058ea..b5e49dff3a94 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -199,7 +199,6 @@ usb_find_last_int_out_endpoint(struct usb_host_interface *alt,
* @dev: driver model's view of this device
* @usb_dev: if an interface is bound to the USB major, this will point
* to the sysfs representation for that device.
- * @pm_usage_cnt: PM usage counter for this interface
* @reset_ws: Used for scheduling resets from atomic context.
* @resetting_device: USB core reset the device, so use alt setting 0 as
* current; needs bandwidth alloc after reset.
@@ -256,7 +255,7 @@ struct usb_interface {
struct device dev; /* interface specific device info */
struct device *usb_dev;
- atomic_t pm_usage_cnt; /* usage counter for autosuspend */
+ atomic_t pm_usage_cnt; /* XXX placeholder only for kABI */
struct work_struct reset_ws; /* for resets in atomic context */
void *suse_kabi_padding;
};
diff --git a/include/linux/virtio_ring.h b/include/linux/virtio_ring.h
index 270cfa81830e..d502e15e4e8e 100644
--- a/include/linux/virtio_ring.h
+++ b/include/linux/virtio_ring.h
@@ -62,7 +62,7 @@ struct virtqueue;
/*
* Creates a virtqueue and allocates the descriptor ring. If
* may_reduce_num is set, then this may allocate a smaller ring than
- * expected. The caller should query virtqueue_get_ring_size to learn
+ * expected. The caller should query virtqueue_get_vring_size to learn
* the actual size of the ring.
*/
struct virtqueue *vring_create_virtqueue(unsigned int index,
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 95ccc1eef558..c9a60089b7e5 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -178,6 +178,9 @@ struct adv_info {
#define HCI_MAX_SHORT_NAME_LENGTH 10
+/* Min encryption key size to match with SMP */
+#define HCI_MIN_ENC_KEY_SIZE 7
+
/* Default LE RPA expiry time, 15 minutes */
#define HCI_DEFAULT_RPA_TIMEOUT (15 * 60)
diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h
index 9c2be3992a77..64524a0affcb 100644
--- a/include/net/sctp/sctp.h
+++ b/include/net/sctp/sctp.h
@@ -444,7 +444,8 @@ static inline int sctp_frag_point(const struct sctp_association *asoc, int pmtu)
if (asoc->user_frag)
frag = min_t(int, frag, asoc->user_frag);
- frag = SCTP_TRUNC4(min_t(int, frag, SCTP_MAX_CHUNK_LEN));
+ frag = SCTP_TRUNC4(min_t(int, frag, SCTP_MAX_CHUNK_LEN -
+ sizeof(struct sctp_data_chunk)));
return frag;
}
diff --git a/include/net/smc.h b/include/net/smc.h
index b65fa27a39fe..58acbf7bf7a1 100644
--- a/include/net/smc.h
+++ b/include/net/smc.h
@@ -73,6 +73,9 @@ struct smcd_dev {
struct list_head vlan;
struct workqueue_struct *event_wq;
u8 pnetid[SMC_MAX_PNETID_LEN];
+#ifndef __GENKSYMS__
+ bool pnetid_by_user;
+#endif
};
struct smcd_dev *smcd_alloc_dev(struct device *parent, const char *name,
diff --git a/include/sound/core.h b/include/sound/core.h
index f7d8c10c4c45..9c2e4b514c64 100644
--- a/include/sound/core.h
+++ b/include/sound/core.h
@@ -241,7 +241,6 @@ int copy_from_user_toio(volatile void __iomem *dst, const void __user *src, size
/* init.c */
-extern struct snd_card *snd_cards[SNDRV_CARDS];
int snd_card_locked(int card);
#if defined(CONFIG_SND_MIXER_OSS) || defined(CONFIG_SND_MIXER_OSS_MODULE)
#define SND_MIXER_OSS_NOTIFY_REGISTER 0
@@ -265,7 +264,20 @@ int snd_card_add_dev_attr(struct snd_card *card,
int snd_component_add(struct snd_card *card, const char *component);
int snd_card_file_add(struct snd_card *card, struct file *file);
int snd_card_file_remove(struct snd_card *card, struct file *file);
-#define snd_card_unref(card) put_device(&(card)->card_dev)
+
+struct snd_card *snd_card_ref(int card);
+
+/**
+ * snd_card_unref - Unreference the card object
+ * @card: the card object to unreference
+ *
+ * Call this function for the card object that was obtained via snd_card_ref()
+ * or snd_lookup_minor_data().
+ */
+static inline void snd_card_unref(struct snd_card *card)
+{
+ put_device(&card->card_dev);
+}
#define snd_card_set_dev(card, devptr) ((card)->dev = (devptr))
diff --git a/include/sound/seq_kernel.h b/include/sound/seq_kernel.h
index 4b9ee3009aa0..e43d04a1d663 100644
--- a/include/sound/seq_kernel.h
+++ b/include/sound/seq_kernel.h
@@ -73,7 +73,10 @@ __printf(3, 4)
int snd_seq_create_kernel_client(struct snd_card *card, int client_index,
const char *name_fmt, ...);
int snd_seq_delete_kernel_client(int client);
-int snd_seq_kernel_client_enqueue(int client, struct snd_seq_event *ev, int atomic, int hop);
+/* XXX kABI compatibility for SLE15 XXX */
+#define snd_seq_kernel_client_enqueue __snd_seq_kernel_client_enqueue
+int snd_seq_kernel_client_enqueue(int client, struct snd_seq_event *ev,
+ struct file *file, bool blocking);
int snd_seq_kernel_client_dispatch(int client, struct snd_seq_event *ev, int atomic, int hop);
int snd_seq_kernel_client_ctl(int client, unsigned int cmd, void *arg);
diff --git a/include/trace/events/bcache.h b/include/trace/events/bcache.h
index daf749138ff8..d39d83630b7c 100644
--- a/include/trace/events/bcache.h
+++ b/include/trace/events/bcache.h
@@ -220,9 +220,30 @@ DEFINE_EVENT(cache_set, bcache_journal_entry_full,
TP_ARGS(c)
);
-DEFINE_EVENT(bcache_bio, bcache_journal_write,
- TP_PROTO(struct bio *bio),
- TP_ARGS(bio)
+TRACE_EVENT(bcache_journal_write,
+ TP_PROTO(struct bio *bio, u32 keys),
+ TP_ARGS(bio, keys),
+
+ TP_STRUCT__entry(
+ __field(dev_t, dev )
+ __field(sector_t, sector )
+ __field(unsigned int, nr_sector )
+ __array(char, rwbs, 6 )
+ __field(u32, nr_keys )
+ ),
+
+ TP_fast_assign(
+ __entry->dev = bio_dev(bio);
+ __entry->sector = bio->bi_iter.bi_sector;
+ __entry->nr_sector = bio->bi_iter.bi_size >> 9;
+ __entry->nr_keys = keys;
+ blk_fill_rwbs(__entry->rwbs, bio->bi_opf, bio->bi_iter.bi_size);
+ ),
+
+ TP_printk("%d,%d %s %llu + %u keys %u",
+ MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs,
+ (unsigned long long)__entry->sector, __entry->nr_sector,
+ __entry->nr_keys)
);
/* Btree */
diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h
index aad5303e8d58..1387a243794d 100644
--- a/include/trace/events/btrfs.h
+++ b/include/trace/events/btrfs.h
@@ -797,11 +797,10 @@ DEFINE_EVENT(btrfs_delayed_data_ref, run_delayed_data_ref,
DECLARE_EVENT_CLASS(btrfs_delayed_ref_head,
TP_PROTO(const struct btrfs_fs_info *fs_info,
- const struct btrfs_delayed_ref_node *ref,
const struct btrfs_delayed_ref_head *head_ref,
int action),
- TP_ARGS(fs_info, ref, head_ref, action),
+ TP_ARGS(fs_info, head_ref, action),
TP_STRUCT__entry_btrfs(
__field( u64, bytenr )
@@ -811,8 +810,8 @@ DECLARE_EVENT_CLASS(btrfs_delayed_ref_head,
),
TP_fast_assign_btrfs(fs_info,
- __entry->bytenr = ref->bytenr;
- __entry->num_bytes = ref->num_bytes;
+ __entry->bytenr = head_ref->bytenr;
+ __entry->num_bytes = head_ref->num_bytes;
__entry->action = action;
__entry->is_data = head_ref->is_data;
),
@@ -827,21 +826,19 @@ DECLARE_EVENT_CLASS(btrfs_delayed_ref_head,
DEFINE_EVENT(btrfs_delayed_ref_head, add_delayed_ref_head,
TP_PROTO(const struct btrfs_fs_info *fs_info,
- const struct btrfs_delayed_ref_node *ref,
const struct btrfs_delayed_ref_head *head_ref,
int action),
- TP_ARGS(fs_info, ref, head_ref, action)
+ TP_ARGS(fs_info, head_ref, action)
);
DEFINE_EVENT(btrfs_delayed_ref_head, run_delayed_ref_head,
TP_PROTO(const struct btrfs_fs_info *fs_info,
- const struct btrfs_delayed_ref_node *ref,
const struct btrfs_delayed_ref_head *head_ref,
int action),
- TP_ARGS(fs_info, ref, head_ref, action)
+ TP_ARGS(fs_info, head_ref, action)
);
#define show_chunk_type(type) \
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index 316d2f3596a1..34d2b08233eb 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -900,7 +900,7 @@ struct drm_i915_gem_execbuffer2 {
* struct drm_i915_gem_exec_fence *fences.
*/
__u64 cliprects_ptr;
-#define I915_EXEC_RING_MASK (7<<0)
+#define I915_EXEC_RING_MASK (0x3f)
#define I915_EXEC_DEFAULT (0<<0)
#define I915_EXEC_RENDER (1<<0)
#define I915_EXEC_BSD (2<<0)
diff --git a/include/uapi/linux/bcache.h b/include/uapi/linux/bcache.h
index 3b92610502ca..630a0dbeb871 100644
--- a/include/uapi/linux/bcache.h
+++ b/include/uapi/linux/bcache.h
@@ -29,10 +29,10 @@ struct bkey {
BITMASK(name, struct bkey, field, offset, size)
#define PTR_FIELD(name, offset, size) \
-static inline __u64 name(const struct bkey *k, unsigned i) \
+static inline __u64 name(const struct bkey *k, unsigned int i) \
{ return (k->ptr[i] >> offset) & ~(~0ULL << size); } \
\
-static inline void SET_##name(struct bkey *k, unsigned i, __u64 v) \
+static inline void SET_##name(struct bkey *k, unsigned int i, __u64 v) \
{ \
k->ptr[i] &= ~(~(~0ULL << size) << offset); \
k->ptr[i] |= (v & ~(~0ULL << size)) << offset; \
@@ -116,12 +116,14 @@ static inline void bkey_copy_key(struct bkey *dest, const struct bkey *src)
static inline struct bkey *bkey_next(const struct bkey *k)
{
__u64 *d = (void *) k;
+
return (struct bkey *) (d + bkey_u64s(k));
}
-static inline struct bkey *bkey_idx(const struct bkey *k, unsigned nr_keys)
+static inline struct bkey *bkey_idx(const struct bkey *k, unsigned int nr_keys)
{
__u64 *d = (void *) k;
+
return (struct bkey *) (d + nr_keys);
}
/* Enough for a key with 6 pointers */
@@ -194,7 +196,7 @@ struct cache_sb {
};
};
- __u32 last_mount; /* time_t */
+ __u32 last_mount; /* time overflow in y2106 */
__u16 first_bucket;
union {
@@ -317,7 +319,7 @@ struct uuid_entry {
struct {
__u8 uuid[16];
__u8 label[32];
- __u32 first_reg;
+ __u32 first_reg; /* time overflow in y2106 */
__u32 last_reg;
__u32 invalidated;
diff --git a/include/uapi/linux/input-event-codes.h b/include/uapi/linux/input-event-codes.h
index 81a22886f289..5baa87b4d4fc 100644
--- a/include/uapi/linux/input-event-codes.h
+++ b/include/uapi/linux/input-event-codes.h
@@ -600,6 +600,7 @@
#define KEY_APPSELECT 0x244 /* AL Select Task/Application */
#define KEY_SCREENSAVER 0x245 /* AL Screen Saver */
#define KEY_VOICECOMMAND 0x246 /* Listening Voice Command */
+#define KEY_ASSISTANT 0x247 /* AL Context-aware desktop assistant */
#define KEY_BRIGHTNESS_MIN 0x250 /* Set Brightness to Minimum */
#define KEY_BRIGHTNESS_MAX 0x251 /* Set Brightness to Maximum */
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 1fa1b805085c..560ea327330c 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -876,6 +876,13 @@ static inline void audit_proctitle_free(struct audit_context *context)
context->proctitle.len = 0;
}
+static inline void audit_free_module(struct audit_context *context)
+{
+ if (context->type == AUDIT_KERN_MODULE) {
+ kfree(context->module.name);
+ context->module.name = NULL;
+ }
+}
static inline void audit_free_names(struct audit_context *context)
{
struct audit_names *n, *next;
@@ -959,6 +966,7 @@ int audit_alloc(struct task_struct *tsk)
static inline void audit_free_context(struct audit_context *context)
{
+ audit_free_module(context);
audit_free_names(context);
unroll_tree_refs(context, NULL, 0);
free_tree_refs(context);
@@ -1275,7 +1283,6 @@ static void show_special(struct audit_context *context, int *call_panic)
audit_log_format(ab, "name=");
if (context->module.name) {
audit_log_untrustedstring(ab, context->module.name);
- kfree(context->module.name);
} else
audit_log_format(ab, "(null)");
@@ -1579,6 +1586,7 @@ void __audit_syscall_exit(int success, long return_code)
if (!list_empty(&context->killed_trees))
audit_kill_trees(&context->killed_trees);
+ audit_free_module(context);
audit_free_names(context);
unroll_tree_refs(context, NULL, 0);
audit_free_aux(context);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 6cc40261f75e..1304fcedb01f 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -125,6 +125,7 @@ static int zero;
static int __maybe_unused one = 1;
static int __maybe_unused two = 2;
static int __maybe_unused four = 4;
+static unsigned long zero_ul;
static unsigned long one_ul = 1;
static unsigned long long_max = LONG_MAX;
static int one_hundred = 100;
@@ -1733,7 +1734,7 @@ static struct ctl_table fs_table[] = {
.maxlen = sizeof(files_stat.max_files),
.mode = 0644,
.proc_handler = proc_doulongvec_minmax,
- .extra1 = &zero,
+ .extra1 = &zero_ul,
.extra2 = &long_max,
},
{
@@ -2608,7 +2609,16 @@ static int do_proc_dointvec_minmax_conv(bool *negp, unsigned long *lvalp,
{
struct do_proc_dointvec_minmax_conv_param *param = data;
if (write) {
- int val = *negp ? -*lvalp : *lvalp;
+ int val;
+ if (*negp) {
+ if (*lvalp > (unsigned long) INT_MAX + 1)
+ return -EINVAL;
+ val = -*lvalp;
+ } else {
+ if (*lvalp > (unsigned long) INT_MAX)
+ return -EINVAL;
+ val = *lvalp;
+ }
if ((param->min && *param->min > val) ||
(param->max && *param->max < val))
return -EINVAL;
@@ -2786,6 +2796,8 @@ static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table, int
bool neg;
left -= proc_skip_spaces(&p);
+ if (!left)
+ break;
err = proc_get_long(&p, &left, &val, &neg,
proc_wspace_sep,
diff --git a/lib/.gitignore b/lib/.gitignore
index 09aae85418ab..f2a39c9e5485 100644
--- a/lib/.gitignore
+++ b/lib/.gitignore
@@ -2,5 +2,7 @@
# Generated files
#
gen_crc32table
+gen_crc64table
crc32table.h
+crc64table.h
oid_registry_data.c
diff --git a/lib/Kconfig b/lib/Kconfig
index ca2e9c8b42df..29852cae19b2 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -158,6 +158,14 @@ config CRC32_BIT
endchoice
+config CRC64
+ tristate "CRC64 functions"
+ help
+ This option is provided for the case where no in-kernel-tree
+ modules require CRC64 functions, but a module built outside
+ the kernel tree does. Such modules that use library CRC64
+ functions require M here.
+
config CRC7
tristate "CRC7 functions"
help
diff --git a/lib/Makefile b/lib/Makefile
index 9fa048880d86..d7fa13803d44 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -101,6 +101,7 @@ obj-$(CONFIG_CRC16) += crc16.o
obj-$(CONFIG_CRC_T10DIF)+= crc-t10dif.o
obj-$(CONFIG_CRC_ITU_T) += crc-itu-t.o
obj-$(CONFIG_CRC32) += crc32.o
+obj-$(CONFIG_CRC64) += crc64.o
obj-$(CONFIG_CRC32_SELFTEST) += crc32test.o
obj-$(CONFIG_CRC7) += crc7.o
obj-$(CONFIG_LIBCRC32C) += libcrc32c.o
@@ -212,7 +213,9 @@ obj-$(CONFIG_FONT_SUPPORT) += fonts/
obj-$(CONFIG_PRIME_NUMBERS) += prime_numbers.o
hostprogs-y := gen_crc32table
+hostprogs-y += gen_crc64table
clean-files := crc32table.h
+clean-files += crc64table.h
$(obj)/crc32.o: $(obj)/crc32table.h
@@ -222,6 +225,14 @@ quiet_cmd_crc32 = GEN $@
$(obj)/crc32table.h: $(obj)/gen_crc32table
$(call cmd,crc32)
+$(obj)/crc64.o: $(obj)/crc64table.h
+
+quiet_cmd_crc64 = GEN $@
+ cmd_crc64 = $< > $@
+
+$(obj)/crc64table.h: $(obj)/gen_crc64table
+ $(call cmd,crc64)
+
#
# Build a fast OID lookip registry from include/linux/oid_registry.h
#
diff --git a/lib/crc64.c b/lib/crc64.c
new file mode 100644
index 000000000000..0ef8ae6ac047
--- /dev/null
+++ b/lib/crc64.c
@@ -0,0 +1,56 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Normal 64-bit CRC calculation.
+ *
+ * This is a basic crc64 implementation following ECMA-182 specification,
+ * which can be found from,
+ * http://www.ecma-international.org/publications/standards/Ecma-182.htm
+ *
+ * Dr. Ross N. Williams has a great document to introduce the idea of CRC
+ * algorithm, here the CRC64 code is also inspired by the table-driven
+ * algorithm and detail example from this paper. This paper can be found
+ * from,
+ * http://www.ross.net/crc/download/crc_v3.txt
+ *
+ * crc64table[256] is the lookup table of a table-driven 64-bit CRC
+ * calculation, which is generated by gen_crc64table.c in kernel build
+ * time. The polynomial of crc64 arithmetic is from ECMA-182 specification
+ * as well, which is defined as,
+ *
+ * x^64 + x^62 + x^57 + x^55 + x^54 + x^53 + x^52 + x^47 + x^46 + x^45 +
+ * x^40 + x^39 + x^38 + x^37 + x^35 + x^33 + x^32 + x^31 + x^29 + x^27 +
+ * x^24 + x^23 + x^22 + x^21 + x^19 + x^17 + x^13 + x^12 + x^10 + x^9 +
+ * x^7 + x^4 + x + 1
+ *
+ * Copyright 2018 SUSE Linux.
+ * Author: Coly Li <colyli@suse.de>
+ */
+
+#include <linux/module.h>
+#include <linux/types.h>
+#include "crc64table.h"
+
+MODULE_DESCRIPTION("CRC64 calculations");
+MODULE_LICENSE("GPL v2");
+
+/**
+ * crc64_be - Calculate bitwise big-endian ECMA-182 CRC64
+ * @crc: seed value for computation. 0 or (u64)~0 for a new CRC calculation,
+ or the previous crc64 value if computing incrementally.
+ * @p: pointer to buffer over which CRC64 is run
+ * @len: length of buffer @p
+ */
+u64 __pure crc64_be(u64 crc, const void *p, size_t len)
+{
+ size_t i, t;
+
+ const unsigned char *_p = p;
+
+ for (i = 0; i < len; i++) {
+ t = ((crc >> 56) ^ (*_p++)) & 0xFF;
+ crc = crc64table[t] ^ (crc << 8);
+ }
+
+ return crc;
+}
+EXPORT_SYMBOL_GPL(crc64_be);
diff --git a/lib/gen_crc64table.c b/lib/gen_crc64table.c
new file mode 100644
index 000000000000..094b43aef8db
--- /dev/null
+++ b/lib/gen_crc64table.c
@@ -0,0 +1,66 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Generate lookup table for the table-driven CRC64 calculation.
+ *
+ * gen_crc64table is executed in kernel build time and generates
+ * lib/crc64table.h. This header is included by lib/crc64.c for
+ * the table-driven CRC64 calculation.
+ *
+ * See lib/crc64.c for more information about which specification
+ * and polynomial arithmetic that gen_crc64table.c follows to
+ * generate the lookup table.
+ *
+ * Copyright 2018 SUSE Linux.
+ * Author: Coly Li <colyli@suse.de>
+ */
+#include <inttypes.h>
+#include <stdio.h>
+
+#define CRC64_ECMA182_POLY 0x42F0E1EBA9EA3693ULL
+
+static uint64_t crc64_table[256] = {0};
+
+static void generate_crc64_table(void)
+{
+ uint64_t i, j, c, crc;
+
+ for (i = 0; i < 256; i++) {
+ crc = 0;
+ c = i << 56;
+
+ for (j = 0; j < 8; j++) {
+ if ((crc ^ c) & 0x8000000000000000ULL)
+ crc = (crc << 1) ^ CRC64_ECMA182_POLY;
+ else
+ crc <<= 1;
+ c <<= 1;
+ }
+
+ crc64_table[i] = crc;
+ }
+}
+
+static void print_crc64_table(void)
+{
+ int i;
+
+ printf("/* this file is generated - do not edit */\n\n");
+ printf("#include <linux/types.h>\n");
+ printf("#include <linux/cache.h>\n\n");
+ printf("static const u64 ____cacheline_aligned crc64table[256] = {\n");
+ for (i = 0; i < 256; i++) {
+ printf("\t0x%016" PRIx64 "ULL", crc64_table[i]);
+ if (i & 0x1)
+ printf(",\n");
+ else
+ printf(", ");
+ }
+ printf("};\n");
+}
+
+int main(int argc, char *argv[])
+{
+ generate_crc64_table();
+ print_crc64_table();
+ return 0;
+}
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index dc59eae54717..c02864a9ef24 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -1152,6 +1152,14 @@ int hci_conn_check_link_mode(struct hci_conn *conn)
!test_bit(HCI_CONN_ENCRYPT, &conn->flags))
return 0;
+ /* The minimum encryption key size needs to be enforced by the
+ * host stack before establishing any L2CAP connections. The
+ * specification in theory allows a minimum of 1, but to align
+ * BR/EDR and LE transports, a minimum of 7 is chosen.
+ */
+ if (conn->enc_key_size < HCI_MIN_ENC_KEY_SIZE)
+ return 0;
+
return 1;
}
diff --git a/net/bluetooth/hidp/sock.c b/net/bluetooth/hidp/sock.c
index 008ba439bd62..cc80c76177b6 100644
--- a/net/bluetooth/hidp/sock.c
+++ b/net/bluetooth/hidp/sock.c
@@ -76,6 +76,7 @@ static int hidp_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long
sockfd_put(csock);
return err;
}
+ ca.name[sizeof(ca.name)-1] = 0;
err = hidp_connection_add(&ca, csock, isock);
if (!err && copy_to_user(argp, &ca, sizeof(ca)))
diff --git a/net/bridge/netfilter/ebt_among.c b/net/bridge/netfilter/ebt_among.c
index 279527f8b1fe..0b589a6b365c 100644
--- a/net/bridge/netfilter/ebt_among.c
+++ b/net/bridge/netfilter/ebt_among.c
@@ -172,18 +172,69 @@ ebt_among_mt(const struct sk_buff *skb, struct xt_action_param *par)
return true;
}
+static bool poolsize_invalid(const struct ebt_mac_wormhash *w)
+{
+ return w && w->poolsize >= (INT_MAX / sizeof(struct ebt_mac_wormhash_tuple));
+}
+
+static bool wormhash_offset_invalid(int off, unsigned int len)
+{
+ if (off == 0) /* not present */
+ return false;
+
+ if (off < (int)sizeof(struct ebt_among_info) ||
+ off % __alignof__(struct ebt_mac_wormhash))
+ return true;
+
+ off += sizeof(struct ebt_mac_wormhash);
+
+ return off > len;
+}
+
+static bool wormhash_sizes_valid(const struct ebt_mac_wormhash *wh, int a, int b)
+{
+ if (a == 0)
+ a = sizeof(struct ebt_among_info);
+
+ return ebt_mac_wormhash_size(wh) + a == b;
+}
+
static int ebt_among_mt_check(const struct xt_mtchk_param *par)
{
const struct ebt_among_info *info = par->matchinfo;
const struct ebt_entry_match *em =
container_of(par->matchinfo, const struct ebt_entry_match, data);
- int expected_length = sizeof(struct ebt_among_info);
+ unsigned int expected_length = sizeof(struct ebt_among_info);
const struct ebt_mac_wormhash *wh_dst, *wh_src;
int err;
+ if (expected_length > em->match_size)
+ return -EINVAL;
+
+ if (wormhash_offset_invalid(info->wh_dst_ofs, em->match_size) ||
+ wormhash_offset_invalid(info->wh_src_ofs, em->match_size))
+ return -EINVAL;
+
wh_dst = ebt_among_wh_dst(info);
- wh_src = ebt_among_wh_src(info);
+ if (poolsize_invalid(wh_dst))
+ return -EINVAL;
+
expected_length += ebt_mac_wormhash_size(wh_dst);
+ if (expected_length > em->match_size)
+ return -EINVAL;
+
+ wh_src = ebt_among_wh_src(info);
+ if (poolsize_invalid(wh_src))
+ return -EINVAL;
+
+ if (info->wh_src_ofs < info->wh_dst_ofs) {
+ if (!wormhash_sizes_valid(wh_src, info->wh_src_ofs, info->wh_dst_ofs))
+ return -EINVAL;
+ } else {
+ if (!wormhash_sizes_valid(wh_dst, info->wh_dst_ofs, info->wh_src_ofs))
+ return -EINVAL;
+ }
+
expected_length += ebt_mac_wormhash_size(wh_src);
if (em->match_size != EBT_ALIGN(expected_length)) {
diff --git a/net/core/dev.c b/net/core/dev.c
index 1d6586d5c722..a726f4ee9346 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2820,7 +2820,7 @@ struct sk_buff *__skb_gso_segment(struct sk_buff *skb,
segs = skb_mac_gso_segment(skb, features);
- if (unlikely(skb_needs_check(skb, tx_path)))
+ if (unlikely(skb_needs_check(skb, tx_path) && !IS_ERR(segs)))
skb_warn_bad_offload(skb);
return segs;
diff --git a/net/dsa/legacy.c b/net/dsa/legacy.c
index 7281098df04e..957510550b1e 100644
--- a/net/dsa/legacy.c
+++ b/net/dsa/legacy.c
@@ -277,10 +277,6 @@ static void dsa_switch_destroy(struct dsa_switch *ds)
if (!(dsa_is_cpu_port(ds, port) || dsa_is_dsa_port(ds, port)))
continue;
dsa_cpu_dsa_destroy(&ds->ports[port]);
-
- /* Clearing a bit which is not set does no harm */
- ds->cpu_port_mask |= ~(1 << port);
- ds->dsa_port_mask |= ~(1 << port);
}
if (ds->slave_mii_bus && ds->ops->phy_read)
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 2f42cc256a6c..965ab000be62 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -949,6 +949,7 @@ static int esp_init_state(struct xfrm_state *x)
switch (encap->encap_type) {
default:
+ err = -EINVAL;
goto error;
case UDP_ENCAP_ESPINUDP:
x->props.header_len += sizeof(struct udphdr);
diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
index 20146bc5a3f5..dce49dfe54f4 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
@@ -166,8 +166,20 @@ static unsigned int ipv4_conntrack_local(void *priv,
ip_hdrlen(skb) < sizeof(struct iphdr))
return NF_ACCEPT;
- if (ip_is_fragment(ip_hdr(skb))) /* IP_NODEFRAG setsockopt set */
+ if (ip_is_fragment(ip_hdr(skb))) { /* IP_NODEFRAG setsockopt set */
+ enum ip_conntrack_info ctinfo;
+ struct nf_conn *tmpl;
+
+ tmpl = nf_ct_get(skb, &ctinfo);
+ if (tmpl && nf_ct_is_template(tmpl)) {
+ /* when skipping ct, clear templates to avoid fooling
+ * later targets/matches
+ */
+ skb->_nfct = 0;
+ nf_ct_put(tmpl);
+ }
return NF_ACCEPT;
+ }
return nf_conntrack_in(state->net, PF_INET, state->hook, skb);
}
diff --git a/net/ipv4/netfilter/nf_socket_ipv4.c b/net/ipv4/netfilter/nf_socket_ipv4.c
index e9293bdebba0..4824b1e183a1 100644
--- a/net/ipv4/netfilter/nf_socket_ipv4.c
+++ b/net/ipv4/netfilter/nf_socket_ipv4.c
@@ -108,10 +108,12 @@ struct sock *nf_sk_lookup_slow_v4(struct net *net, const struct sk_buff *skb,
int doff = 0;
if (iph->protocol == IPPROTO_UDP || iph->protocol == IPPROTO_TCP) {
- struct udphdr _hdr, *hp;
+ struct tcphdr _hdr;
+ struct udphdr *hp;
hp = skb_header_pointer(skb, ip_hdrlen(skb),
- sizeof(_hdr), &_hdr);
+ iph->protocol == IPPROTO_UDP ?
+ sizeof(*hp) : sizeof(_hdr), &_hdr);
if (hp == NULL)
return NULL;
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index 3e4d442222f9..8cd8c2e0f853 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -866,13 +866,12 @@ static int esp6_init_state(struct xfrm_state *x)
x->props.header_len += IPV4_BEET_PHMAXLEN +
(sizeof(struct ipv6hdr) - sizeof(struct iphdr));
break;
+ default:
case XFRM_MODE_TRANSPORT:
break;
case XFRM_MODE_TUNNEL:
x->props.header_len += sizeof(struct ipv6hdr);
break;
- default:
- goto error;
}
align = ALIGN(crypto_aead_blocksize(aead), 4);
diff --git a/net/ipv6/netfilter/nf_socket_ipv6.c b/net/ipv6/netfilter/nf_socket_ipv6.c
index ebb2bf84232a..f14de4b6d639 100644
--- a/net/ipv6/netfilter/nf_socket_ipv6.c
+++ b/net/ipv6/netfilter/nf_socket_ipv6.c
@@ -116,9 +116,11 @@ struct sock *nf_sk_lookup_slow_v6(struct net *net, const struct sk_buff *skb,
}
if (tproto == IPPROTO_UDP || tproto == IPPROTO_TCP) {
- struct udphdr _hdr, *hp;
+ struct tcphdr _hdr;
+ struct udphdr *hp;
- hp = skb_header_pointer(skb, thoff, sizeof(_hdr), &_hdr);
+ hp = skb_header_pointer(skb, thoff, tproto == IPPROTO_UDP ?
+ sizeof(*hp) : sizeof(_hdr), &_hdr);
if (hp == NULL)
return NULL;
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index 568a638d7eec..5ded7a3feaa8 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -948,6 +948,12 @@ static int __ovs_ct_lookup(struct net *net, struct sw_flow_key *key,
GFP_ATOMIC);
if (err)
return err;
+
+ /* helper installed, add seqadj if NAT is required */
+ if (info->nat && !nfct_seqadj(ct)) {
+ if (!nfct_seqadj_ext_add(ct))
+ return -EINVAL;
+ }
}
/* Call the helper only if:
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 6f908fd41bbd..c1bf67024dee 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -1967,14 +1967,14 @@ static struct nlattr *reserve_sfa_size(struct sw_flow_actions **sfa,
struct sw_flow_actions *acts;
int new_acts_size;
- int req_size = NLA_ALIGN(attr_len);
+ size_t req_size = NLA_ALIGN(attr_len);
int next_offset = offsetof(struct sw_flow_actions, actions) +
(